From 2543a87108d2af7d48a43b3d6685c2b1ea279e36 Mon Sep 17 00:00:00 2001 From: Amerigo Wang Date: Wed, 6 Apr 2011 10:43:11 +0200 Subject: workqueue: remove cancel_rearming_delayed_work[queue]() cancel_rearming_delayed_work() and cancel_rearming_delayed_workqueue() can be removed now. Signed-off-by: WANG Cong Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index f584aba78ca9..57b31b3d83bd 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -412,21 +412,6 @@ static inline bool __cancel_delayed_work(struct delayed_work *work) return ret; } -/* Obsolete. use cancel_delayed_work_sync() */ -static inline __deprecated -void cancel_rearming_delayed_workqueue(struct workqueue_struct *wq, - struct delayed_work *work) -{ - cancel_delayed_work_sync(work); -} - -/* Obsolete. use cancel_delayed_work_sync() */ -static inline __deprecated -void cancel_rearming_delayed_work(struct delayed_work *work) -{ - cancel_delayed_work_sync(work); -} - #ifndef CONFIG_SMP static inline long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg) { -- cgit v1.2.3 From 9c5a2ba70251ecaab18c7a83e38b3c620223476c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 5 Apr 2011 18:01:44 +0200 Subject: workqueue: separate out drain_workqueue() from destroy_workqueue() There are users which want to drain workqueues without destroying it. Separate out drain functionality from destroy_workqueue() into drain_workqueue() and make it accessible to workqueue users. To guarantee forward-progress, only chain queueing is allowed while drain is in progress. If a new work item which isn't chained from the running or pending work items is queued while draining is in progress, WARN_ON_ONCE() is triggered. Signed-off-by: Tejun Heo Cc: James Bottomley --- include/linux/workqueue.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 57b31b3d83bd..2be2887c6958 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -255,7 +255,7 @@ enum { WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */ - WQ_DYING = 1 << 6, /* internal: workqueue is dying */ + WQ_DRAINING = 1 << 6, /* internal: workqueue is draining */ WQ_RESCUER = 1 << 7, /* internal: workqueue has rescuer */ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ @@ -355,6 +355,7 @@ extern int queue_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *work, unsigned long delay); extern void flush_workqueue(struct workqueue_struct *wq); +extern void drain_workqueue(struct workqueue_struct *wq); extern void flush_scheduled_work(void); extern int schedule_work(struct work_struct *work); -- cgit v1.2.3 From 988acec9ee9d8b38ca0d1187d904cb53588e8c64 Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Wed, 25 May 2011 15:12:20 +0300 Subject: hwrng: fix spelling mistake in header comment Cc: Herbert Xu Cc: Matt Mackall Signed-off-by: Sasha Levin Signed-off-by: Jiri Kosina --- include/linux/hw_random.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hw_random.h b/include/linux/hw_random.h index 9bede7633f74..b4b0eef5fddf 100644 --- a/include/linux/hw_random.h +++ b/include/linux/hw_random.h @@ -25,7 +25,7 @@ * there is always data available. *OBSOLETE* * @data_read: Read data from the RNG device. * Returns the number of lower random bytes in "data". - * Must not be NULL. *OSOLETE* + * Must not be NULL. *OBSOLETE* * @read: New API. drivers can fill up to max bytes of data * into the buffer. The buffer is aligned for any type. * @priv: Private data, for use by the RNG driver. -- cgit v1.2.3 From a1b383870a28cfbd1657d4922c0fafc634a62ebd Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Mon, 30 May 2011 11:14:13 -0600 Subject: virtio: add full three-clause BSD text to headers. It's unclear to me if it's important, but it's obviously causing my technical colleages some headaches and I'd hate such imprecision to slow virtio adoption. I've emailed this to all non-trivial contributors for approval, too. Signed-off-by: Rusty Russell Acked-by: Grant Likely Acked-by: Ryan Harper Acked-by: Anthony Liguori Acked-by: Eric Van Hensbergen Acked-by: john cooper Acked-by: Aneesh Kumar K.V Acked-by: Christian Borntraeger Acked-by: Fernando Luis Vazquez Cao --- include/linux/virtio_9p.h | 25 ++++++++++++++++++++++++- include/linux/virtio_balloon.h | 25 ++++++++++++++++++++++++- include/linux/virtio_blk.h | 25 ++++++++++++++++++++++++- include/linux/virtio_config.h | 25 ++++++++++++++++++++++++- include/linux/virtio_console.h | 26 +++++++++++++++++++++++++- include/linux/virtio_ids.h | 24 +++++++++++++++++++++++- include/linux/virtio_net.h | 25 ++++++++++++++++++++++++- include/linux/virtio_pci.h | 23 +++++++++++++++++++++++ include/linux/virtio_ring.h | 23 +++++++++++++++++++++++ 9 files changed, 214 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_9p.h b/include/linux/virtio_9p.h index e68b439b2860..277c4ad44e84 100644 --- a/include/linux/virtio_9p.h +++ b/include/linux/virtio_9p.h @@ -1,7 +1,30 @@ #ifndef _LINUX_VIRTIO_9P_H #define _LINUX_VIRTIO_9P_H /* This header is BSD licensed so anyone can use the definitions to implement - * compatible drivers/servers. */ + * compatible drivers/servers. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of IBM nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. */ #include #include #include diff --git a/include/linux/virtio_balloon.h b/include/linux/virtio_balloon.h index a50ecd1b81a2..652dc8bea921 100644 --- a/include/linux/virtio_balloon.h +++ b/include/linux/virtio_balloon.h @@ -1,7 +1,30 @@ #ifndef _LINUX_VIRTIO_BALLOON_H #define _LINUX_VIRTIO_BALLOON_H /* This header is BSD licensed so anyone can use the definitions to implement - * compatible drivers/servers. */ + * compatible drivers/servers. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of IBM nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. */ #include #include diff --git a/include/linux/virtio_blk.h b/include/linux/virtio_blk.h index 167720d695ed..e0edb40ca7aa 100644 --- a/include/linux/virtio_blk.h +++ b/include/linux/virtio_blk.h @@ -1,7 +1,30 @@ #ifndef _LINUX_VIRTIO_BLK_H #define _LINUX_VIRTIO_BLK_H /* This header is BSD licensed so anyone can use the definitions to implement - * compatible drivers/servers. */ + * compatible drivers/servers. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of IBM nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. */ #include #include #include diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 800617b4ddd5..39c88c5ad19d 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -1,7 +1,30 @@ #ifndef _LINUX_VIRTIO_CONFIG_H #define _LINUX_VIRTIO_CONFIG_H /* This header, excluding the #ifdef __KERNEL__ part, is BSD licensed so - * anyone can use the definitions to implement compatible drivers/servers. */ + * anyone can use the definitions to implement compatible drivers/servers. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of IBM nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. */ /* Virtio devices use a standardized configuration space to define their * features and pass configuration information, but each implementation can diff --git a/include/linux/virtio_console.h b/include/linux/virtio_console.h index e4d333543a33..bdf4b0034739 100644 --- a/include/linux/virtio_console.h +++ b/include/linux/virtio_console.h @@ -5,7 +5,31 @@ #include /* * This header, excluding the #ifdef __KERNEL__ part, is BSD licensed so - * anyone can use the definitions to implement compatible drivers/servers. + * anyone can use the definitions to implement compatible drivers/servers: + * + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of IBM nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. * * Copyright (C) Red Hat, Inc., 2009, 2010, 2011 * Copyright (C) Amit Shah , 2009, 2010, 2011 diff --git a/include/linux/virtio_ids.h b/include/linux/virtio_ids.h index 06660c0a78d7..85bb0bb66ffc 100644 --- a/include/linux/virtio_ids.h +++ b/include/linux/virtio_ids.h @@ -5,7 +5,29 @@ * * This header is BSD licensed so anyone can use the definitions to implement * compatible drivers/servers. - */ + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of IBM nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. */ #define VIRTIO_ID_NET 1 /* virtio net */ #define VIRTIO_ID_BLOCK 2 /* virtio block */ diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 085e42298ce5..136040bba3e3 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -1,7 +1,30 @@ #ifndef _LINUX_VIRTIO_NET_H #define _LINUX_VIRTIO_NET_H /* This header is BSD licensed so anyone can use the definitions to implement - * compatible drivers/servers. */ + * compatible drivers/servers. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of IBM nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. */ #include #include #include diff --git a/include/linux/virtio_pci.h b/include/linux/virtio_pci.h index 9a3d7c48c622..ea66f3f60d63 100644 --- a/include/linux/virtio_pci.h +++ b/include/linux/virtio_pci.h @@ -11,6 +11,29 @@ * * This header is BSD licensed so anyone can use the definitions to implement * compatible drivers/servers. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of IBM nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. */ #ifndef _LINUX_VIRTIO_PCI_H diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index e4d144b132b5..a813e5d460eb 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -7,6 +7,29 @@ * This header is BSD licensed so anyone can use the definitions to implement * compatible drivers/servers. * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of IBM nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + * * Copyright Rusty Russell IBM Corporation 2007. */ #include -- cgit v1.2.3 From 770b31a85e000b0194974922f238a30ade4246b6 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 20 May 2011 02:10:17 +0300 Subject: virtio: event index interface Define a new feature bit for the guest and host to utilize an event index (like Xen) instead if a flag bit to enable/disable interrupts and kicks. Signed-off-by: Michael S. Tsirkin Signed-off-by: Rusty Russell --- include/linux/virtio_ring.h | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index a813e5d460eb..c4eef73deb3f 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -52,6 +52,12 @@ /* We support indirect buffer descriptors */ #define VIRTIO_RING_F_INDIRECT_DESC 28 +/* The Guest publishes the used index for which it expects an interrupt + * at the end of the avail ring. Host should ignore the avail->flags field. */ +/* The Host publishes the avail index for which it expects a kick + * at the end of the used ring. Guest should ignore the used->flags field. */ +#define VIRTIO_RING_F_EVENT_IDX 29 + /* Virtio ring descriptors: 16 bytes. These can chain together via "next". */ struct vring_desc { /* Address (guest-physical). */ @@ -106,6 +112,7 @@ struct vring { * __u16 avail_flags; * __u16 avail_idx; * __u16 available[num]; + * __u16 used_event_idx; * * // Padding to the next align boundary. * char pad[]; @@ -114,8 +121,14 @@ struct vring { * __u16 used_flags; * __u16 used_idx; * struct vring_used_elem used[num]; + * __u16 avail_event_idx; * }; */ +/* We publish the used event index at the end of the available ring, and vice + * versa. They are at the end for backwards compatibility. */ +#define vring_used_event(vr) ((vr)->avail->ring[(vr)->num]) +#define vring_avail_event(vr) (*(__u16 *)&(vr)->used->ring[(vr)->num]) + static inline void vring_init(struct vring *vr, unsigned int num, void *p, unsigned long align) { @@ -130,7 +143,7 @@ static inline unsigned vring_size(unsigned int num, unsigned long align) { return ((sizeof(struct vring_desc) * num + sizeof(__u16) * (2 + num) + align - 1) & ~(align - 1)) - + sizeof(__u16) * 2 + sizeof(struct vring_used_elem) * num; + + sizeof(__u16) * 3 + sizeof(struct vring_used_elem) * num; } #ifdef __KERNEL__ -- cgit v1.2.3 From bf7035bf20563a6cadcb9e870406e7b21daf5e30 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 20 May 2011 02:10:27 +0300 Subject: virtio ring: inline function to check for events With the new used_event and avail_event and features, both host and guest need similar logic to check whether events are enabled, so it helps to put the common code in the header. Note that Xen has similar logic for notification hold-off in include/xen/interface/io/ring.h with req_event and req_prod corresponding to event_idx + 1 and new_idx respectively. +1 comes from the fact that req_event and req_prod in Xen start at 1, while event index in virtio starts at 0. Signed-off-by: Michael S. Tsirkin Signed-off-by: Rusty Russell --- include/linux/virtio_ring.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index c4eef73deb3f..4a32cb6da425 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -146,6 +146,20 @@ static inline unsigned vring_size(unsigned int num, unsigned long align) + sizeof(__u16) * 3 + sizeof(struct vring_used_elem) * num; } +/* The following is used with USED_EVENT_IDX and AVAIL_EVENT_IDX */ +/* Assuming a given event_idx value from the other size, if + * we have just incremented index from old to new_idx, + * should we trigger an event? */ +static inline int vring_need_event(__u16 event_idx, __u16 new_idx, __u16 old) +{ + /* Note: Xen has similar logic for notification hold-off + * in include/xen/interface/io/ring.h with req_event and req_prod + * corresponding to event_idx + 1 and new_idx respectively. + * Note also that req_event and req_prod in Xen start at 1, + * event indexes in virtio start at 0. */ + return (__u16)(new_idx - event_idx - 1) < (__u16)(new_idx - old); +} + #ifdef __KERNEL__ #include struct virtio_device; -- cgit v1.2.3 From 7ab358c23cbf15cea08129cd722d1ce77433a94d Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 20 May 2011 02:11:14 +0300 Subject: virtio: add api for delayed callbacks Add an API that tells the other side that callbacks should be delayed until a lot of work has been done. Implement using the new event_idx feature. Note: it might seem advantageous to let the drivers ask for a callback after a specific capacity has been reached. However, as a single head can free many entries in the descriptor table, we don't really have a clue about capacity until get_buf is called. The API is the simplest to implement at the moment, we'll see what kind of hints drivers can pass when there's more than one user of the feature. Signed-off-by: Michael S. Tsirkin Signed-off-by: Rusty Russell --- include/linux/virtio.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index aff5b4f74041..710885749605 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -51,6 +51,13 @@ struct virtqueue { * This re-enables callbacks; it returns "false" if there are pending * buffers in the queue, to detect a possible race between the driver * checking for more work, and enabling callbacks. + * virtqueue_enable_cb_delayed: restart callbacks after disable_cb. + * vq: the struct virtqueue we're talking about. + * This re-enables callbacks but hints to the other side to delay + * interrupts until most of the available buffers have been processed; + * it returns "false" if there are many pending buffers in the queue, + * to detect a possible race between the driver checking for more work, + * and enabling callbacks. * virtqueue_detach_unused_buf: detach first unused buffer * vq: the struct virtqueue we're talking about. * Returns NULL or the "data" token handed to add_buf @@ -86,6 +93,8 @@ void virtqueue_disable_cb(struct virtqueue *vq); bool virtqueue_enable_cb(struct virtqueue *vq); +bool virtqueue_enable_cb_delayed(struct virtqueue *vq); + void *virtqueue_detach_unused_buf(struct virtqueue *vq); /** -- cgit v1.2.3 From a1706ac4c0201ea0143dc0db0659001b26ceeabb Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 30 May 2011 07:42:51 +0200 Subject: Revert "block: Remove extra discard_alignment from hd_struct." It was not a good idea to start dereferencing disk->queue from the fs sysfs strategy for displaying discard alignment. We ran into first a NULL pointer deref, and after fixing that we sometimes see unvalid disk->queue pointer values. Since discard is the only one of the bunch actually looking into the queue, just revert the change. This reverts commit 23ceb5b7719e9276d4fa72a3ecf94dd396755276. Conflicts: fs/partitions/check.c --- include/linux/genhd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index b78956b3c2e7..300d7582006e 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -100,6 +100,7 @@ struct hd_struct { sector_t start_sect; sector_t nr_sects; sector_t alignment_offset; + unsigned int discard_alignment; struct device __dev; struct kobject *holder_dir; int policy, partno; -- cgit v1.2.3 From f21e0e81d81b649ad309cedc7226f1bed72982e0 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 24 May 2011 08:12:40 +0800 Subject: regulator: Do bulk enables of regulators in parallel In order to reduce the impact of ramp times rather than enabling the regulators for a device in series use async tasks to run the actual enables. This means that the delays which the enables implement can all run in parallel, though it does mean that the order in which the supplies come on may be unstable. For super bonus fun points if any of the regulators are shared between multiple supplies on the same device (as is rather likely) then this will test our locking. Note that in this case we only delay once for each physical regulator so the threads shouldn't block each other while delaying. It'd be even nicer if we could coalesce writes to a shared enable registers in PMICs but that's definitely future work, and it may also be useful and is certainly more achievable to optimise out the parallelism if none of the regulators implement ramp delays. Signed-off-by: Mark Brown Signed-off-by: Liam Girdwood --- include/linux/regulator/consumer.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 9e87c1cb7270..26f6ea4444e3 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -122,6 +122,9 @@ struct regulator; struct regulator_bulk_data { const char *supply; struct regulator *consumer; + + /* Internal use */ + int ret; }; #if defined(CONFIG_REGULATOR) -- cgit v1.2.3 From ea9d6553b3b3044e7374774cc33bb1b2eee19dd3 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 31 May 2011 13:45:53 +0200 Subject: block: remove unwanted semicolons Since those defined functions require additional semicolon from the caller, they could cause potential syntax errors when used in if-else statements. Signed-off-by: Namhyung Kim Acked-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ae9091a68480..1a23722e8878 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1282,8 +1282,8 @@ queue_max_integrity_segments(struct request_queue *q) #define blk_get_integrity(a) (0) #define blk_integrity_compare(a, b) (0) #define blk_integrity_register(a, b) (0) -#define blk_integrity_unregister(a) do { } while (0); -#define blk_queue_max_integrity_segments(a, b) do { } while (0); +#define blk_integrity_unregister(a) do { } while (0) +#define blk_queue_max_integrity_segments(a, b) do { } while (0) #define queue_max_integrity_segments(a) (0) #define blk_integrity_merge_rq(a, b, c) (0) #define blk_integrity_merge_bio(a, b, c) (0) -- cgit v1.2.3 From f339b9dc1f03591761d5d930800db24bc0eda1e1 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 31 May 2011 10:49:20 +0200 Subject: sched: Fix schedstat.nr_wakeups_migrate While looking over the code I found that with the ttwu rework the nr_wakeups_migrate test broke since we now switch cpus prior to calling ttwu_stat(), hence the test is always true. Cure this by passing the migration state in wake_flags. Also move the whole test under CONFIG_SMP, its hard to migrate tasks on UP :-) Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-pwwxl7gdqs5676f1d4cx6pj7@git.kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 8da84b7bc1b8..483c1ed5bc4d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1063,6 +1063,7 @@ struct sched_domain; */ #define WF_SYNC 0x01 /* waker goes to sleep after wakup */ #define WF_FORK 0x02 /* child wakeup after fork */ +#define WF_MIGRATED 0x04 /* internal use, task got migrated */ #define ENQUEUE_WAKEUP 1 #define ENQUEUE_HEAD 2 -- cgit v1.2.3 From 63da029015b5255915cd6d61f19ffc276ad4635d Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 23 May 2011 11:37:09 -0700 Subject: mtd: fix physmap.h warnings Fix build warnings in physmap.h: include/linux/mtd/physmap.h:25: warning: 'struct platform_device' declared inside parameter list include/linux/mtd/physmap.h:25: warning: its scope is only this definition or declaration, which is probably not what you want include/linux/mtd/physmap.h:26: warning: 'struct platform_device' declared inside parameter list include/linux/mtd/physmap.h:27: warning: 'struct platform_device' declared inside parameter list Signed-off-by: Randy Dunlap Signed-off-by: David Woodhouse --- include/linux/mtd/physmap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/physmap.h b/include/linux/mtd/physmap.h index d40bfa1d9c91..e5f21d293c70 100644 --- a/include/linux/mtd/physmap.h +++ b/include/linux/mtd/physmap.h @@ -19,6 +19,7 @@ #include struct map_info; +struct platform_device; struct physmap_flash_data { unsigned int width; -- cgit v1.2.3 From 6dd9a7c73761a8a5f5475d5cfdc15368a0f4c06d Mon Sep 17 00:00:00 2001 From: Youquan Song Date: Wed, 25 May 2011 19:13:49 +0100 Subject: intel-iommu: Enable super page (2MiB, 1GiB, etc.) support There are no externally-visible changes with this. In the loop in the internal __domain_mapping() function, we simply detect if we are mapping: - size >= 2MiB, and - virtual address aligned to 2MiB, and - physical address aligned to 2MiB, and - on hardware that supports superpages. (and likewise for larger superpages). We automatically use a superpage for such mappings. We never have to worry about *breaking* superpages, since we trust that we will always *unmap* the same range that was mapped. So all we need to do is ensure that dma_pte_clear_range() will also cope with superpages. Adjust pfn_to_dma_pte() to take a superpage 'level' as an argument, so it can return a PTE at the appropriate level rather than always extending the page tables all the way down to level 1. Again, this is simplified by the fact that we should never encounter existing small pages when we're creating a mapping; any old mapping that used the same virtual range will have been entirely removed and its obsolete page tables freed. Provide an 'intel_iommu=sp_off' argument on the command line as a chicken bit. Not that it should ever be required. == The original commit seen in the iommu-2.6.git was Youquan's implementation (and completion) of my own half-baked code which I'd typed into an email. Followed by half a dozen subsequent 'fixes'. I've taken the unusual step of rewriting history and collapsing the original commits in order to keep the main history simpler, and make life easier for the people who are going to have to backport this to older kernels. And also so I can give it a more coherent commit comment which (hopefully) gives a better explanation of what's going on. The original sequence of commits leading to identical code was: Youquan Song (3): intel-iommu: super page support intel-iommu: Fix superpage alignment calculation error intel-iommu: Fix superpage level calculation error in dma_pfn_level_pte() David Woodhouse (4): intel-iommu: Precalculate superpage support for dmar_domain intel-iommu: Fix hardware_largepage_caps() intel-iommu: Fix inappropriate use of superpages in __domain_mapping() intel-iommu: Fix phys_pfn in __domain_mapping for sglist pages Signed-off-by: Youquan Song Signed-off-by: David Woodhouse --- include/linux/dma_remapping.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma_remapping.h b/include/linux/dma_remapping.h index 5619f8522738..bbd8661b3473 100644 --- a/include/linux/dma_remapping.h +++ b/include/linux/dma_remapping.h @@ -9,8 +9,12 @@ #define VTD_PAGE_MASK (((u64)-1) << VTD_PAGE_SHIFT) #define VTD_PAGE_ALIGN(addr) (((addr) + VTD_PAGE_SIZE - 1) & VTD_PAGE_MASK) +#define VTD_STRIDE_SHIFT (9) +#define VTD_STRIDE_MASK (((u64)-1) << VTD_STRIDE_SHIFT) + #define DMA_PTE_READ (1) #define DMA_PTE_WRITE (2) +#define DMA_PTE_LARGE_PAGE (1 << 7) #define DMA_PTE_SNP (1 << 11) #define CONTEXT_TT_MULTI_LEVEL 0 -- cgit v1.2.3 From 333ba7325213f0a09dfa5ceeddb056d6ad74b3b5 Mon Sep 17 00:00:00 2001 From: Eliad Peller Date: Sun, 29 May 2011 15:53:20 +0300 Subject: cfg80211: don't drop p2p probe responses Commit 0a35d36 ("cfg80211: Use capability info to detect mesh beacons") assumed that probe response with both ESS and IBSS bits cleared means that the frame was sent by a mesh sta. However, these capabilities are also being used in the p2p_find phase, and the mesh-validation broke it. Rename the WLAN_CAPABILITY_IS_MBSS macro, and verify that mesh ies exist before assuming this frame was sent by a mesh sta. Signed-off-by: Eliad Peller Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index b2eee5879883..bf56b6f78270 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1003,8 +1003,12 @@ struct ieee80211_ht_info { #define WLAN_CAPABILITY_ESS (1<<0) #define WLAN_CAPABILITY_IBSS (1<<1) -/* A mesh STA sets the ESS and IBSS capability bits to zero */ -#define WLAN_CAPABILITY_IS_MBSS(cap) \ +/* + * A mesh STA sets the ESS and IBSS capability bits to zero. + * however, this holds true for p2p probe responses (in the p2p_find + * phase) as well. + */ +#define WLAN_CAPABILITY_IS_STA_BSS(cap) \ (!((cap) & (WLAN_CAPABILITY_ESS | WLAN_CAPABILITY_IBSS))) #define WLAN_CAPABILITY_CF_POLLABLE (1<<2) -- cgit v1.2.3 From 1bdcd095e39a789135f8638a2ff76f74e3071d46 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Wed, 18 May 2011 11:40:22 +0200 Subject: bcma: add IRQ number and pointer to DMA dev MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Rafał Miłecki Signed-off-by: John W. Linville --- include/linux/bcma/bcma.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index 08763e4e848f..8b0cef9fd692 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -117,6 +117,8 @@ struct bcma_device { struct bcma_device_id id; struct device dev; + struct device *dma_dev; + unsigned int irq; bool dev_registered; u8 core_index; -- cgit v1.2.3 From 9d75ef0f8f6d2e31ed940b3057a42a25f07076fb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Fri, 20 May 2011 03:27:06 +0200 Subject: bcma: host pci: implement block R/W operations MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Rafał Miłecki Signed-off-by: John W. Linville --- include/linux/bcma/bcma.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index 8b0cef9fd692..27a27a79bea3 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -31,6 +31,12 @@ struct bcma_host_ops { void (*write8)(struct bcma_device *core, u16 offset, u8 value); void (*write16)(struct bcma_device *core, u16 offset, u16 value); void (*write32)(struct bcma_device *core, u16 offset, u32 value); +#ifdef CONFIG_BCMA_BLOCKIO + void (*block_read)(struct bcma_device *core, void *buffer, + size_t count, u16 offset, u8 reg_width); + void (*block_write)(struct bcma_device *core, const void *buffer, + size_t count, u16 offset, u8 reg_width); +#endif /* Agent ops */ u32 (*aread32)(struct bcma_device *core, u16 offset); void (*awrite32)(struct bcma_device *core, u16 offset, u32 value); @@ -210,6 +216,18 @@ void bcma_write32(struct bcma_device *core, u16 offset, u32 value) { core->bus->ops->write32(core, offset, value); } +#ifdef CONFIG_BCMA_BLOCKIO +extern inline void bcma_block_read(struct bcma_device *core, void *buffer, + size_t count, u16 offset, u8 reg_width) +{ + core->bus->ops->block_read(core, buffer, count, offset, reg_width); +} +extern inline void bcma_block_write(struct bcma_device *core, const void *buffer, + size_t count, u16 offset, u8 reg_width) +{ + core->bus->ops->block_write(core, buffer, count, offset, reg_width); +} +#endif extern inline u32 bcma_aread32(struct bcma_device *core, u16 offset) { return core->bus->ops->aread32(core, offset); -- cgit v1.2.3 From a3bcc23e890a6d49d6763d9eb073d711de2e0469 Mon Sep 17 00:00:00 2001 From: Ben Greear Date: Wed, 1 Jun 2011 06:49:10 +0000 Subject: af-packet: Add flag to distinguish VID 0 from no-vlan. Currently, user-space cannot determine if a 0 tcp_vlan_tci means there is no VLAN tag or the VLAN ID was zero. Add flag to make this explicit. User-space can check for TP_STATUS_VLAN_VALID || tp_vlan_tci > 0, which will be backwards compatible. Older could would have just checked for tp_vlan_tci, so it will work no worse than before. Signed-off-by: Ben Greear Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/if_packet.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/if_packet.h b/include/linux/if_packet.h index 72bfa5a034dd..6d66ce1791a9 100644 --- a/include/linux/if_packet.h +++ b/include/linux/if_packet.h @@ -70,6 +70,7 @@ struct tpacket_auxdata { #define TP_STATUS_COPY 0x2 #define TP_STATUS_LOSING 0x4 #define TP_STATUS_CSUMNOTREADY 0x8 +#define TP_STATUS_VLAN_VALID 0x10 /* auxdata has valid tp_vlan_tci */ /* Tx ring - header status */ #define TP_STATUS_AVAILABLE 0x0 -- cgit v1.2.3 From 796d5116c407690b14fd5bda136aa67a39e7061a Mon Sep 17 00:00:00 2001 From: Jeff Moyer Date: Thu, 2 Jun 2011 21:19:05 +0200 Subject: iosched: prevent aliased requests from starving other I/O Hi, Jens, If you recall, I posted an RFC patch for this back in July of last year: http://lkml.org/lkml/2010/7/13/279 The basic problem is that a process can issue a never-ending stream of async direct I/Os to the same sector on a device, thus starving out other I/O in the system (due to the way the alias handling works in both cfq and deadline). The solution I proposed back then was to start dispatching from the fifo after a certain number of aliases had been dispatched. Vivek asked why we had to treat aliases differently at all, and I never had a good answer. So, I put together a simple patch which allows aliases to be added to the rb tree (it adds them to the right, though that doesn't matter as the order isn't guaranteed anyway). I think this is the preferred solution, as it doesn't break up time slices in CFQ or batches in deadline. I've tested it, and it does solve the starvation issue. Let me know what you think. Cheers, Jeff Signed-off-by: Jeff Moyer Signed-off-by: Jens Axboe --- include/linux/elevator.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 21a8ebf2dc3a..d800d5142184 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -146,7 +146,7 @@ extern struct request *elv_rb_latter_request(struct request_queue *, struct requ /* * rb support functions. */ -extern struct request *elv_rb_add(struct rb_root *, struct request *); +extern void elv_rb_add(struct rb_root *, struct request *); extern void elv_rb_del(struct rb_root *, struct request *); extern struct request *elv_rb_find(struct rb_root *, sector_t); -- cgit v1.2.3 From 3a43e05f4d0600e906fa09f4a65d749288c44592 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 31 May 2011 08:56:11 +0200 Subject: irq: Handle spurios irq detection for threaded irqs The detection of spurios interrupts is currently limited to first level handler. In force-threaded mode we never notice if the threaded irq does not feel responsible. This patch catches the return value of the threaded handler and forwards it to the spurious detector. If the primary handler returns only IRQ_WAKE_THREAD then the spourious detector ignores it because it gets called again from the threaded handler. [ tglx: Report the erroneous return value early and bail out ] Signed-off-by: Sebastian Andrzej Siewior Link: http://lkml.kernel.org/r/1306824972-27067-2-git-send-email-sebastian@breakpoint.cc Signed-off-by: Thomas Gleixner --- include/linux/irqreturn.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqreturn.h b/include/linux/irqreturn.h index 819acaaac3f5..714ba08dc092 100644 --- a/include/linux/irqreturn.h +++ b/include/linux/irqreturn.h @@ -8,9 +8,9 @@ * @IRQ_WAKE_THREAD handler requests to wake the handler thread */ enum irqreturn { - IRQ_NONE, - IRQ_HANDLED, - IRQ_WAKE_THREAD, + IRQ_NONE = (0 << 0), + IRQ_HANDLED = (1 << 0), + IRQ_WAKE_THREAD = (1 << 1), }; typedef enum irqreturn irqreturn_t; -- cgit v1.2.3 From d4d84fef6d0366b585b7de13527a0faeca84d9ce Mon Sep 17 00:00:00 2001 From: Chris Metcalf Date: Thu, 2 Jun 2011 10:19:41 -0400 Subject: slub: always align cpu_slab to honor cmpxchg_double requirement On an architecture without CMPXCHG_LOCAL but with DEBUG_VM enabled, the VM_BUG_ON() in __pcpu_double_call_return_bool() will cause an early panic during boot unless we always align cpu_slab properly. In principle we could remove the alignment-testing VM_BUG_ON() for architectures that don't have CMPXCHG_LOCAL, but leaving it in means that new code will tend not to break x86 even if it is introduced on another platform, and it's low cost to require alignment. Acked-by: David Rientjes Acked-by: Christoph Lameter Signed-off-by: Chris Metcalf Signed-off-by: Pekka Enberg --- include/linux/percpu.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 8b97308e65df..9ca008f0c542 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -259,6 +259,9 @@ extern void __bad_size_call_parameter(void); * Special handling for cmpxchg_double. cmpxchg_double is passed two * percpu variables. The first has to be aligned to a double word * boundary and the second has to follow directly thereafter. + * We enforce this on all architectures even if they don't support + * a double cmpxchg instruction, since it's a cheap requirement, and it + * avoids breaking the requirement for architectures with the instruction. */ #define __pcpu_double_call_return_bool(stem, pcp1, pcp2, ...) \ ({ \ -- cgit v1.2.3 From a3cc68c37897f0656489a0d853d6e342fc6f076b Mon Sep 17 00:00:00 2001 From: H Hartley Sweeten Date: Fri, 27 May 2011 16:35:59 -0700 Subject: gpio/74x164: remove unnecessary defines and prototype Remove the #define GEN_74X164_GPIO_COUNT since it's only used in one place and it's meaning is obvious. Also remove the #define GEN_74X164_DRIVER_NAME and use spi->modalias to set the gpio chip's label and the string "74x164" for the driver name. Reorder the code slightly to remove the need to prototype gen_74x164_set_value. Signed-off-by: H Hartley Sweeten Signed-off-by: Grant Likely --- include/linux/spi/74x164.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/74x164.h b/include/linux/spi/74x164.h index d85c52f294a0..0aa6acc73317 100644 --- a/include/linux/spi/74x164.h +++ b/include/linux/spi/74x164.h @@ -1,8 +1,6 @@ #ifndef LINUX_SPI_74X164_H #define LINUX_SPI_74X164_H -#define GEN_74X164_DRIVER_NAME "74x164" - struct gen_74x164_chip_platform_data { /* number assigned to the first GPIO */ unsigned base; -- cgit v1.2.3 From 7150962d637cf38617924f7f72ea00612283eb89 Mon Sep 17 00:00:00 2001 From: Arend van Spriel Date: Tue, 31 May 2011 11:22:15 +0200 Subject: lib: crc8: add new library module providing crc8 algorithm The brcm80211 driver in staging tree uses a crc8 function. Based on feedback from John Linville to move this to lib directory, the linux source has been searched. Although there is currently only one other kernel driver using this algorithm (ie. drivers/ssb) we are providing this as a library function for others to use. Cc: linux-kernel@vger.kernel.org Cc: linux-wireless@vger.kernel.org Cc: Dan Carpenter Cc: George Spelvin Cc: Randy Dunlap Reviewed-by: Henry Ptasinski Reviewed-by: Roland Vossen Reviewed-by: "Franky (Zhenhui) Lin" Signed-off-by: Arend van Spriel Signed-off-by: John W. Linville --- include/linux/crc8.h | 101 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 101 insertions(+) create mode 100644 include/linux/crc8.h (limited to 'include/linux') diff --git a/include/linux/crc8.h b/include/linux/crc8.h new file mode 100644 index 000000000000..13c8dabb0441 --- /dev/null +++ b/include/linux/crc8.h @@ -0,0 +1,101 @@ +/* + * Copyright (c) 2011 Broadcom Corporation + * + * Permission to use, copy, modify, and/or distribute this software for any + * purpose with or without fee is hereby granted, provided that the above + * copyright notice and this permission notice appear in all copies. + * + * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES + * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY + * SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES + * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION + * OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN + * CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + */ +#ifndef __CRC8_H_ +#define __CRC8_H_ + +#include + +/* see usage of this value in crc8() description */ +#define CRC8_INIT_VALUE 0xFF + +/* + * Return value of crc8() indicating valid message+crc. This is true + * if a CRC is inverted before transmission. The CRC computed over the + * whole received bitstream is _table[x], where x is the bit pattern + * of the modification (almost always 0xff). + */ +#define CRC8_GOOD_VALUE(_table) (_table[0xFF]) + +/* required table size for crc8 algorithm */ +#define CRC8_TABLE_SIZE 256 + +/* helper macro assuring right table size is used */ +#define DECLARE_CRC8_TABLE(_table) \ + static u8 _table[CRC8_TABLE_SIZE] + +/** + * crc8_populate_lsb - fill crc table for given polynomial in regular bit order. + * + * @table: table to be filled. + * @polynomial: polynomial for which table is to be filled. + * + * This function fills the provided table according the polynomial provided for + * regular bit order (lsb first). Polynomials in CRC algorithms are typically + * represented as shown below. + * + * poly = x^8 + x^7 + x^6 + x^4 + x^2 + 1 + * + * For lsb first direction x^7 maps to the lsb. So the polynomial is as below. + * + * - lsb first: poly = 10101011(1) = 0xAB + */ +void crc8_populate_lsb(u8 table[CRC8_TABLE_SIZE], u8 polynomial); + +/** + * crc8_populate_msb - fill crc table for given polynomial in reverse bit order. + * + * @table: table to be filled. + * @polynomial: polynomial for which table is to be filled. + * + * This function fills the provided table according the polynomial provided for + * reverse bit order (msb first). Polynomials in CRC algorithms are typically + * represented as shown below. + * + * poly = x^8 + x^7 + x^6 + x^4 + x^2 + 1 + * + * For msb first direction x^7 maps to the msb. So the polynomial is as below. + * + * - msb first: poly = (1)11010101 = 0xD5 + */ +void crc8_populate_msb(u8 table[CRC8_TABLE_SIZE], u8 polynomial); + +/** + * crc8() - calculate a crc8 over the given input data. + * + * @table: crc table used for calculation. + * @pdata: pointer to data buffer. + * @nbytes: number of bytes in data buffer. + * @crc: previous returned crc8 value. + * + * The CRC8 is calculated using the polynomial given in crc8_populate_msb() + * or crc8_populate_lsb(). + * + * The caller provides the initial value (either %CRC8_INIT_VALUE + * or the previous returned value) to allow for processing of + * discontiguous blocks of data. When generating the CRC the + * caller is responsible for complementing the final return value + * and inserting it into the byte stream. When validating a byte + * stream (including CRC8), a final return value of %CRC8_GOOD_VALUE + * indicates the byte stream data can be considered valid. + * + * Reference: + * "A Painless Guide to CRC Error Detection Algorithms", ver 3, Aug 1993 + * Williams, Ross N., rossross.net + * (see URL http://www.ross.net/crc/download/crc_v3.txt). + */ +u8 crc8(const u8 table[CRC8_TABLE_SIZE], u8 *pdata, size_t nbytes, u8 crc); + +#endif /* __CRC8_H_ */ -- cgit v1.2.3 From 10f8113ecb76eea72f96c7cfb72d7fed7c282565 Mon Sep 17 00:00:00 2001 From: Arend van Spriel Date: Tue, 31 May 2011 11:22:16 +0200 Subject: lib: cordic: add library module providing cordic angle calculation The brcm80211 driver in the staging tree has a cordic function to determine cosine and sine for a given angle. Feedback received from John Linville suggested that these kind of functions should be made available to others as a library function in the kernel tree. The b43 driver also has a cordic angle calculation implemented. Cc: linux-kernel@vger.kernel.org Cc: linux-wireless@vger.kernel.org Cc: "John W. Linville" Cc: Greg Kroah-Hartman Cc: Dan Carpenter Cc: Randy Dunlap Cc: Larry Finger Reviewed-by: Roland Vossen Reviewed-by: Henry Ptasinski Reviewed-by: Franky (Zhenhui) Lin Signed-off-by: Arend van Spriel Signed-off-by: John W. Linville --- include/linux/cordic.h | 48 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) create mode 100644 include/linux/cordic.h (limited to 'include/linux') diff --git a/include/linux/cordic.h b/include/linux/cordic.h new file mode 100644 index 000000000000..f932093e20c2 --- /dev/null +++ b/include/linux/cordic.h @@ -0,0 +1,48 @@ +/* + * Copyright (c) 2011 Broadcom Corporation + * + * Permission to use, copy, modify, and/or distribute this software for any + * purpose with or without fee is hereby granted, provided that the above + * copyright notice and this permission notice appear in all copies. + * + * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES + * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY + * SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES + * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION + * OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN + * CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + */ +#ifndef __CORDIC_H_ +#define __CORDIC_H_ + +#include + +/** + * struct cordic_iq - i/q coordinate. + * + * @i: real part of coordinate (in phase). + * @q: imaginary part of coordinate (quadrature). + */ +struct cordic_iq { + s32 i; + s32 q; +}; + +/** + * cordic_calc_iq() - calculates the i/q coordinate for given angle. + * + * @theta: angle in degrees for which i/q coordinate is to be calculated. + * @coord: function output parameter holding the i/q coordinate. + * + * The function calculates the i/q coordinate for a given angle using + * cordic algorithm. The coordinate consists of a real (i) and an + * imaginary (q) part. The real part is essentially the cosine of the + * angle and the imaginary part is the sine of the angle. The returned + * values are scaled by 2^16 for precision. The range for theta is + * for -180 degrees to +180 degrees. Passed values outside this range are + * converted before doing the actual calculation. + */ +struct cordic_iq cordic_calc_iq(s32 theta); + +#endif /* __CORDIC_H_ */ -- cgit v1.2.3 From 27f18dc2dafe66a93c7101fc94201b8c83903597 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Thu, 2 Jun 2011 02:08:51 +0200 Subject: bcma: read SPROM and extract MAC from it MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In case of BCMA cards SPROM is located in the ChipCommon core, it is not mapped as separated host window. So far we have met only SPROMs rev 8. SPROM layout seems to be the same as for SSB buses, so we decided to share SPROM struct and some defines. For now we extract MAC address only, this can be improved of course. Signed-off-by: Rafał Miłecki Signed-off-by: John W. Linville --- include/linux/bcma/bcma.h | 5 +++++ include/linux/bcma/bcma_driver_chipcommon.h | 1 + 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index 27a27a79bea3..6ff080eac0b2 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -6,6 +6,7 @@ #include #include +#include /* SPROM sharing */ #include "bcma_regs.h" @@ -187,6 +188,10 @@ struct bcma_bus { struct bcma_drv_cc drv_cc; struct bcma_drv_pci drv_pci; + + /* We decided to share SPROM struct with SSB as long as we do not need + * any hacks for BCMA. This simplifies drivers code. */ + struct ssb_sprom sprom; }; extern inline u32 bcma_read8(struct bcma_device *core, u16 offset) diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index 083c3b6cd5ce..9c5b69fc985a 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -244,6 +244,7 @@ #define BCMA_CC_REGCTL_DATA 0x065C #define BCMA_CC_PLLCTL_ADDR 0x0660 #define BCMA_CC_PLLCTL_DATA 0x0664 +#define BCMA_CC_SPROM 0x0830 /* SPROM beginning */ /* Data for the PMU, if available. * Check availability with ((struct bcma_chipcommon)->capabilities & BCMA_CC_CAP_PMU) -- cgit v1.2.3 From 55db4c64eddf37e31279ec15fe90314713bc9cfa Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 4 Jun 2011 06:33:24 +0900 Subject: Revert "tty: make receive_buf() return the amout of bytes received" This reverts commit b1c43f82c5aa265442f82dba31ce985ebb7aa71c. It was broken in so many ways, and results in random odd pty issues. It re-introduced the buggy schedule_work() in flush_to_ldisc() that can cause endless work-loops (see commit a5660b41af6a: "tty: fix endless work loop when the buffer fills up"). It also used an "unsigned int" return value fo the ->receive_buf() function, but then made multiple functions return a negative error code, and didn't actually check for the error in the caller. And it didn't actually work at all. BenH bisected down odd tty behavior to it: "It looks like the patch is causing some major malfunctions of the X server for me, possibly related to PTYs. For example, cat'ing a large file in a gnome terminal hangs the kernel for -minutes- in a loop of what looks like flush_to_ldisc/workqueue code, (some ftrace data in the quoted bits further down). ... Some more data: It -looks- like what happens is that the flush_to_ldisc work queue entry constantly re-queues itself (because the PTY is full ?) and the workqueue thread will basically loop forver calling it without ever scheduling, thus starving the consumer process that could have emptied the PTY." which is pretty much exactly the problem we fixed in a5660b41af6a. Milton Miller pointed out the 'unsigned int' issue. Reported-by: Benjamin Herrenschmidt Reported-by: Milton Miller Cc: Stefan Bigler Cc: Toby Gray Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Alan Cox Signed-off-by: Linus Torvalds --- include/linux/tty_ldisc.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index 5b07792ccb46..ff7dc08696a8 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -76,7 +76,7 @@ * tty device. It is solely the responsibility of the line * discipline to handle poll requests. * - * unsigned int (*receive_buf)(struct tty_struct *, const unsigned char *cp, + * void (*receive_buf)(struct tty_struct *, const unsigned char *cp, * char *fp, int count); * * This function is called by the low-level tty driver to send @@ -84,8 +84,7 @@ * processing. is a pointer to the buffer of input * character received by the device. is a pointer to a * pointer of flag bytes which indicate whether a character was - * received with a parity error, etc. Returns the amount of bytes - * received. + * received with a parity error, etc. * * void (*write_wakeup)(struct tty_struct *); * @@ -141,8 +140,8 @@ struct tty_ldisc_ops { /* * The following routines are called from below. */ - unsigned int (*receive_buf)(struct tty_struct *, - const unsigned char *cp, char *fp, int count); + void (*receive_buf)(struct tty_struct *, const unsigned char *cp, + char *fp, int count); void (*write_wakeup)(struct tty_struct *); void (*dcd_change)(struct tty_struct *, unsigned int, struct pps_event_time *); -- cgit v1.2.3 From 9e1f1de02c2275d7172e18dc4e7c2065777611bf Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 3 Jun 2011 18:24:58 -0400 Subject: more conservative S_NOSEC handling Caching "we have already removed suid/caps" was overenthusiastic as merged. On network filesystems we might have had suid/caps set on another client, silently picked by this client on revalidate, all of that *without* clearing the S_NOSEC flag. AFAICS, the only reasonably sane way to deal with that is * new superblock flag; unless set, S_NOSEC is not going to be set. * local block filesystems set it in their ->mount() (more accurately, mount_bdev() does, so does btrfs ->mount(), users of mount_bdev() other than local block ones clear it) * if any network filesystem (or a cluster one) wants to use S_NOSEC, it'll need to set MS_NOSEC in sb->s_flags *AND* take care to clear S_NOSEC when inode attribute changes are picked from other clients. It's not an earth-shattering hole (anybody that can set suid on another client will almost certainly be able to write to the file before doing that anyway), but it's a bug that needs fixing. Signed-off-by: Al Viro --- include/linux/fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index c55d6b7cd5d6..646a1836152a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -208,6 +208,7 @@ struct inodes_stat_t { #define MS_KERNMOUNT (1<<22) /* this is a kern_mount call */ #define MS_I_VERSION (1<<23) /* Update inode I_version field */ #define MS_STRICTATIME (1<<24) /* Always perform atime updates */ +#define MS_NOSEC (1<<28) #define MS_BORN (1<<29) #define MS_ACTIVE (1<<30) #define MS_NOUSER (1<<31) @@ -2591,7 +2592,7 @@ static inline int is_sxid(mode_t mode) static inline void inode_has_no_xattr(struct inode *inode) { - if (!is_sxid(inode->i_mode)) + if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & MS_NOSEC)) inode->i_flags |= S_NOSEC; } -- cgit v1.2.3 From d7ebe75b065a7c2d58ffc12f9d2e00d5ea4e71eb Mon Sep 17 00:00:00 2001 From: Vince Weaver Date: Fri, 3 Jun 2011 17:59:51 -0400 Subject: perf: Fix comments in include/linux/perf_event.h Fix include/linux/perf_event.h comments to be consistent with the actual #define names. This is trivial, but it can be a bit confusing when first reading through the file. Signed-off-by: Vince Weaver Cc: Peter Zijlstra Cc: paulus@samba.org Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Steven Rostedt Link: http://lkml.kernel.org/r/alpine.DEB.2.00.1106031757090.29381@cl320.eecs.utk.edu Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 3412684ce5d5..e0786e35f247 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -137,14 +137,14 @@ enum perf_event_sample_format { * * struct read_format { * { u64 value; - * { u64 time_enabled; } && PERF_FORMAT_ENABLED - * { u64 time_running; } && PERF_FORMAT_RUNNING + * { u64 time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED + * { u64 time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING * { u64 id; } && PERF_FORMAT_ID * } && !PERF_FORMAT_GROUP * * { u64 nr; - * { u64 time_enabled; } && PERF_FORMAT_ENABLED - * { u64 time_running; } && PERF_FORMAT_RUNNING + * { u64 time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED + * { u64 time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING * { u64 value; * { u64 id; } && PERF_FORMAT_ID * } cntr[nr]; -- cgit v1.2.3 From a8f072c1d624a627b67f2ace2f0c25d856ef4e54 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 2 Jun 2011 11:13:59 +0200 Subject: job control: rename signal->group_stop and flags to jobctl and update them signal->group_stop currently hosts mostly group stop related flags; however, it's gonna be used for wider purposes and the GROUP_STOP_ flag prefix becomes confusing. Rename signal->group_stop to signal->jobctl and rename all GROUP_STOP_* flags to JOBCTL_*. Bit position macros JOBCTL_*_BIT are defined and JOBCTL_* flags are defined in terms of them to allow using bitops later. While at it, reassign JOBCTL_TRAPPING to bit 22 to better accomodate future additions. This doesn't cause any functional change. -v2: JOBCTL_*_BIT macros added as suggested by Linus. Signed-off-by: Tejun Heo Cc: Linus Torvalds Signed-off-by: Oleg Nesterov --- include/linux/sched.h | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 2a8621c4be1e..b0dd064eb4fc 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1282,7 +1282,7 @@ struct task_struct { int exit_state; int exit_code, exit_signal; int pdeath_signal; /* The signal sent when the parent dies */ - unsigned int group_stop; /* GROUP_STOP_*, siglock protected */ + unsigned int jobctl; /* JOBCTL_*, siglock protected */ /* ??? */ unsigned int personality; unsigned did_exec:1; @@ -1803,15 +1803,21 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t * #define used_math() tsk_used_math(current) /* - * task->group_stop flags + * task->jobctl flags */ -#define GROUP_STOP_SIGMASK 0xffff /* signr of the last group stop */ -#define GROUP_STOP_PENDING (1 << 16) /* task should stop for group stop */ -#define GROUP_STOP_CONSUME (1 << 17) /* consume group stop count */ -#define GROUP_STOP_TRAPPING (1 << 18) /* switching from STOPPED to TRACED */ -#define GROUP_STOP_DEQUEUED (1 << 19) /* stop signal dequeued */ +#define JOBCTL_STOP_SIGMASK 0xffff /* signr of the last group stop */ -extern void task_clear_group_stop_pending(struct task_struct *task); +#define JOBCTL_STOP_DEQUEUED_BIT 16 /* stop signal dequeued */ +#define JOBCTL_STOP_PENDING_BIT 17 /* task should stop for group stop */ +#define JOBCTL_STOP_CONSUME_BIT 18 /* consume group stop count */ +#define JOBCTL_TRAPPING_BIT 21 /* switching to TRACED */ + +#define JOBCTL_STOP_DEQUEUED (1 << JOBCTL_STOP_DEQUEUED_BIT) +#define JOBCTL_STOP_PENDING (1 << JOBCTL_STOP_PENDING_BIT) +#define JOBCTL_STOP_CONSUME (1 << JOBCTL_STOP_CONSUME_BIT) +#define JOBCTL_TRAPPING (1 << JOBCTL_TRAPPING_BIT) + +extern void task_clear_jobctl_stop_pending(struct task_struct *task); #ifdef CONFIG_PREEMPT_RCU -- cgit v1.2.3 From 755e276b3326f300585435d2f3876e66e248c476 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 2 Jun 2011 11:13:59 +0200 Subject: ptrace: ptrace_check_attach(): rename @kill to @ignore_state and add comments PTRACE_INTERRUPT is going to be added which should also skip task_is_traced() check in ptrace_check_attach(). Rename @kill to @ignore_state and make it bool. Add function comment while at it. This patch doesn't introduce any behavior difference. Signed-off-by: Tejun Heo Signed-off-by: Oleg Nesterov --- include/linux/ptrace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 9178d5cc0b01..e93ef1a54fc7 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -105,7 +105,7 @@ extern long arch_ptrace(struct task_struct *child, long request, extern int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len); extern int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long dst, int len); extern void ptrace_disable(struct task_struct *); -extern int ptrace_check_attach(struct task_struct *task, int kill); +extern int ptrace_check_attach(struct task_struct *task, bool ignore_state); extern int ptrace_request(struct task_struct *child, long request, unsigned long addr, unsigned long data); extern void ptrace_notify(int exit_code); -- cgit v1.2.3 From 3759a0d94c18764247b66511d1038f2b93aa95de Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 2 Jun 2011 11:14:00 +0200 Subject: job control: introduce JOBCTL_PENDING_MASK and task_clear_jobctl_pending() This patch introduces JOBCTL_PENDING_MASK and replaces task_clear_jobctl_stop_pending() with task_clear_jobctl_pending() which takes an extra @mask argument. JOBCTL_PENDING_MASK is currently equal to JOBCTL_STOP_PENDING but future patches will add more bits. recalc_sigpending_tsk() is updated to use JOBCTL_PENDING_MASK instead. task_clear_jobctl_pending() takes @mask which in subset of JOBCTL_PENDING_MASK and clears the relevant jobctl bits. If JOBCTL_STOP_PENDING is set, other STOP bits are cleared together. All task_clear_jobctl_stop_pending() users are updated to call task_clear_jobctl_pending() with JOBCTL_STOP_PENDING which is functionally identical to task_clear_jobctl_stop_pending(). This patch doesn't cause any functional change. Signed-off-by: Tejun Heo Signed-off-by: Oleg Nesterov --- include/linux/sched.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index b0dd064eb4fc..5a958b17f9fe 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1817,7 +1817,10 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t * #define JOBCTL_STOP_CONSUME (1 << JOBCTL_STOP_CONSUME_BIT) #define JOBCTL_TRAPPING (1 << JOBCTL_TRAPPING_BIT) -extern void task_clear_jobctl_stop_pending(struct task_struct *task); +#define JOBCTL_PENDING_MASK JOBCTL_STOP_PENDING + +extern void task_clear_jobctl_pending(struct task_struct *task, + unsigned int mask); #ifdef CONFIG_PREEMPT_RCU -- cgit v1.2.3 From 7dd3db54e77d21eb95e145f19ba53f68250d0e73 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 2 Jun 2011 11:14:00 +0200 Subject: job control: introduce task_set_jobctl_pending() task->jobctl currently hosts JOBCTL_STOP_PENDING and will host TRAP pending bits too. Setting pending conditions on a dying task may make the task unkillable. Currently, each setting site is responsible for checking for the condition but with to-be-added job control traps this becomes too fragile. This patch adds task_set_jobctl_pending() which should be used when setting task->jobctl bits to schedule a stop or trap. The function performs the followings to ease setting pending bits. * Sanity checks. * If fatal signal is pending or PF_EXITING is set, no bit is set. * STOP_SIGMASK is automatically cleared if new value is being set. do_signal_stop() and ptrace_attach() are updated to use task_set_jobctl_pending() instead of setting STOP_PENDING explicitly. The surrounding structures around setting are changed to fit task_set_jobctl_pending() better but there should be no userland visible behavior difference. Signed-off-by: Tejun Heo Cc: Oleg Nesterov Signed-off-by: Oleg Nesterov --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 5a958b17f9fe..5157bd9eee37 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1819,6 +1819,8 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t * #define JOBCTL_PENDING_MASK JOBCTL_STOP_PENDING +extern bool task_set_jobctl_pending(struct task_struct *task, + unsigned int mask); extern void task_clear_jobctl_pending(struct task_struct *task, unsigned int mask); -- cgit v1.2.3 From dd1d6772692316fe35094085c5e4d9a370ad3462 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 2 Jun 2011 11:14:00 +0200 Subject: signal: remove three noop tracehooks Remove the following three noop tracehooks in signals.c. * tracehook_force_sigpending() * tracehook_get_signal() * tracehook_finish_jctl() The code area is about to be updated and these hooks don't do anything other than obfuscating the logic. Signed-off-by: Tejun Heo Signed-off-by: Oleg Nesterov --- include/linux/tracehook.h | 52 ----------------------------------------------- 1 file changed, 52 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index e95f5236611f..15745cdd32ce 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -425,58 +425,6 @@ static inline int tracehook_consider_fatal_signal(struct task_struct *task, return (task_ptrace(task) & PT_PTRACED) != 0; } -/** - * tracehook_force_sigpending - let tracing force signal_pending(current) on - * - * Called when recomputing our signal_pending() flag. Return nonzero - * to force the signal_pending() flag on, so that tracehook_get_signal() - * will be called before the next return to user mode. - * - * Called with @current->sighand->siglock held. - */ -static inline int tracehook_force_sigpending(void) -{ - return 0; -} - -/** - * tracehook_get_signal - deliver synthetic signal to traced task - * @task: @current - * @regs: task_pt_regs(@current) - * @info: details of synthetic signal - * @return_ka: sigaction for synthetic signal - * - * Return zero to check for a real pending signal normally. - * Return -1 after releasing the siglock to repeat the check. - * Return a signal number to induce an artificial signal delivery, - * setting *@info and *@return_ka to specify its details and behavior. - * - * The @return_ka->sa_handler value controls the disposition of the - * signal, no matter the signal number. For %SIG_DFL, the return value - * is a representative signal to indicate the behavior (e.g. %SIGTERM - * for death, %SIGQUIT for core dump, %SIGSTOP for job control stop, - * %SIGTSTP for stop unless in an orphaned pgrp), but the signal number - * reported will be @info->si_signo instead. - * - * Called with @task->sighand->siglock held, before dequeuing pending signals. - */ -static inline int tracehook_get_signal(struct task_struct *task, - struct pt_regs *regs, - siginfo_t *info, - struct k_sigaction *return_ka) -{ - return 0; -} - -/** - * tracehook_finish_jctl - report about return from job control stop - * - * This is called by do_signal_stop() after wakeup. - */ -static inline void tracehook_finish_jctl(void) -{ -} - #define DEATH_REAP -1 #define DEATH_DELAYED_GROUP_LEADER -2 -- cgit v1.2.3 From fb04883371f2cb7867d24783e7d590036dc9b548 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 19 May 2011 15:44:27 +0200 Subject: netfilter: add more values to enum ip_conntrack_info MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Following error is raised (and other similar ones) : net/ipv4/netfilter/nf_nat_standalone.c: In function ‘nf_nat_fn’: net/ipv4/netfilter/nf_nat_standalone.c:119:2: warning: case value ‘4’ not in enumerated type ‘enum ip_conntrack_info’ gcc barfs on adding two enum values and getting a not enumerated result : case IP_CT_RELATED+IP_CT_IS_REPLY: Add missing enum values Signed-off-by: Eric Dumazet CC: David Miller Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_common.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h index 50cdc2559a5a..0d3dd66322ec 100644 --- a/include/linux/netfilter/nf_conntrack_common.h +++ b/include/linux/netfilter/nf_conntrack_common.h @@ -18,6 +18,9 @@ enum ip_conntrack_info { /* >= this indicates reply direction */ IP_CT_IS_REPLY, + IP_CT_ESTABLISHED_REPLY = IP_CT_ESTABLISHED + IP_CT_IS_REPLY, + IP_CT_RELATED_REPLY = IP_CT_RELATED + IP_CT_IS_REPLY, + IP_CT_NEW_REPLY = IP_CT_NEW + IP_CT_IS_REPLY, /* Number of distinct IP_CT types (no NEW in reply dirn). */ IP_CT_NUMBER = IP_CT_IS_REPLY * 2 - 1 }; -- cgit v1.2.3 From b084f598df36b62dfae83c10ed17f0b66b50f442 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Tue, 31 May 2011 12:24:58 -0400 Subject: nfsd: fix dependency of nfsd on auth_rpcgss Commit b0b0c0a26e84 "nfsd: add proc file listing kernel's gss_krb5 enctypes" added an nunnecessary dependency of nfsd on the auth_rpcgss module. It's a little ad hoc, but since the only piece of information nfsd needs from rpcsec_gss_krb5 is a single static string, one solution is just to share it with an include file. Cc: stable@kernel.org Reported-by: Michael Guntsche Cc: Kevin Coffman Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/gss_krb5_enctypes.h | 4 ++++ 1 file changed, 4 insertions(+) create mode 100644 include/linux/sunrpc/gss_krb5_enctypes.h (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5_enctypes.h b/include/linux/sunrpc/gss_krb5_enctypes.h new file mode 100644 index 000000000000..ec6234eee89c --- /dev/null +++ b/include/linux/sunrpc/gss_krb5_enctypes.h @@ -0,0 +1,4 @@ +/* + * Dumb way to share this static piece of information with nfsd + */ +#define KRB5_SUPPORTED_ENCTYPES "18,17,16,23,3,1,2" -- cgit v1.2.3 From 5f98ecdbcef1920323d8777c0ba55dbd4335d3cf Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Sun, 5 Jun 2011 11:47:29 +0900 Subject: swiotlb: Export swioltb_nr_tbl and utilize it as appropiate. By default the io_tlb_nslabs is set to zero, and gets set to whatever value is passed in via swiotlb_init_with_tbl function. The default value passed in is 64MB. However, if the user provides the 'swiotlb=' the default value is ignored and the value provided by the user is used... Except when the SWIOTLB is used under Xen - there the default value of 64MB is used and the Xen-SWIOTLB has no mechanism to get the 'io_tlb_nslabs' filled out by setup_io_tlb_npages functions. This patch provides a function for the Xen-SWIOTLB to call to see if the io_tlb_nslabs is set and if so use that value. Signed-off-by: FUJITA Tomonori Signed-off-by: Konrad Rzeszutek Wilk --- include/linux/swiotlb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 8c0e349f4a6c..445702c60d04 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -24,6 +24,7 @@ extern int swiotlb_force; extern void swiotlb_init(int verbose); extern void swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose); +extern unsigned long swioltb_nr_tbl(void); /* * Enumeration for sync targets -- cgit v1.2.3 From f7a2d73fe75c71941fb0a6b4d8fe7da8144f2c7b Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Mon, 6 Jun 2011 15:36:24 -0400 Subject: x86, efi: Fix argument types for SetVariable() The spec says this takes uint32 for attributes, not uintn. Signed-off-by: Matthew Garrett Link: http://lkml.kernel.org/r/1307388985-7852-1-git-send-email-mjg@redhat.com Signed-off-by: H. Peter Anvin --- include/linux/efi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index e376270cd26e..0758753a17a1 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -168,7 +168,7 @@ typedef efi_status_t efi_get_variable_t (efi_char16_t *name, efi_guid_t *vendor, typedef efi_status_t efi_get_next_variable_t (unsigned long *name_size, efi_char16_t *name, efi_guid_t *vendor); typedef efi_status_t efi_set_variable_t (efi_char16_t *name, efi_guid_t *vendor, - unsigned long attr, unsigned long data_size, + u32 attr, unsigned long data_size, void *data); typedef efi_status_t efi_get_next_high_mono_count_t (u32 *count); typedef void efi_reset_system_t (int reset_type, efi_status_t status, -- cgit v1.2.3 From 3b3702377c576f6624348c7c6fd113bfd934fbd7 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Mon, 6 Jun 2011 15:36:25 -0400 Subject: x86, efi: Add infrastructure for UEFI 2.0 runtime services We're currently missing support for any of the runtime service calls introduced with the UEFI 2.0 spec in 2006. Add the infrastructure for supporting them. Signed-off-by: Matthew Garrett Link: http://lkml.kernel.org/r/1307388985-7852-2-git-send-email-mjg@redhat.com Signed-off-by: H. Peter Anvin --- include/linux/efi.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 0758753a17a1..ec2572693925 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -101,6 +101,13 @@ typedef struct { u64 attribute; } efi_memory_desc_t; +typedef struct { + efi_guid_t guid; + u32 headersize; + u32 flags; + u32 imagesize; +} efi_capsule_header_t; + typedef int (*efi_freemem_callback_t) (u64 start, u64 end, void *arg); /* @@ -156,6 +163,9 @@ typedef struct { unsigned long set_variable; unsigned long get_next_high_mono_count; unsigned long reset_system; + unsigned long update_capsule; + unsigned long query_capsule_caps; + unsigned long query_variable_info; } efi_runtime_services_t; typedef efi_status_t efi_get_time_t (efi_time_t *tm, efi_time_cap_t *tc); @@ -177,6 +187,17 @@ typedef efi_status_t efi_set_virtual_address_map_t (unsigned long memory_map_siz unsigned long descriptor_size, u32 descriptor_version, efi_memory_desc_t *virtual_map); +typedef efi_status_t efi_query_variable_info_t(u32 attr, + u64 *storage_space, + u64 *remaining_space, + u64 *max_variable_size); +typedef efi_status_t efi_update_capsule_t(efi_capsule_header_t **capsules, + unsigned long count, + unsigned long sg_list); +typedef efi_status_t efi_query_capsule_caps_t(efi_capsule_header_t **capsules, + unsigned long count, + u64 *max_size, + int *reset_type); /* * EFI Configuration Table and GUID definitions @@ -218,6 +239,13 @@ typedef struct { #define EFI_SYSTEM_TABLE_SIGNATURE ((u64)0x5453595320494249ULL) +#define EFI_2_30_SYSTEM_TABLE_REVISION ((2 << 16) | (30)) +#define EFI_2_20_SYSTEM_TABLE_REVISION ((2 << 16) | (20)) +#define EFI_2_10_SYSTEM_TABLE_REVISION ((2 << 16) | (10)) +#define EFI_2_00_SYSTEM_TABLE_REVISION ((2 << 16) | (00)) +#define EFI_1_10_SYSTEM_TABLE_REVISION ((1 << 16) | (10)) +#define EFI_1_02_SYSTEM_TABLE_REVISION ((1 << 16) | (02)) + typedef struct { efi_table_hdr_t hdr; unsigned long fw_vendor; /* physical addr of CHAR16 vendor string */ @@ -250,6 +278,7 @@ struct efi_memory_map { */ extern struct efi { efi_system_table_t *systab; /* EFI system table */ + unsigned int runtime_version; /* Runtime services version */ unsigned long mps; /* MPS table */ unsigned long acpi; /* ACPI table (IA64 ext 0.71) */ unsigned long acpi20; /* ACPI table (ACPI 2.0) */ @@ -266,6 +295,9 @@ extern struct efi { efi_get_variable_t *get_variable; efi_get_next_variable_t *get_next_variable; efi_set_variable_t *set_variable; + efi_query_variable_info_t *query_variable_info; + efi_update_capsule_t *update_capsule; + efi_query_capsule_caps_t *query_capsule_caps; efi_get_next_high_mono_count_t *get_next_high_mono_count; efi_reset_system_t *reset_system; efi_set_virtual_address_map_t *set_virtual_address_map; -- cgit v1.2.3 From 3019de124b9f5b1526cb3668b74af14371e21795 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 6 Jun 2011 16:41:33 -0700 Subject: net: Rework netdev_drivername() to avoid warning. This interface uses a temporary buffer, but for no real reason. And now can generate warnings like: net/sched/sch_generic.c: In function dev_watchdog net/sched/sch_generic.c:254:10: warning: unused variable drivername Just return driver->name directly or "". Reported-by: Connor Hansen Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ca333e79e10f..54b8b4d7b68f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2555,7 +2555,7 @@ extern void netdev_class_remove_file(struct class_attribute *class_attr); extern struct kobj_ns_type_operations net_ns_type_operations; -extern char *netdev_drivername(const struct net_device *dev, char *buffer, int len); +extern const char *netdev_drivername(const struct net_device *dev); extern void linkwatch_run_queue(void); -- cgit v1.2.3 From 13fcb7bd322164c67926ffe272846d4860196dc6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 6 Jun 2011 22:42:06 -0700 Subject: af_packet: prevent information leak In 2.6.27, commit 393e52e33c6c2 (packet: deliver VLAN TCI to userspace) added a small information leak. Add padding field and make sure its zeroed before copy to user. Signed-off-by: Eric Dumazet CC: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_packet.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_packet.h b/include/linux/if_packet.h index 6d66ce1791a9..7b318630139f 100644 --- a/include/linux/if_packet.h +++ b/include/linux/if_packet.h @@ -62,6 +62,7 @@ struct tpacket_auxdata { __u16 tp_mac; __u16 tp_net; __u16 tp_vlan_tci; + __u16 tp_padding; }; /* Rx ring - header status */ @@ -101,6 +102,7 @@ struct tpacket2_hdr { __u32 tp_sec; __u32 tp_nsec; __u16 tp_vlan_tci; + __u16 tp_padding; }; #define TPACKET2_HDRLEN (TPACKET_ALIGN(sizeof(struct tpacket2_hdr)) + sizeof(struct sockaddr_ll)) -- cgit v1.2.3 From a6b7a407865aab9f849dd99a71072b7cd1175116 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 6 Jun 2011 10:43:46 +0000 Subject: net: remove interrupt.h inclusion from netdevice.h * remove interrupt.g inclusion from netdevice.h -- not needed * fixup fallout, add interrupt.h and hardirq.h back where needed. Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- include/linux/arcdevice.h | 1 + include/linux/dccp.h | 1 + include/linux/netdevice.h | 1 - 3 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/arcdevice.h b/include/linux/arcdevice.h index 7d650a0e3d8f..7216b0daf544 100644 --- a/include/linux/arcdevice.h +++ b/include/linux/arcdevice.h @@ -20,6 +20,7 @@ #include #ifdef __KERNEL__ +#include #ifndef bool #define bool int diff --git a/include/linux/dccp.h b/include/linux/dccp.h index d638e85dc501..710c04302a15 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -236,6 +236,7 @@ enum dccp_packet_dequeueing_policy { #ifdef __KERNEL__ #include +#include #include #include #include diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ca333e79e10f..336288567c78 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1563,7 +1563,6 @@ struct packet_type { struct list_head list; }; -#include #include extern rwlock_t dev_base_lock; /* Device list lock */ -- cgit v1.2.3 From 5cec93c216db77c45f7ce970d46283bcb1933884 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Sun, 5 Jun 2011 13:50:24 -0400 Subject: x86-64: Emulate legacy vsyscalls There's a fair amount of code in the vsyscall page. It contains a syscall instruction (in the gettimeofday fallback) and who knows what will happen if an exploit jumps into the middle of some other code. Reduce the risk by replacing the vsyscalls with short magic incantations that cause the kernel to emulate the real vsyscalls. These incantations are useless if entered in the middle. This causes vsyscalls to be a little more expensive than real syscalls. Fortunately sensible programs don't use them. The only exception is time() which is still called by glibc through the vsyscall - but calling time() millions of times per second is not sensible. glibc has this fixed in the development tree. This patch is not perfect: the vread_tsc and vread_hpet functions are still at a fixed address. Fixing that might involve making alternative patching work in the vDSO. Signed-off-by: Andy Lutomirski Acked-by: Linus Torvalds Cc: Jesper Juhl Cc: Borislav Petkov Cc: Arjan van de Ven Cc: Jan Beulich Cc: richard -rw- weinberger Cc: Mikael Pettersson Cc: Andi Kleen Cc: Brian Gerst Cc: Louis Rilling Cc: Valdis.Kletnieks@vt.edu Cc: pageexec@freemail.hu Link: http://lkml.kernel.org/r/e64e1b3c64858820d12c48fa739efbd1485e79d5.1307292171.git.luto@mit.edu [ Removed the CONFIG option - it's simpler to just do it unconditionally. Tidied up the code as well. ] Signed-off-by: Ingo Molnar --- include/linux/seccomp.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index 167c33361d9c..cc7a4e9cc7ad 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -19,6 +19,11 @@ static inline void secure_computing(int this_syscall) extern long prctl_get_seccomp(void); extern long prctl_set_seccomp(unsigned long); +static inline int seccomp_mode(seccomp_t *s) +{ + return s->mode; +} + #else /* CONFIG_SECCOMP */ #include @@ -37,6 +42,11 @@ static inline long prctl_set_seccomp(unsigned long arg2) return -EINVAL; } +static inline int seccomp_mode(seccomp_t *s) +{ + return 0; +} + #endif /* CONFIG_SECCOMP */ #endif /* _LINUX_SECCOMP_H */ -- cgit v1.2.3 From 6dc1418e13144162e8bc4858789010d8f0e1e65c Mon Sep 17 00:00:00 2001 From: Tomoki Sekiyama Date: Mon, 23 May 2011 15:45:44 -0700 Subject: HID: yurex: recognize GeneralKeys wireless presenter as generic HID Unfortunately, the device seems to have the same Vendor ID and Product ID as YUREX leg-shakes sensors, and the commit 6bc235a2e2 ("USB: add driver for Meywa-Denki & Kayac YUREX") added the ID to hid_ignore_list. I believe that we can distinguish YUREX and the Wireless Presenter by device type. The patch below makes the driver ignore only YUREX (bInterfaceProtocol==0), and recognize Wireless Presenter (bInterfaceProtocol is keyboard or mouse) as generic HID. (I don't have the Wireless Presenter, so not yet ested.) ** YUREX lsusb information: Bus 002 Device 007: ID 0c45:1010 Microdia Device Descriptor: bLength 18 bDescriptorType 1 bcdUSB 1.10 bDeviceClass 0 (Defined at Interface level) bDeviceSubClass 0 bDeviceProtocol 0 bMaxPacketSize0 8 idVendor 0x0c45 Microdia idProduct 0x1010 bcdDevice 0.03 iManufacturer 1 JESS iProduct 2 YUREX iSerial 3 10000269 bNumConfigurations 1 Configuration Descriptor: bLength 9 bDescriptorType 2 wTotalLength 34 bNumInterfaces 1 bConfigurationValue 1 iConfiguration 0 bmAttributes 0xa0 (Bus Powered) Remote Wakeup MaxPower 100mA Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 0 bAlternateSetting 0 bNumEndpoints 1 bInterfaceClass 3 Human Interface Device bInterfaceSubClass 1 Boot Interface Subclass bInterfaceProtocol 0 None iInterface 0 HID Device Descriptor: bLength 9 bDescriptorType 33 bcdHID 1.10 bCountryCode 0 Not supported bNumDescriptors 1 bDescriptorType 34 Report wDescriptorLength 31 Report Descriptors: ** UNAVAILABLE ** Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x81 EP 1 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x0008 1x 8 bytes bInterval 10 Device Status: 0x0002 (Bus Powered) Remote Wakeup Enabled Addresses https://bugzilla.kernel.org/show_bug.cgi?id=26922 Signed-off-by: Tomoki Sekiyama Cc: Greg KH Cc: "Rafael J. Wysocki" Cc: Maciej Rutecki Reported-by: Thomas B?chler Tested-by: Thomas B?chler Signed-off-by: Andrew Morton Signed-off-by: Jiri Kosina --- include/linux/hid.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 42f7e2fb501f..9cf8e7ae7450 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -453,7 +453,8 @@ struct hid_input { enum hid_type { HID_TYPE_OTHER = 0, - HID_TYPE_USBMOUSE + HID_TYPE_USBMOUSE, + HID_TYPE_USBNONE }; struct hid_driver; -- cgit v1.2.3 From 21c13a4f7bc185552c4b402b792c3bbb9aa69df0 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Tue, 7 Jun 2011 11:35:52 -0400 Subject: usb-storage: redo incorrect reads Some USB mass-storage devices have bugs that cause them not to handle the first READ(10) command they receive correctly. The Corsair Padlock v2 returns completely bogus data for its first read (possibly it returns the data in encrypted form even though the device is supposed to be unlocked). The Feiya SD/SDHC card reader fails to complete the first READ(10) command after it is plugged in or after a new card is inserted, returning a status code that indicates it thinks the command was invalid, which prevents the kernel from retrying the read. Since the first read of a new device or a new medium is for the partition sector, the kernel is unable to retrieve the device's partition table. Users have to manually issue an "hdparm -z" or "blockdev --rereadpt" command before they can access the device. This patch (as1470) works around the problem. It adds a new quirk flag, US_FL_INVALID_READ10, indicating that the first READ(10) should always be retried immediately, as should any failing READ(10) commands (provided the preceding READ(10) command succeeded, to avoid getting stuck in a loop). The patch also adds appropriate unusual_devs entries containing the new flag. Signed-off-by: Alan Stern Tested-by: Sven Geggus Tested-by: Paul Hartman CC: Matthew Dharm CC: Signed-off-by: Greg Kroah-Hartman --- include/linux/usb_usual.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb_usual.h b/include/linux/usb_usual.h index 71693d4a4fe1..17df3600bcef 100644 --- a/include/linux/usb_usual.h +++ b/include/linux/usb_usual.h @@ -62,7 +62,9 @@ US_FLAG(NO_READ_DISC_INFO, 0x00040000) \ /* cannot handle READ_DISC_INFO */ \ US_FLAG(NO_READ_CAPACITY_16, 0x00080000) \ - /* cannot handle READ_CAPACITY_16 */ + /* cannot handle READ_CAPACITY_16 */ \ + US_FLAG(INITIAL_READ10, 0x00100000) \ + /* Initial READ(10) (and others) must be retried */ #define US_FLAG(name, value) US_FL_##name = value , enum { US_DO_ALL_FLAGS }; -- cgit v1.2.3 From 325fd182cafe5c5ead51c27afb6b8be83c9081d4 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 7 Jun 2011 15:39:18 +0100 Subject: USB: gadget.h depends on ch9.h so include ch9.h directly The struct definitions are used. Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/gadget.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index dd1571db55e7..55d1a88ff11f 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -16,6 +16,7 @@ #define __LINUX_USB_GADGET_H #include +#include struct usb_ep; -- cgit v1.2.3 From e73a9891b3a1c9fc0970e0c9dbe2cc47933ad752 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 6 Jun 2011 14:19:03 +0900 Subject: usb: renesas_usbhs: add DMAEngine support USB DMA was installed on "normal DMAC" when SH7724 or older SuperH, but the "USB-DMAC" was prepared on recent SuperH. These 2 DMAC have a little bit different behavior. This patch add DMAEngine code for "normal DMAC", but it is still using PIO fifo. The DMA fifo will be formally supported in the future. You can enable DMA fifo by local fixup usbhs_fifo_pio_push_handler -> usbhs_fifo_dma_push_handler usbhs_fifo_pio_pop_handler -> usbhs_fifo_dma_pop_handler on usbhsg_ep_enable. This DMAEngine was tested by g_file_storage on SH7724 Ecovec board Signed-off-by: Kuninori Morimoto Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/renesas_usbhs.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/renesas_usbhs.h b/include/linux/usb/renesas_usbhs.h index 3a7f1d982dd6..8977431259c6 100644 --- a/include/linux/usb/renesas_usbhs.h +++ b/include/linux/usb/renesas_usbhs.h @@ -110,6 +110,23 @@ struct renesas_usbhs_driver_param { * delay time from notify_hotplug callback */ int detection_delay; + + /* + * option: + * + * dma id for dmaengine + */ + int d0_tx_id; + int d0_rx_id; + int d1_tx_id; + int d1_rx_id; + + /* + * option: + * + * pio <--> dma border. + */ + int pio_dma_border; /* default is 64byte */ }; /* -- cgit v1.2.3 From 7808edcd306f22aeb23775d34e70b7fa2f58b852 Mon Sep 17 00:00:00 2001 From: Nicos Gollan Date: Thu, 5 May 2011 21:00:37 +0200 Subject: Basic support for Moschip 9900 family I/O chips Add I/O based support for serial and parallel ports of the following chips: Vendor: Moschip (0x9710) Parts (device IDs) * 9900 (0x9900) * 9904 (0x9904 * 9901 (0x9912, also sold as 9912) * 9922 (0x9922) On all chips but the 9900, a single port is provided per PCI subdevice (subvendor-ID 0xA000, subdevice-IDs 0x1000 for serial, 0x2000 for parallel with proper class codes). In cascading configurations, the 9900 provides two devices per subdevice, with subvendor-ID 0xA000 and subdevice-IDs 0x30ps where p is the number of parallel ports and s the number of serial ports. Basic testing was only done on the serial part of a 9912 to the point where it can be used for a serial kernel console, and advanced features are completely untested. It is possible to reduce functionality of the chips by adding a configuration EEPROM, and the datasheet [1] is inconsistent w.r.t subdevices in the 4s+2s1p and 2s1p+4s configurations. The subdevice-ID 0x3012 should likely read 0x3011 with a serial port in function 3, which would be consistent with the BAR layouts. For now, the drivers ignore subdevices with ID 0x1000 and no class code. The parallel ports are integrated in parport_serial even for purely parallel parts to reduce the footprint of the patch. [1] http://www.moschip.com/data/products/MCS9900/MCS9900_Datasheet.pdf Signed-off-by: Nicos Gollan Signed-off-by: Greg Kroah-Hartman --- include/linux/pci_ids.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index a311008af5e1..034ebb4451c2 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2821,7 +2821,11 @@ #define PCI_DEVICE_ID_NETMOS_9845 0x9845 #define PCI_DEVICE_ID_NETMOS_9855 0x9855 #define PCI_DEVICE_ID_NETMOS_9865 0x9865 +#define PCI_DEVICE_ID_NETMOS_9900 0x9900 #define PCI_DEVICE_ID_NETMOS_9901 0x9901 +#define PCI_DEVICE_ID_NETMOS_9904 0x9904 +#define PCI_DEVICE_ID_NETMOS_9912 0x9912 +#define PCI_DEVICE_ID_NETMOS_9922 0x9922 #define PCI_VENDOR_ID_3COM_2 0xa727 -- cgit v1.2.3 From ae92c1f5e7b6708371365d262625ac19e67c1e79 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 24 May 2011 10:43:03 +0200 Subject: TTY: export NR_LDISC and N_* line discipline numbers to user-space Since commit (4564f9e5: consolidate line discipline number definitions) the patch moved all line discipline number from a per-architecture termios.h to a shared one: tty.h. However, prior to this consolidation work, the line discipline numbers were outside of an ifdef __KERNEL__/endif block so these numbers used to be exported to user-space. Since such numbers are kernel ABI anyway, and tty.h is already included for user- space header processing, just move these relevant defines outside of the ifdef __KERNEL__/endif block in include/linux/tty.h. CC: Maxime Bizon Signed-off-by: Florian Fainelli Acked-by: Tilman Schmidt Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 37 +++++++++++++++++++------------------ 1 file changed, 19 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index d6f05292e456..44bc0c5617e1 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -5,24 +5,6 @@ * 'tty.h' defines some structures used by tty_io.c and some defines. */ -#ifdef __KERNEL__ -#include -#include -#include -#include -#include -#include -#include - -#include - - -/* - * (Note: the *_driver.minor_start values 1, 64, 128, 192 are - * hardcoded at present.) - */ -#define NR_UNIX98_PTY_DEFAULT 4096 /* Default maximum for Unix98 ptys */ -#define NR_UNIX98_PTY_MAX (1 << MINORBITS) /* Absolute limit */ #define NR_LDISCS 30 /* line disciplines */ @@ -53,6 +35,25 @@ #define N_TRACESINK 23 /* Trace data routing for MIPI P1149.7 */ #define N_TRACEROUTER 24 /* Trace data routing for MIPI P1149.7 */ +#ifdef __KERNEL__ +#include +#include +#include +#include +#include +#include +#include + +#include + + +/* + * (Note: the *_driver.minor_start values 1, 64, 128, 192 are + * hardcoded at present.) + */ +#define NR_UNIX98_PTY_DEFAULT 4096 /* Default maximum for Unix98 ptys */ +#define NR_UNIX98_PTY_MAX (1 << MINORBITS) /* Absolute limit */ + /* * This character is the same as _POSIX_VDISABLE: it cannot be used as * a c_cc[] character, but indicates that a particular special character -- cgit v1.2.3 From ea2c00095c022846dd8dfd211de05154d3e4e1b8 Mon Sep 17 00:00:00 2001 From: "K. Y. Srinivasan" Date: Tue, 17 May 2011 15:25:37 -0700 Subject: Connector: Set the CN_NETLINK_USERS correctly The CN_NETLINK_USERS must be set to the highest valid index +1. Thanks to Evgeniy for pointing this out. Signed-off-by: K. Y. Srinivasan Acked-by: Evgeniy Polyakov Cc: stable [.39] Signed-off-by: Greg Kroah-Hartman --- include/linux/connector.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/connector.h b/include/linux/connector.h index 7c60d0942adb..f696bccd48cb 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -44,7 +44,7 @@ #define CN_VAL_DRBD 0x1 #define CN_KVP_IDX 0x9 /* HyperV KVP */ -#define CN_NETLINK_USERS 9 +#define CN_NETLINK_USERS 10 /* Highest index + 1 */ /* * Maximum connector's message size. -- cgit v1.2.3 From 98d9f30c820d509145757e6ecbc36013aa02f7bc Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 11 Apr 2011 11:37:07 +1000 Subject: pci/of: Match PCI devices to OF nodes dynamically powerpc has two different ways of matching PCI devices to their corresponding OF node (if any) for historical reasons. The ppc64 one does a scan looking for matching bus/dev/fn, while the ppc32 one does a scan looking only for matching dev/fn on each level in order to be agnostic to busses being renumbered (which Linux does on some platforms). This removes both and instead moves the matching code to the PCI core itself. It's the most logical place to do it: when a pci_dev is created, we know the parent and thus can do a single level scan for the matching device_node (if any). The benefit is that all archs now get the matching for free. There's one hook the arch might want to provide to match a PHB bus to its device node. A default weak implementation is provided that looks for the parent device device node, but it's not entirely reliable on powerpc for various reasons so powerpc provides its own. Signed-off-by: Benjamin Herrenschmidt Acked-by: Michal Simek Acked-by: Jesse Barnes --- include/linux/of_pci.h | 5 +++++ include/linux/pci.h | 18 ++++++++++++++++++ 2 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h index 85a27b650d76..f93e21700d3e 100644 --- a/include/linux/of_pci.h +++ b/include/linux/of_pci.h @@ -6,4 +6,9 @@ struct pci_dev; struct of_irq; int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq); + +struct device_node; +struct device_node *of_pci_find_child_device(struct device_node *parent, + unsigned int devfn); + #endif diff --git a/include/linux/pci.h b/include/linux/pci.h index c446b5ca2d38..e5086e9a9bf7 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1589,5 +1589,23 @@ int pci_vpd_find_tag(const u8 *buf, unsigned int off, unsigned int len, u8 rdt); int pci_vpd_find_info_keyword(const u8 *buf, unsigned int off, unsigned int len, const char *kw); +/* PCI <-> OF binding helpers */ +#ifdef CONFIG_OF +struct device_node; +extern void pci_set_of_node(struct pci_dev *dev); +extern void pci_release_of_node(struct pci_dev *dev); +extern void pci_set_bus_of_node(struct pci_bus *bus); +extern void pci_release_bus_of_node(struct pci_bus *bus); + +/* Arch may override this (weak) */ +extern struct device_node * __weak pcibios_get_phb_of_node(struct pci_bus *bus); + +#else /* CONFIG_OF */ +static inline void pci_set_of_node(struct pci_dev *dev) { } +static inline void pci_release_of_node(struct pci_dev *dev) { } +static inline void pci_set_bus_of_node(struct pci_bus *bus) { } +static inline void pci_release_bus_of_node(struct pci_bus *bus) { } +#endif /* CONFIG_OF */ + #endif /* __KERNEL__ */ #endif /* LINUX_PCI_H */ -- cgit v1.2.3 From 64099d981c9916ec4a485b3ffbb89fa877fc595f Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 7 Apr 2011 13:09:47 +1000 Subject: pci/of: Consolidate pci_device_to_OF_node() All archs do more or less the same thing now, move it into a single generic place. I chose pci.h rather than of_pci.h to avoid having to change all call-sites to include the later. Signed-off-by: Benjamin Herrenschmidt Acked-by: Michal Simek Acked-by: Grant Likely Acked-by: Jesse Barnes --- include/linux/pci.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index e5086e9a9bf7..795e6a56d8cd 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1600,6 +1600,11 @@ extern void pci_release_bus_of_node(struct pci_bus *bus); /* Arch may override this (weak) */ extern struct device_node * __weak pcibios_get_phb_of_node(struct pci_bus *bus); +static inline struct device_node *pci_device_to_OF_node(struct pci_dev *pdev) +{ + return pdev ? pdev->dev.of_node : NULL; +} + #else /* CONFIG_OF */ static inline void pci_set_of_node(struct pci_dev *dev) { } static inline void pci_release_of_node(struct pci_dev *dev) { } -- cgit v1.2.3 From ef3b4f8cc20e80c767e47b848fb7512770ab80d7 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 11 Apr 2011 11:34:33 +1000 Subject: pci/of: Consolidate pci_bus_to_OF_node() The generic code always get the device-node in the right place now so a single implementation will work for all archs Signed-off-by: Benjamin Herrenschmidt Acked-by: Grant Likely Acked-by: Michal Simek Acked-by: Jesse Barnes --- include/linux/pci.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 795e6a56d8cd..2d292182dde5 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1605,6 +1605,11 @@ static inline struct device_node *pci_device_to_OF_node(struct pci_dev *pdev) return pdev ? pdev->dev.of_node : NULL; } +static inline struct device_node *pci_bus_to_OF_node(struct pci_bus *bus) +{ + return bus ? bus->dev.of_node : NULL; +} + #else /* CONFIG_OF */ static inline void pci_set_of_node(struct pci_dev *dev) { } static inline void pci_release_of_node(struct pci_dev *dev) { } -- cgit v1.2.3 From 6e6938b6d3130305a5960c86b1a9b21e58cf6144 Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Sun, 6 Jun 2010 10:38:15 -0600 Subject: writeback: introduce .tagged_writepages for the WB_SYNC_NONE sync stage sync(2) is performed in two stages: the WB_SYNC_NONE sync and the WB_SYNC_ALL sync. Identify the first stage with .tagged_writepages and do livelock prevention for it, too. Jan's commit f446daaea9 ("mm: implement writeback livelock avoidance using page tagging") is a partial fix in that it only fixed the WB_SYNC_ALL phase livelock. Although ext4 is tested to no longer livelock with commit f446daaea9, it may due to some "redirty_tail() after pages_skipped" effect which is by no means a guarantee for _all_ the file systems. Note that writeback_inodes_sb() is called by not only sync(), they are treated the same because the other callers also need livelock prevention. Impact: It changes the order in which pages/inodes are synced to disk. Now in the WB_SYNC_NONE stage, it won't proceed to write the next inode until finished with the current inode. Acked-by: Jan Kara CC: Dave Chinner Signed-off-by: Wu Fengguang --- include/linux/writeback.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 17e7ccc322a5..3f6542ca6198 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -47,6 +47,7 @@ struct writeback_control { unsigned encountered_congestion:1; /* An output: a queue is full */ unsigned for_kupdate:1; /* A kupdate writeback */ unsigned for_background:1; /* A background writeback */ + unsigned tagged_writepages:1; /* tag-and-write to avoid livelock */ unsigned for_reclaim:1; /* Invoked from the page allocator */ unsigned range_cyclic:1; /* range_start is cyclic */ unsigned more_io:1; /* more io to be dispatched */ -- cgit v1.2.3 From cb9bd1159c5fe8995e151fa7df10fa19f8c119cc Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Wed, 21 Jul 2010 22:50:57 -0600 Subject: writeback: introduce writeback_control.inodes_written The flusher works on dirty inodes in batches, and may quit prematurely if the batch of inodes happen to be metadata-only dirtied: in this case wbc->nr_to_write won't be decreased at all, which stands for "no pages written" but also mis-interpreted as "no progress". So introduce writeback_control.inodes_written to count the inodes get cleaned from VFS POV. A non-zero value means there are some progress on writeback, in which case more writeback can be tried. Acked-by: Jan Kara Acked-by: Mel Gorman Signed-off-by: Wu Fengguang --- include/linux/writeback.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 3f6542ca6198..7df9026f7129 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -34,6 +34,7 @@ struct writeback_control { long nr_to_write; /* Write this many pages, and decrement this for each page written */ long pages_skipped; /* Pages which were not written */ + long inodes_written; /* # of inodes written (at least) */ /* * For a_ops->writepages(): is start or end are non-zero then this is -- cgit v1.2.3 From f758eeabeb96f878c860e8f110f94ec8820822a9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 21 Apr 2011 18:19:44 -0600 Subject: writeback: split inode_wb_list_lock into bdi_writeback.list_lock Split the global inode_wb_list_lock into a per-bdi_writeback list_lock, as it's currently the most contended lock in the system for metadata heavy workloads. It won't help for single-filesystem workloads for which we'll need the I/O-less balance_dirty_pages, but at least we can dedicate a cpu to spinning on each bdi now for larger systems. Based on earlier patches from Nick Piggin and Dave Chinner. It reduces lock contentions to 1/4 in this test case: 10 HDD JBOD, 100 dd on each disk, XFS, 6GB ram lock_stat version 0.3 ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- class name con-bounces contentions waittime-min waittime-max waittime-total acq-bounces acquisitions holdtime-min holdtime-max holdtime-total ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- vanilla 2.6.39-rc3: inode_wb_list_lock: 42590 44433 0.12 147.74 144127.35 252274 886792 0.08 121.34 917211.23 ------------------ inode_wb_list_lock 2 [] bdev_inode_switch_bdi+0x29/0x85 inode_wb_list_lock 34 [] inode_wb_list_del+0x22/0x49 inode_wb_list_lock 12893 [] __mark_inode_dirty+0x170/0x1d0 inode_wb_list_lock 10702 [] writeback_single_inode+0x16d/0x20a ------------------ inode_wb_list_lock 2 [] bdev_inode_switch_bdi+0x29/0x85 inode_wb_list_lock 19 [] inode_wb_list_del+0x22/0x49 inode_wb_list_lock 5550 [] __mark_inode_dirty+0x170/0x1d0 inode_wb_list_lock 8511 [] writeback_sb_inodes+0x10f/0x157 2.6.39-rc3 + patch: &(&wb->list_lock)->rlock: 11383 11657 0.14 151.69 40429.51 90825 527918 0.11 145.90 556843.37 ------------------------ &(&wb->list_lock)->rlock 10 [] inode_wb_list_del+0x5f/0x86 &(&wb->list_lock)->rlock 1493 [] writeback_inodes_wb+0x3d/0x150 &(&wb->list_lock)->rlock 3652 [] writeback_sb_inodes+0x123/0x16f &(&wb->list_lock)->rlock 1412 [] writeback_single_inode+0x17f/0x223 ------------------------ &(&wb->list_lock)->rlock 3 [] bdi_lock_two+0x46/0x4b &(&wb->list_lock)->rlock 6 [] inode_wb_list_del+0x5f/0x86 &(&wb->list_lock)->rlock 2061 [] __mark_inode_dirty+0x173/0x1cf &(&wb->list_lock)->rlock 2629 [] writeback_sb_inodes+0x123/0x16f hughd@google.com: fix recursive lock when bdi_lock_two() is called with new the same as old akpm@linux-foundation.org: cleanup bdev_inode_switch_bdi() comment Signed-off-by: Christoph Hellwig Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Wu Fengguang --- include/linux/backing-dev.h | 2 ++ include/linux/writeback.h | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 96f4094b706d..47feb2c4706a 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -57,6 +57,7 @@ struct bdi_writeback { struct list_head b_dirty; /* dirty inodes */ struct list_head b_io; /* parked for writeback */ struct list_head b_more_io; /* parked for more writeback */ + spinlock_t list_lock; /* protects the b_* lists */ }; struct backing_dev_info { @@ -106,6 +107,7 @@ int bdi_writeback_thread(void *data); int bdi_has_dirty_io(struct backing_dev_info *bdi); void bdi_arm_supers_timer(void); void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi); +void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2); extern spinlock_t bdi_lock; extern struct list_head bdi_list; diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 7df9026f7129..c2d957fb38d3 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -9,8 +9,6 @@ struct backing_dev_info; -extern spinlock_t inode_wb_list_lock; - /* * fs/fs-writeback.c */ -- cgit v1.2.3 From e185dda89d69cde142b48059413a03561f41f78a Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Sat, 23 Apr 2011 11:26:07 -0600 Subject: writeback: avoid extra sync work at enqueue time This removes writeback_control.wb_start and does more straightforward sync livelock prevention by setting .older_than_this to prevent extra inodes from being enqueued in the first place. Acked-by: Jan Kara Signed-off-by: Wu Fengguang --- include/linux/writeback.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index c2d957fb38d3..d8e96a480850 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -26,9 +26,6 @@ struct writeback_control { enum writeback_sync_modes sync_mode; unsigned long *older_than_this; /* If !NULL, only write back inodes older than this */ - unsigned long wb_start; /* Time writeback_inodes_wb was - called. This is needed to avoid - extra jobs and livelock */ long nr_to_write; /* Write this many pages, and decrement this for each page written */ long pages_skipped; /* Pages which were not written */ -- cgit v1.2.3 From b7a2441f9966fe3e1be960a876ab52e6029ea005 Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Wed, 21 Jul 2010 22:19:51 -0600 Subject: writeback: remove writeback_control.more_io When wbc.more_io was first introduced, it indicates whether there are at least one superblock whose s_more_io contains more IO work. Now with the per-bdi writeback, it can be replaced with a simple b_more_io test. Acked-by: Jan Kara Acked-by: Mel Gorman Reviewed-by: Minchan Kim Signed-off-by: Wu Fengguang --- include/linux/writeback.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index d8e96a480850..8797b20dd22b 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -46,7 +46,6 @@ struct writeback_control { unsigned tagged_writepages:1; /* tag-and-write to avoid livelock */ unsigned for_reclaim:1; /* Invoked from the page allocator */ unsigned range_cyclic:1; /* range_start is cyclic */ - unsigned more_io:1; /* more io to be dispatched */ }; /* -- cgit v1.2.3 From 846d5a091b0506b75489577cde27f39b37a192a4 Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Thu, 5 May 2011 21:10:38 -0600 Subject: writeback: remove .nonblocking and .encountered_congestion Remove two unused struct writeback_control fields: .encountered_congestion (completely unused) .nonblocking (never set, checked/showed in XFS,NFS/btrfs) The .for_background check in nfs_write_inode() is also removed btw, as .for_background implies WB_SYNC_NONE. Reviewed-by: Jan Kara Proposed-by: Christoph Hellwig Signed-off-by: Wu Fengguang --- include/linux/writeback.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 8797b20dd22b..2f1b512bd6e0 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -39,8 +39,6 @@ struct writeback_control { loff_t range_start; loff_t range_end; - unsigned nonblocking:1; /* Don't get stuck on request queues */ - unsigned encountered_congestion:1; /* An output: a queue is full */ unsigned for_kupdate:1; /* A kupdate writeback */ unsigned for_background:1; /* A background writeback */ unsigned tagged_writepages:1; /* tag-and-write to avoid livelock */ -- cgit v1.2.3 From debf9507166eede1e676d27d3298cdfb27399cb4 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 8 Jun 2011 18:19:37 +0900 Subject: serial: sh-sci: Generalize overrun handling. This consolidates all of the broken out overrun handling and ensures that we have sensible defaults per-port type, in addition to making sure that overruns are flagged appropriately in the error mask for parts that haven't explicitly disabled support for it. Signed-off-by: Paul Mundt --- include/linux/serial_sci.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_sci.h b/include/linux/serial_sci.h index a2afc9fbe186..5fac3bccfd87 100644 --- a/include/linux/serial_sci.h +++ b/include/linux/serial_sci.h @@ -8,6 +8,8 @@ * Generic header for SuperH SCI(F) (used by sh/sh64/h8300 and related parts) */ +#define SCIx_NOT_SUPPORTED (-1) + enum { SCBRR_ALGO_1, /* ((clk + 16 * bps) / (16 * bps) - 1) */ SCBRR_ALGO_2, /* ((clk + 16 * bps) / (32 * bps) - 1) */ @@ -25,6 +27,28 @@ enum { #define SCSCR_CKE1 (1 << 1) #define SCSCR_CKE0 (1 << 0) +/* SCxSR SCI */ +#define SCI_TDRE 0x80 +#define SCI_RDRF 0x40 +#define SCI_ORER 0x20 +#define SCI_FER 0x10 +#define SCI_PER 0x08 +#define SCI_TEND 0x04 + +#define SCI_DEFAULT_ERROR_MASK (SCI_PER | SCI_FER) + +/* SCxSR SCIF */ +#define SCIF_ER 0x0080 +#define SCIF_TEND 0x0040 +#define SCIF_TDFE 0x0020 +#define SCIF_BRK 0x0010 +#define SCIF_FER 0x0008 +#define SCIF_PER 0x0004 +#define SCIF_RDF 0x0002 +#define SCIF_DR 0x0001 + +#define SCIF_DEFAULT_ERROR_MASK (SCIF_PER | SCIF_FER | SCIF_ER | SCIF_BRK) + /* Offsets into the sci_port->irqs array */ enum { SCIx_ERI_IRQ, @@ -56,6 +80,12 @@ struct plat_sci_port { unsigned int scbrr_algo_id; /* SCBRR calculation algo */ unsigned int scscr; /* SCSCR initialization */ + /* + * Platform overrides if necessary, defaults otherwise. + */ + int overrun_bit; + unsigned int error_mask; + struct device *dma_dev; unsigned int dma_slave_tx; -- cgit v1.2.3 From 514820eb982eb85677ed2ecef9710e90e24fbdab Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 8 Jun 2011 18:51:32 +0900 Subject: serial: sh-sci: Consolidate RXD pin handling. Non-SCI parts do not have the special port reg necessary for cases where the RX and SCI pins are muxed and need to be manually polled, so these like always fall back on the normal FIFO processing paths. SH7760 is in a class in and of itself with regards to mapping its SIM card interface via the SCI port class despite not having any of the RXD lines wired up and so implicitly behaving more like a SCIF in this regard. Out of the other CPUs, some support the port check via the same block while others do it through an external SuperI/O, so it's not even possible to perform the check relative to the ioremapped cookie offset, so the separate read semantics are preserved here, too. Signed-off-by: Paul Mundt --- include/linux/serial_sci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_sci.h b/include/linux/serial_sci.h index 5fac3bccfd87..ecefec7c0b67 100644 --- a/include/linux/serial_sci.h +++ b/include/linux/serial_sci.h @@ -86,6 +86,8 @@ struct plat_sci_port { int overrun_bit; unsigned int error_mask; + int port_reg; + struct device *dma_dev; unsigned int dma_slave_tx; -- cgit v1.2.3 From 13e12d14e2dccc7995b8f15a5678a338ab4e6a8c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 8 Jun 2011 15:18:19 -0700 Subject: vfs: reorganize 'struct inode' layout a bit This tries to make the 'struct inode' accesses denser in the data cache by moving a commonly accessed field (i_security) closer to other fields that are accessed often. It also makes 'i_state' just an 'unsigned int' rather than 'unsigned long', since we only use a few bits of that field, and moves it next to the existing 'i_flags' so that we potentially get better structure layout (although depending on config options, i_flags may already have packed in the same word as i_lock, so this improves packing only for the case of spinlock debugging) Out 'struct inode' is still way too big, and we should probably move some other fields around too (the acl fields in particular) for better data cache access density. Other fields (like the inode hash) are likely to be entirely irrelevant under most loads. Signed-off-by: Linus Torvalds --- include/linux/fs.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 646a1836152a..1c777878f1ea 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -744,9 +744,13 @@ struct inode { spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned int i_flags; + unsigned int i_state; +#ifdef CONFIG_SECURITY + void *i_security; +#endif struct mutex i_mutex; - unsigned long i_state; + unsigned long dirtied_when; /* jiffies of first dirtying */ struct hlist_node i_hash; @@ -798,9 +802,6 @@ struct inode { atomic_t i_readcount; /* struct files open RO */ #endif atomic_t i_writecount; -#ifdef CONFIG_SECURITY - void *i_security; -#endif #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *i_acl; struct posix_acl *i_default_acl; -- cgit v1.2.3 From bff55273f98dea0ceb78e28eb69462fe5f72ef3d Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 8 Jun 2011 12:35:08 +0000 Subject: v2 ethtool: remove support for ETHTOOL_GRXNTUPLE This change is meant to remove all support for displaying an ntuple as strings via ETHTOOL_GRXNTUPLE. The reason for this change is due to the fact that multiple issues have been found including: - Multiple buffer overruns for strings being displayed. - Incorrect filters displayed, cleared filters with ring of -2 are displayed - Setting get_rx_ntuple displays no rules if defined. - Endianess wrong on displayed values. - Hard limit of 1024 filters makes display functionality extremely limited The only driver that had supported this interface was ixgbe. Since it no longer uses the interface and due to the issues mentioned above I am submitting this patch to remove it. v2: Updated based on comments from Ben Hutchings - Left ETH_SS_NTUPLE_FILTERS in code but commented on it being deprecated - Removed ethtool_rx_ntuple_list and ethtool_rx_ntuple_flow_spec_container - Left ETHTOOL_GRXNTUPLE but commented it as deprecated Also cleaned up set_rx_ntuple since there is no flow spec container to maintain we can drop all the code for the alloc and free of it and just return ops->set_rx_ntuple(). Signed-off-by: Alexander Duyck Acked-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/ethtool.h | 19 ++----------------- include/linux/netdevice.h | 3 --- 2 files changed, 2 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index c6a850ab2ec5..dfd34934213d 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -287,7 +287,7 @@ enum ethtool_stringset { ETH_SS_TEST = 0, ETH_SS_STATS, ETH_SS_PRIV_FLAGS, - ETH_SS_NTUPLE_FILTERS, + ETH_SS_NTUPLE_FILTERS, /* Do not use, GRXNTUPLE is now deprecated */ ETH_SS_FEATURES, }; @@ -714,18 +714,6 @@ enum ethtool_sfeatures_retval_bits { /* needed by dev_disable_lro() */ extern int __ethtool_set_flags(struct net_device *dev, u32 flags); -struct ethtool_rx_ntuple_flow_spec_container { - struct ethtool_rx_ntuple_flow_spec fs; - struct list_head list; -}; - -struct ethtool_rx_ntuple_list { -#define ETHTOOL_MAX_NTUPLE_LIST_ENTRY 1024 -#define ETHTOOL_MAX_NTUPLE_STRING_PER_ENTRY 14 - struct list_head list; - unsigned int count; -}; - /** * enum ethtool_phys_id_state - indicator state for physical identification * @ETHTOOL_ID_INACTIVE: Physical ID indicator should be deactivated @@ -758,7 +746,6 @@ u32 ethtool_op_get_ufo(struct net_device *dev); int ethtool_op_set_ufo(struct net_device *dev, u32 data); u32 ethtool_op_get_flags(struct net_device *dev); int ethtool_op_set_flags(struct net_device *dev, u32 data, u32 supported); -void ethtool_ntuple_flush(struct net_device *dev); bool ethtool_invalid_flags(struct net_device *dev, u32 data, u32 supported); /** @@ -865,7 +852,6 @@ bool ethtool_invalid_flags(struct net_device *dev, u32 data, u32 supported); * error code or zero. * @set_rx_ntuple: Set an RX n-tuple rule. Returns a negative error code * or zero. - * @get_rx_ntuple: Deprecated. * @get_rxfh_indir: Get the contents of the RX flow hash indirection table. * Returns a negative error code or zero. * @set_rxfh_indir: Set the contents of the RX flow hash indirection table. @@ -944,7 +930,6 @@ struct ethtool_ops { int (*reset)(struct net_device *, u32 *); int (*set_rx_ntuple)(struct net_device *, struct ethtool_rx_ntuple *); - int (*get_rx_ntuple)(struct net_device *, u32 stringset, void *); int (*get_rxfh_indir)(struct net_device *, struct ethtool_rxfh_indir *); int (*set_rxfh_indir)(struct net_device *, @@ -1017,7 +1002,7 @@ struct ethtool_ops { #define ETHTOOL_FLASHDEV 0x00000033 /* Flash firmware to device */ #define ETHTOOL_RESET 0x00000034 /* Reset hardware */ #define ETHTOOL_SRXNTUPLE 0x00000035 /* Add an n-tuple filter to device */ -#define ETHTOOL_GRXNTUPLE 0x00000036 /* Get n-tuple filters from device */ +#define ETHTOOL_GRXNTUPLE 0x00000036 /* deprecated */ #define ETHTOOL_GSSET_INFO 0x00000037 /* Get string set info */ #define ETHTOOL_GRXFHINDIR 0x00000038 /* Get RX flow hash indir'n table */ #define ETHTOOL_SRXFHINDIR 0x00000039 /* Set RX flow hash indir'n table */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 336288567c78..6469fa942d1d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1348,9 +1348,6 @@ struct net_device { /* max exchange id for FCoE LRO by ddp */ unsigned int fcoe_ddp_xid; #endif - /* n-tuple filter list attached to this device */ - struct ethtool_rx_ntuple_list ethtool_ntuple_list; - /* phy device may attach itself for hardware timestamping */ struct phy_device *phydev; -- cgit v1.2.3 From 9ad7c049f0f79c418e293b1b68cf10d68f54fcdb Mon Sep 17 00:00:00 2001 From: Jerry Chu Date: Wed, 8 Jun 2011 11:08:38 +0000 Subject: tcp: RFC2988bis + taking RTT sample from 3WHS for the passive open side This patch lowers the default initRTO from 3secs to 1sec per RFC2988bis. It falls back to 3secs if the SYN or SYN-ACK packet has been retransmitted, AND the TCP timestamp option is not on. It also adds support to take RTT sample during 3WHS on the passive open side, just like its active open counterpart, and uses it, if valid, to seed the initRTO for the data transmission phase. The patch also resets ssthresh to its initial default at the beginning of the data transmission phase, and reduces cwnd to 1 if there has been MORE THAN ONE retransmission during 3WHS per RFC5681. Signed-off-by: H.K. Jerry Chu Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index e64f4c67d0ef..531ede8006d9 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -282,6 +282,7 @@ struct tcp_request_sock { #endif u32 rcv_isn; u32 snt_isn; + u32 snt_synack; /* synack sent time */ }; static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req) -- cgit v1.2.3 From 76369139ceb955deefc509e6e12ce9d6ce50ccab Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 19 May 2011 19:55:04 +0200 Subject: perf: Split up buffer handling from core code And create the internal perf events header. v2: Keep an internal inlined perf_output_copy() Signed-off-by: Frederic Weisbecker Acked-by: Peter Zijlstra Cc: Borislav Petkov Cc: Stephane Eranian Cc: Arnaldo Carvalho de Melo Cc: Steven Rostedt Link: http://lkml.kernel.org/r/1305827704-5607-1-git-send-email-fweisbec@gmail.com [ v3: use clearer 'ring_buffer' and 'rb' naming ] Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 33 ++++----------------------------- 1 file changed, 4 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 3412684ce5d5..779f6ed54d52 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -680,33 +680,6 @@ enum perf_event_active_state { }; struct file; - -#define PERF_BUFFER_WRITABLE 0x01 - -struct perf_buffer { - atomic_t refcount; - struct rcu_head rcu_head; -#ifdef CONFIG_PERF_USE_VMALLOC - struct work_struct work; - int page_order; /* allocation order */ -#endif - int nr_pages; /* nr of data pages */ - int writable; /* are we writable */ - - atomic_t poll; /* POLL_ for wakeups */ - - local_t head; /* write position */ - local_t nest; /* nested writers */ - local_t events; /* event limit */ - local_t wakeup; /* wakeup stamp */ - local_t lost; /* nr records lost */ - - long watermark; /* wakeup watermark */ - - struct perf_event_mmap_page *user_page; - void *data_pages[0]; -}; - struct perf_sample_data; typedef void (*perf_overflow_handler_t)(struct perf_event *, int, @@ -745,6 +718,8 @@ struct perf_cgroup { }; #endif +struct ring_buffer; + /** * struct perf_event - performance event kernel representation: */ @@ -834,7 +809,7 @@ struct perf_event { atomic_t mmap_count; int mmap_locked; struct user_struct *mmap_user; - struct perf_buffer *buffer; + struct ring_buffer *rb; /* poll related */ wait_queue_head_t waitq; @@ -945,7 +920,7 @@ struct perf_cpu_context { struct perf_output_handle { struct perf_event *event; - struct perf_buffer *buffer; + struct ring_buffer *rb; unsigned long wakeup; unsigned long size; void *addr; -- cgit v1.2.3 From 334955ef964bee9d3b1e20966847eee28cfd05f6 Mon Sep 17 00:00:00 2001 From: Ralf Baechle Date: Wed, 1 Jun 2011 19:04:57 +0100 Subject: i8253: Create linux/i8253.h and use it in all 8253 related files Signed-off-by: Ralf Baechle Cc: linux-mips@linux-mips.org Link: http://lkml.kernel.org/r/20110601180610.054254048@duck.linux-mips.net Signed-off-by: Thomas Gleixner arch/arm/mach-footbridge/isa-timer.c | 2 +- arch/mips/cobalt/time.c | 2 +- arch/mips/jazz/irq.c | 2 +- arch/mips/kernel/i8253.c | 2 +- arch/mips/mti-malta/malta-time.c | 2 +- arch/mips/sgi-ip22/ip22-time.c | 2 +- arch/mips/sni/time.c | 2 +- arch/x86/kernel/apic/apic.c | 2 +- arch/x86/kernel/apm_32.c | 2 +- arch/x86/kernel/hpet.c | 2 +- arch/x86/kernel/i8253.c | 2 +- arch/x86/kernel/time.c | 2 +- drivers/block/hd.c | 2 +- drivers/clocksource/i8253.c | 2 +- drivers/input/gameport/gameport.c | 2 +- drivers/input/joystick/analog.c | 2 +- drivers/input/misc/pcspkr.c | 2 +- include/linux/i8253.h | 11 +++++++++++ sound/drivers/pcsp/pcsp.h | 2 +- 19 files changed, 29 insertions(+), 18 deletions(-) --- include/linux/i8253.h | 11 +++++++++++ 1 file changed, 11 insertions(+) create mode 100644 include/linux/i8253.h (limited to 'include/linux') diff --git a/include/linux/i8253.h b/include/linux/i8253.h new file mode 100644 index 000000000000..d2cba88f75d6 --- /dev/null +++ b/include/linux/i8253.h @@ -0,0 +1,11 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + */ +#ifndef __LINUX_I8253_H +#define __LINUX_I8253_H + +#include + +#endif /* __LINUX_I8253_H */ -- cgit v1.2.3 From cb2455aa274b780802c593fecf115240a655d809 Mon Sep 17 00:00:00 2001 From: Ralf Baechle Date: Wed, 1 Jun 2011 19:04:58 +0100 Subject: i8253: Unify all kernel declarations of i8253_lock Signed-off-by: Ralf Baechle Cc: Russell King Cc: linux-arm-kernel@lists.infradead.org Cc: linux-mips@linux-mips.org Link: http://lkml.kernel.org/r/20110601180610.134151920@duck.linux-mips.net Signed-off-by: Thomas Gleixner --- include/linux/i8253.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i8253.h b/include/linux/i8253.h index d2cba88f75d6..13048d335368 100644 --- a/include/linux/i8253.h +++ b/include/linux/i8253.h @@ -2,10 +2,24 @@ * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive * for more details. + * + * Machine specific IO port address definition for generic. + * Written by Osamu Tomita */ #ifndef __LINUX_I8253_H #define __LINUX_I8253_H +#include #include +/* i8253A PIT registers */ +#define PIT_MODE 0x43 +#define PIT_CH0 0x40 +#define PIT_CH2 0x42 + +#define inb_pit inb_p +#define outb_pit outb_p + +extern raw_spinlock_t i8253_lock; + #endif /* __LINUX_I8253_H */ -- cgit v1.2.3 From 49cf3f29a1ef2e59f1be823e376c1fbac586eb8d Mon Sep 17 00:00:00 2001 From: Ralf Baechle Date: Wed, 1 Jun 2011 19:05:07 +0100 Subject: i8253: Consolidate definitions of PIT_LATCH x86 defines PIT_LATCH as LATCH which in is defined as ((CLOCK_TICK_RATE + HZ/2) / HZ) and again defines CLOCK_TICK_RATE as PIT_TICK_RATE. MIPS defines PIT_LATCH as LATCH which in is defined as ((CLOCK_TICK_RATE + HZ/2) / HZ) and again defines CLOCK_TICK_RATE as 1193182. ARM defines PITCH_LATCH as ((PIT_TICK_RATE + HZ / 2) / HZ) - and that's the sanest thing and equivalent to above definitions so use that as the new definition in . Signed-off-by: Ralf Baechle Cc: Russell King Cc: linux-arm-kernel@lists.infradead.org Cc: linux-mips@linux-mips.org Link: http://lkml.kernel.org/r/20110601180610.832810002@duck.linux-mips.net Signed-off-by: Thomas Gleixner --- include/linux/i8253.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i8253.h b/include/linux/i8253.h index 13048d335368..1ec6323a1507 100644 --- a/include/linux/i8253.h +++ b/include/linux/i8253.h @@ -9,7 +9,9 @@ #ifndef __LINUX_I8253_H #define __LINUX_I8253_H +#include #include +#include #include /* i8253A PIT registers */ @@ -17,6 +19,8 @@ #define PIT_CH0 0x40 #define PIT_CH2 0x42 +#define PIT_LATCH ((PIT_TICK_RATE + HZ/2) / HZ) + #define inb_pit inb_p #define outb_pit outb_p -- cgit v1.2.3 From 850492760cfd38d14d64a5fc6d636091464f755e Mon Sep 17 00:00:00 2001 From: Ralf Baechle Date: Wed, 1 Jun 2011 19:05:08 +0100 Subject: i8253: Move remaining content and delete asm/i8253.h Move setup_pit_timer() declaration to the common header file and remove the arch specific ones. [ tglx: Move it to linux/i8253.h instead of asm/mips and asm/x86 ] Signed-off-by: Ralf Baechle Cc: linux-arm-kernel@lists.infradead.org Cc: Russell King Cc: linux-mips@linux-mips.org Cc: Sergei Shtylyov --- include/linux/i8253.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i8253.h b/include/linux/i8253.h index 1ec6323a1507..76039c86ab58 100644 --- a/include/linux/i8253.h +++ b/include/linux/i8253.h @@ -12,7 +12,6 @@ #include #include #include -#include /* i8253A PIT registers */ #define PIT_MODE 0x43 @@ -26,4 +25,6 @@ extern raw_spinlock_t i8253_lock; +extern void setup_pit_timer(void); + #endif /* __LINUX_I8253_H */ -- cgit v1.2.3 From 3801b86aa482d26a8ae460f67fca29e016491a86 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 9 Jun 2011 16:22:22 +0100 Subject: regulator: Refactor supply implementation to work as regular consumers Currently the regulator supply implementation is somewhat complex and fragile as it doesn't look like standard consumers but is instead a parallel implementation. This causes issues with locking and reference counting. Move the implementation over to using standard consumers to address this. Rather than only notifying the supply on the first enable/disable we do so every time the regulator is enabled or disabled, simplifying locking as we don't need to hold a lock on the consumer we are about to enable. Signed-off-by: Mark Brown Signed-off-by: Liam Girdwood --- include/linux/regulator/driver.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 6c433b89c80d..1a80bc77517d 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -188,18 +188,16 @@ struct regulator_dev { /* lists we belong to */ struct list_head list; /* list of all regulators */ - struct list_head slist; /* list of supplied regulators */ /* lists we own */ struct list_head consumer_list; /* consumers we supply */ - struct list_head supply_list; /* regulators we supply */ struct blocking_notifier_head notifier; struct mutex mutex; /* consumer lock */ struct module *owner; struct device dev; struct regulation_constraints *constraints; - struct regulator_dev *supply; /* for tree */ + struct regulator *supply; /* for tree */ void *reg_data; /* regulator_dev data */ -- cgit v1.2.3 From b4c8cc88c18213688268d1d53a51d97ce2f19a64 Mon Sep 17 00:00:00 2001 From: Yegor Yefremov Date: Thu, 9 Jun 2011 15:05:48 -0700 Subject: ethtool.h: fix typos Signed-off-by: Yegor Yefremov Signed-off-by: David S. Miller --- include/linux/ethtool.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index c6a850ab2ec5..439b173c5882 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -268,7 +268,7 @@ struct ethtool_pauseparam { __u32 cmd; /* ETHTOOL_{G,S}PAUSEPARAM */ /* If the link is being auto-negotiated (via ethtool_cmd.autoneg - * being true) the user may set 'autonet' here non-zero to have the + * being true) the user may set 'autoneg' here non-zero to have the * pause parameters be auto-negotiated too. In such a case, the * {rx,tx}_pause values below determine what capabilities are * advertised. @@ -811,7 +811,7 @@ bool ethtool_invalid_flags(struct net_device *dev, u32 data, u32 supported); * @get_tx_csum: Deprecated as redundant. Report whether transmit checksums * are turned on or off. * @set_tx_csum: Deprecated in favour of generic netdev features. Turn - * transmit checksums on or off. Returns a egative error code or zero. + * transmit checksums on or off. Returns a negative error code or zero. * @get_sg: Deprecated as redundant. Report whether scatter-gather is * enabled. * @set_sg: Deprecated in favour of generic netdev features. Turn @@ -1087,7 +1087,7 @@ struct ethtool_ops { /* The following are all involved in forcing a particular link * mode for the device for setting things. When getting the * devices settings, these indicate the current mode and whether - * it was foced up into this mode or autonegotiated. + * it was forced up into this mode or autonegotiated. */ /* The forced speed, 10Mb, 100Mb, gigabit, 2.5Gb, 10GbE. */ -- cgit v1.2.3 From c7ac8679bec9397afe8918f788cbcef88c38da54 Mon Sep 17 00:00:00 2001 From: Greg Rose Date: Fri, 10 Jun 2011 01:27:09 +0000 Subject: rtnetlink: Compute and store minimum ifinfo dump size The message size allocated for rtnl ifinfo dumps was limited to a single page. This is not enough for additional interface info available with devices that support SR-IOV and caused a bug in which VF info would not be displayed if more than approximately 40 VFs were created per interface. Implement a new function pointer for the rtnl_register service that will calculate the amount of data required for the ifinfo dump and allocate enough data to satisfy the request. Signed-off-by: Greg Rose Signed-off-by: Jeff Kirsher --- include/linux/netlink.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index a9dd89552f9c..fdd0188a167e 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -221,7 +221,8 @@ struct netlink_callback { int (*dump)(struct sk_buff * skb, struct netlink_callback *cb); int (*done)(struct netlink_callback *cb); - int family; + u16 family; + u16 min_dump_alloc; long args[6]; }; @@ -259,7 +260,8 @@ __nlmsg_put(struct sk_buff *skb, u32 pid, u32 seq, int type, int len, int flags) extern int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, const struct nlmsghdr *nlh, int (*dump)(struct sk_buff *skb, struct netlink_callback*), - int (*done)(struct netlink_callback*)); + int (*done)(struct netlink_callback*), + u16 min_dump_alloc); #define NL_NONROOT_RECV 0x1 -- cgit v1.2.3 From 28f65c11f2ffb3957259dece647a24f8ad2e241b Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Thu, 9 Jun 2011 09:13:32 -0700 Subject: treewide: Convert uses of struct resource to resource_size(ptr) Several fixes as well where the +1 was missing. Done via coccinelle scripts like: @@ struct resource *ptr; @@ - ptr->end - ptr->start + 1 + resource_size(ptr) and some grep and typing. Mostly uncompiled, no cross-compilers. Signed-off-by: Joe Perches Signed-off-by: Jiri Kosina --- include/linux/dio.h | 2 +- include/linux/pnp.h | 2 +- include/linux/zorro.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dio.h b/include/linux/dio.h index b2dd31ca1710..2cc0fd00463f 100644 --- a/include/linux/dio.h +++ b/include/linux/dio.h @@ -254,7 +254,7 @@ static inline struct dio_driver *dio_dev_driver(const struct dio_dev *d) #define dio_resource_start(d) ((d)->resource.start) #define dio_resource_end(d) ((d)->resource.end) -#define dio_resource_len(d) ((d)->resource.end-(d)->resource.start+1) +#define dio_resource_len(d) (resource_size(&(d)->resource)) #define dio_resource_flags(d) ((d)->resource.flags) #define dio_request_device(d, name) \ diff --git a/include/linux/pnp.h b/include/linux/pnp.h index 1bc1338b817b..195aafc6cd07 100644 --- a/include/linux/pnp.h +++ b/include/linux/pnp.h @@ -50,7 +50,7 @@ static inline resource_size_t pnp_resource_len(struct resource *res) { if (res->start == 0 && res->end == 0) return 0; - return res->end - res->start + 1; + return resource_size(res); } diff --git a/include/linux/zorro.h b/include/linux/zorro.h index 7bf9db525e9e..dff42025649b 100644 --- a/include/linux/zorro.h +++ b/include/linux/zorro.h @@ -187,7 +187,7 @@ extern struct zorro_dev *zorro_find_device(zorro_id id, #define zorro_resource_start(z) ((z)->resource.start) #define zorro_resource_end(z) ((z)->resource.end) -#define zorro_resource_len(z) ((z)->resource.end-(z)->resource.start+1) +#define zorro_resource_len(z) (resource_size(&(z)->resource)) #define zorro_resource_flags(z) ((z)->resource.flags) #define zorro_request_device(z, name) \ -- cgit v1.2.3 From bdd4e85dc36cdbcfc1608a5b2a17c80a9db8986a Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 8 Jun 2011 01:13:27 +0200 Subject: sched: Isolate preempt counting in its own config option Create a new CONFIG_PREEMPT_COUNT that handles the inc/dec of preempt count offset independently. So that the offset can be updated by preempt_disable() and preempt_enable() even without the need for CONFIG_PREEMPT beeing set. This prepares to make CONFIG_DEBUG_SPINLOCK_SLEEP working with !CONFIG_PREEMPT where it currently doesn't detect code that sleeps inside explicit preemption disabled sections. Signed-off-by: Frederic Weisbecker Acked-by: Paul E. McKenney Cc: Ingo Molnar Cc: Peter Zijlstra --- include/linux/bit_spinlock.h | 2 +- include/linux/hardirq.h | 4 ++-- include/linux/pagemap.h | 4 ++-- include/linux/preempt.h | 26 +++++++++++++++++--------- include/linux/rcupdate.h | 12 ++++++------ include/linux/sched.h | 2 +- 6 files changed, 29 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bit_spinlock.h b/include/linux/bit_spinlock.h index b4326bfa684f..564d997e2168 100644 --- a/include/linux/bit_spinlock.h +++ b/include/linux/bit_spinlock.h @@ -88,7 +88,7 @@ static inline int bit_spin_is_locked(int bitnum, unsigned long *addr) { #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) return test_bit(bitnum, addr); -#elif defined CONFIG_PREEMPT +#elif defined CONFIG_PREEMPT_COUNT return preempt_count(); #else return 1; diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index ba362171e8ae..f743883f769e 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -93,7 +93,7 @@ */ #define in_nmi() (preempt_count() & NMI_MASK) -#if defined(CONFIG_PREEMPT) +#if defined(CONFIG_PREEMPT_COUNT) # define PREEMPT_CHECK_OFFSET 1 #else # define PREEMPT_CHECK_OFFSET 0 @@ -115,7 +115,7 @@ #define in_atomic_preempt_off() \ ((preempt_count() & ~PREEMPT_ACTIVE) != PREEMPT_CHECK_OFFSET) -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPT_COUNT # define preemptible() (preempt_count() == 0 && !irqs_disabled()) # define IRQ_EXIT_OFFSET (HARDIRQ_OFFSET-1) #else diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 716875e53520..8e38d4c140ff 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -134,7 +134,7 @@ static inline int page_cache_get_speculative(struct page *page) VM_BUG_ON(in_interrupt()); #if !defined(CONFIG_SMP) && defined(CONFIG_TREE_RCU) -# ifdef CONFIG_PREEMPT +# ifdef CONFIG_PREEMPT_COUNT VM_BUG_ON(!in_atomic()); # endif /* @@ -172,7 +172,7 @@ static inline int page_cache_add_speculative(struct page *page, int count) VM_BUG_ON(in_interrupt()); #if !defined(CONFIG_SMP) && defined(CONFIG_TREE_RCU) -# ifdef CONFIG_PREEMPT +# ifdef CONFIG_PREEMPT_COUNT VM_BUG_ON(!in_atomic()); # endif VM_BUG_ON(page_count(page) == 0); diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 2e681d9555bd..58969b2a8a82 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -27,6 +27,21 @@ asmlinkage void preempt_schedule(void); +#define preempt_check_resched() \ +do { \ + if (unlikely(test_thread_flag(TIF_NEED_RESCHED))) \ + preempt_schedule(); \ +} while (0) + +#else /* !CONFIG_PREEMPT */ + +#define preempt_check_resched() do { } while (0) + +#endif /* CONFIG_PREEMPT */ + + +#ifdef CONFIG_PREEMPT_COUNT + #define preempt_disable() \ do { \ inc_preempt_count(); \ @@ -39,12 +54,6 @@ do { \ dec_preempt_count(); \ } while (0) -#define preempt_check_resched() \ -do { \ - if (unlikely(test_thread_flag(TIF_NEED_RESCHED))) \ - preempt_schedule(); \ -} while (0) - #define preempt_enable() \ do { \ preempt_enable_no_resched(); \ @@ -80,18 +89,17 @@ do { \ preempt_check_resched(); \ } while (0) -#else +#else /* !CONFIG_PREEMPT_COUNT */ #define preempt_disable() do { } while (0) #define preempt_enable_no_resched() do { } while (0) #define preempt_enable() do { } while (0) -#define preempt_check_resched() do { } while (0) #define preempt_disable_notrace() do { } while (0) #define preempt_enable_no_resched_notrace() do { } while (0) #define preempt_enable_notrace() do { } while (0) -#endif +#endif /* CONFIG_PREEMPT_COUNT */ #ifdef CONFIG_PREEMPT_NOTIFIERS diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 99f9aa7c2804..8f4f881a0ad8 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -239,7 +239,7 @@ extern int rcu_read_lock_bh_held(void); * Check debug_lockdep_rcu_enabled() to prevent false positives during boot * and while lockdep is disabled. */ -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPT_COUNT static inline int rcu_read_lock_sched_held(void) { int lockdep_opinion = 0; @@ -250,12 +250,12 @@ static inline int rcu_read_lock_sched_held(void) lockdep_opinion = lock_is_held(&rcu_sched_lock_map); return lockdep_opinion || preempt_count() != 0 || irqs_disabled(); } -#else /* #ifdef CONFIG_PREEMPT */ +#else /* #ifdef CONFIG_PREEMPT_COUNT */ static inline int rcu_read_lock_sched_held(void) { return 1; } -#endif /* #else #ifdef CONFIG_PREEMPT */ +#endif /* #else #ifdef CONFIG_PREEMPT_COUNT */ #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ @@ -276,17 +276,17 @@ static inline int rcu_read_lock_bh_held(void) return 1; } -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPT_COUNT static inline int rcu_read_lock_sched_held(void) { return preempt_count() != 0 || irqs_disabled(); } -#else /* #ifdef CONFIG_PREEMPT */ +#else /* #ifdef CONFIG_PREEMPT_COUNT */ static inline int rcu_read_lock_sched_held(void) { return 1; } -#endif /* #else #ifdef CONFIG_PREEMPT */ +#endif /* #else #ifdef CONFIG_PREEMPT_COUNT */ #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 483c1ed5bc4d..4ecd5cbe7e24 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2502,7 +2502,7 @@ extern int _cond_resched(void); extern int __cond_resched_lock(spinlock_t *lock); -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPT_COUNT #define PREEMPT_LOCK_OFFSET PREEMPT_OFFSET #else #define PREEMPT_LOCK_OFFSET 0 -- cgit v1.2.3 From e5ea3f12d41d96edf4ad9374db2b1725e457acec Mon Sep 17 00:00:00 2001 From: Jamie Iles Date: Fri, 10 Jun 2011 13:44:49 +0100 Subject: gpio/basic_mmio: add missing include of spinlock_types.h include/linux/basic_mmio_gpio.h uses a spinlock_t without including any of the spinlock headers resulting in this compiler warning. include/linux/basic_mmio_gpio.h:51:2: error: expected specifier-qualifier-list before 'spinlock_t' Explicitly include linux/spinlock_types.h to fix it. Signed-off-by: Jamie Iles Signed-off-by: Grant Likely --- include/linux/basic_mmio_gpio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/basic_mmio_gpio.h b/include/linux/basic_mmio_gpio.h index 1ae12710d732..98999cf107ce 100644 --- a/include/linux/basic_mmio_gpio.h +++ b/include/linux/basic_mmio_gpio.h @@ -16,6 +16,7 @@ #include #include #include +#include struct bgpio_pdata { int base; -- cgit v1.2.3 From e3ae0cac00042d7fb76914c30c5f991f918e65b4 Mon Sep 17 00:00:00 2001 From: Arend van Spriel Date: Thu, 9 Jun 2011 20:07:20 +0200 Subject: drivers: bcma: export bcma_core_disable() function In the brcm80211 driver we disable the 80211 core when the driver is 'down'. The bcma_core_disable() function exactly does the same as our implementation so exporting this function makes sense. Cc: linux-wireless@vger.kernel.org Cc: Rafal Milecki Signed-off-by: Arend van Spriel Signed-off-by: John W. Linville --- include/linux/bcma/bcma.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index 6ff080eac0b2..3895aeb494a3 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -244,6 +244,7 @@ void bcma_awrite32(struct bcma_device *core, u16 offset, u32 value) } extern bool bcma_core_is_enabled(struct bcma_device *core); +extern void bcma_core_disable(struct bcma_device *core, u32 flags); extern int bcma_core_enable(struct bcma_device *core, u32 flags); #endif /* LINUX_BCMA_H_ */ -- cgit v1.2.3 From 56a210526adb2854d5b7c398a40260720390ee05 Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 11 Jun 2011 12:29:58 +0100 Subject: linux/seqlock.h should #include asm/processor.h for cpu_relax() It uses cpu_relax(), and so needs Without this patch, I see: CC arch/mn10300/kernel/asm-offsets.s In file included from include/linux/time.h:8, from include/linux/timex.h:56, from include/linux/sched.h:57, from arch/mn10300/kernel/asm-offsets.c:7: include/linux/seqlock.h: In function 'read_seqbegin': include/linux/seqlock.h:91: error: implicit declaration of function 'cpu_relax' whilst building asb2364_defconfig on MN10300. Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- include/linux/seqlock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index e9811892844f..c6db9fb33c44 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -28,6 +28,7 @@ #include #include +#include typedef struct { unsigned sequence; -- cgit v1.2.3 From 10a8d94a95742bb15b4e617ee9884bb4381362be Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 10 Jun 2011 00:56:17 +0000 Subject: virtio_net: introduce VIRTIO_NET_HDR_F_DATA_VALID There's no need for the guest to validate the checksum if it have been validated by host nics. So this patch introduces a new flag - VIRTIO_NET_HDR_F_DATA_VALID which is used to bypass the checksum examing in guest. The backend (tap/macvtap) may set this flag when met skbs with CHECKSUM_UNNECESSARY to save cpu utilization. No feature negotiation is needed as old driver just ignore this flag. Iperf shows 12%-30% performance improvement for UDP traffic. For TCP, when gro is on no difference as it produces skb with partial checksum. But when gro is disabled, 20% or even higher improvement could be measured by netperf. Signed-off-by: Jason Wang Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- include/linux/virtio_net.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 136040bba3e3..970d5a2a9047 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -63,6 +63,7 @@ struct virtio_net_config { * specify GSO or CSUM features, you can simply ignore the header. */ struct virtio_net_hdr { #define VIRTIO_NET_HDR_F_NEEDS_CSUM 1 // Use csum_start, csum_offset +#define VIRTIO_NET_HDR_F_DATA_VALID 2 // Csum is valid __u8 flags; #define VIRTIO_NET_HDR_GSO_NONE 0 // Not a GSO frame #define VIRTIO_NET_HDR_GSO_TCPV4 1 // GSO frame, IPv4 TCP (TSO) -- cgit v1.2.3 From 0b5c9db1b11d3175bb42b80663a9f072f801edf5 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 10 Jun 2011 06:56:58 +0000 Subject: vlan: Fix the ingress VLAN_FLAG_REORDER_HDR check Testing of VLAN_FLAG_REORDER_HDR does not belong in vlan_untag but rather in vlan_do_receive. Otherwise the vlan header will not be properly put on the packet in the case of vlan header accelleration. As we remove the check from vlan_check_reorder_header rename it vlan_reorder_header to keep the naming clean. Fix up the skb->pkt_type early so we don't look at the packet after adding the vlan tag, which guarantees we don't goof and look at the wrong field. Use a simple if statement instead of a complicated switch statement to decided that we need to increment rx_stats for a multicast packet. Hopefully at somepoint we will just declare the case where VLAN_FLAG_REORDER_HDR is cleared as unsupported and remove the code. Until then this keeps it working correctly. Signed-off-by: Eric W. Biederman Signed-off-by: Jiri Pirko Acked-by: Changli Gao Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 25 ++++++++++++++++++++++--- include/linux/skbuff.h | 5 +++++ 2 files changed, 27 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index dc01681fbb42..affa27380b72 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -225,7 +225,7 @@ static inline int vlan_hwaccel_receive_skb(struct sk_buff *skb, } /** - * __vlan_put_tag - regular VLAN tag inserting + * vlan_insert_tag - regular VLAN tag inserting * @skb: skbuff to tag * @vlan_tci: VLAN TCI to insert * @@ -234,8 +234,10 @@ static inline int vlan_hwaccel_receive_skb(struct sk_buff *skb, * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. + * + * Does not change skb->protocol so this function can be used during receive. */ -static inline struct sk_buff *__vlan_put_tag(struct sk_buff *skb, u16 vlan_tci) +static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, u16 vlan_tci) { struct vlan_ethhdr *veth; @@ -255,8 +257,25 @@ static inline struct sk_buff *__vlan_put_tag(struct sk_buff *skb, u16 vlan_tci) /* now, the TCI */ veth->h_vlan_TCI = htons(vlan_tci); - skb->protocol = htons(ETH_P_8021Q); + return skb; +} +/** + * __vlan_put_tag - regular VLAN tag inserting + * @skb: skbuff to tag + * @vlan_tci: VLAN TCI to insert + * + * Inserts the VLAN tag into @skb as part of the payload + * Returns a VLAN tagged skb. If a new skb is created, @skb is freed. + * + * Following the skb_unshare() example, in case of error, the calling function + * doesn't have to worry about freeing the original skb. + */ +static inline struct sk_buff *__vlan_put_tag(struct sk_buff *skb, u16 vlan_tci) +{ + skb = vlan_insert_tag(skb, vlan_tci); + if (skb) + skb->protocol = htons(ETH_P_8021Q); return skb; } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index e8b78ce14474..c0a4f3ab0cc0 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1256,6 +1256,11 @@ static inline void skb_reserve(struct sk_buff *skb, int len) skb->tail += len; } +static inline void skb_reset_mac_len(struct sk_buff *skb) +{ + skb->mac_len = skb->network_header - skb->mac_header; +} + #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_transport_header(const struct sk_buff *skb) { -- cgit v1.2.3 From a685e08987d1edf1995b76511d4c98ea0e905377 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 8 Jun 2011 21:13:01 -0400 Subject: Delay struct net freeing while there's a sysfs instance refering to it * new refcount in struct net, controlling actual freeing of the memory * new method in kobj_ns_type_operations (->drop_ns()) * ->current_ns() semantics change - it's supposed to be followed by corresponding ->drop_ns(). For struct net in case of CONFIG_NET_NS it bumps the new refcount; net_drop_ns() decrements it and calls net_free() if the last reference has been dropped. Method renamed to ->grab_current_ns(). * old net_free() callers call net_drop_ns() instead. * sysfs_exit_ns() is gone, along with a large part of callchain leading to it; now that the references stored in ->ns[...] stay valid we do not need to hunt them down and replace them with NULL. That fixes problems in sysfs_lookup() and sysfs_readdir(), along with getting rid of sb->s_instances abuse. Note that struct net *shutdown* logics has not changed - net_cleanup() is called exactly when it used to be called. The only thing postponed by having a sysfs instance refering to that struct net is actual freeing of memory occupied by struct net. Signed-off-by: Al Viro --- include/linux/kobject_ns.h | 10 ++++++---- include/linux/sysfs.h | 7 ------- 2 files changed, 6 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kobject_ns.h b/include/linux/kobject_ns.h index 82cb5bf461fb..f66b065a8b5f 100644 --- a/include/linux/kobject_ns.h +++ b/include/linux/kobject_ns.h @@ -32,15 +32,17 @@ enum kobj_ns_type { /* * Callbacks so sysfs can determine namespaces - * @current_ns: return calling task's namespace + * @grab_current_ns: return a new reference to calling task's namespace * @netlink_ns: return namespace to which a sock belongs (right?) * @initial_ns: return the initial namespace (i.e. init_net_ns) + * @drop_ns: drops a reference to namespace */ struct kobj_ns_type_operations { enum kobj_ns_type type; - const void *(*current_ns)(void); + void *(*grab_current_ns)(void); const void *(*netlink_ns)(struct sock *sk); const void *(*initial_ns)(void); + void (*drop_ns)(void *); }; int kobj_ns_type_register(const struct kobj_ns_type_operations *ops); @@ -48,9 +50,9 @@ int kobj_ns_type_registered(enum kobj_ns_type type); const struct kobj_ns_type_operations *kobj_child_ns_ops(struct kobject *parent); const struct kobj_ns_type_operations *kobj_ns_ops(struct kobject *kobj); -const void *kobj_ns_current(enum kobj_ns_type type); +void *kobj_ns_grab_current(enum kobj_ns_type type); const void *kobj_ns_netlink(enum kobj_ns_type type, struct sock *sk); const void *kobj_ns_initial(enum kobj_ns_type type); -void kobj_ns_exit(enum kobj_ns_type type, const void *ns); +void kobj_ns_drop(enum kobj_ns_type type, void *ns); #endif /* _LINUX_KOBJECT_NS_H */ diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index c3acda60eee0..e2696d76a599 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -177,9 +177,6 @@ struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd, struct sysfs_dirent *sysfs_get(struct sysfs_dirent *sd); void sysfs_put(struct sysfs_dirent *sd); -/* Called to clear a ns tag when it is no longer valid */ -void sysfs_exit_ns(enum kobj_ns_type type, const void *tag); - int __must_check sysfs_init(void); #else /* CONFIG_SYSFS */ @@ -338,10 +335,6 @@ static inline void sysfs_put(struct sysfs_dirent *sd) { } -static inline void sysfs_exit_ns(int type, const void *tag) -{ -} - static inline int __must_check sysfs_init(void) { return 0; -- cgit v1.2.3 From 08e8138adebdd511e0955e8d6c051904bb4082af Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 13 Jun 2011 10:42:49 +0200 Subject: block: Add __attribute__((format(printf...) and fix fallout Use the compiler to verify format strings and arguments. Fix fallout. Signed-off-by: Joe Perches Signed-off-by: Jens Axboe --- include/linux/blktrace_api.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index b22fb0d3db0f..8c7c2de7631a 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -169,7 +169,8 @@ extern void blk_trace_shutdown(struct request_queue *); extern int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, struct block_device *bdev, struct blk_user_trace_setup *buts); -extern void __trace_note_message(struct blk_trace *, const char *fmt, ...); +extern __attribute__((format(printf, 2, 3))) +void __trace_note_message(struct blk_trace *, const char *fmt, ...); /** * blk_add_trace_msg - Add a (simple) message to the blktrace stream -- cgit v1.2.3 From 4d0d98b60eba726e0a4f3e6617628b070c444707 Mon Sep 17 00:00:00 2001 From: Wanlong Gao Date: Mon, 13 Jun 2011 10:45:38 +0200 Subject: block:fix the comment error in blkdev.h There is not a function rq_init but blk_rq_init in block/blk-core.c. Signed-off-by: Wanlong Gao Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ae9091a68480..4ce6e68da2bd 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -73,7 +73,7 @@ enum rq_cmd_type_bits { /* * try to put the fields that are referenced together in the same cacheline. - * if you modify this structure, be sure to check block/blk-core.c:rq_init() + * if you modify this structure, be sure to check block/blk-core.c:blk_rq_init() * as well! */ struct request { -- cgit v1.2.3 From fd16d263194aa6b50b215eb593a567b59d744d6e Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 13 Jun 2011 10:42:49 +0200 Subject: block: Add __attribute__((format(printf...) and fix fallout Use the compiler to verify format strings and arguments. Fix fallout. Signed-off-by: Joe Perches Signed-off-by: Jens Axboe --- include/linux/blktrace_api.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index b22fb0d3db0f..8c7c2de7631a 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -169,7 +169,8 @@ extern void blk_trace_shutdown(struct request_queue *); extern int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, struct block_device *bdev, struct blk_user_trace_setup *buts); -extern void __trace_note_message(struct blk_trace *, const char *fmt, ...); +extern __attribute__((format(printf, 2, 3))) +void __trace_note_message(struct blk_trace *, const char *fmt, ...); /** * blk_add_trace_msg - Add a (simple) message to the blktrace stream -- cgit v1.2.3 From de1b794130b130e77ffa975bb58cb843744f9ae5 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 13 Jun 2011 15:38:22 -0400 Subject: jbd2: Fix oops in jbd2_journal_remove_journal_head() jbd2_journal_remove_journal_head() can oops when trying to access journal_head returned by bh2jh(). This is caused for example by the following race: TASK1 TASK2 jbd2_journal_commit_transaction() ... processing t_forget list __jbd2_journal_refile_buffer(jh); if (!jh->b_transaction) { jbd_unlock_bh_state(bh); jbd2_journal_try_to_free_buffers() jbd2_journal_grab_journal_head(bh) jbd_lock_bh_state(bh) __journal_try_to_free_buffer() jbd2_journal_put_journal_head(jh) jbd2_journal_remove_journal_head(bh); jbd2_journal_put_journal_head() in TASK2 sees that b_jcount == 0 and buffer is not part of any transaction and thus frees journal_head before TASK1 gets to doing so. Note that even buffer_head can be released by try_to_free_buffers() after jbd2_journal_put_journal_head() which adds even larger opportunity for oops (but I didn't see this happen in reality). Fix the problem by making transactions hold their own journal_head reference (in b_jcount). That way we don't have to remove journal_head explicitely via jbd2_journal_remove_journal_head() and instead just remove journal_head when b_jcount drops to zero. The result of this is that [__]jbd2_journal_refile_buffer(), [__]jbd2_journal_unfile_buffer(), and __jdb2_journal_remove_checkpoint() can free journal_head which needs modification of a few callers. Also we have to be careful because once journal_head is removed, buffer_head might be freed as well. So we have to get our own buffer_head reference where it matters. Signed-off-by: Jan Kara Signed-off-by: "Theodore Ts'o" --- include/linux/jbd2.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 4ecb7b16b278..d087c2e7b2aa 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1024,7 +1024,6 @@ struct journal_s /* Filing buffers */ extern void jbd2_journal_unfile_buffer(journal_t *, struct journal_head *); -extern void __jbd2_journal_unfile_buffer(struct journal_head *); extern void __jbd2_journal_refile_buffer(struct journal_head *); extern void jbd2_journal_refile_buffer(journal_t *, struct journal_head *); extern void __jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); @@ -1165,7 +1164,6 @@ extern void jbd2_journal_release_jbd_inode(journal_t *journal, struct jbd2_in */ struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh); struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh); -void jbd2_journal_remove_journal_head(struct buffer_head *bh); void jbd2_journal_put_journal_head(struct journal_head *jh); /* -- cgit v1.2.3 From 61a6976bf19a6cf5dfcf37c3536665b316f22d49 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Tue, 14 Jun 2011 12:40:19 +0900 Subject: serial: sh-sci: Abstract register maps. This takes a bit of a sledgehammer to the horribly CPU subtype ifdef-ridden header and abstracts all of the different register layouts in to distinct types which in turn can be overriden on a per-port basis, or permitted to default to the map matching the port type at probe time. In the process this ultimately fixes up inumerable bugs with mismatches on various CPU types (particularly the legacy ones that were obviously broken years ago and no one noticed) and provides a more tightly coupled and consolidated platform for extending and implementing generic features. Signed-off-by: Paul Mundt --- include/linux/serial_sci.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_sci.h b/include/linux/serial_sci.h index ecefec7c0b67..4ca130a90ea5 100644 --- a/include/linux/serial_sci.h +++ b/include/linux/serial_sci.h @@ -58,6 +58,22 @@ enum { SCIx_NR_IRQS, }; +enum { + SCIx_PROBE_REGTYPE, + + SCIx_SCI_REGTYPE, + SCIx_IRDA_REGTYPE, + SCIx_SCIFA_REGTYPE, + SCIx_SCIFB_REGTYPE, + SCIx_SH3_SCIF_REGTYPE, + SCIx_SH4_SCIF_REGTYPE, + SCIx_SH4_SCIF_NO_SCSPTR_REGTYPE, + SCIx_SH4_SCIF_FIFODATA_REGTYPE, + SCIx_SH7705_SCIF_REGTYPE, + + SCIx_NR_REGTYPES, +}; + #define SCIx_IRQ_MUXED(irq) \ { \ [SCIx_ERI_IRQ] = (irq), \ @@ -66,8 +82,24 @@ enum { [SCIx_BRI_IRQ] = (irq), \ } +/* + * SCI register subset common for all port types. + * Not all registers will exist on all parts. + */ +enum { + SCSMR, SCBRR, SCSCR, SCxSR, + SCFCR, SCFDR, SCxTDR, SCxRDR, + SCLSR, SCTFDR, SCRFDR, SCSPTR, + + SCIx_NR_REGS, +}; + struct device; +struct plat_sci_port_ops { + void (*init_pins)(struct uart_port *, unsigned int cflag); +}; + /* * Platform device specific platform_data struct */ @@ -87,6 +119,10 @@ struct plat_sci_port { unsigned int error_mask; int port_reg; + unsigned char regshift; + unsigned char regtype; + + struct plat_sci_port_ops *ops; struct device *dma_dev; -- cgit v1.2.3 From 55309216baeb9d7f951520cf8e8bf2337cd17bad Mon Sep 17 00:00:00 2001 From: Harry Butterworth Date: Sat, 11 Jun 2011 16:02:06 +0800 Subject: ALSA: ctxfi: Add support for Creative Titanium HD Initialise model-specific DAC and ADC parts. Add controls for output and mic source selection. Rename some mixer controls according to ControlNames.txt. Remove Playback switches for Line-in and IEC958-in - these were controlling the input mute/unmute which affected capture too. Use the capture switches to control the input mute/unmute instead - it's less confusing. Initialise the WM8775 to invert the left-right clock to swap the left and right channels of the mic and aux input. Signed-off-by: Harry Butterworth Signed-off-by: Takashi Iwai --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index a311008af5e1..f23f8bf02b04 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1308,6 +1308,7 @@ #define PCI_SUBDEVICE_ID_CREATIVE_SB08801 0x0041 #define PCI_SUBDEVICE_ID_CREATIVE_SB08802 0x0042 #define PCI_SUBDEVICE_ID_CREATIVE_SB08803 0x0043 +#define PCI_SUBDEVICE_ID_CREATIVE_SB1270 0x0062 #define PCI_SUBDEVICE_ID_CREATIVE_HENDRIX 0x6000 #define PCI_VENDOR_ID_ECTIVA 0x1102 /* duplicate: CREATIVE */ -- cgit v1.2.3 From 74315cccd2104a953f493acca2c6b0519d6f5c6f Mon Sep 17 00:00:00 2001 From: Laura Abbott Date: Wed, 8 Jun 2011 17:29:11 -0400 Subject: iommu-api: Add missing header file If CONFIG_IOMMU_API is not defined some functions will just return -ENODEV. Add errno.h for the definition of ENODEV. Signed-off-by: Laura Abbott Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 0a2ba4098996..9940319d6f9d 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -19,6 +19,8 @@ #ifndef __LINUX_IOMMU_H #define __LINUX_IOMMU_H +#include + #define IOMMU_READ (1) #define IOMMU_WRITE (2) #define IOMMU_CACHE (4) /* DMA cache coherency */ -- cgit v1.2.3 From 09223371deac67d08ca0b70bd18787920284c967 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Tue, 14 Jun 2011 13:26:25 +0800 Subject: rcu: Use softirq to address performance regression Commit a26ac2455ffcf3(rcu: move TREE_RCU from softirq to kthread) introduced performance regression. In an AIM7 test, this commit degraded performance by about 40%. The commit runs rcu callbacks in a kthread instead of softirq. We observed high rate of context switch which is caused by this. Out test system has 64 CPUs and HZ is 1000, so we saw more than 64k context switch per second which is caused by RCU's per-CPU kthread. A trace showed that most of the time the RCU per-CPU kthread doesn't actually handle any callbacks, but instead just does a very small amount of work handling grace periods. This means that RCU's per-CPU kthreads are making the scheduler do quite a bit of work in order to allow a very small amount of RCU-related processing to be done. Alex Shi's analysis determined that this slowdown is due to lock contention within the scheduler. Unfortunately, as Peter Zijlstra points out, the scheduler's real-time semantics require global action, which means that this contention is inherent in real-time scheduling. (Yes, perhaps someone will come up with a workaround -- otherwise, -rt is not going to do well on large SMP systems -- but this patch will work around this issue in the meantime. And "the meantime" might well be forever.) This patch therefore re-introduces softirq processing to RCU, but only for core RCU work. RCU callbacks are still executed in kthread context, so that only a small amount of RCU work runs in softirq context in the common case. This should minimize ksoftirqd execution, allowing us to skip boosting of ksoftirqd for CONFIG_RCU_BOOST=y kernels. Signed-off-by: Shaohua Li Tested-by: "Alex,Shi" Signed-off-by: Paul E. McKenney --- include/linux/interrupt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 6c12989839d9..f6efed0039ed 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -414,6 +414,7 @@ enum TASKLET_SOFTIRQ, SCHED_SOFTIRQ, HRTIMER_SOFTIRQ, + RCU_SOFTIRQ, /* Preferable RCU should always be the last softirq */ NR_SOFTIRQS }; -- cgit v1.2.3 From 7ea5906405a1f3fc1c0033dfd7e02f2cfd1de5e5 Mon Sep 17 00:00:00 2001 From: Vaibhav Nagarnaik Date: Tue, 3 May 2011 17:56:42 -0700 Subject: tracing: Use NUMA allocation for per-cpu ring buffer pages The tracing ring buffer is a group of per-cpu ring buffers where allocation and logging is done on a per-cpu basis. The events that are generated on a particular CPU are logged in the corresponding buffer. This is to provide wait-free writes between CPUs and good NUMA node locality while accessing the ring buffer. However, the allocation routines consider NUMA locality only for buffer page metadata and not for the actual buffer page. This causes the pages to be allocated on the NUMA node local to the CPU where the allocation routine is running at the time. This patch fixes the problem by using a NUMA node specific allocation routine so that the pages are allocated from a NUMA node local to the logging CPU. I tested with the getuid_microbench from autotest. It is a simple binary that calls getuid() in a loop and measures the average time for the syscall to complete. The following command was used to test: $ getuid_microbench 1000000 Compared the numbers found on kernel with and without this patch and found that logging latency decreases by 30-50 ns/call. tracing with non-NUMA allocation - 569 ns/call tracing with NUMA allocation - 512 ns/call Signed-off-by: Vaibhav Nagarnaik Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Michael Rubin Cc: David Sharp Link: http://lkml.kernel.org/r/1304470602-20366-1-git-send-email-vnagarnaik@google.com Signed-off-by: Steven Rostedt --- include/linux/ring_buffer.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index ab38ac80b0f9..b891de96000f 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -169,7 +169,7 @@ void ring_buffer_set_clock(struct ring_buffer *buffer, size_t ring_buffer_page_len(void *page); -void *ring_buffer_alloc_read_page(struct ring_buffer *buffer); +void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu); void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data); int ring_buffer_read_page(struct ring_buffer *buffer, void **data_page, size_t len, int cpu, int full); -- cgit v1.2.3 From 395810627b6a43c8d0ec948884043946fa162308 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 8 Jun 2011 16:09:21 +0900 Subject: x86: Swap save_stack_trace_regs parameters Swap the 1st and 2nd parameters of save_stack_trace_regs() as same as the parameters of save_stack_trace_tsk(). Signed-off-by: Masami Hiramatsu Cc: yrl.pp-manager.tt@hitachi.com Cc: Frederic Weisbecker Cc: Peter Zijlstra Cc: Namhyung Kim Link: http://lkml.kernel.org/r/20110608070921.17777.31103.stgit@fedora15 Signed-off-by: Steven Rostedt --- include/linux/stacktrace.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h index 25310f1d7f37..115b570e3bff 100644 --- a/include/linux/stacktrace.h +++ b/include/linux/stacktrace.h @@ -14,8 +14,8 @@ struct stack_trace { }; extern void save_stack_trace(struct stack_trace *trace); -extern void save_stack_trace_regs(struct stack_trace *trace, - struct pt_regs *regs); +extern void save_stack_trace_regs(struct pt_regs *regs, + struct stack_trace *trace); extern void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace); -- cgit v1.2.3 From 1fd8df2c3970c9e7e4e262354154ee39e58bdd7c Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 8 Jun 2011 16:09:34 +0900 Subject: tracing/kprobes: Fix kprobe-tracer to support stack trace Fix to support kernel stack trace correctly on kprobe-tracer. Since the execution path of kprobe-based dynamic events is different from other tracepoint-based events, normal ftrace_trace_stack() doesn't work correctly. To fix that, this introduces ftrace_trace_stack_regs() which traces stack via pt_regs instead of current stack register. e.g. # echo p schedule+4 > /sys/kernel/debug/tracing/kprobe_events # echo 1 > /sys/kernel/debug/tracing/options/stacktrace # echo 1 > /sys/kernel/debug/tracing/events/kprobes/enable # head -n 20 /sys/kernel/debug/tracing/trace bash-2968 [000] 10297.050245: p_schedule_4: (schedule+0x4/0x4ca) bash-2968 [000] 10297.050247: => schedule_timeout => n_tty_read => tty_read => vfs_read => sys_read => system_call_fastpath kworker/0:1-2940 [000] 10297.050265: p_schedule_4: (schedule+0x4/0x4ca) kworker/0:1-2940 [000] 10297.050266: => worker_thread => kthread => kernel_thread_helper sshd-1132 [000] 10297.050365: p_schedule_4: (schedule+0x4/0x4ca) sshd-1132 [000] 10297.050365: => sysret_careful Note: Even with this fix, the first entry will be skipped if the probe is put on the function entry area before the frame pointer is set up (usually, that is 4 bytes (push %bp; mov %sp %bp) on x86), because stack unwinder depends on the frame pointer. Signed-off-by: Masami Hiramatsu Cc: Frederic Weisbecker Cc: yrl.pp-manager.tt@hitachi.com Cc: Peter Zijlstra Cc: Namhyung Kim Link: http://lkml.kernel.org/r/20110608070934.17777.17116.stgit@fedora15 Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 59d3ef100eb9..b1e69eefc203 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -129,6 +129,10 @@ void trace_current_buffer_unlock_commit(struct ring_buffer *buffer, void trace_nowake_buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event, unsigned long flags, int pc); +void trace_nowake_buffer_unlock_commit_regs(struct ring_buffer *buffer, + struct ring_buffer_event *event, + unsigned long flags, int pc, + struct pt_regs *regs); void trace_current_buffer_discard_commit(struct ring_buffer *buffer, struct ring_buffer_event *event); -- cgit v1.2.3 From 221c56373ee7088dd3015b928782d5e70dc5074e Mon Sep 17 00:00:00 2001 From: Matt Carlson Date: Mon, 13 Jun 2011 13:39:01 +0000 Subject: tg3: Migrate phy preprocessor defs to system defs This patch changes to code to use some of the preprocessor definitions from mii.h over its homegrown equivalents. Signed-off-by: Matt Carlson Reviewed-by: Michael Chan Reviewed-by: Benjamin Li Signed-off-by: David S. Miller --- include/linux/mii.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mii.h b/include/linux/mii.h index 359fba880274..103113a2fd18 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -128,6 +128,8 @@ /* 1000BASE-T Control register */ #define ADVERTISE_1000FULL 0x0200 /* Advertise 1000BASE-T full duplex */ #define ADVERTISE_1000HALF 0x0100 /* Advertise 1000BASE-T half duplex */ +#define CTL1000_AS_MASTER 0x0800 +#define CTL1000_ENABLE_MASTER 0x1000 /* 1000BASE-T Status register */ #define LPA_1000LOCALRXOK 0x2000 /* Link partner local receiver status */ -- cgit v1.2.3 From 0b760113a3a155269a3fba93a409c640031dd68f Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 31 May 2011 15:15:34 -0400 Subject: NLM: Don't hang forever on NLM unlock requests If the NLM daemon is killed on the NFS server, we can currently end up hanging forever on an 'unlock' request, instead of aborting. Basically, if the rpcbind request fails, or the server keeps returning garbage, we really want to quit instead of retrying. Tested-by: Vasily Averin Signed-off-by: Trond Myklebust Cc: stable@kernel.org --- include/linux/sunrpc/sched.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index f73c482ec9c6..fe2d8e6b923b 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -84,7 +84,8 @@ struct rpc_task { #endif unsigned char tk_priority : 2,/* Task priority */ tk_garb_retry : 2, - tk_cred_retry : 2; + tk_cred_retry : 2, + tk_rebind_retry : 2; }; #define tk_xprt tk_client->cl_xprt -- cgit v1.2.3 From c9c30dd5f73dccaa326a54dfcf490316946aea87 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Sat, 11 Jun 2011 17:08:39 -0400 Subject: NFSv4.1: deprecate headerpadsz in CREATE_SESSION We don't support header padding yet so better off ditching it Reported-by: Sid Moore Signed-off-by: Benny Halevy Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 5e8444a11adf..00848d86ffb2 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -158,7 +158,6 @@ struct nfs_seqid; /* nfs41 sessions channel attributes */ struct nfs4_channel_attrs { - u32 headerpadsz; u32 max_rqst_sz; u32 max_resp_sz; u32 max_resp_sz_cached; -- cgit v1.2.3 From a59ec1e7ff98cc4365d5b1bff4e7102e86b5716b Mon Sep 17 00:00:00 2001 From: Michael Hennerich Date: Wed, 15 Jun 2011 15:08:11 -0700 Subject: backlight: new driver for the ADP8870 backlight devices Signed-off-by: Michael Hennerich Signed-off-by: Mike Frysinger Cc: Richard Purdie Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/i2c/adp8870.h | 153 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 153 insertions(+) create mode 100644 include/linux/i2c/adp8870.h (limited to 'include/linux') diff --git a/include/linux/i2c/adp8870.h b/include/linux/i2c/adp8870.h new file mode 100644 index 000000000000..624dceccbd5b --- /dev/null +++ b/include/linux/i2c/adp8870.h @@ -0,0 +1,153 @@ +/* + * Definitions and platform data for Analog Devices + * Backlight drivers ADP8870 + * + * Copyright 2009-2010 Analog Devices Inc. + * + * Licensed under the GPL-2 or later. + */ + +#ifndef __LINUX_I2C_ADP8870_H +#define __LINUX_I2C_ADP8870_H + +#define ID_ADP8870 8870 + +#define ADP8870_MAX_BRIGHTNESS 0x7F +#define FLAG_OFFT_SHIFT 8 + +/* + * LEDs subdevice platform data + */ + +#define ADP8870_LED_DIS_BLINK (0 << FLAG_OFFT_SHIFT) +#define ADP8870_LED_OFFT_600ms (1 << FLAG_OFFT_SHIFT) +#define ADP8870_LED_OFFT_1200ms (2 << FLAG_OFFT_SHIFT) +#define ADP8870_LED_OFFT_1800ms (3 << FLAG_OFFT_SHIFT) + +#define ADP8870_LED_ONT_200ms 0 +#define ADP8870_LED_ONT_600ms 1 +#define ADP8870_LED_ONT_800ms 2 +#define ADP8870_LED_ONT_1200ms 3 + +#define ADP8870_LED_D7 (7) +#define ADP8870_LED_D6 (6) +#define ADP8870_LED_D5 (5) +#define ADP8870_LED_D4 (4) +#define ADP8870_LED_D3 (3) +#define ADP8870_LED_D2 (2) +#define ADP8870_LED_D1 (1) + +/* + * Backlight subdevice platform data + */ + +#define ADP8870_BL_D7 (1 << 6) +#define ADP8870_BL_D6 (1 << 5) +#define ADP8870_BL_D5 (1 << 4) +#define ADP8870_BL_D4 (1 << 3) +#define ADP8870_BL_D3 (1 << 2) +#define ADP8870_BL_D2 (1 << 1) +#define ADP8870_BL_D1 (1 << 0) + +#define ADP8870_FADE_T_DIS 0 /* Fade Timer Disabled */ +#define ADP8870_FADE_T_300ms 1 /* 0.3 Sec */ +#define ADP8870_FADE_T_600ms 2 +#define ADP8870_FADE_T_900ms 3 +#define ADP8870_FADE_T_1200ms 4 +#define ADP8870_FADE_T_1500ms 5 +#define ADP8870_FADE_T_1800ms 6 +#define ADP8870_FADE_T_2100ms 7 +#define ADP8870_FADE_T_2400ms 8 +#define ADP8870_FADE_T_2700ms 9 +#define ADP8870_FADE_T_3000ms 10 +#define ADP8870_FADE_T_3500ms 11 +#define ADP8870_FADE_T_4000ms 12 +#define ADP8870_FADE_T_4500ms 13 +#define ADP8870_FADE_T_5000ms 14 +#define ADP8870_FADE_T_5500ms 15 /* 5.5 Sec */ + +#define ADP8870_FADE_LAW_LINEAR 0 +#define ADP8870_FADE_LAW_SQUARE 1 +#define ADP8870_FADE_LAW_CUBIC1 2 +#define ADP8870_FADE_LAW_CUBIC2 3 + +#define ADP8870_BL_AMBL_FILT_80ms 0 /* Light sensor filter time */ +#define ADP8870_BL_AMBL_FILT_160ms 1 +#define ADP8870_BL_AMBL_FILT_320ms 2 +#define ADP8870_BL_AMBL_FILT_640ms 3 +#define ADP8870_BL_AMBL_FILT_1280ms 4 +#define ADP8870_BL_AMBL_FILT_2560ms 5 +#define ADP8870_BL_AMBL_FILT_5120ms 6 +#define ADP8870_BL_AMBL_FILT_10240ms 7 /* 10.24 sec */ + +/* + * Blacklight current 0..30mA + */ +#define ADP8870_BL_CUR_mA(I) ((I * 127) / 30) + +/* + * L2 comparator current 0..1106uA + */ +#define ADP8870_L2_COMP_CURR_uA(I) ((I * 255) / 1106) + +/* + * L3 comparator current 0..551uA + */ +#define ADP8870_L3_COMP_CURR_uA(I) ((I * 255) / 551) + +/* + * L4 comparator current 0..275uA + */ +#define ADP8870_L4_COMP_CURR_uA(I) ((I * 255) / 275) + +/* + * L5 comparator current 0..138uA + */ +#define ADP8870_L5_COMP_CURR_uA(I) ((I * 255) / 138) + +struct adp8870_backlight_platform_data { + u8 bl_led_assign; /* 1 = Backlight 0 = Individual LED */ + u8 pwm_assign; /* 1 = Enables PWM mode */ + + u8 bl_fade_in; /* Backlight Fade-In Timer */ + u8 bl_fade_out; /* Backlight Fade-Out Timer */ + u8 bl_fade_law; /* fade-on/fade-off transfer characteristic */ + + u8 en_ambl_sens; /* 1 = enable ambient light sensor */ + u8 abml_filt; /* Light sensor filter time */ + + u8 l1_daylight_max; /* use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l1_daylight_dim; /* typ = 0, use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l2_bright_max; /* use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l2_bright_dim; /* typ = 0, use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l3_office_max; /* use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l3_office_dim; /* typ = 0, use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l4_indoor_max; /* use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l4_indor_dim; /* typ = 0, use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l5_dark_max; /* use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l5_dark_dim; /* typ = 0, use BL_CUR_mA(I) 0 <= I <= 30 mA */ + + u8 l2_trip; /* use L2_COMP_CURR_uA(I) 0 <= I <= 1106 uA */ + u8 l2_hyst; /* use L2_COMP_CURR_uA(I) 0 <= I <= 1106 uA */ + u8 l3_trip; /* use L3_COMP_CURR_uA(I) 0 <= I <= 551 uA */ + u8 l3_hyst; /* use L3_COMP_CURR_uA(I) 0 <= I <= 551 uA */ + u8 l4_trip; /* use L4_COMP_CURR_uA(I) 0 <= I <= 275 uA */ + u8 l4_hyst; /* use L4_COMP_CURR_uA(I) 0 <= I <= 275 uA */ + u8 l5_trip; /* use L5_COMP_CURR_uA(I) 0 <= I <= 138 uA */ + u8 l5_hyst; /* use L6_COMP_CURR_uA(I) 0 <= I <= 138 uA */ + + /** + * Independent Current Sinks / LEDS + * Sinks not assigned to the Backlight can be exposed to + * user space using the LEDS CLASS interface + */ + + int num_leds; + struct led_info *leds; + u8 led_fade_in; /* LED Fade-In Timer */ + u8 led_fade_out; /* LED Fade-Out Timer */ + u8 led_fade_law; /* fade-on/fade-off transfer characteristic */ + u8 led_on_time; +}; + +#endif /* __LINUX_I2C_ADP8870_H */ -- cgit v1.2.3 From a433658c30974fc87ba3ff52d7e4e6299762aa3d Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Wed, 15 Jun 2011 15:08:13 -0700 Subject: vmscan,memcg: memcg aware swap token Currently, memcg reclaim can disable swap token even if the swap token mm doesn't belong in its memory cgroup. It's slightly risky. If an admin creates very small mem-cgroup and silly guy runs contentious heavy memory pressure workload, every tasks are going to lose swap token and then system may become unresponsive. That's bad. This patch adds 'memcg' parameter into disable_swap_token(). and if the parameter doesn't match swap token, VM doesn't disable it. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: KOSAKI Motohiro Reviewed-by: KAMEZAWA Hiroyuki Reviewed-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 6 ++++++ include/linux/swap.h | 8 ++------ 2 files changed, 8 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 9724a38ee69d..50940da6adf3 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -84,6 +84,7 @@ int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem); extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page); extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); +extern struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm); static inline int mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *cgroup) @@ -246,6 +247,11 @@ static inline struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) return NULL; } +static inline struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm) +{ + return NULL; +} + static inline int mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *mem) { return 1; diff --git a/include/linux/swap.h b/include/linux/swap.h index 384eb5fe530b..e70564647039 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -358,6 +358,7 @@ struct backing_dev_info; extern struct mm_struct *swap_token_mm; extern void grab_swap_token(struct mm_struct *); extern void __put_swap_token(struct mm_struct *); +extern void disable_swap_token(struct mem_cgroup *memcg); static inline int has_swap_token(struct mm_struct *mm) { @@ -370,11 +371,6 @@ static inline void put_swap_token(struct mm_struct *mm) __put_swap_token(mm); } -static inline void disable_swap_token(void) -{ - put_swap_token(swap_token_mm); -} - #ifdef CONFIG_CGROUP_MEM_RES_CTLR extern void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout); @@ -500,7 +496,7 @@ static inline int has_swap_token(struct mm_struct *mm) return 0; } -static inline void disable_swap_token(void) +static inline void disable_swap_token(struct mem_cgroup *memcg) { } -- cgit v1.2.3 From ac5622418bbff9cd3dc607aa57dfb4f62a7f2043 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 15 Jun 2011 15:08:17 -0700 Subject: kmsg_dump.h: fix build when CONFIG_PRINTK is disabled Fix when CONFIG_PRINTK is not enabled: include/linux/kmsg_dump.h:56: error: 'EINVAL' undeclared (first use in this function) include/linux/kmsg_dump.h:61: error: 'EINVAL' undeclared (first use in this function) Looks like commit 595dd3d8bf95 ("kmsg_dump: fix build for CONFIG_PRINTK=n") uses EINVAL without having the needed header file(s), but I'm sure that I build tested that patch also. oh well. Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kmsg_dump.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kmsg_dump.h b/include/linux/kmsg_dump.h index 2a0d7d651dc3..ee0c952188de 100644 --- a/include/linux/kmsg_dump.h +++ b/include/linux/kmsg_dump.h @@ -12,6 +12,7 @@ #ifndef _LINUX_KMSG_DUMP_H #define _LINUX_KMSG_DUMP_H +#include #include enum kmsg_dump_reason { -- cgit v1.2.3 From 32e45ff43eaf5c17f5a82c9ad358d515622c2562 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Wed, 15 Jun 2011 15:08:20 -0700 Subject: mm: increase RECLAIM_DISTANCE to 30 Recently, Robert Mueller reported (http://lkml.org/lkml/2010/9/12/236) that zone_reclaim_mode doesn't work properly on his new NUMA server (Dual Xeon E5520 + Intel S5520UR MB). He is using Cyrus IMAPd and it's built on a very traditional single-process model. * a master process which reads config files and manages the other process * multiple imapd processes, one per connection * multiple pop3d processes, one per connection * multiple lmtpd processes, one per connection * periodical "cleanup" processes. There are thousands of independent processes. The problem is, recent Intel motherboard turn on zone_reclaim_mode by default and traditional prefork model software don't work well on it. Unfortunatelly, such models are still typical even in the 21st century. We can't ignore them. This patch raises the zone_reclaim_mode threshold to 30. 30 doesn't have any specific meaning. but 20 means that one-hop QPI/Hypertransport and such relatively cheap 2-4 socket machine are often used for traditional servers as above. The intention is that these machines don't use zone_reclaim_mode. Note: ia64 and Power have arch specific RECLAIM_DISTANCE definitions. This patch doesn't change such high-end NUMA machine behavior. Dave Hansen said: : I know specifically of pieces of x86 hardware that set the information : in the BIOS to '21' *specifically* so they'll get the zone_reclaim_mode : behavior which that implies. : : They've done performance testing and run very large and scary benchmarks : to make sure that they _want_ this turned on. What this means for them : is that they'll probably be de-optimized, at least on newer versions of : the kernel. : : If you want to do this for particular systems, maybe _that_'s what we : should do. Have a list of specific configurations that need the : defaults overridden either because they're buggy, or they have an : unusual hardware configuration not really reflected in the distance : table. And later said: : The original change in the hardware tables was for the benefit of a : benchmark. Said benchmark isn't going to get run on mainline until the : next batch of enterprise distros drops, at which point the hardware where : this was done will be irrelevant for the benchmark. I'm sure any new : hardware will just set this distance to another yet arbitrary value to : make the kernel do what it wants. :) : : Also, when the hardware got _set_ to this initially, I complained. So, I : guess I'm getting my way now, with this patch. I'm cool with it. Reported-by: Robert Mueller Signed-off-by: KOSAKI Motohiro Acked-by: Christoph Lameter Acked-by: David Rientjes Reviewed-by: KAMEZAWA Hiroyuki Cc: Benjamin Herrenschmidt Cc: "Luck, Tony" Acked-by: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/topology.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/topology.h b/include/linux/topology.h index b91a40e847d2..fc839bfa7935 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -60,7 +60,7 @@ int arch_update_cpu_topology(void); * (in whatever arch specific measurement units returned by node_distance()) * then switch on zone reclaim on boot. */ -#define RECLAIM_DISTANCE 20 +#define RECLAIM_DISTANCE 30 #endif #ifndef PENALTY_FOR_NODE_WITH_CPUS #define PENALTY_FOR_NODE_WITH_CPUS (1) -- cgit v1.2.3 From ca39599c633fb02aceac31a7e67563612e4fe347 Mon Sep 17 00:00:00 2001 From: "Dr. David Alan Gilbert" Date: Wed, 15 Jun 2011 15:08:27 -0700 Subject: BUILD_BUG_ON_ZERO: fix sparse breakage BUILD_BUG_ON_ZERO and BUILD_BUG_ON_NULL must return values, even in the CHECKER case otherwise various users of it become syntactically invalid. Signed-off-by: Dr. David Alan Gilbert Reviewed-by: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index fb0e7329fee1..953352a88336 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -671,8 +671,8 @@ struct sysinfo { #ifdef __CHECKER__ #define BUILD_BUG_ON_NOT_POWER_OF_2(n) -#define BUILD_BUG_ON_ZERO(e) -#define BUILD_BUG_ON_NULL(e) +#define BUILD_BUG_ON_ZERO(e) (0) +#define BUILD_BUG_ON_NULL(e) ((void*)0) #define BUILD_BUG_ON(condition) #else /* __CHECKER__ */ -- cgit v1.2.3 From bd5dc17be87b3a3073d50b23802647db3ae3fa8e Mon Sep 17 00:00:00 2001 From: Josh Triplett Date: Wed, 15 Jun 2011 15:08:28 -0700 Subject: uts: make default hostname configurable, rather than always using "(none)" The "hostname" tool falls back to setting the hostname to "localhost" if /etc/hostname does not exist. Distribution init scripts have the same fallback. However, if userspace never calls sethostname, such as when booting with init=/bin/sh, or otherwise booting a minimal system without the usual init scripts, the default hostname of "(none)" remains, unhelpfully appearing in various places such as prompts ("root@(none):~#") and logs. Furthermore, "(none)" doesn't typically resolve to anything useful. Make the default hostname configurable. This removes the need for the standard fallback, provides a useful default for systems that never call sethostname, and makes minimal systems that much more useful with less configuration. Distributions could choose to use "localhost" here to avoid the fallback, while embedded systems may wish to use a specific target hostname. Signed-off-by: Josh Triplett Acked-by: Linus Torvalds Acked-by: David Miller Cc: Serge Hallyn Cc: Kel Modderman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/uts.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uts.h b/include/linux/uts.h index 73eb1ed36ec4..6ddbd86377de 100644 --- a/include/linux/uts.h +++ b/include/linux/uts.h @@ -9,7 +9,7 @@ #endif #ifndef UTS_NODENAME -#define UTS_NODENAME "(none)" /* set by sethostname() */ +#define UTS_NODENAME CONFIG_DEFAULT_HOSTNAME /* set by sethostname() */ #endif #ifndef UTS_DOMAINNAME -- cgit v1.2.3 From c001fb72a7b705f902bdfdd05b5d2408efe6f848 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 14 Jun 2011 17:05:11 -0700 Subject: gpio: add GPIOF_ values regardless on kconfig settings Make GPIOF_ defined values available even when GPIOLIB nor GENERIC_GPIO is enabled by moving them to . Fixes these build errors in linux-next: sound/soc/codecs/ak4641.c:524: error: 'GPIOF_OUT_INIT_LOW' undeclared (first use in this function) sound/soc/codecs/wm8915.c:2921: error: 'GPIOF_OUT_INIT_LOW' undeclared (first use in this function) Signed-off-by: Randy Dunlap Signed-off-by: Grant Likely --- include/linux/gpio.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio.h b/include/linux/gpio.h index 32d47e710661..17b5a0d80e42 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -3,6 +3,17 @@ /* see Documentation/gpio.txt */ +/* make these flag values available regardless of GPIO kconfig options */ +#define GPIOF_DIR_OUT (0 << 0) +#define GPIOF_DIR_IN (1 << 0) + +#define GPIOF_INIT_LOW (0 << 1) +#define GPIOF_INIT_HIGH (1 << 1) + +#define GPIOF_IN (GPIOF_DIR_IN) +#define GPIOF_OUT_INIT_LOW (GPIOF_DIR_OUT | GPIOF_INIT_LOW) +#define GPIOF_OUT_INIT_HIGH (GPIOF_DIR_OUT | GPIOF_INIT_HIGH) + #ifdef CONFIG_GENERIC_GPIO #include -- cgit v1.2.3 From 3192b920bf7d0c528ab54e7d3689f44055316a37 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Tue, 14 Jun 2011 16:16:36 -0500 Subject: slab, slub, slob: Unify alignment definition Every slab has its on alignment definition in include/linux/sl?b_def.h. Extract those and define a common set in include/linux/slab.h. SLOB: As notes sometimes we need double word alignment on 32 bit. This gives all structures allocated by SLOB a unsigned long long alignment like the others do. SLAB: If ARCH_SLAB_MINALIGN is not set SLAB would set ARCH_SLAB_MINALIGN to zero meaning no alignment at all. Give it the default unsigned long long alignment. Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slab.h | 10 ++++++++++ include/linux/slab_def.h | 26 -------------------------- include/linux/slob_def.h | 10 ---------- include/linux/slub_def.h | 10 ---------- 4 files changed, 10 insertions(+), 46 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index ad4dd1c8d30a..646a639a4aae 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -133,6 +133,16 @@ unsigned int kmem_cache_size(struct kmem_cache *); #define KMALLOC_MAX_SIZE (1UL << KMALLOC_SHIFT_HIGH) #define KMALLOC_MAX_ORDER (KMALLOC_SHIFT_HIGH - PAGE_SHIFT) +#ifdef ARCH_DMA_MINALIGN +#define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN +#else +#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) +#endif + +#ifndef ARCH_SLAB_MINALIGN +#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) +#endif + /* * Common kmalloc functions provided by all allocators */ diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index 83203ae9390b..d7f63112f63c 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -17,32 +17,6 @@ #include -/* - * Enforce a minimum alignment for the kmalloc caches. - * Usually, the kmalloc caches are cache_line_size() aligned, except when - * DEBUG and FORCED_DEBUG are enabled, then they are BYTES_PER_WORD aligned. - * Some archs want to perform DMA into kmalloc caches and need a guaranteed - * alignment larger than the alignment of a 64-bit integer. - * ARCH_KMALLOC_MINALIGN allows that. - * Note that increasing this value may disable some debug features. - */ -#ifdef ARCH_DMA_MINALIGN -#define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN -#else -#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) -#endif - -#ifndef ARCH_SLAB_MINALIGN -/* - * Enforce a minimum alignment for all caches. - * Intended for archs that get misalignment faults even for BYTES_PER_WORD - * aligned buffers. Includes ARCH_KMALLOC_MINALIGN. - * If possible: Do not enable this flag for CONFIG_DEBUG_SLAB, it disables - * some debug features. - */ -#define ARCH_SLAB_MINALIGN 0 -#endif - /* * struct kmem_cache * diff --git a/include/linux/slob_def.h b/include/linux/slob_def.h index 4382db09df4f..0ec00b39d006 100644 --- a/include/linux/slob_def.h +++ b/include/linux/slob_def.h @@ -1,16 +1,6 @@ #ifndef __LINUX_SLOB_DEF_H #define __LINUX_SLOB_DEF_H -#ifdef ARCH_DMA_MINALIGN -#define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN -#else -#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long) -#endif - -#ifndef ARCH_SLAB_MINALIGN -#define ARCH_SLAB_MINALIGN __alignof__(unsigned long) -#endif - void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node); static __always_inline void *kmem_cache_alloc(struct kmem_cache *cachep, diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index c8668d161dd8..fd4fdc72bc8c 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -113,16 +113,6 @@ struct kmem_cache { #define KMALLOC_SHIFT_LOW ilog2(KMALLOC_MIN_SIZE) -#ifdef ARCH_DMA_MINALIGN -#define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN -#else -#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) -#endif - -#ifndef ARCH_SLAB_MINALIGN -#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) -#endif - /* * Maximum kmalloc object size handled by SLUB. Larger object allocations * are passed through to the page allocator. The page allocator "fastpath" -- cgit v1.2.3 From 5416219e5ca4504ea80d662fdda7337e52e86ee5 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Thu, 16 Jun 2011 18:40:55 +0200 Subject: netfilter: ipset: timeout can be modified for already added elements When an element to a set with timeout added, one can change the timeout by "readding" the element with the "-exist" flag. That means the timeout value is reset to the specified one (or to the default from the set specification if the "timeout n" option is not used). Example ipset add foo 1.2.3.4 timeout 10 ipset add foo 1.2.3.4 timeout 600 -exist Signed-off-by: Jozsef Kadlecsik Signed-off-by: Patrick McHardy --- include/linux/netfilter/ipset/ip_set.h | 3 ++- include/linux/netfilter/ipset/ip_set_ahash.h | 15 ++++++++------- 2 files changed, 10 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 5a262e3ae715..277b7fbc7fb2 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -214,7 +214,8 @@ enum ip_set_feature { struct ip_set; -typedef int (*ipset_adtfn)(struct ip_set *set, void *value, u32 timeout); +typedef int (*ipset_adtfn)(struct ip_set *set, void *value, + u32 timeout, u32 flags); /* Set type, variant-specific part */ struct ip_set_type_variant { diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h index ac3c822eb39a..36cf4dc703bb 100644 --- a/include/linux/netfilter/ipset/ip_set_ahash.h +++ b/include/linux/netfilter/ipset/ip_set_ahash.h @@ -349,7 +349,7 @@ retry: /* Add an element to a hash and update the internal counters when succeeded, * otherwise report the proper error code. */ static int -type_pf_add(struct ip_set *set, void *value, u32 timeout) +type_pf_add(struct ip_set *set, void *value, u32 timeout, u32 flags) { struct ip_set_hash *h = set->data; struct htable *t; @@ -388,7 +388,7 @@ out: * and free up space if possible. */ static int -type_pf_del(struct ip_set *set, void *value, u32 timeout) +type_pf_del(struct ip_set *set, void *value, u32 timeout, u32 flags) { struct ip_set_hash *h = set->data; struct htable *t = h->table; @@ -463,7 +463,7 @@ type_pf_test_cidrs(struct ip_set *set, struct type_pf_elem *d, u32 timeout) /* Test whether the element is added to the set */ static int -type_pf_test(struct ip_set *set, void *value, u32 timeout) +type_pf_test(struct ip_set *set, void *value, u32 timeout, u32 flags) { struct ip_set_hash *h = set->data; struct htable *t = h->table; @@ -776,7 +776,7 @@ retry: } static int -type_pf_tadd(struct ip_set *set, void *value, u32 timeout) +type_pf_tadd(struct ip_set *set, void *value, u32 timeout, u32 flags) { struct ip_set_hash *h = set->data; struct htable *t = h->table; @@ -784,6 +784,7 @@ type_pf_tadd(struct ip_set *set, void *value, u32 timeout) struct hbucket *n; struct type_pf_elem *data; int ret = 0, i, j = AHASH_MAX_SIZE + 1; + bool flag_exist = flags & IPSET_FLAG_EXIST; u32 key; if (h->elements >= h->maxelem) @@ -799,7 +800,7 @@ type_pf_tadd(struct ip_set *set, void *value, u32 timeout) for (i = 0; i < n->pos; i++) { data = ahash_tdata(n, i); if (type_pf_data_equal(data, d)) { - if (type_pf_data_expired(data)) + if (type_pf_data_expired(data) || flag_exist) j = i; else { ret = -IPSET_ERR_EXIST; @@ -833,7 +834,7 @@ out: } static int -type_pf_tdel(struct ip_set *set, void *value, u32 timeout) +type_pf_tdel(struct ip_set *set, void *value, u32 timeout, u32 flags) { struct ip_set_hash *h = set->data; struct htable *t = h->table; @@ -905,7 +906,7 @@ type_pf_ttest_cidrs(struct ip_set *set, struct type_pf_elem *d, u32 timeout) #endif static int -type_pf_ttest(struct ip_set *set, void *value, u32 timeout) +type_pf_ttest(struct ip_set *set, void *value, u32 timeout, u32 flags) { struct ip_set_hash *h = set->data; struct htable *t = h->table; -- cgit v1.2.3 From ac8cc925d35fc5a05da2bd097e602f20de2478a4 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Thu, 16 Jun 2011 18:42:40 +0200 Subject: netfilter: ipset: options and flags support added to the kernel API The support makes possible to specify the timeout value for the SET target and a flag to reset the timeout for already existing entries. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Patrick McHardy --- include/linux/netfilter/ipset/ip_set.h | 18 ++++++++++++++---- include/linux/netfilter/ipset/ip_set_ahash.h | 2 +- include/linux/netfilter/ipset/ip_set_timeout.h | 3 +++ include/linux/netfilter/xt_set.h | 15 ++++++++++++--- 4 files changed, 30 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 277b7fbc7fb2..68b21f5d6a84 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -217,6 +217,15 @@ struct ip_set; typedef int (*ipset_adtfn)(struct ip_set *set, void *value, u32 timeout, u32 flags); +/* Kernel API function options */ +struct ip_set_adt_opt { + u8 family; /* Actual protocol family */ + u8 dim; /* Dimension of match/target */ + u8 flags; /* Direction and negation flags */ + u32 cmdflags; /* Command-like flags */ + u32 timeout; /* Timeout value */ +}; + /* Set type, variant-specific part */ struct ip_set_type_variant { /* Kernelspace: test/add/del entries @@ -224,7 +233,7 @@ struct ip_set_type_variant { * zero for no match/success to add/delete * positive for matching element */ int (*kadt)(struct ip_set *set, const struct sk_buff * skb, - enum ipset_adt adt, u8 pf, u8 dim, u8 flags); + enum ipset_adt adt, const struct ip_set_adt_opt *opt); /* Userspace: test/add/del entries * returns negative error code, @@ -314,12 +323,13 @@ extern ip_set_id_t ip_set_nfnl_get_byindex(ip_set_id_t index); extern void ip_set_nfnl_put(ip_set_id_t index); /* API for iptables set match, and SET target */ + extern int ip_set_add(ip_set_id_t id, const struct sk_buff *skb, - u8 family, u8 dim, u8 flags); + const struct ip_set_adt_opt *opt); extern int ip_set_del(ip_set_id_t id, const struct sk_buff *skb, - u8 family, u8 dim, u8 flags); + const struct ip_set_adt_opt *opt); extern int ip_set_test(ip_set_id_t id, const struct sk_buff *skb, - u8 family, u8 dim, u8 flags); + const struct ip_set_adt_opt *opt); /* Utility functions */ extern void * ip_set_alloc(size_t size); diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h index 36cf4dc703bb..6c0219348b43 100644 --- a/include/linux/netfilter/ipset/ip_set_ahash.h +++ b/include/linux/netfilter/ipset/ip_set_ahash.h @@ -586,7 +586,7 @@ nla_put_failure: static int type_pf_kadt(struct ip_set *set, const struct sk_buff * skb, - enum ipset_adt adt, u8 pf, u8 dim, u8 flags); + enum ipset_adt adt, const struct ip_set_adt_opt *opt); static int type_pf_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags); diff --git a/include/linux/netfilter/ipset/ip_set_timeout.h b/include/linux/netfilter/ipset/ip_set_timeout.h index bcdd40ad39ed..bae086af0e44 100644 --- a/include/linux/netfilter/ipset/ip_set_timeout.h +++ b/include/linux/netfilter/ipset/ip_set_timeout.h @@ -22,6 +22,9 @@ #define with_timeout(timeout) ((timeout) != IPSET_NO_TIMEOUT) +#define opt_timeout(opt, map) \ + (with_timeout((opt)->timeout) ? (opt)->timeout : (map)->timeout) + static inline unsigned int ip_set_timeout_uget(struct nlattr *tb) { diff --git a/include/linux/netfilter/xt_set.h b/include/linux/netfilter/xt_set.h index 081f1ded2842..c0405ac92870 100644 --- a/include/linux/netfilter/xt_set.h +++ b/include/linux/netfilter/xt_set.h @@ -35,7 +35,7 @@ struct xt_set_info_target_v0 { struct xt_set_info_v0 del_set; }; -/* Revision 1: current interface to netfilter/iptables */ +/* Revision 1 match and target */ struct xt_set_info { ip_set_id_t index; @@ -44,13 +44,22 @@ struct xt_set_info { }; /* match and target infos */ -struct xt_set_info_match { +struct xt_set_info_match_v1 { struct xt_set_info match_set; }; -struct xt_set_info_target { +struct xt_set_info_target_v1 { struct xt_set_info add_set; struct xt_set_info del_set; }; +/* Revision 2 target */ + +struct xt_set_info_target_v2 { + struct xt_set_info add_set; + struct xt_set_info del_set; + u32 flags; + u32 timeout; +}; + #endif /*_XT_SET_H*/ -- cgit v1.2.3 From c1e2e04388b2539960453689b8e721709f71dc9c Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Thu, 16 Jun 2011 18:47:07 +0200 Subject: netfilter: ipset: support listing setnames and headers too Current listing makes possible to list sets with full content only. The patch adds support partial listings, i.e. listing just the existing setnames or listing set headers, without set members. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Patrick McHardy --- include/linux/netfilter/ipset/ip_set.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 68b21f5d6a84..e677c4d8f00e 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -142,6 +142,10 @@ enum ipset_errno { enum ipset_cmd_flags { IPSET_FLAG_BIT_EXIST = 0, IPSET_FLAG_EXIST = (1 << IPSET_FLAG_BIT_EXIST), + IPSET_FLAG_BIT_LIST_SETNAME = 1, + IPSET_FLAG_LIST_SETNAME = (1 << IPSET_FLAG_BIT_LIST_SETNAME), + IPSET_FLAG_BIT_LIST_HEADER = 2, + IPSET_FLAG_LIST_HEADER = (1 << IPSET_FLAG_BIT_LIST_HEADER), }; /* Flags at CADT attribute level */ -- cgit v1.2.3 From 3d14b171f004f75c2d1e82e10545966f94132705 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Thu, 16 Jun 2011 18:49:17 +0200 Subject: netfilter: ipset: fix adding ranges to hash types When ranges are added to hash types, the elements may trigger rehashing the set. However, the last successfully added element was not kept track so the adding started again with the first element after the rehashing. Bug reported by Mr Dash Four. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Patrick McHardy --- include/linux/netfilter/ipset/ip_set.h | 2 +- include/linux/netfilter/ipset/ip_set_ahash.h | 22 +++++++++++++++++++--- 2 files changed, 20 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index e677c4d8f00e..710ba0070298 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -244,7 +244,7 @@ struct ip_set_type_variant { * zero for no match/success to add/delete * positive for matching element */ int (*uadt)(struct ip_set *set, struct nlattr *tb[], - enum ipset_adt adt, u32 *lineno, u32 flags); + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried); /* Low level add/del/test functions */ ipset_adtfn adt[IPSET_ADT_MAX]; diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h index 6c0219348b43..8709bd950c8b 100644 --- a/include/linux/netfilter/ipset/ip_set_ahash.h +++ b/include/linux/netfilter/ipset/ip_set_ahash.h @@ -5,6 +5,11 @@ #include #include +#define CONCAT(a, b, c) a##b##c +#define TOKEN(a, b, c) CONCAT(a, b, c) + +#define type_pf_next TOKEN(TYPE, PF, _elem) + /* Hashing which uses arrays to resolve clashing. The hash table is resized * (doubled) when searching becomes too long. * Internally jhash is used with the assumption that the size of the @@ -54,6 +59,7 @@ struct ip_set_hash { u32 initval; /* random jhash init value */ u32 timeout; /* timeout value, if enabled */ struct timer_list gc; /* garbage collection when timeout enabled */ + struct type_pf_next next; /* temporary storage for uadd */ #ifdef IP_SET_HASH_WITH_NETMASK u8 netmask; /* netmask value for subnets to store */ #endif @@ -217,6 +223,7 @@ ip_set_hash_destroy(struct ip_set *set) #define type_pf_data_netmask TOKEN(TYPE, PF, _data_netmask) #define type_pf_data_list TOKEN(TYPE, PF, _data_list) #define type_pf_data_tlist TOKEN(TYPE, PF, _data_tlist) +#define type_pf_data_next TOKEN(TYPE, PF, _data_next) #define type_pf_elem TOKEN(TYPE, PF, _elem) #define type_pf_telem TOKEN(TYPE, PF, _telem) @@ -346,6 +353,9 @@ retry: return 0; } +static inline void +type_pf_data_next(struct ip_set_hash *h, const struct type_pf_elem *d); + /* Add an element to a hash and update the internal counters when succeeded, * otherwise report the proper error code. */ static int @@ -372,8 +382,11 @@ type_pf_add(struct ip_set *set, void *value, u32 timeout, u32 flags) } ret = type_pf_elem_add(n, value); - if (ret != 0) + if (ret != 0) { + if (ret == -EAGAIN) + type_pf_data_next(h, d); goto out; + } #ifdef IP_SET_HASH_WITH_NETS add_cidr(h, d->cidr, HOST_MASK); @@ -589,7 +602,7 @@ type_pf_kadt(struct ip_set *set, const struct sk_buff * skb, enum ipset_adt adt, const struct ip_set_adt_opt *opt); static int type_pf_uadt(struct ip_set *set, struct nlattr *tb[], - enum ipset_adt adt, u32 *lineno, u32 flags); + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried); static const struct ip_set_type_variant type_pf_variant = { .kadt = type_pf_kadt, @@ -821,8 +834,11 @@ type_pf_tadd(struct ip_set *set, void *value, u32 timeout, u32 flags) goto out; } ret = type_pf_elem_tadd(n, d, timeout); - if (ret != 0) + if (ret != 0) { + if (ret == -EEXIST) + type_pf_data_next(h, d); goto out; + } #ifdef IP_SET_HASH_WITH_NETS add_cidr(h, d->cidr, HOST_MASK); -- cgit v1.2.3 From f1e00b39797944bf25addaf543839feeb25fbdc5 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Thu, 16 Jun 2011 18:51:41 +0200 Subject: netfilter: ipset: set type support with multiple revisions added A set type may have multiple revisions, for example when syntax is extended. Support continuous revision ranges in set types. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Patrick McHardy --- include/linux/netfilter/ipset/ip_set.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 710ba0070298..ac31e382472b 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -282,8 +282,8 @@ struct ip_set_type { u8 dimension; /* Supported family: may be AF_UNSPEC for both AF_INET/AF_INET6 */ u8 family; - /* Type revision */ - u8 revision; + /* Type revisions */ + u8 revision_min, revision_max; /* Create set */ int (*create)(struct ip_set *set, struct nlattr *tb[], u32 flags); @@ -314,6 +314,8 @@ struct ip_set { const struct ip_set_type_variant *variant; /* The actual INET family of the set */ u8 family; + /* The type revision */ + u8 revision; /* The type specific data */ void *data; }; -- cgit v1.2.3 From d0d9e0a5a8db05b2179c2ffb25d1c2850cce3c8e Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Thu, 16 Jun 2011 18:52:41 +0200 Subject: netfilter: ipset: support range for IPv4 at adding/deleting elements for hash:*net* types The range internally is converted to the network(s) equal to the range. Example: # ipset new test hash:net # ipset add test 10.2.0.0-10.2.1.12 # ipset list test Name: test Type: hash:net Header: family inet hashsize 1024 maxelem 65536 Size in memory: 16888 References: 0 Members: 10.2.1.12 10.2.1.0/29 10.2.0.0/24 10.2.1.8/30 Signed-off-by: Jozsef Kadlecsik Signed-off-by: Patrick McHardy --- include/linux/netfilter/ipset/ip_set.h | 1 + include/linux/netfilter/ipset/ip_set_ahash.h | 2 +- include/linux/netfilter/ipset/ip_set_hash.h | 4 ++++ include/linux/netfilter/ipset/pfxlen.h | 3 +++ 4 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index ac31e382472b..fd83f4f436c3 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -104,6 +104,7 @@ enum { IPSET_ATTR_NAMEREF, IPSET_ATTR_IP2, IPSET_ATTR_CIDR2, + IPSET_ATTR_IP2_TO, __IPSET_ATTR_ADT_MAX, }; #define IPSET_ATTR_ADT_MAX (__IPSET_ATTR_ADT_MAX - 1) diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h index 8709bd950c8b..905e2ac32daf 100644 --- a/include/linux/netfilter/ipset/ip_set_ahash.h +++ b/include/linux/netfilter/ipset/ip_set_ahash.h @@ -353,7 +353,7 @@ retry: return 0; } -static inline void +static void type_pf_data_next(struct ip_set_hash *h, const struct type_pf_elem *d); /* Add an element to a hash and update the internal counters when succeeded, diff --git a/include/linux/netfilter/ipset/ip_set_hash.h b/include/linux/netfilter/ipset/ip_set_hash.h index b86f15c04524..e2a9fae767f6 100644 --- a/include/linux/netfilter/ipset/ip_set_hash.h +++ b/include/linux/netfilter/ipset/ip_set_hash.h @@ -11,6 +11,10 @@ enum { IPSET_ERR_INVALID_PROTO, /* Protocol missing but must be specified */ IPSET_ERR_MISSING_PROTO, + /* Range not supported */ + IPSET_ERR_HASH_RANGE_UNSUPPORTED, + /* Invalid range */ + IPSET_ERR_HASH_RANGE, }; #ifdef __KERNEL__ diff --git a/include/linux/netfilter/ipset/pfxlen.h b/include/linux/netfilter/ipset/pfxlen.h index 0e1fb50da562..84efa3351e0e 100644 --- a/include/linux/netfilter/ipset/pfxlen.h +++ b/include/linux/netfilter/ipset/pfxlen.h @@ -3,6 +3,7 @@ #include #include +#include /* Prefixlen maps, by Jan Engelhardt */ extern const union nf_inet_addr ip_set_netmask_map[]; @@ -32,4 +33,6 @@ ip_set_hostmask6(u8 pfxlen) return &ip_set_hostmask_map[pfxlen].ip6[0]; } +extern u32 ip_set_range_to_cidr(u32 from, u32 to, u8 *cidr); + #endif /*_PFXLEN_H */ -- cgit v1.2.3 From c64562eaf2ad61d7492788ef95678f52d0d28f2a Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Thu, 16 Jun 2011 18:53:51 +0200 Subject: netfilter: ipset: adding ranges to hash types with timeout could still fail, fixed The patch "Fix adding ranges to hash types" had got a mistypeing in the timeout variant of the hash types, which actually made the patch ineffective. Fixed! Signed-off-by: Jozsef Kadlecsik Signed-off-by: Patrick McHardy --- include/linux/netfilter/ipset/ip_set_ahash.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h index 905e2ac32daf..a099d40d120a 100644 --- a/include/linux/netfilter/ipset/ip_set_ahash.h +++ b/include/linux/netfilter/ipset/ip_set_ahash.h @@ -835,7 +835,7 @@ type_pf_tadd(struct ip_set *set, void *value, u32 timeout, u32 flags) } ret = type_pf_elem_tadd(n, d, timeout); if (ret != 0) { - if (ret == -EEXIST) + if (ret == -EAGAIN) type_pf_data_next(h, d); goto out; } -- cgit v1.2.3 From e6146e8684ed6dd4c0ff85ca21bf4324114fbbfa Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Thu, 16 Jun 2011 18:55:58 +0200 Subject: netfilter: ipset: use unified from/to address masking and check the usage Signed-off-by: Jozsef Kadlecsik Signed-off-by: Patrick McHardy --- include/linux/netfilter/ipset/pfxlen.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/pfxlen.h b/include/linux/netfilter/ipset/pfxlen.h index 84efa3351e0e..d55a6ccf662e 100644 --- a/include/linux/netfilter/ipset/pfxlen.h +++ b/include/linux/netfilter/ipset/pfxlen.h @@ -35,4 +35,10 @@ ip_set_hostmask6(u8 pfxlen) extern u32 ip_set_range_to_cidr(u32 from, u32 to, u8 *cidr); +#define ip_set_mask_from_to(from, to, cidr) \ +do { \ + from &= ip_set_hostmask(cidr); \ + to = from | ~ip_set_hostmask(cidr); \ +} while (0) + #endif /*_PFXLEN_H */ -- cgit v1.2.3 From b66554cf03fe866b3fb7b9f40f430b8ba09f41c8 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Thu, 16 Jun 2011 18:56:47 +0200 Subject: netfilter: ipset: add xt_action_param to the variant level kadt functions, ipset API change With the change the sets can use any parameter available for the match and target extensions, like input/output interface. It's required for the hash:net,iface set type. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Patrick McHardy --- include/linux/netfilter/ipset/ip_set.h | 5 +++++ include/linux/netfilter/ipset/ip_set_ahash.h | 1 + 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index fd83f4f436c3..8955165f7dbb 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -170,6 +170,7 @@ enum ipset_adt { #include #include #include +#include #include #include @@ -238,6 +239,7 @@ struct ip_set_type_variant { * zero for no match/success to add/delete * positive for matching element */ int (*kadt)(struct ip_set *set, const struct sk_buff * skb, + const struct xt_action_param *par, enum ipset_adt adt, const struct ip_set_adt_opt *opt); /* Userspace: test/add/del entries @@ -332,10 +334,13 @@ extern void ip_set_nfnl_put(ip_set_id_t index); /* API for iptables set match, and SET target */ extern int ip_set_add(ip_set_id_t id, const struct sk_buff *skb, + const struct xt_action_param *par, const struct ip_set_adt_opt *opt); extern int ip_set_del(ip_set_id_t id, const struct sk_buff *skb, + const struct xt_action_param *par, const struct ip_set_adt_opt *opt); extern int ip_set_test(ip_set_id_t id, const struct sk_buff *skb, + const struct xt_action_param *par, const struct ip_set_adt_opt *opt); /* Utility functions */ diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h index a099d40d120a..1c977e143885 100644 --- a/include/linux/netfilter/ipset/ip_set_ahash.h +++ b/include/linux/netfilter/ipset/ip_set_ahash.h @@ -599,6 +599,7 @@ nla_put_failure: static int type_pf_kadt(struct ip_set *set, const struct sk_buff * skb, + const struct xt_action_param *par, enum ipset_adt adt, const struct ip_set_adt_opt *opt); static int type_pf_uadt(struct ip_set *set, struct nlattr *tb[], -- cgit v1.2.3 From e385357a2f214e4d4e79c6118f1bede2572e0701 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Thu, 16 Jun 2011 19:00:48 +0200 Subject: netfilter: ipset: hash:net,iface type introduced The hash:net,iface type makes possible to store network address and interface name pairs in a set. It's mostly suitable for egress and ingress filtering. Examples: # ipset create test hash:net,iface # ipset add test 192.168.0.0/16,eth0 # ipset add test 192.168.0.0/24,eth1 Signed-off-by: Jozsef Kadlecsik Signed-off-by: Patrick McHardy --- include/linux/netfilter/ipset/ip_set.h | 5 +++++ include/linux/netfilter/ipset/ip_set_ahash.h | 6 ++++++ 2 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 8955165f7dbb..e40917334d04 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -105,6 +105,7 @@ enum { IPSET_ATTR_IP2, IPSET_ATTR_CIDR2, IPSET_ATTR_IP2_TO, + IPSET_ATTR_IFACE, __IPSET_ATTR_ADT_MAX, }; #define IPSET_ATTR_ADT_MAX (__IPSET_ATTR_ADT_MAX - 1) @@ -153,6 +154,8 @@ enum ipset_cmd_flags { enum ipset_cadt_flags { IPSET_FLAG_BIT_BEFORE = 0, IPSET_FLAG_BEFORE = (1 << IPSET_FLAG_BIT_BEFORE), + IPSET_FLAG_BIT_PHYSDEV = 1, + IPSET_FLAG_PHYSDEV = (1 << IPSET_FLAG_BIT_PHYSDEV), }; /* Commands with settype-specific attributes */ @@ -212,6 +215,8 @@ enum ip_set_feature { IPSET_TYPE_IP2 = (1 << IPSET_TYPE_IP2_FLAG), IPSET_TYPE_NAME_FLAG = 4, IPSET_TYPE_NAME = (1 << IPSET_TYPE_NAME_FLAG), + IPSET_TYPE_IFACE_FLAG = 5, + IPSET_TYPE_IFACE = (1 << IPSET_TYPE_IFACE_FLAG), /* Strictly speaking not a feature, but a flag for dumping: * this settype must be dumped last */ IPSET_DUMP_LAST_FLAG = 7, diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h index 1c977e143885..8a0999a8baa1 100644 --- a/include/linux/netfilter/ipset/ip_set_ahash.h +++ b/include/linux/netfilter/ipset/ip_set_ahash.h @@ -63,6 +63,9 @@ struct ip_set_hash { #ifdef IP_SET_HASH_WITH_NETMASK u8 netmask; /* netmask value for subnets to store */ #endif +#ifdef IP_SET_HASH_WITH_RBTREE + struct rb_root rbtree; +#endif #ifdef IP_SET_HASH_WITH_NETS struct ip_set_hash_nets nets[0]; /* book-keeping of prefixes */ #endif @@ -200,6 +203,9 @@ ip_set_hash_destroy(struct ip_set *set) del_timer_sync(&h->gc); ahash_destroy(h->table); +#ifdef IP_SET_HASH_WITH_RBTREE + rbtree_destroy(&h->rbtree); +#endif kfree(h); set->data = NULL; -- cgit v1.2.3 From 15b4d93f0316caec44e07255c1d73bde4fac12e4 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Thu, 16 Jun 2011 19:01:26 +0200 Subject: netfilter: ipset: whitespace and coding fixes detected by checkpatch.pl Signed-off-by: Jozsef Kadlecsik Signed-off-by: Patrick McHardy --- include/linux/netfilter/ipset/ip_set.h | 6 +++--- include/linux/netfilter/ipset/ip_set_ahash.h | 2 +- include/linux/netfilter/ipset/ip_set_timeout.h | 2 +- include/linux/netfilter/ipset/pfxlen.h | 2 +- 4 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index e40917334d04..3540c6e262f7 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -331,7 +331,7 @@ struct ip_set { /* register and unregister set references */ extern ip_set_id_t ip_set_get_byname(const char *name, struct ip_set **set); extern void ip_set_put_byindex(ip_set_id_t index); -extern const char * ip_set_name_byindex(ip_set_id_t index); +extern const char *ip_set_name_byindex(ip_set_id_t index); extern ip_set_id_t ip_set_nfnl_get(const char *name); extern ip_set_id_t ip_set_nfnl_get_byindex(ip_set_id_t index); extern void ip_set_nfnl_put(ip_set_id_t index); @@ -349,7 +349,7 @@ extern int ip_set_test(ip_set_id_t id, const struct sk_buff *skb, const struct ip_set_adt_opt *opt); /* Utility functions */ -extern void * ip_set_alloc(size_t size); +extern void *ip_set_alloc(size_t size); extern void ip_set_free(void *members); extern int ip_set_get_ipaddr4(struct nlattr *nla, __be32 *ipaddr); extern int ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr); @@ -359,7 +359,7 @@ ip_set_get_hostipaddr4(struct nlattr *nla, u32 *ipaddr) { __be32 ip; int ret = ip_set_get_ipaddr4(nla, &ip); - + if (ret) return ret; *ipaddr = ntohl(ip); diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h index 8a0999a8baa1..c5b06aaa205c 100644 --- a/include/linux/netfilter/ipset/ip_set_ahash.h +++ b/include/linux/netfilter/ipset/ip_set_ahash.h @@ -43,7 +43,7 @@ struct htable { struct hbucket bucket[0]; /* hashtable buckets */ }; -#define hbucket(h, i) &((h)->bucket[i]) +#define hbucket(h, i) (&((h)->bucket[i])) /* Book-keeping of the prefixes added to the set */ struct ip_set_hash_nets { diff --git a/include/linux/netfilter/ipset/ip_set_timeout.h b/include/linux/netfilter/ipset/ip_set_timeout.h index bae086af0e44..47923205a4ad 100644 --- a/include/linux/netfilter/ipset/ip_set_timeout.h +++ b/include/linux/netfilter/ipset/ip_set_timeout.h @@ -78,7 +78,7 @@ ip_set_timeout_set(u32 timeout) static inline u32 ip_set_timeout_get(unsigned long timeout) { - return timeout == IPSET_ELEM_PERMANENT ? 0 : + return timeout == IPSET_ELEM_PERMANENT ? 0 : jiffies_to_msecs(timeout - jiffies)/1000; } diff --git a/include/linux/netfilter/ipset/pfxlen.h b/include/linux/netfilter/ipset/pfxlen.h index d55a6ccf662e..199fd11fedc0 100644 --- a/include/linux/netfilter/ipset/pfxlen.h +++ b/include/linux/netfilter/ipset/pfxlen.h @@ -2,7 +2,7 @@ #define _PFXLEN_H #include -#include +#include #include /* Prefixlen maps, by Jan Engelhardt */ -- cgit v1.2.3 From b5199515c25cca622495eb9c6a8a1d275e775088 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 16 Jun 2011 16:22:08 +0200 Subject: clocksource: Make watchdog robust vs. interruption The clocksource watchdog code is interruptible and it has been observed that this can trigger false positives which disable the TSC. The reason is that an interrupt storm or a long running interrupt handler between the read of the watchdog source and the read of the TSC brings the two far enough apart that the delta is larger than the unstable treshold. Move both reads into a short interrupt disabled region to avoid that. Reported-and-tested-by: Vernon Mauery Signed-off-by: Thomas Gleixner Cc: stable@kernel.org --- include/linux/clocksource.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index d4646b48dc4a..18a1baf31f2d 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -188,6 +188,7 @@ struct clocksource { #ifdef CONFIG_CLOCKSOURCE_WATCHDOG /* Watchdog related data, used by the framework */ struct list_head wd_list; + cycle_t cs_last; cycle_t wd_last; #endif } ____cacheline_aligned; -- cgit v1.2.3 From c16d51a32bbb61ac8fd96f78b5ce2fccfe0fb4c3 Mon Sep 17 00:00:00 2001 From: Shreshtha Kumar Sahu Date: Mon, 13 Jun 2011 10:11:33 +0200 Subject: amba pl011: workaround for uart registers lockup This workaround aims to break the deadlock situation which raises during continuous transfer of data for long duration over uart with hardware flow control. It is observed that CTS interrupt cannot be cleared in uart interrupt register (ICR). Hence further transfer over uart gets blocked. It is seen that during such deadlock condition ICR don't get cleared even on multiple write. This leads pass_counter to decrease and finally reach zero. This can be taken as trigger point to run this UART_BT_WA. Workaround backups the register configuration, does soft reset of UART using BIT-0 of PRCC_K_SOFTRST_SET/CLEAR registers and restores the registers. This patch also provides support for uart init and exit function calls if present. Signed-off-by: Shreshtha Kumar Sahu Signed-off-by: Linus Walleij Signed-off-by: Greg Kroah-Hartman --- include/linux/amba/serial.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/amba/serial.h b/include/linux/amba/serial.h index 5479fdc849e9..514ed45c462e 100644 --- a/include/linux/amba/serial.h +++ b/include/linux/amba/serial.h @@ -201,6 +201,9 @@ struct amba_pl011_data { bool (*dma_filter)(struct dma_chan *chan, void *filter_param); void *dma_rx_param; void *dma_tx_param; + void (*init) (void); + void (*exit) (void); + void (*reset) (void); }; #endif -- cgit v1.2.3 From 73ddff2bee159ffb580bd24faf625cd5e628f5ec Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 14 Jun 2011 11:20:14 +0200 Subject: job control: introduce JOBCTL_TRAP_STOP and use it for group stop trap do_signal_stop() implemented both normal group stop and trap for group stop while ptraced. This approach has been enough but scheduled changes require trap mechanism which can be used in more generic manner and using group stop trap for generic trap site simplifies both userland visible interface and implementation. This patch adds a new jobctl flag - JOBCTL_TRAP_STOP. When set, it triggers a trap site, which behaves like group stop trap, in get_signal_to_deliver() after checking for pending signals. While ptraced, do_signal_stop() doesn't stop itself. It initiates group stop if requested and schedules JOBCTL_TRAP_STOP and returns. The caller - get_signal_to_deliver() - is responsible for checking whether TRAP_STOP is pending afterwards and handling it. ptrace_attach() is updated to use JOBCTL_TRAP_STOP instead of JOBCTL_STOP_PENDING and __ptrace_unlink() to clear all pending trap bits and TRAPPING so that TRAP_STOP and future trap bits don't linger after detach. While at it, add proper function comment to do_signal_stop() and make it return bool. -v2: __ptrace_unlink() updated to clear JOBCTL_TRAP_MASK and TRAPPING instead of JOBCTL_PENDING_MASK. This avoids accidentally clearing JOBCTL_STOP_CONSUME. Spotted by Oleg. -v3: do_signal_stop() updated to return %false without dropping siglock while ptraced and TRAP_STOP check moved inside for(;;) loop after group stop participation. This avoids unnecessary relocking and also will help avoiding unnecessary traps by consuming group stop before handling pending traps. -v4: Jobctl trap handling moved into a separate function - do_jobctl_trap(). Signed-off-by: Tejun Heo Cc: Oleg Nesterov --- include/linux/sched.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 5157bd9eee37..8bd84b83a35b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1810,17 +1810,21 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t * #define JOBCTL_STOP_DEQUEUED_BIT 16 /* stop signal dequeued */ #define JOBCTL_STOP_PENDING_BIT 17 /* task should stop for group stop */ #define JOBCTL_STOP_CONSUME_BIT 18 /* consume group stop count */ +#define JOBCTL_TRAP_STOP_BIT 19 /* trap for STOP */ #define JOBCTL_TRAPPING_BIT 21 /* switching to TRACED */ #define JOBCTL_STOP_DEQUEUED (1 << JOBCTL_STOP_DEQUEUED_BIT) #define JOBCTL_STOP_PENDING (1 << JOBCTL_STOP_PENDING_BIT) #define JOBCTL_STOP_CONSUME (1 << JOBCTL_STOP_CONSUME_BIT) +#define JOBCTL_TRAP_STOP (1 << JOBCTL_TRAP_STOP_BIT) #define JOBCTL_TRAPPING (1 << JOBCTL_TRAPPING_BIT) -#define JOBCTL_PENDING_MASK JOBCTL_STOP_PENDING +#define JOBCTL_TRAP_MASK JOBCTL_TRAP_STOP +#define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK) extern bool task_set_jobctl_pending(struct task_struct *task, unsigned int mask); +extern void task_clear_jobctl_trapping(struct task_struct *task); extern void task_clear_jobctl_pending(struct task_struct *task, unsigned int mask); -- cgit v1.2.3 From 3544d72a0e10d0aa1c1bd59ed77a53a59cdc12f7 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 14 Jun 2011 11:20:15 +0200 Subject: ptrace: implement PTRACE_SEIZE PTRACE_ATTACH implicitly issues SIGSTOP on attach which has side effects on tracee signal and job control states. This patch implements a new ptrace request PTRACE_SEIZE which attaches a tracee without trapping it or affecting its signal and job control states. The usage is the same with PTRACE_ATTACH but it takes PTRACE_SEIZE_* flags in @data. Currently, the only defined flag is PTRACE_SEIZE_DEVEL which is a temporary flag to enable PTRACE_SEIZE. PTRACE_SEIZE will change ptrace behaviors outside of attach itself. The changes will be implemented gradually and the DEVEL flag is to prevent programs which expect full SEIZE behavior from using it before all the behavior modifications are complete while allowing unit testing. The flag will be removed once SEIZE behaviors are completely implemented. * PTRACE_SEIZE, unlike ATTACH, doesn't force tracee to trap. After attaching tracee continues to run unless a trap condition occurs. * PTRACE_SEIZE doesn't affect signal or group stop state. * If PTRACE_SEIZE'd, group stop uses PTRACE_EVENT_STOP trap which uses exit_code of (signr | PTRACE_EVENT_STOP << 8) where signr is one of the stopping signals if group stop is in effect or SIGTRAP otherwise, and returns usual trap siginfo on PTRACE_GETSIGINFO instead of NULL. Seizing sets PT_SEIZED in ->ptrace of the tracee. This flag will be used to determine whether new SEIZE behaviors should be enabled. Test program follows. #define PTRACE_SEIZE 0x4206 #define PTRACE_SEIZE_DEVEL 0x80000000 static const struct timespec ts100ms = { .tv_nsec = 100000000 }; static const struct timespec ts1s = { .tv_sec = 1 }; static const struct timespec ts3s = { .tv_sec = 3 }; int main(int argc, char **argv) { pid_t tracee; tracee = fork(); if (tracee == 0) { nanosleep(&ts100ms, NULL); while (1) { printf("tracee: alive\n"); nanosleep(&ts1s, NULL); } } if (argc > 1) kill(tracee, SIGSTOP); nanosleep(&ts100ms, NULL); ptrace(PTRACE_SEIZE, tracee, NULL, (void *)(unsigned long)PTRACE_SEIZE_DEVEL); if (argc > 1) { waitid(P_PID, tracee, NULL, WSTOPPED); ptrace(PTRACE_CONT, tracee, NULL, NULL); } nanosleep(&ts3s, NULL); printf("tracer: exiting\n"); return 0; } When the above program is called w/o argument, tracee is seized while running and remains running. When tracer exits, tracee continues to run and print out messages. # ./test-seize-simple tracee: alive tracee: alive tracee: alive tracer: exiting tracee: alive tracee: alive When called with an argument, tracee is seized from stopped state and continued, and returns to stopped state when tracer exits. # ./test-seize tracee: alive tracee: alive tracee: alive tracer: exiting # ps -el|grep test-seize 1 T 0 4720 1 0 80 0 - 941 signal ttyS0 00:00:00 test-seize -v2: SEIZE doesn't schedule TRAP_STOP and leaves tracee running as Jan suggested. -v3: PTRACE_EVENT_STOP traps now report group stop state by signr. If group stop is in effect the stop signal number is returned as part of exit_code; otherwise, SIGTRAP. This was suggested by Denys and Oleg. Signed-off-by: Tejun Heo Cc: Jan Kratochvil Cc: Denys Vlasenko Cc: Oleg Nesterov --- include/linux/ptrace.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index e93ef1a54fc7..67ad3f152329 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -47,6 +47,11 @@ #define PTRACE_GETREGSET 0x4204 #define PTRACE_SETREGSET 0x4205 +#define PTRACE_SEIZE 0x4206 + +/* flags in @data for PTRACE_SEIZE */ +#define PTRACE_SEIZE_DEVEL 0x80000000 /* temp flag for development */ + /* options set using PTRACE_SETOPTIONS */ #define PTRACE_O_TRACESYSGOOD 0x00000001 #define PTRACE_O_TRACEFORK 0x00000002 @@ -65,6 +70,7 @@ #define PTRACE_EVENT_EXEC 4 #define PTRACE_EVENT_VFORK_DONE 5 #define PTRACE_EVENT_EXIT 6 +#define PTRACE_EVENT_STOP 7 #include @@ -77,6 +83,7 @@ * flags. When the a task is stopped the ptracer owns task->ptrace. */ +#define PT_SEIZED 0x00010000 /* SEIZE used, enable new behavior */ #define PT_PTRACED 0x00000001 #define PT_DTRACE 0x00000002 /* delayed trace (used on m68k, i386) */ #define PT_TRACESYSGOOD 0x00000004 -- cgit v1.2.3 From fca26f260c528ee51a2e451b5b200aeb528f3e09 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 14 Jun 2011 11:20:16 +0200 Subject: ptrace: implement PTRACE_INTERRUPT Currently, there's no way to trap a running ptracee short of sending a signal which has various side effects. This patch implements PTRACE_INTERRUPT which traps ptracee without any signal or job control related side effect. The implementation is almost trivial. It uses the group stop trap - SIGTRAP | PTRACE_EVENT_STOP << 8. A new trap flag JOBCTL_TRAP_INTERRUPT is added, which is set on PTRACE_INTERRUPT and cleared when any trap happens. As INTERRUPT should be useable regardless of the current state of tracee, task_is_traced() test in ptrace_check_attach() is skipped for INTERRUPT. PTRACE_INTERRUPT is available iff tracee is attached with PTRACE_SEIZE. Test program follows. #define PTRACE_SEIZE 0x4206 #define PTRACE_INTERRUPT 0x4207 #define PTRACE_SEIZE_DEVEL 0x80000000 static const struct timespec ts100ms = { .tv_nsec = 100000000 }; static const struct timespec ts1s = { .tv_sec = 1 }; static const struct timespec ts3s = { .tv_sec = 3 }; int main(int argc, char **argv) { pid_t tracee; tracee = fork(); if (tracee == 0) { nanosleep(&ts100ms, NULL); while (1) { printf("tracee: alive pid=%d\n", getpid()); nanosleep(&ts1s, NULL); } } if (argc > 1) kill(tracee, SIGSTOP); nanosleep(&ts100ms, NULL); ptrace(PTRACE_SEIZE, tracee, NULL, (void *)(unsigned long)PTRACE_SEIZE_DEVEL); if (argc > 1) { waitid(P_PID, tracee, NULL, WSTOPPED); ptrace(PTRACE_CONT, tracee, NULL, NULL); } nanosleep(&ts3s, NULL); printf("tracer: INTERRUPT and DETACH\n"); ptrace(PTRACE_INTERRUPT, tracee, NULL, NULL); waitid(P_PID, tracee, NULL, WSTOPPED); ptrace(PTRACE_DETACH, tracee, NULL, NULL); nanosleep(&ts3s, NULL); printf("tracer: exiting\n"); kill(tracee, SIGKILL); return 0; } When called without argument, tracee is seized from running state, interrupted and then detached back to running state. # ./test-interrupt tracee: alive pid=4546 tracee: alive pid=4546 tracee: alive pid=4546 tracer: INTERRUPT and DETACH tracee: alive pid=4546 tracee: alive pid=4546 tracee: alive pid=4546 tracer: exiting When called with argument, tracee is seized from stopped state, continued, interrupted and then detached back to stopped state. # ./test-interrupt 1 tracee: alive pid=4548 tracee: alive pid=4548 tracee: alive pid=4548 tracer: INTERRUPT and DETACH tracer: exiting Before PTRACE_INTERRUPT, once the tracee was running, there was no way to trap tracee and do PTRACE_DETACH without causing side effect. -v2: Updated to use task_set_jobctl_pending() so that it doesn't end up scheduling TRAP_STOP if child is dying which may make the child unkillable. Spotted by Oleg. Signed-off-by: Tejun Heo Cc: Oleg Nesterov --- include/linux/ptrace.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 67ad3f152329..ad754d1e0b13 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -48,6 +48,7 @@ #define PTRACE_SETREGSET 0x4205 #define PTRACE_SEIZE 0x4206 +#define PTRACE_INTERRUPT 0x4207 /* flags in @data for PTRACE_SEIZE */ #define PTRACE_SEIZE_DEVEL 0x80000000 /* temp flag for development */ -- cgit v1.2.3 From fb1d910c178ba0c5bc32d3e5a9e82e05b7aad3cd Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 14 Jun 2011 11:20:17 +0200 Subject: ptrace: implement TRAP_NOTIFY and use it for group stop events Currently there's no way for ptracer to find out whether group stop finished other than polling with INTERRUPT - GETSIGINFO - CONT sequence. This patch implements group stop notification for ptracer using STOP traps. When group stop state of a seized tracee changes, JOBCTL_TRAP_NOTIFY is set, which schedules a STOP trap which is sticky - it isn't cleared by other traps and at least one STOP trap will happen eventually. STOP trap is synchronization point for event notification and the tracer can determine the current group stop state by looking at the signal number portion of exit code (si_status from waitid(2) or si_code from PTRACE_GETSIGINFO). Notifications are generated both on start and end of group stops but, because group stop participation always happens before STOP trap, this doesn't cause an extra trap while tracee is participating in group stop. The symmetry will be useful later. Note that this notification works iff tracee is not trapped. Currently there is no way to be notified of group stop state changes while tracee is trapped. This will be addressed by a later patch. An example program follows. #define PTRACE_SEIZE 0x4206 #define PTRACE_INTERRUPT 0x4207 #define PTRACE_SEIZE_DEVEL 0x80000000 static const struct timespec ts1s = { .tv_sec = 1 }; int main(int argc, char **argv) { pid_t tracee, tracer; int i; tracee = fork(); if (!tracee) while (1) pause(); tracer = fork(); if (!tracer) { siginfo_t si; ptrace(PTRACE_SEIZE, tracee, NULL, (void *)(unsigned long)PTRACE_SEIZE_DEVEL); ptrace(PTRACE_INTERRUPT, tracee, NULL, NULL); repeat: waitid(P_PID, tracee, NULL, WSTOPPED); ptrace(PTRACE_GETSIGINFO, tracee, NULL, &si); if (!si.si_code) { printf("tracer: SIG %d\n", si.si_signo); ptrace(PTRACE_CONT, tracee, NULL, (void *)(unsigned long)si.si_signo); goto repeat; } printf("tracer: stopped=%d signo=%d\n", si.si_signo != SIGTRAP, si.si_signo); ptrace(PTRACE_CONT, tracee, NULL, NULL); goto repeat; } for (i = 0; i < 3; i++) { nanosleep(&ts1s, NULL); printf("mother: SIGSTOP\n"); kill(tracee, SIGSTOP); nanosleep(&ts1s, NULL); printf("mother: SIGCONT\n"); kill(tracee, SIGCONT); } nanosleep(&ts1s, NULL); kill(tracer, SIGKILL); kill(tracee, SIGKILL); return 0; } In the above program, tracer keeps tracee running and gets notification of each group stop state changes. # ./test-notify tracer: stopped=0 signo=5 mother: SIGSTOP tracer: SIG 19 tracer: stopped=1 signo=19 mother: SIGCONT tracer: stopped=0 signo=5 tracer: SIG 18 mother: SIGSTOP tracer: SIG 19 tracer: stopped=1 signo=19 mother: SIGCONT tracer: stopped=0 signo=5 tracer: SIG 18 mother: SIGSTOP tracer: SIG 19 tracer: stopped=1 signo=19 mother: SIGCONT tracer: stopped=0 signo=5 tracer: SIG 18 Signed-off-by: Tejun Heo Cc: Oleg Nesterov --- include/linux/sched.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 8bd84b83a35b..1854def284f5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1811,15 +1811,17 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t * #define JOBCTL_STOP_PENDING_BIT 17 /* task should stop for group stop */ #define JOBCTL_STOP_CONSUME_BIT 18 /* consume group stop count */ #define JOBCTL_TRAP_STOP_BIT 19 /* trap for STOP */ +#define JOBCTL_TRAP_NOTIFY_BIT 20 /* trap for NOTIFY */ #define JOBCTL_TRAPPING_BIT 21 /* switching to TRACED */ #define JOBCTL_STOP_DEQUEUED (1 << JOBCTL_STOP_DEQUEUED_BIT) #define JOBCTL_STOP_PENDING (1 << JOBCTL_STOP_PENDING_BIT) #define JOBCTL_STOP_CONSUME (1 << JOBCTL_STOP_CONSUME_BIT) #define JOBCTL_TRAP_STOP (1 << JOBCTL_TRAP_STOP_BIT) +#define JOBCTL_TRAP_NOTIFY (1 << JOBCTL_TRAP_NOTIFY_BIT) #define JOBCTL_TRAPPING (1 << JOBCTL_TRAPPING_BIT) -#define JOBCTL_TRAP_MASK JOBCTL_TRAP_STOP +#define JOBCTL_TRAP_MASK (JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY) #define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK) extern bool task_set_jobctl_pending(struct task_struct *task, -- cgit v1.2.3 From 544b2c91a9f14f9565af1972203438b7f49afd48 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 14 Jun 2011 11:20:18 +0200 Subject: ptrace: implement PTRACE_LISTEN The previous patch implemented async notification for ptrace but it only worked while trace is running. This patch introduces PTRACE_LISTEN which is suggested by Oleg Nestrov. It's allowed iff tracee is in STOP trap and puts tracee into quasi-running state - tracee never really runs but wait(2) and ptrace(2) consider it to be running. While ptracer is listening, tracee is allowed to re-enter STOP to notify an async event. Listening state is cleared on the first notification. Ptracer can also clear it by issuing INTERRUPT - tracee will re-trap into STOP with listening state cleared. This allows ptracer to monitor group stop state without running tracee - use INTERRUPT to put tracee into STOP trap, issue LISTEN and then wait(2) to wait for the next group stop event. When it happens, PTRACE_GETSIGINFO provides information to determine the current state. Test program follows. #define PTRACE_SEIZE 0x4206 #define PTRACE_INTERRUPT 0x4207 #define PTRACE_LISTEN 0x4208 #define PTRACE_SEIZE_DEVEL 0x80000000 static const struct timespec ts1s = { .tv_sec = 1 }; int main(int argc, char **argv) { pid_t tracee, tracer; int i; tracee = fork(); if (!tracee) while (1) pause(); tracer = fork(); if (!tracer) { siginfo_t si; ptrace(PTRACE_SEIZE, tracee, NULL, (void *)(unsigned long)PTRACE_SEIZE_DEVEL); ptrace(PTRACE_INTERRUPT, tracee, NULL, NULL); repeat: waitid(P_PID, tracee, NULL, WSTOPPED); ptrace(PTRACE_GETSIGINFO, tracee, NULL, &si); if (!si.si_code) { printf("tracer: SIG %d\n", si.si_signo); ptrace(PTRACE_CONT, tracee, NULL, (void *)(unsigned long)si.si_signo); goto repeat; } printf("tracer: stopped=%d signo=%d\n", si.si_signo != SIGTRAP, si.si_signo); if (si.si_signo != SIGTRAP) ptrace(PTRACE_LISTEN, tracee, NULL, NULL); else ptrace(PTRACE_CONT, tracee, NULL, NULL); goto repeat; } for (i = 0; i < 3; i++) { nanosleep(&ts1s, NULL); printf("mother: SIGSTOP\n"); kill(tracee, SIGSTOP); nanosleep(&ts1s, NULL); printf("mother: SIGCONT\n"); kill(tracee, SIGCONT); } nanosleep(&ts1s, NULL); kill(tracer, SIGKILL); kill(tracee, SIGKILL); return 0; } This is identical to the program to test TRAP_NOTIFY except that tracee is PTRACE_LISTEN'd instead of PTRACE_CONT'd when group stopped. This allows ptracer to monitor when group stop ends without running tracee. # ./test-listen tracer: stopped=0 signo=5 mother: SIGSTOP tracer: SIG 19 tracer: stopped=1 signo=19 mother: SIGCONT tracer: stopped=0 signo=5 tracer: SIG 18 mother: SIGSTOP tracer: SIG 19 tracer: stopped=1 signo=19 mother: SIGCONT tracer: stopped=0 signo=5 tracer: SIG 18 mother: SIGSTOP tracer: SIG 19 tracer: stopped=1 signo=19 mother: SIGCONT tracer: stopped=0 signo=5 tracer: SIG 18 -v2: Moved JOBCTL_LISTENING check in wait_task_stopped() into task_stopped_code() as suggested by Oleg. Signed-off-by: Tejun Heo Cc: Oleg Nesterov --- include/linux/ptrace.h | 1 + include/linux/sched.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index ad754d1e0b13..4f224f169524 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -49,6 +49,7 @@ #define PTRACE_SEIZE 0x4206 #define PTRACE_INTERRUPT 0x4207 +#define PTRACE_LISTEN 0x4208 /* flags in @data for PTRACE_SEIZE */ #define PTRACE_SEIZE_DEVEL 0x80000000 /* temp flag for development */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 1854def284f5..87f7ca7ed6f6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1813,6 +1813,7 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t * #define JOBCTL_TRAP_STOP_BIT 19 /* trap for STOP */ #define JOBCTL_TRAP_NOTIFY_BIT 20 /* trap for NOTIFY */ #define JOBCTL_TRAPPING_BIT 21 /* switching to TRACED */ +#define JOBCTL_LISTENING_BIT 22 /* ptracer is listening for events */ #define JOBCTL_STOP_DEQUEUED (1 << JOBCTL_STOP_DEQUEUED_BIT) #define JOBCTL_STOP_PENDING (1 << JOBCTL_STOP_PENDING_BIT) @@ -1820,6 +1821,7 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t * #define JOBCTL_TRAP_STOP (1 << JOBCTL_TRAP_STOP_BIT) #define JOBCTL_TRAP_NOTIFY (1 << JOBCTL_TRAP_NOTIFY_BIT) #define JOBCTL_TRAPPING (1 << JOBCTL_TRAPPING_BIT) +#define JOBCTL_LISTENING (1 << JOBCTL_LISTENING_BIT) #define JOBCTL_TRAP_MASK (JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY) #define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK) -- cgit v1.2.3 From d8ad7d1123a960cc9f276bd499f9325c6f5e1bd1 Mon Sep 17 00:00:00 2001 From: Takao Indoh Date: Tue, 29 Mar 2011 12:35:04 -0400 Subject: generic-ipi: Fix kexec boot crash by initializing call_single_queue before enabling interrupts There is a problem that kdump(2nd kernel) sometimes hangs up due to a pending IPI from 1st kernel. Kernel panic occurs because IPI comes before call_single_queue is initialized. To fix the crash, rename init_call_single_data() to call_function_init() and call it in start_kernel() so that call_single_queue can be initialized before enabling interrupts. The details of the crash are: (1) 2nd kernel boots up (2) A pending IPI from 1st kernel comes when irqs are first enabled in start_kernel(). (3) Kernel tries to handle the interrupt, but call_single_queue is not initialized yet at this point. As a result, in the generic_smp_call_function_single_interrupt(), NULL pointer dereference occurs when list_replace_init() tries to access &q->list.next. Therefore this patch changes the name of init_call_single_data() to call_function_init() and calls it before local_irq_enable() in start_kernel(). Signed-off-by: Takao Indoh Reviewed-by: WANG Cong Acked-by: Neil Horman Acked-by: Vivek Goyal Acked-by: Peter Zijlstra Cc: Milton Miller Cc: Jens Axboe Cc: Paul E. McKenney Cc: kexec@lists.infradead.org Link: http://lkml.kernel.org/r/D6CBEE2F420741indou.takao@jp.fujitsu.com Signed-off-by: Ingo Molnar --- include/linux/smp.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/smp.h b/include/linux/smp.h index 7ad824d510a2..8cc38d3bab0c 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -85,12 +85,15 @@ int smp_call_function_any(const struct cpumask *mask, * Generic and arch helpers */ #ifdef CONFIG_USE_GENERIC_SMP_HELPERS +void __init call_function_init(void); void generic_smp_call_function_single_interrupt(void); void generic_smp_call_function_interrupt(void); void ipi_call_lock(void); void ipi_call_unlock(void); void ipi_call_lock_irq(void); void ipi_call_unlock_irq(void); +#else +static inline void call_function_init(void) { } #endif /* @@ -134,7 +137,7 @@ static inline void smp_send_reschedule(int cpu) { } #define smp_prepare_boot_cpu() do {} while (0) #define smp_call_function_many(mask, func, info, wait) \ (up_smp_call_function(func, info)) -static inline void init_call_single_data(void) { } +static inline void call_function_init(void) { } static inline int smp_call_function_any(const struct cpumask *mask, smp_call_func_t func, -- cgit v1.2.3 From 879669961b11e7f40b518784863a259f735a72bf Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 17 Jun 2011 11:25:59 +0100 Subject: KEYS/DNS: Fix ____call_usermodehelper() to not lose the session keyring ____call_usermodehelper() now erases any credentials set by the subprocess_inf::init() function. The problem is that commit 17f60a7da150 ("capabilites: allow the application of capability limits to usermode helpers") creates and commits new credentials with prepare_kernel_cred() after the call to the init() function. This wipes all keyrings after umh_keys_init() is called. The best way to deal with this is to put the init() call just prior to the commit_creds() call, and pass the cred pointer to init(). That means that umh_keys_init() and suchlike can modify the credentials _before_ they are published and potentially in use by the rest of the system. This prevents request_key() from working as it is prevented from passing the session keyring it set up with the authorisation token to /sbin/request-key, and so the latter can't assume the authority to instantiate the key. This causes the in-kernel DNS resolver to fail with ENOKEY unconditionally. Signed-off-by: David Howells Acked-by: Eric Paris Tested-by: Jeff Layton Signed-off-by: Linus Torvalds --- include/linux/kmod.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kmod.h b/include/linux/kmod.h index d4a5c84c503d..0da38cf7db7b 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -45,7 +45,7 @@ static inline int request_module_nowait(const char *name, ...) { return -ENOSYS; #endif -struct key; +struct cred; struct file; enum umh_wait { @@ -62,7 +62,7 @@ struct subprocess_info { char **envp; enum umh_wait wait; int retval; - int (*init)(struct subprocess_info *info); + int (*init)(struct subprocess_info *info, struct cred *new); void (*cleanup)(struct subprocess_info *info); void *data; }; @@ -73,7 +73,7 @@ struct subprocess_info *call_usermodehelper_setup(char *path, char **argv, /* Set various pieces of state into the subprocess_info structure */ void call_usermodehelper_setfns(struct subprocess_info *info, - int (*init)(struct subprocess_info *info), + int (*init)(struct subprocess_info *info, struct cred *new), void (*cleanup)(struct subprocess_info *info), void *data); @@ -87,7 +87,7 @@ void call_usermodehelper_freeinfo(struct subprocess_info *info); static inline int call_usermodehelper_fns(char *path, char **argv, char **envp, enum umh_wait wait, - int (*init)(struct subprocess_info *info), + int (*init)(struct subprocess_info *info, struct cred *new), void (*cleanup)(struct subprocess_info *), void *data) { struct subprocess_info *info; -- cgit v1.2.3 From cca23d0b5350c9ca0473625c3f5879422ba534a6 Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Sat, 18 Jun 2011 02:51:52 -0700 Subject: Input: sh_keysc - 8x8 MODE_6 fix According to the data sheet for G4, AP4 and AG5 KEYSC MODE_6 is 8x8 keys. Bump up MAXKEYS to 64 too. Signed-off-by: Magnus Damm Reviewed-by: Simon Horman Signed-off-by: Dmitry Torokhov --- include/linux/input/sh_keysc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/input/sh_keysc.h b/include/linux/input/sh_keysc.h index 649dc7f12925..5d253cd93691 100644 --- a/include/linux/input/sh_keysc.h +++ b/include/linux/input/sh_keysc.h @@ -1,7 +1,7 @@ #ifndef __SH_KEYSC_H__ #define __SH_KEYSC_H__ -#define SH_KEYSC_MAXKEYS 49 +#define SH_KEYSC_MAXKEYS 64 struct sh_keysc_info { enum { SH_KEYSC_MODE_1, SH_KEYSC_MODE_2, SH_KEYSC_MODE_3, -- cgit v1.2.3 From be98ca652faa6468916a9b7608befff215a8ca70 Mon Sep 17 00:00:00 2001 From: Manoj Iyer Date: Thu, 26 May 2011 11:19:05 -0500 Subject: mmc: Add PCI fixup quirks for Ricoh 1180:e823 reader Signed-off-by: Manoj Iyer Cc: Signed-off-by: Chris Ball --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index a311008af5e1..f8910e155566 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1537,6 +1537,7 @@ #define PCI_DEVICE_ID_RICOH_RL5C476 0x0476 #define PCI_DEVICE_ID_RICOH_RL5C478 0x0478 #define PCI_DEVICE_ID_RICOH_R5C822 0x0822 +#define PCI_DEVICE_ID_RICOH_R5CE823 0xe823 #define PCI_DEVICE_ID_RICOH_R5C832 0x0832 #define PCI_DEVICE_ID_RICOH_R5C843 0x0843 -- cgit v1.2.3 From 4ff75b7cf3b06efb72a50e26008d09b259b1231b Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Sun, 19 Jun 2011 03:31:39 +0000 Subject: net: correct comment on where to place transmit time stamp hook. The comment for the skb_tx_timestamp() function suggests calling it just after a buffer is released to the hardware for transmission. However, for drivers that free the buffer in an ISR, this produces a race between the time stamp code and the ISR. This commit changes the comment to advise placing the call just before handing the buffer over to the hardware. Signed-off-by: Richard Cochran Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index e8b78ce14474..f3af147c211d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2023,8 +2023,7 @@ static inline void sw_tx_timestamp(struct sk_buff *skb) * skb_tx_timestamp() - Driver hook for transmit timestamping * * Ethernet MAC Drivers should call this function in their hard_xmit() - * function as soon as possible after giving the sk_buff to the MAC - * hardware, but before freeing the sk_buff. + * function immediately before giving the sk_buff to the MAC hardware. * * @skb: A socket buffer. */ -- cgit v1.2.3 From 155d109b5f52ffd749219b27702462dcd9cf4f8d Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Mon, 20 Jun 2011 13:23:14 +0200 Subject: block: add REQ_SECURE to REQ_COMMON_MASK Add REQ_SECURE flag to REQ_COMMON_MASK so that init_request_from_bio() can pass it to @req->cmd_flags. Signed-off-by: Namhyung Kim Acked-by: Adrian Hunter Cc: stable@kernel.org # 2.6.36 and newer Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 2a7cea53ca0d..6395692b2e7a 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -167,7 +167,7 @@ enum rq_flag_bits { (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) #define REQ_COMMON_MASK \ (REQ_WRITE | REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_DISCARD | \ - REQ_NOIDLE | REQ_FLUSH | REQ_FUA) + REQ_NOIDLE | REQ_FLUSH | REQ_FUA | REQ_SECURE) #define REQ_CLONE_MASK REQ_COMMON_MASK #define REQ_RAHEAD (1 << __REQ_RAHEAD) -- cgit v1.2.3 From 1816315b10862277a961a70ec394b6607983041d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jonathan=20Neusch=C3=A4fer?= Date: Sun, 19 Jun 2011 11:50:22 +0200 Subject: stop_machine.h: "disables preeempt" -> "disables preemption" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use the noun instead of a misspelled verb. Signed-off-by: Jonathan Neuschäfer Signed-off-by: Jiri Kosina --- include/linux/stop_machine.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index 092dc9b1ce7d..2d3f0b1b054c 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -94,7 +94,7 @@ static inline int try_stop_cpus(const struct cpumask *cpumask, * stop_machine "Bogolock": stop the entire machine, disable * interrupts. This is a very heavy lock, which is equivalent to * grabbing every spinlock (and more). So the "read" side to such a - * lock is anything which disables preeempt. + * lock is anything which disables preemption. */ #if defined(CONFIG_STOP_MACHINE) && defined(CONFIG_SMP) -- cgit v1.2.3 From e44ba033c5654dbfda53461c9b1f7dd9bd1d198f Mon Sep 17 00:00:00 2001 From: Vitaliy Ivanov Date: Mon, 20 Jun 2011 16:08:07 +0200 Subject: treewide: remove duplicate includes Many stupid corrections of duplicated includes based on the output of scripts/checkincludes.pl. Signed-off-by: Vitaliy Ivanov Signed-off-by: Jiri Kosina --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 1c777878f1ea..450ca245df84 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -376,7 +376,6 @@ struct inodes_stat_t { #include #include -#include #include #include #include -- cgit v1.2.3 From 482e0cd3dbaa70f2a2bead4b5f2c0d203ef654ba Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 19 Jun 2011 13:01:04 -0400 Subject: devcgroup_inode_permission: take "is it a device node" checks to inlined wrapper inode_permission() calls devcgroup_inode_permission() and almost all such calls are _not_ for device nodes; let's at least keep the common path straight... Signed-off-by: Al Viro --- include/linux/device_cgroup.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device_cgroup.h b/include/linux/device_cgroup.h index 0b0d9c39ed67..7aad1f440867 100644 --- a/include/linux/device_cgroup.h +++ b/include/linux/device_cgroup.h @@ -2,8 +2,16 @@ #include #ifdef CONFIG_CGROUP_DEVICE -extern int devcgroup_inode_permission(struct inode *inode, int mask); +extern int __devcgroup_inode_permission(struct inode *inode, int mask); extern int devcgroup_inode_mknod(int mode, dev_t dev); +static inline int devcgroup_inode_permission(struct inode *inode, int mask) +{ + if (likely(!inode->i_rdev)) + return 0; + if (!S_ISBLK(inode->i_mode) && !S_ISCHR(inode->i_mode)) + return 0; + return __devcgroup_inode_permission(inode, mask); +} #else static inline int devcgroup_inode_permission(struct inode *inode, int mask) { return 0; } -- cgit v1.2.3 From 440ca98fe8407808a9ad8e934f6e28408f546313 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Sat, 18 Jun 2011 01:01:59 +0200 Subject: bcma: clean exports of functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Function managing IRQs is needed for external drivers like b43. On the other side we do not expect writing any hosts drivers outside of bcma, so this is safe to do not export functions related to this. Signed-off-by: Rafał Miłecki Signed-off-by: John W. Linville --- include/linux/bcma/bcma_driver_pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma_driver_pci.h b/include/linux/bcma/bcma_driver_pci.h index b7e191cf00ec..3871b668caf9 100644 --- a/include/linux/bcma/bcma_driver_pci.h +++ b/include/linux/bcma/bcma_driver_pci.h @@ -85,5 +85,7 @@ struct bcma_drv_pci { #define pcicore_write32(pc, offset, val) bcma_write32((pc)->core, offset, val) extern void bcma_core_pci_init(struct bcma_drv_pci *pc); +extern int bcma_core_pci_irq_ctl(struct bcma_drv_pci *pc, + struct bcma_device *core, bool enable); #endif /* LINUX_BCMA_DRIVER_PCI_H_ */ -- cgit v1.2.3 From 19345cb299e8234006c5125151ab723e851a1d24 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Sun, 19 Jun 2011 18:33:46 -0400 Subject: NFSv4.1: file layout must consider pg_bsize for coalescing Otherwise we end up overflowing the rpc buffer size on the receive end. Signed-off-by: Benny Halevy Signed-off-by: Trond Myklebust --- include/linux/nfs_page.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 3a34e80ae92f..25311b3bedf8 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -92,6 +92,9 @@ extern int nfs_pageio_add_request(struct nfs_pageio_descriptor *, struct nfs_page *); extern void nfs_pageio_complete(struct nfs_pageio_descriptor *desc); extern void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *, pgoff_t); +extern bool nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, + struct nfs_page *prev, + struct nfs_page *req); extern int nfs_wait_on_request(struct nfs_page *); extern void nfs_unlock_request(struct nfs_page *req); extern int nfs_set_page_tag_locked(struct nfs_page *req); -- cgit v1.2.3 From 79568f5be06c91071697c065f01f3ebfbeb25a61 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 20 Jun 2011 20:13:49 -0700 Subject: vfs: i_state needs to be 'unsigned long' for now Commit 13e12d14e2dc ("vfs: reorganize 'struct inode' layout a bit") moved things around a bit changed i_state to be unsigned int instead of unsigned long. That was to help structure layout for the 64-bit case, and shrink 'struct inode' a bit (admittedly that only happened when spinlock debugging was on and i_flags didn't pack with i_lock). However, Meelis Roos reports that this results in unaligned exceptions on sprc, and it turns out that the bit-locking primitives that we use for the I_NEW bit want to use the bitops. Which want 'unsigned long', not 'unsigned int'. We really should fix the bit locking code to not have that kind of requirement, but that's a much bigger change. So for now, revert that field back to 'unsigned long' (but keep the other re-ordering changes from the commit that caused this). Andi points out that we have played games with this in 'struct page', so it's solvable with other hacks too, but since right now the struct inode size advantage only happens with some rare config options, it's not worth fighting. It _would_ be worth fixing the bitlocking code, though. Especially since there is no type safety in the bitlocking code (this never caused any warnings, and worked fine on x86-64, because the bitlocks take a 'void *' and x86-64 doesn't care that deeply about alignment). So it's currently a very easy problem to trigger by mistake and never notice. Reported-by: Meelis Roos Cc: Andi Kleen Cc: David Miller Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 1c777878f1ea..6e73e2e9ae33 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -744,7 +744,7 @@ struct inode { spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned int i_flags; - unsigned int i_state; + unsigned long i_state; #ifdef CONFIG_SECURITY void *i_security; #endif -- cgit v1.2.3 From 166e9278a3f98bab29ebb3d685a81cfb11b98be0 Mon Sep 17 00:00:00 2001 From: Ohad Ben-Cohen Date: Fri, 10 Jun 2011 21:42:27 +0300 Subject: x86/ia64: intel-iommu: move to drivers/iommu/ This should ease finding similarities with different platforms, with the intention of solving problems once in a generic framework which everyone can use. Note: to move intel-iommu.c, the declaration of pci_find_upstream_pcie_bridge() has to move from drivers/pci/pci.h to include/linux/pci.h. This is handled in this patch, too. As suggested, also drop DMAR's EXPERIMENTAL tag while we're at it. Compile-tested on x86_64. Signed-off-by: Ohad Ben-Cohen Signed-off-by: Joerg Roedel --- include/linux/pci.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index c446b5ca2d38..970bfe0941c3 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1589,5 +1589,16 @@ int pci_vpd_find_tag(const u8 *buf, unsigned int off, unsigned int len, u8 rdt); int pci_vpd_find_info_keyword(const u8 *buf, unsigned int off, unsigned int len, const char *kw); +/** + * pci_find_upstream_pcie_bridge - find upstream PCIe-to-PCI bridge of a device + * @pdev: the PCI device + * + * if the device is PCIE, return NULL + * if the device isn't connected to a PCIe bridge (that is its parent is a + * legacy PCI bridge and the bridge is directly connected to bus 0), return its + * parent + */ +struct pci_dev *pci_find_upstream_pcie_bridge(struct pci_dev *pdev); + #endif /* __KERNEL__ */ #endif /* LINUX_PCI_H */ -- cgit v1.2.3 From 403f81d8ee532c976d50a5e1051f14ec78ae8db3 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 14 Jun 2011 16:44:25 +0200 Subject: iommu/amd: Move missing parts to drivers/iommu A few parts of the driver were missing in drivers/iommu. Move them there to have the complete driver in that directory. Signed-off-by: Joerg Roedel --- include/linux/amd-iommu.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) create mode 100644 include/linux/amd-iommu.h (limited to 'include/linux') diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h new file mode 100644 index 000000000000..a6863a2dec1f --- /dev/null +++ b/include/linux/amd-iommu.h @@ -0,0 +1,35 @@ +/* + * Copyright (C) 2007-2010 Advanced Micro Devices, Inc. + * Author: Joerg Roedel + * Leo Duran + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#ifndef _ASM_X86_AMD_IOMMU_H +#define _ASM_X86_AMD_IOMMU_H + +#include + +#ifdef CONFIG_AMD_IOMMU + +extern int amd_iommu_detect(void); + +#else + +static inline int amd_iommu_detect(void) { return -ENODEV; } + +#endif + +#endif /* _ASM_X86_AMD_IOMMU_H */ -- cgit v1.2.3 From 5899a723b336da241b492583d7e55f1055f8f3b3 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Fri, 17 Jun 2011 08:20:40 +0000 Subject: dmaengine: shdma: add chcr_write/read function CHCR register position is not same in all DMAC. This patch adds new "chcr_offset" to decide it. Signed-off-by: Kuninori Morimoto Signed-off-by: Paul Mundt --- include/linux/sh_dma.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sh_dma.h b/include/linux/sh_dma.h index b08cd4efa15c..41fe4c2d6481 100644 --- a/include/linux/sh_dma.h +++ b/include/linux/sh_dma.h @@ -62,6 +62,7 @@ struct sh_dmae_pdata { const unsigned int *ts_shift; int ts_shift_num; u16 dmaor_init; + unsigned int chcr_offset; }; /* DMA register */ -- cgit v1.2.3 From 67c6269e5c998b53c2c08ce2befbbe20a7b6f57f Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Fri, 17 Jun 2011 08:20:51 +0000 Subject: dmaengine: shdma: add chcr_ie_bit IE bit position on CHCR register is not same in all DMAC. This patch adds new "chcr_ie_bit" to decide it. Signed-off-by: Kuninori Morimoto Signed-off-by: Paul Mundt --- include/linux/sh_dma.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sh_dma.h b/include/linux/sh_dma.h index 41fe4c2d6481..96803aa7b6bd 100644 --- a/include/linux/sh_dma.h +++ b/include/linux/sh_dma.h @@ -63,6 +63,7 @@ struct sh_dmae_pdata { int ts_shift_num; u16 dmaor_init; unsigned int chcr_offset; + u32 chcr_ie_bit; }; /* DMA register */ -- cgit v1.2.3 From e76c3af873025f5a704d56a28882be761e15657b Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Fri, 17 Jun 2011 08:20:56 +0000 Subject: dmaengine: shdma: add dmaor_is_32bit flag Signed-off-by: Kuninori Morimoto Signed-off-by: Paul Mundt --- include/linux/sh_dma.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sh_dma.h b/include/linux/sh_dma.h index 96803aa7b6bd..f25afc61e1c6 100644 --- a/include/linux/sh_dma.h +++ b/include/linux/sh_dma.h @@ -64,6 +64,8 @@ struct sh_dmae_pdata { u16 dmaor_init; unsigned int chcr_offset; u32 chcr_ie_bit; + + unsigned int dmaor_is_32bit:1; }; /* DMA register */ -- cgit v1.2.3 From 260bf2c5f69f419b04b6861ca91565b5fb16ce48 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Fri, 17 Jun 2011 08:21:05 +0000 Subject: dmaengine: shdma: add .needs_tend_set / .no_dmars flags Signed-off-by: Kuninori Morimoto Signed-off-by: Paul Mundt --- include/linux/sh_dma.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sh_dma.h b/include/linux/sh_dma.h index f25afc61e1c6..cb2dd118cc0f 100644 --- a/include/linux/sh_dma.h +++ b/include/linux/sh_dma.h @@ -66,6 +66,8 @@ struct sh_dmae_pdata { u32 chcr_ie_bit; unsigned int dmaor_is_32bit:1; + unsigned int needs_tend_set:1; + unsigned int no_dmars:1; }; /* DMA register */ @@ -75,6 +77,8 @@ struct sh_dmae_pdata { #define CHCR 0x0C #define DMAOR 0x40 +#define TEND 0x18 /* USB-DMAC */ + /* DMAOR definitions */ #define DMAOR_AE 0x00000004 #define DMAOR_NMIF 0x00000002 -- cgit v1.2.3 From cbb49c2665eebfd1fa2e491403684d0542662137 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 21 Jun 2011 10:59:34 -0600 Subject: dt: Add default match table for bus ids No need for most platforms to define their own bus table when calling of_platform_populate(). Supply a stock one. Signed-off-by: Grant Likely --- include/linux/of_platform.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index fb51ae38cea7..8f023f889a8a 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -40,6 +40,8 @@ struct of_platform_driver #define to_of_platform_driver(drv) \ container_of(drv,struct of_platform_driver, driver) +extern const struct of_device_id of_default_bus_match_table[]; + /* Platform drivers register/unregister */ extern struct platform_device *of_device_alloc(struct device_node *np, const char *bus_id, -- cgit v1.2.3 From 29d4f8a4974aacf46b028fa92f9dd3ffdba3e614 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 21 Jun 2011 10:59:34 -0600 Subject: dt: add of_platform_populate() for creating device from the device tree of_platform_populate() is similar to of_platform_bus_probe() except that it strictly enforces that all device nodes must have a compatible property, and it can be used to register devices (not buses) which are children of the root node. Signed-off-by: Grant Likely --- include/linux/of_platform.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index 8f023f889a8a..839023351176 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -57,6 +57,9 @@ extern struct platform_device *of_platform_device_create(struct device_node *np, extern int of_platform_bus_probe(struct device_node *root, const struct of_device_id *matches, struct device *parent); +extern int of_platform_populate(struct device_node *root, + const struct of_device_id *matches, + struct device *parent); #endif /* !CONFIG_SPARC */ #endif /* CONFIG_OF_DEVICE */ -- cgit v1.2.3 From 15c3597d6ea47e8f3caf068887c4666165df63ad Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 21 Jun 2011 10:59:35 -0600 Subject: dt/platform: allow device name to be overridden Some platform code has specific requirements on the naming of devices. This patch allows callers of of_platform_populate() to provide a device name lookup table. Signed-off-by: Grant Likely --- include/linux/of_platform.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index 839023351176..5a6f458a4bb7 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -19,6 +19,40 @@ #include #include +/** + * struct of_dev_auxdata - lookup table entry for device names & platform_data + * @compatible: compatible value of node to match against node + * @phys_addr: Start address of registers to match against node + * @name: Name to assign for matching nodes + * @platform_data: platform_data to assign for matching nodes + * + * This lookup table allows the caller of of_platform_populate() to override + * the names of devices when creating devices from the device tree. The table + * should be terminated with an empty entry. It also allows the platform_data + * pointer to be set. + * + * The reason for this functionality is that some Linux infrastructure uses + * the device name to look up a specific device, but the Linux-specific names + * are not encoded into the device tree, so the kernel needs to provide specific + * values. + * + * Note: Using an auxdata lookup table should be considered a last resort when + * converting a platform to use the DT. Normally the automatically generated + * device name will not matter, and drivers should obtain data from the device + * node instead of from an anonymouns platform_data pointer. + */ +struct of_dev_auxdata { + char *compatible; + resource_size_t phys_addr; + char *name; + void *platform_data; +}; + +/* Macro to simplify populating a lookup table */ +#define OF_DEV_AUXDATA(_compat,_phys,_name,_pdata) \ + { .compatible = _compat, .phys_addr = _phys, .name = _name, \ + .platform_data = _pdata } + /** * of_platform_driver - Legacy of-aware driver for platform devices. * @@ -59,6 +93,7 @@ extern int of_platform_bus_probe(struct device_node *root, struct device *parent); extern int of_platform_populate(struct device_node *root, const struct of_device_id *matches, + const struct of_dev_auxdata *lookup, struct device *parent); #endif /* !CONFIG_SPARC */ -- cgit v1.2.3 From f76b168b6f117a49d36307053e1acbe30580ea5b Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Sat, 18 Jun 2011 20:22:23 +0200 Subject: PM: Rename dev_pm_info.in_suspend to is_prepared This patch (as1473) renames the "in_suspend" field in struct dev_pm_info to "is_prepared", in preparation for an upcoming change. The new name is more descriptive of what the field really means. Signed-off-by: Alan Stern Signed-off-by: Rafael J. Wysocki Cc: stable@kernel.org --- include/linux/device.h | 4 ++-- include/linux/pm.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index c66111affca9..553fd37b173b 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -654,13 +654,13 @@ static inline int device_is_registered(struct device *dev) static inline void device_enable_async_suspend(struct device *dev) { - if (!dev->power.in_suspend) + if (!dev->power.is_prepared) dev->power.async_suspend = true; } static inline void device_disable_async_suspend(struct device *dev) { - if (!dev->power.in_suspend) + if (!dev->power.is_prepared) dev->power.async_suspend = false; } diff --git a/include/linux/pm.h b/include/linux/pm.h index 3160648ccdda..cc536bd80984 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -425,7 +425,7 @@ struct dev_pm_info { pm_message_t power_state; unsigned int can_wakeup:1; unsigned int async_suspend:1; - unsigned int in_suspend:1; /* Owned by the PM core */ + bool is_prepared:1; /* Owned by the PM core */ spinlock_t lock; #ifdef CONFIG_PM_SLEEP struct list_head entry; -- cgit v1.2.3 From 6d0e0e84f66d32c33511984dd3badd32364b863c Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Sat, 18 Jun 2011 22:42:09 +0200 Subject: PM: Fix async resume following suspend failure The PM core doesn't handle suspend failures correctly when it comes to asynchronously suspended devices. These devices are moved onto the dpm_suspended_list as soon as the corresponding async thread is started up, and they remain on the list even if they fail to suspend or the sleep transition is cancelled before they get suspended. As a result, when the PM core unwinds the transition, it tries to resume the devices even though they were never suspended. This patch (as1474) fixes the problem by adding a new "is_suspended" flag to dev_pm_info. Devices are resumed only if the flag is set. [rjw: * Moved the dev->power.is_suspended check into device_resume(), because we need to complete dev->power.completion and clear dev->power.is_prepared too for devices whose dev->power.is_suspended flags are unset. * Fixed __device_suspend() to avoid setting dev->power.is_suspended if async_error is different from zero.] Signed-off-by: Alan Stern Signed-off-by: Rafael J. Wysocki Cc: stable@kernel.org --- include/linux/pm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index cc536bd80984..411e4f4be52b 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -426,6 +426,7 @@ struct dev_pm_info { unsigned int can_wakeup:1; unsigned int async_suspend:1; bool is_prepared:1; /* Owned by the PM core */ + bool is_suspended:1; /* Ditto */ spinlock_t lock; #ifdef CONFIG_PM_SLEEP struct list_head entry; -- cgit v1.2.3 From f4b5ad26bcb983c493e131ff34b2fa60100c82e5 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Mon, 20 Jun 2011 15:15:56 +0000 Subject: cnic, bnx2i: Add support for new devices - 57800, 57810, and 57840 And change iSCSI RQ doorbell size from 16B to 64B to match new firmware. Signed-off-by: Michael Chan Signed-off-by: Eddie Wai Signed-off-by: David S. Miller --- include/linux/pci_ids.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index a311008af5e1..d76bd9e4c784 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2102,6 +2102,9 @@ #define PCI_DEVICE_ID_TIGON3_5761E 0x1680 #define PCI_DEVICE_ID_TIGON3_5761 0x1681 #define PCI_DEVICE_ID_TIGON3_5764 0x1684 +#define PCI_DEVICE_ID_NX2_57800 0x168a +#define PCI_DEVICE_ID_NX2_57840 0x168d +#define PCI_DEVICE_ID_NX2_57810 0x168e #define PCI_DEVICE_ID_TIGON3_5787M 0x1693 #define PCI_DEVICE_ID_TIGON3_5782 0x1696 #define PCI_DEVICE_ID_TIGON3_5784 0x1698 @@ -2109,11 +2112,17 @@ #define PCI_DEVICE_ID_TIGON3_5787 0x169b #define PCI_DEVICE_ID_TIGON3_5788 0x169c #define PCI_DEVICE_ID_TIGON3_5789 0x169d +#define PCI_DEVICE_ID_NX2_57800_MF 0x16a5 #define PCI_DEVICE_ID_TIGON3_5702X 0x16a6 #define PCI_DEVICE_ID_TIGON3_5703X 0x16a7 #define PCI_DEVICE_ID_TIGON3_5704S 0x16a8 +#define PCI_DEVICE_ID_NX2_57800_VF 0x16a9 #define PCI_DEVICE_ID_NX2_5706S 0x16aa +#define PCI_DEVICE_ID_NX2_57840_MF 0x16ab #define PCI_DEVICE_ID_NX2_5708S 0x16ac +#define PCI_DEVICE_ID_NX2_57840_VF 0x16ad +#define PCI_DEVICE_ID_NX2_57810_MF 0x16ae +#define PCI_DEVICE_ID_NX2_57810_VF 0x16af #define PCI_DEVICE_ID_TIGON3_5702A3 0x16c6 #define PCI_DEVICE_ID_TIGON3_5703A3 0x16c7 #define PCI_DEVICE_ID_TIGON3_5781 0x16dd -- cgit v1.2.3 From 314b4778ed579f29b6d46ba90dbf31314c13805f Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 21 Jun 2011 07:34:37 +0000 Subject: net: dcbnl, add multicast group for DCB Now that dcbnl is being used in many cases by more than a single agent it is beneficial to be notified when some entity either driver or user space has changed the DCB attributes. Today applications either end up polling the interface or relying on a user space database to maintain the DCB state and post events. Polling is a poor solution for obvious reasons. And relying on a user space database has its own downside. Namely it has created strange boot dependencies requiring the database be populated before any applications dependent on DCB attributes starts or the application goes into a polling loop. Populating the database requires negotiating link setting with the peer and can take anywhere from less than a second up to a few seconds depending on the switch implementation. Perhaps more importantly if another application or an embedded agent sets a DCB link attribute the database has no way of knowing other than polling the kernel. This prevents applications from responding quickly to changes in link events which at least in the FCoE case and probably any other protocols expecting a lossless link may result in IO errors. By adding a multicast group for DCB we have clean way to disseminate kernel DCB link attributes up to user space. Avoiding the need for user space to maintain a coherant database and disperse events that potentially do not reflect the current link state. Signed-off-by: John Fastabend Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index bbad657a3725..c81226a9a35c 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -585,6 +585,8 @@ enum rtnetlink_groups { #define RTNLGRP_PHONET_IFADDR RTNLGRP_PHONET_IFADDR RTNLGRP_PHONET_ROUTE, #define RTNLGRP_PHONET_ROUTE RTNLGRP_PHONET_ROUTE + RTNLGRP_DCB, +#define RTNLGRP_DCB RTNLGRP_DCB __RTNLGRP_MAX }; #define RTNLGRP_MAX (__RTNLGRP_MAX - 1) -- cgit v1.2.3 From f9ae7e4b515c4d56baf6e0e84ebee2e03ae57a25 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 21 Jun 2011 07:34:48 +0000 Subject: dcb: Add ieee_dcb_delapp() and dcb op to delete app entry Now that we allow multiple IEEE App entries we need a way to remove specific entries. To do this add the ieee_dcb_delapp() routine. Additionaly drivers may need to remove the APP entry from their firmware tables. Add dcb ops routine to handle this. Signed-off-by: John Fastabend Signed-off-by: David S. Miller --- include/linux/dcbnl.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dcbnl.h b/include/linux/dcbnl.h index c52280047e2c..66a67235e729 100644 --- a/include/linux/dcbnl.h +++ b/include/linux/dcbnl.h @@ -203,6 +203,7 @@ struct dcbmsg { * @DCB_CMD_GFEATCFG: get DCBX features flags * @DCB_CMD_SFEATCFG: set DCBX features negotiation flags * @DCB_CMD_CEE_GET: get CEE aggregated configuration + * @DCB_CMD_IEEE_DEL: delete IEEE 802.1Qaz configuration */ enum dcbnl_commands { DCB_CMD_UNDEFINED, @@ -246,6 +247,7 @@ enum dcbnl_commands { DCB_CMD_SFEATCFG, DCB_CMD_CEE_GET, + DCB_CMD_IEEE_DEL, __DCB_CMD_ENUM_MAX, DCB_CMD_MAX = __DCB_CMD_ENUM_MAX - 1, -- cgit v1.2.3 From b7f080cfe223b3b7424872639d153695615a9255 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 16 Jun 2011 11:01:34 +0000 Subject: net: remove mm.h inclusion from netdevice.h Remove linux/mm.h inclusion from netdevice.h -- it's unused (I've checked manually). To prevent mm.h inclusion via other channels also extract "enum dma_data_direction" definition into separate header. This tiny piece is what gluing netdevice.h with mm.h via "netdevice.h => dmaengine.h => dma-mapping.h => scatterlist.h => mm.h". Removal of mm.h from scatterlist.h was tried and was found not feasible on most archs, so the link was cutoff earlier. Hope people are OK with tiny include file. Note, that mm_types.h is still dragged in, but it is a separate story. Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- include/linux/dma-direction.h | 13 +++++++++++++ include/linux/dma-mapping.h | 10 +--------- include/linux/dmaengine.h | 4 +++- include/linux/netdevice.h | 1 - 4 files changed, 17 insertions(+), 11 deletions(-) create mode 100644 include/linux/dma-direction.h (limited to 'include/linux') diff --git a/include/linux/dma-direction.h b/include/linux/dma-direction.h new file mode 100644 index 000000000000..95b6a82f5951 --- /dev/null +++ b/include/linux/dma-direction.h @@ -0,0 +1,13 @@ +#ifndef _LINUX_DMA_DIRECTION_H +#define _LINUX_DMA_DIRECTION_H +/* + * These definitions mirror those in pci.h, so they can be used + * interchangeably with their PCI_ counterparts. + */ +enum dma_data_direction { + DMA_BIDIRECTIONAL = 0, + DMA_TO_DEVICE = 1, + DMA_FROM_DEVICE = 2, + DMA_NONE = 3, +}; +#endif diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index ba8319ae5fcc..1a167c48d84d 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -4,17 +4,9 @@ #include #include #include +#include #include -/* These definitions mirror those in pci.h, so they can be used - * interchangeably with their PCI_ counterparts */ -enum dma_data_direction { - DMA_BIDIRECTIONAL = 0, - DMA_TO_DEVICE = 1, - DMA_FROM_DEVICE = 2, - DMA_NONE = 3, -}; - struct dma_map_ops { void* (*alloc_coherent)(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp); diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index eee7addec282..8fbf40e0713c 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -23,7 +23,9 @@ #include #include -#include +#include + +struct scatterlist; /** * typedef dma_cookie_t - an opaque DMA cookie diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 22a8ceca0ed0..011eb89e9582 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -34,7 +34,6 @@ #include #include #include -#include #include #include #include -- cgit v1.2.3 From d21142ece414ce1088cfcae760689aa60d6fee80 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 17 Jun 2011 16:50:34 +0200 Subject: ptrace: kill task_ptrace() task_ptrace(task) simply dereferences task->ptrace and isn't even used consistently only adding confusion. Kill it and directly access ->ptrace instead. This doesn't introduce any behavior change. Signed-off-by: Tejun Heo Signed-off-by: Oleg Nesterov --- include/linux/ptrace.h | 11 ----------- include/linux/tracehook.h | 16 ++++++++-------- 2 files changed, 8 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 4f224f169524..3ff20b322598 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -145,17 +145,6 @@ int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr, int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr, unsigned long data); -/** - * task_ptrace - return %PT_* flags that apply to a task - * @task: pointer to &task_struct in question - * - * Returns the %PT_* flags that apply to @task. - */ -static inline int task_ptrace(struct task_struct *task) -{ - return task->ptrace; -} - /** * ptrace_event - possibly stop for a ptrace event notification * @mask: %PT_* bit to check in @current->ptrace diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 15745cdd32ce..a3e838784f43 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -63,7 +63,7 @@ struct linux_binprm; */ static inline int tracehook_expect_breakpoints(struct task_struct *task) { - return (task_ptrace(task) & PT_PTRACED) != 0; + return (task->ptrace & PT_PTRACED) != 0; } /* @@ -71,7 +71,7 @@ static inline int tracehook_expect_breakpoints(struct task_struct *task) */ static inline void ptrace_report_syscall(struct pt_regs *regs) { - int ptrace = task_ptrace(current); + int ptrace = current->ptrace; if (!(ptrace & PT_PTRACED)) return; @@ -155,7 +155,7 @@ static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step) static inline int tracehook_unsafe_exec(struct task_struct *task) { int unsafe = 0; - int ptrace = task_ptrace(task); + int ptrace = task->ptrace; if (ptrace & PT_PTRACED) { if (ptrace & PT_PTRACE_CAP) unsafe |= LSM_UNSAFE_PTRACE_CAP; @@ -178,7 +178,7 @@ static inline int tracehook_unsafe_exec(struct task_struct *task) */ static inline struct task_struct *tracehook_tracer_task(struct task_struct *tsk) { - if (task_ptrace(tsk) & PT_PTRACED) + if (tsk->ptrace & PT_PTRACED) return rcu_dereference(tsk->parent); return NULL; } @@ -202,7 +202,7 @@ static inline void tracehook_report_exec(struct linux_binfmt *fmt, struct pt_regs *regs) { if (!ptrace_event(PT_TRACE_EXEC, PTRACE_EVENT_EXEC, 0) && - unlikely(task_ptrace(current) & PT_PTRACED)) + unlikely(current->ptrace & PT_PTRACED)) send_sig(SIGTRAP, current, 0); } @@ -285,7 +285,7 @@ static inline void tracehook_report_clone(struct pt_regs *regs, unsigned long clone_flags, pid_t pid, struct task_struct *child) { - if (unlikely(task_ptrace(child))) { + if (unlikely(child->ptrace)) { /* * It doesn't matter who attached/attaching to this * task, the pending SIGSTOP is right in any case. @@ -403,7 +403,7 @@ static inline void tracehook_signal_handler(int sig, siginfo_t *info, static inline int tracehook_consider_ignored_signal(struct task_struct *task, int sig) { - return (task_ptrace(task) & PT_PTRACED) != 0; + return (task->ptrace & PT_PTRACED) != 0; } /** @@ -422,7 +422,7 @@ static inline int tracehook_consider_ignored_signal(struct task_struct *task, static inline int tracehook_consider_fatal_signal(struct task_struct *task, int sig) { - return (task_ptrace(task) & PT_PTRACED) != 0; + return (task->ptrace & PT_PTRACED) != 0; } #define DEATH_REAP -1 -- cgit v1.2.3 From 643ad8388e189dfd14ef76972cf7dc394b3cbebd Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 17 Jun 2011 16:50:35 +0200 Subject: ptrace: introduce ptrace_event_enabled() and simplify ptrace_event() and tracehook_prepare_clone() This patch implements ptrace_event_enabled() which tests whether a given PTRACE_EVENT_* is enabled and use it to simplify ptrace_event() and tracehook_prepare_clone(). PT_EVENT_FLAG() macro is added which calculates PT_TRACE_* flag from PTRACE_EVENT_*. This is used to define PT_TRACE_* flags and by ptrace_event_enabled() to find the matching flag. This is used to make ptrace_event() and tracehook_prepare_clone() simpler. * ptrace_event() callers were responsible for providing mask to test whether the event was enabled. This patch implements ptrace_event_enabled() and make ptrace_event() drop @mask and determine whether the event is enabled from @event. Note that @event is constant and this conversion doesn't add runtime overhead. All conversions except tracehook_report_clone_complete() are trivial. tracehook_report_clone_complete() used to use 0 for @mask (always enabled) but now tests whether the specified event is enabled. This doesn't cause any behavior difference as it's guaranteed that the event specified by @trace is enabled. * tracehook_prepare_clone() now only determines which event is applicable and use ptrace_event_enabled() for enable test. This doesn't introduce any behavior change. Signed-off-by: Tejun Heo Signed-off-by: Oleg Nesterov --- include/linux/ptrace.h | 46 ++++++++++++++++++++++++++++++++-------------- include/linux/tracehook.h | 26 +++++++++++++------------- 2 files changed, 45 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 3ff20b322598..18feac6f441e 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -90,12 +90,17 @@ #define PT_DTRACE 0x00000002 /* delayed trace (used on m68k, i386) */ #define PT_TRACESYSGOOD 0x00000004 #define PT_PTRACE_CAP 0x00000008 /* ptracer can follow suid-exec */ -#define PT_TRACE_FORK 0x00000010 -#define PT_TRACE_VFORK 0x00000020 -#define PT_TRACE_CLONE 0x00000040 -#define PT_TRACE_EXEC 0x00000080 -#define PT_TRACE_VFORK_DONE 0x00000100 -#define PT_TRACE_EXIT 0x00000200 + +/* PT_TRACE_* event enable flags */ +#define PT_EVENT_FLAG_SHIFT 4 +#define PT_EVENT_FLAG(event) (1 << (PT_EVENT_FLAG_SHIFT + (event) - 1)) + +#define PT_TRACE_FORK PT_EVENT_FLAG(PTRACE_EVENT_FORK) +#define PT_TRACE_VFORK PT_EVENT_FLAG(PTRACE_EVENT_VFORK) +#define PT_TRACE_CLONE PT_EVENT_FLAG(PTRACE_EVENT_CLONE) +#define PT_TRACE_EXEC PT_EVENT_FLAG(PTRACE_EVENT_EXEC) +#define PT_TRACE_VFORK_DONE PT_EVENT_FLAG(PTRACE_EVENT_VFORK_DONE) +#define PT_TRACE_EXIT PT_EVENT_FLAG(PTRACE_EVENT_EXIT) #define PT_TRACE_MASK 0x000003f4 @@ -145,26 +150,39 @@ int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr, int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr, unsigned long data); +/** + * ptrace_event_enabled - test whether a ptrace event is enabled + * @task: ptracee of interest + * @event: %PTRACE_EVENT_* to test + * + * Test whether @event is enabled for ptracee @task. + * + * Returns %true if @event is enabled, %false otherwise. + */ +static inline bool ptrace_event_enabled(struct task_struct *task, int event) +{ + return task->ptrace & PT_EVENT_FLAG(event); +} + /** * ptrace_event - possibly stop for a ptrace event notification - * @mask: %PT_* bit to check in @current->ptrace - * @event: %PTRACE_EVENT_* value to report if @mask is set + * @event: %PTRACE_EVENT_* value to report * @message: value for %PTRACE_GETEVENTMSG to return * - * This checks the @mask bit to see if ptrace wants stops for this event. - * If so we stop, reporting @event and @message to the ptrace parent. + * Check whether @event is enabled and, if so, report @event and @message + * to the ptrace parent. * * Returns nonzero if we did a ptrace notification, zero if not. * * Called without locks. */ -static inline int ptrace_event(int mask, int event, unsigned long message) +static inline int ptrace_event(int event, unsigned long message) { - if (mask && likely(!(current->ptrace & mask))) - return 0; + if (likely(!ptrace_event_enabled(current, event))) + return false; current->ptrace_message = message; ptrace_notify((event << 8) | SIGTRAP); - return 1; + return true; } /** diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index a3e838784f43..7d38571b0c05 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -201,7 +201,7 @@ static inline void tracehook_report_exec(struct linux_binfmt *fmt, struct linux_binprm *bprm, struct pt_regs *regs) { - if (!ptrace_event(PT_TRACE_EXEC, PTRACE_EVENT_EXEC, 0) && + if (!ptrace_event(PTRACE_EVENT_EXEC, 0) && unlikely(current->ptrace & PT_PTRACED)) send_sig(SIGTRAP, current, 0); } @@ -218,7 +218,7 @@ static inline void tracehook_report_exec(struct linux_binfmt *fmt, */ static inline void tracehook_report_exit(long *exit_code) { - ptrace_event(PT_TRACE_EXIT, PTRACE_EVENT_EXIT, *exit_code); + ptrace_event(PTRACE_EVENT_EXIT, *exit_code); } /** @@ -232,19 +232,19 @@ static inline void tracehook_report_exit(long *exit_code) */ static inline int tracehook_prepare_clone(unsigned clone_flags) { + int event = 0; + if (clone_flags & CLONE_UNTRACED) return 0; - if (clone_flags & CLONE_VFORK) { - if (current->ptrace & PT_TRACE_VFORK) - return PTRACE_EVENT_VFORK; - } else if ((clone_flags & CSIGNAL) != SIGCHLD) { - if (current->ptrace & PT_TRACE_CLONE) - return PTRACE_EVENT_CLONE; - } else if (current->ptrace & PT_TRACE_FORK) - return PTRACE_EVENT_FORK; + if (clone_flags & CLONE_VFORK) + event = PTRACE_EVENT_VFORK; + else if ((clone_flags & CSIGNAL) != SIGCHLD) + event = PTRACE_EVENT_CLONE; + else + event = PTRACE_EVENT_FORK; - return 0; + return ptrace_event_enabled(current, event) ? event : 0; } /** @@ -318,7 +318,7 @@ static inline void tracehook_report_clone_complete(int trace, struct task_struct *child) { if (unlikely(trace)) - ptrace_event(0, trace, pid); + ptrace_event(trace, pid); } /** @@ -336,7 +336,7 @@ static inline void tracehook_report_clone_complete(int trace, static inline void tracehook_report_vfork_done(struct task_struct *child, pid_t pid) { - ptrace_event(PT_TRACE_VFORK_DONE, PTRACE_EVENT_VFORK_DONE, pid); + ptrace_event(PTRACE_EVENT_VFORK_DONE, pid); } /** -- cgit v1.2.3 From f3c04b934d429b1ace21866f011b66de328c0dc9 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 17 Jun 2011 16:50:36 +0200 Subject: ptrace: move SIGTRAP on exec(2) logic to ptrace_event() Move SIGTRAP on exec(2) logic from tracehook_report_exec() to ptrace_event(). This is part of changes to make ptrace_event() smarter and handle ptrace event related details in one place. This doesn't introduce any behavior change. Signed-off-by: Tejun Heo Signed-off-by: Oleg Nesterov --- include/linux/ptrace.h | 16 ++++++++-------- include/linux/tracehook.h | 4 +--- 2 files changed, 9 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 18feac6f441e..b546fd6c3506 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -172,17 +172,17 @@ static inline bool ptrace_event_enabled(struct task_struct *task, int event) * Check whether @event is enabled and, if so, report @event and @message * to the ptrace parent. * - * Returns nonzero if we did a ptrace notification, zero if not. - * * Called without locks. */ -static inline int ptrace_event(int event, unsigned long message) +static inline void ptrace_event(int event, unsigned long message) { - if (likely(!ptrace_event_enabled(current, event))) - return false; - current->ptrace_message = message; - ptrace_notify((event << 8) | SIGTRAP); - return true; + if (unlikely(ptrace_event_enabled(current, event))) { + current->ptrace_message = message; + ptrace_notify((event << 8) | SIGTRAP); + } else if (event == PTRACE_EVENT_EXEC && unlikely(current->ptrace)) { + /* legacy EXEC report via SIGTRAP */ + send_sig(SIGTRAP, current, 0); + } } /** diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 7d38571b0c05..3b68aa842a92 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -201,9 +201,7 @@ static inline void tracehook_report_exec(struct linux_binfmt *fmt, struct linux_binprm *bprm, struct pt_regs *regs) { - if (!ptrace_event(PTRACE_EVENT_EXEC, 0) && - unlikely(current->ptrace & PT_PTRACED)) - send_sig(SIGTRAP, current, 0); + ptrace_event(PTRACE_EVENT_EXEC, 0); } /** -- cgit v1.2.3 From a288eecce5253cc1565d400a52b9b476a157e040 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 17 Jun 2011 16:50:37 +0200 Subject: ptrace: kill trivial tracehooks At this point, tracehooks aren't useful to mainline kernel and mostly just add an extra layer of obfuscation. Although they have comments, without actual in-kernel users, it is difficult to tell what are their assumptions and they're actually trying to achieve. To mainline kernel, they just aren't worth keeping around. This patch kills the following trivial tracehooks. * Ones testing whether task is ptraced. Replace with ->ptrace test. tracehook_expect_breakpoints() tracehook_consider_ignored_signal() tracehook_consider_fatal_signal() * ptrace_event() wrappers. Call directly. tracehook_report_exec() tracehook_report_exit() tracehook_report_vfork_done() * ptrace_release_task() wrapper. Call directly. tracehook_finish_release_task() * noop tracehook_prepare_release_task() tracehook_report_death() This doesn't introduce any behavior change. Signed-off-by: Tejun Heo Cc: Christoph Hellwig Cc: Martin Schwidefsky Signed-off-by: Oleg Nesterov --- include/linux/tracehook.h | 156 ---------------------------------------------- 1 file changed, 156 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 3b68aa842a92..8b06d4f2b814 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -51,21 +51,6 @@ #include struct linux_binprm; -/** - * tracehook_expect_breakpoints - guess if task memory might be touched - * @task: current task, making a new mapping - * - * Return nonzero if @task is expected to want breakpoint insertion in - * its memory at some point. A zero return is no guarantee it won't - * be done, but this is a hint that it's known to be likely. - * - * May be called with @task->mm->mmap_sem held for writing. - */ -static inline int tracehook_expect_breakpoints(struct task_struct *task) -{ - return (task->ptrace & PT_PTRACED) != 0; -} - /* * ptrace report for syscall entry and exit looks identical. */ @@ -183,42 +168,6 @@ static inline struct task_struct *tracehook_tracer_task(struct task_struct *tsk) return NULL; } -/** - * tracehook_report_exec - a successful exec was completed - * @fmt: &struct linux_binfmt that performed the exec - * @bprm: &struct linux_binprm containing exec details - * @regs: user-mode register state - * - * An exec just completed, we are shortly going to return to user mode. - * The freshly initialized register state can be seen and changed in @regs. - * The name, file and other pointers in @bprm are still on hand to be - * inspected, but will be freed as soon as this returns. - * - * Called with no locks, but with some kernel resources held live - * and a reference on @fmt->module. - */ -static inline void tracehook_report_exec(struct linux_binfmt *fmt, - struct linux_binprm *bprm, - struct pt_regs *regs) -{ - ptrace_event(PTRACE_EVENT_EXEC, 0); -} - -/** - * tracehook_report_exit - task has begun to exit - * @exit_code: pointer to value destined for @current->exit_code - * - * @exit_code points to the value passed to do_exit(), which tracing - * might change here. This is almost the first thing in do_exit(), - * before freeing any resources or setting the %PF_EXITING flag. - * - * Called with no locks held. - */ -static inline void tracehook_report_exit(long *exit_code) -{ - ptrace_event(PTRACE_EVENT_EXIT, *exit_code); -} - /** * tracehook_prepare_clone - prepare for new child to be cloned * @clone_flags: %CLONE_* flags from clone/fork/vfork system call @@ -319,52 +268,6 @@ static inline void tracehook_report_clone_complete(int trace, ptrace_event(trace, pid); } -/** - * tracehook_report_vfork_done - vfork parent's child has exited or exec'd - * @child: child task, already running - * @pid: new child's PID in the parent's namespace - * - * Called after a %CLONE_VFORK parent has waited for the child to complete. - * The clone/vfork system call will return immediately after this. - * The @child pointer may be invalid if a self-reaping child died and - * tracehook_report_clone() took no action to prevent it from self-reaping. - * - * Called with no locks held. - */ -static inline void tracehook_report_vfork_done(struct task_struct *child, - pid_t pid) -{ - ptrace_event(PTRACE_EVENT_VFORK_DONE, pid); -} - -/** - * tracehook_prepare_release_task - task is being reaped, clean up tracing - * @task: task in %EXIT_DEAD state - * - * This is called in release_task() just before @task gets finally reaped - * and freed. This would be the ideal place to remove and clean up any - * tracing-related state for @task. - * - * Called with no locks held. - */ -static inline void tracehook_prepare_release_task(struct task_struct *task) -{ -} - -/** - * tracehook_finish_release_task - final tracing clean-up - * @task: task in %EXIT_DEAD state - * - * This is called in release_task() when @task is being in the middle of - * being reaped. After this, there must be no tracing entanglements. - * - * Called with write_lock_irq(&tasklist_lock) held. - */ -static inline void tracehook_finish_release_task(struct task_struct *task) -{ - ptrace_release_task(task); -} - /** * tracehook_signal_handler - signal handler setup is complete * @sig: number of signal being delivered @@ -388,41 +291,6 @@ static inline void tracehook_signal_handler(int sig, siginfo_t *info, ptrace_notify(SIGTRAP); } -/** - * tracehook_consider_ignored_signal - suppress short-circuit of ignored signal - * @task: task receiving the signal - * @sig: signal number being sent - * - * Return zero iff tracing doesn't care to examine this ignored signal, - * so it can short-circuit normal delivery and never even get queued. - * - * Called with @task->sighand->siglock held. - */ -static inline int tracehook_consider_ignored_signal(struct task_struct *task, - int sig) -{ - return (task->ptrace & PT_PTRACED) != 0; -} - -/** - * tracehook_consider_fatal_signal - suppress special handling of fatal signal - * @task: task receiving the signal - * @sig: signal number being sent - * - * Return nonzero to prevent special handling of this termination signal. - * Normally handler for signal is %SIG_DFL. It can be %SIG_IGN if @sig is - * ignored, in which case force_sig() is about to reset it to %SIG_DFL. - * When this returns zero, this signal might cause a quick termination - * that does not give the debugger a chance to intercept the signal. - * - * Called with or without @task->sighand->siglock held. - */ -static inline int tracehook_consider_fatal_signal(struct task_struct *task, - int sig) -{ - return (task->ptrace & PT_PTRACED) != 0; -} - #define DEATH_REAP -1 #define DEATH_DELAYED_GROUP_LEADER -2 @@ -457,30 +325,6 @@ static inline int tracehook_notify_death(struct task_struct *task, return task->ptrace ? SIGCHLD : DEATH_DELAYED_GROUP_LEADER; } -/** - * tracehook_report_death - task is dead and ready to be reaped - * @task: @current task now exiting - * @signal: return value from tracheook_notify_death() - * @death_cookie: value passed back from tracehook_notify_death() - * @group_dead: nonzero if this was the last thread in the group to die - * - * Thread has just become a zombie or is about to self-reap. If positive, - * @signal is the signal number just sent to the parent (usually %SIGCHLD). - * If @signal is %DEATH_REAP, this thread will self-reap. If @signal is - * %DEATH_DELAYED_GROUP_LEADER, this is a delayed_group_leader() zombie. - * The @death_cookie was passed back by tracehook_notify_death(). - * - * If normal reaping is not inhibited, @task->exit_state might be changing - * in parallel. - * - * Called without locks. - */ -static inline void tracehook_report_death(struct task_struct *task, - int signal, void *death_cookie, - int group_dead) -{ -} - #ifdef TIF_NOTIFY_RESUME /** * set_notify_resume - cause tracehook_notify_resume() to be called -- cgit v1.2.3 From 4b9d33e6d83cc05a8005a8f9a8b9677fa0f53626 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 17 Jun 2011 16:50:38 +0200 Subject: ptrace: kill clone/exec tracehooks At this point, tracehooks aren't useful to mainline kernel and mostly just add an extra layer of obfuscation. Although they have comments, without actual in-kernel users, it is difficult to tell what are their assumptions and they're actually trying to achieve. To mainline kernel, they just aren't worth keeping around. This patch kills the following clone and exec related tracehooks. tracehook_prepare_clone() tracehook_finish_clone() tracehook_report_clone() tracehook_report_clone_complete() tracehook_unsafe_exec() The changes are mostly trivial - logic is moved to the caller and comments are merged and adjusted appropriately. The only exception is in check_unsafe_exec() where LSM_UNSAFE_PTRACE* are OR'd to bprm->unsafe instead of setting it, which produces the same result as the field is always zero on entry. It also tests p->ptrace instead of (p->ptrace & PT_PTRACED) for consistency, which also gives the same result. This doesn't introduce any behavior change. Signed-off-by: Tejun Heo Cc: Christoph Hellwig Signed-off-by: Oleg Nesterov --- include/linux/tracehook.h | 121 ---------------------------------------------- 1 file changed, 121 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 8b06d4f2b814..bcc4ca762aee 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -129,27 +129,6 @@ static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step) ptrace_report_syscall(regs); } -/** - * tracehook_unsafe_exec - check for exec declared unsafe due to tracing - * @task: current task doing exec - * - * Return %LSM_UNSAFE_* bits applied to an exec because of tracing. - * - * @task->signal->cred_guard_mutex is held by the caller through the do_execve(). - */ -static inline int tracehook_unsafe_exec(struct task_struct *task) -{ - int unsafe = 0; - int ptrace = task->ptrace; - if (ptrace & PT_PTRACED) { - if (ptrace & PT_PTRACE_CAP) - unsafe |= LSM_UNSAFE_PTRACE_CAP; - else - unsafe |= LSM_UNSAFE_PTRACE; - } - return unsafe; -} - /** * tracehook_tracer_task - return the task that is tracing the given task * @tsk: task to consider @@ -168,106 +147,6 @@ static inline struct task_struct *tracehook_tracer_task(struct task_struct *tsk) return NULL; } -/** - * tracehook_prepare_clone - prepare for new child to be cloned - * @clone_flags: %CLONE_* flags from clone/fork/vfork system call - * - * This is called before a new user task is to be cloned. - * Its return value will be passed to tracehook_finish_clone(). - * - * Called with no locks held. - */ -static inline int tracehook_prepare_clone(unsigned clone_flags) -{ - int event = 0; - - if (clone_flags & CLONE_UNTRACED) - return 0; - - if (clone_flags & CLONE_VFORK) - event = PTRACE_EVENT_VFORK; - else if ((clone_flags & CSIGNAL) != SIGCHLD) - event = PTRACE_EVENT_CLONE; - else - event = PTRACE_EVENT_FORK; - - return ptrace_event_enabled(current, event) ? event : 0; -} - -/** - * tracehook_finish_clone - new child created and being attached - * @child: new child task - * @clone_flags: %CLONE_* flags from clone/fork/vfork system call - * @trace: return value from tracehook_prepare_clone() - * - * This is called immediately after adding @child to its parent's children list. - * The @trace value is that returned by tracehook_prepare_clone(). - * - * Called with current's siglock and write_lock_irq(&tasklist_lock) held. - */ -static inline void tracehook_finish_clone(struct task_struct *child, - unsigned long clone_flags, int trace) -{ - ptrace_init_task(child, (clone_flags & CLONE_PTRACE) || trace); -} - -/** - * tracehook_report_clone - in parent, new child is about to start running - * @regs: parent's user register state - * @clone_flags: flags from parent's system call - * @pid: new child's PID in the parent's namespace - * @child: new child task - * - * Called after a child is set up, but before it has been started running. - * This is not a good place to block, because the child has not started - * yet. Suspend the child here if desired, and then block in - * tracehook_report_clone_complete(). This must prevent the child from - * self-reaping if tracehook_report_clone_complete() uses the @child - * pointer; otherwise it might have died and been released by the time - * tracehook_report_clone_complete() is called. - * - * Called with no locks held, but the child cannot run until this returns. - */ -static inline void tracehook_report_clone(struct pt_regs *regs, - unsigned long clone_flags, - pid_t pid, struct task_struct *child) -{ - if (unlikely(child->ptrace)) { - /* - * It doesn't matter who attached/attaching to this - * task, the pending SIGSTOP is right in any case. - */ - sigaddset(&child->pending.signal, SIGSTOP); - set_tsk_thread_flag(child, TIF_SIGPENDING); - } -} - -/** - * tracehook_report_clone_complete - new child is running - * @trace: return value from tracehook_prepare_clone() - * @regs: parent's user register state - * @clone_flags: flags from parent's system call - * @pid: new child's PID in the parent's namespace - * @child: child task, already running - * - * This is called just after the child has started running. This is - * just before the clone/fork syscall returns, or blocks for vfork - * child completion if @clone_flags has the %CLONE_VFORK bit set. - * The @child pointer may be invalid if a self-reaping child died and - * tracehook_report_clone() took no action to prevent it from self-reaping. - * - * Called with no locks held. - */ -static inline void tracehook_report_clone_complete(int trace, - struct pt_regs *regs, - unsigned long clone_flags, - pid_t pid, - struct task_struct *child) -{ - if (unlikely(trace)) - ptrace_event(trace, pid); -} - /** * tracehook_signal_handler - signal handler setup is complete * @sig: number of signal being delivered -- cgit v1.2.3 From 06d984737bac0545fe20bb5447ee488b95adb531 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 17 Jun 2011 16:50:40 +0200 Subject: ptrace: s/tracehook_tracer_task()/ptrace_parent()/ tracehook.h is on the way out. Rename tracehook_tracer_task() to ptrace_parent() and move it from tracehook.h to ptrace.h. Signed-off-by: Tejun Heo Cc: Christoph Hellwig Cc: John Johansen Cc: Stephen Smalley Signed-off-by: Oleg Nesterov --- include/linux/ptrace.h | 18 ++++++++++++++++++ include/linux/tracehook.h | 18 ------------------ 2 files changed, 18 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index b546fd6c3506..bb157bdd0c55 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -150,6 +150,24 @@ int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr, int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr, unsigned long data); +/** + * ptrace_parent - return the task that is tracing the given task + * @task: task to consider + * + * Returns %NULL if no one is tracing @task, or the &struct task_struct + * pointer to its tracer. + * + * Must called under rcu_read_lock(). The pointer returned might be kept + * live only by RCU. During exec, this may be called with task_lock() held + * on @task, still held from when check_unsafe_exec() was called. + */ +static inline struct task_struct *ptrace_parent(struct task_struct *task) +{ + if (unlikely(task->ptrace)) + return rcu_dereference(task->parent); + return NULL; +} + /** * ptrace_event_enabled - test whether a ptrace event is enabled * @task: ptracee of interest diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index bcc4ca762aee..7a1bd12aeffa 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -129,24 +129,6 @@ static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step) ptrace_report_syscall(regs); } -/** - * tracehook_tracer_task - return the task that is tracing the given task - * @tsk: task to consider - * - * Returns NULL if no one is tracing @task, or the &struct task_struct - * pointer to its tracer. - * - * Must called under rcu_read_lock(). The pointer returned might be kept - * live only by RCU. During exec, this may be called with task_lock() - * held on @task, still held from when tracehook_unsafe_exec() was called. - */ -static inline struct task_struct *tracehook_tracer_task(struct task_struct *tsk) -{ - if (tsk->ptrace & PT_PTRACED) - return rcu_dereference(tsk->parent); - return NULL; -} - /** * tracehook_signal_handler - signal handler setup is complete * @sig: number of signal being delivered -- cgit v1.2.3 From 670dc2833d144375eac36ad74111495a825a9288 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 20 Jun 2011 13:40:46 +0200 Subject: netlink: advertise incomplete dumps Consider the following situation: * a dump that would show 8 entries, four in the first round, and four in the second * between the first and second rounds, 6 entries are removed * now the second round will not show any entry, and even if there is a sequence/generation counter the application will not know To solve this problem, add a new flag NLM_F_DUMP_INTR to the netlink header that indicates the dump wasn't consistent, this flag can also be set on the MSG_DONE message that terminates the dump, and as such above situation can be detected. To achieve this, add a sequence counter to the netlink callback struct. Of course, netlink code still needs to use this new functionality. The correct way to do that is to always set cb->seq when a dumpit callback is invoked and call nl_dump_check_consistent() for each new message. The core code will also call this function for the final MSG_DONE message. To make it usable with generic netlink, a new function genlmsg_nlhdr() is needed to obtain the netlink header from the genetlink user header. Signed-off-by: Johannes Berg Acked-by: David S. Miller Signed-off-by: John W. Linville --- include/linux/netlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 4c4ac3f3ce5a..8d1bcec5cc06 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -48,6 +48,7 @@ struct nlmsghdr { #define NLM_F_MULTI 2 /* Multipart message, terminated by NLMSG_DONE */ #define NLM_F_ACK 4 /* Reply with ack, with zero or error code */ #define NLM_F_ECHO 8 /* Echo this request */ +#define NLM_F_DUMP_INTR 16 /* Dump was inconsistent due to sequence change */ /* Modifiers to GET request */ #define NLM_F_ROOT 0x100 /* specify tree root */ @@ -221,6 +222,7 @@ struct netlink_callback { struct netlink_callback *cb); int (*done)(struct netlink_callback *cb); int family; + unsigned int prev_seq, seq; long args[6]; }; -- cgit v1.2.3 From 3762561aa8afb0bd9fb60d3d847961f9945f8143 Mon Sep 17 00:00:00 2001 From: Gabor Juhos Date: Tue, 21 Jun 2011 11:23:23 +0200 Subject: ath9k: add MAC revision detection for AR9330 The AR9330 1.0 and 1.1 are using the same revision, thus it is not possible to distinguish the two chips. The platform setup code can distinguish the chips based on the SoC revision. Add a callback function to ath9k_platform_data in order to allow getting the revision number from the platform code. Signed-off-by: Gabor Juhos Signed-off-by: John W. Linville --- include/linux/ath9k_platform.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ath9k_platform.h b/include/linux/ath9k_platform.h index 60a7c49dcb49..c207607acada 100644 --- a/include/linux/ath9k_platform.h +++ b/include/linux/ath9k_platform.h @@ -30,6 +30,7 @@ struct ath9k_platform_data { u32 gpio_val; bool is_clk_25mhz; + int (*get_mac_revision)(void); }; #endif /* _LINUX_ATH9K_PLATFORM_H */ -- cgit v1.2.3 From 7d95847c9b3631d31f657d8cede153b518ed9e2e Mon Sep 17 00:00:00 2001 From: Gabor Juhos Date: Tue, 21 Jun 2011 11:23:51 +0200 Subject: ath9k: add external_reset callback to ath9k_platfom_data for AR9330 The patch adds a callback to ath9k_platform_data. If the callback is provided by the platform code, then it can be used to hard reset the WMAC device. The callback is required for doing a hard reset of the AR9330 chips to get them working again after a hang. Signed-off-by: Gabor Juhos Signed-off-by: John W. Linville --- include/linux/ath9k_platform.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ath9k_platform.h b/include/linux/ath9k_platform.h index c207607acada..6e3f54f37844 100644 --- a/include/linux/ath9k_platform.h +++ b/include/linux/ath9k_platform.h @@ -31,6 +31,7 @@ struct ath9k_platform_data { bool is_clk_25mhz; int (*get_mac_revision)(void); + int (*external_reset)(void); }; #endif /* _LINUX_ATH9K_PLATFORM_H */ -- cgit v1.2.3 From a7de915383a6d5c05663f9badbd10d5a87bc1586 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 22 Jun 2011 22:53:27 +0200 Subject: genirq: Remove unused CHECK_IRQ_PER_CPU() No more users. Kill it. Signed-off-by: Thomas Gleixner --- include/linux/irq.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 8b4538446636..68258f0369db 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -96,11 +96,6 @@ enum { #define IRQ_NO_BALANCING_MASK (IRQ_PER_CPU | IRQ_NO_BALANCING) -static inline __deprecated bool CHECK_IRQ_PER_CPU(unsigned int status) -{ - return status & IRQ_PER_CPU; -} - /* * Return value for chip->irq_set_affinity() * -- cgit v1.2.3 From d902db1eb60387040fe541573083e47469db50ac Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 8 Jun 2011 19:31:56 +0200 Subject: sched: Generalize sleep inside spinlock detection The sleeping inside spinlock detection is actually used for more general sleeping inside atomic sections debugging: preemption disabled, rcu read side critical sections, interrupts, interrupt disabled, etc... Change the name of the config and its help section to reflect its more general role. Signed-off-by: Frederic Weisbecker Acked-by: Paul E. McKenney Acked-by: Randy Dunlap Cc: Peter Zijlstra Cc: Ingo Molnar --- include/linux/kernel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index fb0e7329fee1..24b489f66592 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -121,7 +121,7 @@ extern int _cond_resched(void); # define might_resched() do { } while (0) #endif -#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP +#ifdef CONFIG_DEBUG_ATOMIC_SLEEP void __might_sleep(const char *file, int line, int preempt_offset); /** * might_sleep - annotation for functions that can sleep -- cgit v1.2.3 From 01dc9cc314ad1009f5b7356399b386015fdb0400 Mon Sep 17 00:00:00 2001 From: David Wagner Date: Mon, 20 Jun 2011 17:34:19 +0200 Subject: UBI: clarify the volume notification types' doc I realized the new descriptions of ADDED and REMOVED could also be misleading: they can also be triggered after using a userland util (ubi{mk,rm}vol). Artem: amend the commentaries Signed-off-by David Wagner Signed-off-by: Artem Bityutskiy --- include/linux/mtd/ubi.h | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/ubi.h b/include/linux/mtd/ubi.h index 15da0e99f48a..db4836bed514 100644 --- a/include/linux/mtd/ubi.h +++ b/include/linux/mtd/ubi.h @@ -155,12 +155,14 @@ struct ubi_device_info { }; /* - * enum - volume notification types. - * @UBI_VOLUME_ADDED: volume has been added - * @UBI_VOLUME_REMOVED: start volume volume - * @UBI_VOLUME_RESIZED: volume size has been re-sized - * @UBI_VOLUME_RENAMED: volume name has been re-named - * @UBI_VOLUME_UPDATED: volume name has been updated + * Volume notification types. + * @UBI_VOLUME_ADDED: a volume has been added (an UBI device was attached or a + * volume was created) + * @UBI_VOLUME_REMOVED: a volume has been removed (an UBI device was detached + * or a volume was removed) + * @UBI_VOLUME_RESIZED: a volume has been re-sized + * @UBI_VOLUME_RENAMED: a volume has been re-named + * @UBI_VOLUME_UPDATED: data has been written to a volume * * These constants define which type of event has happened when a volume * notification function is invoked. -- cgit v1.2.3 From 39785eb1d3e6c58cc8bf8f6990956a58037ecc75 Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Thu, 23 Jun 2011 20:20:26 +0000 Subject: fsl-diu-fb: remove check for pixel clock ranges The Freescale DIU framebuffer driver defines two constants, MIN_PIX_CLK and MAX_PIX_CLK, that are supposed to represent the lower and upper limits of the pixel clock. These values, however, are true only for one platform clock rate (533MHz) and only for the MPC8610. So the actual range for the pixel clock is chip-specific, which means the current values are almost always wrong. The chance of an out-of-range pixel clock being used are also remote. Rather than try to detect an out-of-range clock in the DIU driver, we depend on the board-specific pixel clock function (e.g. p1022ds_set_pixel_clock) to clamp the pixel clock to a supported value. Signed-off-by: Timur Tabi Signed-off-by: Paul Mundt --- include/linux/fsl-diu-fb.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsl-diu-fb.h b/include/linux/fsl-diu-fb.h index 781d4671415f..daa9952d2174 100644 --- a/include/linux/fsl-diu-fb.h +++ b/include/linux/fsl-diu-fb.h @@ -24,12 +24,6 @@ * See mpc8610fb_set_par(), map_video_memory(), and unmap_video_memory() */ #define MEM_ALLOC_THRESHOLD (1024*768*4+32) -/* Minimum value that the pixel clock can be set to in pico seconds - * This is determined by platform clock/3 where the minimum platform - * clock is 533MHz. This gives 5629 pico seconds. - */ -#define MIN_PIX_CLK 5629 -#define MAX_PIX_CLK 96096 #include -- cgit v1.2.3 From 40680f2fa4670ab35ee554822a69dda1a118f966 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 24 May 2011 22:24:47 +0200 Subject: ext3: Convert ext3 to new truncate calling convention Mostly trivial conversion. We fix a bug that IS_IMMUTABLE and IS_APPEND files could not be truncated during failed writes as we change the code. In fact the test is not needed at all because both IS_IMMUTABLE and IS_APPEND is tested in upper layers in do_sys_[f]truncate(), may_write(), etc. Signed-off-by: Jan Kara --- include/linux/ext3_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index 5e06acf95d0f..9aaa3a84d373 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -913,7 +913,7 @@ extern void ext3_dirty_inode(struct inode *, int); extern int ext3_change_inode_journal_flag(struct inode *, int); extern int ext3_get_inode_loc(struct inode *, struct ext3_iloc *); extern int ext3_can_truncate(struct inode *inode); -extern void ext3_truncate (struct inode *); +extern void ext3_truncate(struct inode *inode); extern void ext3_set_inode_flags(struct inode *); extern void ext3_get_inode_flags(struct ext3_inode_info *); extern void ext3_set_aops(struct inode *inode); -- cgit v1.2.3 From fbcc9e624b8dbc7f740fac3906aa261b83398100 Mon Sep 17 00:00:00 2001 From: Petr Uzel Date: Tue, 31 May 2011 11:36:06 +0200 Subject: ext2: include fs.h into ext2_fs.h AC_CHECK_HEADERS([linux/ext2_fs.h]) fails with configure:34666: checking linux/ext2_fs.h usability configure:34666: gcc -std=gnu99 -c -ggdb3 -O0 -Wunreachable-code conftest.c >&5 In file included from conftest.c:406:0: /usr/include/linux/ext2_fs.h: In function 'ext2_mask_flags': /usr/include/linux/ext2_fs.h:182:21: error: 'FS_DIRSYNC_FL' undeclared (first use in this function) /usr/include/linux/ext2_fs.h:182:21: note: each undeclared identifier is reported only once for each function it appears in /usr/include/linux/ext2_fs.h:182:37: error: 'FS_TOPDIR_FL' undeclared (first use in this function) /usr/include/linux/ext2_fs.h:184:19: error: 'FS_NODUMP_FL' undeclared (first use in this function) /usr/include/linux/ext2_fs.h:184:34: error: 'FS_NOATIME_FL' undeclared (first use in this function) It's reasonable to have headers that include all necessary definitions. So fix this by including fs.h into ext2_fs.h. Signed-off-by: Petr Uzel Signed-off-by: Jan Kara --- include/linux/ext2_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ext2_fs.h b/include/linux/ext2_fs.h index 2dfa7076e8b6..53792bf36c71 100644 --- a/include/linux/ext2_fs.h +++ b/include/linux/ext2_fs.h @@ -18,6 +18,7 @@ #include #include +#include /* * The second extended filesystem constants/structures -- cgit v1.2.3 From 9008593017069ad513cc7dc78a6c94e8dfddba31 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Wed, 1 Jun 2011 23:34:04 +0900 Subject: ext3: use proper little-endian bitops ext3_{set,clear}_bit() is defined as __test_and_{set,clear}_bit_le() for ext3. But all ext3_{set,clear}_bit() calls ignore return values. So these can be replaced with __{set,clear}_bit_le(). This changes ext3_{set,clear}_bit safely, because if someone uses these macros without noticing the change, new ext3_{set,clear}_bit don't have return value and causes compiler errors where the return value is used. This also removes unused ext3_find_first_zero_bit(). Signed-off-by: Akinobu Mita Cc: Jan Kara Cc: Andrew Morton Cc: Andreas Dilger Cc: linux-ext4@vger.kernel.org Signed-off-by: Jan Kara --- include/linux/ext3_fs.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index 9aaa3a84d373..8f1f908eddb8 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -418,12 +418,11 @@ struct ext3_inode { #define EXT2_MOUNT_DATA_FLAGS EXT3_MOUNT_DATA_FLAGS #endif -#define ext3_set_bit __test_and_set_bit_le +#define ext3_set_bit __set_bit_le #define ext3_set_bit_atomic ext2_set_bit_atomic -#define ext3_clear_bit __test_and_clear_bit_le +#define ext3_clear_bit __clear_bit_le #define ext3_clear_bit_atomic ext2_clear_bit_atomic #define ext3_test_bit test_bit_le -#define ext3_find_first_zero_bit find_first_zero_bit_le #define ext3_find_next_zero_bit find_next_zero_bit_le /* -- cgit v1.2.3 From bb189247f35688a3353545902c56290fb7d7754a Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 24 Jun 2011 23:11:59 +0200 Subject: jbd: Fix oops in journal_remove_journal_head() journal_remove_journal_head() can oops when trying to access journal_head returned by bh2jh(). This is caused for example by the following race: TASK1 TASK2 journal_commit_transaction() ... processing t_forget list __journal_refile_buffer(jh); if (!jh->b_transaction) { jbd_unlock_bh_state(bh); journal_try_to_free_buffers() journal_grab_journal_head(bh) jbd_lock_bh_state(bh) __journal_try_to_free_buffer() journal_put_journal_head(jh) journal_remove_journal_head(bh); journal_put_journal_head() in TASK2 sees that b_jcount == 0 and buffer is not part of any transaction and thus frees journal_head before TASK1 gets to doing so. Note that even buffer_head can be released by try_to_free_buffers() after journal_put_journal_head() which adds even larger opportunity for oops (but I didn't see this happen in reality). Fix the problem by making transactions hold their own journal_head reference (in b_jcount). That way we don't have to remove journal_head explicitely via journal_remove_journal_head() and instead just remove journal_head when b_jcount drops to zero. The result of this is that [__]journal_refile_buffer(), [__]journal_unfile_buffer(), and __journal_remove_checkpoint() can free journal_head which needs modification of a few callers. Also we have to be careful because once journal_head is removed, buffer_head might be freed as well. So we have to get our own buffer_head reference where it matters. Signed-off-by: Jan Kara --- include/linux/jbd.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/jbd.h b/include/linux/jbd.h index e06965081ba5..e6a5e34bed4f 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -940,7 +940,6 @@ extern int journal_force_commit(journal_t *); */ struct journal_head *journal_add_journal_head(struct buffer_head *bh); struct journal_head *journal_grab_journal_head(struct buffer_head *bh); -void journal_remove_journal_head(struct buffer_head *bh); void journal_put_journal_head(struct journal_head *jh); /* -- cgit v1.2.3 From f8f8527103a264b5e4ab2ce5c1743b28f3219d90 Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Mon, 27 Jun 2011 13:45:43 +0200 Subject: eCryptfs: export global eCryptfs definitions to include/linux/ecryptfs.h Some eCryptfs specific definitions, such as the current version and the authentication token structure, are moved to the new include file 'include/linux/ecryptfs.h', in order to be available for all kernel subsystems. Signed-off-by: Roberto Sassu Acked-by: Gianluca Ramunno Acked-by: Tyler Hicks Acked-by: David Howells Signed-off-by: Mimi Zohar --- include/linux/ecryptfs.h | 113 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 113 insertions(+) create mode 100644 include/linux/ecryptfs.h (limited to 'include/linux') diff --git a/include/linux/ecryptfs.h b/include/linux/ecryptfs.h new file mode 100644 index 000000000000..2224a8c0cb64 --- /dev/null +++ b/include/linux/ecryptfs.h @@ -0,0 +1,113 @@ +#ifndef _LINUX_ECRYPTFS_H +#define _LINUX_ECRYPTFS_H + +/* Version verification for shared data structures w/ userspace */ +#define ECRYPTFS_VERSION_MAJOR 0x00 +#define ECRYPTFS_VERSION_MINOR 0x04 +#define ECRYPTFS_SUPPORTED_FILE_VERSION 0x03 +/* These flags indicate which features are supported by the kernel + * module; userspace tools such as the mount helper read + * ECRYPTFS_VERSIONING_MASK from a sysfs handle in order to determine + * how to behave. */ +#define ECRYPTFS_VERSIONING_PASSPHRASE 0x00000001 +#define ECRYPTFS_VERSIONING_PUBKEY 0x00000002 +#define ECRYPTFS_VERSIONING_PLAINTEXT_PASSTHROUGH 0x00000004 +#define ECRYPTFS_VERSIONING_POLICY 0x00000008 +#define ECRYPTFS_VERSIONING_XATTR 0x00000010 +#define ECRYPTFS_VERSIONING_MULTKEY 0x00000020 +#define ECRYPTFS_VERSIONING_DEVMISC 0x00000040 +#define ECRYPTFS_VERSIONING_HMAC 0x00000080 +#define ECRYPTFS_VERSIONING_FILENAME_ENCRYPTION 0x00000100 +#define ECRYPTFS_VERSIONING_GCM 0x00000200 +#define ECRYPTFS_VERSIONING_MASK (ECRYPTFS_VERSIONING_PASSPHRASE \ + | ECRYPTFS_VERSIONING_PLAINTEXT_PASSTHROUGH \ + | ECRYPTFS_VERSIONING_PUBKEY \ + | ECRYPTFS_VERSIONING_XATTR \ + | ECRYPTFS_VERSIONING_MULTKEY \ + | ECRYPTFS_VERSIONING_DEVMISC \ + | ECRYPTFS_VERSIONING_FILENAME_ENCRYPTION) +#define ECRYPTFS_MAX_PASSWORD_LENGTH 64 +#define ECRYPTFS_MAX_PASSPHRASE_BYTES ECRYPTFS_MAX_PASSWORD_LENGTH +#define ECRYPTFS_SALT_SIZE 8 +#define ECRYPTFS_SALT_SIZE_HEX (ECRYPTFS_SALT_SIZE*2) +/* The original signature size is only for what is stored on disk; all + * in-memory representations are expanded hex, so it better adapted to + * be passed around or referenced on the command line */ +#define ECRYPTFS_SIG_SIZE 8 +#define ECRYPTFS_SIG_SIZE_HEX (ECRYPTFS_SIG_SIZE*2) +#define ECRYPTFS_PASSWORD_SIG_SIZE ECRYPTFS_SIG_SIZE_HEX +#define ECRYPTFS_MAX_KEY_BYTES 64 +#define ECRYPTFS_MAX_ENCRYPTED_KEY_BYTES 512 +#define ECRYPTFS_FILE_VERSION 0x03 +#define ECRYPTFS_MAX_PKI_NAME_BYTES 16 + +#define RFC2440_CIPHER_DES3_EDE 0x02 +#define RFC2440_CIPHER_CAST_5 0x03 +#define RFC2440_CIPHER_BLOWFISH 0x04 +#define RFC2440_CIPHER_AES_128 0x07 +#define RFC2440_CIPHER_AES_192 0x08 +#define RFC2440_CIPHER_AES_256 0x09 +#define RFC2440_CIPHER_TWOFISH 0x0a +#define RFC2440_CIPHER_CAST_6 0x0b + +#define RFC2440_CIPHER_RSA 0x01 + +/** + * For convenience, we may need to pass around the encrypted session + * key between kernel and userspace because the authentication token + * may not be extractable. For example, the TPM may not release the + * private key, instead requiring the encrypted data and returning the + * decrypted data. + */ +struct ecryptfs_session_key { +#define ECRYPTFS_USERSPACE_SHOULD_TRY_TO_DECRYPT 0x00000001 +#define ECRYPTFS_USERSPACE_SHOULD_TRY_TO_ENCRYPT 0x00000002 +#define ECRYPTFS_CONTAINS_DECRYPTED_KEY 0x00000004 +#define ECRYPTFS_CONTAINS_ENCRYPTED_KEY 0x00000008 + u32 flags; + u32 encrypted_key_size; + u32 decrypted_key_size; + u8 encrypted_key[ECRYPTFS_MAX_ENCRYPTED_KEY_BYTES]; + u8 decrypted_key[ECRYPTFS_MAX_KEY_BYTES]; +}; + +struct ecryptfs_password { + u32 password_bytes; + s32 hash_algo; + u32 hash_iterations; + u32 session_key_encryption_key_bytes; +#define ECRYPTFS_PERSISTENT_PASSWORD 0x01 +#define ECRYPTFS_SESSION_KEY_ENCRYPTION_KEY_SET 0x02 + u32 flags; + /* Iterated-hash concatenation of salt and passphrase */ + u8 session_key_encryption_key[ECRYPTFS_MAX_KEY_BYTES]; + u8 signature[ECRYPTFS_PASSWORD_SIG_SIZE + 1]; + /* Always in expanded hex */ + u8 salt[ECRYPTFS_SALT_SIZE]; +}; + +enum ecryptfs_token_types {ECRYPTFS_PASSWORD, ECRYPTFS_PRIVATE_KEY}; + +struct ecryptfs_private_key { + u32 key_size; + u32 data_len; + u8 signature[ECRYPTFS_PASSWORD_SIG_SIZE + 1]; + char pki_type[ECRYPTFS_MAX_PKI_NAME_BYTES + 1]; + u8 data[]; +}; + +/* May be a password or a private key */ +struct ecryptfs_auth_tok { + u16 version; /* 8-bit major and 8-bit minor */ + u16 token_type; +#define ECRYPTFS_ENCRYPT_ONLY 0x00000001 + u32 flags; + struct ecryptfs_session_key session_key; + u8 reserved[32]; + union { + struct ecryptfs_password password; + struct ecryptfs_private_key private_key; + } token; +} __attribute__ ((packed)); + +#endif /* _LINUX_ECRYPTFS_H */ -- cgit v1.2.3 From 53c8f9f199b239668e6b1a907735ee323a0d1ccd Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 22 Jun 2011 23:08:18 +0200 Subject: make do_notify_parent() return bool - change do_notify_parent() to return a boolean, true if the task should be reaped because its parent ignores SIGCHLD. - update the only caller which checks the returned value, exit_notify(). This temporary uglifies exit_notify() even more, will be cleanuped by the next change. Signed-off-by: Oleg Nesterov Acked-by: Tejun Heo --- include/linux/sched.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 87f7ca7ed6f6..0df7231d9ee0 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2145,7 +2145,7 @@ static inline int dequeue_signal_lock(struct task_struct *tsk, sigset_t *mask, s spin_unlock_irqrestore(&tsk->sighand->siglock, flags); return ret; -} +} extern void block_all_signals(int (*notifier)(void *priv), void *priv, sigset_t *mask); @@ -2160,7 +2160,7 @@ extern int kill_pid_info_as_uid(int, struct siginfo *, struct pid *, uid_t, uid_ extern int kill_pgrp(struct pid *pid, int sig, int priv); extern int kill_pid(struct pid *pid, int sig, int priv); extern int kill_proc_info(int, struct siginfo *, pid_t); -extern int do_notify_parent(struct task_struct *, int); +extern bool do_notify_parent(struct task_struct *, int); extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent); extern void force_sig(int, struct task_struct *); extern int send_sig(int, struct task_struct *, int); -- cgit v1.2.3 From 45cdf5cc0703c537194588c63d53bad1f2539d36 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 23 Jun 2011 19:06:50 +0200 Subject: kill tracehook_notify_death() Kill tracehook_notify_death(), reimplement the logic in its caller, exit_notify(). Also, change the exec_id's check to use thread_group_leader() instead of task_detached(), this is more clear. This logic only applies to the exiting leader, a sub-thread must never change its exit_signal. Note: when the traced group leader exits the exit_signal-or-SIGCHLD logic looks really strange: - we notify the tracer even if !thread_group_empty() but do_wait(WEXITED) can't work until all threads exit - if the tracer is real_parent, it is not clear why can't we use ->exit_signal event if !thread_group_empty() -v2: do not try to fix the 2nd oddity to avoid the subtle behavior change mixed with reorganization, suggested by Tejun. Signed-off-by: Oleg Nesterov Reviewed-by: Tejun Heo --- include/linux/tracehook.h | 34 ---------------------------------- 1 file changed, 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 7a1bd12aeffa..a71a2927a6a0 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -152,40 +152,6 @@ static inline void tracehook_signal_handler(int sig, siginfo_t *info, ptrace_notify(SIGTRAP); } -#define DEATH_REAP -1 -#define DEATH_DELAYED_GROUP_LEADER -2 - -/** - * tracehook_notify_death - task is dead, ready to notify parent - * @task: @current task now exiting - * @death_cookie: value to pass to tracehook_report_death() - * @group_dead: nonzero if this was the last thread in the group to die - * - * A return value >= 0 means call do_notify_parent() with that signal - * number. Negative return value can be %DEATH_REAP to self-reap right - * now, or %DEATH_DELAYED_GROUP_LEADER to a zombie without notifying our - * parent. Note that a return value of 0 means a do_notify_parent() call - * that sends no signal, but still wakes up a parent blocked in wait*(). - * - * Called with write_lock_irq(&tasklist_lock) held. - */ -static inline int tracehook_notify_death(struct task_struct *task, - void **death_cookie, int group_dead) -{ - if (task_detached(task)) - return task->ptrace ? SIGCHLD : DEATH_REAP; - - /* - * If something other than our normal parent is ptracing us, then - * send it a SIGCHLD instead of honoring exit_signal. exit_signal - * only has special meaning to our real parent. - */ - if (thread_group_empty(task) && !ptrace_reparented(task)) - return task->exit_signal; - - return task->ptrace ? SIGCHLD : DEATH_DELAYED_GROUP_LEADER; -} - #ifdef TIF_NOTIFY_RESUME /** * set_notify_resume - cause tracehook_notify_resume() to be called -- cgit v1.2.3 From 8677347378044ab564470bced2275520efb3670d Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 22 Jun 2011 23:09:09 +0200 Subject: make do_notify_parent() __must_check, update the callers Change other callers of do_notify_parent() to check the value it returns, this makes the subsequent task_detached() unnecessary. Mark do_notify_parent() as __must_check. Use thread_group_leader() instead of !task_detached() to check if we need to notify the real parent in wait_task_zombie(). Remove the stale comment in release_task(). "just for sanity" is no longer true, we have to set EXIT_DEAD to avoid the races with do_wait(). Signed-off-by: Oleg Nesterov Acked-by: Tejun Heo --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 0df7231d9ee0..0cb4f097f76c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2160,7 +2160,7 @@ extern int kill_pid_info_as_uid(int, struct siginfo *, struct pid *, uid_t, uid_ extern int kill_pgrp(struct pid *pid, int sig, int priv); extern int kill_pid(struct pid *pid, int sig, int priv); extern int kill_proc_info(int, struct siginfo *, pid_t); -extern bool do_notify_parent(struct task_struct *, int); +extern __must_check bool do_notify_parent(struct task_struct *, int); extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent); extern void force_sig(int, struct task_struct *); extern int send_sig(int, struct task_struct *, int); -- cgit v1.2.3 From e550f14dc6322e794d4e70825f63c9c99177ae8b Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 22 Jun 2011 23:09:54 +0200 Subject: kill task_detached() Upadate the last user of task_detached(), wait_task_zombie(), to use thread_group_leader() and kill task_detached(). Signed-off-by: Oleg Nesterov Reviewed-by: Tejun Heo --- include/linux/sched.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 0cb4f097f76c..39acee2c8929 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2318,11 +2318,6 @@ static inline int thread_group_empty(struct task_struct *p) #define delay_group_leader(p) \ (thread_group_leader(p) && !thread_group_empty(p)) -static inline int task_detached(struct task_struct *p) -{ - return p->exit_signal == -1; -} - /* * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring * subscriptions and synchronises with wait4(). Also used in procfs. Also -- cgit v1.2.3 From 087806b1281563e4ae7a5bce3155f894af5f4118 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 22 Jun 2011 23:10:26 +0200 Subject: redefine thread_group_leader() as exit_signal >= 0 Change de_thread() to set old_leader->exit_signal = -1. This is good for the consistency, it is no longer the leader and all sub-threads have exit_signal = -1 set by copy_process(CLONE_THREAD). And this allows us to micro-optimize thread_group_leader(), it can simply check exit_signal >= 0. This also makes sense because we should move ->group_leader from task_struct to signal_struct. Signed-off-by: Oleg Nesterov Reviewed-by: Tejun Heo --- include/linux/sched.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 39acee2c8929..b38ed51d5c64 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2284,8 +2284,10 @@ static inline int get_nr_threads(struct task_struct *tsk) return tsk->signal->nr_threads; } -/* de_thread depends on thread_group_leader not being a pid based check */ -#define thread_group_leader(p) (p == p->group_leader) +static inline bool thread_group_leader(struct task_struct *p) +{ + return p->exit_signal >= 0; +} /* Do to the insanities of de_thread it is possible for a process * to have the pid of the thread group leader without actually being -- cgit v1.2.3 From 0347e17739095c58c0194fed6a61aced3536d258 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 24 Jun 2011 17:34:06 +0200 Subject: ptrace: ptrace_reparented() should check same_thread_group() ptrace_reparented() naively does parent != real_parent, this means it returns true even if the tracer _is_ the real parent. This is per process thing, not per-thread. The only reason ->real_parent can point to the non-leader thread is that we have __WNOTHREAD. Change it to check !same_thread_group(parent, real_parent). It has two callers, and in both cases the current check does not look right. exit_notify: we should respect ->exit_signal if the exiting leader is traced by any thread from the parent thread group. It is the child of the whole group, and we are going to send the signal to the whole group. wait_task_zombie: without __WNOTHREAD do_wait() should do the same for any thread, only sys_ptrace() is "bound" to the single thread. However do_wait(WEXITED) succeeds but does not release a traced natural child unless the caller is the tracer. Test-case: void *tfunc(void *arg) { assert(ptrace(PTRACE_ATTACH, (long)arg, 0,0) == 0); pause(); return NULL; } int main(void) { pthread_t thr; pid_t pid, stat, ret; pid = fork(); if (!pid) { pause(); assert(0); } assert(pthread_create(&thr, NULL, tfunc, (void*)(long)pid) == 0); assert(waitpid(-1, &stat, 0) == pid); assert(WIFSTOPPED(stat)); kill(pid, SIGKILL); assert(waitpid(-1, &stat, 0) == pid); assert(WIFSIGNALED(stat) && WTERMSIG(stat) == SIGKILL); ret = waitpid(pid, &stat, 0); if (ret < 0) return 0; printf("WTF? %d is dead, but: wait=%d stat=%x\n", pid, ret, stat); return 1; } Note that the main thread simply does pid = fork(); kill(pid, SIGKILL); and then without the patch wait4(WEXITED) succeeds twice and reports WTERMSIG(stat) == SIGKILL. Signed-off-by: Oleg Nesterov Acked-by: Tejun Heo --- include/linux/ptrace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index bb157bdd0c55..eae381d584f9 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -136,7 +136,7 @@ extern bool ptrace_may_access(struct task_struct *task, unsigned int mode); static inline int ptrace_reparented(struct task_struct *child) { - return child->real_parent != child->parent; + return !same_thread_group(child->real_parent, child->parent); } static inline void ptrace_unlink(struct task_struct *child) -- cgit v1.2.3 From 04b7dcf979d71e870683c804802e44287a802760 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 22 Jun 2011 10:06:59 +0200 Subject: wireless: unify QoS control field definitions Move all that mac80211 has into the generic ieee80211.h header file and use them. At the same time move them from mask+shift to just bits and rename them for consistent names. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index bf56b6f78270..a26108e4d924 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -117,8 +117,19 @@ #define IEEE80211_MAX_MESH_ID_LEN 32 #define IEEE80211_QOS_CTL_LEN 2 -#define IEEE80211_QOS_CTL_TID_MASK 0x000F -#define IEEE80211_QOS_CTL_TAG1D_MASK 0x0007 +/* 1d tag mask */ +#define IEEE80211_QOS_CTL_TAG1D_MASK 0x0007 +/* TID mask */ +#define IEEE80211_QOS_CTL_TID_MASK 0x000f +/* EOSP */ +#define IEEE80211_QOS_CTL_EOSP 0x0010 +/* ACK policy */ +#define IEEE80211_QOS_CTL_ACK_POLICY_NORMAL 0x0000 +#define IEEE80211_QOS_CTL_ACK_POLICY_NOACK 0x0020 +#define IEEE80211_QOS_CTL_ACK_POLICY_NO_EXPL 0x0040 +#define IEEE80211_QOS_CTL_ACK_POLICY_BLOCKACK 0x0060 +/* A-MSDU 802.11n */ +#define IEEE80211_QOS_CTL_A_MSDU_PRESENT 0x0080 /* U-APSD queue for WMM IEs sent by AP */ #define IEEE80211_WMM_IE_AP_QOSINFO_UAPSD (1<<7) @@ -1423,9 +1434,6 @@ enum ieee80211_sa_query_action { }; -/* A-MSDU 802.11n */ -#define IEEE80211_QOS_CONTROL_A_MSDU_PRESENT 0x0080 - /* cipher suite selectors */ #define WLAN_CIPHER_SUITE_USE_GROUP 0x000FAC00 #define WLAN_CIPHER_SUITE_WEP40 0x000FAC01 -- cgit v1.2.3 From 6d3321e8e2b3bf6a5892e2ef673c7bf536e3f904 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Thu, 23 Jun 2011 11:19:26 -0700 Subject: x86, mtrr: lock stop machine during MTRR rendezvous sequence MTRR rendezvous sequence using stop_one_cpu_nowait() can potentially happen in parallel with another system wide rendezvous using stop_machine(). This can lead to deadlock (The order in which works are queued can be different on different cpu's. Some cpu's will be running the first rendezvous handler and others will be running the second rendezvous handler. Each set waiting for the other set to join for the system wide rendezvous, leading to a deadlock). MTRR rendezvous sequence is not implemented using stop_machine() as this gets called both from the process context aswell as the cpu online paths (where the cpu has not come online and the interrupts are disabled etc). stop_machine() works with only online cpus. For now, take the stop_machine mutex in the MTRR rendezvous sequence that gets called from an online cpu (here we are in the process context and can potentially sleep while taking the mutex). And the MTRR rendezvous that gets triggered during cpu online doesn't need to take this stop_machine lock (as the stop_machine() already ensures that there is no cpu hotplug going on in parallel by doing get_online_cpus()) TBD: Pursue a cleaner solution of extending the stop_machine() infrastructure to handle the case where the calling cpu is still not online and use this for MTRR rendezvous sequence. fixes: https://bugzilla.novell.com/show_bug.cgi?id=672008 Reported-by: Vadim Kotelnikov Signed-off-by: Suresh Siddha Link: http://lkml.kernel.org/r/20110623182056.807230326@sbsiddha-MOBL3.sc.intel.com Cc: stable@kernel.org # 2.6.35+, backport a week or two after this gets more testing in mainline Signed-off-by: H. Peter Anvin --- include/linux/stop_machine.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index 092dc9b1ce7d..14d3524d1274 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -27,6 +27,8 @@ struct cpu_stop_work { struct cpu_stop_done *done; }; +extern struct mutex stop_cpus_mutex; + int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg); void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg, struct cpu_stop_work *work_buf); -- cgit v1.2.3 From c6830c22603aaecf65405af23f6da2d55892f9cb Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Thu, 16 Jun 2011 17:28:07 +0900 Subject: Fix node_start/end_pfn() definition for mm/page_cgroup.c commit 21a3c96 uses node_start/end_pfn(nid) for detection start/end of nodes. But, it's not defined in linux/mmzone.h but defined in /arch/???/include/mmzone.h which is included only under CONFIG_NEED_MULTIPLE_NODES=y. Then, we see mm/page_cgroup.c: In function 'page_cgroup_init': mm/page_cgroup.c:308: error: implicit declaration of function 'node_start_pfn' mm/page_cgroup.c:309: error: implicit declaration of function 'node_end_pfn' So, fixiing page_cgroup.c is an idea... But node_start_pfn()/node_end_pfn() is a very generic macro and should be implemented in the same manner for all archs. (m32r has different implementation...) This patch removes definitions of node_start/end_pfn() in each archs and defines a unified one in linux/mmzone.h. It's not under CONFIG_NEED_MULTIPLE_NODES, now. A result of macro expansion is here (mm/page_cgroup.c) for !NUMA start_pfn = ((&contig_page_data)->node_start_pfn); end_pfn = ({ pg_data_t *__pgdat = (&contig_page_data); __pgdat->node_start_pfn + __pgdat->node_spanned_pages;}); for NUMA (x86-64) start_pfn = ((node_data[nid])->node_start_pfn); end_pfn = ({ pg_data_t *__pgdat = (node_data[nid]); __pgdat->node_start_pfn + __pgdat->node_spanned_pages;}); Changelog: - fixed to avoid using "nid" twice in node_end_pfn() macro. Reported-and-acked-by: Randy Dunlap Reported-and-tested-by: Ingo Molnar Acked-by: Mel Gorman Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index c928dac6cad0..9f7c3ebcbbad 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -647,6 +647,13 @@ typedef struct pglist_data { #endif #define nid_page_nr(nid, pagenr) pgdat_page_nr(NODE_DATA(nid),(pagenr)) +#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) + +#define node_end_pfn(nid) ({\ + pg_data_t *__pgdat = NODE_DATA(nid);\ + __pgdat->node_start_pfn + __pgdat->node_spanned_pages;\ +}) + #include extern struct mutex zonelists_mutex; -- cgit v1.2.3 From 06c3df49521c1b112b777cc4946e5de057c814ba Mon Sep 17 00:00:00 2001 From: Jamie Iles Date: Mon, 6 Jun 2011 12:43:07 +0100 Subject: clocksource: apb: Share APB timer code with other platforms The APB timers are an IP block from Synopsys (DesignWare APB timers) and are also found in other systems including ARM SoC's. This patch adds functions for creating clock_event_devices and clocksources from APB timers but does not do the resource allocation. This is handled in a higher layer to allow the timers to be created from multiple methods such as platform_devices. Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Jacob Pan Signed-off-by: Jamie Iles Signed-off-by: John Stultz --- include/linux/dw_apb_timer.h | 56 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 56 insertions(+) create mode 100644 include/linux/dw_apb_timer.h (limited to 'include/linux') diff --git a/include/linux/dw_apb_timer.h b/include/linux/dw_apb_timer.h new file mode 100644 index 000000000000..49638ea3b776 --- /dev/null +++ b/include/linux/dw_apb_timer.h @@ -0,0 +1,56 @@ +/* + * (C) Copyright 2009 Intel Corporation + * Author: Jacob Pan (jacob.jun.pan@intel.com) + * + * Shared with ARM platforms, Jamie Iles, Picochip 2011 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Support for the Synopsys DesignWare APB Timers. + */ +#ifndef __DW_APB_TIMER_H__ +#define __DW_APB_TIMER_H__ + +#include +#include +#include + +#define APBTMRS_REG_SIZE 0x14 + +struct dw_apb_timer { + void __iomem *base; + unsigned long freq; + int irq; +}; + +struct dw_apb_clock_event_device { + struct clock_event_device ced; + struct dw_apb_timer timer; + struct irqaction irqaction; + void (*eoi)(struct dw_apb_timer *); +}; + +struct dw_apb_clocksource { + struct dw_apb_timer timer; + struct clocksource cs; +}; + +void dw_apb_clockevent_register(struct dw_apb_clock_event_device *dw_ced); +void dw_apb_clockevent_pause(struct dw_apb_clock_event_device *dw_ced); +void dw_apb_clockevent_resume(struct dw_apb_clock_event_device *dw_ced); +void dw_apb_clockevent_stop(struct dw_apb_clock_event_device *dw_ced); + +struct dw_apb_clock_event_device * +dw_apb_clockevent_init(int cpu, const char *name, unsigned rating, + void __iomem *base, int irq, unsigned long freq); +struct dw_apb_clocksource * +dw_apb_clocksource_init(unsigned rating, char *name, void __iomem *base, + unsigned long freq); +void dw_apb_clocksource_register(struct dw_apb_clocksource *dw_cs); +void dw_apb_clocksource_start(struct dw_apb_clocksource *dw_cs); +cycle_t dw_apb_clocksource_read(struct dw_apb_clocksource *dw_cs); +void dw_apb_clocksource_unregister(struct dw_apb_clocksource *dw_cs); + +#endif /* __DW_APB_TIMER_H__ */ -- cgit v1.2.3 From f740e6cd0cb5e7468e46831aeb4d9c30e03d5ebc Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 23 Jun 2011 11:19:28 -0700 Subject: stop_machine: implement stop_machine_from_inactive_cpu() Currently, mtrr wants stop_machine functionality while a CPU is being brought up. As stop_machine() requires the calling CPU to be active, mtrr implements its own stop_machine using stop_one_cpu() on each online CPU. This doesn't only unnecessarily duplicate complex logic but also introduces a possibility of deadlock when it races against the generic stop_machine(). This patch implements stop_machine_from_inactive_cpu() to serve such use cases. Its functionality is basically the same as stop_machine(); however, it should be called from a CPU which isn't active and doesn't depend on working scheduling on the calling CPU. This is achieved by using busy loops for synchronization and open-coding stop_cpus queuing and waiting with direct invocation of fn() for local CPU inbetween. Signed-off-by: Tejun Heo Link: http://lkml.kernel.org/r/20110623182056.982526827@sbsiddha-MOBL3.sc.intel.com Signed-off-by: Suresh Siddha Cc: Ingo Molnar Cc: Andrew Morton Cc: Linus Torvalds Cc: Peter Zijlstra Signed-off-by: H. Peter Anvin --- include/linux/stop_machine.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index 14d3524d1274..e0f2da25d751 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -126,15 +126,19 @@ int stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus); */ int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus); +int stop_machine_from_inactive_cpu(int (*fn)(void *), void *data, + const struct cpumask *cpus); + #else /* CONFIG_STOP_MACHINE && CONFIG_SMP */ static inline int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus) { + unsigned long flags; int ret; - local_irq_disable(); + local_irq_save(flags); ret = fn(data); - local_irq_enable(); + local_irq_restore(flags); return ret; } @@ -144,5 +148,11 @@ static inline int stop_machine(int (*fn)(void *), void *data, return __stop_machine(fn, data, cpus); } +static inline int stop_machine_from_inactive_cpu(int (*fn)(void *), void *data, + const struct cpumask *cpus) +{ + return __stop_machine(fn, data, cpus); +} + #endif /* CONFIG_STOP_MACHINE && CONFIG_SMP */ #endif /* _LINUX_STOP_MACHINE */ -- cgit v1.2.3 From 192d8857427dd23707d5f0b86ca990c3af6f2d74 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Thu, 23 Jun 2011 11:19:29 -0700 Subject: x86, mtrr: use stop_machine APIs for doing MTRR rendezvous MTRR rendezvous sequence is not implemened using stop_machine() before, as this gets called both from the process context aswell as the cpu online paths (where the cpu has not come online and the interrupts are disabled etc). Now that we have a new stop_machine_from_inactive_cpu() API, use it for rendezvous during mtrr init of a logical processor that is coming online. For the rest (runtime MTRR modification, system boot, resume paths), use stop_machine() to implement the rendezvous sequence. This will consolidate and cleanup the code. Signed-off-by: Suresh Siddha Link: http://lkml.kernel.org/r/20110623182057.076997177@sbsiddha-MOBL3.sc.intel.com Signed-off-by: H. Peter Anvin --- include/linux/stop_machine.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index e0f2da25d751..4a9d0c7edc65 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -27,8 +27,6 @@ struct cpu_stop_work { struct cpu_stop_done *done; }; -extern struct mutex stop_cpus_mutex; - int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg); void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg, struct cpu_stop_work *work_buf); -- cgit v1.2.3 From 4d258b25d947521c8b913154db61ec55198243f8 Mon Sep 17 00:00:00 2001 From: Vitaliy Ivanov Date: Mon, 27 Jun 2011 19:07:08 +0300 Subject: Fix some kernel-doc warnings Fix 'make htmldocs' warnings: Warning(/include/linux/hrtimer.h:153): No description found for parameter 'clockid' Warning(/include/linux/device.h:604): Excess struct/union/enum/typedef member 'of_match' description in 'device' Warning(/include/net/sock.h:349): Excess struct/union/enum/typedef member 'sk_rmem_alloc' description in 'sock' Signed-off-by: Vitaliy Ivanov Acked-by: Grant Likely Acked-by: David S. Miller Signed-off-by: Linus Torvalds --- include/linux/device.h | 1 - include/linux/hrtimer.h | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 553fd37b173b..e4f62d8896b7 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -530,7 +530,6 @@ struct device_dma_parameters { * @dma_mem: Internal for coherent mem override. * @archdata: For arch-specific additions. * @of_node: Associated device tree node. - * @of_match: Matching of_device_id from driver. * @devt: For creating the sysfs "dev". * @devres_lock: Spinlock to protect the resource of the device. * @devres_head: The resources list of the device. diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 51932e5acf7c..fd0dc30c9f15 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -135,6 +135,7 @@ struct hrtimer_sleeper { * @cpu_base: per cpu clock base * @index: clock type index for per_cpu support when moving a * timer to a base on another cpu. + * @clockid: clock id for per_cpu support * @active: red black tree root node for the active timers * @resolution: the resolution of the clock, in nanoseconds * @get_time: function to retrieve the current time of the clock -- cgit v1.2.3 From 072441e21ddcd1140606b7d4ef6eab579a86b0b3 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 27 Jun 2011 16:18:02 -0700 Subject: mm: move shmem prototypes to shmem_fs.h Before adding any more global entry points into shmem.c, gather such prototypes into shmem_fs.h. Remove mm's own declarations from swap.h, but for now leave the ones in mm.h: because shmem_file_setup() and shmem_zero_setup() are called from various places, and we should not force other subsystems to update immediately. Signed-off-by: Hugh Dickins Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shmem_fs.h | 17 +++++++++++++++++ include/linux/swap.h | 10 ---------- 2 files changed, 17 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 2b7fec840517..cae65dc42bcc 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -5,6 +5,13 @@ #include #include +struct page; +struct file; +struct inode; +struct super_block; +struct user_struct; +struct vm_area_struct; + /* inode in-kernel data */ #define SHMEM_NR_DIRECT 16 @@ -45,7 +52,17 @@ static inline struct shmem_inode_info *SHMEM_I(struct inode *inode) return container_of(inode, struct shmem_inode_info, vfs_inode); } +/* + * Functions in mm/shmem.c called directly from elsewhere: + */ extern int init_tmpfs(void); extern int shmem_fill_super(struct super_block *sb, void *data, int silent); +extern struct file *shmem_file_setup(const char *name, + loff_t size, unsigned long flags); +extern int shmem_zero_setup(struct vm_area_struct *); +extern int shmem_lock(struct file *file, int lock, struct user_struct *user); +extern int shmem_unuse(swp_entry_t entry, struct page *page); +extern void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t pgoff, + struct page **pagep, swp_entry_t *ent); #endif diff --git a/include/linux/swap.h b/include/linux/swap.h index e70564647039..a273468f8285 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -300,16 +300,6 @@ static inline void scan_unevictable_unregister_node(struct node *node) extern int kswapd_run(int nid); extern void kswapd_stop(int nid); -#ifdef CONFIG_MMU -/* linux/mm/shmem.c */ -extern int shmem_unuse(swp_entry_t entry, struct page *page); -#endif /* CONFIG_MMU */ - -#ifdef CONFIG_CGROUP_MEM_RES_CTLR -extern void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t pgoff, - struct page **pagep, swp_entry_t *ent); -#endif - #ifdef CONFIG_SWAP /* linux/mm/page_io.c */ extern int swap_readpage(struct page *); -- cgit v1.2.3 From 94c1e62df4494b79782cb9c7279f827212d1de70 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 27 Jun 2011 16:18:03 -0700 Subject: tmpfs: take control of its truncate_range 2.6.35's new truncate convention gave tmpfs the opportunity to control its file truncation, no longer enforced from outside by vmtruncate(). We shall want to build upon that, to handle pagecache and swap together. Slightly redefine the ->truncate_range interface: let it now be called between the unmap_mapping_range()s, with the filesystem responsible for doing the truncate_inode_pages_range() from it - just as the filesystem is nowadays responsible for doing that from its ->setattr. Let's rename shmem_notify_change() to shmem_setattr(). Instead of calling the generic truncate_setsize(), bring that code in so we can call shmem_truncate_range() - which will later be updated to perform its own variant of truncate_inode_pages_range(). Remove the punch_hole unmap_mapping_range() from shmem_truncate_range(): now that the COW's unmap_mapping_range() comes after ->truncate_range, there is no need to call it a third time. Export shmem_truncate_range() and add it to the list in shmem_fs.h, so that i915_gem_object_truncate() can call it explicitly in future; get this patch in first, then update drm/i915 once this is available (until then, i915 will just be doing the truncate_inode_pages() twice). Though introduced five years ago, no other filesystem is implementing ->truncate_range, and its only other user is madvise(,,MADV_REMOVE): we expect to convert it to fallocate(,FALLOC_FL_PUNCH_HOLE,,) shortly, whereupon ->truncate_range can be removed from inode_operations - shmem_truncate_range() will help i915 across that transition too. Signed-off-by: Hugh Dickins Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shmem_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index cae65dc42bcc..22a20af4d785 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -61,6 +61,7 @@ extern struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags); extern int shmem_zero_setup(struct vm_area_struct *); extern int shmem_lock(struct file *file, int lock, struct user_struct *user); +extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); extern int shmem_unuse(swp_entry_t entry, struct page *page); extern void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t pgoff, struct page **pagep, swp_entry_t *ent); -- cgit v1.2.3 From d9d90e5eb70e09903dadff42099b6c948f814050 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 27 Jun 2011 16:18:04 -0700 Subject: tmpfs: add shmem_read_mapping_page_gfp Although it is used (by i915) on nothing but tmpfs, read_cache_page_gfp() is unsuited to tmpfs, because it inserts a page into pagecache before calling the filesystem's ->readpage: tmpfs may have pages in swapcache which only it knows how to locate and switch to filecache. At present tmpfs provides a ->readpage method, and copes with this by copying pages; but soon we can simplify it by removing its ->readpage. Provide shmem_read_mapping_page_gfp() now, ready for that transition, Export shmem_read_mapping_page_gfp() and add it to list in shmem_fs.h, with shmem_read_mapping_page() inline for the common mapping_gfp case. (shmem_read_mapping_page_gfp or shmem_read_cache_page_gfp? Generally the read_mapping_page functions use the mapping's ->readpage, and the read_cache_page functions use the supplied filler, so I think read_cache_page_gfp was slightly misnamed.) Signed-off-by: Hugh Dickins Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shmem_fs.h | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 22a20af4d785..aa08fa8fd79b 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -3,15 +3,9 @@ #include #include +#include #include -struct page; -struct file; -struct inode; -struct super_block; -struct user_struct; -struct vm_area_struct; - /* inode in-kernel data */ #define SHMEM_NR_DIRECT 16 @@ -61,9 +55,18 @@ extern struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags); extern int shmem_zero_setup(struct vm_area_struct *); extern int shmem_lock(struct file *file, int lock, struct user_struct *user); +extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, + pgoff_t index, gfp_t gfp_mask); extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); extern int shmem_unuse(swp_entry_t entry, struct page *page); extern void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t pgoff, struct page **pagep, swp_entry_t *ent); +static inline struct page *shmem_read_mapping_page( + struct address_space *mapping, pgoff_t index) +{ + return shmem_read_mapping_page_gfp(mapping, index, + mapping_gfp_mask(mapping)); +} + #endif -- cgit v1.2.3 From 507c5f1224014f9956e604ee8703b3bbea7da4a4 Mon Sep 17 00:00:00 2001 From: Chris Metcalf Date: Mon, 27 Jun 2011 16:18:07 -0700 Subject: include/linux/compat.h: declare compat_sys_sendmmsg() This is required for tilegx to be able to use the compat unistd.h header where compat_sys_sendmmsg() is now mentioned. Signed-off-by: Chris Metcalf Cc: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compat.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index ddcb7db38e67..846bb1792572 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -467,6 +467,8 @@ asmlinkage long compat_sys_setsockopt(int fd, int level, int optname, char __user *optval, unsigned int optlen); asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, unsigned flags); +asmlinkage long compat_sys_sendmmsg(int fd, struct compat_mmsghdr __user *mmsg, + unsigned vlen, unsigned int flags); asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg, unsigned int flags); asmlinkage long compat_sys_recv(int fd, void __user *buf, size_t len, -- cgit v1.2.3 From 08142579b6ca35883c1ed066a2681de6f6917062 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 27 Jun 2011 16:18:10 -0700 Subject: mm: fix assertion mapping->nrpages == 0 in end_writeback() Under heavy memory and filesystem load, users observe the assertion mapping->nrpages == 0 in end_writeback() trigger. This can be caused by page reclaim reclaiming the last page from a mapping in the following race: CPU0 CPU1 ... shrink_page_list() __remove_mapping() __delete_from_page_cache() radix_tree_delete() evict_inode() truncate_inode_pages() truncate_inode_pages_range() pagevec_lookup() - finds nothing end_writeback() mapping->nrpages != 0 -> BUG page->mapping = NULL mapping->nrpages-- Fix the problem by doing a reliable check of mapping->nrpages under mapping->tree_lock in end_writeback(). Analyzed by Jay , lost in LKML, and dug out by Miklos Szeredi . Cc: Jay Cc: Miklos Szeredi Signed-off-by: Jan Kara Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 6e73e2e9ae33..b5b979247863 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -639,6 +639,7 @@ struct address_space { struct prio_tree_root i_mmap; /* tree of private and shared mappings */ struct list_head i_mmap_nonlinear;/*list VM_NONLINEAR mappings */ struct mutex i_mmap_mutex; /* protect tree, count, list */ + /* Protected by tree_lock together with the radix tree */ unsigned long nrpages; /* number of total pages */ pgoff_t writeback_index;/* writeback starts here */ const struct address_space_operations *a_ops; /* methods */ -- cgit v1.2.3 From 9174fc8f111982e024a00512c521ad8f1056fccb Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Tue, 28 Jun 2011 15:25:36 +0900 Subject: serial: sh-sci: Fix up pretty name printing for port IRQs. Presently these were all using the same static string with no regard to dev_name() and the like. This implements a bit of rework to name the IRQ dynamically, as it should have been doing all along anyways. Signed-off-by: Paul Mundt --- include/linux/serial_sci.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_sci.h b/include/linux/serial_sci.h index 4ca130a90ea5..8bffe9ae2ca0 100644 --- a/include/linux/serial_sci.h +++ b/include/linux/serial_sci.h @@ -56,6 +56,8 @@ enum { SCIx_TXI_IRQ, SCIx_BRI_IRQ, SCIx_NR_IRQS, + + SCIx_MUX_IRQ = SCIx_NR_IRQS, /* special case */ }; enum { @@ -82,6 +84,11 @@ enum { [SCIx_BRI_IRQ] = (irq), \ } +#define SCIx_IRQ_IS_MUXED(port) \ + ((port)->cfg->irqs[SCIx_ERI_IRQ] == \ + (port)->cfg->irqs[SCIx_RXI_IRQ]) || \ + ((port)->cfg->irqs[SCIx_ERI_IRQ] && \ + !(port)->cfg->irqs[SCIx_RXI_IRQ]) /* * SCI register subset common for all port types. * Not all registers will exist on all parts. -- cgit v1.2.3 From e1f91f82b8bb031fe1b7731fb3666fa68c97fd38 Mon Sep 17 00:00:00 2001 From: Vitaliy Ivanov Date: Mon, 27 Jun 2011 19:07:08 +0300 Subject: treewide: fix kernel-doc warnings Fix 'make htmldocs' warnings: Warning(/include/linux/hrtimer.h:153): No description found for parameter 'clockid' Warning(/include/linux/device.h:604): Excess struct/union/enum/typedef member 'of_match' description in 'device' Warning(/include/net/sock.h:349): Excess struct/union/enum/typedef member 'sk_rmem_alloc' description in 'sock' Signed-off-by: Vitaliy Ivanov Acked-by: Grant Likely Acked-by: David S. Miller Acked-by: Randy Dunlap Signed-off-by: Jiri Kosina --- include/linux/device.h | 1 - include/linux/hrtimer.h | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index c66111affca9..5056cf8d935f 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -530,7 +530,6 @@ struct device_dma_parameters { * @dma_mem: Internal for coherent mem override. * @archdata: For arch-specific additions. * @of_node: Associated device tree node. - * @of_match: Matching of_device_id from driver. * @devt: For creating the sysfs "dev". * @devres_lock: Spinlock to protect the resource of the device. * @devres_head: The resources list of the device. diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 51932e5acf7c..fd0dc30c9f15 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -135,6 +135,7 @@ struct hrtimer_sleeper { * @cpu_base: per cpu clock base * @index: clock type index for per_cpu support when moving a * timer to a base on another cpu. + * @clockid: clock id for per_cpu support * @active: red black tree root node for the active timers * @resolution: the resolution of the clock, in nanoseconds * @get_time: function to retrieve the current time of the clock -- cgit v1.2.3 From 2ccea03a8f7ec93641791f2760d7cdc6cab6205f Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Tue, 28 Jun 2011 16:33:46 +0300 Subject: usb: gadget: introduce UDC Class this class will be used to abstract away several of the duplicated operations scattered among the USB gadget controller drivers. Later, we can add an atomic notifier to tell interested drivers about what's happening with the controller. Notifications such as suspend, resume, enumerated, etc. will be useful, at a minimum, for implementing usb charger detection. As part of the converting process usb_gadget_probe_driver() is no longer part of each udc but pushed into the ->stap() callback. The same for his couterpart. The core is currently set explicit to 'n'. It will be changed to 'y' once all users are converted since it provides functions which clash with other drivers. Signed-off-by: Felipe Balbi Signed-off-by: Sebastian Andrzej Siewior Acked-by: Michal Nazarewicz Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/gadget.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 55d1a88ff11f..18979cfb6d66 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -418,6 +418,7 @@ static inline void usb_ep_fifo_flush(struct usb_ep *ep) /*-------------------------------------------------------------------------*/ struct usb_gadget; +struct usb_gadget_driver; /* the rest of the api to the controller hardware: device operations, * which don't involve endpoints (or i/o). @@ -431,6 +432,9 @@ struct usb_gadget_ops { int (*pullup) (struct usb_gadget *, int is_on); int (*ioctl)(struct usb_gadget *, unsigned code, unsigned long param); + int (*start)(struct usb_gadget_driver *, + int (*bind)(struct usb_gadget *)); + int (*stop)(struct usb_gadget_driver *); }; /** @@ -822,6 +826,9 @@ int usb_gadget_probe_driver(struct usb_gadget_driver *driver, */ int usb_gadget_unregister_driver(struct usb_gadget_driver *driver); +extern int usb_add_gadget_udc(struct device *parent, struct usb_gadget *gadget); +extern void usb_del_gadget_udc(struct usb_gadget *gadget); + /*-------------------------------------------------------------------------*/ /* utility to simplify dealing with string descriptors */ -- cgit v1.2.3 From 72c973dd2b01b212a159faa330a2bc641a3ed809 Mon Sep 17 00:00:00 2001 From: Tatyana Brokhman Date: Tue, 28 Jun 2011 16:33:48 +0300 Subject: usb: gadget: add usb_endpoint_descriptor to struct usb_ep Change usb_ep_enable() prototype to use endpoint descriptor from usb_ep. This optimization spares the FDs from saving the endpoint chosen descriptor. This optimization is not full though. To fully exploit this change, one needs to update all the UDCs as well since in the current implementation each of them saves the endpoint descriptor in it's internal (and extended) endpoint structure. Signed-off-by: Tatyana Brokhman Signed-off-by: Felipe Balbi Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/gadget.h | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 18979cfb6d66..fe50912585f8 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -132,8 +132,9 @@ struct usb_ep_ops { * @maxpacket:The maximum packet size used on this endpoint. The initial * value can sometimes be reduced (hardware allowing), according to * the endpoint descriptor used to configure the endpoint. - * @driver_data:for use by the gadget driver. all other fields are - * read-only to gadget drivers. + * @driver_data:for use by the gadget driver. + * @desc: endpoint descriptor. This pointer is set before the endpoint is + * enabled and remains valid until the endpoint is disabled. * * the bus controller driver lists all the general purpose endpoints in * gadget->ep_list. the control endpoint (gadget->ep0) is not in that list, @@ -146,6 +147,7 @@ struct usb_ep { const struct usb_ep_ops *ops; struct list_head ep_list; unsigned maxpacket:16; + const struct usb_endpoint_descriptor *desc; }; /*-------------------------------------------------------------------------*/ @@ -154,11 +156,8 @@ struct usb_ep { * usb_ep_enable - configure endpoint, making it usable * @ep:the endpoint being configured. may not be the endpoint named "ep0". * drivers discover endpoints through the ep_list of a usb_gadget. - * @desc:descriptor for desired behavior. caller guarantees this pointer - * remains valid until the endpoint is disabled; the data byte order - * is little-endian (usb-standard). * - * when configurations are set, or when interface settings change, the driver + * When configurations are set, or when interface settings change, the driver * will enable or disable the relevant endpoints. while it is enabled, an * endpoint may be used for i/o until the driver receives a disconnect() from * the host or until the endpoint is disabled. @@ -173,10 +172,9 @@ struct usb_ep { * * returns zero, or a negative error code. */ -static inline int usb_ep_enable(struct usb_ep *ep, - const struct usb_endpoint_descriptor *desc) +static inline int usb_ep_enable(struct usb_ep *ep) { - return ep->ops->enable(ep, desc); + return ep->ops->enable(ep, ep->desc); } /** -- cgit v1.2.3 From 48767a4e8263620c347c3fa17812c943dd0fc2fa Mon Sep 17 00:00:00 2001 From: Tatyana Brokhman Date: Tue, 28 Jun 2011 16:33:49 +0300 Subject: usb: gadget: configure endpoint according to gadget speed Add config_ep_by_speed() to configure the endpoint according to the gadget speed. Using this function will spare the FDs from handling the endpoint chosen descriptor. Signed-off-by: Tatyana Brokhman Signed-off-by: Felipe Balbi Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/composite.h | 3 +++ include/linux/usb/gadget.h | 3 +++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index b78cba466d3d..2014d6b1babc 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -145,6 +145,9 @@ int usb_function_activate(struct usb_function *); int usb_interface_id(struct usb_configuration *, struct usb_function *); +int config_ep_by_speed(struct usb_gadget *g, struct usb_function *f, + struct usb_ep *_ep); + /** * ep_choose - select descriptor endpoint at current device speed * @g: gadget, connected and running at some speed diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index fe50912585f8..0bcc2b76bcd8 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -133,6 +133,8 @@ struct usb_ep_ops { * value can sometimes be reduced (hardware allowing), according to * the endpoint descriptor used to configure the endpoint. * @driver_data:for use by the gadget driver. + * @address: used to identify the endpoint when finding descriptor that + * matches connection speed * @desc: endpoint descriptor. This pointer is set before the endpoint is * enabled and remains valid until the endpoint is disabled. * @@ -147,6 +149,7 @@ struct usb_ep { const struct usb_ep_ops *ops; struct list_head ep_list; unsigned maxpacket:16; + u8 address; const struct usb_endpoint_descriptor *desc; }; -- cgit v1.2.3 From ea2a1df7b2b1de839a72217d85bfb4b7b049010c Mon Sep 17 00:00:00 2001 From: Tatyana Brokhman Date: Tue, 28 Jun 2011 16:33:50 +0300 Subject: usb: gadget: use config_ep_by_speed() instead of ep_choose() Remove obsolete functions: 1. ep_choose() 2. usb_find_endpoint() Signed-off-by: Tatyana Brokhman Signed-off-by: Felipe Balbi Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/composite.h | 15 --------------- include/linux/usb/gadget.h | 6 ------ 2 files changed, 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 2014d6b1babc..99830d63d8f1 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -148,21 +148,6 @@ int usb_interface_id(struct usb_configuration *, struct usb_function *); int config_ep_by_speed(struct usb_gadget *g, struct usb_function *f, struct usb_ep *_ep); -/** - * ep_choose - select descriptor endpoint at current device speed - * @g: gadget, connected and running at some speed - * @hs: descriptor to use for high speed operation - * @fs: descriptor to use for full or low speed operation - */ -static inline struct usb_endpoint_descriptor * -ep_choose(struct usb_gadget *g, struct usb_endpoint_descriptor *hs, - struct usb_endpoint_descriptor *fs) -{ - if (gadget_is_dualspeed(g) && g->speed == USB_SPEED_HIGH) - return hs; - return fs; -} - #define MAX_CONFIG_INTERFACES 16 /* arbitrary; max 255 */ /** diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 0bcc2b76bcd8..d22b4a4936cb 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -879,12 +879,6 @@ int usb_gadget_config_buf(const struct usb_config_descriptor *config, struct usb_descriptor_header **usb_copy_descriptors( struct usb_descriptor_header **); -/* return copy of endpoint descriptor given original descriptor set */ -struct usb_endpoint_descriptor *usb_find_endpoint( - struct usb_descriptor_header **src, - struct usb_descriptor_header **copy, - struct usb_endpoint_descriptor *match); - /** * usb_free_descriptors - free descriptors returned by usb_copy_descriptors() * @v: vector of descriptors -- cgit v1.2.3 From a59d6b91cbca52235e3ed9f7f9e34c4f2f3e1996 Mon Sep 17 00:00:00 2001 From: Tatyana Brokhman Date: Tue, 28 Jun 2011 16:33:53 +0300 Subject: usb: gadget: add streams support to the gadget framework This patch defines necessary fields to support streaming for USB3.0. It implements a new function, called usb_ep_autoconfig_ss(), to be used instead of the existing usb_ep_autoconfig() when working in SuperSpeed mode and there is a need to search for an endpoint according to the number of required streams. [ balbi@ti.com : slight changes to commit log ] Signed-off-by: Maya Erez Signed-off-by: Tatyana Brokhman Signed-off-by: Felipe Balbi Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/gadget.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index d22b4a4936cb..625971292c20 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -28,6 +28,7 @@ struct usb_ep; * field, and the usb controller needs one, it is responsible * for mapping and unmapping the buffer. * @length: Length of that data + * @stream_id: The stream id, when USB3.0 bulk streams are being used * @no_interrupt: If true, hints that no completion irq is needed. * Helpful sometimes with deep request queues that are handled * directly by DMA controllers. @@ -82,6 +83,7 @@ struct usb_request { unsigned length; dma_addr_t dma; + unsigned stream_id:16; unsigned no_interrupt:1; unsigned zero:1; unsigned short_not_ok:1; @@ -132,11 +134,15 @@ struct usb_ep_ops { * @maxpacket:The maximum packet size used on this endpoint. The initial * value can sometimes be reduced (hardware allowing), according to * the endpoint descriptor used to configure the endpoint. + * @max_streams: The maximum number of streams supported + * by this EP (0 - 16, actual number is 2^n) * @driver_data:for use by the gadget driver. * @address: used to identify the endpoint when finding descriptor that * matches connection speed * @desc: endpoint descriptor. This pointer is set before the endpoint is * enabled and remains valid until the endpoint is disabled. + * @comp_desc: In case of SuperSpeed support, this is the endpoint companion + * descriptor that is used to configure the endpoint * * the bus controller driver lists all the general purpose endpoints in * gadget->ep_list. the control endpoint (gadget->ep0) is not in that list, @@ -149,8 +155,10 @@ struct usb_ep { const struct usb_ep_ops *ops; struct list_head ep_list; unsigned maxpacket:16; + unsigned max_streams:16; u8 address; const struct usb_endpoint_descriptor *desc; + const struct usb_ss_ep_comp_descriptor *comp_desc; }; /*-------------------------------------------------------------------------*/ @@ -895,6 +903,11 @@ static inline void usb_free_descriptors(struct usb_descriptor_header **v) extern struct usb_ep *usb_ep_autoconfig(struct usb_gadget *, struct usb_endpoint_descriptor *); + +extern struct usb_ep *usb_ep_autoconfig_ss(struct usb_gadget *, + struct usb_endpoint_descriptor *, + struct usb_ss_ep_comp_descriptor *); + extern void usb_ep_autoconfig_reset(struct usb_gadget *); #endif /* __LINUX_USB_GADGET_H */ -- cgit v1.2.3 From 3d73710880afa3d61cf57b5d4eb192e812eb7e4f Mon Sep 17 00:00:00 2001 From: Jesse Barnes Date: Tue, 28 Jun 2011 10:59:12 -0700 Subject: cpufreq: expose a cpufreq_quick_get_max routine This allows drivers and other code to get the max reported CPU frequency. Initial use is for scaling ring frequency with GPU frequency in the i915 driver. Signed-off-by: Jesse Barnes Signed-off-by: Keith Packard --- include/linux/cpufreq.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 11be48e0d168..6216115c7789 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -324,11 +324,16 @@ static inline unsigned int cpufreq_get(unsigned int cpu) /* query the last known CPU freq (in kHz). If zero, cpufreq couldn't detect it */ #ifdef CONFIG_CPU_FREQ unsigned int cpufreq_quick_get(unsigned int cpu); +unsigned int cpufreq_quick_get_max(unsigned int cpu); #else static inline unsigned int cpufreq_quick_get(unsigned int cpu) { return 0; } +static inline unsigned int cpufreq_quick_get_max(unsigned int cpu) +{ + return 0; +} #endif -- cgit v1.2.3 From a6b0919140b49e0871584362ae0cf1d18c476058 Mon Sep 17 00:00:00 2001 From: John Bonesio Date: Mon, 27 Jun 2011 16:49:57 -0700 Subject: of/gpio: Add new method for getting gpios under different property names This patch adds a new routine, of_get_named_gpio_flags(), which takes the property name as a parameter rather than assuming "gpios". of_get_gpio_flags() is modified to call of_get_named_gpio_flags() with "gpios" as the property parameter. Signed-off-by: John Bonesio [grant.likely: Tidied up whitespace and tweaked kerneldoc comments.] Signed-off-by: Grant Likely --- include/linux/of_gpio.h | 42 +++++++++++++++++++++++++++++++++++++----- 1 file changed, 37 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_gpio.h b/include/linux/of_gpio.h index 6598c04dab01..aec8025c786a 100644 --- a/include/linux/of_gpio.h +++ b/include/linux/of_gpio.h @@ -46,8 +46,9 @@ static inline struct of_mm_gpio_chip *to_of_mm_gpio_chip(struct gpio_chip *gc) return container_of(gc, struct of_mm_gpio_chip, gc); } -extern int of_get_gpio_flags(struct device_node *np, int index, - enum of_gpio_flags *flags); +extern int of_get_named_gpio_flags(struct device_node *np, + const char *list_name, int index, enum of_gpio_flags *flags); + extern unsigned int of_gpio_count(struct device_node *np); extern int of_mm_gpiochip_add(struct device_node *np, @@ -60,8 +61,8 @@ extern struct gpio_chip *of_node_to_gpiochip(struct device_node *np); #else /* CONFIG_OF_GPIO */ /* Drivers may not strictly depend on the GPIO support, so let them link. */ -static inline int of_get_gpio_flags(struct device_node *np, int index, - enum of_gpio_flags *flags) +static inline int of_get_named_gpio_flags(struct device_node *np, + const char *list_name, int index, enum of_gpio_flags *flags) { return -ENOSYS; } @@ -77,7 +78,38 @@ static inline void of_gpiochip_remove(struct gpio_chip *gc) { } #endif /* CONFIG_OF_GPIO */ /** - * of_get_gpio - Get a GPIO number to use with GPIO API + * of_get_gpio_flags() - Get a GPIO number and flags to use with GPIO API + * @np: device node to get GPIO from + * @index: index of the GPIO + * @flags: a flags pointer to fill in + * + * Returns GPIO number to use with Linux generic GPIO API, or one of the errno + * value on the error condition. If @flags is not NULL the function also fills + * in flags for the GPIO. + */ +static inline int of_get_gpio_flags(struct device_node *np, int index, + enum of_gpio_flags *flags) +{ + return of_get_named_gpio_flags(np, "gpios", index, flags); +} + +/** + * of_get_named_gpio() - Get a GPIO number to use with GPIO API + * @np: device node to get GPIO from + * @propname: Name of property containing gpio specifier(s) + * @index: index of the GPIO + * + * Returns GPIO number to use with Linux generic GPIO API, or one of the errno + * value on the error condition. + */ +static inline int of_get_named_gpio(struct device_node *np, + const char *propname, int index) +{ + return of_get_named_gpio_flags(np, propname, index, NULL); +} + +/** + * of_get_gpio() - Get a GPIO number to use with GPIO API * @np: device node to get GPIO from * @index: index of the GPIO * -- cgit v1.2.3 From f457a46f179df41b0f6d80dee33b6e629945f276 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 24 Jun 2011 15:11:53 -0500 Subject: [SCSI] iscsi_ibft, be2iscsi, iscsi_boot: fix boot kobj data lifetime management be2iscsi passes the boot functions its phba object which is allocated in the shost, but iscsi_ibft passes in a object allocated for each item to display. The problem is that iscsi_boot_sysfs was managing the lifetime of the object passed in and doing a kfree on release. This causes a double free for be2iscsi which frees the shost in its pci_remove. This patch fixes the problem by adding a release callback which the drivers can call kfree or a put() type of function (needed for be2iscsi which will do a get/put on the shost). Signed-off-by: Mike Christie Signed-off-by: James Bottomley --- include/linux/iscsi_boot_sysfs.h | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iscsi_boot_sysfs.h b/include/linux/iscsi_boot_sysfs.h index f1e6c184f14f..f0a2f8b0aa13 100644 --- a/include/linux/iscsi_boot_sysfs.h +++ b/include/linux/iscsi_boot_sysfs.h @@ -92,6 +92,13 @@ struct iscsi_boot_kobj { * properties. */ mode_t (*is_visible) (void *data, int type); + + /* + * Driver specific release function. + * + * The function should free the data passed in. + */ + void (*release) (void *data); }; struct iscsi_boot_kset { @@ -103,18 +110,21 @@ struct iscsi_boot_kobj * iscsi_boot_create_initiator(struct iscsi_boot_kset *boot_kset, int index, void *data, ssize_t (*show) (void *data, int type, char *buf), - mode_t (*is_visible) (void *data, int type)); + mode_t (*is_visible) (void *data, int type), + void (*release) (void *data)); struct iscsi_boot_kobj * iscsi_boot_create_ethernet(struct iscsi_boot_kset *boot_kset, int index, void *data, ssize_t (*show) (void *data, int type, char *buf), - mode_t (*is_visible) (void *data, int type)); + mode_t (*is_visible) (void *data, int type), + void (*release) (void *data)); struct iscsi_boot_kobj * iscsi_boot_create_target(struct iscsi_boot_kset *boot_kset, int index, void *data, ssize_t (*show) (void *data, int type, char *buf), - mode_t (*is_visible) (void *data, int type)); + mode_t (*is_visible) (void *data, int type), + void (*release) (void *data)); struct iscsi_boot_kset *iscsi_boot_create_kset(const char *set_name); struct iscsi_boot_kset *iscsi_boot_create_host_kset(unsigned int hostno); -- cgit v1.2.3 From 15b493d11fcce3c5547e3d7fb6d90e11ffe12777 Mon Sep 17 00:00:00 2001 From: Lars Ellenberg Date: Tue, 28 Jun 2011 09:48:48 +0200 Subject: drbd: fix limit define, we support 1 PiByte now Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg --- include/linux/drbd_limits.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h index 246f576c981d..447c36752385 100644 --- a/include/linux/drbd_limits.h +++ b/include/linux/drbd_limits.h @@ -117,10 +117,10 @@ /* drbdsetup XY resize -d Z * you are free to reduce the device size to nothing, if you want to. * the upper limit with 64bit kernel, enough ram and flexible meta data - * is 16 TB, currently. */ + * is 1 PiB, currently. */ /* DRBD_MAX_SECTORS */ #define DRBD_DISK_SIZE_SECT_MIN 0 -#define DRBD_DISK_SIZE_SECT_MAX (16 * (2LLU << 30)) +#define DRBD_DISK_SIZE_SECT_MAX (1 * (2LLU << 40)) #define DRBD_DISK_SIZE_SECT_DEF 0 /* = disabled = no user size... */ #define DRBD_ON_IO_ERROR_DEF EP_PASS_ON -- cgit v1.2.3 From 131ad62d8fc06d9d0a5c61d9526876352c2f2bbd Mon Sep 17 00:00:00 2001 From: Mr Dash Four Date: Thu, 30 Jun 2011 13:31:57 +0200 Subject: netfilter: add SELinux context support to AUDIT target In this revision the conversion of secid to SELinux context and adding it to the audit log is moved from xt_AUDIT.c to audit.c with the aid of a separate helper function - audit_log_secctx - which does both the conversion and logging of SELinux context, thus also preventing internal secid number being leaked to userspace. If conversion is not successful an error is raised. With the introduction of this helper function the work done in xt_AUDIT.c is much more simplified. It also opens the possibility of this helper function being used by other modules (including auditd itself), if desired. With this addition, typical (raw auditd) output after applying the patch would be: type=NETFILTER_PKT msg=audit(1305852240.082:31012): action=0 hook=1 len=52 inif=? outif=eth0 saddr=10.1.1.7 daddr=10.1.2.1 ipid=16312 proto=6 sport=56150 dport=22 obj=system_u:object_r:ssh_client_packet_t:s0 type=NETFILTER_PKT msg=audit(1306772064.079:56): action=0 hook=3 len=48 inif=eth0 outif=? smac=00:05:5d:7c:27:0b dmac=00:02:b3:0a:7f:81 macproto=0x0800 saddr=10.1.2.1 daddr=10.1.1.7 ipid=462 proto=6 sport=22 dport=3561 obj=system_u:object_r:ssh_server_packet_t:s0 Acked-by: Eric Paris Signed-off-by: Mr Dash Four Signed-off-by: Patrick McHardy --- include/linux/audit.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 9d339eb27881..0c8006129fb2 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -613,6 +613,12 @@ extern void audit_log_d_path(struct audit_buffer *ab, extern void audit_log_key(struct audit_buffer *ab, char *key); extern void audit_log_lost(const char *message); +#ifdef CONFIG_SECURITY +extern void audit_log_secctx(struct audit_buffer *ab, u32 secid); +#else +#define audit_log_secctx(b,s) do { ; } while (0) +#endif + extern int audit_update_lsm_rules(void); /* Private API (for audit.c only) */ @@ -635,6 +641,7 @@ extern int audit_enabled; #define audit_log_untrustedstring(a,s) do { ; } while (0) #define audit_log_d_path(b, p, d) do { ; } while (0) #define audit_log_key(b, k) do { ; } while (0) +#define audit_log_secctx(b,s) do { ; } while (0) #define audit_enabled 0 #endif #endif -- cgit v1.2.3 From a3b853633d78c3930b513ee219df48637ac82eed Mon Sep 17 00:00:00 2001 From: Thomas Abraham Date: Thu, 30 Jun 2011 21:26:10 +0530 Subject: dt: add helper functions to read u32 and string property values Add helper functions to retrieve unsigned integer and string property values from properties of a device node. These helper functions can be used to lookup a property in a device node, perform error checking and read the property value. [grant.likely@secretlab.ca: Proposal and initial implementation] Signed-off-by: Thomas Abraham [grant.likely: some word smithing and be more defensive validating the string] Signed-off-by: Grant Likely --- include/linux/of.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index bfc0ed1b0ced..4fc4c1b8d5d5 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -195,6 +195,10 @@ extern struct device_node *of_find_node_with_property( extern struct property *of_find_property(const struct device_node *np, const char *name, int *lenp); +extern int of_property_read_u32(struct device_node *np, char *propname, + u32 *out_value); +extern int of_property_read_string(struct device_node *np, char *propname, + char **out_string); extern int of_device_is_compatible(const struct device_node *device, const char *); extern int of_device_is_available(const struct device_node *device); -- cgit v1.2.3 From 0209bcd4d9ee66569d4ea76f9ab2de3a9c740c71 Mon Sep 17 00:00:00 2001 From: Amit Kumar Salecha Date: Wed, 29 Jun 2011 20:00:49 +0000 Subject: net: add external loopback test in ethtool self test External loopback test can be performed by application without any driver support on normal Ethernet cards. But on CNA devices, where multiple functions share same physical port. Here internal loopback test and external loopback test can be initiated by multiple functions at same time. To co exist all functions, firmware need to regulate what test can be run by which function. So before performing external loopback test, command need to send to firmware, which will quiescent other functions. User may not want to run external loopback test always. As special cable need to be connected for this test. So adding explicit flag in ethtool self test, which will specify interface to perform external loopback test. ETH_TEST_FL_EXTERNAL_LB: Application set to request external loopback test ETH_TEST_FL_EXTERNAL_LB_DONE: Driver ack if test performed Signed-off-by: Amit Kumar Salecha Reviewed-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/ethtool.h | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 048d0fa38d03..c6e427ab65fe 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -310,9 +310,21 @@ struct ethtool_sset_info { __u32's, etc. */ }; +/** + * enum ethtool_test_flags - flags definition of ethtool_test + * @ETH_TEST_FL_OFFLINE: if set perform online and offline tests, otherwise + * only online tests. + * @ETH_TEST_FL_FAILED: Driver set this flag if test fails. + * @ETH_TEST_FL_EXTERNAL_LB: Application request to perform external loopback + * test. + * @ETH_TEST_FL_EXTERNAL_LB_DONE: Driver performed the external loopback test + */ + enum ethtool_test_flags { - ETH_TEST_FL_OFFLINE = (1 << 0), /* online / offline */ - ETH_TEST_FL_FAILED = (1 << 1), /* test passed / failed */ + ETH_TEST_FL_OFFLINE = (1 << 0), + ETH_TEST_FL_FAILED = (1 << 1), + ETH_TEST_FL_EXTERNAL_LB = (1 << 2), + ETH_TEST_FL_EXTERNAL_LB_DONE = (1 << 3), }; /* for requesting NIC test and getting results*/ -- cgit v1.2.3 From e6220bdc9485c5ea972f9e0e6d062a05934bb74b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 9 Jun 2011 13:08:25 +0000 Subject: i8253: Create common clockevent implementation arm, mips and x86 implement i8253 based clockevents. All the same code copied. Create a common implementation in drivers/clocksource/i8253.c. About time to rename drivers/clocksource/ to something else. Signed-off-by: Thomas Gleixner Cc: Russell King Cc: Ralf Baechle Cc: John Stultz Link: http://lkml.kernel.org/r/20110609130621.921710458@linutronix.de --- include/linux/i8253.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i8253.h b/include/linux/i8253.h index 76039c86ab58..487d50c7db39 100644 --- a/include/linux/i8253.h +++ b/include/linux/i8253.h @@ -24,6 +24,8 @@ #define outb_pit outb_p extern raw_spinlock_t i8253_lock; +extern struct clock_event_device i8253_clockevent; +extern void clockevent_i8253_init(bool oneshot); extern void setup_pit_timer(void); -- cgit v1.2.3 From 01898e3e29ea8242d81923da11ce88ba71290a48 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 9 Jun 2011 13:08:30 +0000 Subject: i8253: Cleanup outb/inb magic Remove the hysterical outb/inb_pit defines and use outb_p/inb_p in the code. Signed-off-by: Thomas Gleixner Cc: Russell King Cc: Ralf Baechle Cc: John Stultz Link: http://lkml.kernel.org/r/20110609130622.348437125@linutronix.de --- include/linux/i8253.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i8253.h b/include/linux/i8253.h index 487d50c7db39..e6bb36a97519 100644 --- a/include/linux/i8253.h +++ b/include/linux/i8253.h @@ -20,9 +20,6 @@ #define PIT_LATCH ((PIT_TICK_RATE + HZ/2) / HZ) -#define inb_pit inb_p -#define outb_pit outb_p - extern raw_spinlock_t i8253_lock; extern struct clock_event_device i8253_clockevent; extern void clockevent_i8253_init(bool oneshot); -- cgit v1.2.3 From 28009ce4a8130af7260a9271901b4419834ad152 Mon Sep 17 00:00:00 2001 From: Richard Kennedy Date: Tue, 7 Jun 2011 16:33:38 +0100 Subject: perf: Remove 64-bit alignment padding from perf_event_context Reorder perf_event_context to remove 8 bytes of 64 bit alignment padding shrinking its size to 192 bytes, allowing it to fit into a smaller slab and use one fewer cache lines. Signed-off-by: Richard Kennedy Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1307460819.1950.5.camel@castor.rsk Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index e76a41010e1f..2f7b5d42ab41 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -894,8 +894,8 @@ struct perf_event_context { u64 parent_gen; u64 generation; int pin_count; - struct rcu_head rcu_head; int nr_cgroups; /* cgroup events present */ + struct rcu_head rcu_head; }; /* -- cgit v1.2.3 From a8b0ca17b80e92faab46ee7179ba9e99ccb61233 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 27 Jun 2011 14:41:57 +0200 Subject: perf: Remove the nmi parameter from the swevent and overflow interface The nmi parameter indicated if we could do wakeups from the current context, if not, we would set some state and self-IPI and let the resulting interrupt do the wakeup. For the various event classes: - hardware: nmi=0; PMI is in fact an NMI or we run irq_work_run from the PMI-tail (ARM etc.) - tracepoint: nmi=0; since tracepoint could be from NMI context. - software: nmi=[0,1]; some, like the schedule thing cannot perform wakeups, and hence need 0. As one can see, there is very little nmi=1 usage, and the down-side of not using it is that on some platforms some software events can have a jiffy delay in wakeup (when arch_irq_work_raise isn't implemented). The up-side however is that we can remove the nmi parameter and save a bunch of conditionals in fast paths. Signed-off-by: Peter Zijlstra Cc: Michael Cree Cc: Will Deacon Cc: Deng-Cheng Zhu Cc: Anton Blanchard Cc: Eric B Munson Cc: Heiko Carstens Cc: Paul Mundt Cc: David S. Miller Cc: Frederic Weisbecker Cc: Jason Wessel Cc: Don Zickus Link: http://lkml.kernel.org/n/tip-agjev8eu666tvknpb3iaj0fg@git.kernel.org Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 2f7b5d42ab41..0946a8bc098d 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -682,7 +682,7 @@ enum perf_event_active_state { struct file; struct perf_sample_data; -typedef void (*perf_overflow_handler_t)(struct perf_event *, int, +typedef void (*perf_overflow_handler_t)(struct perf_event *, struct perf_sample_data *, struct pt_regs *regs); @@ -925,7 +925,6 @@ struct perf_output_handle { unsigned long size; void *addr; int page; - int nmi; int sample; }; @@ -993,7 +992,7 @@ extern void perf_prepare_sample(struct perf_event_header *header, struct perf_event *event, struct pt_regs *regs); -extern int perf_event_overflow(struct perf_event *event, int nmi, +extern int perf_event_overflow(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); @@ -1012,7 +1011,7 @@ static inline int is_software_event(struct perf_event *event) extern struct jump_label_key perf_swevent_enabled[PERF_COUNT_SW_MAX]; -extern void __perf_sw_event(u32, u64, int, struct pt_regs *, u64); +extern void __perf_sw_event(u32, u64, struct pt_regs *, u64); #ifndef perf_arch_fetch_caller_regs static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip) { } @@ -1034,7 +1033,7 @@ static inline void perf_fetch_caller_regs(struct pt_regs *regs) } static __always_inline void -perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr) +perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { struct pt_regs hot_regs; @@ -1043,7 +1042,7 @@ perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr) perf_fetch_caller_regs(&hot_regs); regs = &hot_regs; } - __perf_sw_event(event_id, nr, nmi, regs, addr); + __perf_sw_event(event_id, nr, regs, addr); } } @@ -1057,7 +1056,7 @@ static inline void perf_event_task_sched_in(struct task_struct *task) static inline void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next) { - perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0); + perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, NULL, 0); __perf_event_task_sched_out(task, next); } @@ -1119,7 +1118,7 @@ extern void perf_bp_event(struct perf_event *event, void *data); extern int perf_output_begin(struct perf_output_handle *handle, struct perf_event *event, unsigned int size, - int nmi, int sample); + int sample); extern void perf_output_end(struct perf_output_handle *handle); extern void perf_output_copy(struct perf_output_handle *handle, const void *buf, unsigned int len); @@ -1143,8 +1142,7 @@ static inline int perf_event_task_disable(void) { return -EINVAL; } static inline int perf_event_task_enable(void) { return -EINVAL; } static inline void -perf_sw_event(u32 event_id, u64 nr, int nmi, - struct pt_regs *regs, u64 addr) { } +perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { } static inline void perf_bp_event(struct perf_event *event, void *data) { } -- cgit v1.2.3 From a7ac67ea021b4603095d2aa458bc41641238f22c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 27 Jun 2011 16:47:16 +0200 Subject: perf: Remove the perf_output_begin(.sample) argument Since only samples call perf_output_sample() its much saner (and more correct) to put the sample logic in there than in the perf_output_begin()/perf_output_end() pair. Saves a useless argument, reduces conditionals and shrinks struct perf_output_handle, win! Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-2crpvsx3cqu67q3zqjbnlpsc@git.kernel.org Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 0946a8bc098d..771b0b2845e4 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -925,7 +925,6 @@ struct perf_output_handle { unsigned long size; void *addr; int page; - int sample; }; #ifdef CONFIG_PERF_EVENTS @@ -1117,8 +1116,7 @@ extern void perf_bp_event(struct perf_event *event, void *data); #endif extern int perf_output_begin(struct perf_output_handle *handle, - struct perf_event *event, unsigned int size, - int sample); + struct perf_event *event, unsigned int size); extern void perf_output_end(struct perf_output_handle *handle); extern void perf_output_copy(struct perf_output_handle *handle, const void *buf, unsigned int len); -- cgit v1.2.3 From efc9f05df2dd171280dcb736a4d973ffefd5508e Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Mon, 6 Jun 2011 16:57:03 +0200 Subject: perf_events: Update Intel extra regs shared constraints management This patch improves the code managing the extra shared registers used for offcore_response events on Intel Nehalem/Westmere. The idea is to use static allocation instead of dynamic allocation. This simplifies greatly the get and put constraint routines for those events. The patch also renames per_core to shared_regs because the same data structure gets used whether or not HT is on. When HT is off, those events still need to coordination because they use a extra MSR that has to be shared within an event group. Signed-off-by: Stephane Eranian Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110606145703.GA7258@quad Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 771b0b2845e4..069315eefb22 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -536,6 +536,16 @@ struct perf_branch_stack { struct task_struct; +/* + * extra PMU register associated with an event + */ +struct hw_perf_event_extra { + u64 config; /* register value */ + unsigned int reg; /* register address or index */ + int alloc; /* extra register already allocated */ + int idx; /* index in shared_regs->regs[] */ +}; + /** * struct hw_perf_event - performance event hardware details: */ @@ -549,9 +559,7 @@ struct hw_perf_event { unsigned long event_base; int idx; int last_cpu; - unsigned int extra_reg; - u64 extra_config; - int extra_alloc; + struct hw_perf_event_extra extra_reg; }; struct { /* software */ struct hrtimer hrtimer; -- cgit v1.2.3 From 89d6c0b5bdbb1927775584dcf532d98b3efe1477 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 22 Apr 2011 23:37:06 +0200 Subject: perf, arch: Add generic NODE cache events Add a NODE level to the generic cache events which is used to measure local vs remote memory accesses. Like all other cache events, an ACCESS is HIT+MISS, if there is no way to distinguish between reads and writes do reads only etc.. The below needs filling out for !x86 (which I filled out with unsupported events). I'm fairly sure ARM can leave it like that since it doesn't strike me as an architecture that even has NUMA support. SH might have something since it does appear to have some NUMA bits. Sparc64, PowerPC and MIPS certainly want a good look there since they clearly are NUMA capable. Signed-off-by: Peter Zijlstra Cc: David Miller Cc: Anton Blanchard Cc: David Daney Cc: Deng-Cheng Zhu Cc: Paul Mundt Cc: Will Deacon Cc: Robert Richter Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1303508226.4865.8.camel@laptop Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 069315eefb22..a5f54b973bdb 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -61,7 +61,7 @@ enum perf_hw_id { /* * Generalized hardware cache events: * - * { L1-D, L1-I, LLC, ITLB, DTLB, BPU } x + * { L1-D, L1-I, LLC, ITLB, DTLB, BPU, NODE } x * { read, write, prefetch } x * { accesses, misses } */ @@ -72,6 +72,7 @@ enum perf_hw_cache_id { PERF_COUNT_HW_CACHE_DTLB = 3, PERF_COUNT_HW_CACHE_ITLB = 4, PERF_COUNT_HW_CACHE_BPU = 5, + PERF_COUNT_HW_CACHE_NODE = 6, PERF_COUNT_HW_CACHE_MAX, /* non-ABI */ }; -- cgit v1.2.3 From 4dc0da86967d5463708631d02a70cfed5b104884 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Wed, 29 Jun 2011 18:42:35 +0300 Subject: perf: Add context field to perf_event The perf_event overflow handler does not receive any caller-derived argument, so many callers need to resort to looking up the perf_event in their local data structure. This is ugly and doesn't scale if a single callback services many perf_events. Fix by adding a context parameter to perf_event_create_kernel_counter() (and derived hardware breakpoints APIs) and storing it in the perf_event. The field can be accessed from the callback as event->overflow_handler_context. All callers are updated. Signed-off-by: Avi Kivity Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1309362157-6596-2-git-send-email-avi@redhat.com Signed-off-by: Ingo Molnar --- include/linux/hw_breakpoint.h | 10 ++++++++-- include/linux/perf_event.h | 4 +++- 2 files changed, 11 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h index d1e55fed2c7d..6ae9c631a1be 100644 --- a/include/linux/hw_breakpoint.h +++ b/include/linux/hw_breakpoint.h @@ -73,6 +73,7 @@ static inline unsigned long hw_breakpoint_len(struct perf_event *bp) extern struct perf_event * register_user_hw_breakpoint(struct perf_event_attr *attr, perf_overflow_handler_t triggered, + void *context, struct task_struct *tsk); /* FIXME: only change from the attr, and don't unregister */ @@ -85,11 +86,13 @@ modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr); extern struct perf_event * register_wide_hw_breakpoint_cpu(struct perf_event_attr *attr, perf_overflow_handler_t triggered, + void *context, int cpu); extern struct perf_event * __percpu * register_wide_hw_breakpoint(struct perf_event_attr *attr, - perf_overflow_handler_t triggered); + perf_overflow_handler_t triggered, + void *context); extern int register_perf_hw_breakpoint(struct perf_event *bp); extern int __register_perf_hw_breakpoint(struct perf_event *bp); @@ -115,6 +118,7 @@ static inline int __init init_hw_breakpoint(void) { return 0; } static inline struct perf_event * register_user_hw_breakpoint(struct perf_event_attr *attr, perf_overflow_handler_t triggered, + void *context, struct task_struct *tsk) { return NULL; } static inline int modify_user_hw_breakpoint(struct perf_event *bp, @@ -122,10 +126,12 @@ modify_user_hw_breakpoint(struct perf_event *bp, static inline struct perf_event * register_wide_hw_breakpoint_cpu(struct perf_event_attr *attr, perf_overflow_handler_t triggered, + void *context, int cpu) { return NULL; } static inline struct perf_event * __percpu * register_wide_hw_breakpoint(struct perf_event_attr *attr, - perf_overflow_handler_t triggered) { return NULL; } + perf_overflow_handler_t triggered, + void *context) { return NULL; } static inline int register_perf_hw_breakpoint(struct perf_event *bp) { return -ENOSYS; } static inline int diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index a5f54b973bdb..2a08cacb1628 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -839,6 +839,7 @@ struct perf_event { u64 id; perf_overflow_handler_t overflow_handler; + void *overflow_handler_context; #ifdef CONFIG_EVENT_TRACING struct ftrace_event_call *tp_event; @@ -960,7 +961,8 @@ extern struct perf_event * perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, struct task_struct *task, - perf_overflow_handler_t callback); + perf_overflow_handler_t callback, + void *context); extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running); -- cgit v1.2.3 From 26ca5c11fb45ae2b2ac7e3574b8db6b3a3c7d350 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Wed, 29 Jun 2011 18:42:37 +0300 Subject: perf: export perf_event_refresh() to modules KVM needs one-shot samples, since a PMC programmed to -X will fire after X events and then again after 2^40 events (i.e. variable period). Signed-off-by: Avi Kivity Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1309362157-6596-4-git-send-email-avi@redhat.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 2a08cacb1628..3f2711ccf910 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -955,6 +955,7 @@ extern void perf_pmu_disable(struct pmu *pmu); extern void perf_pmu_enable(struct pmu *pmu); extern int perf_event_task_disable(void); extern int perf_event_task_enable(void); +extern int perf_event_refresh(struct perf_event *event, int refresh); extern void perf_event_update_userpage(struct perf_event *event); extern int perf_event_release_kernel(struct perf_event *event); extern struct perf_event * @@ -1149,6 +1150,10 @@ static inline void perf_event_delayed_put(struct task_struct *task) { } static inline void perf_event_print_debug(void) { } static inline int perf_event_task_disable(void) { return -EINVAL; } static inline int perf_event_task_enable(void) { return -EINVAL; } +static inline int perf_event_refresh(struct perf_event *event, int refresh) +{ + return -EINVAL; +} static inline void perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { } -- cgit v1.2.3 From 85ef06d1d252f6a2e73b678591ab71caad4667bb Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 1 Jul 2011 16:17:47 +0200 Subject: block: flush MEDIA_CHANGE from drivers on close(2) Currently, only open(2) is defined as the 'clearing' point. It has two roles - first, it's an acknowledgement from userland indicating that the event has been received and kernel can clear pending states and proceed to generate more events. Secondly, it's passed on to device drivers as a hint indicating that a synchronization point has been reached and it might want to take a deeper look at the device. The latter currently is only used by sr which uses two different mechanisms - GET_EVENT_MEDIA_STATUS_NOTIFICATION and TEST_UNIT_READY to discover events, where the former is lighter weight and safe to be used repeatedly but may not provide full coverage. Among other things, GET_EVENT can't detect media removal while TUR can. This patch makes close(2) - blkdev_put() - indicate clearing hint for MEDIA_CHANGE to drivers. disk_check_events() is renamed to disk_flush_events() and updated to take @mask for events to flush which is or'd to ev->clearing and will be passed to the driver on the next ->check_events() invocation. This change makes sr generate MEDIA_CHANGE when media is ejected from userland - e.g. with eject(1). Note: Given the current usage, it seems @clearing hint is needlessly complex. disk_clear_events() can simply clear all events and the hint can be boolean @flush. Signed-off-by: Tejun Heo Cc: Kay Sievers Signed-off-by: Jens Axboe --- include/linux/genhd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 300d7582006e..02fa4697a0e5 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -420,7 +420,7 @@ static inline int get_disk_ro(struct gendisk *disk) extern void disk_block_events(struct gendisk *disk); extern void disk_unblock_events(struct gendisk *disk); -extern void disk_check_events(struct gendisk *disk); +extern void disk_flush_events(struct gendisk *disk, unsigned int mask); extern unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask); /* drivers/char/random.c */ -- cgit v1.2.3 From 390192b300570b2bc721d77067ca133f58015ae8 Mon Sep 17 00:00:00 2001 From: Johannes Stezenbach Date: Fri, 1 Jul 2011 22:32:26 +0200 Subject: compat_ioctl: fix warning caused by qemu On Linux x86_64 host with 32bit userspace, running qemu or even just "qemu-img create -f qcow2 some.img 1G" causes a kernel warning: ioctl32(qemu-img:5296): Unknown cmd fd(3) cmd(00005326){t:'S';sz:0} arg(7fffffff) on some.img ioctl32(qemu-img:5296): Unknown cmd fd(3) cmd(801c0204){t:02;sz:28} arg(fff77350) on some.img ioctl 00005326 is CDROM_DRIVE_STATUS, ioctl 801c0204 is FDGETPRM. The warning appears because the Linux compat-ioctl handler for these ioctls only applies to block devices, while qemu also uses the ioctls on plain files. Signed-off-by: Johannes Stezenbach Acked-by: Arnd Bergmann Signed-off-by: Jens Axboe --- include/linux/fd.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fd.h b/include/linux/fd.h index f5d194af07a8..c6a68d011608 100644 --- a/include/linux/fd.h +++ b/include/linux/fd.h @@ -3,6 +3,7 @@ #include #include +#include /* New file layout: Now the ioctl definitions immediately follow the * definitions of the structures that they use */ @@ -377,4 +378,21 @@ struct floppy_raw_cmd { #define FDEJECT _IO(2, 0x5a) /* eject the disk */ +#ifdef CONFIG_COMPAT +struct compat_floppy_struct { + compat_uint_t size; + compat_uint_t sect; + compat_uint_t head; + compat_uint_t track; + compat_uint_t stretch; + unsigned char gap; + unsigned char rate; + unsigned char spec1; + unsigned char fmt_gap; + const compat_caddr_t name; +}; + +#define FDGETPRM32 _IOR(2, 0x04, struct compat_floppy_struct) +#endif + #endif -- cgit v1.2.3 From 35a0e0bf6f6b2b900d461e9f35c286953b2b1afc Mon Sep 17 00:00:00 2001 From: Tatyana Brokhman Date: Wed, 29 Jun 2011 16:41:49 +0300 Subject: usb: gadget: add max_speed to usb_composite_driver This field is used by the Gadget drivers to specify the maximum speed they support, meaning: the maximum speed they can provide descriptors for. The driver speed will be set in consideration of this value. [ balbi@ti.com : dropped the ifdeffery ] Signed-off-by: Tatyana Brokhman Signed-off-by: Felipe Balbi Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/composite.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 99830d63d8f1..a3e72dfa6996 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -240,6 +240,7 @@ int usb_add_config(struct usb_composite_dev *, * identifiers. * @strings: tables of strings, keyed by identifiers assigned during bind() * and language IDs provided in control requests + * @max_speed: Highest speed the driver supports. * @needs_serial: set to 1 if the gadget needs userspace to provide * a serial number. If one is not provided, warning will be printed. * @unbind: Reverses bind; called as a side effect of unregistering @@ -267,6 +268,7 @@ struct usb_composite_driver { const char *iManufacturer; const struct usb_device_descriptor *dev; struct usb_gadget_strings **strings; + enum usb_device_speed max_speed; unsigned needs_serial:1; int (*unbind)(struct usb_composite_dev *); -- cgit v1.2.3 From bdb64d727216b49a18c2b8337658adc6b2db82ea Mon Sep 17 00:00:00 2001 From: Tatyana Brokhman Date: Wed, 29 Jun 2011 16:41:50 +0300 Subject: usb: gadget: add SuperSpeed support to the Gadget Framework SuperSpeed USB has defined a new descriptor, called the Binary Device Object Store (BOS) Descriptor. It has also changed a bit the definition of SET_FEATURE and GET_STATUS requests to add USB3-specific details. This patch implements both changes to the Composite Gadget Framework. [ balbi@ti.com : slight changes to commit log fixed a compile error on ARM ] Signed-off-by: Tatyana Brokhman Signed-off-by: Felipe Balbi Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/composite.h | 14 ++++++++++++++ include/linux/usb/gadget.h | 31 +++++++++++++++++++++++++++++++ 2 files changed, 45 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index a3e72dfa6996..a316fba73518 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -59,6 +59,10 @@ struct usb_configuration; * @hs_descriptors: Table of high speed descriptors, using interface and * string identifiers assigned during @bind(). If this pointer is null, * the function will not be available at high speed. + * @ss_descriptors: Table of super speed descriptors, using interface and + * string identifiers assigned during @bind(). If this + * pointer is null after initiation, the function will not + * be available at super speed. * @config: assigned when @usb_add_function() is called; this is the * configuration with which this function is associated. * @bind: Before the gadget can register, all of its functions bind() to the @@ -77,6 +81,10 @@ struct usb_configuration; * @setup: Used for interface-specific control requests. * @suspend: Notifies functions when the host stops sending USB traffic. * @resume: Notifies functions when the host restarts USB traffic. + * @get_status: Returns function status as a reply to + * GetStatus() request when the recepient is Interface. + * @func_suspend: callback to be called when + * SetFeature(FUNCTION_SUSPEND) is reseived * * A single USB function uses one or more interfaces, and should in most * cases support operation at both full and high speeds. Each function is @@ -106,6 +114,7 @@ struct usb_function { struct usb_gadget_strings **strings; struct usb_descriptor_header **descriptors; struct usb_descriptor_header **hs_descriptors; + struct usb_descriptor_header **ss_descriptors; struct usb_configuration *config; @@ -132,6 +141,10 @@ struct usb_function { void (*suspend)(struct usb_function *); void (*resume)(struct usb_function *); + /* USB 3.0 additions */ + int (*get_status)(struct usb_function *); + int (*func_suspend)(struct usb_function *, + u8 suspend_opt); /* private: */ /* internals */ struct list_head list; @@ -219,6 +232,7 @@ struct usb_configuration { struct list_head list; struct list_head functions; u8 next_interface_id; + unsigned superspeed:1; unsigned highspeed:1; unsigned fullspeed:1; struct usb_function *interface[MAX_CONFIG_INTERFACES]; diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 625971292c20..e22ce7e5a444 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -136,6 +136,8 @@ struct usb_ep_ops { * the endpoint descriptor used to configure the endpoint. * @max_streams: The maximum number of streams supported * by this EP (0 - 16, actual number is 2^n) + * @mult: multiplier, 'mult' value for SS Isoc EPs + * @maxburst: the maximum number of bursts supported by this EP (for usb3) * @driver_data:for use by the gadget driver. * @address: used to identify the endpoint when finding descriptor that * matches connection speed @@ -156,6 +158,8 @@ struct usb_ep { struct list_head ep_list; unsigned maxpacket:16; unsigned max_streams:16; + unsigned mult:2; + unsigned maxburst:4; u8 address; const struct usb_endpoint_descriptor *desc; const struct usb_ss_ep_comp_descriptor *comp_desc; @@ -426,6 +430,14 @@ static inline void usb_ep_fifo_flush(struct usb_ep *ep) /*-------------------------------------------------------------------------*/ +struct usb_dcd_config_params { + __u8 bU1devExitLat; /* U1 Device exit Latency */ +#define USB_DEFULT_U1_DEV_EXIT_LAT 0x01 /* Less then 1 microsec */ + __le16 bU2DevExitLat; /* U2 Device exit Latency */ +#define USB_DEFULT_U2_DEV_EXIT_LAT 0x1F4 /* Less then 500 microsec */ +}; + + struct usb_gadget; struct usb_gadget_driver; @@ -441,6 +453,7 @@ struct usb_gadget_ops { int (*pullup) (struct usb_gadget *, int is_on); int (*ioctl)(struct usb_gadget *, unsigned code, unsigned long param); + void (*get_config_params)(struct usb_dcd_config_params *); int (*start)(struct usb_gadget_driver *, int (*bind)(struct usb_gadget *)); int (*stop)(struct usb_gadget_driver *); @@ -534,6 +547,24 @@ static inline int gadget_is_dualspeed(struct usb_gadget *g) #endif } +/** + * gadget_is_superspeed() - return true if the hardware handles + * supperspeed + * @g: controller that might support supper speed + */ +static inline int gadget_is_superspeed(struct usb_gadget *g) +{ +#ifdef CONFIG_USB_GADGET_SUPERSPEED + /* + * runtime test would check "g->is_superspeed" ... that might be + * useful to work around hardware bugs, but is mostly pointless + */ + return 1; +#else + return 0; +#endif +} + /** * gadget_is_otg - return true iff the hardware is OTG-ready * @g: controller that might have a Mini-AB connector -- cgit v1.2.3 From e9c23a255a33cf423336b7cba39b2b6dcc83a6bc Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Wed, 15 Jun 2011 21:10:37 +0300 Subject: usb: gadget: add missing #include's When #include'd alone, causes a lot of compilation errors and warnings -- all because it relies on the including code to bring in the necessary #include's instead of doing this itself. Signed-off-by: Sergei Shtylyov Signed-off-by: Felipe Balbi Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/gadget.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index e22ce7e5a444..afb67d997f0c 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -15,7 +15,12 @@ #ifndef __LINUX_USB_GADGET_H #define __LINUX_USB_GADGET_H +#include +#include +#include +#include #include +#include #include struct usb_ep; -- cgit v1.2.3 From 352c2dc8b07491bbab77ddf86c20c16a97326ee7 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 23 Jun 2011 14:26:15 +0200 Subject: usb: gadget: udc-core: add "new-style" registration interface udc_start() should only trigger the internal state machine and make minimal house keeping. Before that call udc-core calls the bind() callback and after the callback the pullup(). udc_stop() is simillar, udc-core calls pullup(), unbind() and finally udc_stop(). Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Felipe Balbi Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/gadget.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index afb67d997f0c..087f4b931833 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -459,6 +459,12 @@ struct usb_gadget_ops { int (*ioctl)(struct usb_gadget *, unsigned code, unsigned long param); void (*get_config_params)(struct usb_dcd_config_params *); + int (*udc_start)(struct usb_gadget *, + struct usb_gadget_driver *); + int (*udc_stop)(struct usb_gadget *, + struct usb_gadget_driver *); + + /* Those two are deprecated */ int (*start)(struct usb_gadget_driver *, int (*bind)(struct usb_gadget *)); int (*stop)(struct usb_gadget_driver *); -- cgit v1.2.3 From bcd5abe28f40cc6a935d3339cde27976f6be3f1a Mon Sep 17 00:00:00 2001 From: Russ Gorby Date: Thu, 16 Jun 2011 14:20:12 -0700 Subject: tty: n_gsm: Add raw-ip support This patch adds the ability to open a network data connection over a mux virtual tty channel. This is for modems that support data connections with raw IP frames instead of PPP. On high speed data connections this eliminates a significant amount of PPP overhead. To use this interface, the application must first tell the modem to open a network connection on a virtual tty. Once that has been accomplished, the app will issue an IOCTL on that virtual tty to create the network interface. The IOCTL will return the index of the interface created. The two IOCTL commands are: ioctl( fd, GSMIOC_ENABLE_NET ); ioctl( fd, GSMIOC_DISABLE_NET ); Signed-off-by: Russ Gorby Acked-by: Alan Cox Signed-off-by: Greg Kroah-Hartman --- include/linux/gsmmux.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gsmmux.h b/include/linux/gsmmux.h index 378de4195caf..c25e9477f7c3 100644 --- a/include/linux/gsmmux.h +++ b/include/linux/gsmmux.h @@ -21,5 +21,16 @@ struct gsm_config #define GSMIOC_GETCONF _IOR('G', 0, struct gsm_config) #define GSMIOC_SETCONF _IOW('G', 1, struct gsm_config) +struct gsm_netconfig { + unsigned int adaption; /* Adaption to use in network mode */ + unsigned short protocol;/* Protocol to use - only ETH_P_IP supported */ + unsigned short unused2; + char if_name[IFNAMSIZ]; /* interface name format string */ + __u8 unused[28]; /* For future use */ +}; + +#define GSMIOC_ENABLE_NET _IOW('G', 2, struct gsm_netconfig) +#define GSMIOC_DISABLE_NET _IO('G', 3) + #endif -- cgit v1.2.3 From 8168e9c2de7383c497aff9cd906dd475f9b42b2c Mon Sep 17 00:00:00 2001 From: J Freyensee Date: Fri, 17 Jun 2011 15:09:53 -0700 Subject: PTI feature to allow user to name and mark masterchannel request. This feature addition provides a new parameter in pti_request_masterchannel() to allow the user to provide their own name to mark the request when the trace is viewed in a PTI SW trace viewer (like MPTA). If a name is not provided and NULL is provided, the 'current' process name is used. API function header documentation documents this. Signed-off-by: Jeremy Rocher Signed-off-by: J Freyensee Signed-off-by: Greg Kroah-Hartman --- include/linux/pti.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pti.h b/include/linux/pti.h index 81af667bb2d5..b3ea01a3197e 100644 --- a/include/linux/pti.h +++ b/include/linux/pti.h @@ -36,7 +36,8 @@ struct pti_masterchannel { /* the following functions are defined in misc/pti.c */ void pti_writedata(struct pti_masterchannel *mc, u8 *buf, int count); -struct pti_masterchannel *pti_request_masterchannel(u8 type); +struct pti_masterchannel *pti_request_masterchannel(u8 type, + const char *thread_name); void pti_release_masterchannel(struct pti_masterchannel *mc); #endif /*PTI_H_*/ -- cgit v1.2.3 From 50d5c41cd151b21ac1dfc98f048210456ccacc20 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 1 Jun 2011 12:25:45 -0500 Subject: slub: Do not use frozen page flag but a bit in the page counters Do not use a page flag for the frozen bit. It needs to be part of the state that is handled with cmpxchg_double(). So use a bit in the counter struct in the page struct for that purpose. Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/mm_types.h | 5 +++-- include/linux/page-flags.h | 5 ----- 2 files changed, 3 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 027935c86c68..e5fb2a70518b 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -41,8 +41,9 @@ struct page { * & limit reverse map searches. */ struct { /* SLUB */ - u16 inuse; - u16 objects; + unsigned inuse:16; + unsigned objects:15; + unsigned frozen:1; }; }; union { diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 6081493db68f..20791f18f5cf 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -124,9 +124,6 @@ enum pageflags { /* SLOB */ PG_slob_free = PG_private, - - /* SLUB */ - PG_slub_frozen = PG_active, }; #ifndef __GENERATING_BOUNDS_H @@ -212,8 +209,6 @@ PAGEFLAG(SwapBacked, swapbacked) __CLEARPAGEFLAG(SwapBacked, swapbacked) __PAGEFLAG(SlobFree, slob_free) -__PAGEFLAG(SlubFrozen, slub_frozen) - /* * Private page markings that may be used by the filesystem that owns the page * for its own purposes. -- cgit v1.2.3 From fc9bb8c768abe7ae10861c3510e01a95f98d5933 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 1 Jun 2011 12:25:48 -0500 Subject: mm: Rearrange struct page We need to be able to use cmpxchg_double on the freelist and object count field in struct page. Rearrange the fields in struct page according to doubleword entities so that the freelist pointer comes before the counters. Do the rearranging with a future in mind where we use more doubleword atomics to avoid locking of updates to flags/mapping or lru pointers. Create another union to allow access to counters in struct page as a single unsigned long value. The doublewords must be properly aligned for cmpxchg_double to work. Sadly this increases the size of page struct by one word on some architectures. But as a resultpage structs are now cacheline aligned on x86_64. Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/mm_types.h | 87 ++++++++++++++++++++++++++++++++---------------- 1 file changed, 59 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index e5fb2a70518b..3d76a433d52f 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -30,24 +30,60 @@ struct address_space; * moment. Note that we have no way to track which tasks are using * a page, though if it is a pagecache page, rmap structures can tell us * who is mapping it. + * + * The objects in struct page are organized in double word blocks in + * order to allows us to use atomic double word operations on portions + * of struct page. That is currently only used by slub but the arrangement + * allows the use of atomic double word operations on the flags/mapping + * and lru list pointers also. */ struct page { + /* First double word block */ unsigned long flags; /* Atomic flags, some possibly * updated asynchronously */ - atomic_t _count; /* Usage count, see below. */ + struct address_space *mapping; /* If low bit clear, points to + * inode address_space, or NULL. + * If page mapped as anonymous + * memory, low bit is set, and + * it points to anon_vma object: + * see PAGE_MAPPING_ANON below. + */ + /* Second double word */ union { - atomic_t _mapcount; /* Count of ptes mapped in mms, - * to show when page is mapped - * & limit reverse map searches. + struct { + pgoff_t index; /* Our offset within mapping. */ + atomic_t _mapcount; /* Count of ptes mapped in mms, + * to show when page is mapped + * & limit reverse map searches. + */ + atomic_t _count; /* Usage count, see below. */ + }; + + struct { /* SLUB cmpxchg_double area */ + void *freelist; + union { + unsigned long counters; + struct { + unsigned inuse:16; + unsigned objects:15; + unsigned frozen:1; + /* + * Kernel may make use of this field even when slub + * uses the rest of the double word! */ - struct { /* SLUB */ - unsigned inuse:16; - unsigned objects:15; - unsigned frozen:1; + atomic_t _count; + }; + }; }; }; + + /* Third double word block */ + struct list_head lru; /* Pageout list, eg. active_list + * protected by zone->lru_lock ! + */ + + /* Remainder is not double word aligned */ union { - struct { unsigned long private; /* Mapping-private opaque data: * usually used for buffer_heads * if PagePrivate set; used for @@ -55,27 +91,13 @@ struct page { * indicates order in the buddy * system if PG_buddy is set. */ - struct address_space *mapping; /* If low bit clear, points to - * inode address_space, or NULL. - * If page mapped as anonymous - * memory, low bit is set, and - * it points to anon_vma object: - * see PAGE_MAPPING_ANON below. - */ - }; #if USE_SPLIT_PTLOCKS - spinlock_t ptl; + spinlock_t ptl; #endif - struct kmem_cache *slab; /* SLUB: Pointer to slab */ - struct page *first_page; /* Compound tail pages */ + struct kmem_cache *slab; /* SLUB: Pointer to slab */ + struct page *first_page; /* Compound tail pages */ }; - union { - pgoff_t index; /* Our offset within mapping. */ - void *freelist; /* SLUB: freelist req. slab lock */ - }; - struct list_head lru; /* Pageout list, eg. active_list - * protected by zone->lru_lock ! - */ + /* * On machines where all RAM is mapped into kernel address space, * we can simply calculate the virtual address. On machines with @@ -101,7 +123,16 @@ struct page { */ void *shadow; #endif -}; +} +/* + * If another subsystem starts using the double word pairing for atomic + * operations on struct page then it must change the #if to ensure + * proper alignment of the page struct. + */ +#if defined(CONFIG_SLUB) && defined(CONFIG_CMPXCHG_LOCAL) + __attribute__((__aligned__(2*sizeof(unsigned long)))) +#endif +; typedef unsigned long __nocast vm_flags_t; -- cgit v1.2.3 From b789ef518b2a7231b0668c813f677cee528a9d3f Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 1 Jun 2011 12:25:49 -0500 Subject: slub: Add cmpxchg_double_slab() Add a function that operates on the second doubleword in the page struct and manipulates the object counters, the freelist and the frozen attribute. Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slub_def.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index c8668d161dd8..b42715294147 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -33,6 +33,7 @@ enum stat_item { DEACTIVATE_REMOTE_FREES,/* Slab contained remotely freed objects */ ORDER_FALLBACK, /* Number of times fallback was necessary */ CMPXCHG_DOUBLE_CPU_FAIL,/* Failure of this_cpu_cmpxchg_double */ + CMPXCHG_DOUBLE_FAIL, /* Number of times that cmpxchg double did not match */ NR_SLUB_STAT_ITEMS }; struct kmem_cache_cpu { -- cgit v1.2.3 From e36a2652d7d1ad97f7636a39bdd8654d296cc36b Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 1 Jun 2011 12:25:57 -0500 Subject: slub: Add statistics for the case that the current slab does not match the node Slub reloads the per cpu slab if the page does not satisfy the NUMA condition. Track those reloads since doing so has a performance impact. Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slub_def.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index b42715294147..5b228b785377 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -24,6 +24,7 @@ enum stat_item { ALLOC_FROM_PARTIAL, /* Cpu slab acquired from partial list */ ALLOC_SLAB, /* Cpu slab acquired from page allocator */ ALLOC_REFILL, /* Refill cpu slab from slab freelist */ + ALLOC_NODE_MISMATCH, /* Switching cpu slab */ FREE_SLAB, /* Slab freed to the page allocator */ CPUSLAB_FLUSH, /* Abandoning of the cpu slab */ DEACTIVATE_FULL, /* Cpu slab was full when deactivated */ -- cgit v1.2.3 From 03e404af26dc2ea0d278d7a342de0aab394793ce Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 1 Jun 2011 12:25:58 -0500 Subject: slub: fast release on full slab Make deactivation occur implicitly while checking out the current freelist. This avoids one cmpxchg operation on a slab that is now fully in use. Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slub_def.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 5b228b785377..71441f89729b 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -32,6 +32,7 @@ enum stat_item { DEACTIVATE_TO_HEAD, /* Cpu slab was moved to the head of partials */ DEACTIVATE_TO_TAIL, /* Cpu slab was moved to the tail of partials */ DEACTIVATE_REMOTE_FREES,/* Slab contained remotely freed objects */ + DEACTIVATE_BYPASS, /* Implicit deactivation */ ORDER_FALLBACK, /* Number of times fallback was necessary */ CMPXCHG_DOUBLE_CPU_FAIL,/* Failure of this_cpu_cmpxchg_double */ CMPXCHG_DOUBLE_FAIL, /* Number of times that cmpxchg double did not match */ -- cgit v1.2.3 From 564b905ab10d17fb42f86aa8b7b9b796276d1336 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 23 Jun 2011 01:52:55 +0200 Subject: PM / Domains: Rename struct dev_power_domain to struct dev_pm_domain The naming convention used by commit 7538e3db6e015e890825fbd9f86599b (PM: Add support for device power domains), which introduced the struct dev_power_domain type for representing device power domains, evidently confuses some developers who tend to think that objects of this type must correspond to "power domains" as defined by hardware, which is not the case. Namely, at the kernel level, a struct dev_power_domain object can represent arbitrary set of devices that are mutually dependent power management-wise and need not belong to one hardware power domain. To avoid that confusion, rename struct dev_power_domain to struct dev_pm_domain and rename the related pointers in struct device and struct pm_clk_notifier_block from pwr_domain to pm_domain. Signed-off-by: Rafael J. Wysocki Acked-by: Kevin Hilman --- include/linux/device.h | 4 ++-- include/linux/pm.h | 2 +- include/linux/pm_runtime.h | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index e4f62d8896b7..160d4ddb2499 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -516,7 +516,7 @@ struct device_dma_parameters { * minimizes board-specific #ifdefs in drivers. * @power: For device power management. * See Documentation/power/devices.txt for details. - * @pwr_domain: Provide callbacks that are executed during system suspend, + * @pm_domain: Provide callbacks that are executed during system suspend, * hibernation, system resume and during runtime PM transitions * along with subsystem-level and driver-level callbacks. * @numa_node: NUMA node this device is close to. @@ -567,7 +567,7 @@ struct device { void *platform_data; /* Platform specific data, device core doesn't touch it */ struct dev_pm_info power; - struct dev_power_domain *pwr_domain; + struct dev_pm_domain *pm_domain; #ifdef CONFIG_NUMA int numa_node; /* NUMA node this device is close to */ diff --git a/include/linux/pm.h b/include/linux/pm.h index 411e4f4be52b..e3963208aa93 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -472,7 +472,7 @@ extern void update_pm_runtime_accounting(struct device *dev); * hibernation, system resume and during runtime PM transitions along with * subsystem-level and driver-level callbacks. */ -struct dev_power_domain { +struct dev_pm_domain { struct dev_pm_ops ops; }; diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 878cf84baeb1..ef91904c7110 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -247,7 +247,7 @@ static inline void pm_runtime_dont_use_autosuspend(struct device *dev) struct pm_clk_notifier_block { struct notifier_block nb; - struct dev_power_domain *pwr_domain; + struct dev_pm_domain *pm_domain; char *con_ids[]; }; -- cgit v1.2.3 From dc6e4e56e6ef473a696a1ab24f80b79b9aceb92d Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 23 Jun 2011 01:53:04 +0200 Subject: PM: subsys_data in struct dev_pm_info need not depend on RM_RUNTIME The subsys_data field of struct dev_pm_info, introduced by commit 1d2b71f61b6a10216274e27b717becf9ae101fc7 (PM / Runtime: Add subsystem data field to struct dev_pm_info), is going to be used even if CONFIG_PM_RUNTIME is not set, so move it from under the #ifdef. Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index e3963208aa93..7e8f0763d1ec 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -461,8 +461,8 @@ struct dev_pm_info { unsigned long active_jiffies; unsigned long suspended_jiffies; unsigned long accounting_timestamp; - void *subsys_data; /* Owned by the subsystem. */ #endif + void *subsys_data; /* Owned by the subsystem. */ }; extern void update_pm_runtime_accounting(struct device *dev); -- cgit v1.2.3 From f721889ff65afa6243c463832c74dee3bed418d5 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 1 Jul 2011 22:12:45 +0200 Subject: PM / Domains: Support for generic I/O PM domains (v8) Introduce common headers, helper functions and callbacks allowing platforms to use simple generic power domains for runtime power management. Introduce struct generic_pm_domain to be used for representing power domains that each contain a number of devices and may be parent domains or subdomains with respect to other power domains. Among other things, this structure includes callbacks to be provided by platforms for performing specific tasks related to power management (i.e. ->stop_device() may disable a device's clocks, while ->start_device() may enable them, ->power_off() is supposed to remove power from the entire power domain and ->power_on() is supposed to restore it). Introduce functions that can be used as power domain runtime PM callbacks, pm_genpd_runtime_suspend() and pm_genpd_runtime_resume(), as well as helper functions for the initialization of a power domain represented by a struct generic_power_domain object, adding a device to or removing a device from it and adding or removing subdomains. Introduce configuration option CONFIG_PM_GENERIC_DOMAINS to be selected by the platforms that want to use the new code. Signed-off-by: Rafael J. Wysocki Acked-by: Greg Kroah-Hartman Reviewed-by: Kevin Hilman --- include/linux/pm_domain.h | 78 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 78 insertions(+) create mode 100644 include/linux/pm_domain.h (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h new file mode 100644 index 000000000000..b1a22c65380b --- /dev/null +++ b/include/linux/pm_domain.h @@ -0,0 +1,78 @@ +/* + * pm_domain.h - Definitions and headers related to device power domains. + * + * Copyright (C) 2011 Rafael J. Wysocki , Renesas Electronics Corp. + * + * This file is released under the GPLv2. + */ + +#ifndef _LINUX_PM_DOMAIN_H +#define _LINUX_PM_DOMAIN_H + +#include + +struct dev_power_governor { + bool (*power_down_ok)(struct dev_pm_domain *domain); +}; + +struct generic_pm_domain { + struct dev_pm_domain domain; /* PM domain operations */ + struct list_head sd_node; /* Node in the parent's subdomain list */ + struct generic_pm_domain *parent; /* Parent PM domain */ + struct list_head sd_list; /* List of dubdomains */ + struct list_head dev_list; /* List of devices */ + struct mutex lock; + struct dev_power_governor *gov; + struct work_struct power_off_work; + unsigned int in_progress; /* Number of devices being suspended now */ + unsigned int sd_count; /* Number of subdomains with power "on" */ + bool power_is_off; /* Whether or not power has been removed */ + int (*power_off)(struct generic_pm_domain *domain); + int (*power_on)(struct generic_pm_domain *domain); + int (*start_device)(struct device *dev); + int (*stop_device)(struct device *dev); +}; + +struct dev_list_entry { + struct list_head node; + struct device *dev; + bool need_restore; +}; + +#ifdef CONFIG_PM_GENERIC_DOMAINS +extern int pm_genpd_add_device(struct generic_pm_domain *genpd, + struct device *dev); +extern int pm_genpd_remove_device(struct generic_pm_domain *genpd, + struct device *dev); +extern int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, + struct generic_pm_domain *new_subdomain); +extern int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, + struct generic_pm_domain *target); +extern void pm_genpd_init(struct generic_pm_domain *genpd, + struct dev_power_governor *gov, bool is_off); +#else +static inline int pm_genpd_add_device(struct generic_pm_domain *genpd, + struct device *dev) +{ + return -ENOSYS; +} +static inline int pm_genpd_remove_device(struct generic_pm_domain *genpd, + struct device *dev) +{ + return -ENOSYS; +} +static inline int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, + struct generic_pm_domain *new_sd) +{ + return -ENOSYS; +} +static inline int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, + struct generic_pm_domain *target) +{ + return -ENOSYS; +} +static inline void pm_genpd_init(struct generic_pm_domain *genpd, + struct dev_power_governor *gov, bool is_off) {} +#endif + +#endif /* _LINUX_PM_DOMAIN_H */ -- cgit v1.2.3 From e5291928839877f8e73c2643ee1d3fe0bcdcaf5c Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 1 Jul 2011 22:12:59 +0200 Subject: PM: Introduce generic "noirq" callback routines for subsystems (v2) Introduce generic "noirq" power management callback routines for subsystems in addition to the "regular" generic PM callback routines. The new routines will be used, among other things, for implementing system-wide PM transitions support for generic PM domains. Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index 7e8f0763d1ec..f7c84c9abd30 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -553,11 +553,17 @@ extern void __suspend_report_result(const char *function, void *fn, int ret); extern int device_pm_wait_for_dev(struct device *sub, struct device *dev); extern int pm_generic_prepare(struct device *dev); +extern int pm_generic_suspend_noirq(struct device *dev); extern int pm_generic_suspend(struct device *dev); +extern int pm_generic_resume_noirq(struct device *dev); extern int pm_generic_resume(struct device *dev); +extern int pm_generic_freeze_noirq(struct device *dev); extern int pm_generic_freeze(struct device *dev); +extern int pm_generic_thaw_noirq(struct device *dev); extern int pm_generic_thaw(struct device *dev); +extern int pm_generic_restore_noirq(struct device *dev); extern int pm_generic_restore(struct device *dev); +extern int pm_generic_poweroff_noirq(struct device *dev); extern int pm_generic_poweroff(struct device *dev); extern void pm_generic_complete(struct device *dev); -- cgit v1.2.3 From 596ba34bcd2978ee9823cc1d84df230576f8ffb9 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 1 Jul 2011 22:13:19 +0200 Subject: PM / Domains: System-wide transitions support for generic domains (v5) Make generic PM domains support system-wide power transitions (system suspend and hibernation). Add suspend, resume, freeze, thaw, poweroff and restore callbacks to be associated with struct generic_pm_domain objects and make pm_genpd_init() use them as appropriate. The new callbacks do nothing for devices belonging to power domains that were powered down at run time (before the transition). For the other devices the action carried out depends on the type of the transition. During system suspend the power domain .suspend() callback executes pm_generic_suspend() for the device, while the PM domain .suspend_noirq() callback runs pm_generic_suspend_noirq() for it, stops it and eventually removes power from the PM domain it belongs to (after all devices in the domain have been stopped and its subdomains have been powered off). During system resume the PM domain .resume_noirq() callback restores power to the PM domain (when executed for it first time), starts the device and executes pm_generic_resume_noirq() for it, while the .resume() callback executes pm_generic_resume() for the device. Finally, the .complete() callback executes pm_runtime_idle() for the device which should put it back into the suspended state if its runtime PM usage count is equal to zero at that time. The actions carried out during hibernation and resume from it are analogous to the ones described above. Signed-off-by: Rafael J. Wysocki Reviewed-by: Kevin Hilman --- include/linux/pm_domain.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index b1a22c65380b..7961b0dac437 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -11,6 +11,9 @@ #include +#define GPD_IN_SUSPEND 1 +#define GPD_POWER_OFF 2 + struct dev_power_governor { bool (*power_down_ok)(struct dev_pm_domain *domain); }; @@ -27,12 +30,21 @@ struct generic_pm_domain { unsigned int in_progress; /* Number of devices being suspended now */ unsigned int sd_count; /* Number of subdomains with power "on" */ bool power_is_off; /* Whether or not power has been removed */ + unsigned int device_count; /* Number of devices */ + unsigned int suspended_count; /* System suspend device counter */ + unsigned int prepared_count; /* Suspend counter of prepared devices */ + bool suspend_power_off; /* Power status before system suspend */ int (*power_off)(struct generic_pm_domain *domain); int (*power_on)(struct generic_pm_domain *domain); int (*start_device)(struct device *dev); int (*stop_device)(struct device *dev); }; +static inline struct generic_pm_domain *pd_to_genpd(struct dev_pm_domain *pd) +{ + return container_of(pd, struct generic_pm_domain, domain); +} + struct dev_list_entry { struct list_head node; struct device *dev; -- cgit v1.2.3 From d4f2d87a8b46c14c4307c690c92bd08229f66ecf Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 1 Jul 2011 22:13:29 +0200 Subject: PM / Domains: Wakeup devices support for system sleep transitions There is the problem how to handle devices set up to wake up the system from sleep states during system-wide power transitions. In some cases, those devices can be turned off entirely, because the wakeup signals will be generated on their behalf anyway. In some other cases, they will generate wakeup signals if their clocks are stopped, but only if power is not removed from them. Finally, in some cases, they can only generate wakeup signals if power is not removed from them and their clocks are enabled. To allow platform-specific code to decide whether or not to put wakeup devices (and their PM domains) into low-power state during system-wide transitions, such as system suspend, introduce a new generic PM domain callback, .active_wakeup(), that will be used during the "noirq" phase of system suspend and hibernation (after image creation) to decide what to do with wakeup devices. Specifically, if this callback is present and returns "true", the generic PM domain code will not execute .stop_device() for the given wakeup device and its PM domain won't be powered off. Signed-off-by: Rafael J. Wysocki Acked-by: Kevin Hilman --- include/linux/pm_domain.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 7961b0dac437..98491ee35102 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -38,6 +38,7 @@ struct generic_pm_domain { int (*power_on)(struct generic_pm_domain *domain); int (*start_device)(struct device *dev); int (*stop_device)(struct device *dev); + bool (*active_wakeup)(struct device *dev); }; static inline struct generic_pm_domain *pd_to_genpd(struct dev_pm_domain *pd) -- cgit v1.2.3 From b7b95920aa2e89e655afe9913ee0e55855ceda90 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 1 Jul 2011 22:13:37 +0200 Subject: PM: Allow the clocks management code to be used during system suspend The common clocks management code in drivers/base/power/clock_ops.c is going to be used during system-wide power transitions as well as for runtime PM, so it shouldn't depend on CONFIG_PM_RUNTIME. However, the suspend/resume functions provided by it for CONFIG_PM_RUNTIME unset, to be used during system-wide power transitions, should not behave in the same way as their counterparts defined for CONFIG_PM_RUNTIME set, because in that case the clocks are managed differently at run time. The names of the functions still contain the word "runtime" after this change, but that is going to be modified by a separate patch later. Signed-off-by: Rafael J. Wysocki Reviewed-by: Kevin Hilman --- include/linux/pm_runtime.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index ef91904c7110..1bd5063a2cc8 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -251,7 +251,7 @@ struct pm_clk_notifier_block { char *con_ids[]; }; -#ifdef CONFIG_PM_RUNTIME_CLK +#ifdef CONFIG_PM_CLK extern int pm_runtime_clk_init(struct device *dev); extern void pm_runtime_clk_destroy(struct device *dev); extern int pm_runtime_clk_add(struct device *dev, const char *con_id); -- cgit v1.2.3 From 3d5c30367cbc0c55c93bb158e824e00badc7ddc4 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 1 Jul 2011 22:13:44 +0200 Subject: PM: Rename clock management functions The common PM clock management functions may be used for system suspend/resume as well as for runtime PM, so rename them accordingly. Modify kerneldoc comments describing these functions and kernel messages printed by them, so that they refer to power management in general rather that to runtime PM. Signed-off-by: Rafael J. Wysocki Reviewed-by: Kevin Hilman --- include/linux/pm_runtime.h | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 1bd5063a2cc8..dfb8539ed686 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -252,36 +252,36 @@ struct pm_clk_notifier_block { }; #ifdef CONFIG_PM_CLK -extern int pm_runtime_clk_init(struct device *dev); -extern void pm_runtime_clk_destroy(struct device *dev); -extern int pm_runtime_clk_add(struct device *dev, const char *con_id); -extern void pm_runtime_clk_remove(struct device *dev, const char *con_id); -extern int pm_runtime_clk_suspend(struct device *dev); -extern int pm_runtime_clk_resume(struct device *dev); +extern int pm_clk_init(struct device *dev); +extern void pm_clk_destroy(struct device *dev); +extern int pm_clk_add(struct device *dev, const char *con_id); +extern void pm_clk_remove(struct device *dev, const char *con_id); +extern int pm_clk_suspend(struct device *dev); +extern int pm_clk_resume(struct device *dev); #else -static inline int pm_runtime_clk_init(struct device *dev) +static inline int pm_clk_init(struct device *dev) { return -EINVAL; } -static inline void pm_runtime_clk_destroy(struct device *dev) +static inline void pm_clk_destroy(struct device *dev) { } -static inline int pm_runtime_clk_add(struct device *dev, const char *con_id) +static inline int pm_clk_add(struct device *dev, const char *con_id) { return -EINVAL; } -static inline void pm_runtime_clk_remove(struct device *dev, const char *con_id) +static inline void pm_clk_remove(struct device *dev, const char *con_id) { } -#define pm_runtime_clock_suspend NULL -#define pm_runtime_clock_resume NULL +#define pm_clk_suspend NULL +#define pm_clk_resume NULL #endif #ifdef CONFIG_HAVE_CLK -extern void pm_runtime_clk_add_notifier(struct bus_type *bus, +extern void pm_clk_add_notifier(struct bus_type *bus, struct pm_clk_notifier_block *clknb); #else -static inline void pm_runtime_clk_add_notifier(struct bus_type *bus, +static inline void pm_clk_add_notifier(struct bus_type *bus, struct pm_clk_notifier_block *clknb) { } -- cgit v1.2.3 From 234b921dbcf144826e2e2b3663cd8090892ee2b2 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Thu, 30 Jun 2011 15:08:57 +0000 Subject: netpoll: Remove unused EXPORT_SYMBOLs of netpoll_poll and netpoll_poll_dev Unused symbols waste space. Commit 0e34e93177fb "(netpoll: add generic support for bridge and bonding devices)" added the symbol more than a year ago with the promise of "future use". Because it is so far unused, remove it for now. It can be easily readded if or when it actually needs to be used. cc: WANG Cong Signed-off-by: Joe Perches Signed-off-by: David S. Miller --- include/linux/netpoll.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 79358bb712c6..5dfa091c3347 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -40,8 +40,6 @@ struct netpoll_info { struct netpoll *netpoll; }; -void netpoll_poll_dev(struct net_device *dev); -void netpoll_poll(struct netpoll *np); void netpoll_send_udp(struct netpoll *np, const char *msg, int len); void netpoll_print_options(struct netpoll *np); int netpoll_parse_options(struct netpoll *np, char *opt); -- cgit v1.2.3 From f09bc831b7693f93ecb95dea7180d55b45b88e76 Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Mon, 4 Jul 2011 09:01:18 +0800 Subject: dt: add 'const' for of_property_read_string parameter **out_string The existing dt codes usually call of_get_property to get a string property and save it as a 'const char *'. The patch adds'const' for of_property_read_string parameter **out_string to make the converting of existing code a little easier. Signed-off-by: Shawn Guo Signed-off-by: Grant Likely --- include/linux/of.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 4fc4c1b8d5d5..b23852002b30 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -198,7 +198,7 @@ extern struct property *of_find_property(const struct device_node *np, extern int of_property_read_u32(struct device_node *np, char *propname, u32 *out_value); extern int of_property_read_string(struct device_node *np, char *propname, - char **out_string); + const char **out_string); extern int of_device_is_compatible(const struct device_node *device, const char *); extern int of_device_is_available(const struct device_node *device); -- cgit v1.2.3 From 57fe7251f5bfc4332f24479376de48a1e8ca6211 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Tue, 31 May 2011 12:02:49 +0300 Subject: MFD: twl4030-codec -> twl4030-audio: Rename the driver Rename the driver, and header file from twl4030-codec to twl4030-audio. To avoid breakage change depending drivers at the same time. Signed-off-by: Peter Ujfalusi CC: Misael Lopez Cruz Acked-by: Samuel Ortiz --- include/linux/mfd/twl4030-audio.h | 272 ++++++++++++++++++++++++++++++++++++++ include/linux/mfd/twl4030-codec.h | 272 -------------------------------------- 2 files changed, 272 insertions(+), 272 deletions(-) create mode 100644 include/linux/mfd/twl4030-audio.h delete mode 100644 include/linux/mfd/twl4030-codec.h (limited to 'include/linux') diff --git a/include/linux/mfd/twl4030-audio.h b/include/linux/mfd/twl4030-audio.h new file mode 100644 index 000000000000..3d22b72df076 --- /dev/null +++ b/include/linux/mfd/twl4030-audio.h @@ -0,0 +1,272 @@ +/* + * MFD driver for twl4030 audio submodule + * + * Author: Peter Ujfalusi + * + * Copyright: (C) 2009 Nokia Corporation + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA + * 02110-1301 USA + * + */ + +#ifndef __TWL4030_CODEC_H__ +#define __TWL4030_CODEC_H__ + +/* Codec registers */ +#define TWL4030_REG_CODEC_MODE 0x01 +#define TWL4030_REG_OPTION 0x02 +#define TWL4030_REG_UNKNOWN 0x03 +#define TWL4030_REG_MICBIAS_CTL 0x04 +#define TWL4030_REG_ANAMICL 0x05 +#define TWL4030_REG_ANAMICR 0x06 +#define TWL4030_REG_AVADC_CTL 0x07 +#define TWL4030_REG_ADCMICSEL 0x08 +#define TWL4030_REG_DIGMIXING 0x09 +#define TWL4030_REG_ATXL1PGA 0x0A +#define TWL4030_REG_ATXR1PGA 0x0B +#define TWL4030_REG_AVTXL2PGA 0x0C +#define TWL4030_REG_AVTXR2PGA 0x0D +#define TWL4030_REG_AUDIO_IF 0x0E +#define TWL4030_REG_VOICE_IF 0x0F +#define TWL4030_REG_ARXR1PGA 0x10 +#define TWL4030_REG_ARXL1PGA 0x11 +#define TWL4030_REG_ARXR2PGA 0x12 +#define TWL4030_REG_ARXL2PGA 0x13 +#define TWL4030_REG_VRXPGA 0x14 +#define TWL4030_REG_VSTPGA 0x15 +#define TWL4030_REG_VRX2ARXPGA 0x16 +#define TWL4030_REG_AVDAC_CTL 0x17 +#define TWL4030_REG_ARX2VTXPGA 0x18 +#define TWL4030_REG_ARXL1_APGA_CTL 0x19 +#define TWL4030_REG_ARXR1_APGA_CTL 0x1A +#define TWL4030_REG_ARXL2_APGA_CTL 0x1B +#define TWL4030_REG_ARXR2_APGA_CTL 0x1C +#define TWL4030_REG_ATX2ARXPGA 0x1D +#define TWL4030_REG_BT_IF 0x1E +#define TWL4030_REG_BTPGA 0x1F +#define TWL4030_REG_BTSTPGA 0x20 +#define TWL4030_REG_EAR_CTL 0x21 +#define TWL4030_REG_HS_SEL 0x22 +#define TWL4030_REG_HS_GAIN_SET 0x23 +#define TWL4030_REG_HS_POPN_SET 0x24 +#define TWL4030_REG_PREDL_CTL 0x25 +#define TWL4030_REG_PREDR_CTL 0x26 +#define TWL4030_REG_PRECKL_CTL 0x27 +#define TWL4030_REG_PRECKR_CTL 0x28 +#define TWL4030_REG_HFL_CTL 0x29 +#define TWL4030_REG_HFR_CTL 0x2A +#define TWL4030_REG_ALC_CTL 0x2B +#define TWL4030_REG_ALC_SET1 0x2C +#define TWL4030_REG_ALC_SET2 0x2D +#define TWL4030_REG_BOOST_CTL 0x2E +#define TWL4030_REG_SOFTVOL_CTL 0x2F +#define TWL4030_REG_DTMF_FREQSEL 0x30 +#define TWL4030_REG_DTMF_TONEXT1H 0x31 +#define TWL4030_REG_DTMF_TONEXT1L 0x32 +#define TWL4030_REG_DTMF_TONEXT2H 0x33 +#define TWL4030_REG_DTMF_TONEXT2L 0x34 +#define TWL4030_REG_DTMF_TONOFF 0x35 +#define TWL4030_REG_DTMF_WANONOFF 0x36 +#define TWL4030_REG_I2S_RX_SCRAMBLE_H 0x37 +#define TWL4030_REG_I2S_RX_SCRAMBLE_M 0x38 +#define TWL4030_REG_I2S_RX_SCRAMBLE_L 0x39 +#define TWL4030_REG_APLL_CTL 0x3A +#define TWL4030_REG_DTMF_CTL 0x3B +#define TWL4030_REG_DTMF_PGA_CTL2 0x3C +#define TWL4030_REG_DTMF_PGA_CTL1 0x3D +#define TWL4030_REG_MISC_SET_1 0x3E +#define TWL4030_REG_PCMBTMUX 0x3F +#define TWL4030_REG_RX_PATH_SEL 0x43 +#define TWL4030_REG_VDL_APGA_CTL 0x44 +#define TWL4030_REG_VIBRA_CTL 0x45 +#define TWL4030_REG_VIBRA_SET 0x46 +#define TWL4030_REG_VIBRA_PWM_SET 0x47 +#define TWL4030_REG_ANAMIC_GAIN 0x48 +#define TWL4030_REG_MISC_SET_2 0x49 + +/* Bitfield Definitions */ + +/* TWL4030_CODEC_MODE (0x01) Fields */ +#define TWL4030_APLL_RATE 0xF0 +#define TWL4030_APLL_RATE_8000 0x00 +#define TWL4030_APLL_RATE_11025 0x10 +#define TWL4030_APLL_RATE_12000 0x20 +#define TWL4030_APLL_RATE_16000 0x40 +#define TWL4030_APLL_RATE_22050 0x50 +#define TWL4030_APLL_RATE_24000 0x60 +#define TWL4030_APLL_RATE_32000 0x80 +#define TWL4030_APLL_RATE_44100 0x90 +#define TWL4030_APLL_RATE_48000 0xA0 +#define TWL4030_APLL_RATE_96000 0xE0 +#define TWL4030_SEL_16K 0x08 +#define TWL4030_CODECPDZ 0x02 +#define TWL4030_OPT_MODE 0x01 +#define TWL4030_OPTION_1 (1 << 0) +#define TWL4030_OPTION_2 (0 << 0) + +/* TWL4030_OPTION (0x02) Fields */ +#define TWL4030_ATXL1_EN (1 << 0) +#define TWL4030_ATXR1_EN (1 << 1) +#define TWL4030_ATXL2_VTXL_EN (1 << 2) +#define TWL4030_ATXR2_VTXR_EN (1 << 3) +#define TWL4030_ARXL1_VRX_EN (1 << 4) +#define TWL4030_ARXR1_EN (1 << 5) +#define TWL4030_ARXL2_EN (1 << 6) +#define TWL4030_ARXR2_EN (1 << 7) + +/* TWL4030_REG_MICBIAS_CTL (0x04) Fields */ +#define TWL4030_MICBIAS2_CTL 0x40 +#define TWL4030_MICBIAS1_CTL 0x20 +#define TWL4030_HSMICBIAS_EN 0x04 +#define TWL4030_MICBIAS2_EN 0x02 +#define TWL4030_MICBIAS1_EN 0x01 + +/* ANAMICL (0x05) Fields */ +#define TWL4030_CNCL_OFFSET_START 0x80 +#define TWL4030_OFFSET_CNCL_SEL 0x60 +#define TWL4030_OFFSET_CNCL_SEL_ARX1 0x00 +#define TWL4030_OFFSET_CNCL_SEL_ARX2 0x20 +#define TWL4030_OFFSET_CNCL_SEL_VRX 0x40 +#define TWL4030_OFFSET_CNCL_SEL_ALL 0x60 +#define TWL4030_MICAMPL_EN 0x10 +#define TWL4030_CKMIC_EN 0x08 +#define TWL4030_AUXL_EN 0x04 +#define TWL4030_HSMIC_EN 0x02 +#define TWL4030_MAINMIC_EN 0x01 + +/* ANAMICR (0x06) Fields */ +#define TWL4030_MICAMPR_EN 0x10 +#define TWL4030_AUXR_EN 0x04 +#define TWL4030_SUBMIC_EN 0x01 + +/* AVADC_CTL (0x07) Fields */ +#define TWL4030_ADCL_EN 0x08 +#define TWL4030_AVADC_CLK_PRIORITY 0x04 +#define TWL4030_ADCR_EN 0x02 + +/* TWL4030_REG_ADCMICSEL (0x08) Fields */ +#define TWL4030_DIGMIC1_EN 0x08 +#define TWL4030_TX2IN_SEL 0x04 +#define TWL4030_DIGMIC0_EN 0x02 +#define TWL4030_TX1IN_SEL 0x01 + +/* AUDIO_IF (0x0E) Fields */ +#define TWL4030_AIF_SLAVE_EN 0x80 +#define TWL4030_DATA_WIDTH 0x60 +#define TWL4030_DATA_WIDTH_16S_16W 0x00 +#define TWL4030_DATA_WIDTH_32S_16W 0x40 +#define TWL4030_DATA_WIDTH_32S_24W 0x60 +#define TWL4030_AIF_FORMAT 0x18 +#define TWL4030_AIF_FORMAT_CODEC 0x00 +#define TWL4030_AIF_FORMAT_LEFT 0x08 +#define TWL4030_AIF_FORMAT_RIGHT 0x10 +#define TWL4030_AIF_FORMAT_TDM 0x18 +#define TWL4030_AIF_TRI_EN 0x04 +#define TWL4030_CLK256FS_EN 0x02 +#define TWL4030_AIF_EN 0x01 + +/* VOICE_IF (0x0F) Fields */ +#define TWL4030_VIF_SLAVE_EN 0x80 +#define TWL4030_VIF_DIN_EN 0x40 +#define TWL4030_VIF_DOUT_EN 0x20 +#define TWL4030_VIF_SWAP 0x10 +#define TWL4030_VIF_FORMAT 0x08 +#define TWL4030_VIF_TRI_EN 0x04 +#define TWL4030_VIF_SUB_EN 0x02 +#define TWL4030_VIF_EN 0x01 + +/* EAR_CTL (0x21) */ +#define TWL4030_EAR_GAIN 0x30 + +/* HS_GAIN_SET (0x23) Fields */ +#define TWL4030_HSR_GAIN 0x0C +#define TWL4030_HSR_GAIN_PWR_DOWN 0x00 +#define TWL4030_HSR_GAIN_PLUS_6DB 0x04 +#define TWL4030_HSR_GAIN_0DB 0x08 +#define TWL4030_HSR_GAIN_MINUS_6DB 0x0C +#define TWL4030_HSL_GAIN 0x03 +#define TWL4030_HSL_GAIN_PWR_DOWN 0x00 +#define TWL4030_HSL_GAIN_PLUS_6DB 0x01 +#define TWL4030_HSL_GAIN_0DB 0x02 +#define TWL4030_HSL_GAIN_MINUS_6DB 0x03 + +/* HS_POPN_SET (0x24) Fields */ +#define TWL4030_VMID_EN 0x40 +#define TWL4030_EXTMUTE 0x20 +#define TWL4030_RAMP_DELAY 0x1C +#define TWL4030_RAMP_DELAY_20MS 0x00 +#define TWL4030_RAMP_DELAY_40MS 0x04 +#define TWL4030_RAMP_DELAY_81MS 0x08 +#define TWL4030_RAMP_DELAY_161MS 0x0C +#define TWL4030_RAMP_DELAY_323MS 0x10 +#define TWL4030_RAMP_DELAY_645MS 0x14 +#define TWL4030_RAMP_DELAY_1291MS 0x18 +#define TWL4030_RAMP_DELAY_2581MS 0x1C +#define TWL4030_RAMP_EN 0x02 + +/* PREDL_CTL (0x25) */ +#define TWL4030_PREDL_GAIN 0x30 + +/* PREDR_CTL (0x26) */ +#define TWL4030_PREDR_GAIN 0x30 + +/* PRECKL_CTL (0x27) */ +#define TWL4030_PRECKL_GAIN 0x30 + +/* PRECKR_CTL (0x28) */ +#define TWL4030_PRECKR_GAIN 0x30 + +/* HFL_CTL (0x29, 0x2A) Fields */ +#define TWL4030_HF_CTL_HB_EN 0x04 +#define TWL4030_HF_CTL_LOOP_EN 0x08 +#define TWL4030_HF_CTL_RAMP_EN 0x10 +#define TWL4030_HF_CTL_REF_EN 0x20 + +/* APLL_CTL (0x3A) Fields */ +#define TWL4030_APLL_EN 0x10 +#define TWL4030_APLL_INFREQ 0x0F +#define TWL4030_APLL_INFREQ_19200KHZ 0x05 +#define TWL4030_APLL_INFREQ_26000KHZ 0x06 +#define TWL4030_APLL_INFREQ_38400KHZ 0x0F + +/* REG_MISC_SET_1 (0x3E) Fields */ +#define TWL4030_CLK64_EN 0x80 +#define TWL4030_SCRAMBLE_EN 0x40 +#define TWL4030_FMLOOP_EN 0x20 +#define TWL4030_SMOOTH_ANAVOL_EN 0x02 +#define TWL4030_DIGMIC_LR_SWAP_EN 0x01 + +/* VIBRA_CTL (0x45) */ +#define TWL4030_VIBRA_EN 0x01 +#define TWL4030_VIBRA_DIR 0x02 +#define TWL4030_VIBRA_AUDIO_SEL_L1 (0x00 << 2) +#define TWL4030_VIBRA_AUDIO_SEL_R1 (0x01 << 2) +#define TWL4030_VIBRA_AUDIO_SEL_L2 (0x02 << 2) +#define TWL4030_VIBRA_AUDIO_SEL_R2 (0x03 << 2) +#define TWL4030_VIBRA_SEL 0x10 +#define TWL4030_VIBRA_DIR_SEL 0x20 + +/* TWL4030 codec resource IDs */ +enum twl4030_audio_res { + TWL4030_AUDIO_RES_POWER = 0, + TWL4030_AUDIO_RES_APLL, + TWL4030_AUDIO_RES_MAX, +}; + +int twl4030_audio_disable_resource(enum twl4030_audio_res id); +int twl4030_audio_enable_resource(enum twl4030_audio_res id); +unsigned int twl4030_audio_get_mclk(void); + +#endif /* End of __TWL4030_CODEC_H__ */ diff --git a/include/linux/mfd/twl4030-codec.h b/include/linux/mfd/twl4030-codec.h deleted file mode 100644 index 5cc16bbd1da1..000000000000 --- a/include/linux/mfd/twl4030-codec.h +++ /dev/null @@ -1,272 +0,0 @@ -/* - * MFD driver for twl4030 codec submodule - * - * Author: Peter Ujfalusi - * - * Copyright: (C) 2009 Nokia Corporation - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA - * 02110-1301 USA - * - */ - -#ifndef __TWL4030_CODEC_H__ -#define __TWL4030_CODEC_H__ - -/* Codec registers */ -#define TWL4030_REG_CODEC_MODE 0x01 -#define TWL4030_REG_OPTION 0x02 -#define TWL4030_REG_UNKNOWN 0x03 -#define TWL4030_REG_MICBIAS_CTL 0x04 -#define TWL4030_REG_ANAMICL 0x05 -#define TWL4030_REG_ANAMICR 0x06 -#define TWL4030_REG_AVADC_CTL 0x07 -#define TWL4030_REG_ADCMICSEL 0x08 -#define TWL4030_REG_DIGMIXING 0x09 -#define TWL4030_REG_ATXL1PGA 0x0A -#define TWL4030_REG_ATXR1PGA 0x0B -#define TWL4030_REG_AVTXL2PGA 0x0C -#define TWL4030_REG_AVTXR2PGA 0x0D -#define TWL4030_REG_AUDIO_IF 0x0E -#define TWL4030_REG_VOICE_IF 0x0F -#define TWL4030_REG_ARXR1PGA 0x10 -#define TWL4030_REG_ARXL1PGA 0x11 -#define TWL4030_REG_ARXR2PGA 0x12 -#define TWL4030_REG_ARXL2PGA 0x13 -#define TWL4030_REG_VRXPGA 0x14 -#define TWL4030_REG_VSTPGA 0x15 -#define TWL4030_REG_VRX2ARXPGA 0x16 -#define TWL4030_REG_AVDAC_CTL 0x17 -#define TWL4030_REG_ARX2VTXPGA 0x18 -#define TWL4030_REG_ARXL1_APGA_CTL 0x19 -#define TWL4030_REG_ARXR1_APGA_CTL 0x1A -#define TWL4030_REG_ARXL2_APGA_CTL 0x1B -#define TWL4030_REG_ARXR2_APGA_CTL 0x1C -#define TWL4030_REG_ATX2ARXPGA 0x1D -#define TWL4030_REG_BT_IF 0x1E -#define TWL4030_REG_BTPGA 0x1F -#define TWL4030_REG_BTSTPGA 0x20 -#define TWL4030_REG_EAR_CTL 0x21 -#define TWL4030_REG_HS_SEL 0x22 -#define TWL4030_REG_HS_GAIN_SET 0x23 -#define TWL4030_REG_HS_POPN_SET 0x24 -#define TWL4030_REG_PREDL_CTL 0x25 -#define TWL4030_REG_PREDR_CTL 0x26 -#define TWL4030_REG_PRECKL_CTL 0x27 -#define TWL4030_REG_PRECKR_CTL 0x28 -#define TWL4030_REG_HFL_CTL 0x29 -#define TWL4030_REG_HFR_CTL 0x2A -#define TWL4030_REG_ALC_CTL 0x2B -#define TWL4030_REG_ALC_SET1 0x2C -#define TWL4030_REG_ALC_SET2 0x2D -#define TWL4030_REG_BOOST_CTL 0x2E -#define TWL4030_REG_SOFTVOL_CTL 0x2F -#define TWL4030_REG_DTMF_FREQSEL 0x30 -#define TWL4030_REG_DTMF_TONEXT1H 0x31 -#define TWL4030_REG_DTMF_TONEXT1L 0x32 -#define TWL4030_REG_DTMF_TONEXT2H 0x33 -#define TWL4030_REG_DTMF_TONEXT2L 0x34 -#define TWL4030_REG_DTMF_TONOFF 0x35 -#define TWL4030_REG_DTMF_WANONOFF 0x36 -#define TWL4030_REG_I2S_RX_SCRAMBLE_H 0x37 -#define TWL4030_REG_I2S_RX_SCRAMBLE_M 0x38 -#define TWL4030_REG_I2S_RX_SCRAMBLE_L 0x39 -#define TWL4030_REG_APLL_CTL 0x3A -#define TWL4030_REG_DTMF_CTL 0x3B -#define TWL4030_REG_DTMF_PGA_CTL2 0x3C -#define TWL4030_REG_DTMF_PGA_CTL1 0x3D -#define TWL4030_REG_MISC_SET_1 0x3E -#define TWL4030_REG_PCMBTMUX 0x3F -#define TWL4030_REG_RX_PATH_SEL 0x43 -#define TWL4030_REG_VDL_APGA_CTL 0x44 -#define TWL4030_REG_VIBRA_CTL 0x45 -#define TWL4030_REG_VIBRA_SET 0x46 -#define TWL4030_REG_VIBRA_PWM_SET 0x47 -#define TWL4030_REG_ANAMIC_GAIN 0x48 -#define TWL4030_REG_MISC_SET_2 0x49 - -/* Bitfield Definitions */ - -/* TWL4030_CODEC_MODE (0x01) Fields */ -#define TWL4030_APLL_RATE 0xF0 -#define TWL4030_APLL_RATE_8000 0x00 -#define TWL4030_APLL_RATE_11025 0x10 -#define TWL4030_APLL_RATE_12000 0x20 -#define TWL4030_APLL_RATE_16000 0x40 -#define TWL4030_APLL_RATE_22050 0x50 -#define TWL4030_APLL_RATE_24000 0x60 -#define TWL4030_APLL_RATE_32000 0x80 -#define TWL4030_APLL_RATE_44100 0x90 -#define TWL4030_APLL_RATE_48000 0xA0 -#define TWL4030_APLL_RATE_96000 0xE0 -#define TWL4030_SEL_16K 0x08 -#define TWL4030_CODECPDZ 0x02 -#define TWL4030_OPT_MODE 0x01 -#define TWL4030_OPTION_1 (1 << 0) -#define TWL4030_OPTION_2 (0 << 0) - -/* TWL4030_OPTION (0x02) Fields */ -#define TWL4030_ATXL1_EN (1 << 0) -#define TWL4030_ATXR1_EN (1 << 1) -#define TWL4030_ATXL2_VTXL_EN (1 << 2) -#define TWL4030_ATXR2_VTXR_EN (1 << 3) -#define TWL4030_ARXL1_VRX_EN (1 << 4) -#define TWL4030_ARXR1_EN (1 << 5) -#define TWL4030_ARXL2_EN (1 << 6) -#define TWL4030_ARXR2_EN (1 << 7) - -/* TWL4030_REG_MICBIAS_CTL (0x04) Fields */ -#define TWL4030_MICBIAS2_CTL 0x40 -#define TWL4030_MICBIAS1_CTL 0x20 -#define TWL4030_HSMICBIAS_EN 0x04 -#define TWL4030_MICBIAS2_EN 0x02 -#define TWL4030_MICBIAS1_EN 0x01 - -/* ANAMICL (0x05) Fields */ -#define TWL4030_CNCL_OFFSET_START 0x80 -#define TWL4030_OFFSET_CNCL_SEL 0x60 -#define TWL4030_OFFSET_CNCL_SEL_ARX1 0x00 -#define TWL4030_OFFSET_CNCL_SEL_ARX2 0x20 -#define TWL4030_OFFSET_CNCL_SEL_VRX 0x40 -#define TWL4030_OFFSET_CNCL_SEL_ALL 0x60 -#define TWL4030_MICAMPL_EN 0x10 -#define TWL4030_CKMIC_EN 0x08 -#define TWL4030_AUXL_EN 0x04 -#define TWL4030_HSMIC_EN 0x02 -#define TWL4030_MAINMIC_EN 0x01 - -/* ANAMICR (0x06) Fields */ -#define TWL4030_MICAMPR_EN 0x10 -#define TWL4030_AUXR_EN 0x04 -#define TWL4030_SUBMIC_EN 0x01 - -/* AVADC_CTL (0x07) Fields */ -#define TWL4030_ADCL_EN 0x08 -#define TWL4030_AVADC_CLK_PRIORITY 0x04 -#define TWL4030_ADCR_EN 0x02 - -/* TWL4030_REG_ADCMICSEL (0x08) Fields */ -#define TWL4030_DIGMIC1_EN 0x08 -#define TWL4030_TX2IN_SEL 0x04 -#define TWL4030_DIGMIC0_EN 0x02 -#define TWL4030_TX1IN_SEL 0x01 - -/* AUDIO_IF (0x0E) Fields */ -#define TWL4030_AIF_SLAVE_EN 0x80 -#define TWL4030_DATA_WIDTH 0x60 -#define TWL4030_DATA_WIDTH_16S_16W 0x00 -#define TWL4030_DATA_WIDTH_32S_16W 0x40 -#define TWL4030_DATA_WIDTH_32S_24W 0x60 -#define TWL4030_AIF_FORMAT 0x18 -#define TWL4030_AIF_FORMAT_CODEC 0x00 -#define TWL4030_AIF_FORMAT_LEFT 0x08 -#define TWL4030_AIF_FORMAT_RIGHT 0x10 -#define TWL4030_AIF_FORMAT_TDM 0x18 -#define TWL4030_AIF_TRI_EN 0x04 -#define TWL4030_CLK256FS_EN 0x02 -#define TWL4030_AIF_EN 0x01 - -/* VOICE_IF (0x0F) Fields */ -#define TWL4030_VIF_SLAVE_EN 0x80 -#define TWL4030_VIF_DIN_EN 0x40 -#define TWL4030_VIF_DOUT_EN 0x20 -#define TWL4030_VIF_SWAP 0x10 -#define TWL4030_VIF_FORMAT 0x08 -#define TWL4030_VIF_TRI_EN 0x04 -#define TWL4030_VIF_SUB_EN 0x02 -#define TWL4030_VIF_EN 0x01 - -/* EAR_CTL (0x21) */ -#define TWL4030_EAR_GAIN 0x30 - -/* HS_GAIN_SET (0x23) Fields */ -#define TWL4030_HSR_GAIN 0x0C -#define TWL4030_HSR_GAIN_PWR_DOWN 0x00 -#define TWL4030_HSR_GAIN_PLUS_6DB 0x04 -#define TWL4030_HSR_GAIN_0DB 0x08 -#define TWL4030_HSR_GAIN_MINUS_6DB 0x0C -#define TWL4030_HSL_GAIN 0x03 -#define TWL4030_HSL_GAIN_PWR_DOWN 0x00 -#define TWL4030_HSL_GAIN_PLUS_6DB 0x01 -#define TWL4030_HSL_GAIN_0DB 0x02 -#define TWL4030_HSL_GAIN_MINUS_6DB 0x03 - -/* HS_POPN_SET (0x24) Fields */ -#define TWL4030_VMID_EN 0x40 -#define TWL4030_EXTMUTE 0x20 -#define TWL4030_RAMP_DELAY 0x1C -#define TWL4030_RAMP_DELAY_20MS 0x00 -#define TWL4030_RAMP_DELAY_40MS 0x04 -#define TWL4030_RAMP_DELAY_81MS 0x08 -#define TWL4030_RAMP_DELAY_161MS 0x0C -#define TWL4030_RAMP_DELAY_323MS 0x10 -#define TWL4030_RAMP_DELAY_645MS 0x14 -#define TWL4030_RAMP_DELAY_1291MS 0x18 -#define TWL4030_RAMP_DELAY_2581MS 0x1C -#define TWL4030_RAMP_EN 0x02 - -/* PREDL_CTL (0x25) */ -#define TWL4030_PREDL_GAIN 0x30 - -/* PREDR_CTL (0x26) */ -#define TWL4030_PREDR_GAIN 0x30 - -/* PRECKL_CTL (0x27) */ -#define TWL4030_PRECKL_GAIN 0x30 - -/* PRECKR_CTL (0x28) */ -#define TWL4030_PRECKR_GAIN 0x30 - -/* HFL_CTL (0x29, 0x2A) Fields */ -#define TWL4030_HF_CTL_HB_EN 0x04 -#define TWL4030_HF_CTL_LOOP_EN 0x08 -#define TWL4030_HF_CTL_RAMP_EN 0x10 -#define TWL4030_HF_CTL_REF_EN 0x20 - -/* APLL_CTL (0x3A) Fields */ -#define TWL4030_APLL_EN 0x10 -#define TWL4030_APLL_INFREQ 0x0F -#define TWL4030_APLL_INFREQ_19200KHZ 0x05 -#define TWL4030_APLL_INFREQ_26000KHZ 0x06 -#define TWL4030_APLL_INFREQ_38400KHZ 0x0F - -/* REG_MISC_SET_1 (0x3E) Fields */ -#define TWL4030_CLK64_EN 0x80 -#define TWL4030_SCRAMBLE_EN 0x40 -#define TWL4030_FMLOOP_EN 0x20 -#define TWL4030_SMOOTH_ANAVOL_EN 0x02 -#define TWL4030_DIGMIC_LR_SWAP_EN 0x01 - -/* VIBRA_CTL (0x45) */ -#define TWL4030_VIBRA_EN 0x01 -#define TWL4030_VIBRA_DIR 0x02 -#define TWL4030_VIBRA_AUDIO_SEL_L1 (0x00 << 2) -#define TWL4030_VIBRA_AUDIO_SEL_R1 (0x01 << 2) -#define TWL4030_VIBRA_AUDIO_SEL_L2 (0x02 << 2) -#define TWL4030_VIBRA_AUDIO_SEL_R2 (0x03 << 2) -#define TWL4030_VIBRA_SEL 0x10 -#define TWL4030_VIBRA_DIR_SEL 0x20 - -/* TWL4030 codec resource IDs */ -enum twl4030_codec_res { - TWL4030_CODEC_RES_POWER = 0, - TWL4030_CODEC_RES_APLL, - TWL4030_CODEC_RES_MAX, -}; - -int twl4030_codec_disable_resource(enum twl4030_codec_res id); -int twl4030_codec_enable_resource(enum twl4030_codec_res id); -unsigned int twl4030_codec_get_mclk(void); - -#endif /* End of __TWL4030_CODEC_H__ */ -- cgit v1.2.3 From 4ae6df5e1018796ce260be59b2c603bd0f9faa94 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Tue, 31 May 2011 15:21:13 +0300 Subject: MFD: twl4030-audio: Rename platform data Allign the platform data names for twl4030 audio submodule: twl4030_audio_data: for the core MFD driver twl4030_codec_data: for ASoC codec driver twl4030_vibra_data: for the input/ForceFeedback driver To avoid breakage, change all depending drivers, files to use the new types. Signed-off-by: Peter Ujfalusi Acked-by: Samuel Ortiz --- include/linux/i2c/twl.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c/twl.h b/include/linux/i2c/twl.h index ba4f88624fcd..e0aba2b92fa1 100644 --- a/include/linux/i2c/twl.h +++ b/include/linux/i2c/twl.h @@ -657,7 +657,7 @@ struct twl4030_power_data { extern void twl4030_power_init(struct twl4030_power_data *triton2_scripts); extern int twl4030_remove_script(u8 flags); -struct twl4030_codec_audio_data { +struct twl4030_codec_data { unsigned int digimic_delay; /* in ms */ unsigned int ramp_delay_value; unsigned int offset_cncl_path; @@ -667,14 +667,14 @@ struct twl4030_codec_audio_data { void (*set_hs_extmute)(int mute); }; -struct twl4030_codec_vibra_data { +struct twl4030_vibra_data { unsigned int coexist; }; -struct twl4030_codec_data { +struct twl4030_audio_data { unsigned int audio_mclk; - struct twl4030_codec_audio_data *audio; - struct twl4030_codec_vibra_data *vibra; + struct twl4030_codec_data *codec; + struct twl4030_vibra_data *vibra; /* twl6040 */ int audpwron_gpio; /* audio power-on gpio */ @@ -690,7 +690,7 @@ struct twl4030_platform_data { struct twl4030_keypad_data *keypad; struct twl4030_usb_data *usb; struct twl4030_power_data *power; - struct twl4030_codec_data *codec; + struct twl4030_audio_data *audio; /* Common LDO regulators for TWL4030/TWL6030 */ struct regulator_init_data *vdac; -- cgit v1.2.3 From f19b2823f82499c60ec15d5fe8783193d77e3043 Mon Sep 17 00:00:00 2001 From: Misael Lopez Cruz Date: Wed, 27 Apr 2011 02:14:07 -0500 Subject: mfd: twl6040: Add initial support TWL6040 IC provides analog high-end audio codec functions for handset applications. It contains several audio analog inputs and outputs as well as vibrator support. It's connected to the host processor via PDM interface for audio data communication. The audio modules are controlled by internal registers that can be accessed by I2C and PDM interface. TWL6040 MFD will be registered as a child of TWL-CORE, and will have two children of its own: twl6040-codec and twl6040-vibra. This driver is based on TWL4030 and WM8350 MFD drivers. Signed-off-by: Misael Lopez Cruz Signed-off-by: Peter Ujfalusi Acked-by: Samuel Ortiz --- include/linux/i2c/twl.h | 1 + include/linux/mfd/twl6040.h | 255 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 256 insertions(+) create mode 100644 include/linux/mfd/twl6040.h (limited to 'include/linux') diff --git a/include/linux/i2c/twl.h b/include/linux/i2c/twl.h index e0aba2b92fa1..ea5baa269226 100644 --- a/include/linux/i2c/twl.h +++ b/include/linux/i2c/twl.h @@ -679,6 +679,7 @@ struct twl4030_audio_data { /* twl6040 */ int audpwron_gpio; /* audio power-on gpio */ int naudint_irq; /* audio interrupt */ + unsigned int irq_base; }; struct twl4030_platform_data { diff --git a/include/linux/mfd/twl6040.h b/include/linux/mfd/twl6040.h new file mode 100644 index 000000000000..c3c1de53dcfe --- /dev/null +++ b/include/linux/mfd/twl6040.h @@ -0,0 +1,255 @@ +/* + * MFD driver for twl6040 + * + * Authors: Jorge Eduardo Candelaria + * Misael Lopez Cruz + * + * Copyright: (C) 2011 Texas Instruments, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA + * 02110-1301 USA + * + */ + +#ifndef __TWL6040_CODEC_H__ +#define __TWL6040_CODEC_H__ + +#include +#include + +#define TWL6040_REG_ASICID 0x01 +#define TWL6040_REG_ASICREV 0x02 +#define TWL6040_REG_INTID 0x03 +#define TWL6040_REG_INTMR 0x04 +#define TWL6040_REG_NCPCTL 0x05 +#define TWL6040_REG_LDOCTL 0x06 +#define TWL6040_REG_HPPLLCTL 0x07 +#define TWL6040_REG_LPPLLCTL 0x08 +#define TWL6040_REG_LPPLLDIV 0x09 +#define TWL6040_REG_AMICBCTL 0x0A +#define TWL6040_REG_DMICBCTL 0x0B +#define TWL6040_REG_MICLCTL 0x0C +#define TWL6040_REG_MICRCTL 0x0D +#define TWL6040_REG_MICGAIN 0x0E +#define TWL6040_REG_LINEGAIN 0x0F +#define TWL6040_REG_HSLCTL 0x10 +#define TWL6040_REG_HSRCTL 0x11 +#define TWL6040_REG_HSGAIN 0x12 +#define TWL6040_REG_EARCTL 0x13 +#define TWL6040_REG_HFLCTL 0x14 +#define TWL6040_REG_HFLGAIN 0x15 +#define TWL6040_REG_HFRCTL 0x16 +#define TWL6040_REG_HFRGAIN 0x17 +#define TWL6040_REG_VIBCTLL 0x18 +#define TWL6040_REG_VIBDATL 0x19 +#define TWL6040_REG_VIBCTLR 0x1A +#define TWL6040_REG_VIBDATR 0x1B +#define TWL6040_REG_HKCTL1 0x1C +#define TWL6040_REG_HKCTL2 0x1D +#define TWL6040_REG_GPOCTL 0x1E +#define TWL6040_REG_ALB 0x1F +#define TWL6040_REG_DLB 0x20 +#define TWL6040_REG_TRIM1 0x28 +#define TWL6040_REG_TRIM2 0x29 +#define TWL6040_REG_TRIM3 0x2A +#define TWL6040_REG_HSOTRIM 0x2B +#define TWL6040_REG_HFOTRIM 0x2C +#define TWL6040_REG_ACCCTL 0x2D +#define TWL6040_REG_STATUS 0x2E + +#define TWL6040_CACHEREGNUM (TWL6040_REG_STATUS + 1) + +#define TWL6040_VIOREGNUM 18 +#define TWL6040_VDDREGNUM 21 + +/* INTID (0x03) fields */ + +#define TWL6040_THINT 0x01 +#define TWL6040_PLUGINT 0x02 +#define TWL6040_UNPLUGINT 0x04 +#define TWL6040_HOOKINT 0x08 +#define TWL6040_HFINT 0x10 +#define TWL6040_VIBINT 0x20 +#define TWL6040_READYINT 0x40 + +/* INTMR (0x04) fields */ + +#define TWL6040_THMSK 0x01 +#define TWL6040_PLUGMSK 0x02 +#define TWL6040_HOOKMSK 0x08 +#define TWL6040_HFMSK 0x10 +#define TWL6040_VIBMSK 0x20 +#define TWL6040_READYMSK 0x40 +#define TWL6040_ALLINT_MSK 0x7B + +/* NCPCTL (0x05) fields */ + +#define TWL6040_NCPENA 0x01 +#define TWL6040_NCPOPEN 0x40 + +/* LDOCTL (0x06) fields */ + +#define TWL6040_LSLDOENA 0x01 +#define TWL6040_HSLDOENA 0x04 +#define TWL6040_REFENA 0x40 +#define TWL6040_OSCENA 0x80 + +/* HPPLLCTL (0x07) fields */ + +#define TWL6040_HPLLENA 0x01 +#define TWL6040_HPLLRST 0x02 +#define TWL6040_HPLLBP 0x04 +#define TWL6040_HPLLSQRENA 0x08 +#define TWL6040_MCLK_12000KHZ (0 << 5) +#define TWL6040_MCLK_19200KHZ (1 << 5) +#define TWL6040_MCLK_26000KHZ (2 << 5) +#define TWL6040_MCLK_38400KHZ (3 << 5) +#define TWL6040_MCLK_MSK 0x60 + +/* LPPLLCTL (0x08) fields */ + +#define TWL6040_LPLLENA 0x01 +#define TWL6040_LPLLRST 0x02 +#define TWL6040_LPLLSEL 0x04 +#define TWL6040_LPLLFIN 0x08 +#define TWL6040_HPLLSEL 0x10 + +/* HSLCTL (0x10) fields */ + +#define TWL6040_HSDACMODEL 0x02 +#define TWL6040_HSDRVMODEL 0x08 + +/* HSRCTL (0x11) fields */ + +#define TWL6040_HSDACMODER 0x02 +#define TWL6040_HSDRVMODER 0x08 + +/* VIBCTLL (0x18) fields */ + +#define TWL6040_VIBENAL 0x01 +#define TWL6040_VIBCTRLL 0x04 +#define TWL6040_VIBCTRLLP 0x08 +#define TWL6040_VIBCTRLLN 0x10 + +/* VIBDATL (0x19) fields */ + +#define TWL6040_VIBDAT_MAX 0x64 + +/* VIBCTLR (0x1A) fields */ + +#define TWL6040_VIBENAR 0x01 +#define TWL6040_VIBCTRLR 0x04 +#define TWL6040_VIBCTRLRP 0x08 +#define TWL6040_VIBCTRLRN 0x10 + +/* GPOCTL (0x1E) fields */ + +#define TWL6040_GPO1 0x01 +#define TWL6040_GPO2 0x02 +#define TWL6040_GPO3 0x03 + +/* ACCCTL (0x2D) fields */ + +#define TWL6040_I2CSEL 0x01 +#define TWL6040_RESETSPLIT 0x04 +#define TWL6040_INTCLRMODE 0x08 + +#define TWL6040_SYSCLK_SEL_LPPLL 1 +#define TWL6040_SYSCLK_SEL_HPPLL 2 + +/* STATUS (0x2E) fields */ + +#define TWL6040_PLUGCOMP 0x02 +#define TWL6040_VIBLOCDET 0x10 +#define TWL6040_VIBROCDET 0x20 +#define TWL6040_TSHUTDET 0x40 + +#define TWL6040_CELLS 2 + +#define TWL6040_REV_ES1_0 0x00 +#define TWL6040_REV_ES1_1 0x01 +#define TWL6040_REV_ES1_2 0x02 + +#define TWL6040_IRQ_TH 0 +#define TWL6040_IRQ_PLUG 1 +#define TWL6040_IRQ_HOOK 2 +#define TWL6040_IRQ_HF 3 +#define TWL6040_IRQ_VIB 4 +#define TWL6040_IRQ_READY 5 + +enum twl6040_pll_id { + TWL6040_NOPLL_ID, + TWL6040_LPPLL_ID, + TWL6040_HPPLL_ID, +}; + +struct twl6040 { + struct device *dev; + struct mutex mutex; + struct mutex io_mutex; + struct mutex irq_mutex; + struct mfd_cell cells[TWL6040_CELLS]; + struct completion ready; + + int audpwron; + int power_count; + int rev; + + enum twl6040_pll_id pll; + unsigned int sysclk; + + unsigned int irq; + unsigned int irq_base; + u8 irq_masks_cur; + u8 irq_masks_cache; +}; + +static inline int twl6040_request_irq(struct twl6040 *twl6040, int irq, + irq_handler_t handler, + unsigned long irqflags, + const char *name, + void *data) +{ + if (!twl6040->irq_base) + return -EINVAL; + + return request_threaded_irq(twl6040->irq_base + irq, NULL, handler, + irqflags, name, data); +} + +static inline void twl6040_free_irq(struct twl6040 *twl6040, int irq, + void *data) +{ + if (!twl6040->irq_base) + return; + + free_irq(twl6040->irq_base + irq, data); +} + +int twl6040_reg_read(struct twl6040 *twl6040, unsigned int reg); +int twl6040_reg_write(struct twl6040 *twl6040, unsigned int reg, + u8 val); +int twl6040_set_bits(struct twl6040 *twl6040, unsigned int reg, + u8 mask); +int twl6040_clear_bits(struct twl6040 *twl6040, unsigned int reg, + u8 mask); +int twl6040_power(struct twl6040 *twl6040, int on); +int twl6040_set_pll(struct twl6040 *twl6040, enum twl6040_pll_id id, + unsigned int freq_in, unsigned int freq_out); +enum twl6040_pll_id twl6040_get_pll(struct twl6040 *twl6040); +unsigned int twl6040_get_sysclk(struct twl6040 *twl6040); +int twl6040_irq_init(struct twl6040 *twl6040); +void twl6040_irq_exit(struct twl6040 *twl6040); + +#endif /* End of __TWL6040_CODEC_H__ */ -- cgit v1.2.3 From cc697d38392c92b7504e7719c65ae905f0a0618a Mon Sep 17 00:00:00 2001 From: Misael Lopez Cruz Date: Sun, 1 May 2011 03:51:24 -0500 Subject: input: Add initial support for TWL6040 vibrator Add twl6040_vibra as a child of MFD device twl6040_codec. This implementation covers the PCM-to-PWM mode of TWL6040 vibrator module. Signed-off-by: Misael Lopez Cruz Signed-off-by: Peter Ujfalusi CC: Tejun Heo Acked-by: Dmitry Torokhov --- include/linux/i2c/twl.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c/twl.h b/include/linux/i2c/twl.h index ea5baa269226..685fd767c69b 100644 --- a/include/linux/i2c/twl.h +++ b/include/linux/i2c/twl.h @@ -669,6 +669,14 @@ struct twl4030_codec_data { struct twl4030_vibra_data { unsigned int coexist; + + /* twl6040 */ + unsigned int vibldrv_res; /* left driver resistance */ + unsigned int vibrdrv_res; /* right driver resistance */ + unsigned int viblmotor_res; /* left motor resistance */ + unsigned int vibrmotor_res; /* right motor resistance */ + int vddvibl_uV; /* VDDVIBL volt, set 0 for fixed reg */ + int vddvibr_uV; /* VDDVIBR volt, set 0 for fixed reg */ }; struct twl4030_audio_data { -- cgit v1.2.3 From 1fbe99529d9490fd29982af07731650f112ffdfa Mon Sep 17 00:00:00 2001 From: Axel Castaneda Gonzalez Date: Wed, 23 Feb 2011 20:08:28 -0600 Subject: ASoC: twl6040: Configure ramp step based on platform Enable ramp down/up step to be configured based on platform. Signed-off-by: Axel Castaneda Gonzalez Signed-off-by: Misael Lopez Cruz Signed-off-by: Peter Ujfalusi Acked-by: Mark Brown --- include/linux/i2c/twl.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c/twl.h b/include/linux/i2c/twl.h index 685fd767c69b..114c0f6fc63d 100644 --- a/include/linux/i2c/twl.h +++ b/include/linux/i2c/twl.h @@ -664,6 +664,10 @@ struct twl4030_codec_data { unsigned int check_defaults:1; unsigned int reset_registers:1; unsigned int hs_extmute:1; + u16 hs_left_step; + u16 hs_right_step; + u16 hf_left_step; + u16 hf_right_step; void (*set_hs_extmute)(int mute); }; -- cgit v1.2.3 From 2456689b3b11ddecc091cd5f00b9adea6a9854cf Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Mon, 4 Jul 2011 19:22:00 -0700 Subject: Input: wm97xx - remove redundant define Signed-off-by: Wolfram Sang Acked-by: Mark Brown Signed-off-by: Dmitry Torokhov --- include/linux/wm97xx.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/wm97xx.h b/include/linux/wm97xx.h index 38e8c4d9289e..10b9e614fccd 100644 --- a/include/linux/wm97xx.h +++ b/include/linux/wm97xx.h @@ -38,7 +38,7 @@ #define WM97XX_ADCSEL_X 0x1000 /* x coord measurement */ #define WM97XX_ADCSEL_Y 0x2000 /* y coord measurement */ #define WM97XX_ADCSEL_PRES 0x3000 /* pressure measurement */ -#define WM97XX_ADCSEL_MASK 0x7000 +#define WM97XX_ADCSEL_MASK 0x7000 /* ADC selection mask */ #define WM97XX_COO 0x0800 /* enable coordinate mode */ #define WM97XX_CTC 0x0400 /* enable continuous mode */ #define WM97XX_CM_RATE_93 0x0000 /* 93.75Hz continuous rate */ @@ -61,7 +61,6 @@ #define WM97XX_PRP_DET_DIG 0xc000 /* setect on, digitise on */ #define WM97XX_RPR 0x2000 /* wake up on pen down */ #define WM97XX_PEN_DOWN 0x8000 /* pen is down */ -#define WM97XX_ADCSRC_MASK 0x7000 /* ADC source mask */ #define WM97XX_AUX_ID1 0x8001 #define WM97XX_AUX_ID2 0x8002 -- cgit v1.2.3 From c8f205258bc8942e79cd37ebc1c8ec4652a1a501 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Mon, 4 Jul 2011 19:22:00 -0700 Subject: Input: wm97xx - refactor channel selection in poll_sample() The current implementation of poll_sample() has the problem that one of its arguments, the channel to be selected, differs from wm9713 to other variants. This parameter gets passed to the (currently unused) mach-specific functions pre_sample() and post_sample() which thus have to deal with codec-specific differences. Refactor the routine so that the argument to poll_sample() is generic for all codecs and do necessary conversions only in the codec-specific driver. The outcome even uses less code and removes the non-standard use of the PEN_DOWN bit to mark the AUX-channels. Signed-off-by: Wolfram Sang Acked-by: Mark Brown Signed-off-by: Dmitry Torokhov --- include/linux/wm97xx.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/wm97xx.h b/include/linux/wm97xx.h index 10b9e614fccd..fd98bb968219 100644 --- a/include/linux/wm97xx.h +++ b/include/linux/wm97xx.h @@ -38,6 +38,10 @@ #define WM97XX_ADCSEL_X 0x1000 /* x coord measurement */ #define WM97XX_ADCSEL_Y 0x2000 /* y coord measurement */ #define WM97XX_ADCSEL_PRES 0x3000 /* pressure measurement */ +#define WM97XX_AUX_ID1 0x4000 +#define WM97XX_AUX_ID2 0x5000 +#define WM97XX_AUX_ID3 0x6000 +#define WM97XX_AUX_ID4 0x7000 #define WM97XX_ADCSEL_MASK 0x7000 /* ADC selection mask */ #define WM97XX_COO 0x0800 /* enable coordinate mode */ #define WM97XX_CTC 0x0400 /* enable continuous mode */ @@ -62,12 +66,6 @@ #define WM97XX_RPR 0x2000 /* wake up on pen down */ #define WM97XX_PEN_DOWN 0x8000 /* pen is down */ -#define WM97XX_AUX_ID1 0x8001 -#define WM97XX_AUX_ID2 0x8002 -#define WM97XX_AUX_ID3 0x8003 -#define WM97XX_AUX_ID4 0x8004 - - /* WM9712 Bits */ #define WM9712_45W 0x1000 /* set for 5-wire touchscreen */ #define WM9712_PDEN 0x0800 /* measure only when pen down */ -- cgit v1.2.3 From 7bed4b2c97d548c652ada6111604568ea6b0c423 Mon Sep 17 00:00:00 2001 From: Simon Budig Date: Mon, 4 Jul 2011 19:56:01 -0700 Subject: Input: add guarding parentheses to macros Put parentheses around macro argument uses. This avoids pitfalls for the programmer, where the argument expansion does not give the expected result, for example: ioctl (fd, EVIOCGABS (have_mt ? ABS_MT_POSITION_X : ABS_X), &abs); Signed-off-by: Simon Budig Signed-off-by: Dmitry Torokhov --- include/linux/input.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/input.h b/include/linux/input.h index 771d6d85667d..068784e17972 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -119,9 +119,9 @@ struct input_keymap_entry { #define EVIOCGSND(len) _IOC(_IOC_READ, 'E', 0x1a, len) /* get all sounds status */ #define EVIOCGSW(len) _IOC(_IOC_READ, 'E', 0x1b, len) /* get all switch states */ -#define EVIOCGBIT(ev,len) _IOC(_IOC_READ, 'E', 0x20 + ev, len) /* get event bits */ -#define EVIOCGABS(abs) _IOR('E', 0x40 + abs, struct input_absinfo) /* get abs value/limits */ -#define EVIOCSABS(abs) _IOW('E', 0xc0 + abs, struct input_absinfo) /* set abs value/limits */ +#define EVIOCGBIT(ev,len) _IOC(_IOC_READ, 'E', 0x20 + (ev), len) /* get event bits */ +#define EVIOCGABS(abs) _IOR('E', 0x40 + (abs), struct input_absinfo) /* get abs value/limits */ +#define EVIOCSABS(abs) _IOW('E', 0xc0 + (abs), struct input_absinfo) /* set abs value/limits */ #define EVIOCSFF _IOC(_IOC_WRITE, 'E', 0x80, sizeof(struct ff_effect)) /* send a force effect to a force feedback device */ #define EVIOCRMFF _IOW('E', 0x81, int) /* Erase a force effect */ -- cgit v1.2.3 From e4c2fb0d5776b58049d2556b456144a4db3fe5a9 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Jul 2011 10:56:32 +0200 Subject: sched: Disable (revert) SCHED_LOAD_SCALE increase Alex reported that commit c8b281161df ("sched: Increase SCHED_LOAD_SCALE resolution") caused a power usage regression under light load as it increases the number of load-balance operations and keeps idle cpus from staying idle. Time has run out to find the root cause for this release so disable the feature for v3.0 until we can figure out what causes the problem. Reported-by: "Alex, Shi" Signed-off-by: Peter Zijlstra Cc: Nikhil Rao Cc: Ming Lei Cc: Mike Galbraith Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/n/tip-m4onxn0sxnyn5iz9o88eskc3@git.kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index a837b20ba190..496770a96487 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -808,7 +808,7 @@ enum cpu_idle_type { * when BITS_PER_LONG <= 32 are pretty high and the returns do not justify the * increased costs. */ -#if BITS_PER_LONG > 32 +#if 0 /* BITS_PER_LONG > 32 -- currently broken: it increases power usage under light load */ # define SCHED_LOAD_RESOLUTION 10 # define scale_load(w) ((w) << SCHED_LOAD_RESOLUTION) # define scale_load_down(w) ((w) >> SCHED_LOAD_RESOLUTION) -- cgit v1.2.3 From 304e21bbeab0d208dc7e6142fb75db8a466d5217 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Fri, 1 Jul 2011 22:35:28 +0400 Subject: ssb: PCI revision ID register is 8-bit wide The SSB code reads PCI revision ID register as 16-bit entity while the register is actually 8-bit only (the next 8 bits are the programming interface register). Fix the read and make the 'rev' field of 'struct ssb_boardinfo' 8-bit as well, to match the register size. Signed-off-by: Sergei Shtylyov Signed-off-by: John W. Linville --- include/linux/ssb/ssb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index 252e44821787..b0928c10111b 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -99,7 +99,7 @@ struct ssb_sprom { struct ssb_boardinfo { u16 vendor; u16 type; - u16 rev; + u8 rev; }; -- cgit v1.2.3 From 4d12b8b129f170d0fc3188de1e51a2a1b0f87730 Mon Sep 17 00:00:00 2001 From: Lauro Ramos Venancio Date: Fri, 1 Jul 2011 19:31:34 -0300 Subject: NFC: add nfc generic netlink interface The NFC generic netlink interface exports the NFC control operations to the user space. Signed-off-by: Lauro Ramos Venancio Signed-off-by: Aloisio Almeida Jr Signed-off-by: Samuel Ortiz Reviewed-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nfc.h | 112 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 112 insertions(+) create mode 100644 include/linux/nfc.h (limited to 'include/linux') diff --git a/include/linux/nfc.h b/include/linux/nfc.h new file mode 100644 index 000000000000..1170476d270a --- /dev/null +++ b/include/linux/nfc.h @@ -0,0 +1,112 @@ +/* + * Copyright (C) 2011 Instituto Nokia de Tecnologia + * + * Authors: + * Lauro Ramos Venancio + * Aloisio Almeida Jr + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the + * Free Software Foundation, Inc., + * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + */ + +#ifndef __LINUX_NFC_H +#define __LINUX_NFC_H + +#define NFC_GENL_NAME "nfc" +#define NFC_GENL_VERSION 1 + +#define NFC_GENL_MCAST_EVENT_NAME "events" + +/** + * enum nfc_commands - supported nfc commands + * + * @NFC_CMD_UNSPEC: unspecified command + * + * @NFC_CMD_GET_DEVICE: request information about a device (requires + * %NFC_ATTR_DEVICE_INDEX) or dump request to get a list of all nfc devices + * @NFC_CMD_START_POLL: start polling for targets using the given protocols + * (requires %NFC_ATTR_DEVICE_INDEX and %NFC_ATTR_PROTOCOLS) + * @NFC_CMD_STOP_POLL: stop polling for targets (requires + * %NFC_ATTR_DEVICE_INDEX) + * @NFC_CMD_GET_TARGET: dump all targets found by the previous poll (requires + * %NFC_ATTR_DEVICE_INDEX) + * @NFC_EVENT_TARGETS_FOUND: event emitted when a new target is found + * (it sends %NFC_ATTR_DEVICE_INDEX) + * @NFC_EVENT_DEVICE_ADDED: event emitted when a new device is registred + * (it sends %NFC_ATTR_DEVICE_NAME, %NFC_ATTR_DEVICE_INDEX and + * %NFC_ATTR_PROTOCOLS) + * @NFC_EVENT_DEVICE_REMOVED: event emitted when a device is removed + * (it sends %NFC_ATTR_DEVICE_INDEX) + */ +enum nfc_commands { + NFC_CMD_UNSPEC, + NFC_CMD_GET_DEVICE, + NFC_CMD_START_POLL, + NFC_CMD_STOP_POLL, + NFC_CMD_GET_TARGET, + NFC_EVENT_TARGETS_FOUND, + NFC_EVENT_DEVICE_ADDED, + NFC_EVENT_DEVICE_REMOVED, +/* private: internal use only */ + __NFC_CMD_AFTER_LAST +}; +#define NFC_CMD_MAX (__NFC_CMD_AFTER_LAST - 1) + +/** + * enum nfc_attrs - supported nfc attributes + * + * @NFC_ATTR_UNSPEC: unspecified attribute + * + * @NFC_ATTR_DEVICE_INDEX: index of nfc device + * @NFC_ATTR_DEVICE_NAME: device name, max 8 chars + * @NFC_ATTR_PROTOCOLS: nfc protocols - bitwise or-ed combination from + * NFC_PROTO_*_MASK constants + * @NFC_ATTR_TARGET_INDEX: index of the nfc target + * @NFC_ATTR_TARGET_SENS_RES: NFC-A targets extra information such as NFCID + * @NFC_ATTR_TARGET_SEL_RES: NFC-A targets extra information (useful if the + * target is not NFC-Forum compliant) + */ +enum nfc_attrs { + NFC_ATTR_UNSPEC, + NFC_ATTR_DEVICE_INDEX, + NFC_ATTR_DEVICE_NAME, + NFC_ATTR_PROTOCOLS, + NFC_ATTR_TARGET_INDEX, + NFC_ATTR_TARGET_SENS_RES, + NFC_ATTR_TARGET_SEL_RES, +/* private: internal use only */ + __NFC_ATTR_AFTER_LAST +}; +#define NFC_ATTR_MAX (__NFC_ATTR_AFTER_LAST - 1) + +#define NFC_DEVICE_NAME_MAXSIZE 8 + +/* NFC protocols */ +#define NFC_PROTO_JEWEL 1 +#define NFC_PROTO_MIFARE 2 +#define NFC_PROTO_FELICA 3 +#define NFC_PROTO_ISO14443 4 +#define NFC_PROTO_NFC_DEP 5 + +#define NFC_PROTO_MAX 6 + +/* NFC protocols masks used in bitsets */ +#define NFC_PROTO_JEWEL_MASK (1 << NFC_PROTO_JEWEL) +#define NFC_PROTO_MIFARE_MASK (1 << NFC_PROTO_MIFARE) +#define NFC_PROTO_FELICA_MASK (1 << NFC_PROTO_FELICA) +#define NFC_PROTO_ISO14443_MASK (1 << NFC_PROTO_ISO14443) +#define NFC_PROTO_NFC_DEP_MASK (1 << NFC_PROTO_NFC_DEP) + +#endif /*__LINUX_NFC_H */ -- cgit v1.2.3 From c7fe3b52c1283b8ba810eb6ecddf1c8a0bcc13ab Mon Sep 17 00:00:00 2001 From: Aloisio Almeida Jr Date: Fri, 1 Jul 2011 19:31:35 -0300 Subject: NFC: add NFC socket family Signed-off-by: Lauro Ramos Venancio Signed-off-by: Aloisio Almeida Jr Signed-off-by: John W. Linville --- include/linux/nfc.h | 3 +++ include/linux/socket.h | 4 +++- 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfc.h b/include/linux/nfc.h index 1170476d270a..15f8cb3edcc6 100644 --- a/include/linux/nfc.h +++ b/include/linux/nfc.h @@ -109,4 +109,7 @@ enum nfc_attrs { #define NFC_PROTO_ISO14443_MASK (1 << NFC_PROTO_ISO14443) #define NFC_PROTO_NFC_DEP_MASK (1 << NFC_PROTO_NFC_DEP) +/* NFC socket protocols */ +#define NFC_SOCKPROTO_MAX 0 + #endif /*__LINUX_NFC_H */ diff --git a/include/linux/socket.h b/include/linux/socket.h index 4ef98e422fde..e17f82266639 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -192,7 +192,8 @@ struct ucred { #define AF_IEEE802154 36 /* IEEE802154 sockets */ #define AF_CAIF 37 /* CAIF sockets */ #define AF_ALG 38 /* Algorithm sockets */ -#define AF_MAX 39 /* For now.. */ +#define AF_NFC 39 /* NFC sockets */ +#define AF_MAX 40 /* For now.. */ /* Protocol families, same as address families. */ #define PF_UNSPEC AF_UNSPEC @@ -234,6 +235,7 @@ struct ucred { #define PF_IEEE802154 AF_IEEE802154 #define PF_CAIF AF_CAIF #define PF_ALG AF_ALG +#define PF_NFC AF_NFC #define PF_MAX AF_MAX /* Maximum queue length specifiable by listen. */ -- cgit v1.2.3 From 23b7869c0fd08d73c9f83a2db88a13312d6198bb Mon Sep 17 00:00:00 2001 From: Lauro Ramos Venancio Date: Fri, 1 Jul 2011 19:31:36 -0300 Subject: NFC: add the NFC socket raw protocol This socket protocol is used to perform data exchange with NFC targets. Signed-off-by: Lauro Ramos Venancio Signed-off-by: Aloisio Almeida Jr Signed-off-by: Samuel Ortiz Signed-off-by: John W. Linville --- include/linux/nfc.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfc.h b/include/linux/nfc.h index 15f8cb3edcc6..330a4c5db588 100644 --- a/include/linux/nfc.h +++ b/include/linux/nfc.h @@ -24,6 +24,9 @@ #ifndef __LINUX_NFC_H #define __LINUX_NFC_H +#include +#include + #define NFC_GENL_NAME "nfc" #define NFC_GENL_VERSION 1 @@ -109,7 +112,15 @@ enum nfc_attrs { #define NFC_PROTO_ISO14443_MASK (1 << NFC_PROTO_ISO14443) #define NFC_PROTO_NFC_DEP_MASK (1 << NFC_PROTO_NFC_DEP) +struct sockaddr_nfc { + sa_family_t sa_family; + __u32 dev_idx; + __u32 target_idx; + __u32 nfc_protocol; +}; + /* NFC socket protocols */ -#define NFC_SOCKPROTO_MAX 0 +#define NFC_SOCKPROTO_RAW 0 +#define NFC_SOCKPROTO_MAX 1 #endif /*__LINUX_NFC_H */ -- cgit v1.2.3 From dc99f600698dcac69b8f56dda9a8a00d645c5ffc Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 5 Jul 2011 01:45:05 -0700 Subject: packet: Add fanout support. Fanouts allow packet capturing to be demuxed to a set of AF_PACKET sockets. Two fanout policies are implemented: 1) Hashing based upon skb->rxhash 2) Pure round-robin An AF_PACKET socket must be fully bound before it tries to add itself to a fanout. All AF_PACKET sockets trying to join the same fanout must all have the same bind settings. Fanouts are identified (within a network namespace) by a 16-bit ID. The first socket to try to add itself to a fanout with a particular ID, creates that fanout. When the last socket leaves the fanout (which happens only when the socket is closed), that fanout is destroyed. Signed-off-by: David S. Miller --- include/linux/if_packet.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_packet.h b/include/linux/if_packet.h index 7b318630139f..1efa1cb827f5 100644 --- a/include/linux/if_packet.h +++ b/include/linux/if_packet.h @@ -49,6 +49,10 @@ struct sockaddr_ll { #define PACKET_VNET_HDR 15 #define PACKET_TX_TIMESTAMP 16 #define PACKET_TIMESTAMP 17 +#define PACKET_FANOUT 18 + +#define PACKET_FANOUT_HASH 0 +#define PACKET_FANOUT_LB 1 struct tpacket_stats { unsigned int tp_packets; -- cgit v1.2.3 From 7736d33f4262d437c51ed7a28114eacbfca236ff Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 5 Jul 2011 01:43:20 -0700 Subject: packet: Add pre-defragmentation support for ipv4 fanouts. The skb->rxhash cannot be properly computed if the packet is a fragment. To alleviate this, allow the AF_PACKET client to ask for defragmentation to be done at demux time. Signed-off-by: David S. Miller --- include/linux/if_packet.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/if_packet.h b/include/linux/if_packet.h index 1efa1cb827f5..84e684e6935c 100644 --- a/include/linux/if_packet.h +++ b/include/linux/if_packet.h @@ -53,6 +53,7 @@ struct sockaddr_ll { #define PACKET_FANOUT_HASH 0 #define PACKET_FANOUT_LB 1 +#define PACKET_FANOUT_FLAG_DEFRAG 0x8000 struct tpacket_stats { unsigned int tp_packets; -- cgit v1.2.3 From 37cf4d1a9b0903b874a638d0f8649873ddde8a12 Mon Sep 17 00:00:00 2001 From: Shmulik Ravid Date: Tue, 5 Jul 2011 06:16:22 +0000 Subject: dcbnl: Aggregated CEE GET operation The following couple of patches add dcbnl an unsolicited notification of the the DCB configuration for the CEE flavor of the DCBX protocol. This is useful when the user-mode DCB client is not responsible for conducting and resolving the DCBX negotiation (either because the DCBX stack is embedded in the HW or the negotiation is handled by another agent in the host), but still needs to get the negotiated parameters. This functionality already exists for the IEEE flavor of the DCBX protocol and these patches add it to the older CEE flavor. The first patch extends the CEE attribute GET operation to include not only the peer information, but also all the pertinent local configuration (negotiated parameters). The second patch adds and export a CEE specific notification routine. Signed-off-by: Shmulik Ravid Signed-off-by: David S. Miller --- include/linux/dcbnl.h | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dcbnl.h b/include/linux/dcbnl.h index 66a67235e729..65a2562f66b4 100644 --- a/include/linux/dcbnl.h +++ b/include/linux/dcbnl.h @@ -333,18 +333,30 @@ enum ieee_attrs_app { #define DCB_ATTR_IEEE_APP_MAX (__DCB_ATTR_IEEE_APP_MAX - 1) /** - * enum cee_attrs - CEE DCBX get attributes + * enum cee_attrs - CEE DCBX get attributes. * * @DCB_ATTR_CEE_UNSPEC: unspecified * @DCB_ATTR_CEE_PEER_PG: peer PG configuration - get only * @DCB_ATTR_CEE_PEER_PFC: peer PFC configuration - get only - * @DCB_ATTR_CEE_PEER_APP: peer APP tlv - get only + * @DCB_ATTR_CEE_PEER_APP_TABLE: peer APP tlv - get only + * @DCB_ATTR_CEE_TX_PG: TX PG configuration (DCB_CMD_PGTX_GCFG) + * @DCB_ATTR_CEE_RX_PG: RX PG configuration (DCB_CMD_PGRX_GCFG) + * @DCB_ATTR_CEE_PFC: PFC configuration (DCB_CMD_PFC_GCFG) + * @DCB_ATTR_CEE_APP_TABLE: APP configuration (multi DCB_CMD_GAPP) + * @DCB_ATTR_CEE_FEAT: DCBX features flags (DCB_CMD_GFEATCFG) + * + * An aggregated collection of the cee std negotiated parameters. */ enum cee_attrs { DCB_ATTR_CEE_UNSPEC, DCB_ATTR_CEE_PEER_PG, DCB_ATTR_CEE_PEER_PFC, DCB_ATTR_CEE_PEER_APP_TABLE, + DCB_ATTR_CEE_TX_PG, + DCB_ATTR_CEE_RX_PG, + DCB_ATTR_CEE_PFC, + DCB_ATTR_CEE_APP_TABLE, + DCB_ATTR_CEE_FEAT, __DCB_ATTR_CEE_MAX }; #define DCB_ATTR_CEE_MAX (__DCB_ATTR_CEE_MAX - 1) @@ -357,6 +369,13 @@ enum peer_app_attr { }; #define DCB_ATTR_CEE_PEER_APP_MAX (__DCB_ATTR_CEE_PEER_APP_MAX - 1) +enum cee_attrs_app { + DCB_ATTR_CEE_APP_UNSPEC, + DCB_ATTR_CEE_APP, + __DCB_ATTR_CEE_APP_MAX +}; +#define DCB_ATTR_CEE_APP_MAX (__DCB_ATTR_CEE_APP_MAX - 1) + /** * enum dcbnl_pfc_attrs - DCB Priority Flow Control user priority nested attrs * -- cgit v1.2.3 From 95ec3eb417115fbb2c73b59e2825f6dd5d2f6cf6 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 6 Jul 2011 01:56:38 -0700 Subject: packet: Add 'cpu' fanout policy. Unfortunately we have to use a real modulus here as the multiply trick won't work as effectively with cpu numbers as it does with rxhash values. Signed-off-by: David S. Miller --- include/linux/if_packet.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/if_packet.h b/include/linux/if_packet.h index 84e684e6935c..c1486060f5ed 100644 --- a/include/linux/if_packet.h +++ b/include/linux/if_packet.h @@ -53,6 +53,7 @@ struct sockaddr_ll { #define PACKET_FANOUT_HASH 0 #define PACKET_FANOUT_LB 1 +#define PACKET_FANOUT_CPU 2 #define PACKET_FANOUT_FLAG_DEFRAG 0x8000 struct tpacket_stats { -- cgit v1.2.3 From e5497d766adb92bcbd1fa4a147e188f84f34b20a Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 5 Jul 2011 16:35:40 +0200 Subject: cfg80211/nl80211: support GTK rekey offload In certain circumstances, like WoWLAN scenarios, devices may implement (partial) GTK rekeying on the device to avoid waking up the host for it. In order to successfully go through GTK rekeying, the KEK, KCK and the replay counter are required. Add API to let the supplicant hand the parameters to the driver which may store it for future GTK rekey operations. Note that, of course, if GTK rekeying is done by the device, the EAP frame must not be passed up to userspace, instead a rekey event needs to be sent to let userspace update its replay counter. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nl80211.h | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index c7ccaae15af6..3ec2f949bf7a 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -483,6 +483,14 @@ * more background information, see * http://wireless.kernel.org/en/users/Documentation/WoWLAN. * + * @NL80211_CMD_SET_REKEY_OFFLOAD: This command is used give the driver + * the necessary information for supporting GTK rekey offload. This + * feature is typically used during WoWLAN. The configuration data + * is contained in %NL80211_ATTR_REKEY_DATA (which is nested and + * contains the data in sub-attributes). After rekeying happened, + * this command may also be sent by the driver as an MLME event to + * inform userspace of the new replay counter. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -605,6 +613,8 @@ enum nl80211_commands { NL80211_CMD_SCHED_SCAN_RESULTS, NL80211_CMD_SCHED_SCAN_STOPPED, + NL80211_CMD_SET_REKEY_OFFLOAD, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -996,6 +1006,9 @@ enum nl80211_commands { * are managed in software: interfaces of these types aren't subject to * any restrictions in their number or combinations. * + * @%NL80211_ATTR_REKEY_DATA: nested attribute containing the information + * necessary for GTK rekeying in the device, see &enum nl80211_rekey_data. + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -1194,6 +1207,8 @@ enum nl80211_attrs { NL80211_ATTR_INTERFACE_COMBINATIONS, NL80211_ATTR_SOFTWARE_IFTYPES, + NL80211_ATTR_REKEY_DATA, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -2361,4 +2376,28 @@ enum nl80211_plink_state { MAX_NL80211_PLINK_STATES = NUM_NL80211_PLINK_STATES - 1 }; +#define NL80211_KCK_LEN 16 +#define NL80211_KEK_LEN 16 +#define NL80211_REPLAY_CTR_LEN 8 + +/** + * enum nl80211_rekey_data - attributes for GTK rekey offload + * @__NL80211_REKEY_DATA_INVALID: invalid number for nested attributes + * @NL80211_REKEY_DATA_KEK: key encryption key (binary) + * @NL80211_REKEY_DATA_KCK: key confirmation key (binary) + * @NL80211_REKEY_DATA_REPLAY_CTR: replay counter (binary) + * @NUM_NL80211_REKEY_DATA: number of rekey attributes (internal) + * @MAX_NL80211_REKEY_DATA: highest rekey attribute (internal) + */ +enum nl80211_rekey_data { + __NL80211_REKEY_DATA_INVALID, + NL80211_REKEY_DATA_KEK, + NL80211_REKEY_DATA_KCK, + NL80211_REKEY_DATA_REPLAY_CTR, + + /* keep last */ + NUM_NL80211_REKEY_DATA, + MAX_NL80211_REKEY_DATA = NUM_NL80211_REKEY_DATA - 1 +}; + #endif /* __LINUX_NL80211_H */ -- cgit v1.2.3 From 0e373639ad7c7ef2b0c9cf907574b266791b9778 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 6 Jul 2011 15:42:58 -0500 Subject: dt: add helper function to read u32 arrays Rework of_property_read_u32 to read an array of values. Then of_property_read_u32 becomes an inline with array size of 1. Also make struct device_node ptr const. Signed-off-by: Rob Herring Signed-off-by: Grant Likely --- include/linux/of.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index b23852002b30..b5f1c88e40a7 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -195,8 +195,18 @@ extern struct device_node *of_find_node_with_property( extern struct property *of_find_property(const struct device_node *np, const char *name, int *lenp); -extern int of_property_read_u32(struct device_node *np, char *propname, - u32 *out_value); +extern int of_property_read_u32_array(const struct device_node *np, + char *propname, + u32 *out_values, + size_t sz); + +static inline int of_property_read_u32(const struct device_node *np, + char *propname, + u32 *out_value) +{ + return of_property_read_u32_array(np, propname, out_value, 1); +} + extern int of_property_read_string(struct device_node *np, char *propname, const char **out_string); extern int of_device_is_compatible(const struct device_node *device, -- cgit v1.2.3 From 7a0d4fcf6d4b80b30503fd2701eeef1883e11404 Mon Sep 17 00:00:00 2001 From: Daniel Drake Date: Sat, 25 Jun 2011 17:34:09 +0100 Subject: x86, olpc: Move CS5536-related constants to cs5535.h Move these definitions into the relevant header file. This was requested in the review of the upcoming XO-1 suspend/resume code. Signed-off-by: Daniel Drake Link: http://lkml.kernel.org/r/1309019658-1712-3-git-send-email-dsd@laptop.org Acked-by: Andres Salomon Signed-off-by: H. Peter Anvin --- include/linux/cs5535.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cs5535.h b/include/linux/cs5535.h index 6fe2114f8ad2..e46b8b0f9057 100644 --- a/include/linux/cs5535.h +++ b/include/linux/cs5535.h @@ -49,6 +49,27 @@ #define LBAR_ACPI_SIZE 0x40 #define LBAR_PMS_SIZE 0x80 +/* + * PMC registers (PMS block) + * It is only safe to access these registers as dword accesses. + * See CS5536 Specification Update erratas 17 & 18 + */ +#define CS5536_PM_SCLK 0x10 +#define CS5536_PM_IN_SLPCTL 0x20 +#define CS5536_PM_WKXD 0x34 +#define CS5536_PM_WKD 0x30 +#define CS5536_PM_SSC 0x54 + +/* + * PM registers (ACPI block) + * It is only safe to access these registers as dword accesses. + * See CS5536 Specification Update erratas 17 & 18 + */ +#define CS5536_PM1_STS 0x00 +#define CS5536_PM1_EN 0x02 +#define CS5536_PM1_CNT 0x08 +#define CS5536_PM_GPE0_STS 0x18 + /* VSA2 magic values */ #define VSA_VRC_INDEX 0xAC1C #define VSA_VRC_DATA 0xAC1E -- cgit v1.2.3 From 97c4cb71c18fe045a763ff6681a8ebbbbbec0b2b Mon Sep 17 00:00:00 2001 From: Daniel Drake Date: Sat, 25 Jun 2011 17:34:11 +0100 Subject: x86, olpc: Add XO-1 suspend/resume support Add code needed for basic suspend/resume of the XO-1 laptop. Based on earlier work by Jordan Crouse, Andres Salomon, and others. This patch incorporates all earlier feedback from Thomas Gleixner. To clarify a certain point (now more obvious in the code itself): On resume, OpenFirmware returns execution to Linux in protected mode with a kernel-compatible GDT already set up. The changes and simplifications suggested have all been included. Signed-off-by: Daniel Drake Link: http://lkml.kernel.org/r/1309019658-1712-5-git-send-email-dsd@laptop.org Acked-by: Andres Salomon Signed-off-by: H. Peter Anvin --- include/linux/cs5535.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cs5535.h b/include/linux/cs5535.h index e46b8b0f9057..2facf16f017b 100644 --- a/include/linux/cs5535.h +++ b/include/linux/cs5535.h @@ -70,6 +70,9 @@ #define CS5536_PM1_CNT 0x08 #define CS5536_PM_GPE0_STS 0x18 +/* CS5536_PM1_EN bits */ +#define CS5536_PM_PWRBTN (1 << 8) + /* VSA2 magic values */ #define VSA_VRC_INDEX 0xAC1C #define VSA_VRC_DATA 0xAC1E -- cgit v1.2.3 From 7feda8e9f35ebb0e9f90e03acb02280bc137f784 Mon Sep 17 00:00:00 2001 From: Daniel Drake Date: Sat, 25 Jun 2011 17:34:12 +0100 Subject: x86, olpc: Add XO-1 SCI driver and power button control The System Control Interrupt is used in the OLPC XO-1 to control various features of the laptop. Add the driver base and the power button functionality. This driver can't be built as a module, because functionality added in future patches means that some drivers need to know at boot-time whether SCI-based functionality is available. Signed-off-by: Daniel Drake Link: http://lkml.kernel.org/r/1309019658-1712-6-git-send-email-dsd@laptop.org Acked-by: Andres Salomon Signed-off-by: H. Peter Anvin --- include/linux/cs5535.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cs5535.h b/include/linux/cs5535.h index 2facf16f017b..6f78235cb905 100644 --- a/include/linux/cs5535.h +++ b/include/linux/cs5535.h @@ -43,6 +43,10 @@ #define MSR_GX_GLD_MSR_CONFIG 0xC0002001 #define MSR_GX_MSR_PADSEL 0xC0002011 +/* PIC registers */ +#define CS5536_PIC_INT_SEL1 0x4d0 +#define CS5536_PIC_INT_SEL2 0x4d1 + /* resource sizes */ #define LBAR_GPIO_SIZE 0xFF #define LBAR_MFGPT_SIZE 0x40 @@ -70,6 +74,10 @@ #define CS5536_PM1_CNT 0x08 #define CS5536_PM_GPE0_STS 0x18 +/* CS5536_PM1_STS bits */ +#define CS5536_WAK_FLAG (1 << 15) +#define CS5536_PWRBTN_FLAG (1 << 8) + /* CS5536_PM1_EN bits */ #define CS5536_PM_PWRBTN (1 << 8) -- cgit v1.2.3 From 7bc74b3df73776fe06f3df9fafd2d2698e6ca28a Mon Sep 17 00:00:00 2001 From: Daniel Drake Date: Sat, 25 Jun 2011 17:34:14 +0100 Subject: x86, olpc-xo1-sci: Add GPE handler and ebook switch functionality The EC in the OLPC XO-1 delivers GPE events to provide various notifications. Add the basic code for GPE/EC event processing and enable the ebook switch, which can be used as a wakeup source. Signed-off-by: Daniel Drake Link: http://lkml.kernel.org/r/1309019658-1712-8-git-send-email-dsd@laptop.org Acked-by: Andres Salomon Signed-off-by: H. Peter Anvin --- include/linux/cs5535.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cs5535.h b/include/linux/cs5535.h index 6f78235cb905..d7e9a7f6ddb0 100644 --- a/include/linux/cs5535.h +++ b/include/linux/cs5535.h @@ -11,6 +11,8 @@ #ifndef _CS5535_H #define _CS5535_H +#include + /* MSRs */ #define MSR_GLIU_P2D_RO0 0x10000029 @@ -43,6 +45,18 @@ #define MSR_GX_GLD_MSR_CONFIG 0xC0002001 #define MSR_GX_MSR_PADSEL 0xC0002011 +static inline int cs5535_pic_unreqz_select_high(unsigned int group, + unsigned int irq) +{ + uint32_t lo, hi; + + rdmsr(MSR_PIC_ZSEL_HIGH, lo, hi); + lo &= ~(0xF << (group * 4)); + lo |= (irq & 0xF) << (group * 4); + wrmsr(MSR_PIC_ZSEL_HIGH, lo, hi); + return 0; +} + /* PIC registers */ #define CS5536_PIC_INT_SEL1 0x4d0 #define CS5536_PIC_INT_SEL2 0x4d1 @@ -73,6 +87,7 @@ #define CS5536_PM1_EN 0x02 #define CS5536_PM1_CNT 0x08 #define CS5536_PM_GPE0_STS 0x18 +#define CS5536_PM_GPE0_EN 0x1c /* CS5536_PM1_STS bits */ #define CS5536_WAK_FLAG (1 << 15) @@ -81,6 +96,13 @@ /* CS5536_PM1_EN bits */ #define CS5536_PM_PWRBTN (1 << 8) +/* CS5536_PM_GPE0_STS bits */ +#define CS5536_GPIOM7_PME_FLAG (1 << 31) +#define CS5536_GPIOM6_PME_FLAG (1 << 30) + +/* CS5536_PM_GPE0_EN bits */ +#define CS5536_GPIOM7_PME_EN (1 << 31) + /* VSA2 magic values */ #define VSA_VRC_INDEX 0xAC1C #define VSA_VRC_DATA 0xAC1E -- cgit v1.2.3 From 2cf2baea103f0a3d68b0f989d28df66f16dbc834 Mon Sep 17 00:00:00 2001 From: Daniel Drake Date: Sat, 25 Jun 2011 17:34:15 +0100 Subject: x86, olpc-xo1-sci: Add lid switch functionality Configure the XO-1's lid switch GPIO to trigger an SCI interrupt, and correctly expose this input device which can be used as a wakeup source. Signed-off-by: Daniel Drake Link: http://lkml.kernel.org/r/1309019658-1712-9-git-send-email-dsd@laptop.org Acked-by: Andres Salomon Signed-off-by: H. Peter Anvin --- include/linux/cs5535.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cs5535.h b/include/linux/cs5535.h index d7e9a7f6ddb0..72954c6bf5d6 100644 --- a/include/linux/cs5535.h +++ b/include/linux/cs5535.h @@ -102,6 +102,7 @@ static inline int cs5535_pic_unreqz_select_high(unsigned int group, /* CS5536_PM_GPE0_EN bits */ #define CS5536_GPIOM7_PME_EN (1 << 31) +#define CS5536_GPIOM6_PME_EN (1 << 30) /* VSA2 magic values */ #define VSA_VRC_INDEX 0xAC1C -- cgit v1.2.3 From cfee95977bea090ae5ec4fd442ebd381792d46c4 Mon Sep 17 00:00:00 2001 From: Daniel Drake Date: Sat, 25 Jun 2011 17:34:17 +0100 Subject: x86, olpc: Add XO-1 RTC driver Add a driver to configure the XO-1 RTC via CS5536 MSRs, to be used as a system wakeup source via olpc-xo1-pm. Device detection is based on finding the relevant device tree node. Signed-off-by: Daniel Drake Link: http://lkml.kernel.org/r/1309019658-1712-11-git-send-email-dsd@laptop.org Acked-by: Andres Salomon Acked-by: Grant Likely Reviewed-by: Sebastian Andrzej Siewior Cc: devicetree-discuss@lists.ozlabs.org Signed-off-by: H. Peter Anvin --- include/linux/cs5535.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cs5535.h b/include/linux/cs5535.h index 72954c6bf5d6..c077aec3a6ff 100644 --- a/include/linux/cs5535.h +++ b/include/linux/cs5535.h @@ -40,6 +40,10 @@ #define MSR_MFGPT_NR 0x51400029 #define MSR_MFGPT_SETUP 0x5140002B +#define MSR_RTC_DOMA_OFFSET 0x51400055 +#define MSR_RTC_MONA_OFFSET 0x51400056 +#define MSR_RTC_CEN_OFFSET 0x51400057 + #define MSR_LX_SPARE_MSR 0x80000011 /* DC-specific */ #define MSR_GX_GLD_MSR_CONFIG 0xC0002001 @@ -95,6 +99,7 @@ static inline int cs5535_pic_unreqz_select_high(unsigned int group, /* CS5536_PM1_EN bits */ #define CS5536_PM_PWRBTN (1 << 8) +#define CS5536_PM_RTC (1 << 10) /* CS5536_PM_GPE0_STS bits */ #define CS5536_GPIOM7_PME_FLAG (1 << 31) -- cgit v1.2.3 From e8e70d83912b40c5c9ea7b85a6110b9925fbed62 Mon Sep 17 00:00:00 2001 From: Chris Hudson Date: Wed, 6 Jul 2011 18:36:51 -0700 Subject: Input: add support for Kionix KXTJ9 accelerometer Signed-off-by: Chris Hudson Signed-off-by: Dmitry Torokhov --- include/linux/input/kxtj9.h | 70 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 70 insertions(+) create mode 100644 include/linux/input/kxtj9.h (limited to 'include/linux') diff --git a/include/linux/input/kxtj9.h b/include/linux/input/kxtj9.h new file mode 100644 index 000000000000..f6bac89537b8 --- /dev/null +++ b/include/linux/input/kxtj9.h @@ -0,0 +1,70 @@ +/* + * Copyright (C) 2011 Kionix, Inc. + * Written by Chris Hudson + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA + * 02111-1307, USA + */ + +#ifndef __KXTJ9_H__ +#define __KXTJ9_H__ + +#define KXTJ9_I2C_ADDR 0x0F + +struct kxtj9_platform_data { + unsigned int min_interval; /* minimum poll interval (in milli-seconds) */ + + /* + * By default, x is axis 0, y is axis 1, z is axis 2; these can be + * changed to account for sensor orientation within the host device. + */ + u8 axis_map_x; + u8 axis_map_y; + u8 axis_map_z; + + /* + * Each axis can be negated to account for sensor orientation within + * the host device. + */ + bool negate_x; + bool negate_y; + bool negate_z; + + /* CTRL_REG1: set resolution, g-range, data ready enable */ + /* Output resolution: 8-bit valid or 12-bit valid */ + #define RES_8BIT 0 + #define RES_12BIT (1 << 6) + u8 res_12bit; + /* Output g-range: +/-2g, 4g, or 8g */ + #define KXTJ9_G_2G 0 + #define KXTJ9_G_4G (1 << 3) + #define KXTJ9_G_8G (1 << 4) + u8 g_range; + + /* DATA_CTRL_REG: controls the output data rate of the part */ + #define ODR12_5F 0 + #define ODR25F 1 + #define ODR50F 2 + #define ODR100F 3 + #define ODR200F 4 + #define ODR400F 5 + #define ODR800F 6 + u8 data_odr_init; + + int (*init)(void); + void (*exit)(void); + int (*power_on)(void); + int (*power_off)(void); +}; +#endif /* __KXTJ9_H__ */ -- cgit v1.2.3 From 719c0c590609809365c6f3da2f923cd84dc99113 Mon Sep 17 00:00:00 2001 From: Johannes Stezenbach Date: Thu, 7 Jul 2011 08:18:18 +0200 Subject: compat_ioctl: fix make headers_check regression Fix headers_check error introduced by 390192b30057: include/linux/fd.h:6: included file 'linux/compat.h' is not exported Signed-off-by: Johannes Stezenbach Signed-off-by: Jens Axboe --- include/linux/fd.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fd.h b/include/linux/fd.h index c6a68d011608..72202b1b9a6a 100644 --- a/include/linux/fd.h +++ b/include/linux/fd.h @@ -3,7 +3,6 @@ #include #include -#include /* New file layout: Now the ioctl definitions immediately follow the * definitions of the structures that they use */ @@ -378,7 +377,11 @@ struct floppy_raw_cmd { #define FDEJECT _IO(2, 0x5a) /* eject the disk */ + +#ifdef __KERNEL__ #ifdef CONFIG_COMPAT +#include + struct compat_floppy_struct { compat_uint_t size; compat_uint_t sect; @@ -394,5 +397,6 @@ struct compat_floppy_struct { #define FDGETPRM32 _IOR(2, 0x04, struct compat_floppy_struct) #endif +#endif #endif -- cgit v1.2.3 From 1b7c4725e2e926eaeb8657ac22992ec27fe03135 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Mon, 4 Jul 2011 20:16:23 +0300 Subject: MFD: twl6040: Remove wrapper for threaded irq request Remove the twl6040_request_irq/free_irq inline functions, and use direct calls instead in the core driver to register the threaded irq. Signed-off-by: Peter Ujfalusi Reviewed-by: Felipe Balbi Acked-by: Samuel Ortiz --- include/linux/mfd/twl6040.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/twl6040.h b/include/linux/mfd/twl6040.h index c3c1de53dcfe..df890a247c36 100644 --- a/include/linux/mfd/twl6040.h +++ b/include/linux/mfd/twl6040.h @@ -215,28 +215,6 @@ struct twl6040 { u8 irq_masks_cache; }; -static inline int twl6040_request_irq(struct twl6040 *twl6040, int irq, - irq_handler_t handler, - unsigned long irqflags, - const char *name, - void *data) -{ - if (!twl6040->irq_base) - return -EINVAL; - - return request_threaded_irq(twl6040->irq_base + irq, NULL, handler, - irqflags, name, data); -} - -static inline void twl6040_free_irq(struct twl6040 *twl6040, int irq, - void *data) -{ - if (!twl6040->irq_base) - return; - - free_irq(twl6040->irq_base + irq, data); -} - int twl6040_reg_read(struct twl6040 *twl6040, unsigned int reg); int twl6040_reg_write(struct twl6040 *twl6040, unsigned int reg, u8 val); -- cgit v1.2.3 From cfb7a33bea259d2d72a64adcb3de28532170dc25 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Mon, 4 Jul 2011 10:28:28 +0300 Subject: MFD: twl6040: Remove enum for PLL tracking There is no need to have two different types for tracking the selected PLL. Use only the defines, when dealing with the PLLs. Signed-off-by: Peter Ujfalusi Acked-by: Samuel Ortiz --- include/linux/mfd/twl6040.h | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/twl6040.h b/include/linux/mfd/twl6040.h index df890a247c36..4c806f6d663e 100644 --- a/include/linux/mfd/twl6040.h +++ b/include/linux/mfd/twl6040.h @@ -165,9 +165,6 @@ #define TWL6040_RESETSPLIT 0x04 #define TWL6040_INTCLRMODE 0x08 -#define TWL6040_SYSCLK_SEL_LPPLL 1 -#define TWL6040_SYSCLK_SEL_HPPLL 2 - /* STATUS (0x2E) fields */ #define TWL6040_PLUGCOMP 0x02 @@ -188,11 +185,9 @@ #define TWL6040_IRQ_VIB 4 #define TWL6040_IRQ_READY 5 -enum twl6040_pll_id { - TWL6040_NOPLL_ID, - TWL6040_LPPLL_ID, - TWL6040_HPPLL_ID, -}; +/* PLL selection */ +#define TWL6040_SYSCLK_SEL_LPPLL 0 +#define TWL6040_SYSCLK_SEL_HPPLL 1 struct twl6040 { struct device *dev; @@ -206,7 +201,7 @@ struct twl6040 { int power_count; int rev; - enum twl6040_pll_id pll; + int pll; unsigned int sysclk; unsigned int irq; @@ -223,9 +218,9 @@ int twl6040_set_bits(struct twl6040 *twl6040, unsigned int reg, int twl6040_clear_bits(struct twl6040 *twl6040, unsigned int reg, u8 mask); int twl6040_power(struct twl6040 *twl6040, int on); -int twl6040_set_pll(struct twl6040 *twl6040, enum twl6040_pll_id id, +int twl6040_set_pll(struct twl6040 *twl6040, int pll_id, unsigned int freq_in, unsigned int freq_out); -enum twl6040_pll_id twl6040_get_pll(struct twl6040 *twl6040); +int twl6040_get_pll(struct twl6040 *twl6040); unsigned int twl6040_get_sysclk(struct twl6040 *twl6040); int twl6040_irq_init(struct twl6040 *twl6040); void twl6040_irq_exit(struct twl6040 *twl6040); -- cgit v1.2.3 From a6686f2f382b13f8a7253401a66690c3633b6a74 Mon Sep 17 00:00:00 2001 From: Shirley Ma Date: Wed, 6 Jul 2011 12:22:12 +0000 Subject: skbuff: skb supports zero-copy buffers This patch adds userspace buffers support in skb shared info. A new struct skb_ubuf_info is needed to maintain the userspace buffers argument and index, a callback is used to notify userspace to release the buffers once lower device has done DMA (Last reference to that skb has gone). If there is any userspace apps to reference these userspace buffers, then these userspaces buffers will be copied into kernel. This way we can prevent userspace apps from holding these userspace buffers too long. Use destructor_arg to point to the userspace buffer info; a new tx flags SKBTX_DEV_ZEROCOPY is added for zero-copy buffer check. Signed-off-by: Shirley Ma Signed-off-by: David S. Miller --- include/linux/skbuff.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3e543371254e..08d4507715f5 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -187,6 +187,20 @@ enum { /* ensure the originating sk reference is available on driver level */ SKBTX_DRV_NEEDS_SK_REF = 1 << 3, + + /* device driver supports TX zero-copy buffers */ + SKBTX_DEV_ZEROCOPY = 1 << 4, +}; + +/* + * The callback notifies userspace to release buffers when skb DMA is done in + * lower device, the skb last reference should be 0 when calling this. + * The desc is used to track userspace buffer index. + */ +struct ubuf_info { + void (*callback)(void *); + void *arg; + unsigned long desc; }; /* This data is invariant across clones and lives at @@ -211,6 +225,7 @@ struct skb_shared_info { /* Intermediate layers must ensure that destructor_arg * remains valid until skb destructor */ void * destructor_arg; + /* must be last field, see pskb_expand_head() */ skb_frag_t frags[MAX_SKB_FRAGS]; }; @@ -2265,5 +2280,6 @@ static inline void skb_checksum_none_assert(struct sk_buff *skb) } bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off); + #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ -- cgit v1.2.3 From eb032b9837a958e21ca000358a5bde5e17192ddb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Michael=20B=C3=BCsch?= Date: Mon, 4 Jul 2011 20:50:05 +0200 Subject: Update my e-mail address Signed-off-by: Michael Buesch Signed-off-by: Jiri Kosina --- include/linux/nl80211.h | 2 +- include/linux/ssb/ssb_driver_chipcommon.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index c7ccaae15af6..9043118a70d9 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -6,7 +6,7 @@ * Copyright 2006-2010 Johannes Berg * Copyright 2008 Michael Wu * Copyright 2008 Luis Carlos Cobo - * Copyright 2008 Michael Buesch + * Copyright 2008 Michael Buesch * Copyright 2008, 2009 Luis R. Rodriguez * Copyright 2008 Jouni Malinen * Copyright 2008 Colin McCabe diff --git a/include/linux/ssb/ssb_driver_chipcommon.h b/include/linux/ssb/ssb_driver_chipcommon.h index a08d693d8324..1a6b0045b06b 100644 --- a/include/linux/ssb/ssb_driver_chipcommon.h +++ b/include/linux/ssb/ssb_driver_chipcommon.h @@ -8,7 +8,7 @@ * gpio interface, extbus, and support for serial and parallel flashes. * * Copyright 2005, Broadcom Corporation - * Copyright 2006, Michael Buesch + * Copyright 2006, Michael Buesch * * Licensed under the GPL version 2. See COPYING for details. */ -- cgit v1.2.3 From 43dd61c9a09bd413e837df829e6bfb42159be52a Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 7 Jul 2011 11:09:22 -0400 Subject: ftrace: Fix regression of :mod:module function enabling The new code that allows different utilities to pick and choose what functions they trace broke the :mod: hook that allows users to trace only functions of a particular module. The reason is that the :mod: hook bypasses the hash that is setup to allow individual users to trace their own functions and uses the global hash directly. But if the global hash has not been set up, it will cause a bug: echo '*:mod:radeon' > /sys/kernel/debug/set_ftrace_filter produces: [drm:drm_mode_getfb] *ERROR* invalid framebuffer id [drm:radeon_crtc_page_flip] *ERROR* failed to reserve new rbo buffer before flip BUG: unable to handle kernel paging request at ffffffff8160ec90 IP: [] add_hash_entry+0x66/0xd0 PGD 1a05067 PUD 1a09063 PMD 80000000016001e1 Oops: 0003 [#1] SMP Jul 7 04:02:28 phyllis kernel: [55303.858604] CPU 1 Modules linked in: cryptd aes_x86_64 aes_generic binfmt_misc rfcomm bnep ip6table_filter hid radeon r8169 ahci libahci mii ttm drm_kms_helper drm video i2c_algo_bit intel_agp intel_gtt Pid: 10344, comm: bash Tainted: G WC 3.0.0-rc5 #1 Dell Inc. Inspiron N5010/0YXXJJ RIP: 0010:[] [] add_hash_entry+0x66/0xd0 RSP: 0018:ffff88003a96bda8 EFLAGS: 00010246 RAX: ffff8801301735c0 RBX: ffffffff8160ec80 RCX: 0000000000306ee0 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff880137c92940 RBP: ffff88003a96bdb8 R08: ffff880137c95680 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000000 R12: ffffffff81c9df78 R13: ffff8801153d1000 R14: 0000000000000000 R15: 0000000000000000 FS: 00007f329c18a700(0000) GS:ffff880137c80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffff8160ec90 CR3: 000000003002b000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process bash (pid: 10344, threadinfo ffff88003a96a000, task ffff88012fcfc470) Stack: 0000000000000fd0 00000000000000fc ffff88003a96be38 ffffffff810d92f5 ffff88011c4c4e00 ffff880000000000 000000000b69f4d0 ffffffff8160ec80 ffff8800300e6f06 0000000081130295 0000000000000282 ffff8800300e6f00 Call Trace: [] match_records+0x155/0x1b0 [] ftrace_mod_callback+0xbc/0x100 [] ftrace_regex_write+0x16f/0x210 [] ftrace_filter_write+0xf/0x20 [] vfs_write+0xc8/0x190 [] sys_write+0x51/0x90 [] system_call_fastpath+0x16/0x1b Code: 48 8b 33 31 d2 48 85 f6 75 33 49 89 d4 4c 03 63 08 49 8b 14 24 48 85 d2 48 89 10 74 04 48 89 42 08 49 89 04 24 4c 89 60 08 31 d2 RIP [] add_hash_entry+0x66/0xd0 RSP CR2: ffffffff8160ec90 ---[ end trace a5d031828efdd88e ]--- Reported-by: Brian Marete Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 9d88e1cb5dbb..ed0eb5254d1c 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -123,7 +123,8 @@ stack_trace_sysctl(struct ctl_table *table, int write, struct ftrace_func_command { struct list_head list; char *name; - int (*func)(char *func, char *cmd, + int (*func)(struct ftrace_hash *hash, + char *func, char *cmd, char *params, int enable); }; -- cgit v1.2.3 From 659fb32d1b67476f4ade25e9ea0e2642a5b9c4b5 Mon Sep 17 00:00:00 2001 From: Simon Guinot Date: Wed, 6 Jul 2011 12:41:31 -0400 Subject: genirq: replace irq_gc_ack() with {set,clr}_bit variants (fwd) This fixes a regression introduced by e59347a "arm: orion: Use generic irq chip". Depending on the device, interrupts acknowledgement is done by setting or by clearing a dedicated register. Replace irq_gc_ack() with some {set,clr}_bit variants allows to handle both cases. Note that this patch affects the following SoCs: Davinci, Samsung and Orion. Except for this last, the change is minor: irq_gc_ack() is just renamed into irq_gc_ack_set_bit(). For the Orion SoCs, the edge GPIO interrupts support is currently broken. irq_gc_ack() try to acknowledge a such interrupt by setting the corresponding cause register bit. The Orion GPIO device expect the opposite. To fix this issue, the irq_gc_ack_clr_bit() variant is used. Tested on Network Space v2. Reported-by: Joey Oravec Signed-off-by: Simon Guinot Signed-off-by: Arnd Bergmann --- include/linux/irq.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 8b4538446636..baa397eb9c33 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -676,7 +676,8 @@ void irq_gc_mask_disable_reg(struct irq_data *d); void irq_gc_mask_set_bit(struct irq_data *d); void irq_gc_mask_clr_bit(struct irq_data *d); void irq_gc_unmask_enable_reg(struct irq_data *d); -void irq_gc_ack(struct irq_data *d); +void irq_gc_ack_set_bit(struct irq_data *d); +void irq_gc_ack_clr_bit(struct irq_data *d); void irq_gc_mask_disable_reg_and_ack(struct irq_data *d); void irq_gc_eoi(struct irq_data *d); int irq_gc_set_wake(struct irq_data *d, unsigned int on); -- cgit v1.2.3 From 90810645f78f894acfb04b3768e8a7d45f2b303a Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 23 Jun 2011 09:36:12 -0500 Subject: slab allocators: Provide generic description of alignment defines Provide description for alignment defines. Acked-by: David Rientjes Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slab.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 646a639a4aae..573c809c33d9 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -133,12 +133,22 @@ unsigned int kmem_cache_size(struct kmem_cache *); #define KMALLOC_MAX_SIZE (1UL << KMALLOC_SHIFT_HIGH) #define KMALLOC_MAX_ORDER (KMALLOC_SHIFT_HIGH - PAGE_SHIFT) +/* + * Some archs want to perform DMA into kmalloc caches and need a guaranteed + * alignment larger than the alignment of a 64-bit integer. + * Setting ARCH_KMALLOC_MINALIGN in arch headers allows that. + */ #ifdef ARCH_DMA_MINALIGN #define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN #else #define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) #endif +/* + * Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment. + * Intended for arches that get misalignment faults even for 64 bit integer + * aligned buffers. + */ #ifndef ARCH_SLAB_MINALIGN #define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) #endif -- cgit v1.2.3 From d18a90dd85f8243ed20cdadb6d8a37d595df456d Mon Sep 17 00:00:00 2001 From: Ben Greear Date: Thu, 7 Jul 2011 11:36:37 -0700 Subject: slub: Add method to verify memory is not freed This is for tracking down suspect memory usage. Acked-by: Christoph Lameter Signed-off-by: Ben Greear Signed-off-by: Pekka Enberg --- include/linux/slub_def.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index fd4fdc72bc8c..4b35c06dfbc5 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -218,6 +218,19 @@ kmalloc_order(size_t size, gfp_t flags, unsigned int order) return ret; } +/** + * Calling this on allocated memory will check that the memory + * is expected to be in use, and print warnings if not. + */ +#ifdef CONFIG_SLUB_DEBUG +extern bool verify_mem_not_deleted(const void *x); +#else +static inline bool verify_mem_not_deleted(const void *x) +{ + return true; +} +#endif + #ifdef CONFIG_TRACING extern void * kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size); -- cgit v1.2.3 From ea6bd8ee1a2ccdffc38b2b1fcfe941addfafaade Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 6 Jul 2011 09:46:18 -0500 Subject: SLUB: Fix build breakage in linux/mm_types.h On Wed, 6 Jul 2011, Jonathan Cameron wrote: > Getting: > > CHK include/linux/version.h > CHK include/generated/utsrelease.h > make[1]: `include/generated/mach-types.h' is up to date. > CC arch/arm/kernel/asm-offsets.s > In file included from include/linux/sched.h:64:0, > from arch/arm/kernel/asm-offsets.c:13: > include/linux/mm_types.h:74:15: error: duplicate member '_count' > make[1]: *** [arch/arm/kernel/asm-offsets.s] Error 1 > make: *** [prepare0] Error 2 > > Issue looks to have been introduced by > > mm: Rearrange struct page > > fc9bb8c768abe7ae10861c3510e01a95f98d5933 > > Guessing it's a known issue, but just thought I'd flag it up in case > it's something very specific about my build. > > gcc-2.6 armv7a > > Reverting that patch works, but given I don't know the history, I'm > not proposing doing that in general! Well _count exists in two unionized structs but always has the same offset within the larger struct. Maybe ARM creates different offsets there for some reason? The following is a patch to restructure the union / structs combo in such a way that only a single definition of _count Reported-by: Jonathan Cameron Tested-by: Piotr Hosowicz Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/mm_types.h | 25 ++++++++++--------------- 1 file changed, 10 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 3d76a433d52f..6dc6413f5deb 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -49,32 +49,27 @@ struct page { * see PAGE_MAPPING_ANON below. */ /* Second double word */ - union { - struct { + struct { + union { pgoff_t index; /* Our offset within mapping. */ + void *freelist; /* slub first free object */ + }; + + union { atomic_t _mapcount; /* Count of ptes mapped in mms, * to show when page is mapped * & limit reverse map searches. */ - atomic_t _count; /* Usage count, see below. */ - }; - struct { /* SLUB cmpxchg_double area */ - void *freelist; - union { - unsigned long counters; - struct { + /* Used for cmpxchg_double in slub */ + unsigned long counters; + struct { unsigned inuse:16; unsigned objects:15; unsigned frozen:1; - /* - * Kernel may make use of this field even when slub - * uses the rest of the double word! - */ - atomic_t _count; - }; }; }; + atomic_t _count; /* Usage count, see below. */ }; /* Third double word block */ -- cgit v1.2.3 From c902ce1bfb40d8b049bd2319b388b4b68b04bc27 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 7 Jul 2011 12:19:48 +0100 Subject: FS-Cache: Add a helper to bulk uncache pages on an inode Add an FS-Cache helper to bulk uncache pages on an inode. This will only work for the circumstance where the pages in the cache correspond 1:1 with the pages attached to an inode's page cache. This is required for CIFS and NFS: When disabling inode cookie, we were returning the cookie and setting cifsi->fscache to NULL but failed to invalidate any previously mapped pages. This resulted in "Bad page state" errors and manifested in other kind of errors when running fsstress. Fix it by uncaching mapped pages when we disable the inode cookie. This patch should fix the following oops and "Bad page state" errors seen during fsstress testing. ------------[ cut here ]------------ kernel BUG at fs/cachefiles/namei.c:201! invalid opcode: 0000 [#1] SMP Pid: 5, comm: kworker/u:0 Not tainted 2.6.38.7-30.fc15.x86_64 #1 Bochs Bochs RIP: 0010: cachefiles_walk_to_object+0x436/0x745 [cachefiles] RSP: 0018:ffff88002ce6dd00 EFLAGS: 00010282 RAX: ffff88002ef165f0 RBX: ffff88001811f500 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000100 RDI: 0000000000000282 RBP: ffff88002ce6dda0 R08: 0000000000000100 R09: ffffffff81b3a300 R10: 0000ffff00066c0a R11: 0000000000000003 R12: ffff88002ae54840 R13: ffff88002ae54840 R14: ffff880029c29c00 R15: ffff88001811f4b0 FS: 00007f394dd32720(0000) GS:ffff88002ef00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 00007fffcb62ddf8 CR3: 000000001825f000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process kworker/u:0 (pid: 5, threadinfo ffff88002ce6c000, task ffff88002ce55cc0) Stack: 0000000000000246 ffff88002ce55cc0 ffff88002ce6dd58 ffff88001815dc00 ffff8800185246c0 ffff88001811f618 ffff880029c29d18 ffff88001811f380 ffff88002ce6dd50 ffffffff814757e4 ffff88002ce6dda0 ffffffff8106ac56 Call Trace: cachefiles_lookup_object+0x78/0xd4 [cachefiles] fscache_lookup_object+0x131/0x16d [fscache] fscache_object_work_func+0x1bc/0x669 [fscache] process_one_work+0x186/0x298 worker_thread+0xda/0x15d kthread+0x84/0x8c kernel_thread_helper+0x4/0x10 RIP cachefiles_walk_to_object+0x436/0x745 [cachefiles] ---[ end trace 1d481c9af1804caa ]--- I tested the uncaching by the following means: (1) Create a big file on my NFS server (104857600 bytes). (2) Read the file into the cache with md5sum on the NFS client. Look in /proc/fs/fscache/stats: Pages : mrk=25601 unc=0 (3) Open the file for read/write ("bash 5<>/warthog/bigfile"). Look in proc again: Pages : mrk=25601 unc=25601 Reported-by: Jeff Layton Signed-off-by: David Howells Reviewed-and-Tested-by: Suresh Jayaraman cc: stable@kernel.org Signed-off-by: Linus Torvalds --- include/linux/fscache.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 7c4d72f5581f..9ec20dec3353 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -204,6 +204,8 @@ extern bool __fscache_check_page_write(struct fscache_cookie *, struct page *); extern void __fscache_wait_on_page_write(struct fscache_cookie *, struct page *); extern bool __fscache_maybe_release_page(struct fscache_cookie *, struct page *, gfp_t); +extern void __fscache_uncache_all_inode_pages(struct fscache_cookie *, + struct inode *); /** * fscache_register_netfs - Register a filesystem as desiring caching services @@ -643,4 +645,23 @@ bool fscache_maybe_release_page(struct fscache_cookie *cookie, return false; } +/** + * fscache_uncache_all_inode_pages - Uncache all an inode's pages + * @cookie: The cookie representing the inode's cache object. + * @inode: The inode to uncache pages from. + * + * Uncache all the pages in an inode that are marked PG_fscache, assuming them + * to be associated with the given cookie. + * + * This function may sleep. It will wait for pages that are being written out + * and will wait whilst the PG_fscache mark is removed by the cache. + */ +static inline +void fscache_uncache_all_inode_pages(struct fscache_cookie *cookie, + struct inode *inode) +{ + if (fscache_cookie_valid(cookie)) + __fscache_uncache_all_inode_pages(cookie, inode); +} + #endif /* _LINUX_FSCACHE_H */ -- cgit v1.2.3 From 6db7199407ca56f55bc0832fb124e1ad216ea57b Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Thu, 9 Jun 2011 15:52:06 -0500 Subject: drivers/virt: introduce Freescale hypervisor management driver Add the drivers/virt directory, which houses drivers that support virtualization environments, and add the Freescale hypervisor management driver. The Freescale hypervisor management driver provides several services to drivers and applications related to the Freescale hypervisor: 1. An ioctl interface for querying and managing partitions 2. A file interface to reading incoming doorbells 3. An interrupt handler for shutting down the partition upon receiving the shutdown doorbell from a manager partition 4. A kernel interface for receiving callbacks when a managed partition shuts down. Signed-off-by: Timur Tabi Acked-by: Arnd Bergmann Signed-off-by: Kumar Gala --- include/linux/Kbuild | 1 + include/linux/fsl_hypervisor.h | 241 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 242 insertions(+) create mode 100644 include/linux/fsl_hypervisor.h (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 01f636275057..619b5657af77 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -135,6 +135,7 @@ header-y += firewire-cdev.h header-y += firewire-constants.h header-y += flat.h header-y += fs.h +header-y += fsl_hypervisor.h header-y += fuse.h header-y += futex.h header-y += gameport.h diff --git a/include/linux/fsl_hypervisor.h b/include/linux/fsl_hypervisor.h new file mode 100644 index 000000000000..1cebaeeeef57 --- /dev/null +++ b/include/linux/fsl_hypervisor.h @@ -0,0 +1,241 @@ +/* + * Freescale hypervisor ioctl and kernel interface + * + * Copyright (C) 2008-2011 Freescale Semiconductor, Inc. + * Author: Timur Tabi + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * This software is provided by Freescale Semiconductor "as is" and any + * express or implied warranties, including, but not limited to, the implied + * warranties of merchantability and fitness for a particular purpose are + * disclaimed. In no event shall Freescale Semiconductor be liable for any + * direct, indirect, incidental, special, exemplary, or consequential damages + * (including, but not limited to, procurement of substitute goods or services; + * loss of use, data, or profits; or business interruption) however caused and + * on any theory of liability, whether in contract, strict liability, or tort + * (including negligence or otherwise) arising in any way out of the use of this + * software, even if advised of the possibility of such damage. + * + * This file is used by the Freescale hypervisor management driver. It can + * also be included by applications that need to communicate with the driver + * via the ioctl interface. + */ + +#ifndef FSL_HYPERVISOR_H +#define FSL_HYPERVISOR_H + +#include + +/** + * struct fsl_hv_ioctl_restart - restart a partition + * @ret: return error code from the hypervisor + * @partition: the ID of the partition to restart, or -1 for the + * calling partition + * + * Used by FSL_HV_IOCTL_PARTITION_RESTART + */ +struct fsl_hv_ioctl_restart { + __u32 ret; + __u32 partition; +}; + +/** + * struct fsl_hv_ioctl_status - get a partition's status + * @ret: return error code from the hypervisor + * @partition: the ID of the partition to query, or -1 for the + * calling partition + * @status: The returned status of the partition + * + * Used by FSL_HV_IOCTL_PARTITION_GET_STATUS + * + * Values of 'status': + * 0 = Stopped + * 1 = Running + * 2 = Starting + * 3 = Stopping + */ +struct fsl_hv_ioctl_status { + __u32 ret; + __u32 partition; + __u32 status; +}; + +/** + * struct fsl_hv_ioctl_start - start a partition + * @ret: return error code from the hypervisor + * @partition: the ID of the partition to control + * @entry_point: The offset within the guest IMA to start execution + * @load: If non-zero, reload the partition's images before starting + * + * Used by FSL_HV_IOCTL_PARTITION_START + */ +struct fsl_hv_ioctl_start { + __u32 ret; + __u32 partition; + __u32 entry_point; + __u32 load; +}; + +/** + * struct fsl_hv_ioctl_stop - stop a partition + * @ret: return error code from the hypervisor + * @partition: the ID of the partition to stop, or -1 for the calling + * partition + * + * Used by FSL_HV_IOCTL_PARTITION_STOP + */ +struct fsl_hv_ioctl_stop { + __u32 ret; + __u32 partition; +}; + +/** + * struct fsl_hv_ioctl_memcpy - copy memory between partitions + * @ret: return error code from the hypervisor + * @source: the partition ID of the source partition, or -1 for this + * partition + * @target: the partition ID of the target partition, or -1 for this + * partition + * @reserved: reserved, must be set to 0 + * @local_addr: user-space virtual address of a buffer in the local + * partition + * @remote_addr: guest physical address of a buffer in the + * remote partition + * @count: the number of bytes to copy. Both the local and remote + * buffers must be at least 'count' bytes long + * + * Used by FSL_HV_IOCTL_MEMCPY + * + * The 'local' partition is the partition that calls this ioctl. The + * 'remote' partition is a different partition. The data is copied from + * the 'source' paritition' to the 'target' partition. + * + * The buffer in the remote partition must be guest physically + * contiguous. + * + * This ioctl does not support copying memory between two remote + * partitions or within the same partition, so either 'source' or + * 'target' (but not both) must be -1. In other words, either + * + * source == local and target == remote + * or + * source == remote and target == local + */ +struct fsl_hv_ioctl_memcpy { + __u32 ret; + __u32 source; + __u32 target; + __u32 reserved; /* padding to ensure local_vaddr is aligned */ + __u64 local_vaddr; + __u64 remote_paddr; + __u64 count; +}; + +/** + * struct fsl_hv_ioctl_doorbell - ring a doorbell + * @ret: return error code from the hypervisor + * @doorbell: the handle of the doorbell to ring doorbell + * + * Used by FSL_HV_IOCTL_DOORBELL + */ +struct fsl_hv_ioctl_doorbell { + __u32 ret; + __u32 doorbell; +}; + +/** + * struct fsl_hv_ioctl_prop - get/set a device tree property + * @ret: return error code from the hypervisor + * @handle: handle of partition whose tree to access + * @path: virtual address of path name of node to access + * @propname: virtual address of name of property to access + * @propval: virtual address of property data buffer + * @proplen: Size of property data buffer + * @reserved: reserved, must be set to 0 + * + * Used by FSL_HV_IOCTL_DOORBELL + */ +struct fsl_hv_ioctl_prop { + __u32 ret; + __u32 handle; + __u64 path; + __u64 propname; + __u64 propval; + __u32 proplen; + __u32 reserved; /* padding to ensure structure is aligned */ +}; + +/* The ioctl type, documented in ioctl-number.txt */ +#define FSL_HV_IOCTL_TYPE 0xAF + +/* Restart another partition */ +#define FSL_HV_IOCTL_PARTITION_RESTART \ + _IOWR(FSL_HV_IOCTL_TYPE, 1, struct fsl_hv_ioctl_restart) + +/* Get a partition's status */ +#define FSL_HV_IOCTL_PARTITION_GET_STATUS \ + _IOWR(FSL_HV_IOCTL_TYPE, 2, struct fsl_hv_ioctl_status) + +/* Boot another partition */ +#define FSL_HV_IOCTL_PARTITION_START \ + _IOWR(FSL_HV_IOCTL_TYPE, 3, struct fsl_hv_ioctl_start) + +/* Stop this or another partition */ +#define FSL_HV_IOCTL_PARTITION_STOP \ + _IOWR(FSL_HV_IOCTL_TYPE, 4, struct fsl_hv_ioctl_stop) + +/* Copy data from one partition to another */ +#define FSL_HV_IOCTL_MEMCPY \ + _IOWR(FSL_HV_IOCTL_TYPE, 5, struct fsl_hv_ioctl_memcpy) + +/* Ring a doorbell */ +#define FSL_HV_IOCTL_DOORBELL \ + _IOWR(FSL_HV_IOCTL_TYPE, 6, struct fsl_hv_ioctl_doorbell) + +/* Get a property from another guest's device tree */ +#define FSL_HV_IOCTL_GETPROP \ + _IOWR(FSL_HV_IOCTL_TYPE, 7, struct fsl_hv_ioctl_prop) + +/* Set a property in another guest's device tree */ +#define FSL_HV_IOCTL_SETPROP \ + _IOWR(FSL_HV_IOCTL_TYPE, 8, struct fsl_hv_ioctl_prop) + +#ifdef __KERNEL__ + +/** + * fsl_hv_event_register() - register a callback for failover events + * @nb: pointer to caller-supplied notifier_block structure + * + * This function is called by device drivers to register their callback + * functions for fail-over events. + * + * The caller should allocate a notifier_block object and initialize the + * 'priority' and 'notifier_call' fields. + */ +int fsl_hv_failover_register(struct notifier_block *nb); + +/** + * fsl_hv_event_unregister() - unregister a callback for failover events + * @nb: the same 'nb' used in previous fsl_hv_failover_register call + */ +int fsl_hv_failover_unregister(struct notifier_block *nb); + +#endif + +#endif -- cgit v1.2.3 From a77ce8167cc1d0370fcb1d79b367d62e050cb2b0 Mon Sep 17 00:00:00 2001 From: Kumar Gala Date: Fri, 10 Jun 2011 01:52:57 -0500 Subject: driver core: Add ability for arch code to setup pdev_archdata On some architectures we need to setup pdev_archdata before we add the device. Waiting til a bus_notifier is too late since we might need the pdev_archdata in the bus notifier. One example is setting up of dma_mask pointers such that it can be used in a bus_notifier. We add weak noop version of arch_setup_pdev_archdata() and allow the arch code to override with access the full definitions of struct device, struct platform_device, and struct pdev_archdata. Acked-by: Greg Kroah-Hartman Signed-off-by: Kumar Gala --- include/linux/platform_device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index ede1a80e3358..27bb05aae70d 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -42,6 +42,7 @@ extern void platform_device_unregister(struct platform_device *); extern struct bus_type platform_bus_type; extern struct device platform_bus; +extern void arch_setup_pdev_archdata(struct platform_device *); extern struct resource *platform_get_resource(struct platform_device *, unsigned int, unsigned int); extern int platform_get_irq(struct platform_device *, unsigned int); extern struct resource *platform_get_resource_byname(struct platform_device *, unsigned int, const char *); -- cgit v1.2.3 From 55c022bbddb2c056b5dff1bd1b1758d31b6d64c9 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Fri, 8 Jul 2011 08:19:20 +0200 Subject: block: avoid building too big plug list When I test fio script with big I/O depth, I found the total throughput drops compared to some relative small I/O depth. The reason is the thread accumulates big requests in its plug list and causes some delays (surely this depends on CPU speed). I thought we'd better have a threshold for requests. When a threshold reaches, this means there is no request merge and queue lock contention isn't severe when pushing per-task requests to queue, so the main advantages of blk plug don't exist. We can force a plug list flush in this case. With this, my test throughput actually increases and almost equals to small I/O depth. Another side effect is irq off time decreases in blk_flush_plug_list() for big I/O depth. The BLK_MAX_REQUEST_COUNT is choosen arbitarily, but 16 is efficiently to reduce lock contention to me. But I'm open here, 32 is ok in my test too. Signed-off-by: Shaohua Li Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 36f2e2b99ae3..92edb9601242 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -862,7 +862,10 @@ struct blk_plug { struct list_head list; struct list_head cb_list; unsigned int should_sort; + unsigned int count; }; +#define BLK_MAX_REQUEST_COUNT 16 + struct blk_plug_cb { struct list_head list; void (*callback)(struct blk_plug_cb *); -- cgit v1.2.3 From 316cc67d5e03801a5ee4ac660a4dfe9e02aed475 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Fri, 8 Jul 2011 08:19:21 +0200 Subject: block: document blk_plug list access I'm often confused why not disable preempt when changing blk_plug list. It would be better to add comments here in case others have the similar concerns. Signed-off-by: Shaohua Li Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 92edb9601242..6dcea6885a5d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -857,6 +857,12 @@ struct request_queue *blk_alloc_queue(gfp_t); struct request_queue *blk_alloc_queue_node(gfp_t, int); extern void blk_put_queue(struct request_queue *); +/* + * Note: Code in between changing the blk_plug list/cb_list or element of such + * lists is preemptable, but such code can't do sleep (or be very careful), + * otherwise data is corrupted. For details, please check schedule() where + * blk_schedule_flush_plug() is called. + */ struct blk_plug { unsigned long magic; struct list_head list; -- cgit v1.2.3 From 5154e9f126c1d2ee8f5f93d9954f83d82b2d5e64 Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Fri, 8 Jul 2011 14:51:27 +0900 Subject: usb: gadget: r8a66597-udc: Make BUSWAIT configurable through platform data BUSWAIT is a 4-bit-wide value that controls the number of access waits from the CPU to on-chip USB module. b'0000 inserts 0 wait (2 access cycles) and b'1111 inserts 15 waits (17 access cycles, hardware initial value), respectively. BUSWAIT value depends on peripheral clock frequency supplied to on-chip of each CPU, hence should be configurable through platform data. Note that this patch assumes that b'0000 (0 wait, 2 access cycles) is rerely used and considered as invalid. If valid 'buswait' data is not provided by platform, initial b'1111 (15 waits, 17 access cycles) will be applied as a safe default. Signed-off-by: Yoshihiro Shimoda Signed-off-by: Felipe Balbi --- include/linux/usb/r8a66597.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/r8a66597.h b/include/linux/usb/r8a66597.h index 26d216734057..6e1bfaedb6ca 100644 --- a/include/linux/usb/r8a66597.h +++ b/include/linux/usb/r8a66597.h @@ -31,6 +31,9 @@ struct r8a66597_platdata { /* This callback can control port power instead of DVSTCTR register. */ void (*port_power)(int port, int power); + /* This parameter is for BUSWAIT */ + u16 buswait; + /* set one = on chip controller, set zero = external controller */ unsigned on_chip:1; -- cgit v1.2.3 From 732375c6a5a4cc825b676c922d547aba96b8ce15 Mon Sep 17 00:00:00 2001 From: Dima Zavin Date: Thu, 7 Jul 2011 17:27:59 -0700 Subject: plist: Remove the need to supply locks to plist heads This was legacy code brought over from the RT tree and is no longer necessary. Signed-off-by: Dima Zavin Acked-by: Thomas Gleixner Cc: Daniel Walker Cc: Steven Rostedt Cc: Peter Zijlstra Cc: Andi Kleen Cc: Lai Jiangshan Link: http://lkml.kernel.org/r/1310084879-10351-2-git-send-email-dima@android.com Signed-off-by: Ingo Molnar --- include/linux/plist.h | 55 +++---------------------------------------------- include/linux/rtmutex.h | 4 ++-- 2 files changed, 5 insertions(+), 54 deletions(-) (limited to 'include/linux') diff --git a/include/linux/plist.h b/include/linux/plist.h index c9b9f322c8d8..aa0fb390bd29 100644 --- a/include/linux/plist.h +++ b/include/linux/plist.h @@ -77,14 +77,9 @@ #include #include -#include struct plist_head { struct list_head node_list; -#ifdef CONFIG_DEBUG_PI_LIST - raw_spinlock_t *rawlock; - spinlock_t *spinlock; -#endif }; struct plist_node { @@ -93,37 +88,13 @@ struct plist_node { struct list_head node_list; }; -#ifdef CONFIG_DEBUG_PI_LIST -# define PLIST_HEAD_LOCK_INIT(_lock) .spinlock = _lock -# define PLIST_HEAD_LOCK_INIT_RAW(_lock) .rawlock = _lock -#else -# define PLIST_HEAD_LOCK_INIT(_lock) -# define PLIST_HEAD_LOCK_INIT_RAW(_lock) -#endif - -#define _PLIST_HEAD_INIT(head) \ - .node_list = LIST_HEAD_INIT((head).node_list) - /** * PLIST_HEAD_INIT - static struct plist_head initializer * @head: struct plist_head variable name - * @_lock: lock to initialize for this list - */ -#define PLIST_HEAD_INIT(head, _lock) \ -{ \ - _PLIST_HEAD_INIT(head), \ - PLIST_HEAD_LOCK_INIT(&(_lock)) \ -} - -/** - * PLIST_HEAD_INIT_RAW - static struct plist_head initializer - * @head: struct plist_head variable name - * @_lock: lock to initialize for this list */ -#define PLIST_HEAD_INIT_RAW(head, _lock) \ +#define PLIST_HEAD_INIT(head) \ { \ - _PLIST_HEAD_INIT(head), \ - PLIST_HEAD_LOCK_INIT_RAW(&(_lock)) \ + .node_list = LIST_HEAD_INIT((head).node_list) \ } /** @@ -141,31 +112,11 @@ struct plist_node { /** * plist_head_init - dynamic struct plist_head initializer * @head: &struct plist_head pointer - * @lock: spinlock protecting the list (debugging) */ static inline void -plist_head_init(struct plist_head *head, spinlock_t *lock) +plist_head_init(struct plist_head *head) { INIT_LIST_HEAD(&head->node_list); -#ifdef CONFIG_DEBUG_PI_LIST - head->spinlock = lock; - head->rawlock = NULL; -#endif -} - -/** - * plist_head_init_raw - dynamic struct plist_head initializer - * @head: &struct plist_head pointer - * @lock: raw_spinlock protecting the list (debugging) - */ -static inline void -plist_head_init_raw(struct plist_head *head, raw_spinlock_t *lock) -{ - INIT_LIST_HEAD(&head->node_list); -#ifdef CONFIG_DEBUG_PI_LIST - head->rawlock = lock; - head->spinlock = NULL; -#endif } /** diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index 8d522ffeda33..de17134244f3 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -66,7 +66,7 @@ struct hrtimer_sleeper; #define __RT_MUTEX_INITIALIZER(mutexname) \ { .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \ - , .wait_list = PLIST_HEAD_INIT_RAW(mutexname.wait_list, mutexname.wait_lock) \ + , .wait_list = PLIST_HEAD_INIT(mutexname.wait_list) \ , .owner = NULL \ __DEBUG_RT_MUTEX_INITIALIZER(mutexname)} @@ -100,7 +100,7 @@ extern void rt_mutex_unlock(struct rt_mutex *lock); #ifdef CONFIG_RT_MUTEXES # define INIT_RT_MUTEXES(tsk) \ - .pi_waiters = PLIST_HEAD_INIT(tsk.pi_waiters, tsk.pi_lock), \ + .pi_waiters = PLIST_HEAD_INIT(tsk.pi_waiters), \ INIT_RT_MUTEX_DEBUG(tsk) #else # define INIT_RT_MUTEXES(tsk) -- cgit v1.2.3 From 58ddafae2d7102d8f493840cb7aca0b4b2326b2a Mon Sep 17 00:00:00 2001 From: Rhyland Klein Date: Tue, 24 May 2011 12:05:59 -0700 Subject: bq20z75: Add support for external notification Adding support for external power change notification. One problem found is that there is a lag time before the sensor will return a new status. To ensure that we only fire off the power_supply_changed event when the status returned from the sensor is actually different, we delay sending the the notification, and instead poll on it looking for a change. The amount of time to poll is configurable via platform data. Signed-off-by: Rhyland Klein Signed-off-by: Anton Vorontsov --- include/linux/power/bq20z75.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/power/bq20z75.h b/include/linux/power/bq20z75.h index b0843b68af92..1398eb004e83 100644 --- a/include/linux/power/bq20z75.h +++ b/include/linux/power/bq20z75.h @@ -29,11 +29,14 @@ * @battery_detect: GPIO which is used to detect battery presence * @battery_detect_present: gpio state when battery is present (0 / 1) * @i2c_retry_count: # of times to retry on i2c IO failure + * @poll_retry_count: # of times to retry looking for new status after + * external change notification */ struct bq20z75_platform_data { int battery_detect; int battery_detect_present; int i2c_retry_count; + int poll_retry_count; }; #endif -- cgit v1.2.3 From 149c077b4bd746eca2eeb241e55456eb4882b259 Mon Sep 17 00:00:00 2001 From: Donggeun Kim Date: Wed, 22 Jun 2011 19:40:06 +0900 Subject: power_supply: Add charger driver for MAX8997/8966 MAX8997/8966 chip is a multi-function device which includes PMIC, RTC, Fuel Gauge, MUIC, Haptic, Flash control, and Battery charging control. The driver for it is located at drivers/mfd. This patch supports battery charging control of MAX8997/8966 chip and provides power supply class information to userspace. Signed-off-by: Donggeun Kim Signed-off-by: MyungJoo Ham Signed-off-by: KyungMin Park Acked-by: Samuel Ortiz Signed-off-by: Anton Vorontsov --- include/linux/mfd/max8997.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/max8997.h b/include/linux/mfd/max8997.h index 60931d089422..0bbd13dbe336 100644 --- a/include/linux/mfd/max8997.h +++ b/include/linux/mfd/max8997.h @@ -107,11 +107,16 @@ struct max8997_platform_data { unsigned int buck5_voltage[8]; bool buck5_gpiodvs; + /* ---- Charger control ---- */ + /* eoc stands for 'end of charge' */ + int eoc_mA; /* 50 ~ 200mA by 10mA step */ + /* charge Full Timeout */ + int timeout; /* 0 (no timeout), 5, 6, 7 hours */ + /* MUIC: Not implemented */ /* HAPTIC: Not implemented */ /* RTC: Not implemented */ /* Flash: Not implemented */ - /* Charger control: Not implemented */ }; #endif /* __LINUX_MFD_MAX8998_H */ -- cgit v1.2.3 From bb4ce9708785f40849f1a64931e6cc3b26171201 Mon Sep 17 00:00:00 2001 From: Donggeun Kim Date: Fri, 24 Jun 2011 19:04:18 +0900 Subject: power_supply: Add charger driver for MAX8998/LP3974 This patch supports power supply APIs for MAX8998/LP3974. Signed-off-by: Donggeun Kim Signed-off-by: MyungJoo Ham Signed-off-by: KyungMin Park Acked-by: Samuel Ortiz Signed-off-by: Anton Vorontsov --- include/linux/mfd/max8998.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/max8998.h b/include/linux/mfd/max8998.h index 61daa167b576..f4f0dfa4698a 100644 --- a/include/linux/mfd/max8998.h +++ b/include/linux/mfd/max8998.h @@ -87,6 +87,15 @@ struct max8998_regulator_data { * @wakeup: Allow to wake up from suspend * @rtc_delay: LP3974 RTC chip bug that requires delay after a register * write before reading it. + * @eoc: End of Charge Level in percent: 10% ~ 45% by 5% step + * If it equals 0, leave it unchanged. + * Otherwise, it is a invalid value. + * @restart: Restart Level in mV: 100, 150, 200, and -1 for disable. + * If it equals 0, leave it unchanged. + * Otherwise, it is a invalid value. + * @timeout: Full Timeout in hours: 5, 6, 7, and -1 for disable. + * If it equals 0, leave it unchanged. + * Otherwise, leave it unchanged. */ struct max8998_platform_data { struct max8998_regulator_data *regulators; @@ -107,6 +116,9 @@ struct max8998_platform_data { int buck2_default_idx; bool wakeup; bool rtc_delay; + int eoc; + int restart; + int timeout; }; #endif /* __LINUX_MFD_MAX8998_H */ -- cgit v1.2.3 From 086ef502c202503a19a491838098157cdab6238e Mon Sep 17 00:00:00 2001 From: Donggeun Kim Date: Thu, 30 Jun 2011 18:07:41 +0900 Subject: power_supply: MAX17042: Support additional properties This patch supports additional properties (PRESENT, CYCLE_COUNT, VOLTAGE_MAX, VOLTAGE_MIN_DESIGN, CURRENT_NOW, CURRENT_AVG, CHARGE_FULL, and TEMP). Plus, initialization code for registers is added. Signed-off-by: Donggeun Kim Signed-off-by: MyungJoo Ham Signed-off-by: KyungMin Park Signed-off-by: Anton Vorontsov --- include/linux/power/max17042_battery.h | 91 ++++++++++++++++++++++++++++++++++ 1 file changed, 91 insertions(+) (limited to 'include/linux') diff --git a/include/linux/power/max17042_battery.h b/include/linux/power/max17042_battery.h index 7995deb8bfc1..fe99211fb2b8 100644 --- a/include/linux/power/max17042_battery.h +++ b/include/linux/power/max17042_battery.h @@ -23,8 +23,99 @@ #ifndef __MAX17042_BATTERY_H_ #define __MAX17042_BATTERY_H_ +#define MAX17042_STATUS_BattAbsent (1 << 3) +#define MAX17042_BATTERY_FULL (100) +#define MAX17042_DEFAULT_SNS_RESISTOR (10000) + +enum max17042_register { + MAX17042_STATUS = 0x00, + MAX17042_VALRT_Th = 0x01, + MAX17042_TALRT_Th = 0x02, + MAX17042_SALRT_Th = 0x03, + MAX17042_AtRate = 0x04, + MAX17042_RepCap = 0x05, + MAX17042_RepSOC = 0x06, + MAX17042_Age = 0x07, + MAX17042_TEMP = 0x08, + MAX17042_VCELL = 0x09, + MAX17042_Current = 0x0A, + MAX17042_AvgCurrent = 0x0B, + MAX17042_Qresidual = 0x0C, + MAX17042_SOC = 0x0D, + MAX17042_AvSOC = 0x0E, + MAX17042_RemCap = 0x0F, + MAX17402_FullCAP = 0x10, + MAX17042_TTE = 0x11, + MAX17042_V_empty = 0x12, + + MAX17042_RSLOW = 0x14, + + MAX17042_AvgTA = 0x16, + MAX17042_Cycles = 0x17, + MAX17042_DesignCap = 0x18, + MAX17042_AvgVCELL = 0x19, + MAX17042_MinMaxTemp = 0x1A, + MAX17042_MinMaxVolt = 0x1B, + MAX17042_MinMaxCurr = 0x1C, + MAX17042_CONFIG = 0x1D, + MAX17042_ICHGTerm = 0x1E, + MAX17042_AvCap = 0x1F, + MAX17042_ManName = 0x20, + MAX17042_DevName = 0x21, + MAX17042_DevChem = 0x22, + + MAX17042_TempNom = 0x24, + MAX17042_TempCold = 0x25, + MAX17042_TempHot = 0x26, + MAX17042_AIN = 0x27, + MAX17042_LearnCFG = 0x28, + MAX17042_SHFTCFG = 0x29, + MAX17042_RelaxCFG = 0x2A, + MAX17042_MiscCFG = 0x2B, + MAX17042_TGAIN = 0x2C, + MAx17042_TOFF = 0x2D, + MAX17042_CGAIN = 0x2E, + MAX17042_COFF = 0x2F, + + MAX17042_Q_empty = 0x33, + MAX17042_T_empty = 0x34, + + MAX17042_RCOMP0 = 0x38, + MAX17042_TempCo = 0x39, + MAX17042_Rx = 0x3A, + MAX17042_T_empty0 = 0x3B, + MAX17042_TaskPeriod = 0x3C, + MAX17042_FSTAT = 0x3D, + + MAX17042_SHDNTIMER = 0x3F, + + MAX17042_VFRemCap = 0x4A, + + MAX17042_QH = 0x4D, + MAX17042_QL = 0x4E, +}; + +/* + * used for setting a register to a desired value + * addr : address for a register + * data : setting value for the register + */ +struct max17042_reg_data { + u8 addr; + u16 data; +}; + struct max17042_platform_data { + struct max17042_reg_data *init_data; + int num_init_data; /* Number of enties in init_data array */ bool enable_current_sense; + + /* + * R_sns in micro-ohms. + * default 10000 (if r_sns = 0) as it is the recommended value by + * the datasheet although it can be changed by board designers. + */ + unsigned int r_sns; }; #endif /* __MAX17042_BATTERY_H_ */ -- cgit v1.2.3 From 1a84ff7564ae43dd1ea20e17f867de2700ca5b5b Mon Sep 17 00:00:00 2001 From: Luciano Coelho Date: Fri, 8 Jul 2011 11:16:16 +0300 Subject: cfg80211: return -ENOENT when stopping sched_scan while not running If we try to stop a scheduled scan while it is not running, we should return -ENOENT instead of simply ignoring the command and returning success. This is more consistent with other parts of the code. Reported-by: Johannes Berg Signed-off-by: Luciano Coelho Signed-off-by: John W. Linville --- include/linux/nl80211.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 3ec2f949bf7a..8cb025a00094 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -247,7 +247,8 @@ * passed, all channels allowed for the current regulatory domain * are used. Extra IEs can also be passed from the userspace by * using the %NL80211_ATTR_IE attribute. - * @NL80211_CMD_STOP_SCHED_SCAN: stop a scheduled scan + * @NL80211_CMD_STOP_SCHED_SCAN: stop a scheduled scan. Returns -ENOENT + * if scheduled scan is not running. * @NL80211_CMD_SCHED_SCAN_RESULTS: indicates that there are scheduled scan * results available. * @NL80211_CMD_SCHED_SCAN_STOPPED: indicates that the scheduled scan has -- cgit v1.2.3 From b98c0239204d6603b3a33bcc2b3916adaa8d4160 Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Fri, 8 Jul 2011 16:27:33 +0800 Subject: dt: add empty of_property_read_u32[_array] for non-dt The patch adds empty functions of_property_read_u32 and of_property_read_u32_array for non-dt build, so that drivers migrating to dt can save some '#ifdef CONFIG_OF'. Signed-off-by: Shawn Guo [grant.likely: Moved things around so only one new static inline is needed] [grant.likely: Added _string variant] Signed-off-by: Grant Likely --- include/linux/of.h | 29 +++++++++++++++++++++-------- 1 file changed, 21 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index b5f1c88e40a7..bd716f8908de 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -200,13 +200,6 @@ extern int of_property_read_u32_array(const struct device_node *np, u32 *out_values, size_t sz); -static inline int of_property_read_u32(const struct device_node *np, - char *propname, - u32 *out_value) -{ - return of_property_read_u32_array(np, propname, out_value, 1); -} - extern int of_property_read_string(struct device_node *np, char *propname, const char **out_string); extern int of_device_is_compatible(const struct device_node *device, @@ -241,12 +234,32 @@ extern void of_attach_node(struct device_node *); extern void of_detach_node(struct device_node *); #endif -#else +#else /* CONFIG_OF */ static inline bool of_have_populated_dt(void) { return false; } +static inline int of_property_read_u32_array(const struct device_node *np, + char *propname, u32 *out_values, size_t sz) +{ + return -ENOSYS; +} + +static inline int of_property_read_string(struct device_node *np, + char *propname, const char **out_string) +{ + return -ENOSYS; +} + #endif /* CONFIG_OF */ + +static inline int of_property_read_u32(const struct device_node *np, + char *propname, + u32 *out_value) +{ + return of_property_read_u32_array(np, propname, out_value, 1); +} + #endif /* _LINUX_OF_H */ -- cgit v1.2.3 From d8bf4ca9ca9576548628344c9725edd3786e90b1 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 8 Jul 2011 14:39:41 +0200 Subject: rcu: treewide: Do not use rcu_read_lock_held when calling rcu_dereference_check Since ca5ecddf (rcu: define __rcu address space modifier for sparse) rcu_dereference_check use rcu_read_lock_held as a part of condition automatically so callers do not have to do that as well. Signed-off-by: Michal Hocko Acked-by: Paul E. McKenney Signed-off-by: Jiri Kosina --- include/linux/cgroup.h | 1 - include/linux/cred.h | 1 - include/linux/fdtable.h | 1 - include/linux/rtnetlink.h | 3 +-- 4 files changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index ab4ac0ccb857..da7e4bc34e8c 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -539,7 +539,6 @@ static inline struct cgroup_subsys_state *cgroup_subsys_state( */ #define task_subsys_state_check(task, subsys_id, __c) \ rcu_dereference_check(task->cgroups->subsys[subsys_id], \ - rcu_read_lock_held() || \ lockdep_is_held(&task->alloc_lock) || \ cgroup_lock_is_held() || (__c)) diff --git a/include/linux/cred.h b/include/linux/cred.h index 82607992f308..f240f2fa0197 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -284,7 +284,6 @@ static inline void put_cred(const struct cred *_cred) ({ \ const struct task_struct *__t = (task); \ rcu_dereference_check(__t->real_cred, \ - rcu_read_lock_held() || \ task_is_dead(__t)); \ }) diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index 133c0ba25e30..df7e3cf82e97 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -60,7 +60,6 @@ struct files_struct { #define rcu_dereference_check_fdtable(files, fdtfd) \ (rcu_dereference_check((fdtfd), \ - rcu_read_lock_held() || \ lockdep_is_held(&(files)->file_lock) || \ atomic_read(&(files)->count) == 1 || \ rcu_my_thread_group_empty())) diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index bbad657a3725..27576aa05e8c 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -758,8 +758,7 @@ extern int lockdep_rtnl_is_held(void); * or RTNL. Note : Please prefer rtnl_dereference() or rcu_dereference() */ #define rcu_dereference_rtnl(p) \ - rcu_dereference_check(p, rcu_read_lock_held() || \ - lockdep_rtnl_is_held()) + rcu_dereference_check(p, lockdep_rtnl_is_held()) /** * rtnl_dereference - fetch RCU pointer when updates are prevented by RTNL -- cgit v1.2.3 From f2e9039a43b01f01cab9dfaea2cad5f304fb3343 Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Thu, 7 Jul 2011 09:57:10 +0900 Subject: usb: r8a66597-hcd: add function for external controller R8A66597 has the pin of WR0 and WR1. So, if one write-pin of CPU connects to the pins, we have to change the setting of FIFOSEL register in the controller. If we don't change the setting, the controller cannot send the data of odd length. Signed-off-by: Yoshihiro Shimoda Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/r8a66597.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/r8a66597.h b/include/linux/usb/r8a66597.h index 26d216734057..30e171683a85 100644 --- a/include/linux/usb/r8a66597.h +++ b/include/linux/usb/r8a66597.h @@ -42,6 +42,9 @@ struct r8a66597_platdata { /* set one = big endian, set zero = little endian */ unsigned endian:1; + + /* (external controller only) set one = WR0_N shorted to WR1_N */ + unsigned wr0_shorted_to_wr1:1; }; /* Register definitions */ -- cgit v1.2.3 From 45304e8cd9d9df07e9221551678262b390bdaaa4 Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Thu, 7 Jul 2011 09:58:56 +0900 Subject: usb: update email address in ohci-sh and r8a66597-hcd Signed-off-by: Yoshihiro Shimoda Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/r8a66597.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/r8a66597.h b/include/linux/usb/r8a66597.h index 30e171683a85..f77c4ebba5be 100644 --- a/include/linux/usb/r8a66597.h +++ b/include/linux/usb/r8a66597.h @@ -3,7 +3,7 @@ * * Copyright (C) 2009 Renesas Solutions Corp. * - * Author : Yoshihiro Shimoda + * Author : Yoshihiro Shimoda * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by -- cgit v1.2.3 From bb59dbff4e5fb0ac14e3ee47d3f688490f128155 Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Thu, 7 Jul 2011 09:58:43 +0900 Subject: usb: gadget: m66592-udc: add function for external controller M66592 has the pin of WR0 and WR1. So, if one write-pin of CPU connects to the pins, we have to change the setting of FIFOSEL register in the controller. If we don't change the setting, the controller cannot send the data of odd length. Signed-off-by: Yoshihiro Shimoda Signed-off-by: Felipe Balbi --- include/linux/usb/m66592.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/m66592.h b/include/linux/usb/m66592.h index cda9625e7df0..a4ba31ab2fed 100644 --- a/include/linux/usb/m66592.h +++ b/include/linux/usb/m66592.h @@ -38,6 +38,8 @@ struct m66592_platdata { /* (external controller only) one = 3.3V, zero = 1.5V */ unsigned vif:1; + /* (external controller only) set one = WR0_N shorted to WR1_N */ + unsigned wr0_shorted_to_wr1:1; }; #endif /* __LINUX_USB_M66592_H */ -- cgit v1.2.3 From def90f4239f094f3846c108c1c41a4cd55c33e8e Mon Sep 17 00:00:00 2001 From: Shreshtha Kumar Sahu Date: Thu, 9 Jun 2011 22:56:32 +0200 Subject: amba pl011: workaround for uart registers lockup This workaround aims to break the deadlock situation which raises during continuous transfer of data for long duration over uart with hardware flow control. It is observed that CTS interrupt cannot be cleared in uart interrupt register (ICR). Hence further transfer over uart gets blocked. It is seen that during such deadlock condition ICR don't get cleared even on multiple write. This leads pass_counter to decrease and finally reach zero. This can be taken as trigger point to run this UART_BT_WA. Workaround backups the register configuration, does soft reset of UART using BIT-0 of PRCC_K_SOFTRST_SET/CLEAR registers and restores the registers. This patch also provides support for uart init and exit function calls if present. Signed-off-by: Shreshtha Kumar Sahu Signed-off-by: Linus Walleij Signed-off-by: Greg Kroah-Hartman --- include/linux/amba/serial.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/amba/serial.h b/include/linux/amba/serial.h index 5479fdc849e9..514ed45c462e 100644 --- a/include/linux/amba/serial.h +++ b/include/linux/amba/serial.h @@ -201,6 +201,9 @@ struct amba_pl011_data { bool (*dma_filter)(struct dma_chan *chan, void *filter_param); void *dma_rx_param; void *dma_tx_param; + void (*init) (void); + void (*exit) (void); + void (*reset) (void); }; #endif -- cgit v1.2.3 From f607e7fc5fb94d92030c4527287e9c149ddf9e65 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jean-Fran=C3=A7ois=20Dagenais?= Date: Fri, 8 Jul 2011 15:39:44 -0700 Subject: w1: ds1wm: add a reset recovery parameter MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This fixes a regression in 3.0 reported by Paul Parsons regarding the removal of the msleep(1) in the ds1wm_reset() function: : The linux-3.0-rc4 DS1WM 1-wire driver is logging "bus error, retrying" : error messages on an HP iPAQ hx4700 PDA (XScale-PXA270): : : : Driver for 1-wire Dallas network protocol. : DS1WM w1 busmaster driver - (c) 2004 Szabolcs Gyurko : 1-Wire driver for the DS2760 battery monitor chip - (c) 2004-2005, Szabolcs Gyurko : ds1wm ds1wm: pass: 1 bus error, retrying : ds1wm ds1wm: pass: 2 bus error, retrying : ds1wm ds1wm: pass: 3 bus error, retrying : ds1wm ds1wm: pass: 4 bus error, retrying : ds1wm ds1wm: pass: 5 bus error, retrying : ... : : The visible result is that the battery charging LED is erratic; sometimes : it works, mostly it doesn't. : : The linux-2.6.39 DS1WM 1-wire driver worked OK. I haven't tried 3.0-rc1, : 3.0-rc2, or 3.0-rc3. This sleep should not be required on normal circuitry provided the pull-ups on the bus are correctly adapted to the slaves. Unfortunately, this is not always the case. The sleep is restored but as a parameter to the probe function in the pdata. [akpm@linux-foundation.org: coding-style fixes] Reported-by: Paul Parsons Tested-by: Paul Parsons Signed-off-by: Jean-François Dagenais Cc: Evgeniy Polyakov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mfd/ds1wm.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/ds1wm.h b/include/linux/mfd/ds1wm.h index be469a357cbb..38a372a0e285 100644 --- a/include/linux/mfd/ds1wm.h +++ b/include/linux/mfd/ds1wm.h @@ -3,4 +3,11 @@ struct ds1wm_driver_data { int active_high; int clock_rate; + /* in milliseconds, the amount of time to */ + /* sleep following a reset pulse. Zero */ + /* should work if your bus devices recover*/ + /* time respects the 1-wire spec since the*/ + /* ds1wm implements the precise timings of*/ + /* a reset pulse/presence detect sequence.*/ + unsigned int reset_recover_delay; }; -- cgit v1.2.3 From d46db3d58233be4be980eb1e42eebe7808bcabab Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Wed, 4 May 2011 19:54:37 -0600 Subject: writeback: make writeback_control.nr_to_write straight Pass struct wb_writeback_work all the way down to writeback_sb_inodes(), and initialize the struct writeback_control there. struct writeback_control is basically designed to control writeback of a single file, but we keep abuse it for writing multiple files in writeback_sb_inodes() and its callers. It immediately clean things up, e.g. suddenly wbc.nr_to_write vs work->nr_pages starts to make sense, and instead of saving and restoring pages_skipped in writeback_sb_inodes it can always start with a clean zero value. It also makes a neat IO pattern change: large dirty files are now written in the full 4MB writeback chunk size, rather than whatever remained quota in wbc->nr_to_write. Acked-by: Jan Kara Proposed-by: Christoph Hellwig Signed-off-by: Wu Fengguang --- include/linux/writeback.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 2f1b512bd6e0..df1b7f18f100 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -24,12 +24,9 @@ enum writeback_sync_modes { */ struct writeback_control { enum writeback_sync_modes sync_mode; - unsigned long *older_than_this; /* If !NULL, only write back inodes - older than this */ long nr_to_write; /* Write this many pages, and decrement this for each page written */ long pages_skipped; /* Pages which were not written */ - long inodes_written; /* # of inodes written (at least) */ /* * For a_ops->writepages(): is start or end are non-zero then this is @@ -56,8 +53,7 @@ void writeback_inodes_sb_nr(struct super_block *, unsigned long nr); int writeback_inodes_sb_if_idle(struct super_block *); int writeback_inodes_sb_nr_if_idle(struct super_block *, unsigned long nr); void sync_inodes_sb(struct super_block *); -void writeback_inodes_wb(struct bdi_writeback *wb, - struct writeback_control *wbc); +long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages); long wb_do_writeback(struct bdi_writeback *wb, int force_wait); void wakeup_flusher_threads(long nr_pages); -- cgit v1.2.3 From f7d2b1ecd0c714adefc7d3a942ef87beb828a763 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 8 Dec 2010 22:44:24 -0600 Subject: writeback: account per-bdi accumulated written pages Introduce the BDI_WRITTEN counter. It will be used for estimating the bdi's write bandwidth. Peter Zijlstra : Move BDI_WRITTEN accounting into __bdi_writeout_inc(). This will cover and fix fuse, which only calls bdi_writeout_inc(). CC: Michael Rubin Reviewed-by: KOSAKI Motohiro Signed-off-by: Jan Kara Signed-off-by: Wu Fengguang --- include/linux/backing-dev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 47feb2c4706a..469d56443c63 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -40,6 +40,7 @@ typedef int (congested_fn)(void *, int); enum bdi_stat_item { BDI_RECLAIMABLE, BDI_WRITEBACK, + BDI_WRITTEN, NR_BDI_STAT_ITEMS }; -- cgit v1.2.3 From e98be2d599207c6b31e9bb340d52a231b2f3662d Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Sun, 29 Aug 2010 11:22:30 -0600 Subject: writeback: bdi write bandwidth estimation The estimation value will start from 100MB/s and adapt to the real bandwidth in seconds. It tries to update the bandwidth only when disk is fully utilized. Any inactive period of more than one second will be skipped. The estimated bandwidth will be reflecting how fast the device can writeout when _fully utilized_, and won't drop to 0 when it goes idle. The value will remain constant at disk idle time. At busy write time, if not considering fluctuations, it will also remain high unless be knocked down by possible concurrent reads that compete for the disk time and bandwidth with async writes. The estimation is not done purely in the flusher because there is no guarantee for write_cache_pages() to return timely to update bandwidth. The bdi->avg_write_bandwidth smoothing is very effective for filtering out sudden spikes, however may be a little biased in long term. The overheads are low because the bdi bandwidth update only occurs at 200ms intervals. The 200ms update interval is suitable, because it's not possible to get the real bandwidth for the instance at all, due to large fluctuations. The NFS commits can be as large as seconds worth of data. One XFS completion may be as large as half second worth of data if we are going to increase the write chunk to half second worth of data. In ext4, fluctuations with time period of around 5 seconds is observed. And there is another pattern of irregular periods of up to 20 seconds on SSD tests. That's why we are not only doing the estimation at 200ms intervals, but also averaging them over a period of 3 seconds and then go further to do another level of smoothing in avg_write_bandwidth. CC: Li Shaohua CC: Peter Zijlstra Signed-off-by: Wu Fengguang --- include/linux/backing-dev.h | 5 +++++ include/linux/writeback.h | 3 +++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 469d56443c63..a008982e7c08 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -73,6 +73,11 @@ struct backing_dev_info { struct percpu_counter bdi_stat[NR_BDI_STAT_ITEMS]; + unsigned long bw_time_stamp; /* last time write bw is updated */ + unsigned long written_stamp; /* pages written at bw_time_stamp */ + unsigned long write_bandwidth; /* the estimated write bandwidth */ + unsigned long avg_write_bandwidth; /* further smoothed write bw */ + struct prop_local_percpu completions; int dirty_exceeded; diff --git a/include/linux/writeback.h b/include/linux/writeback.h index df1b7f18f100..66862f2d90c8 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -118,6 +118,9 @@ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty); unsigned long bdi_dirty_limit(struct backing_dev_info *bdi, unsigned long dirty); +void __bdi_update_bandwidth(struct backing_dev_info *bdi, + unsigned long start_time); + void page_writeback_init(void); void balance_dirty_pages_ratelimited_nr(struct address_space *mapping, unsigned long nr_pages_dirtied); -- cgit v1.2.3 From c42843f2f0bbc9d716a32caf667d18fc2bf3bc4c Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Wed, 2 Mar 2011 15:54:09 -0600 Subject: writeback: introduce smoothed global dirty limit The start of a heavy weight application (ie. KVM) may instantly knock down determine_dirtyable_memory() if the swap is not enabled or full. global_dirty_limits() and bdi_dirty_limit() will in turn get global/bdi dirty thresholds that are _much_ lower than the global/bdi dirty pages. balance_dirty_pages() will then heavily throttle all dirtiers including the light ones, until the dirty pages drop below the new dirty thresholds. During this _deep_ dirty-exceeded state, the system may appear rather unresponsive to the users. About "deep" dirty-exceeded: task_dirty_limit() assigns 1/8 lower dirty threshold to heavy dirtiers than light ones, and the dirty pages will be throttled around the heavy dirtiers' dirty threshold and reasonably below the light dirtiers' dirty threshold. In this state, only the heavy dirtiers will be throttled and the dirty pages are carefully controlled to not exceed the light dirtiers' dirty threshold. However if the threshold itself suddenly drops below the number of dirty pages, the light dirtiers will get heavily throttled. So introduce global_dirty_limit for tracking the global dirty threshold with policies - follow downwards slowly - follow up in one shot global_dirty_limit can effectively mask out the impact of sudden drop of dirtyable memory. It will be used in the next patch for two new type of dirty limits. Note that the new dirty limits are not going to avoid throttling the light dirtiers, but could limit their sleep time to 200ms. Signed-off-by: Wu Fengguang --- include/linux/writeback.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 66862f2d90c8..e9d371b6053b 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -84,6 +84,8 @@ static inline void laptop_sync_completion(void) { } #endif void throttle_vm_writeout(gfp_t gfp_mask); +extern unsigned long global_dirty_limit; + /* These are exported to sysctl. */ extern int dirty_background_ratio; extern unsigned long dirty_background_bytes; @@ -119,6 +121,10 @@ unsigned long bdi_dirty_limit(struct backing_dev_info *bdi, unsigned long dirty); void __bdi_update_bandwidth(struct backing_dev_info *bdi, + unsigned long thresh, + unsigned long dirty, + unsigned long bdi_thresh, + unsigned long bdi_dirty, unsigned long start_time); void page_writeback_init(void); -- cgit v1.2.3 From ffd1f609ab10532e8137b4b981fdf903ef4d0b32 Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Sun, 19 Jun 2011 22:18:42 -0600 Subject: writeback: introduce max-pause and pass-good dirty limits The max-pause limit helps to keep the sleep time inside balance_dirty_pages() within MAX_PAUSE=200ms. The 200ms max sleep means per task rate limit of 8pages/200ms=160KB/s when dirty exceeded, which normally is enough to stop dirtiers from continue pushing the dirty pages high, unless there are a sufficient large number of slow dirtiers (eg. 500 tasks doing 160KB/s will still sum up to 80MB/s, exceeding the write bandwidth of a slow disk and hence accumulating more and more dirty pages). The pass-good limit helps to let go of the good bdi's in the presence of a blocked bdi (ie. NFS server not responding) or slow USB disk which for some reason build up a large number of initial dirty pages that refuse to go away anytime soon. For example, given two bdi's A and B and the initial state bdi_thresh_A = dirty_thresh / 2 bdi_thresh_B = dirty_thresh / 2 bdi_dirty_A = dirty_thresh / 2 bdi_dirty_B = dirty_thresh / 2 Then A get blocked, after a dozen seconds bdi_thresh_A = 0 bdi_thresh_B = dirty_thresh bdi_dirty_A = dirty_thresh / 2 bdi_dirty_B = dirty_thresh / 2 The (bdi_dirty_B < bdi_thresh_B) test is now useless and the dirty pages will be effectively throttled by condition (nr_dirty < dirty_thresh). This has two problems: (1) we lose the protections for light dirtiers (2) balance_dirty_pages() effectively becomes IO-less because the (bdi_nr_reclaimable > bdi_thresh) test won't be true. This is good for IO, but balance_dirty_pages() loses an important way to break out of the loop which leads to more spread out throttle delays. DIRTY_PASSGOOD_AREA can eliminate the above issues. The only problem is, DIRTY_PASSGOOD_AREA needs to be defined as 2 to fully cover the above example while this patch uses the more conservative value 8 so as not to surprise people with too many dirty pages than expected. The max-pause limit won't noticeably impact the speed dirty pages are knocked down when there is a sudden drop of global/bdi dirty thresholds. Because the heavy dirties will be throttled below 160KB/s which is slow enough. It does help to avoid long dirty throttle delays and especially will make light dirtiers more responsive. Signed-off-by: Wu Fengguang --- include/linux/writeback.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index e9d371b6053b..b625073b80c8 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -7,6 +7,27 @@ #include #include +/* + * The 1/16 region above the global dirty limit will be put to maximum pauses: + * + * (limit, limit + limit/DIRTY_MAXPAUSE_AREA) + * + * The 1/16 region above the max-pause region, dirty exceeded bdi's will be put + * to loops: + * + * (limit + limit/DIRTY_MAXPAUSE_AREA, limit + limit/DIRTY_PASSGOOD_AREA) + * + * Further beyond, all dirtier tasks will enter a loop waiting (possibly long + * time) for the dirty pages to drop, unless written enough pages. + * + * The global dirty threshold is normally equal to the global dirty limit, + * except when the system suddenly allocates a lot of anonymous memory and + * knocks down the global dirty threshold quickly, in which case the global + * dirty limit will follow down slowly to prevent livelocking all dirtier tasks. + */ +#define DIRTY_MAXPAUSE_AREA 16 +#define DIRTY_PASSGOOD_AREA 8 + struct backing_dev_info; /* -- cgit v1.2.3 From 1a12d8bd7b2998be01ee55edb64e7473728abb9c Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Sun, 29 Aug 2010 13:28:09 -0600 Subject: writeback: scale IO chunk size up to half device bandwidth Originally, MAX_WRITEBACK_PAGES was hard-coded to 1024 because of a concern of not holding I_SYNC for too long. (At least, that was the comment previously.) This doesn't make sense now because the only time we wait for I_SYNC is if we are calling sync or fsync, and in that case we need to write out all of the data anyway. Previously there may have been other code paths that waited on I_SYNC, but not any more. -- Theodore Ts'o So remove the MAX_WRITEBACK_PAGES constraint. The writeback pages will adapt to as large as the storage device can write within 500ms. XFS is observed to do IO completions in a batch, and the batch size is equal to the write chunk size. To avoid dirty pages to suddenly drop out of balance_dirty_pages()'s dirty control scope and create large fluctuations, the chunk size is also limited to half the control scope. The balance_dirty_pages() control scrope is [(background_thresh + dirty_thresh) / 2, dirty_thresh] which is by default [15%, 20%] of global dirty pages, whose range size is dirty_thresh / DIRTY_FULL_SCOPE. The adpative write chunk size will be rounded to the nearest 4MB boundary. http://bugzilla.kernel.org/show_bug.cgi?id=13930 CC: Theodore Ts'o CC: Dave Chinner CC: Chris Mason CC: Peter Zijlstra Signed-off-by: Wu Fengguang --- include/linux/writeback.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index b625073b80c8..f1bfa12ea246 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -8,6 +8,10 @@ #include /* + * The 1/4 region under the global dirty thresh is for smooth dirty throttling: + * + * (thresh - thresh/DIRTY_FULL_SCOPE, thresh) + * * The 1/16 region above the global dirty limit will be put to maximum pauses: * * (limit, limit + limit/DIRTY_MAXPAUSE_AREA) @@ -25,9 +29,16 @@ * knocks down the global dirty threshold quickly, in which case the global * dirty limit will follow down slowly to prevent livelocking all dirtier tasks. */ +#define DIRTY_SCOPE 8 +#define DIRTY_FULL_SCOPE (DIRTY_SCOPE / 2) #define DIRTY_MAXPAUSE_AREA 16 #define DIRTY_PASSGOOD_AREA 8 +/* + * 4MB minimal write chunk size + */ +#define MIN_WRITEBACK_PAGES (4096UL >> (PAGE_CACHE_SHIFT - 10)) + struct backing_dev_info; /* -- cgit v1.2.3 From 18b4f3f5d058b590e7189027eeb5d897742ade0a Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Sun, 10 Jul 2011 10:39:14 +0200 Subject: PM / Domains: Export pm_genpd_poweron() in header Allow SoC-specific code to call pm_genpd_poweron(). Signed-off-by: Magnus Damm Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 98491ee35102..14fb0953fa47 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -63,6 +63,7 @@ extern int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, struct generic_pm_domain *target); extern void pm_genpd_init(struct generic_pm_domain *genpd, struct dev_power_governor *gov, bool is_off); +extern int pm_genpd_poweron(struct generic_pm_domain *genpd); #else static inline int pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev) @@ -86,6 +87,10 @@ static inline int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, } static inline void pm_genpd_init(struct generic_pm_domain *genpd, struct dev_power_governor *gov, bool is_off) {} +static inline int pm_genpd_poweron(struct generic_pm_domain *genpd) +{ + return -ENOSYS; +} #endif #endif /* _LINUX_PM_DOMAIN_H */ -- cgit v1.2.3 From d72fe7883f9f835011cb581aea13e91c6fa2e31d Mon Sep 17 00:00:00 2001 From: Andy Green Date: Sun, 10 Jul 2011 05:27:14 -0600 Subject: I2C: OMAP2+: Introduce I2C IP versioning constants These represent the two kinds of (incompatible) OMAP I2C peripheral unit in use so far. The constants are in linux/i2c-omap.h so the omap i2c driver can have them too. Cc: patches@linaro.org Cc: Ben Dooks Reported-by: Peter Maydell Signed-off-by: Andy Green Signed-off-by: Tony Lindgren Signed-off-by: Kevin Hilman Signed-off-by: Paul Walmsley --- include/linux/i2c-omap.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c-omap.h b/include/linux/i2c-omap.h index 7472449cbb74..701886da76c7 100644 --- a/include/linux/i2c-omap.h +++ b/include/linux/i2c-omap.h @@ -3,6 +3,18 @@ #include +/* + * Version 2 of the I2C peripheral unit has a different register + * layout and extra registers. The ID register in the V2 peripheral + * unit on the OMAP4430 reports the same ID as the V1 peripheral + * unit on the OMAP3530, so we must inform the driver which IP + * version we know it is running on from platform / cpu-specific + * code using these constants in the hwmod class definition. + */ + +#define OMAP_I2C_IP_VERSION_1 1 +#define OMAP_I2C_IP_VERSION_2 2 + struct omap_i2c_bus_platform_data { u32 clkrate; void (*set_mpu_wkup_lat)(struct device *dev, long set); -- cgit v1.2.3 From 5a9aaf0cf89dfb776f45b7ef878fd1508faadbf7 Mon Sep 17 00:00:00 2001 From: Andy Green Date: Sun, 10 Jul 2011 05:27:15 -0600 Subject: I2C: OMAP1/OMAP2+: create omap I2C functionality flags for each cpu_... test These represent the 8 kinds of implementation functionality that up until now were inferred by the 16 remaining cpu_...() tests in the omap i2c driver. Changed to use BIT() as suggested by Balaji T Krishnamoorthy. Cc: patches@linaro.org Cc: Ben Dooks Reported-by: Peter Maydell Signed-off-by: Andy Green Signed-off-by: Tony Lindgren Signed-off-by: Kevin Hilman Signed-off-by: Paul Walmsley --- include/linux/i2c-omap.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c-omap.h b/include/linux/i2c-omap.h index 701886da76c7..0aa0cbd676f7 100644 --- a/include/linux/i2c-omap.h +++ b/include/linux/i2c-omap.h @@ -15,6 +15,21 @@ #define OMAP_I2C_IP_VERSION_1 1 #define OMAP_I2C_IP_VERSION_2 2 +/* struct omap_i2c_bus_platform_data .flags meanings */ + +#define OMAP_I2C_FLAG_NO_FIFO BIT(0) +#define OMAP_I2C_FLAG_SIMPLE_CLOCK BIT(1) +#define OMAP_I2C_FLAG_16BIT_DATA_REG BIT(2) +#define OMAP_I2C_FLAG_RESET_REGS_POSTIDLE BIT(3) +#define OMAP_I2C_FLAG_APPLY_ERRATA_I207 BIT(4) +#define OMAP_I2C_FLAG_ALWAYS_ARMXOR_CLK BIT(5) +#define OMAP_I2C_FLAG_FORCE_19200_INT_CLK BIT(6) +/* how the CPU address bus must be translated for I2C unit access */ +#define OMAP_I2C_FLAG_BUS_SHIFT_NONE 0 +#define OMAP_I2C_FLAG_BUS_SHIFT_1 BIT(7) +#define OMAP_I2C_FLAG_BUS_SHIFT_2 BIT(8) +#define OMAP_I2C_FLAG_BUS_SHIFT__SHIFT 7 + struct omap_i2c_bus_platform_data { u32 clkrate; void (*set_mpu_wkup_lat)(struct device *dev, long set); -- cgit v1.2.3 From d84e0bd7971eb8357c700151ee4e8e4101ee65fa Mon Sep 17 00:00:00 2001 From: Daniel Baluta Date: Sun, 10 Jul 2011 07:04:04 -0700 Subject: skbuff: update struct sk_buff members comments Rearrange struct sk_buff members comments to follow their definition order. Also, add missing comments for ooo_okay and dropcount members. Signed-off-by: Daniel Baluta Signed-off-by: David S. Miller --- include/linux/skbuff.h | 42 ++++++++++++++++++++++-------------------- 1 file changed, 22 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 08d4507715f5..32ada5351ab4 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -285,15 +285,12 @@ typedef unsigned char *sk_buff_data_t; * struct sk_buff - socket buffer * @next: Next buffer in list * @prev: Previous buffer in list - * @sk: Socket we are owned by * @tstamp: Time we arrived + * @sk: Socket we are owned by * @dev: Device we arrived on/are leaving by - * @transport_header: Transport layer header - * @network_header: Network layer header - * @mac_header: Link layer header + * @cb: Control buffer. Free for use by every layer. Put private vars here * @_skb_refdst: destination entry (with norefcount bit) * @sp: the security path, used for xfrm - * @cb: Control buffer. Free for use by every layer. Put private vars here * @len: Length of actual data * @data_len: Data length * @mac_len: Length of link layer header @@ -301,40 +298,45 @@ typedef unsigned char *sk_buff_data_t; * @csum: Checksum (must include start/offset pair) * @csum_start: Offset from skb->head where checksumming should start * @csum_offset: Offset from csum_start where checksum should be stored + * @priority: Packet queueing priority * @local_df: allow local fragmentation * @cloned: Head may be cloned (check refcnt to be sure) + * @ip_summed: Driver fed us an IP checksum * @nohdr: Payload reference only, must not modify header + * @nfctinfo: Relationship of this skb to the connection * @pkt_type: Packet class * @fclone: skbuff clone status - * @ip_summed: Driver fed us an IP checksum - * @priority: Packet queueing priority - * @users: User count - see {datagram,tcp}.c - * @protocol: Packet protocol from driver - * @truesize: Buffer size - * @head: Head of buffer - * @data: Data head pointer - * @tail: Tail pointer - * @end: End pointer - * @destructor: Destruct function - * @mark: Generic packet mark - * @nfct: Associated connection, if any * @ipvs_property: skbuff is owned by ipvs * @peeked: this packet has been seen already, so stats have been * done for it, don't do them again * @nf_trace: netfilter packet trace flag - * @nfctinfo: Relationship of this skb to the connection + * @protocol: Packet protocol from driver + * @destructor: Destruct function + * @nfct: Associated connection, if any * @nfct_reasm: netfilter conntrack re-assembly pointer * @nf_bridge: Saved data about a bridged frame - see br_netfilter.c * @skb_iif: ifindex of device we arrived on - * @rxhash: the packet hash computed on receive - * @queue_mapping: Queue mapping for multiqueue devices * @tc_index: Traffic control index * @tc_verd: traffic control verdict + * @rxhash: the packet hash computed on receive + * @queue_mapping: Queue mapping for multiqueue devices * @ndisc_nodetype: router type (from link layer) + * @ooo_okay: allow the mapping of a socket to a queue to be changed * @dma_cookie: a cookie to one of several possible DMA operations * done by skb DMA functions * @secmark: security marking + * @mark: Generic packet mark + * @dropcount: total number of sk_receive_queue overflows * @vlan_tci: vlan tag control information + * @transport_header: Transport layer header + * @network_header: Network layer header + * @mac_header: Link layer header + * @tail: Tail pointer + * @end: End pointer + * @head: Head of buffer + * @data: Data head pointer + * @truesize: Buffer size + * @users: User count - see {datagram,tcp}.c */ struct sk_buff { -- cgit v1.2.3 From 4862fd6047ed02e2726667c54d35f538eecc56aa Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sun, 10 Jul 2011 22:05:08 -0400 Subject: jbd2: remove jbd2_dev_to_name() from jbd2 tracepoints Using function calls in TP_printk causes perf heartburn, so print the MAJOR/MINOR device numbers instead. Signed-off-by: "Theodore Ts'o" --- include/linux/jbd2.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index d087c2e7b2aa..38f307b8c334 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1329,12 +1329,6 @@ extern int jbd_blocks_per_page(struct inode *inode); #define BUFFER_TRACE2(bh, bh2, info) do {} while (0) #define JBUFFER_TRACE(jh, info) do {} while (0) -/* - * jbd2_dev_to_name is a utility function used by the jbd2 and ext4 - * tracing infrastructure to map a dev_t to a device name. - */ -extern const char *jbd2_dev_to_name(dev_t device); - #endif /* __KERNEL__ */ #endif /* _LINUX_JBD2_H */ -- cgit v1.2.3 From 1522043bf73ef0e9e61dc512a0f3cdbec1cbf89f Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Wed, 6 Jul 2011 02:54:11 +0000 Subject: sh: move CLKDEV_xxx_ID macro to sh_clk.h Signed-off-by: Kuninori Morimoto Signed-off-by: Paul Mundt --- include/linux/sh_clk.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sh_clk.h b/include/linux/sh_clk.h index 9a52f72527dc..3ccf18648d0a 100644 --- a/include/linux/sh_clk.h +++ b/include/linux/sh_clk.h @@ -147,4 +147,8 @@ int sh_clk_div4_reparent_register(struct clk *clks, int nr, int sh_clk_div6_register(struct clk *clks, int nr); int sh_clk_div6_reparent_register(struct clk *clks, int nr); +#define CLKDEV_CON_ID(_id, _clk) { .con_id = _id, .clk = _clk } +#define CLKDEV_DEV_ID(_id, _clk) { .dev_id = _id, .clk = _clk } +#define CLKDEV_ICK_ID(_cid, _did, _clk) { .con_id = _cid, .dev_id = _did, .clk = _clk } + #endif /* __SH_CLOCK_H */ -- cgit v1.2.3 From 04da85b86188f224cc9b391b5bdd92a3ba20ffcf Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 11 Jul 2011 10:12:59 -0400 Subject: ftrace: Fix warning when CONFIG_FUNCTION_TRACER is not defined The struct ftrace_hash was declared within CONFIG_FUNCTION_TRACER but was referenced outside of it. Reported-by: Ingo Molnar Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index ed0eb5254d1c..f0c0e8a47ae6 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -19,6 +19,8 @@ #include +struct ftrace_hash; + #ifdef CONFIG_FUNCTION_TRACER extern int ftrace_enabled; @@ -29,8 +31,6 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip); -struct ftrace_hash; - enum { FTRACE_OPS_FL_ENABLED = 1 << 0, FTRACE_OPS_FL_GLOBAL = 1 << 1, -- cgit v1.2.3 From 17b75eca7683d4942f4d8d00563fd15f37c39589 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 12 Jul 2011 00:39:29 +0200 Subject: PM / Domains: Do not execute device callbacks under locks Currently, the .start_device() and .stop_device() callbacks from struct generic_pm_domain() as well as the device drivers' runtime PM callbacks used by the generic PM domains code are executed under the generic PM domain lock. This, unfortunately, is prone to deadlocks, for example if a device and its parent are boths members of the same PM domain. For this reason, it would be better if the PM domains code didn't execute device callbacks under the lock. Rework the locking in the generic PM domains code so that the lock is dropped for the execution of device callbacks. To this end, introduce PM domains states reflecting the current status of a PM domain and such that the PM domain lock cannot be acquired if the status is GPD_STATE_BUSY. Make threads attempting to acquire a PM domain's lock wait until the status changes to either GPD_STATE_ACTIVE or GPD_STATE_POWER_OFF. This change by itself doesn't fix the deadlock problem mentioned above, but the mechanism introduced by it will be used for for this purpose by a subsequent patch. Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 14fb0953fa47..c71457cb8a79 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -11,8 +11,11 @@ #include -#define GPD_IN_SUSPEND 1 -#define GPD_POWER_OFF 2 +enum gpd_status { + GPD_STATE_ACTIVE = 0, /* PM domain is active */ + GPD_STATE_BUSY, /* Something is happening to the PM domain */ + GPD_STATE_POWER_OFF, /* PM domain is off */ +}; struct dev_power_governor { bool (*power_down_ok)(struct dev_pm_domain *domain); @@ -29,7 +32,8 @@ struct generic_pm_domain { struct work_struct power_off_work; unsigned int in_progress; /* Number of devices being suspended now */ unsigned int sd_count; /* Number of subdomains with power "on" */ - bool power_is_off; /* Whether or not power has been removed */ + enum gpd_status status; /* Current state of the domain */ + wait_queue_head_t status_wait_queue; unsigned int device_count; /* Number of devices */ unsigned int suspended_count; /* System suspend device counter */ unsigned int prepared_count; /* Suspend counter of prepared devices */ -- cgit v1.2.3 From c6d22b37263607ba5aeeb2e11169fa65caa29bee Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 12 Jul 2011 00:39:36 +0200 Subject: PM / Domains: Allow callbacks to execute all runtime PM helpers A deadlock may occur if one of the PM domains' .start_device() or .stop_device() callbacks or a device driver's .runtime_suspend() or .runtime_resume() callback executed by the core generic PM domain code uses a "wrong" runtime PM helper function. This happens, for example, if .runtime_resume() from one device's driver calls pm_runtime_resume() for another device in the same PM domain. A similar situation may take place if a device's parent is in the same PM domain, in which case the runtime PM framework may execute pm_genpd_runtime_resume() automatically for the parent (if it is suspended at the moment). This, of course, is undesirable, so the generic PM domains code should be modified to prevent it from happening. The runtime PM framework guarantees that pm_genpd_runtime_suspend() and pm_genpd_runtime_resume() won't be executed in parallel for the same device, so the generic PM domains code need not worry about those cases. Still, it needs to prevent the other possible race conditions between pm_genpd_runtime_suspend(), pm_genpd_runtime_resume(), pm_genpd_poweron() and pm_genpd_poweroff() from happening and it needs to avoid deadlocks at the same time. To this end, modify the generic PM domains code to relax synchronization rules so that: * pm_genpd_poweron() doesn't wait for the PM domain status to change from GPD_STATE_BUSY. If it finds that the status is not GPD_STATE_POWER_OFF, it returns without powering the domain on (it may modify the status depending on the circumstances). * pm_genpd_poweroff() returns as soon as it finds that the PM domain's status changed from GPD_STATE_BUSY after it's released the PM domain's lock. * pm_genpd_runtime_suspend() doesn't wait for the PM domain status to change from GPD_STATE_BUSY after executing the domain's .stop_device() callback and executes pm_genpd_poweroff() only if pm_genpd_runtime_resume() is not executed in parallel. * pm_genpd_runtime_resume() doesn't wait for the PM domain status to change from GPD_STATE_BUSY after executing pm_genpd_poweron() and sets the domain's status to GPD_STATE_BUSY and increments its counter of resuming devices (introduced by this change) immediately after acquiring the lock. The counter of resuming devices is then decremented after executing __pm_genpd_runtime_resume() for the device and the domain's status is reset to GPD_STATE_ACTIVE (unless there are more resuming devices in the domain, in which case the status remains GPD_STATE_BUSY). This way, for example, if a device driver's .runtime_resume() callback executes pm_runtime_resume() for another device in the same PM domain, pm_genpd_poweron() called by pm_genpd_runtime_resume() invoked by the runtime PM framework will not block and it will see that there's nothing to do for it. Next, the PM domain's lock will be acquired without waiting for its status to change from GPD_STATE_BUSY and the device driver's .runtime_resume() callback will be executed. In turn, if pm_runtime_suspend() is executed by one device driver's .runtime_resume() callback for another device in the same PM domain, pm_genpd_poweroff() executed by pm_genpd_runtime_suspend() invoked by the runtime PM framework as a result will notice that one of the devices in the domain is being resumed, so it will return immediately. Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index c71457cb8a79..feb80af4cc1b 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -14,6 +14,7 @@ enum gpd_status { GPD_STATE_ACTIVE = 0, /* PM domain is active */ GPD_STATE_BUSY, /* Something is happening to the PM domain */ + GPD_STATE_REPEAT, /* Power off in progress, to be repeated */ GPD_STATE_POWER_OFF, /* PM domain is off */ }; @@ -34,6 +35,8 @@ struct generic_pm_domain { unsigned int sd_count; /* Number of subdomains with power "on" */ enum gpd_status status; /* Current state of the domain */ wait_queue_head_t status_wait_queue; + struct task_struct *poweroff_task; /* Powering off task */ + unsigned int resume_count; /* Number of devices being resumed */ unsigned int device_count; /* Number of devices */ unsigned int suspended_count; /* System suspend device counter */ unsigned int prepared_count; /* Suspend counter of prepared devices */ -- cgit v1.2.3 From a63fdc5156f2ef5690b6cf03d72b0c4917efbba7 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Tue, 14 Jun 2011 10:57:50 +1000 Subject: mm: Move definition of MIN_MEMORY_BLOCK_SIZE to a header The macro MIN_MEMORY_BLOCK_SIZE is currently defined twice in two .c files, and I need it in a third one to fix a powerpc bug, so let's first move it into a header Signed-off-by: Benjamin Herrenschmidt Acked-by: Ingo Molnar --- include/linux/memory.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index e1e3b2b84f85..935699b30b7c 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -20,6 +20,8 @@ #include #include +#define MIN_MEMORY_BLOCK_SIZE (1 << SECTION_SIZE_BITS) + struct memory_block { unsigned long start_section_nr; unsigned long end_section_nr; -- cgit v1.2.3 From 4915a0de43c3e9aef92005c1f94a8ff3a6cfced5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 11 Jul 2011 20:08:34 -0700 Subject: net: introduce __netdev_alloc_skb_ip_align RX rings should use GFP_KERNEL allocations if possible, add __netdev_alloc_skb_ip_align() helper to ease this. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 32ada5351ab4..a24218c9c84b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1579,16 +1579,22 @@ static inline struct sk_buff *netdev_alloc_skb(struct net_device *dev, return __netdev_alloc_skb(dev, length, GFP_ATOMIC); } -static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev, - unsigned int length) +static inline struct sk_buff *__netdev_alloc_skb_ip_align(struct net_device *dev, + unsigned int length, gfp_t gfp) { - struct sk_buff *skb = netdev_alloc_skb(dev, length + NET_IP_ALIGN); + struct sk_buff *skb = __netdev_alloc_skb(dev, length + NET_IP_ALIGN, gfp); if (NET_IP_ALIGN && skb) skb_reserve(skb, NET_IP_ALIGN); return skb; } +static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev, + unsigned int length) +{ + return __netdev_alloc_skb_ip_align(dev, length, GFP_ATOMIC); +} + /** * __netdev_alloc_page - allocate a page for ps-rx on a specific device * @dev: network device to receive on -- cgit v1.2.3 From 4aede84b33d6beb401136a3deca0651ae07c5e99 Mon Sep 17 00:00:00 2001 From: Justin TerAvest Date: Tue, 12 Jul 2011 08:31:45 +0200 Subject: fixlet: Remove fs_excl from struct task. fs_excl is a poor man's priority inheritance for filesystems to hint to the block layer that an operation is important. It was never clearly specified, not widely adopted, and will not prevent starvation in many cases (like across cgroups). fs_excl was introduced with the time sliced CFQ IO scheduler, to indicate when a process held FS exclusive resources and thus needed a boost. It doesn't cover all file systems, and it was never fully complete. Lets kill it. Signed-off-by: Justin TerAvest Signed-off-by: Jens Axboe --- include/linux/fs.h | 4 ---- include/linux/init_task.h | 1 - include/linux/sched.h | 1 - 3 files changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 6e73e2e9ae33..f6c866c287b5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1453,10 +1453,6 @@ enum { #define vfs_check_frozen(sb, level) \ wait_event((sb)->s_wait_unfrozen, ((sb)->s_frozen < (level))) -#define get_fs_excl() atomic_inc(¤t->fs_excl) -#define put_fs_excl() atomic_dec(¤t->fs_excl) -#define has_fs_excl() atomic_read(¤t->fs_excl) - /* * until VFS tracks user namespaces for inodes, just make all files * belong to init_user_ns diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 580f70c02391..d14e058aaeed 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -176,7 +176,6 @@ extern struct cred init_cred; .alloc_lock = __SPIN_LOCK_UNLOCKED(tsk.alloc_lock), \ .journal_info = NULL, \ .cpu_timers = INIT_CPU_TIMERS(tsk.cpu_timers), \ - .fs_excl = ATOMIC_INIT(0), \ .pi_lock = __RAW_SPIN_LOCK_UNLOCKED(tsk.pi_lock), \ .timer_slack_ns = 50000, /* 50 usec default slack */ \ .pids = { \ diff --git a/include/linux/sched.h b/include/linux/sched.h index a837b20ba190..22f54249cde1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1503,7 +1503,6 @@ struct task_struct { short il_next; short pref_node_fork; #endif - atomic_t fs_excl; /* holding fs exclusive resources */ struct rcu_head rcu; /* -- cgit v1.2.3 From f3393b62f157cc87f8d78247e97b87778dc077b8 Mon Sep 17 00:00:00 2001 From: Kevin Hilman Date: Tue, 12 Jul 2011 11:17:09 +0200 Subject: PM / Runtime: Add new helper function: pm_runtime_status_suspended() This boolean function simply returns whether or not the runtime status of the device is 'suspended'. Unlike pm_runtime_suspended(), this function returns the runtime status whether or not runtime PM for the device has been disabled or not. Also add entry to Documentation/power/runtime.txt Signed-off-by: Kevin Hilman Signed-off-by: Rafael J. Wysocki --- include/linux/pm_runtime.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index dfb8539ed686..daac05d751b2 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -82,6 +82,11 @@ static inline bool pm_runtime_suspended(struct device *dev) && !dev->power.disable_depth; } +static inline bool pm_runtime_status_suspended(struct device *dev) +{ + return dev->power.runtime_status == RPM_SUSPENDED; +} + static inline bool pm_runtime_enabled(struct device *dev) { return !dev->power.disable_depth; @@ -130,6 +135,7 @@ static inline void pm_runtime_put_noidle(struct device *dev) {} static inline bool device_run_wake(struct device *dev) { return false; } static inline void device_set_run_wake(struct device *dev, bool enable) {} static inline bool pm_runtime_suspended(struct device *dev) { return false; } +static inline bool pm_runtime_status_suspended(struct device *dev) { return false; } static inline bool pm_runtime_enabled(struct device *dev) { return false; } static inline int pm_generic_runtime_idle(struct device *dev) { return 0; } -- cgit v1.2.3 From 91e3d71db29d9b3b67b64e2a08e724a7ff538b4c Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Fri, 3 Jun 2011 08:51:05 +0200 Subject: KVM: Clarify KVM_ASSIGN_PCI_DEVICE documentation Neither host_irq nor the guest_msi struct are used anymore today. Tag the former, drop the latter to avoid confusion. Signed-off-by: Jan Kiszka Signed-off-by: Avi Kivity --- include/linux/kvm.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 55ef181521ff..9c9ca7c7b491 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -773,20 +773,14 @@ struct kvm_assigned_pci_dev { struct kvm_assigned_irq { __u32 assigned_dev_id; - __u32 host_irq; + __u32 host_irq; /* ignored (legacy field) */ __u32 guest_irq; __u32 flags; union { - struct { - __u32 addr_lo; - __u32 addr_hi; - __u32 data; - } guest_msi; __u32 reserved[12]; }; }; - struct kvm_assigned_msix_nr { __u32 assigned_dev_id; __u16 entry_nr; -- cgit v1.2.3 From de56a948b9182fbcf92cb8212f114de096c2d574 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Wed, 29 Jun 2011 00:21:34 +0000 Subject: KVM: PPC: Add support for Book3S processors in hypervisor mode This adds support for KVM running on 64-bit Book 3S processors, specifically POWER7, in hypervisor mode. Using hypervisor mode means that the guest can use the processor's supervisor mode. That means that the guest can execute privileged instructions and access privileged registers itself without trapping to the host. This gives excellent performance, but does mean that KVM cannot emulate a processor architecture other than the one that the hardware implements. This code assumes that the guest is running paravirtualized using the PAPR (Power Architecture Platform Requirements) interface, which is the interface that IBM's PowerVM hypervisor uses. That means that existing Linux distributions that run on IBM pSeries machines will also run under KVM without modification. In order to communicate the PAPR hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code to include/linux/kvm.h. Currently the choice between book3s_hv support and book3s_pr support (i.e. the existing code, which runs the guest in user mode) has to be made at kernel configuration time, so a given kernel binary can only do one or the other. This new book3s_hv code doesn't support MMIO emulation at present. Since we are running paravirtualized guests, this isn't a serious restriction. With the guest running in supervisor mode, most exceptions go straight to the guest. We will never get data or instruction storage or segment interrupts, alignment interrupts, decrementer interrupts, program interrupts, single-step interrupts, etc., coming to the hypervisor from the guest. Therefore this introduces a new KVMTEST_NONHV macro for the exception entry path so that we don't have to do the KVM test on entry to those exception handlers. We do however get hypervisor decrementer, hypervisor data storage, hypervisor instruction storage, and hypervisor emulation assist interrupts, so we have to handle those. In hypervisor mode, real-mode accesses can access all of RAM, not just a limited amount. Therefore we put all the guest state in the vcpu.arch and use the shadow_vcpu in the PACA only for temporary scratch space. We allocate the vcpu with kzalloc rather than vzalloc, and we don't use anything in the kvmppc_vcpu_book3s struct, so we don't allocate it. We don't have a shared page with the guest, but we still need a kvm_vcpu_arch_shared struct to store the values of various registers, so we include one in the vcpu_arch struct. The POWER7 processor has a restriction that all threads in a core have to be in the same partition. MMU-on kernel code counts as a partition (partition 0), so we have to do a partition switch on every entry to and exit from the guest. At present we require the host and guest to run in single-thread mode because of this hardware restriction. This code allocates a hashed page table for the guest and initializes it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We require that the guest memory is allocated using 16MB huge pages, in order to simplify the low-level memory management. This also means that we can get away without tracking paging activity in the host for now, since huge pages can't be paged or swapped. This also adds a few new exports needed by the book3s_hv code. Signed-off-by: Paul Mackerras Signed-off-by: Alexander Graf --- include/linux/kvm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 9c9ca7c7b491..a156294fc22a 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -161,6 +161,7 @@ struct kvm_pit_config { #define KVM_EXIT_NMI 16 #define KVM_EXIT_INTERNAL_ERROR 17 #define KVM_EXIT_OSI 18 +#define KVM_EXIT_PAPR_HCALL 19 /* For KVM_EXIT_INTERNAL_ERROR */ #define KVM_INTERNAL_ERROR_EMULATION 1 @@ -264,6 +265,11 @@ struct kvm_run { struct { __u64 gprs[32]; } osi; + struct { + __u64 nr; + __u64 ret; + __u64 args[9]; + } papr_hcall; /* Fix the size of the union. */ char padding[256]; }; -- cgit v1.2.3 From 54738c097163c3f01e67ccc85462b78d4d4f495f Mon Sep 17 00:00:00 2001 From: David Gibson Date: Wed, 29 Jun 2011 00:22:41 +0000 Subject: KVM: PPC: Accelerate H_PUT_TCE by implementing it in real mode This improves I/O performance for guests using the PAPR paravirtualization interface by making the H_PUT_TCE hcall faster, by implementing it in real mode. H_PUT_TCE is used for updating virtual IOMMU tables, and is used both for virtual I/O and for real I/O in the PAPR interface. Since this moves the IOMMU tables into the kernel, we define a new KVM_CREATE_SPAPR_TCE ioctl to allow qemu to create the tables. The ioctl returns a file descriptor which can be used to mmap the newly created table. The qemu driver models use them in the same way as userspace managed tables, but they can be updated directly by the guest with a real-mode H_PUT_TCE implementation, reducing the number of host/guest context switches during guest IO. There are certain circumstances where it is useful for userland qemu to write to the TCE table even if the kernel H_PUT_TCE path is used most of the time. Specifically, allowing this will avoid awkwardness when we need to reset the table. More importantly, we will in the future need to write the table in order to restore its state after a checkpoint resume or migration. Signed-off-by: David Gibson Signed-off-by: Paul Mackerras Signed-off-by: Alexander Graf --- include/linux/kvm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index a156294fc22a..61f56502732e 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -550,6 +550,7 @@ struct kvm_ppc_pvinfo { #define KVM_CAP_TSC_CONTROL 60 #define KVM_CAP_GET_TSC_KHZ 61 #define KVM_CAP_PPC_BOOKE_SREGS 62 +#define KVM_CAP_SPAPR_TCE 63 #ifdef KVM_CAP_IRQ_ROUTING @@ -752,6 +753,7 @@ struct kvm_clock_data { /* Available with KVM_CAP_XCRS */ #define KVM_GET_XCRS _IOR(KVMIO, 0xa6, struct kvm_xcrs) #define KVM_SET_XCRS _IOW(KVMIO, 0xa7, struct kvm_xcrs) +#define KVM_CREATE_SPAPR_TCE _IOW(KVMIO, 0xa8, struct kvm_create_spapr_tce) #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) -- cgit v1.2.3 From 371fefd6f2dc46668e00871930dde613b88d4bde Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Wed, 29 Jun 2011 00:23:08 +0000 Subject: KVM: PPC: Allow book3s_hv guests to use SMT processor modes This lifts the restriction that book3s_hv guests can only run one hardware thread per core, and allows them to use up to 4 threads per core on POWER7. The host still has to run single-threaded. This capability is advertised to qemu through a new KVM_CAP_PPC_SMT capability. The return value of the ioctl querying this capability is the number of vcpus per virtual CPU core (vcore), currently 4. To use this, the host kernel should be booted with all threads active, and then all the secondary threads should be offlined. This will put the secondary threads into nap mode. KVM will then wake them from nap mode and use them for running guest code (while they are still offline). To wake the secondary threads, we send them an IPI using a new xics_wake_cpu() function, implemented in arch/powerpc/sysdev/xics/icp-native.c. In other words, at this stage we assume that the platform has a XICS interrupt controller and we are using icp-native.c to drive it. Since the woken thread will need to acknowledge and clear the IPI, we also export the base physical address of the XICS registers using kvmppc_set_xics_phys() for use in the low-level KVM book3s code. When a vcpu is created, it is assigned to a virtual CPU core. The vcore number is obtained by dividing the vcpu number by the number of threads per core in the host. This number is exported to userspace via the KVM_CAP_PPC_SMT capability. If qemu wishes to run the guest in single-threaded mode, it should make all vcpu numbers be multiples of the number of threads per core. We distinguish three states of a vcpu: runnable (i.e., ready to execute the guest), blocked (that is, idle), and busy in host. We currently implement a policy that the vcore can run only when all its threads are runnable or blocked. This way, if a vcpu needs to execute elsewhere in the kernel or in qemu, it can do so without being starved of CPU by the other vcpus. When a vcore starts to run, it executes in the context of one of the vcpu threads. The other vcpu threads all go to sleep and stay asleep until something happens requiring the vcpu thread to return to qemu, or to wake up to run the vcore (this can happen when another vcpu thread goes from busy in host state to blocked). It can happen that a vcpu goes from blocked to runnable state (e.g. because of an interrupt), and the vcore it belongs to is already running. In that case it can start to run immediately as long as the none of the vcpus in the vcore have started to exit the guest. We send the next free thread in the vcore an IPI to get it to start to execute the guest. It synchronizes with the other threads via the vcore->entry_exit_count field to make sure that it doesn't go into the guest if the other vcpus are exiting by the time that it is ready to actually enter the guest. Note that there is no fixed relationship between the hardware thread number and the vcpu number. Hardware threads are assigned to vcpus as they become runnable, so we will always use the lower-numbered hardware threads in preference to higher-numbered threads if not all the vcpus in the vcore are runnable, regardless of which vcpus are runnable. Signed-off-by: Paul Mackerras Signed-off-by: Alexander Graf --- include/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 61f56502732e..e2a378d97160 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -551,6 +551,7 @@ struct kvm_ppc_pvinfo { #define KVM_CAP_GET_TSC_KHZ 61 #define KVM_CAP_PPC_BOOKE_SREGS 62 #define KVM_CAP_SPAPR_TCE 63 +#define KVM_CAP_PPC_SMT 64 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From aa04b4cc5be64b4fb9ef4e0fdf2418e2f4737fb2 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Wed, 29 Jun 2011 00:25:44 +0000 Subject: KVM: PPC: Allocate RMAs (Real Mode Areas) at boot for use by guests This adds infrastructure which will be needed to allow book3s_hv KVM to run on older POWER processors, including PPC970, which don't support the Virtual Real Mode Area (VRMA) facility, but only the Real Mode Offset (RMO) facility. These processors require a physically contiguous, aligned area of memory for each guest. When the guest does an access in real mode (MMU off), the address is compared against a limit value, and if it is lower, the address is ORed with an offset value (from the Real Mode Offset Register (RMOR)) and the result becomes the real address for the access. The size of the RMA has to be one of a set of supported values, which usually includes 64MB, 128MB, 256MB and some larger powers of 2. Since we are unlikely to be able to allocate 64MB or more of physically contiguous memory after the kernel has been running for a while, we allocate a pool of RMAs at boot time using the bootmem allocator. The size and number of the RMAs can be set using the kvm_rma_size=xx and kvm_rma_count=xx kernel command line options. KVM exports a new capability, KVM_CAP_PPC_RMA, to signal the availability of the pool of preallocated RMAs. The capability value is 1 if the processor can use an RMA but doesn't require one (because it supports the VRMA facility), or 2 if the processor requires an RMA for each guest. This adds a new ioctl, KVM_ALLOCATE_RMA, which allocates an RMA from the pool and returns a file descriptor which can be used to map the RMA. It also returns the size of the RMA in the argument structure. Having an RMA means we will get multiple KMV_SET_USER_MEMORY_REGION ioctl calls from userspace. To cope with this, we now preallocate the kvm->arch.ram_pginfo array when the VM is created with a size sufficient for up to 64GB of guest memory. Subsequently we will get rid of this array and use memory associated with each memslot instead. This moves most of the code that translates the user addresses into host pfns (page frame numbers) out of kvmppc_prepare_vrma up one level to kvmppc_core_prepare_memory_region. Also, instead of having to look up the VMA for each page in order to check the page size, we now check that the pages we get are compound pages of 16MB. However, if we are adding memory that is mapped to an RMA, we don't bother with calling get_user_pages_fast and instead just offset from the base pfn for the RMA. Typically the RMA gets added after vcpus are created, which makes it inconvenient to have the LPCR (logical partition control register) value in the vcpu->arch struct, since the LPCR controls whether the processor uses RMA or VRMA for the guest. This moves the LPCR value into the kvm->arch struct and arranges for the MER (mediated external request) bit, which is the only bit that varies between vcpus, to be set in assembly code when going into the guest if there is a pending external interrupt request. Signed-off-by: Paul Mackerras Signed-off-by: Alexander Graf --- include/linux/kvm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index e2a378d97160..2c366b52f505 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -552,6 +552,7 @@ struct kvm_ppc_pvinfo { #define KVM_CAP_PPC_BOOKE_SREGS 62 #define KVM_CAP_SPAPR_TCE 63 #define KVM_CAP_PPC_SMT 64 +#define KVM_CAP_PPC_RMA 65 #ifdef KVM_CAP_IRQ_ROUTING @@ -755,6 +756,8 @@ struct kvm_clock_data { #define KVM_GET_XCRS _IOR(KVMIO, 0xa6, struct kvm_xcrs) #define KVM_SET_XCRS _IOW(KVMIO, 0xa7, struct kvm_xcrs) #define KVM_CREATE_SPAPR_TCE _IOW(KVMIO, 0xa8, struct kvm_create_spapr_tce) +/* Available with KVM_CAP_RMA */ +#define KVM_ALLOCATE_RMA _IOR(KVMIO, 0xa9, struct kvm_allocate_rma) #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) -- cgit v1.2.3 From e03b644fe68b1c6401465b02724d261538dba10f Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Mon, 11 Jul 2011 15:28:11 -0400 Subject: KVM: introduce kvm_read_guest_cached Introduce kvm_read_guest_cached() function in addition to write one we already have. [ by glauber: export function signature in kvm header ] Signed-off-by: Gleb Natapov Signed-off-by: Glauber Costa Acked-by: Rik van Riel Tested-by: Eric Munson Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 31ebb59cbd2f..f7df0a3b031d 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -381,6 +381,8 @@ int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len); int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len); +int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, + void *data, unsigned long len); int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data, int offset, int len); int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data, -- cgit v1.2.3 From 383cd7213f95a2784ab5038fe292844178768b82 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Tue, 12 Jul 2011 14:24:35 +0200 Subject: CFQ: move think time check variables to a separate struct Move the variables to do think time check to a sepatate struct. This is to prepare adding think time check for service tree and group. No functional change. Signed-off-by: Shaohua Li Acked-by: Vivek Goyal Signed-off-by: Jens Axboe --- include/linux/iocontext.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h index b2eee896dcbc..5037a0ad2312 100644 --- a/include/linux/iocontext.h +++ b/include/linux/iocontext.h @@ -5,6 +5,14 @@ #include struct cfq_queue; +struct cfq_ttime { + unsigned long last_end_request; + + unsigned long ttime_total; + unsigned long ttime_samples; + unsigned long ttime_mean; +}; + struct cfq_io_context { void *key; @@ -12,11 +20,7 @@ struct cfq_io_context { struct io_context *ioc; - unsigned long last_end_request; - - unsigned long ttime_total; - unsigned long ttime_samples; - unsigned long ttime_mean; + struct cfq_ttime ttime; struct list_head queue_list; struct hlist_node cic_list; -- cgit v1.2.3 From 78fe0f41d9937ee62817912ac8d627e06243c269 Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Tue, 31 May 2011 19:05:47 -0400 Subject: NFS: use scope from exchange_id to skip reclaim can be skipped if the "eir_server_scope" from the exchange_id proc differs from previous calls. Also, in the future server_scope will be useful for determining whether client trunking is available Signed-off-by: Weston Andros Adamson Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 3 +++ include/linux/nfs_xdr.h | 1 + 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 87694ca86914..f23b18831559 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -16,6 +16,7 @@ struct nfs4_sequence_args; struct nfs4_sequence_res; struct nfs_server; struct nfs4_minor_version_ops; +struct server_scope; /* * The nfs_client identifies our client state to the server. @@ -83,6 +84,8 @@ struct nfs_client { #ifdef CONFIG_NFS_FSCACHE struct fscache_cookie *fscache; /* client index cache cookie */ #endif + + struct server_scope *server_scope; /* from exchange_id */ }; /* diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 00848d86ffb2..c4d98df884f3 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1060,6 +1060,7 @@ struct server_scope { struct nfs41_exchange_id_res { struct nfs_client *client; u32 flags; + struct server_scope *server_scope; }; struct nfs41_create_session_args { -- cgit v1.2.3 From 6382a44138e7aa40bf52170e7afc014443a24806 Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Wed, 1 Jun 2011 16:44:44 -0400 Subject: NFS: move pnfs layouts to nfs_server structure Layouts should be tracked per nfs_server (aka superblock) instead of per struct nfs_client, which may have multiple FSIDs associated with it. Signed-off-by: Weston Andros Adamson Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index f23b18831559..4faeac8f448a 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -78,7 +78,6 @@ struct nfs_client { /* The flags used for obtaining the clientid during EXCHANGE_ID */ u32 cl_exchange_flags; struct nfs4_session *cl_session; /* sharred session */ - struct list_head cl_layouts; #endif /* CONFIG_NFS_V4 */ #ifdef CONFIG_NFS_FSCACHE @@ -152,6 +151,7 @@ struct nfs_server { struct rb_root openowner_id; struct rb_root lockowner_id; #endif + struct list_head layouts; struct list_head delegations; void (*destroy)(struct nfs_server *); -- cgit v1.2.3 From fca78d6d2c77f87d7dbee89bbe4836a44da881e2 Mon Sep 17 00:00:00 2001 From: Bryan Schumaker Date: Thu, 2 Jun 2011 14:59:07 -0400 Subject: NFS: Add SECINFO_NO_NAME procedure If the client is using NFS v4.1, then we can use SECINFO_NO_NAME to find the secflavor for the initial mount. If the server doesn't support SECINFO_NO_NAME then I fall back on the "guess and check" method used for v4.0 mounts. Signed-off-by: Bryan Schumaker Signed-off-by: Trond Myklebust --- include/linux/nfs4.h | 1 + include/linux/nfs_xdr.h | 8 ++++++++ 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 504b289ba680..7cc7d5745be5 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -563,6 +563,7 @@ enum { NFSPROC4_CLNT_GETDEVICEINFO, NFSPROC4_CLNT_LAYOUTCOMMIT, NFSPROC4_CLNT_LAYOUTRETURN, + NFSPROC4_CLNT_SECINFO_NO_NAME, }; /* nfs41 types */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index c4d98df884f3..7159e1da63b6 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1084,6 +1084,14 @@ struct nfs41_reclaim_complete_args { struct nfs41_reclaim_complete_res { struct nfs4_sequence_res seq_res; }; + +#define SECINFO_STYLE_CURRENT_FH 0 +#define SECINFO_STYLE_PARENT 1 +struct nfs41_secinfo_no_name_args { + int style; + struct nfs4_sequence_args seq_args; +}; + #endif /* CONFIG_NFS_V4_1 */ struct nfs_page; -- cgit v1.2.3 From 7d9747947ae66d8f6a9a9a023a3a5e28df6a536e Mon Sep 17 00:00:00 2001 From: Bryan Schumaker Date: Thu, 2 Jun 2011 14:59:08 -0400 Subject: NFS: Added TEST_STATEID call This patch adds in the xdr for doing a TEST_STATEID call with a single stateid. RFC 5661 allows multiple stateids to be tested in a single call, but only testing one keeps things simpler for now. Signed-off-by: Bryan Schumaker Signed-off-by: Trond Myklebust --- include/linux/nfs4.h | 1 + include/linux/nfs_xdr.h | 10 ++++++++++ 2 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 7cc7d5745be5..efe07f7a8765 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -564,6 +564,7 @@ enum { NFSPROC4_CLNT_LAYOUTCOMMIT, NFSPROC4_CLNT_LAYOUTRETURN, NFSPROC4_CLNT_SECINFO_NO_NAME, + NFSPROC4_CLNT_TEST_STATEID, }; /* nfs41 types */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 7159e1da63b6..e696c1fb139a 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1092,6 +1092,16 @@ struct nfs41_secinfo_no_name_args { struct nfs4_sequence_args seq_args; }; +struct nfs41_test_stateid_args { + nfs4_stateid *stateid; + struct nfs4_sequence_args seq_args; +}; + +struct nfs41_test_stateid_res { + unsigned int status; + struct nfs4_sequence_res seq_res; +}; + #endif /* CONFIG_NFS_V4_1 */ struct nfs_page; -- cgit v1.2.3 From 9aeda35fd643eba683fdb8dba8907fa796a85dda Mon Sep 17 00:00:00 2001 From: Bryan Schumaker Date: Thu, 2 Jun 2011 14:59:09 -0400 Subject: NFS: added FREE_STATEID call FREE_STATEID is used to tell the server that we want to free a stateid that no longer has any locks associated with it. This allows the client to reclaim locks without encountering edge conditions documented in section 8.4.3 of RFC 5661. Signed-off-by: Bryan Schumaker Signed-off-by: Trond Myklebust --- include/linux/nfs4.h | 1 + include/linux/nfs_xdr.h | 10 ++++++++++ 2 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index efe07f7a8765..a3c4bc800dce 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -565,6 +565,7 @@ enum { NFSPROC4_CLNT_LAYOUTRETURN, NFSPROC4_CLNT_SECINFO_NO_NAME, NFSPROC4_CLNT_TEST_STATEID, + NFSPROC4_CLNT_FREE_STATEID, }; /* nfs41 types */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index e696c1fb139a..209455561749 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1102,6 +1102,16 @@ struct nfs41_test_stateid_res { struct nfs4_sequence_res seq_res; }; +struct nfs41_free_stateid_args { + nfs4_stateid *stateid; + struct nfs4_sequence_args seq_args; +}; + +struct nfs41_free_stateid_res { + unsigned int status; + struct nfs4_sequence_res seq_res; +}; + #endif /* CONFIG_NFS_V4_1 */ struct nfs_page; -- cgit v1.2.3 From 1751c3638f2a07a8c66a803a31791bab9bd3fced Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 10 Jun 2011 13:30:23 -0400 Subject: NFS: Cleanup of the nfs_pageio code in preparation for a pnfs bugfix We need to ensure that the layouts are set up before we can decide to coalesce requests. To do so, we want to further split up the struct nfs_pageio_descriptor operations into an initialisation callback, a coalescing test callback, and a 'do i/o' callback. This patch cleans up the existing callback methods before adding the 'initialisation' callback. Signed-off-by: Trond Myklebust --- include/linux/nfs_page.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 25311b3bedf8..d378f08b905e 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -55,6 +55,12 @@ struct nfs_page { struct nfs_writeverf wb_verf; /* Commit cookie */ }; +struct nfs_pageio_descriptor; +struct nfs_pageio_ops { + bool (*pg_test)(struct nfs_pageio_descriptor *, struct nfs_page *, struct nfs_page *); + int (*pg_doio)(struct nfs_pageio_descriptor *); +}; + struct nfs_pageio_descriptor { struct list_head pg_list; unsigned long pg_bytes_written; @@ -64,11 +70,10 @@ struct nfs_pageio_descriptor { char pg_moreio; struct inode *pg_inode; - int (*pg_doio)(struct nfs_pageio_descriptor *); + const struct nfs_pageio_ops *pg_ops; int pg_ioflags; int pg_error; struct pnfs_layout_segment *pg_lseg; - bool (*pg_test)(struct nfs_pageio_descriptor *, struct nfs_page *, struct nfs_page *); }; #define NFS_WBACK_BUSY(req) (test_bit(PG_BUSY,&(req)->wb_flags)) @@ -85,7 +90,7 @@ extern int nfs_scan_list(struct nfs_inode *nfsi, struct list_head *dst, pgoff_t idx_start, unsigned int npages, int tag); extern void nfs_pageio_init(struct nfs_pageio_descriptor *desc, struct inode *inode, - int (*doio)(struct nfs_pageio_descriptor *desc), + const struct nfs_pageio_ops *pg_ops, size_t bsize, int how); extern int nfs_pageio_add_request(struct nfs_pageio_descriptor *, @@ -100,6 +105,9 @@ extern void nfs_unlock_request(struct nfs_page *req); extern int nfs_set_page_tag_locked(struct nfs_page *req); extern void nfs_clear_page_tag_locked(struct nfs_page *req); +extern int nfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc); +extern int nfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc); + /* * Lock the page of an asynchronous request without getting a new reference -- cgit v1.2.3 From d8007d4dd6ff8749cc8a4063c3ec87442db76d82 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 10 Jun 2011 13:30:23 -0400 Subject: NFSv4.1: Add an initialisation callback for pNFS Ensure that we always get a layout before setting up the i/o request. Signed-off-by: Trond Myklebust --- include/linux/nfs_page.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index d378f08b905e..9ac2dd158d0b 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -57,6 +57,7 @@ struct nfs_page { struct nfs_pageio_descriptor; struct nfs_pageio_ops { + void (*pg_init)(struct nfs_pageio_descriptor *, struct nfs_page *); bool (*pg_test)(struct nfs_pageio_descriptor *, struct nfs_page *, struct nfs_page *); int (*pg_doio)(struct nfs_pageio_descriptor *); }; -- cgit v1.2.3 From aa5c01446610f0305f96251d0f9621866b8e5a14 Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Mon, 13 Jun 2011 17:52:55 -0400 Subject: pnfs-obj: pnfs_osd_xdr: Remove dead code and cleanup * Some leftovers from ancient times. * This file will only define common types and client API. Remove server from comments Signed-off-by: Boaz Harrosh Signed-off-by: Trond Myklebust --- include/linux/pnfs_osd_xdr.h | 31 ++----------------------------- 1 file changed, 2 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pnfs_osd_xdr.h b/include/linux/pnfs_osd_xdr.h index 76efbdd01622..435dd5fa7453 100644 --- a/include/linux/pnfs_osd_xdr.h +++ b/include/linux/pnfs_osd_xdr.h @@ -41,9 +41,6 @@ #include #include -#include - -#define PNFS_OSD_OSDNAME_MAXSIZE 256 /* * draft-ietf-nfsv4-minorversion-22 @@ -99,12 +96,6 @@ struct pnfs_osd_objid { #define _DEVID_HI(oid_device_id) \ (unsigned long long)be64_to_cpup(((__be64 *)(oid_device_id)->data) + 1) -static inline int -pnfs_osd_objid_xdr_sz(void) -{ - return (NFS4_DEVICEID4_SIZE / 4) + 2 + 2; -} - enum pnfs_osd_version { PNFS_OSD_MISSING = 0, PNFS_OSD_VERSION_1 = 1, @@ -189,8 +180,6 @@ struct pnfs_osd_targetid { struct nfs4_string oti_scsi_device_id; }; -enum { PNFS_OSD_TARGETID_MAX = 1 + PNFS_OSD_OSDNAME_MAXSIZE / 4 }; - /* struct netaddr4 { * // see struct rpcb in RFC1833 * string r_netid<>; // network id @@ -207,12 +196,6 @@ struct pnfs_osd_targetaddr { struct pnfs_osd_net_addr ota_netaddr; }; -enum { - NETWORK_ID_MAX = 16 / 4, - UNIVERSAL_ADDRESS_MAX = 64 / 4, - PNFS_OSD_TARGETADDR_MAX = 3 + NETWORK_ID_MAX + UNIVERSAL_ADDRESS_MAX, -}; - struct pnfs_osd_deviceaddr { struct pnfs_osd_targetid oda_targetid; struct pnfs_osd_targetaddr oda_targetaddr; @@ -222,15 +205,6 @@ struct pnfs_osd_deviceaddr { struct nfs4_string oda_osdname; }; -enum { - ODA_OSDNAME_MAX = PNFS_OSD_OSDNAME_MAXSIZE / 4, - PNFS_OSD_DEVICEADDR_MAX = - PNFS_OSD_TARGETID_MAX + PNFS_OSD_TARGETADDR_MAX + - 2 /*oda_lun*/ + - 1 + OSD_SYSTEMID_LEN + - 1 + ODA_OSDNAME_MAX, -}; - /* LAYOUTCOMMIT: layoutupdate */ /* union pnfs_osd_deltaspaceused4 switch (bool dsu_valid) { @@ -279,7 +253,7 @@ struct pnfs_osd_ioerr { u32 oer_errno; }; -/* OSD XDR API */ +/* OSD XDR Client API */ /* Layout helpers */ /* Layout decoding is done in two parts: * 1. First Call pnfs_osd_xdr_decode_layout_map to read in only the header part @@ -337,8 +311,7 @@ extern int pnfs_osd_xdr_encode_layoutupdate(struct xdr_stream *xdr, struct pnfs_osd_layoutupdate *lou); -/* osd_ioerror encoding/decoding (layout_return) */ -/* Client */ +/* osd_ioerror encoding (layout_return) */ extern __be32 *pnfs_osd_xdr_ioerr_reserve_space(struct xdr_stream *xdr); extern void pnfs_osd_xdr_encode_ioerr(__be32 *p, struct pnfs_osd_ioerr *ioerr); -- cgit v1.2.3 From a56aaa02b1f723e28b41d339ddff02e958d32d43 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 15 Jun 2011 11:59:10 -0400 Subject: NFSv4.1: Clean up layoutreturn Since we take a reference to it, we really ought to pass the a pointer to the layout header in the arguments instead of assuming that NFS_I(inode)->layout will forever point to the correct object. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 209455561749..956d3576df7f 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -269,9 +269,10 @@ struct nfs4_layoutcommit_data { }; struct nfs4_layoutreturn_args { - __u32 layout_type; + struct pnfs_layout_hdr *layout; struct inode *inode; nfs4_stateid stateid; + __u32 layout_type; struct nfs4_sequence_args seq_args; }; -- cgit v1.2.3 From 6e4efd568574221840ee8dd86f176dc977c1330c Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 12 Jul 2011 13:42:02 -0400 Subject: NFS: Clean up nfs_read_rpcsetup and nfs_write_rpcsetup Split them up into two parts: one which sets up the struct nfs_read/write_data, the other which sets up the actual RPC call or pNFS call. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 956d3576df7f..5b115956abac 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1126,6 +1126,7 @@ struct nfs_read_data { struct rpc_cred *cred; struct nfs_fattr fattr; /* fattr storage */ struct list_head pages; /* Coalesced read requests */ + struct list_head list; /* lists of struct nfs_read_data */ struct nfs_page *req; /* multi ops per nfs_page */ struct page **pagevec; unsigned int npages; /* Max length of pagevec */ @@ -1149,6 +1150,7 @@ struct nfs_write_data { struct nfs_fattr fattr; struct nfs_writeverf verf; struct list_head pages; /* Coalesced requests we wish to flush */ + struct list_head list; /* lists of struct nfs_write_data */ struct nfs_page *req; /* multi ops per nfs_page */ struct page **pagevec; unsigned int npages; /* Max length of pagevec */ -- cgit v1.2.3 From e2270ea62ae4d7a47d6d72942cdb8c669be6357a Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 12 Jul 2011 10:37:21 -0700 Subject: netdevice: Kill 'feature' test macros. Almost all of these have long outstayed their welcome. And for every one of these macros, there are 10 features for which we didn't add macros. Let's just delete them all, and get out of habit of doing things this way. Signed-off-by: David S. Miller Acked-by: Stephen Hemminger Acked-by: Arnd Bergmann --- include/linux/netdevice.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 011eb89e9582..30f17e42c304 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -60,11 +60,6 @@ struct wireless_dev; #define SET_ETHTOOL_OPS(netdev,ops) \ ( (netdev)->ethtool_ops = (ops) ) -#define HAVE_ALLOC_NETDEV /* feature macro: alloc_xxxdev - functions are available. */ -#define HAVE_FREE_NETDEV /* free_netdev() */ -#define HAVE_NETDEV_PRIV /* netdev_priv() */ - /* hardware address assignment types */ #define NET_ADDR_PERM 0 /* address is permanent (default) */ #define NET_ADDR_RANDOM 1 /* address is generated randomly */ @@ -313,7 +308,6 @@ struct header_ops { const void *saddr, unsigned len); int (*parse)(const struct sk_buff *skb, unsigned char *haddr); int (*rebuild)(struct sk_buff *skb); -#define HAVE_HEADER_CACHE int (*cache)(const struct neighbour *neigh, struct hh_cache *hh); void (*cache_update)(struct hh_cache *hh, const struct net_device *dev, @@ -887,7 +881,6 @@ struct netdev_tc_txq { * Must return >0 or -errno if it changed dev->features itself. * */ -#define HAVE_NET_DEVICE_OPS struct net_device_ops { int (*ndo_init)(struct net_device *dev); void (*ndo_uninit)(struct net_device *dev); @@ -1781,8 +1774,6 @@ static inline void input_queue_tail_incr_save(struct softnet_data *sd, DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); -#define HAVE_NETIF_QUEUE - extern void __netif_schedule(struct Qdisc *q); static inline void netif_schedule_queue(struct netdev_queue *txq) @@ -2058,10 +2049,8 @@ extern void dev_kfree_skb_irq(struct sk_buff *skb); */ extern void dev_kfree_skb_any(struct sk_buff *skb); -#define HAVE_NETIF_RX 1 extern int netif_rx(struct sk_buff *skb); extern int netif_rx_ni(struct sk_buff *skb); -#define HAVE_NETIF_RECEIVE_SKB 1 extern int netif_receive_skb(struct sk_buff *skb); extern gro_result_t dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb); @@ -2241,7 +2230,6 @@ extern void netif_device_attach(struct net_device *dev); /* * Network interface message level settings */ -#define HAVE_NETIF_MSG 1 enum { NETIF_MSG_DRV = 0x0001, -- cgit v1.2.3 From 1e01979c8f502ac13e3cdece4f38712c5944e6e8 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 12 Jul 2011 09:45:34 +0200 Subject: x86, numa: Implement pfn -> nid mapping granularity check SPARSEMEM w/o VMEMMAP and DISCONTIGMEM, both used only on 32bit, use sections array to map pfn to nid which is limited in granularity. If NUMA nodes are laid out such that the mapping cannot be accurate, boot will fail triggering BUG_ON() in mminit_verify_page_links(). On 32bit, it's 512MiB w/ PAE and SPARSEMEM. This seems to have been granular enough until commit 2706a0bf7b (x86, NUMA: Enable CONFIG_AMD_NUMA on 32bit too). Apparently, there is a machine which aligns NUMA nodes to 128MiB and has only AMD NUMA but not SRAT. This led to the following BUG_ON(). On node 0 totalpages: 2096615 DMA zone: 32 pages used for memmap DMA zone: 0 pages reserved DMA zone: 3927 pages, LIFO batch:0 Normal zone: 1740 pages used for memmap Normal zone: 220978 pages, LIFO batch:31 HighMem zone: 16405 pages used for memmap HighMem zone: 1853533 pages, LIFO batch:31 BUG: Int 6: CR2 (null) EDI (null) ESI 00000002 EBP 00000002 ESP c1543ecc EBX f2400000 EDX 00000006 ECX (null) EAX 00000001 err (null) EIP c16209aa CS 00000060 flg 00010002 Stack: f2400000 00220000 f7200800 c1620613 00220000 01000000 04400000 00238000 (null) f7200000 00000002 f7200b58 f7200800 c1620929 000375fe (null) f7200b80 c16395f0 00200a02 f7200a80 (null) 000375fe 00000002 (null) Pid: 0, comm: swapper Not tainted 2.6.39-rc5-00181-g2706a0b #17 Call Trace: [] ? early_fault+0x2e/0x2e [] ? mminit_verify_page_links+0x12/0x42 [] ? memmap_init_zone+0xaf/0x10c [] ? free_area_init_node+0x2b9/0x2e3 [] ? free_area_init_nodes+0x3f2/0x451 [] ? paging_init+0x112/0x118 [] ? setup_arch+0x791/0x82f [] ? start_kernel+0x6a/0x257 This patch implements node_map_pfn_alignment() which determines maximum internode alignment and update numa_register_memblks() to reject NUMA configuration if alignment exceeds the pfn -> nid mapping granularity of the memory model as determined by PAGES_PER_SECTION. This makes the problematic machine boot w/ flatmem by rejecting the NUMA config and provides protection against crazy NUMA configurations. Signed-off-by: Tejun Heo Link: http://lkml.kernel.org/r/20110712074534.GB2872@htj.dyndns.org LKML-Reference: <20110628174613.GP478@escobedo.osrc.amd.com> Reported-and-Tested-by: Hans Rosenfeld Cc: Conny Seidel Signed-off-by: H. Peter Anvin --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9670f71d7be9..c70a326b8f26 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1313,6 +1313,7 @@ extern void remove_active_range(unsigned int nid, unsigned long start_pfn, unsigned long end_pfn); extern void remove_all_active_ranges(void); void sort_node_map(void); +unsigned long node_map_pfn_alignment(void); unsigned long __absent_pages_in_range(int nid, unsigned long start_pfn, unsigned long end_pfn); extern unsigned long absent_pages_in_range(unsigned long start_pfn, -- cgit v1.2.3 From e69dd336ee3a05a589629b505b18ba5e7a5b4c54 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 12 Jul 2011 23:28:12 -0700 Subject: net: Push protocol type directly down to header_ops->cache() Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 2 +- include/linux/netdevice.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index ab68f785fd19..05955cf09937 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -38,7 +38,7 @@ extern int eth_header(struct sk_buff *skb, struct net_device *dev, const void *daddr, const void *saddr, unsigned len); extern int eth_rebuild_header(struct sk_buff *skb); extern int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr); -extern int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh); +extern int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh, __be16 type); extern void eth_header_cache_update(struct hh_cache *hh, const struct net_device *dev, const unsigned char *haddr); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 30f17e42c304..564d89fdddda 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -308,7 +308,7 @@ struct header_ops { const void *saddr, unsigned len); int (*parse)(const struct sk_buff *skb, unsigned char *haddr); int (*rebuild)(struct sk_buff *skb); - int (*cache)(const struct neighbour *neigh, struct hh_cache *hh); + int (*cache)(const struct neighbour *neigh, struct hh_cache *hh, __be16 type); void (*cache_update)(struct hh_cache *hh, const struct net_device *dev, const unsigned char *haddr); -- cgit v1.2.3 From 5c25f686db352082eef8daa21b760192351a023a Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 13 Jul 2011 00:51:10 -0700 Subject: net: Kill support for multiple hh_cache entries per neighbour This never, ever, happens. Neighbour entries are always tied to one address family, and therefore one set of dst_ops, and therefore one dst_ops->protocol "hh_type" value. This capability was blindly imported by Alexey Kuznetsov when he wrote the neighbour layer. Signed-off-by: David S. Miller --- include/linux/netdevice.h | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 564d89fdddda..75382378a1ba 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -252,7 +252,6 @@ struct netdev_hw_addr_list { netdev_hw_addr_list_for_each(ha, &(dev)->mc) struct hh_cache { - struct hh_cache *hh_next; /* Next entry */ atomic_t hh_refcnt; /* number of users */ /* * We want hh_output, hh_len, hh_lock and hh_data be a in a separate @@ -260,12 +259,8 @@ struct hh_cache { * They are mostly read, but hh_refcnt may be changed quite frequently, * incurring cache line ping pongs. */ - __be16 hh_type ____cacheline_aligned_in_smp; - /* protocol identifier, f.e ETH_P_IP - * NOTE: For VLANs, this will be the - * encapuslated type. --BLG - */ - u16 hh_len; /* length of header */ + u16 hh_len ____cacheline_aligned_in_smp; + u16 __pad; int (*hh_output)(struct sk_buff *skb); seqlock_t hh_lock; -- cgit v1.2.3 From 5125bbf3880755419eff68672623cde49c4f31e8 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 13 Jul 2011 12:31:52 +0200 Subject: PM / Domains: Introduce function to power off all unused PM domains Add a new function pm_genpd_poweroff_unused() queuing up the execution of pm_genpd_poweroff() for every initialized generic PM domain. Calling it will cause every generic PM domain without devices in use to be powered off. Signed-off-by: Rafael J. Wysocki Acked-by: Magnus Damm --- include/linux/pm_domain.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index feb80af4cc1b..3e4f3d308f5e 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -24,6 +24,7 @@ struct dev_power_governor { struct generic_pm_domain { struct dev_pm_domain domain; /* PM domain operations */ + struct list_head gpd_list_node; /* Node in the global PM domains list */ struct list_head sd_node; /* Node in the parent's subdomain list */ struct generic_pm_domain *parent; /* Parent PM domain */ struct list_head sd_list; /* List of dubdomains */ @@ -71,6 +72,7 @@ extern int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, extern void pm_genpd_init(struct generic_pm_domain *genpd, struct dev_power_governor *gov, bool is_off); extern int pm_genpd_poweron(struct generic_pm_domain *genpd); +extern void pm_genpd_poweroff_unused(void); #else static inline int pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev) @@ -98,6 +100,7 @@ static inline int pm_genpd_poweron(struct generic_pm_domain *genpd) { return -ENOSYS; } +static inline void pm_genpd_poweroff_unused(void) {} #endif #endif /* _LINUX_PM_DOMAIN_H */ -- cgit v1.2.3 From 433bd805e5fd2c731b3a9025b034f066272d336e Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Wed, 13 Jul 2011 09:24:13 -0400 Subject: clocksource: Replace vread with generic arch data The vread field was bloating struct clocksource everywhere except x86_64, and I want to change the way this works on x86_64, so let's split it out into per-arch data. Cc: x86@kernel.org Cc: Clemens Ladisch Cc: linux-ia64@vger.kernel.org Cc: Tony Luck Cc: Fenghua Yu Cc: John Stultz Cc: Thomas Gleixner Signed-off-by: Andy Lutomirski Link: http://lkml.kernel.org/r/3ae5ec76a168eaaae63f08a2a1060b91aa0b7759.1310563276.git.luto@mit.edu Signed-off-by: H. Peter Anvin --- include/linux/clocksource.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index d4646b48dc4a..0fb83c224471 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -22,6 +22,8 @@ typedef u64 cycle_t; struct clocksource; +#include + /** * struct cyclecounter - hardware abstraction for a free running counter * Provides completely state-free accessors to the underlying hardware. @@ -153,7 +155,7 @@ extern u64 timecounter_cyc2time(struct timecounter *tc, * @shift: cycle to nanosecond divisor (power of two) * @max_idle_ns: max idle time permitted by the clocksource (nsecs) * @flags: flags describing special properties - * @vread: vsyscall based read + * @archdata: arch-specific data * @suspend: suspend function for the clocksource, if necessary * @resume: resume function for the clocksource, if necessary */ @@ -175,10 +177,14 @@ struct clocksource { #else #define CLKSRC_FSYS_MMIO_SET(mmio, addr) do { } while (0) #endif + +#ifdef __ARCH_HAS_CLOCKSOURCE_DATA + struct arch_clocksource_data archdata; +#endif + const char *name; struct list_head list; int rating; - cycle_t (*vread)(void); int (*enable)(struct clocksource *cs); void (*disable)(struct clocksource *cs); unsigned long flags; -- cgit v1.2.3 From f39b2dd9d065151a04f5996656d1f27a7eb32d45 Mon Sep 17 00:00:00 2001 From: Philip Rakity Date: Thu, 7 Jul 2011 09:04:55 -0700 Subject: mmc: core: Bus width testing needs to handle suspend/resume On reading the ext_csd for the first time (in 1 bit mode), save the ext_csd information needed for bus width compare. On every pass we make re-reading the ext_csd, compare the data against the saved ext_csd data. This fixes a regression introduced in 3.0-rc1 by 08ee80cc397ac1a3 ("mmc: core: eMMC bus width may not work on all platforms"), which incorrectly assumed we would be re-reading the ext_csd at resume- time. Signed-off-by: Philip Rakity Tested-by: Jaehoon Chung Signed-off-by: Chris Ball --- include/linux/mmc/card.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index c6927a4d157f..6ad43554ac05 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -64,6 +64,19 @@ struct mmc_ext_csd { unsigned long long enhanced_area_offset; /* Units: Byte */ unsigned int enhanced_area_size; /* Units: KB */ unsigned int boot_size; /* in bytes */ + u8 raw_partition_support; /* 160 */ + u8 raw_erased_mem_count; /* 181 */ + u8 raw_ext_csd_structure; /* 194 */ + u8 raw_card_type; /* 196 */ + u8 raw_s_a_timeout; /* 217 */ + u8 raw_hc_erase_gap_size; /* 221 */ + u8 raw_erase_timeout_mult; /* 223 */ + u8 raw_hc_erase_grp_size; /* 224 */ + u8 raw_sec_trim_mult; /* 229 */ + u8 raw_sec_erase_mult; /* 230 */ + u8 raw_sec_feature_support;/* 231 */ + u8 raw_trim_mult; /* 232 */ + u8 raw_sectors[4]; /* 212 - 4 bytes */ }; struct sd_scr { -- cgit v1.2.3 From d7b7630130e52361af66ce3b994696e2357ba7de Mon Sep 17 00:00:00 2001 From: Richard Kennedy Date: Wed, 13 Jul 2011 21:17:23 +0200 Subject: block: reorder request_queue to remove 64 bit alignment padding Reorder request_queue to remove 16 bytes of alignment padding in 64 bit builds. On my config this shrinks the size of this structure from 1608 to 1592 bytes and therefore needs one fewer cachelines. Also trivially move the open bracket { to be on the same line as the structure name to make it easier to grep. Signed-off-by: Richard Kennedy Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6dcea6885a5d..c0cd9a2f22ef 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -260,8 +260,7 @@ struct queue_limits { unsigned char discard_zeroes_data; }; -struct request_queue -{ +struct request_queue { /* * Together with queue_head for cacheline sharing */ @@ -304,14 +303,14 @@ struct request_queue void *queuedata; /* - * queue needs bounce pages for pages above this limit + * various queue flags, see QUEUE_* below */ - gfp_t bounce_gfp; + unsigned long queue_flags; /* - * various queue flags, see QUEUE_* below + * queue needs bounce pages for pages above this limit */ - unsigned long queue_flags; + gfp_t bounce_gfp; /* * protects queue structures from reentrancy. ->__queue_lock should @@ -334,8 +333,8 @@ struct request_queue unsigned int nr_congestion_off; unsigned int nr_batching; - void *dma_drain_buffer; unsigned int dma_drain_size; + void *dma_drain_buffer; unsigned int dma_pad_mask; unsigned int dma_alignment; -- cgit v1.2.3 From eccddd32ced0df8f9130024157bf8d37df860d76 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 13 Jul 2011 13:14:20 +0800 Subject: ACPI, APEI, Add APEI bit support in generic _OSC call In APEI firmware first mode, hardware error is reported by hardware to firmware firstly, then firmware reports the error to Linux in a GHES error record via POLL/SCI/IRQ/NMI etc. This may result in some issues if OS has no full APEI support. So some firmware implementation will work in a back-compatible mode by default. Where firmware will only notify OS in old-fashion, without GHES record. For example, for a fatal hardware error, only NMI is signaled, no GHES record. To gain full APEI power on these machines, APEI bit in generic _OSC call can be specified to tell firmware that Linux has full APEI support. This patch adds the APEI bit support in generic _OSC call. Signed-off-by: Huang Ying Reviewed-by: Andi Kleen Reviewed-by: Matthew Garrett Signed-off-by: Len Brown --- include/linux/acpi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 1deb2a73c2da..e19527de6a93 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -280,6 +280,8 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); #define OSC_SB_CPUHP_OST_SUPPORT 8 #define OSC_SB_APEI_SUPPORT 16 +extern bool osc_sb_apei_support_acked; + /* PCI defined _OSC bits */ /* _OSC DW1 Definition (OS Support Fields) */ #define OSC_EXT_PCI_CONFIG_SUPPORT 1 -- cgit v1.2.3 From c9aaa8957f203bd6df83b002fb40b98390bed078 Mon Sep 17 00:00:00 2001 From: Glauber Costa Date: Mon, 11 Jul 2011 15:28:14 -0400 Subject: KVM: Steal time implementation To implement steal time, we need the hypervisor to pass the guest information about how much time was spent running other processes outside the VM, while the vcpu had meaningful work to do - halt time does not count. This information is acquired through the run_delay field of delayacct/schedstats infrastructure, that counts time spent in a runqueue but not running. Steal time is a per-cpu information, so the traditional MSR-based infrastructure is used. A new msr, KVM_MSR_STEAL_TIME, holds the memory area address containing information about steal time This patch contains the hypervisor part of the steal time infrasructure, and can be backported independently of the guest portion. [avi, yongjie: export delayacct_on, to avoid build failures in some configs] Signed-off-by: Glauber Costa Tested-by: Eric B Munson CC: Rik van Riel CC: Jeremy Fitzhardinge CC: Peter Zijlstra CC: Anthony Liguori Signed-off-by: Yongjie Ren Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index f7df0a3b031d..c8e023902f79 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -47,6 +47,7 @@ #define KVM_REQ_DEACTIVATE_FPU 10 #define KVM_REQ_EVENT 11 #define KVM_REQ_APF_HALT 12 +#define KVM_REQ_STEAL_UPDATE 13 #define KVM_USERSPACE_IRQ_SOURCE_ID 0 -- cgit v1.2.3 From f6b72b6217f8c24f2a54988e58af858b4e66024d Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Thu, 14 Jul 2011 07:53:20 -0700 Subject: net: Embed hh_cache inside of struct neighbour. Now that there is a one-to-one correspondance between neighbour and hh_cache entries, we no longer need: 1) dynamic allocation 2) attachment to dst->hh 3) refcounting Initialization of the hh_cache entry is indicated by hh_len being non-zero, and such initialization is always done with the neighbour's lock held as a writer. Signed-off-by: David S. Miller --- include/linux/netdevice.h | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 75382378a1ba..5ccc0cb8352b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -252,14 +252,7 @@ struct netdev_hw_addr_list { netdev_hw_addr_list_for_each(ha, &(dev)->mc) struct hh_cache { - atomic_t hh_refcnt; /* number of users */ -/* - * We want hh_output, hh_len, hh_lock and hh_data be a in a separate - * cache line on SMP. - * They are mostly read, but hh_refcnt may be changed quite frequently, - * incurring cache line ping pongs. - */ - u16 hh_len ____cacheline_aligned_in_smp; + u16 hh_len; u16 __pad; int (*hh_output)(struct sk_buff *skb); seqlock_t hh_lock; @@ -273,12 +266,6 @@ struct hh_cache { unsigned long hh_data[HH_DATA_ALIGN(LL_MAX_HEADER) / sizeof(long)]; }; -static inline void hh_cache_put(struct hh_cache *hh) -{ - if (atomic_dec_and_test(&hh->hh_refcnt)) - kfree(hh); -} - /* Reserve HH_DATA_MOD byte aligned hard_header_len, but at least that much. * Alternative is: * dev->hard_header_len ? (dev->hard_header_len + -- cgit v1.2.3 From 0bc5b2debb832191a42baea7ff59d2ca6ce9f7d5 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 14 Jul 2011 20:59:07 +0200 Subject: ARM / shmobile: Use genpd_queue_power_off_work() Make pd_power_down_a3rv() use genpd_queue_power_off_work() to queue up the powering off of the A4LC domain to avoid queuing it up when it is pending. Signed-off-by: Rafael J. Wysocki Acked-by: Magnus Damm --- include/linux/pm_domain.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 3e4f3d308f5e..21097cb086fe 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -73,6 +73,7 @@ extern void pm_genpd_init(struct generic_pm_domain *genpd, struct dev_power_governor *gov, bool is_off); extern int pm_genpd_poweron(struct generic_pm_domain *genpd); extern void pm_genpd_poweroff_unused(void); +extern void genpd_queue_power_off_work(struct generic_pm_domain *genpd); #else static inline int pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev) @@ -101,6 +102,7 @@ static inline int pm_genpd_poweron(struct generic_pm_domain *genpd) return -ENOSYS; } static inline void pm_genpd_poweroff_unused(void) {} +static inline void genpd_queue_power_off_work(struct generic_pm_domain *gpd) {} #endif #endif /* _LINUX_PM_DOMAIN_H */ -- cgit v1.2.3 From 4a9bd3f134decd6d16ead8d288342d57aad486be Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 14 Jul 2011 16:36:53 -0400 Subject: tracing: Have dynamic size event stack traces Currently the stack trace per event in ftace is only 8 frames. This can be quite limiting and sometimes useless. Especially when the "ignore frames" is wrong and we also use up stack frames for the event processing itself. Change this to be dynamic by adding a percpu buffer that we can write a large stack frame into and then copy into the ring buffer. For interrupts and NMIs that come in while another event is being process, will only get to use the 8 frame stack. That should be enough as the task that it interrupted will have the full stack frame anyway. Requested-by: Thomas Gleixner Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index b1e69eefc203..96efa6794ea5 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -76,6 +76,7 @@ struct trace_iterator { struct trace_entry *ent; unsigned long lost_events; int leftover; + int ent_size; int cpu; u64 ts; -- cgit v1.2.3 From fec30c33819b442fd618b10f405248ee7cbb51d8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Miros=C5=82aw?= Date: Wed, 13 Jul 2011 14:10:30 +0000 Subject: net: unexport netdev_fix_features() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It is not used anywhere except net/core/dev.c now. Signed-off-by: Michał Mirosław Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5ccc0cb8352b..f84dfd25c431 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2529,7 +2529,6 @@ static inline u32 netdev_get_wanted_features(struct net_device *dev) return (dev->features & ~dev->hw_features) | dev->wanted_features; } u32 netdev_increment_features(u32 all, u32 one, u32 mask); -u32 netdev_fix_features(struct net_device *dev, u32 features); int __netdev_update_features(struct net_device *dev); void netdev_update_features(struct net_device *dev); void netdev_change_features(struct net_device *dev); -- cgit v1.2.3 From e20e6940736fb7b4dd024933f7456b9da4c44118 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Miros=C5=82aw?= Date: Thu, 14 Jul 2011 14:45:59 -0700 Subject: net: remove SK_ROUTE_CAPS from meta ematch MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Remove it, as it indirectly exposes netdev features. It's not used in iproute2 (2.6.38) - is anything else using its interface? Signed-off-by: Michał Mirosław Signed-off-by: David S. Miller --- include/linux/tc_ematch/tc_em_meta.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tc_ematch/tc_em_meta.h b/include/linux/tc_ematch/tc_em_meta.h index 7138962664f8..b11f8ce2d3c0 100644 --- a/include/linux/tc_ematch/tc_em_meta.h +++ b/include/linux/tc_ematch/tc_em_meta.h @@ -67,7 +67,7 @@ enum { TCF_META_ID_SK_FORWARD_ALLOCS, TCF_META_ID_SK_SNDBUF, TCF_META_ID_SK_ALLOCS, - TCF_META_ID_SK_ROUTE_CAPS, + __TCF_META_ID_SK_ROUTE_CAPS, /* unimplemented but in ABI already */ TCF_META_ID_SK_HASH, TCF_META_ID_SK_LINGERTIME, TCF_META_ID_SK_ACK_BACKLOG, -- cgit v1.2.3 From 62f2a3a48bdc99822a24356e667e52c30df287c9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Miros=C5=82aw?= Date: Wed, 13 Jul 2011 14:10:29 +0000 Subject: net: remove NETIF_F_ALL_TX_OFFLOADS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is no software fallback implemented for SCTP or FCoE checksumming, and so it should not be passed on by software devices like bridge or bonding. For VLAN devices, this is different. First, the driver for underlying device should be prepared to get offloaded packets even when the feature is disabled (especially if it advertises it in vlan_features). Second, devices under VLANs do not get replaced without tearing down the VLAN first. This fixes a mess I accidentally introduced while converting bonding to ndo_fix_features. NETIF_F_SOFT_FEATURES are removed from BOND_VLAN_FEATURES because they are unused as of commit 712ae51afd. Signed-off-by: Michał Mirosław Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 54b8b4d7b68f..9e19477991ad 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1097,12 +1097,6 @@ struct net_device { #define NETIF_F_ALL_FCOE (NETIF_F_FCOE_CRC | NETIF_F_FCOE_MTU | \ NETIF_F_FSO) -#define NETIF_F_ALL_TX_OFFLOADS (NETIF_F_ALL_CSUM | NETIF_F_SG | \ - NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | \ - NETIF_F_HIGHDMA | \ - NETIF_F_SCTP_CSUM | \ - NETIF_F_ALL_FCOE) - /* * If one device supports one of these features, then enable them * for all in netdev_increment_features. -- cgit v1.2.3 From 574c44fa8fa6262ffd5939789ef51a6e98ed62d7 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Wed, 13 Jul 2011 09:24:15 -0400 Subject: ia64: Replace clocksource.fsys_mmio with generic arch data Now that clocksource.archdata is available, use it for ia64-specific code. Cc: Clemens Ladisch Cc: linux-ia64@vger.kernel.org Cc: Tony Luck Cc: Fenghua Yu Cc: John Stultz Cc: Thomas Gleixner Signed-off-by: Andy Lutomirski Link: http://lkml.kernel.org/r/d31de0ee0842a0e322fb6441571c2b0adb323fa2.1310563276.git.luto@mit.edu Signed-off-by: H. Peter Anvin --- include/linux/clocksource.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 0fb83c224471..6bb69702c4fa 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -171,13 +171,6 @@ struct clocksource { u32 shift; u64 max_idle_ns; -#ifdef CONFIG_IA64 - void *fsys_mmio; /* used by fsyscall asm code */ -#define CLKSRC_FSYS_MMIO_SET(mmio, addr) ((mmio) = (addr)) -#else -#define CLKSRC_FSYS_MMIO_SET(mmio, addr) do { } while (0) -#endif - #ifdef __ARCH_HAS_CLOCKSOURCE_DATA struct arch_clocksource_data archdata; #endif -- cgit v1.2.3 From 50828d7e6767a92726708bc0666e2b8b84575808 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 12 Jul 2011 13:42:02 -0400 Subject: NFS: Cache rpc_ops in struct nfs_pageio_descriptor Signed-off-by: Trond Myklebust --- include/linux/nfs_page.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 9ac2dd158d0b..db3194f63479 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -74,6 +74,7 @@ struct nfs_pageio_descriptor { const struct nfs_pageio_ops *pg_ops; int pg_ioflags; int pg_error; + const struct rpc_call_ops *pg_rpc_callops; struct pnfs_layout_segment *pg_lseg; }; -- cgit v1.2.3 From d9156f9f364897e93bdd98b4ad22138de18f7c24 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 12 Jul 2011 13:42:02 -0400 Subject: NFS: Allow the nfs_pageio_descriptor to signal that a re-coalesce is needed If an attempt to do pNFS fails, and we have to fall back to writing through the MDS, then we may want to re-coalesce the requests that we already have since the block size for the MDS read/writes may be different to that of the DS read/writes. Signed-off-by: Trond Myklebust --- include/linux/nfs_page.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index db3194f63479..7241b2a2a4d6 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -68,7 +68,8 @@ struct nfs_pageio_descriptor { size_t pg_count; size_t pg_bsize; unsigned int pg_base; - char pg_moreio; + unsigned char pg_moreio : 1, + pg_recoalesce : 1; struct inode *pg_inode; const struct nfs_pageio_ops *pg_ops; -- cgit v1.2.3 From 493292ddc78d18ee2ad2d5c24c2b7dd6a24641d2 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 13 Jul 2011 15:58:28 -0400 Subject: NFS: Move the pnfs read code into pnfs.c ...and ensure that we recoalese to take into account differences in block sizes when falling back to read through the MDS. Signed-off-by: Trond Myklebust --- include/linux/nfs_page.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 7241b2a2a4d6..0a48f842f83c 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -108,7 +108,6 @@ extern void nfs_unlock_request(struct nfs_page *req); extern int nfs_set_page_tag_locked(struct nfs_page *req); extern void nfs_clear_page_tag_locked(struct nfs_page *req); -extern int nfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc); extern int nfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc); -- cgit v1.2.3 From dce81290eed64d24493989bb7a08f9e20495e184 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 13 Jul 2011 15:59:19 -0400 Subject: NFS: Move the pnfs write code into pnfs.c ...and ensure that we recoalese to take into account differences in differences in block sizes when falling back to write through the MDS. Signed-off-by: Trond Myklebust --- include/linux/nfs_page.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 0a48f842f83c..e2791a27a901 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -108,9 +108,6 @@ extern void nfs_unlock_request(struct nfs_page *req); extern int nfs_set_page_tag_locked(struct nfs_page *req); extern void nfs_clear_page_tag_locked(struct nfs_page *req); -extern int nfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc); - - /* * Lock the page of an asynchronous request without getting a new reference */ -- cgit v1.2.3 From 9e00abc3c20904fd6a5d888bb7023925799ec8a5 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 13 Jul 2011 19:20:49 -0400 Subject: SUNRPC: sunrpc should not explicitly depend on NFS config options Change explicit references to CONFIG_NFS_V4_1 to implicit ones Get rid of the unnecessary defines in backchannel_rqst.c and bc_svc.c: the Makefile takes care of those dependency. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/bc_xprt.h | 6 +++--- include/linux/sunrpc/svc.h | 4 ++-- include/linux/sunrpc/xprt.h | 16 ++++++++-------- 3 files changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h index 082884295f80..f7f3ce340c08 100644 --- a/include/linux/sunrpc/bc_xprt.h +++ b/include/linux/sunrpc/bc_xprt.h @@ -31,7 +31,7 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. #include #include -#ifdef CONFIG_NFS_V4_1 +#ifdef CONFIG_SUNRPC_BACKCHANNEL struct rpc_rqst *xprt_alloc_bc_request(struct rpc_xprt *xprt); void xprt_free_bc_request(struct rpc_rqst *req); int xprt_setup_backchannel(struct rpc_xprt *, unsigned int min_reqs); @@ -47,7 +47,7 @@ static inline int svc_is_backchannel(const struct svc_rqst *rqstp) return 1; return 0; } -#else /* CONFIG_NFS_V4_1 */ +#else /* CONFIG_SUNRPC_BACKCHANNEL */ static inline int xprt_setup_backchannel(struct rpc_xprt *xprt, unsigned int min_reqs) { @@ -62,6 +62,6 @@ static inline int svc_is_backchannel(const struct svc_rqst *rqstp) static inline void xprt_free_bc_request(struct rpc_rqst *req) { } -#endif /* CONFIG_NFS_V4_1 */ +#endif /* CONFIG_SUNRPC_BACKCHANNEL */ #endif /* _LINUX_SUNRPC_BC_XPRT_H */ diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index ea29330b78bd..9a3fa7baf4b8 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -92,7 +92,7 @@ struct svc_serv { struct module * sv_module; /* optional module to count when * adding threads */ svc_thread_fn sv_function; /* main function for threads */ -#if defined(CONFIG_NFS_V4_1) +#if defined(CONFIG_SUNRPC_BACKCHANNEL) struct list_head sv_cb_list; /* queue for callback requests * that arrive over the same * connection */ @@ -100,7 +100,7 @@ struct svc_serv { wait_queue_head_t sv_cb_waitq; /* sleep here if there are no * entries in the svc_cb_list */ struct svc_xprt *sv_bc_xprt; /* callback on fore channel */ -#endif /* CONFIG_NFS_V4_1 */ +#endif /* CONFIG_SUNRPC_BACKCHANNEL */ }; /* diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 81cce3b3ee66..217b0206581b 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -100,11 +100,11 @@ struct rpc_rqst { ktime_t rq_xtime; /* transmit time stamp */ int rq_ntrans; -#if defined(CONFIG_NFS_V4_1) +#if defined(CONFIG_SUNRPC_BACKCHANNEL) struct list_head rq_bc_list; /* Callback service list */ unsigned long rq_bc_pa_state; /* Backchannel prealloc state */ struct list_head rq_bc_pa_list; /* Backchannel prealloc list */ -#endif /* CONFIG_NFS_V4_1 */ +#endif /* CONFIG_SUNRPC_BACKCHANEL */ }; #define rq_svec rq_snd_buf.head #define rq_slen rq_snd_buf.len @@ -200,7 +200,7 @@ struct rpc_xprt { u32 xid; /* Next XID value to use */ struct rpc_task * snd_task; /* Task blocked in send */ struct svc_xprt *bc_xprt; /* NFSv4.1 backchannel */ -#if defined(CONFIG_NFS_V4_1) +#if defined(CONFIG_SUNRPC_BACKCHANNEL) struct svc_serv *bc_serv; /* The RPC service which will */ /* process the callback */ unsigned int bc_alloc_count; /* Total number of preallocs */ @@ -208,7 +208,7 @@ struct rpc_xprt { * items */ struct list_head bc_pa_list; /* List of preallocated * backchannel rpc_rqst's */ -#endif /* CONFIG_NFS_V4_1 */ +#endif /* CONFIG_SUNRPC_BACKCHANNEL */ struct list_head recv; struct { @@ -228,15 +228,15 @@ struct rpc_xprt { const char *address_strings[RPC_DISPLAY_MAX]; }; -#if defined(CONFIG_NFS_V4_1) +#if defined(CONFIG_SUNRPC_BACKCHANNEL) /* * Backchannel flags */ #define RPC_BC_PA_IN_USE 0x0001 /* Preallocated backchannel */ /* buffer in use */ -#endif /* CONFIG_NFS_V4_1 */ +#endif /* CONFIG_SUNRPC_BACKCHANNEL */ -#if defined(CONFIG_NFS_V4_1) +#if defined(CONFIG_SUNRPC_BACKCHANNEL) static inline int bc_prealloc(struct rpc_rqst *req) { return test_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state); @@ -246,7 +246,7 @@ static inline int bc_prealloc(struct rpc_rqst *req) { return 0; } -#endif /* CONFIG_NFS_V4_1 */ +#endif /* CONFIG_SUNRPC_BACKCHANNEL */ struct xprt_create { int ident; /* XPRT_TRANSPORT identifier */ -- cgit v1.2.3 From 77dbbb138986b26cb99f868d4b6410577ef4c040 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 13 Jul 2011 10:48:55 +0200 Subject: nl80211: advertise GTK rekey support, new triggers Since we now have the necessary API in place to support GTK rekeying, applications will need to know whether it is supported by a device. Add a pseudo-trigger that is used only to advertise that capability. Also, add some new triggers that match what iwlagn devices can do. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nl80211.h | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 8cb025a00094..c5f577e9ee27 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -989,8 +989,8 @@ enum nl80211_commands { * driving the peer link management state machine. * @NL80211_MESH_SETUP_USERSPACE_AMPE must be enabled. * - * @NL80211_ATTR_WOWLAN_SUPPORTED: indicates, as part of the wiphy capabilities, - * the supported WoWLAN triggers + * @NL80211_ATTR_WOWLAN_TRIGGERS_SUPPORTED: indicates, as part of the wiphy + * capabilities, the supported WoWLAN triggers * @NL80211_ATTR_WOWLAN_TRIGGERS: used by %NL80211_CMD_SET_WOWLAN to * indicate which WoW triggers should be enabled. This is also * used by %NL80211_CMD_GET_WOWLAN to get the currently enabled WoWLAN @@ -2255,6 +2255,16 @@ struct nl80211_wowlan_pattern_support { * * In %NL80211_ATTR_WOWLAN_TRIGGERS_SUPPORTED, it is a binary attribute * carrying a &struct nl80211_wowlan_pattern_support. + * @NL80211_WOWLAN_TRIG_GTK_REKEY_SUPPORTED: Not a real trigger, and cannot be + * used when setting, used only to indicate that GTK rekeying is supported + * by the device (flag) + * @NL80211_WOWLAN_TRIG_GTK_REKEY_FAILURE: wake up on GTK rekey failure (if + * done by the device) (flag) + * @NL80211_WOWLAN_TRIG_EAP_IDENT_REQUEST: wake up on EAP Identity Request + * packet (flag) + * @NL80211_WOWLAN_TRIG_4WAY_HANDSHAKE: wake up on 4-way handshake (flag) + * @NL80211_WOWLAN_TRIG_RFKILL_RELEASE: wake up when rfkill is released + * (on devices that have rfkill in the device) (flag) * @NUM_NL80211_WOWLAN_TRIG: number of wake on wireless triggers * @MAX_NL80211_WOWLAN_TRIG: highest wowlan trigger attribute number */ @@ -2264,6 +2274,11 @@ enum nl80211_wowlan_triggers { NL80211_WOWLAN_TRIG_DISCONNECT, NL80211_WOWLAN_TRIG_MAGIC_PKT, NL80211_WOWLAN_TRIG_PKT_PATTERN, + NL80211_WOWLAN_TRIG_GTK_REKEY_SUPPORTED, + NL80211_WOWLAN_TRIG_GTK_REKEY_FAILURE, + NL80211_WOWLAN_TRIG_EAP_IDENT_REQUEST, + NL80211_WOWLAN_TRIG_4WAY_HANDSHAKE, + NL80211_WOWLAN_TRIG_RFKILL_RELEASE, /* keep last */ NUM_NL80211_WOWLAN_TRIG, -- cgit v1.2.3 From 93b6aa693a355932b69c96956596b03f91baec35 Mon Sep 17 00:00:00 2001 From: Luciano Coelho Date: Wed, 13 Jul 2011 14:57:28 +0300 Subject: nl80211/cfg80211: add max_sched_scan_ssids in the hw description Some chips can scan more SSIDs with a single scheduled scan command than with a single normal scan command (eg. wl12xx chips). To support this, this patch creates a separate hardware description element that describes the amount of SSIDs supported in scheduled scans. Signed-off-by: Luciano Coelho Signed-off-by: John W. Linville --- include/linux/nl80211.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index c5f577e9ee27..159dda9c2c9f 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -756,6 +756,8 @@ enum nl80211_commands { * * @NL80211_ATTR_MAX_NUM_SCAN_SSIDS: number of SSIDs you can scan with * a single scan request, a wiphy attribute. + * @NL80211_ATTR_MAX_NUM_SCHED_SCAN_SSIDS: number of SSIDs you can + * scan with a single scheduled scan request, a wiphy attribute. * @NL80211_ATTR_MAX_SCAN_IE_LEN: maximum length of information elements * that can be added to a scan request * @@ -1210,6 +1212,8 @@ enum nl80211_attrs { NL80211_ATTR_REKEY_DATA, + NL80211_ATTR_MAX_NUM_SCHED_SCAN_SSIDS, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, -- cgit v1.2.3 From 5a865bad44984de245d20bfb7cff99993e8e8294 Mon Sep 17 00:00:00 2001 From: Luciano Coelho Date: Wed, 13 Jul 2011 14:57:29 +0300 Subject: nl80211/cfg80211: add max_sched_scan_ie_len in the hw description Some chips may support different lengths of user-supplied IEs with a single scheduled scan command than with a single normal scan command. To support this, this patch creates a separate hardware description element that describes the maximum size of user-supplied information element data supported in scheduled scans. Signed-off-by: Luciano Coelho Signed-off-by: John W. Linville --- include/linux/nl80211.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 159dda9c2c9f..7ba71e42449e 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -760,6 +760,8 @@ enum nl80211_commands { * scan with a single scheduled scan request, a wiphy attribute. * @NL80211_ATTR_MAX_SCAN_IE_LEN: maximum length of information elements * that can be added to a scan request + * @NL80211_ATTR_MAX_SCHED_SCAN_IE_LEN: maximum length of information + * elements that can be added to a scheduled scan request * * @NL80211_ATTR_SCAN_FREQUENCIES: nested attribute with frequencies (in MHz) * @NL80211_ATTR_SCAN_SSIDS: nested attribute with SSIDs, leave out for passive @@ -1213,6 +1215,7 @@ enum nl80211_attrs { NL80211_ATTR_REKEY_DATA, NL80211_ATTR_MAX_NUM_SCHED_SCAN_SSIDS, + NL80211_ATTR_MAX_SCHED_SCAN_IE_LEN, /* add attributes here, update the policy in nl80211.c */ -- cgit v1.2.3 From 1bb6f9b042eb1428ba927d2e851a00df6308877a Mon Sep 17 00:00:00 2001 From: Peter Korsgaard Date: Fri, 15 Jul 2011 10:25:30 +0200 Subject: mcp23s08: get rid of setup/teardown callbacks There's no in-tree users, and bus notifiers are more generic anyway. Signed-off-by: Peter Korsgaard Signed-off-by: Grant Likely --- include/linux/spi/mcp23s08.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/mcp23s08.h b/include/linux/spi/mcp23s08.h index c42cff8ca191..2d676d5aaa89 100644 --- a/include/linux/spi/mcp23s08.h +++ b/include/linux/spi/mcp23s08.h @@ -22,13 +22,4 @@ struct mcp23s08_platform_data { * base to base+15 (or base+31 for s17 variant). */ unsigned base; - - void *context; /* param to setup/teardown */ - - int (*setup)(struct spi_device *spi, - int gpio, unsigned ngpio, - void *context); - int (*teardown)(struct spi_device *spi, - int gpio, unsigned ngpio, - void *context); }; -- cgit v1.2.3 From 99f381d3549432a250fe846a2a82d61a032804b0 Mon Sep 17 00:00:00 2001 From: Nishanth Menon Date: Fri, 10 Jun 2011 20:24:57 +0200 Subject: PM / OPP: Introduce function to free cpufreq table cpufreq table allocated by opp_init_cpufreq_table is better freed by OPP layer itself. This allows future modifications to the table handling to be transparent to the users. Signed-off-by: Nishanth Menon Acked-by: Kevin Hilman Signed-off-by: Rafael J. Wysocki --- include/linux/opp.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/opp.h b/include/linux/opp.h index 5449945d589f..7020e9736fc5 100644 --- a/include/linux/opp.h +++ b/include/linux/opp.h @@ -94,12 +94,20 @@ static inline int opp_disable(struct device *dev, unsigned long freq) #if defined(CONFIG_CPU_FREQ) && defined(CONFIG_PM_OPP) int opp_init_cpufreq_table(struct device *dev, struct cpufreq_frequency_table **table); +void opp_free_cpufreq_table(struct device *dev, + struct cpufreq_frequency_table **table); #else static inline int opp_init_cpufreq_table(struct device *dev, struct cpufreq_frequency_table **table) { return -EINVAL; } + +static inline +void opp_free_cpufreq_table(struct device *dev, + struct cpufreq_frequency_table **table) +{ +} #endif /* CONFIG_CPU_FREQ */ #endif /* __LINUX_OPP_H__ */ -- cgit v1.2.3 From 3b5fe85252326217cd96f24a7bda4460d8f71bee Mon Sep 17 00:00:00 2001 From: MyungJoo Ham Date: Sun, 12 Jun 2011 15:57:05 +0200 Subject: PM / Suspend: Add .suspend_again() callback to suspend_ops A system or a device may need to control suspend/wakeup events. It may want to wakeup the system after a predefined amount of time or at a predefined event decided while entering suspend for polling or delayed work. Then, it may want to enter suspend again if its predefined wakeup condition is the only wakeup reason and there is no outstanding events; thus, it does not wakeup the userspace unnecessary or unnecessary devices and keeps suspended as long as possible (saving the power). Enabling a system to wakeup after a specified time can be easily achieved by using RTC. However, to enter suspend again immediately without invoking userland and unrelated devices, we need additional features in the suspend framework. Such need comes from: 1. Monitoring a critical device status without interrupts that can wakeup the system. (in-suspend polling) An example is ambient temperature monitoring that needs to shut down the system or a specific device function if it is too hot or cold. The temperature of a specific device may be needed to be monitored as well; e.g., a charger monitors battery temperature in order to stop charging if overheated. 2. Execute critical "delayed work" at suspend. A driver or a system/board may have a delayed work (or any similar things) that it wants to execute at the requested time. For example, some chargers want to check the battery voltage some time (e.g., 30 seconds) after the battery is fully charged and the charger has stopped. Then, the charger restarts charging if the voltage has dropped more than a threshold, which is smaller than "restart-charger" voltage, which is a threshold to restart charging regardless of the time passed. This patch allows to add "suspend_again" callback at struct platform_suspend_ops and let the "suspend_again" callback return true if the system is required to enter suspend again after the current instance of wakeup. Device-wise suspend_again implemented at dev_pm_ops or syscore is not done because: a) suspend_again feature is usually under platform-wise decision and controls the behavior of the whole platform and b) There are very limited devices related to the usage cases of suspend_again; chargers and temperature sensors are mentioned so far. With suspend_again callback registered at struct platform_suspend_ops suspend_ops in kernel/power/suspend.c with suspend_set_ops by the platform, the suspend framework tries to enter suspend again by looping suspend_enter() if suspend_again has returned true and there has been no errors in the suspending sequence or pending wakeups (by pm_wakeup_pending). Tested at Exynos4-NURI. [rjw: Fixed up kerneldoc comment for suspend_enter().] Signed-off-by: MyungJoo Ham Signed-off-by: Kyungmin Park Acked-by: Pavel Machek Signed-off-by: Rafael J. Wysocki --- include/linux/suspend.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 083ffea7ba18..e1e3742733be 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -92,6 +92,13 @@ typedef int __bitwise suspend_state_t; * @enter() and @wake(), even if any of them fails. It is executed after * a failing @prepare. * + * @suspend_again: Returns whether the system should suspend again (true) or + * not (false). If the platform wants to poll sensors or execute some + * code during suspended without invoking userspace and most of devices, + * suspend_again callback is the place assuming that periodic-wakeup or + * alarm-wakeup is already setup. This allows to execute some codes while + * being kept suspended in the view of userland and devices. + * * @end: Called by the PM core right after resuming devices, to indicate to * the platform that the system has returned to the working state or * the transition to the sleep state has been aborted. @@ -113,6 +120,7 @@ struct platform_suspend_ops { int (*enter)(suspend_state_t state); void (*wake)(void); void (*finish)(void); + bool (*suspend_again)(void); void (*end)(void); void (*recover)(void); }; -- cgit v1.2.3 From 49b28684fdba2c84a3b8e54aaa0faa9ce2e4f140 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 21 Jun 2011 15:27:43 +1000 Subject: nfsd: Remove deprecated nfsctl system call and related code. As promised in feature-removal-schedule.txt it is time to remove the nfsctl system call. Userspace has perferred to not use this call throughout 2.6 and it has been excluded in the default configuration since 2.6.36 (9 months ago). So this patch removes all the code that was being compiled out. There are still references to sys_nfsctl in various arch systemcall tables and related code. These should be cleaned out too, probably in the next merge window. Signed-off-by: NeilBrown Signed-off-by: J. Bruce Fields --- include/linux/compat.h | 9 --------- include/linux/nfsd/export.h | 2 -- include/linux/sunrpc/cache.h | 9 --------- 3 files changed, 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 846bb1792572..8779405e15a8 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -438,16 +438,7 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds, struct compat_timespec __user *tsp, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize); -#if (defined(CONFIG_NFSD) || defined(CONFIG_NFSD_MODULE)) && \ - !defined(CONFIG_NFSD_DEPRECATED) -union compat_nfsctl_res; -struct compat_nfsctl_arg; -asmlinkage long compat_sys_nfsservctl(int cmd, - struct compat_nfsctl_arg __user *arg, - union compat_nfsctl_res __user *res); -#else asmlinkage long compat_sys_nfsservctl(int cmd, void *notused, void *notused2); -#endif asmlinkage long compat_sys_signalfd4(int ufd, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize, int flags); diff --git a/include/linux/nfsd/export.h b/include/linux/nfsd/export.h index 84058ec69390..8a31a20efe7e 100644 --- a/include/linux/nfsd/export.h +++ b/include/linux/nfsd/export.h @@ -133,8 +133,6 @@ __be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp); int nfsd_export_init(void); void nfsd_export_shutdown(void); void nfsd_export_flush(void); -void exp_readlock(void); -void exp_readunlock(void); struct svc_export * rqst_exp_get_by_name(struct svc_rqst *, struct path *); struct svc_export * rqst_exp_parent(struct svc_rqst *, diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index 8d2eef1a8582..d1c79a906397 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -256,13 +256,4 @@ static inline time_t get_expiry(char **bpp) return rv - boot.tv_sec; } -#ifdef CONFIG_NFSD_DEPRECATED -static inline void sunrpc_invalidate(struct cache_head *h, - struct cache_detail *detail) -{ - h->expiry_time = seconds_since_boot() - 1; - detail->nextcheck = seconds_since_boot(); -} -#endif /* CONFIG_NFSD_DEPRECATED */ - #endif /* _LINUX_SUNRPC_CACHE_H_ */ -- cgit v1.2.3 From 93b37905f70083d6143f5f4dba0a45cc64379a62 Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Sat, 9 Jul 2011 16:43:22 +0200 Subject: firewire: cdev: prevent race between first get_info ioctl and bus reset event queuing Between open(2) of a /dev/fw* and the first FW_CDEV_IOC_GET_INFO ioctl(2) on it, the kernel already queues FW_CDEV_EVENT_BUS_RESET events to be read(2) by the client. The get_info ioctl is practically always issued right away after open, hence this condition only occurs if the client opens during a bus reset, especially during a rapid series of bus resets. The problem with this condition is twofold: - These bus reset events carry the (as yet undocumented) @closure value of 0. But it is not the kernel's place to choose closures; they are privat to the client. E.g., this 0 value forced from the kernel makes it unsafe for clients to dereference it as a pointer to a closure object without NULL pointer check. - It is impossible for clients to determine the relative order of bus reset events from get_info ioctl(2) versus those from read(2), except in one way: By comparison of closure values. Again, such a procedure imposes complexity on clients and reduces freedom in use of the bus reset closure. So, change the ABI to suppress queuing of bus reset events before the first FW_CDEV_IOC_GET_INFO ioctl was issued by the client. Note, this ABI change cannot be version-controlled. The kernel cannot distinguish old from new clients before the first FW_CDEV_IOC_GET_INFO ioctl. We will try to back-merge this change into currently maintained stable/ longterm series, and we only document the new behaviour. The old behavior is now considered a kernel bug, which it basically is. Signed-off-by: Stefan Richter Cc: --- include/linux/firewire-cdev.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index 4ff09889c5c0..55814aa33be2 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -475,6 +475,9 @@ union fw_cdev_event { * of the bus. This does not cause a bus reset to happen. * @bus_reset_closure: Value of &closure in this and subsequent bus reset events * @card: The index of the card this device belongs to + * + * As a side effect, reception of %FW_CDEV_EVENT_BUS_RESET events to be read(2) + * is started by this ioctl. */ struct fw_cdev_get_info { __u32 version; -- cgit v1.2.3 From f6a7cd0212c359f7b55414aeee364ee7cac363cc Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Thu, 14 Jul 2011 21:08:39 +0200 Subject: firewire: cdev: ABI documentation enhancements Add overview documentation in Documentation/ABI/stable/firewire-cdev. Improve the inline reference documentation in firewire-cdev.h: - Add /* available since kernel... */ comments to event numbers consistent with the comments on ioctl numbers. - Shorten some documentation on an event and an ioctl that are less interesting to current programming because there are newer preferable variants. - Spell Configuration ROM (name of an IEEE 1212 register) in upper case. - Move the dummy FW_CDEV_VERSION out of the reader's field of vision. We should remove it from the header next year or so. Signed-off-by: Stefan Richter --- include/linux/firewire-cdev.h | 75 ++++++++++++++++++++----------------------- 1 file changed, 34 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index 55814aa33be2..357dbfc2829e 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -30,10 +30,13 @@ #include #include +/* available since kernel version 2.6.22 */ #define FW_CDEV_EVENT_BUS_RESET 0x00 #define FW_CDEV_EVENT_RESPONSE 0x01 #define FW_CDEV_EVENT_REQUEST 0x02 #define FW_CDEV_EVENT_ISO_INTERRUPT 0x03 + +/* available since kernel version 2.6.30 */ #define FW_CDEV_EVENT_ISO_RESOURCE_ALLOCATED 0x04 #define FW_CDEV_EVENT_ISO_RESOURCE_DEALLOCATED 0x05 @@ -120,24 +123,11 @@ struct fw_cdev_event_response { /** * struct fw_cdev_event_request - Old version of &fw_cdev_event_request2 - * @closure: See &fw_cdev_event_common; set by %FW_CDEV_IOC_ALLOCATE ioctl * @type: See &fw_cdev_event_common; always %FW_CDEV_EVENT_REQUEST - * @tcode: See &fw_cdev_event_request2 - * @offset: See &fw_cdev_event_request2 - * @handle: See &fw_cdev_event_request2 - * @length: See &fw_cdev_event_request2 - * @data: See &fw_cdev_event_request2 * * This event is sent instead of &fw_cdev_event_request2 if the kernel or - * the client implements ABI version <= 3. - * - * Unlike &fw_cdev_event_request2, the sender identity cannot be established, - * broadcast write requests cannot be distinguished from unicast writes, and - * @tcode of lock requests is %TCODE_LOCK_REQUEST. - * - * Requests to the FCP_REQUEST or FCP_RESPONSE register are responded to as - * with &fw_cdev_event_request2, except in kernel 2.6.32 and older which send - * the response packet of the client's %FW_CDEV_IOC_SEND_RESPONSE ioctl. + * the client implements ABI version <= 3. &fw_cdev_event_request lacks + * essential information; use &fw_cdev_event_request2 instead. */ struct fw_cdev_event_request { __u64 closure; @@ -452,30 +442,29 @@ union fw_cdev_event { * %FW_CDEV_ISO_CONTEXT_RECEIVE_MULTICHANNEL, and * %FW_CDEV_IOC_SET_ISO_CHANNELS */ -#define FW_CDEV_VERSION 3 /* Meaningless; don't use this macro. */ /** * struct fw_cdev_get_info - General purpose information ioctl * @version: The version field is just a running serial number. Both an * input parameter (ABI version implemented by the client) and * output parameter (ABI version implemented by the kernel). - * A client must not fill in an %FW_CDEV_VERSION defined from an - * included kernel header file but the actual version for which - * the client was implemented. This is necessary for forward - * compatibility. We never break backwards compatibility, but - * may add more structs, events, and ioctls in later revisions. - * @rom_length: If @rom is non-zero, at most rom_length bytes of configuration + * A client shall fill in the ABI @version for which the client + * was implemented. This is necessary for forward compatibility. + * @rom_length: If @rom is non-zero, up to @rom_length bytes of Configuration * ROM will be copied into that user space address. In either * case, @rom_length is updated with the actual length of the - * configuration ROM. + * Configuration ROM. * @rom: If non-zero, address of a buffer to be filled by a copy of the - * device's configuration ROM + * device's Configuration ROM * @bus_reset: If non-zero, address of a buffer to be filled by a * &struct fw_cdev_event_bus_reset with the current state * of the bus. This does not cause a bus reset to happen. * @bus_reset_closure: Value of &closure in this and subsequent bus reset events * @card: The index of the card this device belongs to * + * The %FW_CDEV_IOC_GET_INFO ioctl is usually the very first one which a client + * performs right after it opened a /dev/fw* file. + * * As a side effect, reception of %FW_CDEV_EVENT_BUS_RESET events to be read(2) * is started by this ioctl. */ @@ -615,7 +604,7 @@ struct fw_cdev_initiate_bus_reset { * @handle: Handle to the descriptor, written by the kernel * * Add a descriptor block and optionally a preceding immediate key to the local - * node's configuration ROM. + * node's Configuration ROM. * * The @key field specifies the upper 8 bits of the descriptor root directory * pointer and the @data and @length fields specify the contents. The @key @@ -630,9 +619,9 @@ struct fw_cdev_initiate_bus_reset { * If successful, the kernel adds the descriptor and writes back a @handle to * the kernel-side object to be used for later removal of the descriptor block * and immediate key. The kernel will also generate a bus reset to signal the - * change of the configuration ROM to other nodes. + * change of the Configuration ROM to other nodes. * - * This ioctl affects the configuration ROMs of all local nodes. + * This ioctl affects the Configuration ROMs of all local nodes. * The ioctl only succeeds on device files which represent a local node. */ struct fw_cdev_add_descriptor { @@ -644,13 +633,13 @@ struct fw_cdev_add_descriptor { }; /** - * struct fw_cdev_remove_descriptor - Remove contents from the configuration ROM + * struct fw_cdev_remove_descriptor - Remove contents from the Configuration ROM * @handle: Handle to the descriptor, as returned by the kernel when the * descriptor was added * * Remove a descriptor block and accompanying immediate key from the local - * nodes' configuration ROMs. The kernel will also generate a bus reset to - * signal the change of the configuration ROM to other nodes. + * nodes' Configuration ROMs. The kernel will also generate a bus reset to + * signal the change of the Configuration ROM to other nodes. */ struct fw_cdev_remove_descriptor { __u32 handle; @@ -866,13 +855,8 @@ struct fw_cdev_stop_iso { * @local_time: system time, in microseconds since the Epoch * @cycle_timer: Cycle Time register contents * - * The %FW_CDEV_IOC_GET_CYCLE_TIMER ioctl reads the isochronous cycle timer - * and also the system clock (%CLOCK_REALTIME). This allows to express the - * receive time of an isochronous packet as a system time. - * - * @cycle_timer consists of 7 bits cycleSeconds, 13 bits cycleCount, and - * 12 bits cycleOffset, in host byte order. Cf. the Cycle Time register - * per IEEE 1394 or Isochronous Cycle Timer register per OHCI-1394. + * Same as %FW_CDEV_IOC_GET_CYCLE_TIMER2, but fixed to use %CLOCK_REALTIME + * and only with microseconds resolution. * * In version 1 and 2 of the ABI, this ioctl returned unreliable (non- * monotonic) @cycle_timer values on certain controllers. @@ -889,10 +873,17 @@ struct fw_cdev_get_cycle_timer { * @clk_id: input parameter, clock from which to get the system time * @cycle_timer: Cycle Time register contents * - * The %FW_CDEV_IOC_GET_CYCLE_TIMER2 works like - * %FW_CDEV_IOC_GET_CYCLE_TIMER but lets you choose a clock like with POSIX' - * clock_gettime function. Supported @clk_id values are POSIX' %CLOCK_REALTIME - * and %CLOCK_MONOTONIC and Linux' %CLOCK_MONOTONIC_RAW. + * The %FW_CDEV_IOC_GET_CYCLE_TIMER2 ioctl reads the isochronous cycle timer + * and also the system clock. This allows to correlate reception time of + * isochronous packets with system time. + * + * @clk_id lets you choose a clock like with POSIX' clock_gettime function. + * Supported @clk_id values are POSIX' %CLOCK_REALTIME and %CLOCK_MONOTONIC + * and Linux' %CLOCK_MONOTONIC_RAW. + * + * @cycle_timer consists of 7 bits cycleSeconds, 13 bits cycleCount, and + * 12 bits cycleOffset, in host byte order. Cf. the Cycle Time register + * per IEEE 1394 or Isochronous Cycle Timer register per OHCI-1394. */ struct fw_cdev_get_cycle_timer2 { __s64 tv_sec; @@ -1014,4 +1005,6 @@ struct fw_cdev_receive_phy_packets { __u64 closure; }; +#define FW_CDEV_VERSION 3 /* Meaningless legacy macro; don't use it. */ + #endif /* _LINUX_FIREWIRE_CDEV_H */ -- cgit v1.2.3 From b23b5455b6458920179a1f27513ce42e70d11f37 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sat, 16 Jul 2011 17:45:02 -0700 Subject: neigh: Kill hh_cache->hh_output It's just taking on one of two possible values, either neigh_ops->output or dev_queue_xmit(). And this is purely depending upon whether nud_state has NUD_CONNECTED set or not. Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f84dfd25c431..52c4e3835aa6 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -254,7 +254,6 @@ struct netdev_hw_addr_list { struct hh_cache { u16 hh_len; u16 __pad; - int (*hh_output)(struct sk_buff *skb); seqlock_t hh_lock; /* cached hardware header; allow for machine alignment needs. */ -- cgit v1.2.3 From 6634ae1033ceaeca5877dd75723210f8c2648c17 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 8 Jul 2011 19:13:39 +0200 Subject: ptrace_init_task: initialize child->jobctl explicitly new_child->jobctl is not initialized during the fork, it is copied from parent->jobctl. Currently this is harmless, the forking task is running and copy_process() can't succeed if signal_pending() is true, so only JOBCTL_STOP_DEQUEUED can be copied. Still this is a bit fragile, it would be more clean to set ->jobctl = 0 explicitly. Also, check ->ptrace != 0 instead of PT_PTRACED, move the CONFIG_HAVE_HW_BREAKPOINT code up. Signed-off-by: Oleg Nesterov Acked-by: Tejun Heo --- include/linux/ptrace.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index eae381d584f9..fd8669fc339f 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -217,16 +217,17 @@ static inline void ptrace_init_task(struct task_struct *child, bool ptrace) { INIT_LIST_HEAD(&child->ptrace_entry); INIT_LIST_HEAD(&child->ptraced); - child->parent = child->real_parent; +#ifdef CONFIG_HAVE_HW_BREAKPOINT + atomic_set(&child->ptrace_bp_refcnt, 1); +#endif + child->jobctl = 0; child->ptrace = 0; - if (unlikely(ptrace) && (current->ptrace & PT_PTRACED)) { + child->parent = child->real_parent; + + if (unlikely(ptrace) && current->ptrace) { child->ptrace = current->ptrace; __ptrace_link(child, current->parent); } - -#ifdef CONFIG_HAVE_HW_BREAKPOINT - atomic_set(&child->ptrace_bp_refcnt, 1); -#endif } /** -- cgit v1.2.3 From dcace06cc29df927a74a6bc0e57b9bef87704377 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 8 Jul 2011 19:13:54 +0200 Subject: ptrace: mv send-SIGSTOP from do_fork() to ptrace_init_task() If the new child is traced, do_fork() adds the pending SIGSTOP. It assumes that either it is traced because of auto-attach or the tracer attached later, in both cases sigaddset/set_thread_flag is correct even if SIGSTOP is already pending. Now that we have PTRACE_SEIZE this is no longer right in the latter case. If the tracer does PTRACE_SEIZE after copy_process() makes the child visible the queued SIGSTOP is wrong. We could check PT_SEIZED bit and change ptrace_attach() to set both PT_PTRACED and PT_SEIZED bits simultaneously but see the next patch, we need to know whether this child was auto-attached or not anyway. So this patch simply moves this code to ptrace_init_task(), this way we can never race with ptrace_attach(). Signed-off-by: Oleg Nesterov Acked-by: Tejun Heo --- include/linux/ptrace.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index fd8669fc339f..9b5d2c901d06 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -227,6 +227,9 @@ static inline void ptrace_init_task(struct task_struct *child, bool ptrace) if (unlikely(ptrace) && current->ptrace) { child->ptrace = current->ptrace; __ptrace_link(child, current->parent); + + sigaddset(&child->pending.signal, SIGSTOP); + set_tsk_thread_flag(child, TIF_SIGPENDING); } } -- cgit v1.2.3 From d184d6eb1dc3c9869e25a8e422be5c55ab0db4ac Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 8 Jul 2011 19:14:17 +0200 Subject: ptrace: dont send SIGSTOP on auto-attach if PT_SEIZED The fake SIGSTOP during attach has numerous problems. PTRACE_SEIZE is already fine, but we have basically the same problems is SIGSTOP is sent on auto-attach, the tracer can't know if this signal signal should be cancelled or not. Change ptrace_event() to set JOBCTL_TRAP_STOP if the new child is PT_SEIZED, this triggers the PTRACE_EVENT_STOP report. Thereafter a PT_SEIZED task can never report the bogus SIGSTOP. Test-case: #define PTRACE_SEIZE 0x4206 #define PTRACE_SEIZE_DEVEL 0x80000000 #define PTRACE_EVENT_STOP 7 #define WEVENT(s) ((s & 0xFF0000) >> 16) int main(void) { int child, grand_child, status; long message; child = fork(); if (!child) { kill(getpid(), SIGSTOP); fork(); assert(0); return 0x23; } assert(ptrace(PTRACE_SEIZE, child, 0,PTRACE_SEIZE_DEVEL) == 0); assert(wait(&status) == child); assert(WIFSTOPPED(status) && WSTOPSIG(status) == SIGSTOP); assert(ptrace(PTRACE_SETOPTIONS, child, 0, PTRACE_O_TRACEFORK) == 0); assert(ptrace(PTRACE_CONT, child, 0,0) == 0); assert(waitpid(child, &status, 0) == child); assert(WIFSTOPPED(status) && WSTOPSIG(status) == SIGTRAP); assert(WEVENT(status) == PTRACE_EVENT_FORK); assert(ptrace(PTRACE_GETEVENTMSG, child, 0, &message) == 0); grand_child = message; assert(waitpid(grand_child, &status, 0) == grand_child); assert(WIFSTOPPED(status) && WSTOPSIG(status) == SIGTRAP); assert(WEVENT(status) == PTRACE_EVENT_STOP); kill(child, SIGKILL); kill(grand_child, SIGKILL); return 0; } Signed-off-by: Oleg Nesterov Acked-by: Tejun Heo --- include/linux/ptrace.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 9b5d2c901d06..800f113bea66 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -228,7 +228,11 @@ static inline void ptrace_init_task(struct task_struct *child, bool ptrace) child->ptrace = current->ptrace; __ptrace_link(child, current->parent); - sigaddset(&child->pending.signal, SIGSTOP); + if (child->ptrace & PT_SEIZED) + task_set_jobctl_pending(child, JOBCTL_TRAP_STOP); + else + sigaddset(&child->pending.signal, SIGSTOP); + set_tsk_thread_flag(child, TIF_SIGPENDING); } } -- cgit v1.2.3 From 178edcbc6b539dfc21062fed9bf31701a8952e1c Mon Sep 17 00:00:00 2001 From: David Lamparter Date: Sun, 17 Jul 2011 08:32:12 +0000 Subject: net: add 802.1ad / 802.1ah / QinQ ethertypes define ETH_P_8021AD to 88a8 (assigned by IEEE) and add ETH_P_QINQ{1,2,3} for the pre-standard 9{1,2,3}00 types. all of them use 802.1q frame format, with 1 bit used differently in some cases. also define ETH_P_8021AH to 88e7 (assigned by IEEE). this is Mac-in-Mac and uses a different, 16-byte header. Signed-off-by: David Lamparter Signed-off-by: David S. Miller --- include/linux/if_ether.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h index 0065ffd3226b..a3d99ff6e3b5 100644 --- a/include/linux/if_ether.h +++ b/include/linux/if_ether.h @@ -78,10 +78,15 @@ */ #define ETH_P_PAE 0x888E /* Port Access Entity (IEEE 802.1X) */ #define ETH_P_AOE 0x88A2 /* ATA over Ethernet */ +#define ETH_P_8021AD 0x88A8 /* 802.1ad Service VLAN */ #define ETH_P_TIPC 0x88CA /* TIPC */ +#define ETH_P_8021AH 0x88E7 /* 802.1ah Backbone Service Tag */ #define ETH_P_1588 0x88F7 /* IEEE 1588 Timesync */ #define ETH_P_FCOE 0x8906 /* Fibre Channel over Ethernet */ #define ETH_P_FIP 0x8914 /* FCoE Initialization Protocol */ +#define ETH_P_QINQ1 0x9100 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */ +#define ETH_P_QINQ2 0x9200 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */ +#define ETH_P_QINQ3 0x9300 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */ #define ETH_P_EDSA 0xDADA /* Ethertype DSA [ NOT AN OFFICIALLY REGISTERED ID ] */ /* -- cgit v1.2.3 From 69ecca86da4890c13a5e29c51b4ac76a1a8a62c9 Mon Sep 17 00:00:00 2001 From: David Lamparter Date: Sun, 17 Jul 2011 08:53:12 +0000 Subject: net: vlan, qlcnic: make vlan_find_dev private there is only one user of vlan_find_dev outside of the actual vlan code: qlcnic uses it to iterate over some VLANs it knows. let's just make vlan_find_dev private to the VLAN code and have the iteration in qlcnic be a bit more direct. (a few rcu dereferences less too) Signed-off-by: David Lamparter Cc: Patrick McHardy Cc: Amit Kumar Salecha Cc: Anirban Chakraborty Cc: linux-driver@qlogic.com Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index affa27380b72..bc03e40fd7fd 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -119,17 +119,6 @@ static inline int is_vlan_dev(struct net_device *dev) #define vlan_tx_tag_get(__skb) ((__skb)->vlan_tci & ~VLAN_TAG_PRESENT) #if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE) -/* Must be invoked with rcu_read_lock or with RTNL. */ -static inline struct net_device *vlan_find_dev(struct net_device *real_dev, - u16 vlan_id) -{ - struct vlan_group *grp = rcu_dereference_rtnl(real_dev->vlgrp); - - if (grp) - return vlan_group_get_device(grp, vlan_id); - - return NULL; -} extern struct net_device *vlan_dev_real_dev(const struct net_device *dev); extern u16 vlan_dev_vlan_id(const struct net_device *dev); -- cgit v1.2.3 From 43cedbf0e8dfb9c5610eb7985d5f21263e313802 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 17 Jul 2011 16:01:03 -0400 Subject: SUNRPC: Ensure that we grab the XPRT_LOCK before calling xprt_alloc_slot This throttles the allocation of new slots when the socket is busy reconnecting and/or is out of buffer space. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 217b0206581b..a876882fb923 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -111,7 +111,7 @@ struct rpc_rqst { struct rpc_xprt_ops { void (*set_buffer_size)(struct rpc_xprt *xprt, size_t sndsize, size_t rcvsize); - int (*reserve_xprt)(struct rpc_task *task); + int (*reserve_xprt)(struct rpc_xprt *xprt, struct rpc_task *task); void (*release_xprt)(struct rpc_xprt *xprt, struct rpc_task *task); void (*rpcbind)(struct rpc_task *task); void (*set_port)(struct rpc_xprt *xprt, unsigned short port); @@ -271,8 +271,8 @@ struct xprt_class { struct rpc_xprt *xprt_create_transport(struct xprt_create *args); void xprt_connect(struct rpc_task *task); void xprt_reserve(struct rpc_task *task); -int xprt_reserve_xprt(struct rpc_task *task); -int xprt_reserve_xprt_cong(struct rpc_task *task); +int xprt_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task); +int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task); int xprt_prepare_transmit(struct rpc_task *task); void xprt_transmit(struct rpc_task *task); void xprt_end_transmit(struct rpc_task *task); -- cgit v1.2.3 From 21de0a955f3af29fa1100d96f66e6adade89e77a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 17 Jul 2011 16:57:32 -0400 Subject: SUNRPC: Clean up the slot table allocation Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index a876882fb923..05047250f218 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -168,7 +168,6 @@ struct rpc_xprt { struct rpc_wait_queue pending; /* requests in flight */ struct rpc_wait_queue backlog; /* waiting for slot */ struct list_head free; /* free slots */ - struct rpc_rqst * slot; /* slot table storage */ unsigned int max_reqs; /* total slots */ unsigned long state; /* transport state */ unsigned char shutdown : 1, /* being shut down */ @@ -321,7 +320,6 @@ void xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie); #define XPRT_CLOSING (6) #define XPRT_CONNECTION_ABORT (7) #define XPRT_CONNECTION_CLOSE (8) -#define XPRT_INITIALIZED (9) static inline void xprt_set_connected(struct rpc_xprt *xprt) { -- cgit v1.2.3 From d9ba131d8f58c0d2ff5029e7002ab43f913b36f9 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 17 Jul 2011 18:11:30 -0400 Subject: SUNRPC: Support dynamic slot allocation for TCP connections Allow the number of available slots to grow with the TCP window size. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 05047250f218..d02762d1de27 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -22,6 +22,7 @@ #define RPC_MIN_SLOT_TABLE (2U) #define RPC_DEF_SLOT_TABLE (16U) #define RPC_MAX_SLOT_TABLE (128U) +#define RPC_MAX_SLOT_TABLE_LIMIT (65536U) /* * This describes a timeout strategy @@ -168,7 +169,9 @@ struct rpc_xprt { struct rpc_wait_queue pending; /* requests in flight */ struct rpc_wait_queue backlog; /* waiting for slot */ struct list_head free; /* free slots */ - unsigned int max_reqs; /* total slots */ + unsigned int max_reqs; /* max number of slots */ + unsigned int min_reqs; /* min number of slots */ + atomic_t num_reqs; /* total slots */ unsigned long state; /* transport state */ unsigned char shutdown : 1, /* being shut down */ resvport : 1; /* use a reserved port */ @@ -281,7 +284,9 @@ void xprt_release_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_release(struct rpc_task *task); struct rpc_xprt * xprt_get(struct rpc_xprt *xprt); void xprt_put(struct rpc_xprt *xprt); -struct rpc_xprt * xprt_alloc(struct net *net, int size, int max_req); +struct rpc_xprt * xprt_alloc(struct net *net, size_t size, + unsigned int num_prealloc, + unsigned int max_req); void xprt_free(struct rpc_xprt *); static inline __be32 *xprt_skip_transport_header(struct rpc_xprt *xprt, __be32 *p) -- cgit v1.2.3 From 3b27bad7f7ceacca6d6c0ef647ffb38aa55a8336 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 17 Jul 2011 18:11:34 -0400 Subject: SUNRPC: Allow caller of rpc_sleep_on() to select priority levels Currently, the caller has to change the value of task->tk_priority if it wants to select on which priority level the task will sleep. This patch allows the caller to select a priority level at sleep time rather than always using task->tk_priority. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index fe2d8e6b923b..e7756896f3ca 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -227,6 +227,10 @@ void rpc_init_wait_queue(struct rpc_wait_queue *, const char *); void rpc_destroy_wait_queue(struct rpc_wait_queue *); void rpc_sleep_on(struct rpc_wait_queue *, struct rpc_task *, rpc_action action); +void rpc_sleep_on_priority(struct rpc_wait_queue *, + struct rpc_task *, + rpc_action action, + int priority); void rpc_wake_up_queued_task(struct rpc_wait_queue *, struct rpc_task *); void rpc_wake_up(struct rpc_wait_queue *); -- cgit v1.2.3 From 34006cee28f7344f9557a4be3816c7891b1bbab1 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 17 Jul 2011 18:11:34 -0400 Subject: SUNRPC: Replace xprt->resend and xprt->sending with a priority queue Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index d02762d1de27..15518a152ac3 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -165,7 +165,6 @@ struct rpc_xprt { struct rpc_wait_queue binding; /* requests waiting on rpcbind */ struct rpc_wait_queue sending; /* requests waiting to send */ - struct rpc_wait_queue resend; /* requests waiting to resend */ struct rpc_wait_queue pending; /* requests in flight */ struct rpc_wait_queue backlog; /* waiting for slot */ struct list_head free; /* free slots */ -- cgit v1.2.3 From 3adf004d82c03ca9d57cbe960657757a71e4c2e7 Mon Sep 17 00:00:00 2001 From: Pekka Enberg Date: Mon, 18 Jul 2011 15:16:55 +0300 Subject: Revert "SLUB: Fix build breakage in linux/mm_types.h" This reverts commit ea6bd8ee1a2ccdffc38b2b1fcfe941addfafaade. --- include/linux/mm_types.h | 25 +++++++++++++++---------- 1 file changed, 15 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6dc6413f5deb..3d76a433d52f 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -49,27 +49,32 @@ struct page { * see PAGE_MAPPING_ANON below. */ /* Second double word */ - struct { - union { + union { + struct { pgoff_t index; /* Our offset within mapping. */ - void *freelist; /* slub first free object */ - }; - - union { atomic_t _mapcount; /* Count of ptes mapped in mms, * to show when page is mapped * & limit reverse map searches. */ + atomic_t _count; /* Usage count, see below. */ + }; - /* Used for cmpxchg_double in slub */ - unsigned long counters; - struct { + struct { /* SLUB cmpxchg_double area */ + void *freelist; + union { + unsigned long counters; + struct { unsigned inuse:16; unsigned objects:15; unsigned frozen:1; + /* + * Kernel may make use of this field even when slub + * uses the rest of the double word! + */ + atomic_t _count; + }; }; }; - atomic_t _count; /* Usage count, see below. */ }; /* Third double word block */ -- cgit v1.2.3 From 013e896373fc53f3d3c039364a25ccbd1fc0729a Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 14 Jul 2011 12:48:14 -0500 Subject: Avoid duplicate _count variables in page_struct Restructure the union / struct cascade in struct page so that we only have one definition of _count. Tested-by: Hugh Dickins Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/mm_types.h | 37 +++++++++++++++++++------------------ 1 file changed, 19 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 3d76a433d52f..774b8952deb4 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -49,30 +49,31 @@ struct page { * see PAGE_MAPPING_ANON below. */ /* Second double word */ - union { - struct { + struct { + union { pgoff_t index; /* Our offset within mapping. */ - atomic_t _mapcount; /* Count of ptes mapped in mms, + void *freelist; /* slub first free object */ + }; + + union { + /* Used for cmpxchg_double in slub */ + unsigned long counters; + + struct { + + union { + atomic_t _mapcount; /* Count of ptes mapped in mms, * to show when page is mapped * & limit reverse map searches. */ - atomic_t _count; /* Usage count, see below. */ - }; - struct { /* SLUB cmpxchg_double area */ - void *freelist; - union { - unsigned long counters; - struct { - unsigned inuse:16; - unsigned objects:15; - unsigned frozen:1; - /* - * Kernel may make use of this field even when slub - * uses the rest of the double word! - */ - atomic_t _count; + struct { + unsigned inuse:16; + unsigned objects:15; + unsigned frozen:1; + }; }; + atomic_t _count; /* Usage count, see below. */ }; }; }; -- cgit v1.2.3 From 1091006c5eb15cba56785bd5b498a8d0b9546903 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Mon, 24 Jan 2011 12:11:02 -0500 Subject: nfsd: turn on reply cache for NFSv4 It's sort of ridiculous that we've never had a working reply cache for NFSv4. On the other hand, we may still not: our current reply cache is likely not very good, especially in the TCP case (which is the only case that matters for v4). What we really need here is some serious testing. Anyway, here's a start. Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index ea29330b78bd..2f1e5186e049 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -273,6 +273,7 @@ struct svc_rqst { /* Catering to nfsd */ struct auth_domain * rq_client; /* RPC peer info */ struct auth_domain * rq_gssclient; /* "gss/"-style peer info */ + int rq_cachetype; struct svc_cacherep * rq_cacherep; /* cache info */ int rq_splice_ok; /* turned off in gss privacy * to prevent encrypting page -- cgit v1.2.3 From 6b75e3e8d664a9a1b99d31a7f4976ae70d1d090a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 18 Jul 2011 16:08:07 +0200 Subject: netfilter: nfnetlink: add RCU in nfnetlink_rcv_msg() Goal of this patch is to permit nfnetlink providers not mandate nfnl_mutex being held while nfnetlink_rcv_msg() calls them. If struct nfnl_callback contains a non NULL call_rcu(), then nfnetlink_rcv_msg() will use it instead of call() field, holding rcu_read_lock instead of nfnl_mutex Signed-off-by: Eric Dumazet CC: Florian Westphal CC: Eric Leblond Signed-off-by: Patrick McHardy --- include/linux/netfilter/nfnetlink.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 2b11fc1a86be..74d33861473c 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -60,6 +60,9 @@ struct nfnl_callback { int (*call)(struct sock *nl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[]); + int (*call_rcu)(struct sock *nl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const cda[]); const struct nla_policy *policy; /* netlink attribute policy */ const u_int16_t attr_count; /* number of nlattr's */ }; -- cgit v1.2.3 From 61b8013a114cb041db2c56f747953cac69637f26 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Sun, 17 Jul 2011 20:54:09 +0000 Subject: stmmac: Allow SOCs to use Store forward mode eventhough tx_coe is 0. (V2) This patch adds new field 'force_sf_dma_mode' to plat_stmmacenet_data struct to allow users to specify if they want to use force store forward eventhough tx_coe is not available in hw. without this flag stmmac driver will use cut-thru mode not use store-forward mode. Signed-off-by: Srinivas Kandagatla Signed-off-by: Giuseppe Cavallaro Signed-off-by: David S. Miller --- include/linux/stmmac.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 9529e49b0385..05d775690b72 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -40,6 +40,7 @@ struct plat_stmmacenet_data { int tx_coe; int bugged_jumbo; int pmt; + int force_sf_dma_mode; void (*fix_mac_speed)(void *priv, unsigned int speed); void (*bus_setup)(void __iomem *ioaddr); int (*init)(struct platform_device *pdev); -- cgit v1.2.3 From a07c7964a29b6dc515b120f1e1c223ac2f8666f5 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Sat, 16 Jul 2011 22:22:20 +0000 Subject: include/linux/sdla.h: remove the prototype of sdla() `make headers_check` complains that linux-2.6/usr/include/linux/sdla.h:116: userspace cannot reference function or variable defined in the kernel this is due to that there is no such a kernel function, void sdla(void *cfg_info, char *dev, struct frad_conf *conf, int quiet); I don't know why we have it in a kernel header, so remove it. Signed-off-by: WANG Cong Signed-off-by: David S. Miller --- include/linux/sdla.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sdla.h b/include/linux/sdla.h index 564acd3a71c1..9995c7fc3f60 100644 --- a/include/linux/sdla.h +++ b/include/linux/sdla.h @@ -112,11 +112,7 @@ struct sdla_dlci_conf { short Tb_max; }; -#ifndef __KERNEL__ - -void sdla(void *cfg_info, char *dev, struct frad_conf *conf, int quiet); - -#else +#ifdef __KERNEL__ /* important Z80 window addresses */ #define SDLA_CONTROL_WND 0xE000 -- cgit v1.2.3 From 09779aded8ab0ef475427d4f037a7bd5c74d5faa Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Thu, 14 Jul 2011 21:49:18 +0200 Subject: ssb: SPROM: add LED duty cycle fields MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Rafał Miłecki Signed-off-by: John W. Linville --- include/linux/ssb/ssb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index b0928c10111b..8623217f84d0 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -27,6 +27,8 @@ struct ssb_sprom { u8 et1mdcport; /* MDIO for enet1 */ u8 board_rev; /* Board revision number from SPROM. */ u8 country_code; /* Country Code */ + u16 leddc_on_time; /* LED Powersave Duty Cycle On Count */ + u16 leddc_off_time; /* LED Powersave Duty Cycle Off Count */ u8 ant_available_a; /* 2GHz antenna available bits (up to 4) */ u8 ant_available_bg; /* 5GHz antenna available bits (up to 4) */ u16 pa0b0; -- cgit v1.2.3 From f701e5b73a1a79ea62ffd45d9e2bed4c7d5c1fd2 Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy Date: Fri, 15 Jul 2011 20:45:18 +0300 Subject: connector: add an event for monitoring process tracers This change adds a procfs connector event, which is emitted on every successful process tracer attach or detach. If some process connects to other one, kernelspace connector reports process id and thread group id of both these involved processes. On disconnection null process id is returned. Such an event allows to create a simple automated userspace mechanism to be aware about processes connecting to others, therefore predefined process policies can be applied to them if needed. Note, a detach signal is emitted only in case, if a tracer process explicitly executes PTRACE_DETACH request. In other cases like tracee or tracer exit detach event from proc connector is not reported. Signed-off-by: Vladimir Zapolskiy Acked-by: Evgeniy Polyakov Cc: David S. Miller Signed-off-by: Oleg Nesterov --- include/linux/cn_proc.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cn_proc.h b/include/linux/cn_proc.h index 47dac5ea8d3a..12c517b51ca2 100644 --- a/include/linux/cn_proc.h +++ b/include/linux/cn_proc.h @@ -53,6 +53,7 @@ struct proc_event { PROC_EVENT_UID = 0x00000004, PROC_EVENT_GID = 0x00000040, PROC_EVENT_SID = 0x00000080, + PROC_EVENT_PTRACE = 0x00000100, /* "next" should be 0x00000400 */ /* "last" is the last process event: exit */ PROC_EVENT_EXIT = 0x80000000 @@ -95,6 +96,13 @@ struct proc_event { __kernel_pid_t process_tgid; } sid; + struct ptrace_proc_event { + __kernel_pid_t process_pid; + __kernel_pid_t process_tgid; + __kernel_pid_t tracer_pid; + __kernel_pid_t tracer_tgid; + } ptrace; + struct exit_proc_event { __kernel_pid_t process_pid; __kernel_pid_t process_tgid; @@ -109,6 +117,7 @@ void proc_fork_connector(struct task_struct *task); void proc_exec_connector(struct task_struct *task); void proc_id_connector(struct task_struct *task, int which_id); void proc_sid_connector(struct task_struct *task); +void proc_ptrace_connector(struct task_struct *task, int which_id); void proc_exit_connector(struct task_struct *task); #else static inline void proc_fork_connector(struct task_struct *task) @@ -124,6 +133,10 @@ static inline void proc_id_connector(struct task_struct *task, static inline void proc_sid_connector(struct task_struct *task) {} +static inline void proc_ptrace_connector(struct task_struct *task, + int ptrace_id) +{} + static inline void proc_exit_connector(struct task_struct *task) {} #endif /* CONFIG_PROC_EVENTS */ -- cgit v1.2.3 From 90e33f62e027d330485d03598e1b2d8db3ff031c Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 5 Jul 2011 23:42:28 -0600 Subject: of/address: Add of_find_matching_node_by_address helper of_find_matching_node_by_address() can be used to find a device tree node for a device at a specific address. Signed-off-by: Grant Likely --- include/linux/of_address.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_address.h b/include/linux/of_address.h index 2feda6ee6140..bdfc20d8ff84 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -6,6 +6,10 @@ extern u64 of_translate_address(struct device_node *np, const __be32 *addr); extern int of_address_to_resource(struct device_node *dev, int index, struct resource *r); +extern struct device_node *of_find_matching_node_by_address( + struct device_node *from, + const struct of_device_id *matches, + u64 base_address); extern void __iomem *of_iomap(struct device_node *device, int index); /* Extract an address from a device, returns the region size and -- cgit v1.2.3 From 99ce39e359fa29e4b609a6a13485e7573eda5dfb Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 5 Jul 2011 23:42:37 -0600 Subject: dt: include linux/errno.h in linux/of_address.h of_address.h makes reference to some of the error code #defines, so it needs to include errno.h. If CONFIG_PCI is not selected, then some files will fail to compile. Signed-off-by: Grant Likely --- include/linux/of_address.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/of_address.h b/include/linux/of_address.h index bdfc20d8ff84..3118623c2c1f 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -1,6 +1,7 @@ #ifndef __OF_ADDRESS_H #define __OF_ADDRESS_H #include +#include #include extern u64 of_translate_address(struct device_node *np, const __be32 *addr); -- cgit v1.2.3 From 52eafc68d601afd699b023201b0c6be5209f39ce Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Wed, 15 Jun 2011 14:41:42 +0000 Subject: mlx4_core: Extend capability flags to 64 bits The latest firmware adds a second dword containing more device flags, so extend the device capabilities flags field from 32 to 64 bits. Derived from patch by Eli Cohen Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- include/linux/mlx4/device.h | 34 +++++++++++++++++----------------- 1 file changed, 17 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 8985768e2c0d..f337e989b70f 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -58,22 +58,22 @@ enum { }; enum { - MLX4_DEV_CAP_FLAG_RC = 1 << 0, - MLX4_DEV_CAP_FLAG_UC = 1 << 1, - MLX4_DEV_CAP_FLAG_UD = 1 << 2, - MLX4_DEV_CAP_FLAG_SRQ = 1 << 6, - MLX4_DEV_CAP_FLAG_IPOIB_CSUM = 1 << 7, - MLX4_DEV_CAP_FLAG_BAD_PKEY_CNTR = 1 << 8, - MLX4_DEV_CAP_FLAG_BAD_QKEY_CNTR = 1 << 9, - MLX4_DEV_CAP_FLAG_DPDP = 1 << 12, - MLX4_DEV_CAP_FLAG_BLH = 1 << 15, - MLX4_DEV_CAP_FLAG_MEM_WINDOW = 1 << 16, - MLX4_DEV_CAP_FLAG_APM = 1 << 17, - MLX4_DEV_CAP_FLAG_ATOMIC = 1 << 18, - MLX4_DEV_CAP_FLAG_RAW_MCAST = 1 << 19, - MLX4_DEV_CAP_FLAG_UD_AV_PORT = 1 << 20, - MLX4_DEV_CAP_FLAG_UD_MCAST = 1 << 21, - MLX4_DEV_CAP_FLAG_IBOE = 1 << 30 + MLX4_DEV_CAP_FLAG_RC = 1LL << 0, + MLX4_DEV_CAP_FLAG_UC = 1LL << 1, + MLX4_DEV_CAP_FLAG_UD = 1LL << 2, + MLX4_DEV_CAP_FLAG_SRQ = 1LL << 6, + MLX4_DEV_CAP_FLAG_IPOIB_CSUM = 1LL << 7, + MLX4_DEV_CAP_FLAG_BAD_PKEY_CNTR = 1LL << 8, + MLX4_DEV_CAP_FLAG_BAD_QKEY_CNTR = 1LL << 9, + MLX4_DEV_CAP_FLAG_DPDP = 1LL << 12, + MLX4_DEV_CAP_FLAG_BLH = 1LL << 15, + MLX4_DEV_CAP_FLAG_MEM_WINDOW = 1LL << 16, + MLX4_DEV_CAP_FLAG_APM = 1LL << 17, + MLX4_DEV_CAP_FLAG_ATOMIC = 1LL << 18, + MLX4_DEV_CAP_FLAG_RAW_MCAST = 1LL << 19, + MLX4_DEV_CAP_FLAG_UD_AV_PORT = 1LL << 20, + MLX4_DEV_CAP_FLAG_UD_MCAST = 1LL << 21, + MLX4_DEV_CAP_FLAG_IBOE = 1LL << 30 }; enum { @@ -253,7 +253,7 @@ struct mlx4_caps { int mtt_entry_sz; u32 max_msg_sz; u32 page_size_cap; - u32 flags; + u64 flags; u32 bmme_flags; u32 reserved_lkey; u16 stat_rate_support; -- cgit v1.2.3 From ccf863219675aa86bebdd6a2806acb8176478e37 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Thu, 7 Jul 2011 19:19:29 +0000 Subject: mlx4_core: Read extended capabilities into the flags field Query another dword containing up to 32 extended device capabilities and merge it into struct mlx4_caps.flags. Update the code that handles the current extended device capabilities (e.g UDP RSS, WoL, vep steering, etc) to use the extended device cap flags field instead of a field per extended capability. Initial patch done by Eli Cohen . Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- include/linux/mlx4/device.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index f337e989b70f..fa861134928a 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -73,7 +73,12 @@ enum { MLX4_DEV_CAP_FLAG_RAW_MCAST = 1LL << 19, MLX4_DEV_CAP_FLAG_UD_AV_PORT = 1LL << 20, MLX4_DEV_CAP_FLAG_UD_MCAST = 1LL << 21, - MLX4_DEV_CAP_FLAG_IBOE = 1LL << 30 + MLX4_DEV_CAP_FLAG_IBOE = 1LL << 30, + MLX4_DEV_CAP_FLAG_UC_LOOPBACK = 1LL << 32, + MLX4_DEV_CAP_FLAG_WOL = 1LL << 38, + MLX4_DEV_CAP_FLAG_UDP_RSS = 1LL << 40, + MLX4_DEV_CAP_FLAG_VEP_UC_STEER = 1LL << 41, + MLX4_DEV_CAP_FLAG_VEP_MC_STEER = 1LL << 42 }; enum { @@ -257,11 +262,6 @@ struct mlx4_caps { u32 bmme_flags; u32 reserved_lkey; u16 stat_rate_support; - int udp_rss; - int loopback_support; - int vep_uc_steering; - int vep_mc_steering; - int wol; u8 port_width_cap[MLX4_MAX_PORTS + 1]; int max_gso_sz; int reserved_qps_cnt[MLX4_NUM_QP_REGION]; -- cgit v1.2.3 From 98a13e487a3bdac8508e4dcb98d63385fabe6767 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Wed, 15 Jun 2011 14:43:43 +0000 Subject: mlx4_core: Fix location of counter index in QP context struct Fix the address handle portion of the QP context structure to have the correct bit location for the counter index field. Signed-off-by: Eli Cohen Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- include/linux/mlx4/qp.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 9e9eb21056ca..6486d880bdbf 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -99,7 +99,7 @@ struct mlx4_qp_path { u8 fl; u8 reserved1[2]; u8 pkey_index; - u8 reserved2; + u8 counter_index; u8 grh_mylmc; __be16 rlid; u8 ackto; @@ -111,8 +111,7 @@ struct mlx4_qp_path { u8 sched_queue; u8 vlan_index; u8 reserved3[2]; - u8 counter_index; - u8 reserved4; + u8 reserved4[2]; u8 dmac[6]; }; -- cgit v1.2.3 From f2a3f6a32cf64db1495b5ced8625b9a80bde44e5 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Wed, 15 Jun 2011 14:47:14 +0000 Subject: mlx4_core: Add network flow counters ConnectX devices support a set of flow counters that can be attached to a set containing one or more QPs. Each such counter tracks receive and transmit packets and bytes of these QPs. This patch queries the device to check support for counters, handles initialization of the HCA to enable counters, and initializes a bitmap allocator to control counter allocations. Derived from patch by Eli Cohen . Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- include/linux/mlx4/cmd.h | 3 +++ include/linux/mlx4/device.h | 18 +++++++++++++++++- 2 files changed, 20 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index 9a18667c13cc..b56e4587208d 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -123,6 +123,9 @@ enum { /* debug commands */ MLX4_CMD_QUERY_DEBUG_MSG = 0x2a, MLX4_CMD_SET_DEBUG_MSG = 0x2b, + + /* statistics commands */ + MLX4_CMD_QUERY_IF_STAT = 0X54, }; enum { diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index fa861134928a..387329e02303 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -78,7 +78,8 @@ enum { MLX4_DEV_CAP_FLAG_WOL = 1LL << 38, MLX4_DEV_CAP_FLAG_UDP_RSS = 1LL << 40, MLX4_DEV_CAP_FLAG_VEP_UC_STEER = 1LL << 41, - MLX4_DEV_CAP_FLAG_VEP_MC_STEER = 1LL << 42 + MLX4_DEV_CAP_FLAG_VEP_MC_STEER = 1LL << 42, + MLX4_DEV_CAP_FLAG_COUNTERS = 1LL << 48 }; enum { @@ -274,6 +275,7 @@ struct mlx4_caps { u8 supported_type[MLX4_MAX_PORTS + 1]; u32 port_mask; enum mlx4_port_type possible_type[MLX4_MAX_PORTS + 1]; + u32 max_counters; }; struct mlx4_buf_list { @@ -438,6 +440,17 @@ union mlx4_ext_av { struct mlx4_eth_av eth; }; +struct mlx4_counter { + u8 reserved1[3]; + u8 counter_mode; + __be32 num_ifc; + u32 reserved2[2]; + __be64 rx_frames; + __be64 rx_bytes; + __be64 tx_frames; + __be64 tx_bytes; +}; + struct mlx4_dev { struct pci_dev *pdev; unsigned long flags; @@ -568,4 +581,7 @@ void mlx4_release_eq(struct mlx4_dev *dev, int vec); int mlx4_wol_read(struct mlx4_dev *dev, u64 *config, int port); int mlx4_wol_write(struct mlx4_dev *dev, u64 config, int port); +int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx); +void mlx4_counter_free(struct mlx4_dev *dev, u32 idx); + #endif /* MLX4_DEVICE_H */ -- cgit v1.2.3 From cfcde11c3d7ae175f49280bb6f913478c2f1bd8c Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Wed, 15 Jun 2011 14:49:57 +0000 Subject: IB/mlx4: Use flow counters on IBoE ports Allocate flow counter per Ethernet/IBoE port, and attach this counter to all the QPs created on that port. Based on patch by Eli Cohen . Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- include/linux/mlx4/qp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 6486d880bdbf..4001c8249dbb 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -54,7 +54,8 @@ enum mlx4_qp_optpar { MLX4_QP_OPTPAR_RETRY_COUNT = 1 << 12, MLX4_QP_OPTPAR_RNR_RETRY = 1 << 13, MLX4_QP_OPTPAR_ACK_TIMEOUT = 1 << 14, - MLX4_QP_OPTPAR_SCHED_QUEUE = 1 << 16 + MLX4_QP_OPTPAR_SCHED_QUEUE = 1 << 16, + MLX4_QP_OPTPAR_COUNTER_INDEX = 1 << 20 }; enum mlx4_qp_state { -- cgit v1.2.3 From 97d32cf9440d2111a12471740446d4d63231b79a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 19 Jul 2011 11:46:33 +0200 Subject: netfilter: nfnetlink_queue: batch verdict support Introduces a new nfnetlink type that applies a given verdict to all queued packets with an id <= the id in the verdict message. If a mark is provided it is applied to all matched packets. This reduces the number of verdicts that have to be sent. Applications that make use of this feature need to maintain a timeout to send a batchverdict periodically to avoid starvation. Signed-off-by: Florian Westphal Signed-off-by: Patrick McHardy --- include/linux/netfilter/nfnetlink_queue.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_queue.h b/include/linux/netfilter/nfnetlink_queue.h index af94e0014ebd..24b32e6c009e 100644 --- a/include/linux/netfilter/nfnetlink_queue.h +++ b/include/linux/netfilter/nfnetlink_queue.h @@ -8,6 +8,7 @@ enum nfqnl_msg_types { NFQNL_MSG_PACKET, /* packet from kernel to userspace */ NFQNL_MSG_VERDICT, /* verdict from userspace to kernel */ NFQNL_MSG_CONFIG, /* connect to a particular queue */ + NFQNL_MSG_VERDICT_BATCH, /* batchv from userspace to kernel */ NFQNL_MSG_MAX }; -- cgit v1.2.3 From eb1577b7c4b2cdd0e18b0d5d8e940e36329215e5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Sun, 17 Jul 2011 11:00:59 +0200 Subject: bcma: handle alternative SPROM location MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some cards do not use additional 0x30 offset for SPROM location. We do not know the real condition for it yet, make it BCM4331 specific for now. Signed-off-by: Rafał Miłecki Signed-off-by: John W. Linville --- include/linux/bcma/bcma_driver_chipcommon.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index 9c5b69fc985a..68c3d941a215 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -244,7 +244,8 @@ #define BCMA_CC_REGCTL_DATA 0x065C #define BCMA_CC_PLLCTL_ADDR 0x0660 #define BCMA_CC_PLLCTL_DATA 0x0664 -#define BCMA_CC_SPROM 0x0830 /* SPROM beginning */ +#define BCMA_CC_SPROM 0x0800 /* SPROM beginning */ +#define BCMA_CC_SPROM_PCIE6 0x0830 /* SPROM beginning on PCIe rev >= 6 */ /* Data for the PMU, if available. * Check availability with ((struct bcma_chipcommon)->capabilities & BCMA_CC_CAP_PMU) -- cgit v1.2.3 From 856799d58274bfa6a57bc80051ee1cefdb6b041f Mon Sep 17 00:00:00 2001 From: Kalle Valo Date: Sun, 17 Jul 2011 12:13:56 +0300 Subject: ieee80211: add few wmm tspec values These are needed by ath6kl for parsing tspec status from an IE. Signed-off-by: Kalle Valo Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index a26108e4d924..54c878960872 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1453,6 +1453,43 @@ enum ieee80211_sa_query_action { #define WLAN_PMKID_LEN 16 +/* + * WMM/802.11e Tspec Element + */ +#define IEEE80211_WMM_IE_TSPEC_TID_MASK 0x0F +#define IEEE80211_WMM_IE_TSPEC_TID_SHIFT 1 + +enum ieee80211_tspec_status_code { + IEEE80211_TSPEC_STATUS_ADMISS_ACCEPTED = 0, + IEEE80211_TSPEC_STATUS_ADDTS_INVAL_PARAMS = 0x1, +}; + +struct ieee80211_tspec_ie { + u8 element_id; + u8 len; + u8 oui[3]; + u8 oui_type; + u8 oui_subtype; + u8 version; + __le16 tsinfo; + u8 tsinfo_resvd; + __le16 nominal_msdu; + __le16 max_msdu; + __le32 min_service_int; + __le32 max_service_int; + __le32 inactivity_int; + __le32 suspension_int; + __le32 service_start_time; + __le32 min_data_rate; + __le32 mean_data_rate; + __le32 peak_data_rate; + __le32 max_burst_size; + __le32 delay_bound; + __le32 min_phy_rate; + __le16 sba; + __le16 medium_time; +} __packed; + /** * ieee80211_get_qos_ctl - get pointer to qos control bytes * @hdr: the frame -- cgit v1.2.3 From 2b5e3322b8bff484cb206e7920c6034663d37b87 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Mon, 18 Jul 2011 02:01:28 +0200 Subject: bcma: define IO status register MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Rafał Miłecki Signed-off-by: John W. Linville --- include/linux/bcma/bcma_regs.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma_regs.h b/include/linux/bcma/bcma_regs.h index f82d88a960ce..889219535a83 100644 --- a/include/linux/bcma/bcma_regs.h +++ b/include/linux/bcma/bcma_regs.h @@ -2,12 +2,18 @@ #define LINUX_BCMA_REGS_H_ /* Agent registers (common for every core) */ -#define BCMA_IOCTL 0x0408 +#define BCMA_IOCTL 0x0408 /* IO control */ #define BCMA_IOCTL_CLK 0x0001 #define BCMA_IOCTL_FGC 0x0002 #define BCMA_IOCTL_CORE_BITS 0x3FFC #define BCMA_IOCTL_PME_EN 0x4000 #define BCMA_IOCTL_BIST_EN 0x8000 +#define BCMA_IOST 0x0500 /* IO status */ +#define BCMA_IOST_CORE_BITS 0x0FFF +#define BCMA_IOST_DMA64 0x1000 +#define BCMA_IOST_GATED_CLK 0x2000 +#define BCMA_IOST_BIST_ERROR 0x4000 +#define BCMA_IOST_BIST_DONE 0x8000 #define BCMA_RESET_CTL 0x0800 #define BCMA_RESET_CTL_RESET 0x0001 -- cgit v1.2.3 From 34850ab25d74ab4eead62c3b4a9e8036a25cc669 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 18 Jul 2011 18:08:35 +0200 Subject: cfg80211: allow userspace to control supported rates in scan Some P2P scans are not allowed to advertise 11b rates, but that is a rather special case so instead of having that, allow userspace to request the rate sets (per band) that are advertised in scan probe request frames. Since it's needed in two places now, factor out some common code parsing a rate array. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nl80211.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 7ba71e42449e..e4da76c9e4d9 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -1014,6 +1014,11 @@ enum nl80211_commands { * @%NL80211_ATTR_REKEY_DATA: nested attribute containing the information * necessary for GTK rekeying in the device, see &enum nl80211_rekey_data. * + * @NL80211_ATTR_SCAN_SUPP_RATES: rates per to be advertised as supported in scan, + * nested array attribute containing an entry for each band, with the entry + * being a list of supported rates as defined by IEEE 802.11 7.3.2.2 but + * without the length restriction (at most %NL80211_MAX_SUPP_RATES). + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -1217,6 +1222,8 @@ enum nl80211_attrs { NL80211_ATTR_MAX_NUM_SCHED_SCAN_SSIDS, NL80211_ATTR_MAX_SCHED_SCAN_IE_LEN, + NL80211_ATTR_SCAN_SUPP_RATES, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, -- cgit v1.2.3 From bb932ad9805029af18232ffe5603fbc68e1c1fb6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Sat, 16 Jul 2011 18:43:36 +0200 Subject: bcma: move define of BCMA_CLKCTLST register MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Recent experiments have shown many cores share 0x1E0 register used for clock management. Signed-off-by: Rafał Miłecki Signed-off-by: John W. Linville --- include/linux/bcma/bcma_driver_chipcommon.h | 10 +--------- include/linux/bcma/bcma_regs.h | 19 +++++++++++++++++++ 2 files changed, 20 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index 68c3d941a215..a0f684615ae5 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -179,15 +179,7 @@ #define BCMA_CC_PROG_WAITCNT 0x0124 #define BCMA_CC_FLASH_CFG 0x0128 #define BCMA_CC_FLASH_WAITCNT 0x012C -#define BCMA_CC_CLKCTLST 0x01E0 /* Clock control and status (rev >= 20) */ -#define BCMA_CC_CLKCTLST_FORCEALP 0x00000001 /* Force ALP request */ -#define BCMA_CC_CLKCTLST_FORCEHT 0x00000002 /* Force HT request */ -#define BCMA_CC_CLKCTLST_FORCEILP 0x00000004 /* Force ILP request */ -#define BCMA_CC_CLKCTLST_HAVEALPREQ 0x00000008 /* ALP available request */ -#define BCMA_CC_CLKCTLST_HAVEHTREQ 0x00000010 /* HT available request */ -#define BCMA_CC_CLKCTLST_HWCROFF 0x00000020 /* Force HW clock request off */ -#define BCMA_CC_CLKCTLST_HAVEHT 0x00010000 /* HT available */ -#define BCMA_CC_CLKCTLST_HAVEALP 0x00020000 /* APL available */ +/* 0x1E0 is defined as shared BCMA_CLKCTLST */ #define BCMA_CC_HW_WORKAROUND 0x01E4 /* Hardware workaround (rev >= 20) */ #define BCMA_CC_UART0_DATA 0x0300 #define BCMA_CC_UART0_IMR 0x0304 diff --git a/include/linux/bcma/bcma_regs.h b/include/linux/bcma/bcma_regs.h index 889219535a83..9faae2ae02e8 100644 --- a/include/linux/bcma/bcma_regs.h +++ b/include/linux/bcma/bcma_regs.h @@ -1,6 +1,25 @@ #ifndef LINUX_BCMA_REGS_H_ #define LINUX_BCMA_REGS_H_ +/* Some single registers are shared between many cores */ +/* BCMA_CLKCTLST: ChipCommon (rev >= 20), PCIe, 80211 */ +#define BCMA_CLKCTLST 0x01E0 /* Clock control and status */ +#define BCMA_CLKCTLST_FORCEALP 0x00000001 /* Force ALP request */ +#define BCMA_CLKCTLST_FORCEHT 0x00000002 /* Force HT request */ +#define BCMA_CLKCTLST_FORCEILP 0x00000004 /* Force ILP request */ +#define BCMA_CLKCTLST_HAVEALPREQ 0x00000008 /* ALP available request */ +#define BCMA_CLKCTLST_HAVEHTREQ 0x00000010 /* HT available request */ +#define BCMA_CLKCTLST_HWCROFF 0x00000020 /* Force HW clock request off */ +#define BCMA_CLKCTLST_EXTRESREQ 0x00000700 /* Mask of external resource requests */ +#define BCMA_CLKCTLST_HAVEALP 0x00010000 /* ALP available */ +#define BCMA_CLKCTLST_HAVEHT 0x00020000 /* HT available */ +#define BCMA_CLKCTLST_BP_ON_ALP 0x00040000 /* RO: running on ALP clock */ +#define BCMA_CLKCTLST_BP_ON_HT 0x00080000 /* RO: running on HT clock */ +#define BCMA_CLKCTLST_EXTRESST 0x07000000 /* Mask of external resource status */ +/* Is there any BCM4328 on BCMA bus? */ +#define BCMA_CLKCTLST_4328A0_HAVEHT 0x00010000 /* 4328a0 has reversed bits */ +#define BCMA_CLKCTLST_4328A0_HAVEALP 0x00020000 /* 4328a0 has reversed bits */ + /* Agent registers (common for every core) */ #define BCMA_IOCTL 0x0408 /* IO control */ #define BCMA_IOCTL_CLK 0x0001 -- cgit v1.2.3 From 3de1a7748f68c63daed7c9e04ac9f048efcd9f20 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Sun, 17 Jul 2011 01:06:03 +0200 Subject: bcma: trivial: add helpers for masking/setting MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Rafał Miłecki Signed-off-by: John W. Linville --- include/linux/bcma/bcma.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index 3895aeb494a3..6e5dc7b3c024 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -243,8 +243,16 @@ void bcma_awrite32(struct bcma_device *core, u16 offset, u32 value) core->bus->ops->awrite32(core, offset, value); } +#define bcma_mask32(cc, offset, mask) \ + bcma_write32(cc, offset, bcma_read32(cc, offset) & (mask)) +#define bcma_set32(cc, offset, set) \ + bcma_write32(cc, offset, bcma_read32(cc, offset) | (set)) +#define bcma_maskset32(cc, offset, mask, set) \ + bcma_write32(cc, offset, (bcma_read32(cc, offset) & (mask)) | (set)) + extern bool bcma_core_is_enabled(struct bcma_device *core); extern void bcma_core_disable(struct bcma_device *core, u32 flags); extern int bcma_core_enable(struct bcma_device *core, u32 flags); + #endif /* LINUX_BCMA_H_ */ -- cgit v1.2.3 From 7424dd0d03502b9844b96bf6efd0716b79c36607 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Sun, 17 Jul 2011 01:06:04 +0200 Subject: bcma: allow setting FAST clockmode for a core MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Rafał Miłecki Signed-off-by: John W. Linville --- include/linux/bcma/bcma.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index 6e5dc7b3c024..37017c1cc6b7 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -25,6 +25,11 @@ struct bcma_chipinfo { u8 pkg; }; +enum bcma_clkmode { + BCMA_CLKMODE_FAST, + BCMA_CLKMODE_DYNAMIC, +}; + struct bcma_host_ops { u8 (*read8)(struct bcma_device *core, u16 offset); u16 (*read16)(struct bcma_device *core, u16 offset); @@ -253,6 +258,7 @@ void bcma_awrite32(struct bcma_device *core, u16 offset, u32 value) extern bool bcma_core_is_enabled(struct bcma_device *core); extern void bcma_core_disable(struct bcma_device *core, u32 flags); extern int bcma_core_enable(struct bcma_device *core, u32 flags); - +extern void bcma_core_set_clockmode(struct bcma_device *core, + enum bcma_clkmode clkmode); #endif /* LINUX_BCMA_H_ */ -- cgit v1.2.3 From 6f53912fc317ab130bd910c5c30420a21ea38115 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Sun, 17 Jul 2011 01:06:05 +0200 Subject: bcma: allow enabling PLL MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Rafał Miłecki Signed-off-by: John W. Linville --- include/linux/bcma/bcma.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index 37017c1cc6b7..cc1582d24fbc 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -260,5 +260,7 @@ extern void bcma_core_disable(struct bcma_device *core, u32 flags); extern int bcma_core_enable(struct bcma_device *core, u32 flags); extern void bcma_core_set_clockmode(struct bcma_device *core, enum bcma_clkmode clkmode); +extern void bcma_core_pll_ctl(struct bcma_device *core, u32 req, u32 status, + bool on); #endif /* LINUX_BCMA_H_ */ -- cgit v1.2.3 From 7765be2fec0f476fcd61812d5f9406b04c765020 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 14 Jul 2011 12:24:11 -0700 Subject: rcu: Fix RCU_BOOST race handling current->rcu_read_unlock_special The RCU_BOOST commits for TREE_PREEMPT_RCU introduced an other-task write to a new RCU_READ_UNLOCK_BOOSTED bit in the task_struct structure's ->rcu_read_unlock_special field, but, as noted by Steven Rostedt, without correctly synchronizing all accesses to ->rcu_read_unlock_special. This could result in bits in ->rcu_read_unlock_special being spuriously set and cleared due to conflicting accesses, which in turn could result in deadlocks between the rcu_node structure's ->lock and the scheduler's rq and pi locks. These deadlocks would result from RCU incorrectly believing that the just-ended RCU read-side critical section had been preempted and/or boosted. If that RCU read-side critical section was executed with either rq or pi locks held, RCU's ensuing (incorrect) calls to the scheduler would cause the scheduler to attempt to once again acquire the rq and pi locks, resulting in deadlock. More complex deadlock cycles are also possible, involving multiple rq and pi locks as well as locks from multiple rcu_node structures. This commit fixes synchronization by creating ->rcu_boosted field in task_struct that is accessed and modified only when holding the ->lock in the rcu_node structure on which the task is queued (on that rcu_node structure's ->blkd_tasks list). This results in tasks accessing only their own current->rcu_read_unlock_special fields, making unsynchronized access once again legal, and keeping the rcu_read_unlock() fastpath free of atomic instructions and memory barriers. The reason that the rcu_read_unlock() fastpath does not need to access the new current->rcu_boosted field is that this new field cannot be non-zero unless the RCU_READ_UNLOCK_BLOCKED bit is set in the current->rcu_read_unlock_special field. Therefore, rcu_read_unlock() need only test current->rcu_read_unlock_special: if that is zero, then current->rcu_boosted must also be zero. This bug does not affect TINY_PREEMPT_RCU because this implementation of RCU accesses current->rcu_read_unlock_special with irqs disabled, thus preventing races on the !SMP systems that TINY_PREEMPT_RCU runs on. Maybe-reported-by: Dave Jones Maybe-reported-by: Sergey Senozhatsky Reported-by: Steven Rostedt Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Reviewed-by: Steven Rostedt --- include/linux/sched.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 496770a96487..76676a407e4a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1254,6 +1254,9 @@ struct task_struct { #ifdef CONFIG_PREEMPT_RCU int rcu_read_lock_nesting; char rcu_read_unlock_special; +#if defined(CONFIG_RCU_BOOST) && defined(CONFIG_TREE_PREEMPT_RCU) + int rcu_boosted; +#endif /* #if defined(CONFIG_RCU_BOOST) && defined(CONFIG_TREE_PREEMPT_RCU) */ struct list_head rcu_node_entry; #endif /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TREE_PREEMPT_RCU -- cgit v1.2.3 From 44396f4b5cb8566f7118aec55eeac99be7ad94cb Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 31 May 2011 11:58:49 -0400 Subject: fs: add a DCACHE_NEED_LOOKUP flag for d_flags Btrfs (and I'd venture most other fs's) stores its indexes in nice disk order for readdir, but unfortunately in the case of anything that stats the files in order that readdir spits back (like oh say ls) that means we still have to do the normal lookup of the file, which means looking up our other index and then looking up the inode. What I want is a way to create dummy dentries when we find them in readdir so that when ls or anything else subsequently does a stat(), we already have the location information in the dentry and can go straight to the inode itself. The lookup stuff just assumes that if it finds a dentry it is done, it doesn't perform a lookup. So add a DCACHE_NEED_LOOKUP flag so that the lookup code knows it still needs to run i_op->lookup() on the parent to get the inode for the dentry. I have tested this with btrfs and I went from something that looks like this http://people.redhat.com/jwhiter/ls-noreada.png To this http://people.redhat.com/jwhiter/ls-good.png Thats a savings of 1300 seconds, or 22 minutes. That is a significant savings. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Al Viro --- include/linux/dcache.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 19d90a55541d..5fa5bd33b979 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -216,6 +216,7 @@ struct dentry_operations { #define DCACHE_MOUNTED 0x10000 /* is a mountpoint */ #define DCACHE_NEED_AUTOMOUNT 0x20000 /* handle automount on this dir */ #define DCACHE_MANAGE_TRANSIT 0x40000 /* manage transit from this dirent */ +#define DCACHE_NEED_LOOKUP 0x80000 /* dentry requires i_op->lookup */ #define DCACHE_MANAGED_DENTRY \ (DCACHE_MOUNTED|DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT) @@ -416,6 +417,12 @@ static inline bool d_mountpoint(struct dentry *dentry) return dentry->d_flags & DCACHE_MOUNTED; } +static inline bool d_need_lookup(struct dentry *dentry) +{ + return dentry->d_flags & DCACHE_NEED_LOOKUP; +} + +extern void d_clear_need_lookup(struct dentry *dentry); extern struct dentry *lookup_create(struct nameidata *nd, int is_dir); extern int sysctl_vfs_cache_pressure; -- cgit v1.2.3 From 43e15cdbefea4ce6d68113de98d4f61c0cf45687 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 3 Jun 2011 20:16:57 -0400 Subject: new helper: iterate_supers_type() Call the given function for all superblocks of given type. Function gets a superblock (with s_umount locked shared) and (void *) argument supplied by caller of iterator. Signed-off-by: Al Viro --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index b5b979247863..a8735e7e1b35 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2432,6 +2432,8 @@ extern struct super_block *get_active_super(struct block_device *bdev); extern struct super_block *user_get_super(dev_t); extern void drop_super(struct super_block *sb); extern void iterate_supers(void (*)(struct super_block *, void *), void *); +extern void iterate_supers_type(struct file_system_type *, + void (*)(struct super_block *, void *), void *); extern int dcache_dir_open(struct inode *, struct file *); extern int dcache_dir_close(struct inode *, struct file *); -- cgit v1.2.3 From 1b5d783c94c328d406e801566f161adcfb018dda Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 19 Jun 2011 12:49:47 -0400 Subject: consolidate BINPRM_FLAGS_ENFORCE_NONDUMP handling new helper: would_dump(bprm, file). Checks if we are allowed to read the file and if we are not - sets ENFORCE_NODUMP. Exported, used in places that previously open-coded the same logics. Signed-off-by: Al Viro --- include/linux/binfmts.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 8845613fd7e3..fd88a3945aa1 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -111,6 +111,7 @@ extern int __must_check remove_arg_zero(struct linux_binprm *); extern int search_binary_handler(struct linux_binprm *, struct pt_regs *); extern int flush_old_exec(struct linux_binprm * bprm); extern void setup_new_exec(struct linux_binprm * bprm); +extern void would_dump(struct linux_binprm *, struct file *); extern int suid_dumpable; #define SUID_DUMP_DISABLE 0 /* No setuid dumping */ -- cgit v1.2.3 From 3bfa784a6539f91a27d7ffdd408efdb638e3bebd Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 19 Jun 2011 12:55:10 -0400 Subject: kill file_permission() completely convert the last remaining caller to inode_permission() Signed-off-by: Al Viro --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index a8735e7e1b35..d04e55586a17 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1490,7 +1490,6 @@ extern void dentry_unhash(struct dentry *dentry); /* * VFS file helper functions. */ -extern int file_permission(struct file *, int); extern void inode_init_owner(struct inode *inode, const struct inode *dir, mode_t mode); /* -- cgit v1.2.3 From 07b8ce1ee87d291ff564c02cf878fae973317a52 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 20 Jun 2011 10:52:57 -0400 Subject: lockless get_write_access/deny_write_access new helpers: atomic_inc_unless_negative()/atomic_dec_unless_positive() Signed-off-by: Al Viro --- include/linux/atomic.h | 26 ++++++++++++++++++++++++++ include/linux/fs.h | 29 ++++++++++++++++++++++++++--- 2 files changed, 52 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atomic.h b/include/linux/atomic.h index ee456c79b0e6..bc6615d4132b 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -34,6 +34,32 @@ static inline int atomic_inc_not_zero_hint(atomic_t *v, int hint) } #endif +#ifndef atomic_inc_unless_negative +static inline int atomic_inc_unless_negative(atomic_t *p) +{ + int v, v1; + for (v = 0; v >= 0; v = v1) { + v1 = atomic_cmpxchg(p, v, v + 1); + if (likely(v1 == v)) + return 1; + } + return 0; +} +#endif + +#ifndef atomic_dec_unless_positive +static inline int atomic_dec_unless_positive(atomic_t *p) +{ + int v, v1; + for (v = 0; v <= 0; v = v1) { + v1 = atomic_cmpxchg(p, v, v - 1); + if (likely(v1 == v)) + return 1; + } + return 0; +} +#endif + #ifndef CONFIG_ARCH_HAS_ATOMIC_OR static inline void atomic_or(int i, atomic_t *v) { diff --git a/include/linux/fs.h b/include/linux/fs.h index d04e55586a17..8c84ed930389 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -392,8 +392,8 @@ struct inodes_stat_t { #include #include #include +#include -#include #include struct export_operations; @@ -2195,8 +2195,31 @@ static inline bool execute_ok(struct inode *inode) return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode); } -extern int get_write_access(struct inode *); -extern int deny_write_access(struct file *); +/* + * get_write_access() gets write permission for a file. + * put_write_access() releases this write permission. + * This is used for regular files. + * We cannot support write (and maybe mmap read-write shared) accesses and + * MAP_DENYWRITE mmappings simultaneously. The i_writecount field of an inode + * can have the following values: + * 0: no writers, no VM_DENYWRITE mappings + * < 0: (-i_writecount) vm_area_structs with VM_DENYWRITE set exist + * > 0: (i_writecount) users are writing to the file. + * + * Normally we operate on that counter with atomic_{inc,dec} and it's safe + * except for the cases where we don't hold i_writecount yet. Then we need to + * use {get,deny}_write_access() - these functions check the sign and refuse + * to do the change if sign is wrong. + */ +static inline int get_write_access(struct inode *inode) +{ + return atomic_inc_unless_negative(&inode->i_writecount) ? 0 : -ETXTBSY; +} +static inline int deny_write_access(struct file *file) +{ + struct inode *inode = file->f_path.dentry->d_inode; + return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY; +} static inline void put_write_access(struct inode * inode) { atomic_dec(&inode->i_writecount); -- cgit v1.2.3 From 178ea73521d64ba41d7aa5488fb9f549c6d4507d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 20 Jun 2011 11:31:30 -0400 Subject: kill check_acl callback of generic_permission() its value depends only on inode and does not change; we might as well store it in ->i_op->check_acl and be done with that. Signed-off-by: Al Viro --- include/linux/fs.h | 3 +-- include/linux/reiserfs_xattr.h | 2 ++ 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 8c84ed930389..0c15d5e459d5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2187,8 +2187,7 @@ extern sector_t bmap(struct inode *, sector_t); #endif extern int notify_change(struct dentry *, struct iattr *); extern int inode_permission(struct inode *, int); -extern int generic_permission(struct inode *, int, unsigned int, - int (*check_acl)(struct inode *, int, unsigned int)); +extern int generic_permission(struct inode *, int, unsigned int); static inline bool execute_ok(struct inode *inode) { diff --git a/include/linux/reiserfs_xattr.h b/include/linux/reiserfs_xattr.h index 6deef5dc95fb..1a3ca8f80200 100644 --- a/include/linux/reiserfs_xattr.h +++ b/include/linux/reiserfs_xattr.h @@ -45,6 +45,7 @@ int reiserfs_permission(struct inode *inode, int mask, unsigned int flags); #ifdef CONFIG_REISERFS_FS_XATTR #define has_xattr_dir(inode) (REISERFS_I(inode)->i_flags & i_has_xattr_dir) +int reiserfs_check_acl(struct inode *inode, int mask, unsigned int flags); ssize_t reiserfs_getxattr(struct dentry *dentry, const char *name, void *buffer, size_t size); int reiserfs_setxattr(struct dentry *dentry, const char *name, @@ -122,6 +123,7 @@ static inline void reiserfs_init_xattr_rwsem(struct inode *inode) #define reiserfs_setxattr NULL #define reiserfs_listxattr NULL #define reiserfs_removexattr NULL +#define reiserfs_check_acl NULL static inline void reiserfs_init_xattr_rwsem(struct inode *inode) { -- cgit v1.2.3 From 1fc0f78ca9f311c6277e2f1b7655bb4d43ceb311 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 20 Jun 2011 18:59:02 -0400 Subject: ->permission() sanitizing: MAY_NOT_BLOCK Duplicate the flags argument into mask bitmap. Signed-off-by: Al Viro --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 0c15d5e459d5..60c1fe65bb2d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -63,6 +63,7 @@ struct inodes_stat_t { #define MAY_ACCESS 16 #define MAY_OPEN 32 #define MAY_CHDIR 64 +#define MAY_NOT_BLOCK 128 /* called from RCU mode, don't block */ /* * flags in file.f_mode. Note that FMODE_READ and FMODE_WRITE must correspond -- cgit v1.2.3 From 7e40145eb111a5192e6d819f764db9d6828d1abb Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 20 Jun 2011 19:12:17 -0400 Subject: ->permission() sanitizing: don't pass flags to ->check_acl() not used in the instances anymore. Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- include/linux/generic_acl.h | 2 +- include/linux/reiserfs_xattr.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 60c1fe65bb2d..f218b42718aa 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1579,7 +1579,7 @@ struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameidata *); void * (*follow_link) (struct dentry *, struct nameidata *); int (*permission) (struct inode *, int, unsigned int); - int (*check_acl)(struct inode *, int, unsigned int); + int (*check_acl)(struct inode *, int); int (*readlink) (struct dentry *, char __user *,int); void (*put_link) (struct dentry *, struct nameidata *, void *); diff --git a/include/linux/generic_acl.h b/include/linux/generic_acl.h index 0437e377b555..574bea4013b6 100644 --- a/include/linux/generic_acl.h +++ b/include/linux/generic_acl.h @@ -10,6 +10,6 @@ extern const struct xattr_handler generic_acl_default_handler; int generic_acl_init(struct inode *, struct inode *); int generic_acl_chmod(struct inode *); -int generic_check_acl(struct inode *inode, int mask, unsigned int flags); +int generic_check_acl(struct inode *inode, int mask); #endif /* LINUX_GENERIC_ACL_H */ diff --git a/include/linux/reiserfs_xattr.h b/include/linux/reiserfs_xattr.h index 1a3ca8f80200..424ba6416e7c 100644 --- a/include/linux/reiserfs_xattr.h +++ b/include/linux/reiserfs_xattr.h @@ -45,7 +45,7 @@ int reiserfs_permission(struct inode *inode, int mask, unsigned int flags); #ifdef CONFIG_REISERFS_FS_XATTR #define has_xattr_dir(inode) (REISERFS_I(inode)->i_flags & i_has_xattr_dir) -int reiserfs_check_acl(struct inode *inode, int mask, unsigned int flags); +int reiserfs_check_acl(struct inode *inode, int mask); ssize_t reiserfs_getxattr(struct dentry *dentry, const char *name, void *buffer, size_t size); int reiserfs_setxattr(struct dentry *dentry, const char *name, -- cgit v1.2.3 From 2830ba7f34ebb27c4e5b8b6ef408cd6d74860890 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 20 Jun 2011 19:16:29 -0400 Subject: ->permission() sanitizing: don't pass flags to generic_permission() redundant; all callers get it duplicated in mask & MAY_NOT_BLOCK and none of them removes that bit. Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index f218b42718aa..a1689c13eb77 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2188,7 +2188,7 @@ extern sector_t bmap(struct inode *, sector_t); #endif extern int notify_change(struct dentry *, struct iattr *); extern int inode_permission(struct inode *, int); -extern int generic_permission(struct inode *, int, unsigned int); +extern int generic_permission(struct inode *, int); static inline bool execute_ok(struct inode *inode) { -- cgit v1.2.3 From 10556cb21a0d0b24d95f00ea6df16f599a3345b2 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 20 Jun 2011 19:28:19 -0400 Subject: ->permission() sanitizing: don't pass flags to ->permission() not used by the instances anymore. Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- include/linux/nfs_fs.h | 2 +- include/linux/reiserfs_xattr.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index a1689c13eb77..1fdefe3995fd 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1578,7 +1578,7 @@ struct file_operations { struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameidata *); void * (*follow_link) (struct dentry *, struct nameidata *); - int (*permission) (struct inode *, int, unsigned int); + int (*permission) (struct inode *, int); int (*check_acl)(struct inode *, int); int (*readlink) (struct dentry *, char __user *,int); diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 1b93b9c60e55..86014811a0fb 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -360,7 +360,7 @@ extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *); extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_getattr(struct vfsmount *, struct dentry *, struct kstat *); -extern int nfs_permission(struct inode *, int, unsigned int); +extern int nfs_permission(struct inode *, int); extern int nfs_open(struct inode *, struct file *); extern int nfs_release(struct inode *, struct file *); extern int nfs_attribute_timeout(struct inode *inode); diff --git a/include/linux/reiserfs_xattr.h b/include/linux/reiserfs_xattr.h index 424ba6416e7c..57958c0e1d38 100644 --- a/include/linux/reiserfs_xattr.h +++ b/include/linux/reiserfs_xattr.h @@ -41,7 +41,7 @@ int reiserfs_xattr_init(struct super_block *sb, int mount_flags); int reiserfs_lookup_privroot(struct super_block *sb); int reiserfs_delete_xattrs(struct inode *inode); int reiserfs_chown_xattrs(struct inode *inode, struct iattr *attrs); -int reiserfs_permission(struct inode *inode, int mask, unsigned int flags); +int reiserfs_permission(struct inode *inode, int mask); #ifdef CONFIG_REISERFS_FS_XATTR #define has_xattr_dir(inode) (REISERFS_I(inode)->i_flags & i_has_xattr_dir) -- cgit v1.2.3 From e74f71eb78a4a8b9eaf1bc65f20f761648e85f76 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 20 Jun 2011 19:38:15 -0400 Subject: ->permission() sanitizing: don't pass flags to ->inode_permission() pass that via mask instead. Signed-off-by: Al Viro --- include/linux/security.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 8ce59ef3e5af..ca02f1716736 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1456,7 +1456,7 @@ struct security_operations { struct inode *new_dir, struct dentry *new_dentry); int (*inode_readlink) (struct dentry *dentry); int (*inode_follow_link) (struct dentry *dentry, struct nameidata *nd); - int (*inode_permission) (struct inode *inode, int mask, unsigned flags); + int (*inode_permission) (struct inode *inode, int mask); int (*inode_setattr) (struct dentry *dentry, struct iattr *attr); int (*inode_getattr) (struct vfsmount *mnt, struct dentry *dentry); int (*inode_setxattr) (struct dentry *dentry, const char *name, -- cgit v1.2.3 From eecdd358b467405a084d400d5ec571bbdbfe97a3 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 20 Jun 2011 19:48:41 -0400 Subject: ->permission() sanitizing: don't pass flags to exec_permission() pass mask instead; kill security_inode_exec_permission() since we can use security_inode_permission() instead. Signed-off-by: Al Viro --- include/linux/security.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index ca02f1716736..ebd2a53a3d07 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1720,7 +1720,6 @@ int security_inode_rename(struct inode *old_dir, struct dentry *old_dentry, int security_inode_readlink(struct dentry *dentry); int security_inode_follow_link(struct dentry *dentry, struct nameidata *nd); int security_inode_permission(struct inode *inode, int mask); -int security_inode_exec_permission(struct inode *inode, unsigned int flags); int security_inode_setattr(struct dentry *dentry, struct iattr *attr); int security_inode_getattr(struct vfsmount *mnt, struct dentry *dentry); int security_inode_setxattr(struct dentry *dentry, const char *name, @@ -2113,12 +2112,6 @@ static inline int security_inode_permission(struct inode *inode, int mask) return 0; } -static inline int security_inode_exec_permission(struct inode *inode, - unsigned int flags) -{ - return 0; -} - static inline int security_inode_setattr(struct dentry *dentry, struct iattr *attr) { -- cgit v1.2.3 From 729cdb3a1ee03a4363f9c7e66ddd979727e99e1f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 21 Jun 2011 01:01:22 -0400 Subject: kill IPERM_FLAG_RCU not used anymore Signed-off-by: Al Viro --- include/linux/fs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 1fdefe3995fd..8494aac189f0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1573,8 +1573,6 @@ struct file_operations { loff_t len); }; -#define IPERM_FLAG_RCU 0x0001 - struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameidata *); void * (*follow_link) (struct dentry *, struct nameidata *); -- cgit v1.2.3 From 3d4ff43d895c50319af45eb4bf04a4618eccdf76 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 22 Jun 2011 18:40:12 -0400 Subject: nfs_open_context doesn't need struct path either just dentry, please... Signed-off-by: Al Viro --- include/linux/nfs_fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 86014811a0fb..8b579beb6358 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -85,7 +85,7 @@ struct nfs_lock_context { struct nfs4_state; struct nfs_open_context { struct nfs_lock_context lock_context; - struct path path; + struct dentry *dentry; struct rpc_cred *cred; struct nfs4_state *state; fmode_t mode; @@ -372,7 +372,7 @@ extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr); extern struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx); extern void put_nfs_open_context(struct nfs_open_context *ctx); extern struct nfs_open_context *nfs_find_open_context(struct inode *inode, struct rpc_cred *cred, fmode_t mode); -extern struct nfs_open_context *alloc_nfs_open_context(struct path *path, struct rpc_cred *cred, fmode_t f_mode); +extern struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, struct rpc_cred *cred, fmode_t f_mode); extern void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx); extern struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx); extern void nfs_put_lock_context(struct nfs_lock_context *l_ctx); -- cgit v1.2.3 From 49084c3bb2055c401f3493c13edae14d49128ca0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 25 Jun 2011 21:59:52 -0400 Subject: kill LOOKUP_CONTINUE LOOKUP_PARENT is equivalent to it now Signed-off-by: Al Viro --- include/linux/namei.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index eba45ea10298..3439ab862e1d 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -48,7 +48,6 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; */ #define LOOKUP_FOLLOW 0x0001 #define LOOKUP_DIRECTORY 0x0002 -#define LOOKUP_CONTINUE 0x0004 #define LOOKUP_PARENT 0x0010 #define LOOKUP_REVAL 0x0020 -- cgit v1.2.3 From dae6ad8f37529963ae7df52baaccf056b38f210e Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 26 Jun 2011 11:50:15 -0400 Subject: new helpers: kern_path_create/user_path_create combination of kern_path_parent() and lookup_create(). Does *not* expose struct nameidata to caller. Syscalls converted to that... Signed-off-by: Al Viro --- include/linux/namei.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index 3439ab862e1d..b8cea804d31a 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -74,6 +74,8 @@ extern int user_path_at(int, const char __user *, unsigned, struct path *); extern int kern_path(const char *, unsigned, struct path *); +extern struct dentry *kern_path_create(int, const char *, struct path *, int); +extern struct dentry *user_path_create(int, const char __user *, struct path *, int); extern int kern_path_parent(const char *, struct nameidata *); extern int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct nameidata *); -- cgit v1.2.3 From 6657719390cd05be45f4e3b501d8bb46889c0a19 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 28 Jun 2011 15:41:10 -0400 Subject: make sure that nsproxy_cache is initialized early enough Signed-off-by: Al Viro --- include/linux/nsproxy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index 50d20aba57d3..cc37a55ad004 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -68,6 +68,7 @@ void switch_task_namespaces(struct task_struct *tsk, struct nsproxy *new); void free_nsproxy(struct nsproxy *ns); int unshare_nsproxy_namespaces(unsigned long, struct nsproxy **, struct fs_struct *); +int __init nsproxy_cache_init(void); static inline void put_nsproxy(struct nsproxy *ns) { -- cgit v1.2.3 From ed75e95de574c99575e5f3e1d9ca59ea8c12a9cb Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 27 Jun 2011 16:53:43 -0400 Subject: kill lookup_create() folded into the only caller (kern_path_create()) Signed-off-by: Al Viro --- include/linux/dcache.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 5fa5bd33b979..3f22d8d6d8a3 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -423,7 +423,6 @@ static inline bool d_need_lookup(struct dentry *dentry) } extern void d_clear_need_lookup(struct dentry *dentry); -extern struct dentry *lookup_create(struct nameidata *nd, int is_dir); extern int sysctl_vfs_cache_pressure; -- cgit v1.2.3 From e0a0124936171af6156b80fe8ac8799f039e767f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 27 Jun 2011 17:00:37 -0400 Subject: switch vfs_path_lookup() to struct path Signed-off-by: Al Viro --- include/linux/namei.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index b8cea804d31a..76fe2c62ae71 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -78,7 +78,7 @@ extern struct dentry *kern_path_create(int, const char *, struct path *, int); extern struct dentry *user_path_create(int, const char __user *, struct path *, int); extern int kern_path_parent(const char *, struct nameidata *); extern int vfs_path_lookup(struct dentry *, struct vfsmount *, - const char *, unsigned int, struct nameidata *); + const char *, unsigned int, struct path *); extern struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry *dentry, int (*open)(struct inode *, struct file *)); -- cgit v1.2.3 From 0ee5dc676a5f8fadede608c7281dfedb1ae714ea Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 7 Jul 2011 15:44:25 -0400 Subject: btrfs: kill magical embedded struct superblock Signed-off-by: Al Viro --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 8494aac189f0..a0011aef4338 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1835,6 +1835,8 @@ void kill_litter_super(struct super_block *sb); void deactivate_super(struct super_block *sb); void deactivate_locked_super(struct super_block *sb); int set_anon_super(struct super_block *s, void *data); +int get_anon_bdev(dev_t *); +void free_anon_bdev(dev_t); struct super_block *sget(struct file_system_type *type, int (*test)(struct super_block *,void *), int (*set)(struct super_block *,void *), -- cgit v1.2.3 From e9299f5058595a655c3b207cda9635e28b9197e6 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Fri, 8 Jul 2011 14:14:37 +1000 Subject: vmscan: add customisable shrinker batch size For shrinkers that have their own cond_resched* calls, having shrink_slab break the work down into small batches is not paticularly efficient. Add a custom batchsize field to the struct shrinker so that shrinkers can use a larger batch size if they desire. A value of zero (uninitialised) means "use the default", so behaviour is unchanged by this patch. Signed-off-by: Dave Chinner Signed-off-by: Al Viro --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9670f71d7be9..9b9777ac726d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1150,6 +1150,7 @@ struct shrink_control { struct shrinker { int (*shrink)(struct shrinker *, struct shrink_control *sc); int seeks; /* seeks to recreate an obj */ + long batch; /* reclaim batch size, 0 = default */ /* These are for internal use */ struct list_head list; -- cgit v1.2.3 From 98b745c647a5a90c3c21ea43cbfad9a47b0dfad7 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Fri, 8 Jul 2011 14:14:39 +1000 Subject: inode: Make unused inode LRU per superblock The inode unused list is currently a global LRU. This does not match the other global filesystem cache - the dentry cache - which uses per-superblock LRU lists. Hence we have related filesystem object types using different LRU reclaimation schemes. To enable a per-superblock filesystem cache shrinker, both of these caches need to have per-sb unused object LRU lists. Hence this patch converts the global inode LRU to per-sb LRUs. The patch only does rudimentary per-sb propotioning in the shrinker infrastructure, as this gets removed when the per-sb shrinker callouts are introduced later on. Signed-off-by: Dave Chinner Signed-off-by: Al Viro --- include/linux/fs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index a0011aef4338..9724f0a48742 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1397,6 +1397,10 @@ struct super_block { struct list_head s_dentry_lru; /* unused dentry lru */ int s_nr_dentry_unused; /* # of dentry on lru */ + /* inode_lru_lock protects s_inode_lru and s_nr_inodes_unused */ + struct list_head s_inode_lru; /* unused inode lru */ + int s_nr_inodes_unused; /* # of inodes on lru */ + struct block_device *s_bdev; struct backing_dev_info *s_bdi; struct mtd_info *s_mtd; -- cgit v1.2.3 From 09cc9fc7a7c3d872065426d7fb0f0ad6d3eb90fc Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Fri, 8 Jul 2011 14:14:40 +1000 Subject: inode: move to per-sb LRU locks With the inode LRUs moving to per-sb structures, there is no longer a need for a global inode_lru_lock. The locking can be made more fine-grained by moving to a per-sb LRU lock, isolating the LRU operations of different filesytsems completely from each other. Signed-off-by: Dave Chinner Signed-off-by: Al Viro --- include/linux/fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 9724f0a48742..460d2cc21ec6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1397,7 +1397,8 @@ struct super_block { struct list_head s_dentry_lru; /* unused dentry lru */ int s_nr_dentry_unused; /* # of dentry on lru */ - /* inode_lru_lock protects s_inode_lru and s_nr_inodes_unused */ + /* s_inode_lru_lock protects s_inode_lru and s_nr_inodes_unused */ + spinlock_t s_inode_lru_lock ____cacheline_aligned_in_smp; struct list_head s_inode_lru; /* unused inode lru */ int s_nr_inodes_unused; /* # of inodes on lru */ -- cgit v1.2.3 From d12dc256547cec4fe62dad6e94252dced4ee2d58 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 20 Jul 2011 14:31:47 +0200 Subject: quota: Remove unused declaration There is no point in declaring quotactl() syscall prototype in kernel header and 'make headers_check' complains about it. So just remove those lines. Signed-off-by: Jan Kara --- include/linux/quota.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index 9a85412e0db6..313b7defc088 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -415,13 +415,5 @@ struct quota_module_name { {QFMT_VFS_V0, "quota_v2"},\ {0, NULL}} -#else - -# /* nodep */ include - -__BEGIN_DECLS -long quotactl __P ((unsigned int, const char *, int, caddr_t)); -__END_DECLS - #endif /* __KERNEL__ */ #endif /* _QUOTA_ */ -- cgit v1.2.3 From 9c3f75cbd144014bea6af866a154cc2e73ab2287 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 14 Jul 2011 13:00:06 +0200 Subject: sched: Break out cpu_power from the sched_group structure In order to prepare for non-unique sched_groups per domain, we need to carry the cpu_power elsewhere, so put a level of indirection in. Reported-and-tested-by: Anton Blanchard Signed-off-by: Peter Zijlstra Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/n/tip-qkho2byuhe4482fuknss40ad@git.kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 496770a96487..2e5b3c8e2d3e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -893,16 +893,20 @@ static inline int sd_power_saving_flags(void) return 0; } -struct sched_group { - struct sched_group *next; /* Must be a circular list */ - atomic_t ref; - +struct sched_group_power { /* * CPU power of this group, SCHED_LOAD_SCALE being max power for a * single CPU. */ - unsigned int cpu_power, cpu_power_orig; + unsigned int power, power_orig; +}; + +struct sched_group { + struct sched_group *next; /* Must be a circular list */ + atomic_t ref; + unsigned int group_weight; + struct sched_group_power *sgp; /* * The CPUs this group covers. -- cgit v1.2.3 From e3589f6c81e4764d32a25d2a2a0afe54fa344f5c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 15 Jul 2011 10:35:52 +0200 Subject: sched: Allow for overlapping sched_domain spans Allow for sched_domain spans that overlap by giving such domains their own sched_group list instead of sharing the sched_groups amongst each-other. This is needed for machines with more than 16 nodes, because sched_domain_node_span() will generate a node mask from the 16 nearest nodes without regard if these masks have any overlap. Currently sched_domains have a sched_group that maps to their child sched_domain span, and since there is no overlap we share the sched_group between the sched_domains of the various CPUs. If however there is overlap, we would need to link the sched_group list in different ways for each cpu, and hence sharing isn't possible. In order to solve this, allocate private sched_groups for each CPU's sched_domain but have the sched_groups share a sched_group_power structure such that we can uniquely track the power. Reported-and-tested-by: Anton Blanchard Signed-off-by: Peter Zijlstra Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/n/tip-08bxqw9wis3qti9u5inifh3y@git.kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 2e5b3c8e2d3e..bde99d5358dc 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -844,6 +844,7 @@ enum cpu_idle_type { #define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */ #define SD_ASYM_PACKING 0x0800 /* Place busy groups earlier in the domain */ #define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */ +#define SD_OVERLAP 0x2000 /* sched_domains of this level overlap */ enum powersavings_balance_level { POWERSAVINGS_BALANCE_NONE = 0, /* No power saving load balance */ @@ -894,6 +895,7 @@ static inline int sd_power_saving_flags(void) } struct sched_group_power { + atomic_t ref; /* * CPU power of this group, SCHED_LOAD_SCALE being max power for a * single CPU. -- cgit v1.2.3 From b56efcf0a45aa7fc32de90d5f9838541082fbc19 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 20 Jul 2011 19:04:23 +0200 Subject: slab: shrink sizeof(struct kmem_cache) Reduce high order allocations for some setups. (NR_CPUS=4096 -> we need 64KB per kmem_cache struct) We now allocate exact needed size (using nr_cpu_ids and nr_node_ids) This also makes code a bit smaller on x86_64, since some field offsets are less than the 127 limit : Before patch : # size mm/slab.o text data bss dec hex filename 22605 361665 32 384302 5dd2e mm/slab.o After patch : # size mm/slab.o text data bss dec hex filename 22349 353473 8224 384046 5dc2e mm/slab.o CC: Andrew Morton Reported-by: Konstantin Khlebnikov Signed-off-by: Eric Dumazet Acked-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slab_def.h | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index d7f63112f63c..d00e0bacda93 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -24,21 +24,19 @@ */ struct kmem_cache { -/* 1) per-cpu data, touched during every alloc/free */ - struct array_cache *array[NR_CPUS]; -/* 2) Cache tunables. Protected by cache_chain_mutex */ +/* 1) Cache tunables. Protected by cache_chain_mutex */ unsigned int batchcount; unsigned int limit; unsigned int shared; unsigned int buffer_size; u32 reciprocal_buffer_size; -/* 3) touched by every alloc & free from the backend */ +/* 2) touched by every alloc & free from the backend */ unsigned int flags; /* constant flags */ unsigned int num; /* # of objs per slab */ -/* 4) cache_grow/shrink */ +/* 3) cache_grow/shrink */ /* order of pgs per slab (2^n) */ unsigned int gfporder; @@ -54,11 +52,11 @@ struct kmem_cache { /* constructor func */ void (*ctor)(void *obj); -/* 5) cache creation/removal */ +/* 4) cache creation/removal */ const char *name; struct list_head next; -/* 6) statistics */ +/* 5) statistics */ #ifdef CONFIG_DEBUG_SLAB unsigned long num_active; unsigned long num_allocations; @@ -85,16 +83,18 @@ struct kmem_cache { int obj_size; #endif /* CONFIG_DEBUG_SLAB */ +/* 6) per-cpu/per-node data, touched during every alloc/free */ /* - * We put nodelists[] at the end of kmem_cache, because we want to size - * this array to nr_node_ids slots instead of MAX_NUMNODES + * We put array[] at the end of kmem_cache, because we want to size + * this array to nr_cpu_ids slots instead of NR_CPUS * (see kmem_cache_init()) - * We still use [MAX_NUMNODES] and not [1] or [0] because cache_cache - * is statically defined, so we reserve the max number of nodes. + * We still use [NR_CPUS] and not [1] or [0] because cache_cache + * is statically defined, so we reserve the max number of cpus. */ - struct kmem_list3 *nodelists[MAX_NUMNODES]; + struct kmem_list3 **nodelists; + struct array_cache *array[NR_CPUS]; /* - * Do not add fields after nodelists[] + * Do not add fields after array[] */ }; -- cgit v1.2.3 From 7f70893173b056df691b2ee7546bb44fd9abae6a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jan=20H=2E=20Sch=C3=B6nherr?= Date: Tue, 19 Jul 2011 21:10:26 +0200 Subject: rcu: Fix wrong check in list_splice_init_rcu() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If the list to be spliced is empty, then list_splice_init_rcu() has nothing to do. Unfortunately, list_splice_init_rcu() does not check the list to be spliced; it instead checks the list to be spliced into. This results in memory leaks given current usage. This commit therefore fixes the empty-list check. Signed-off-by: Jan H. Schönherr Signed-off-by: Paul E. McKenney --- include/linux/rculist.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index e3beb315517a..d079290843a9 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -183,7 +183,7 @@ static inline void list_splice_init_rcu(struct list_head *list, struct list_head *last = list->prev; struct list_head *at = head->next; - if (list_empty(head)) + if (list_empty(list)) return; /* "first" and "last" tracking list, so initialize it. */ -- cgit v1.2.3 From 85d6509dc8ca24b2b652863ef7a75622ddca17d6 Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Fri, 27 May 2011 23:48:12 +0800 Subject: mmc: sdhci: make sdhci-pltfm device drivers self registered The patch turns the common stuff in sdhci-pltfm.c into functions, and add device drivers their own .probe and .remove which in turn call into the common functions, so that those sdhci-pltfm device drivers register itself and keep all device specific things away from common sdhci-pltfm file. Signed-off-by: Shawn Guo Reviewed-by: Grant Likely Acked-by: Arnd Bergmann Acked-by: Anton Vorontsov Signed-off-by: Chris Ball --- include/linux/mmc/sdhci-pltfm.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/sdhci-pltfm.h b/include/linux/mmc/sdhci-pltfm.h index 548d59d404cb..f1c2ac3fb300 100644 --- a/include/linux/mmc/sdhci-pltfm.h +++ b/include/linux/mmc/sdhci-pltfm.h @@ -15,21 +15,15 @@ #define _SDHCI_PLTFM_H struct sdhci_ops; -struct sdhci_host; /** * struct sdhci_pltfm_data - SDHCI platform-specific information & hooks * @ops: optional pointer to the platform-provided SDHCI ops * @quirks: optional SDHCI quirks - * @init: optional hook that is called during device probe, before the - * driver tries to access any SDHCI registers - * @exit: optional hook that is called during device removal */ struct sdhci_pltfm_data { struct sdhci_ops *ops; unsigned int quirks; - int (*init)(struct sdhci_host *host, struct sdhci_pltfm_data *pdata); - void (*exit)(struct sdhci_host *host); }; #endif /* _SDHCI_PLTFM_H */ -- cgit v1.2.3 From 94cc6a86567cb3c2234807081a46ce5400c36b31 Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Fri, 27 May 2011 23:48:15 +0800 Subject: mmc: sdhci: merge two sdhci-pltfm.h into one The structure sdhci_pltfm_data is not necessarily to be in a public header like include/linux/mmc/sdhci-pltfm.h, so the patch moves it into drivers/mmc/host/sdhci-pltfm.h and eliminates the former one. Signed-off-by: Shawn Guo Reviewed-by: Grant Likely Reviewed-by: Wolfram Sang Signed-off-by: Chris Ball --- include/linux/mmc/sdhci-pltfm.h | 29 ----------------------------- 1 file changed, 29 deletions(-) delete mode 100644 include/linux/mmc/sdhci-pltfm.h (limited to 'include/linux') diff --git a/include/linux/mmc/sdhci-pltfm.h b/include/linux/mmc/sdhci-pltfm.h deleted file mode 100644 index f1c2ac3fb300..000000000000 --- a/include/linux/mmc/sdhci-pltfm.h +++ /dev/null @@ -1,29 +0,0 @@ -/* - * Platform data declarations for the sdhci-pltfm driver. - * - * Copyright (c) 2010 MontaVista Software, LLC. - * - * Author: Anton Vorontsov - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or (at - * your option) any later version. - */ - -#ifndef _SDHCI_PLTFM_H -#define _SDHCI_PLTFM_H - -struct sdhci_ops; - -/** - * struct sdhci_pltfm_data - SDHCI platform-specific information & hooks - * @ops: optional pointer to the platform-provided SDHCI ops - * @quirks: optional SDHCI quirks - */ -struct sdhci_pltfm_data { - struct sdhci_ops *ops; - unsigned int quirks; -}; - -#endif /* _SDHCI_PLTFM_H */ -- cgit v1.2.3 From 100e918610b7487fa18db97b3879cd8d1fdd5974 Mon Sep 17 00:00:00 2001 From: "Robert P. J. Day" Date: Fri, 27 May 2011 16:04:03 -0400 Subject: mmc: Standardize header file inclusion checks. Standardize the checks for multiple MMC header file inclusion, including adding comments to terminating #endif's, and fixing one incorrect comment. Signed-off-by: Robert P. J. Day Signed-off-by: Chris Ball --- include/linux/mmc/boot.h | 6 +++--- include/linux/mmc/card.h | 2 +- include/linux/mmc/core.h | 2 +- include/linux/mmc/dw_mmc.h | 6 +++--- include/linux/mmc/host.h | 3 +-- include/linux/mmc/ioctl.h | 2 +- include/linux/mmc/mmc.h | 7 +++---- include/linux/mmc/pm.h | 2 +- include/linux/mmc/sd.h | 7 +++---- include/linux/mmc/sdhci-spear.h | 6 +++--- include/linux/mmc/sdhci.h | 6 +++--- include/linux/mmc/sdio.h | 7 +++---- include/linux/mmc/sdio_func.h | 7 +++---- include/linux/mmc/sdio_ids.h | 6 +++--- include/linux/mmc/sh_mmcif.h | 6 +++--- include/linux/mmc/sh_mobile_sdhi.h | 6 +++--- include/linux/mmc/tmio.h | 6 +++--- 17 files changed, 41 insertions(+), 46 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/boot.h b/include/linux/mmc/boot.h index 39d787c229cb..23acc3baa07d 100644 --- a/include/linux/mmc/boot.h +++ b/include/linux/mmc/boot.h @@ -1,7 +1,7 @@ -#ifndef MMC_BOOT_H -#define MMC_BOOT_H +#ifndef LINUX_MMC_BOOT_H +#define LINUX_MMC_BOOT_H enum { MMC_PROGRESS_ENTER, MMC_PROGRESS_INIT, MMC_PROGRESS_LOAD, MMC_PROGRESS_DONE }; -#endif +#endif /* LINUX_MMC_BOOT_H */ diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 6ad43554ac05..b460fc2af8a1 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -403,4 +403,4 @@ extern void mmc_unregister_driver(struct mmc_driver *); extern void mmc_fixup_device(struct mmc_card *card, const struct mmc_fixup *table); -#endif +#endif /* LINUX_MMC_CARD_H */ diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index b6718e549a51..791f060a6f1d 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -179,4 +179,4 @@ static inline void mmc_claim_host(struct mmc_host *host) extern u32 mmc_vddrange_to_ocrmask(int vdd_min, int vdd_max); -#endif +#endif /* LINUX_MMC_CORE_H */ diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h index bdd7ceeb99e4..55d9909c7abd 100644 --- a/include/linux/mmc/dw_mmc.h +++ b/include/linux/mmc/dw_mmc.h @@ -11,8 +11,8 @@ * (at your option) any later version. */ -#ifndef _LINUX_MMC_DW_MMC_H_ -#define _LINUX_MMC_DW_MMC_H_ +#ifndef LINUX_MMC_DW_MMC_H +#define LINUX_MMC_DW_MMC_H #define MAX_MCI_SLOTS 2 @@ -219,4 +219,4 @@ struct dw_mci_board { struct block_settings *blk_settings; }; -#endif /* _LINUX_MMC_DW_MMC_H_ */ +#endif /* LINUX_MMC_DW_MMC_H */ diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 1ee4424462eb..fc24b38b48cb 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -373,5 +373,4 @@ static inline int mmc_host_cmd23(struct mmc_host *host) { return host->caps & MMC_CAP_CMD23; } -#endif - +#endif /* LINUX_MMC_HOST_H */ diff --git a/include/linux/mmc/ioctl.h b/include/linux/mmc/ioctl.h index 5baf2983a12f..8fa5bc5f8059 100644 --- a/include/linux/mmc/ioctl.h +++ b/include/linux/mmc/ioctl.h @@ -51,4 +51,4 @@ struct mmc_ioc_cmd { * block device operations. */ #define MMC_IOC_MAX_BYTES (512L * 256) -#endif /* LINUX_MMC_IOCTL_H */ +#endif /* LINUX_MMC_IOCTL_H */ diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index ac26a685cca8..5bade0605641 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -21,8 +21,8 @@ * 15 May 2002 */ -#ifndef MMC_MMC_H -#define MMC_MMC_H +#ifndef LINUX_MMC_MMC_H +#define LINUX_MMC_MMC_H /* Standard MMC commands (4.1) type argument response */ /* class 1 */ @@ -327,5 +327,4 @@ struct _mmc_csd { #define MMC_SWITCH_MODE_CLEAR_BITS 0x02 /* Clear bits which are 1 in value */ #define MMC_SWITCH_MODE_WRITE_BYTE 0x03 /* Set target to value */ -#endif /* MMC_MMC_PROTOCOL_H */ - +#endif /* LINUX_MMC_MMC_H */ diff --git a/include/linux/mmc/pm.h b/include/linux/mmc/pm.h index d37aac49cf9a..4a139204c20c 100644 --- a/include/linux/mmc/pm.h +++ b/include/linux/mmc/pm.h @@ -27,4 +27,4 @@ typedef unsigned int mmc_pm_flag_t; #define MMC_PM_KEEP_POWER (1 << 0) /* preserve card power during suspend */ #define MMC_PM_WAKE_SDIO_IRQ (1 << 1) /* wake up host system on SDIO IRQ assertion */ -#endif +#endif /* LINUX_MMC_PM_H */ diff --git a/include/linux/mmc/sd.h b/include/linux/mmc/sd.h index 7d35d52c3df3..1ebcf9ba1256 100644 --- a/include/linux/mmc/sd.h +++ b/include/linux/mmc/sd.h @@ -9,8 +9,8 @@ * your option) any later version. */ -#ifndef MMC_SD_H -#define MMC_SD_H +#ifndef LINUX_MMC_SD_H +#define LINUX_MMC_SD_H /* SD commands type argument response */ /* class 0 */ @@ -91,5 +91,4 @@ #define SD_SWITCH_ACCESS_DEF 0 #define SD_SWITCH_ACCESS_HS 1 -#endif - +#endif /* LINUX_MMC_SD_H */ diff --git a/include/linux/mmc/sdhci-spear.h b/include/linux/mmc/sdhci-spear.h index 9188c973f3e1..5cdc96da9dd5 100644 --- a/include/linux/mmc/sdhci-spear.h +++ b/include/linux/mmc/sdhci-spear.h @@ -11,8 +11,8 @@ * warranty of any kind, whether express or implied. */ -#ifndef MMC_SDHCI_SPEAR_H -#define MMC_SDHCI_SPEAR_H +#ifndef LINUX_MMC_SDHCI_SPEAR_H +#define LINUX_MMC_SDHCI_SPEAR_H #include /* @@ -39,4 +39,4 @@ sdhci_set_plat_data(struct platform_device *pdev, struct sdhci_plat_data *data) pdev->dev.platform_data = data; } -#endif /* MMC_SDHCI_SPEAR_H */ +#endif /* LINUX_MMC_SDHCI_SPEAR_H */ diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h index 6a68c4eb4e44..5666f3abfab7 100644 --- a/include/linux/mmc/sdhci.h +++ b/include/linux/mmc/sdhci.h @@ -8,8 +8,8 @@ * the Free Software Foundation; either version 2 of the License, or (at * your option) any later version. */ -#ifndef __SDHCI_H -#define __SDHCI_H +#ifndef LINUX_MMC_SDHCI_H +#define LINUX_MMC_SDHCI_H #include #include @@ -162,4 +162,4 @@ struct sdhci_host { unsigned long private[0] ____cacheline_aligned; }; -#endif /* __SDHCI_H */ +#endif /* LINUX_MMC_SDHCI_H */ diff --git a/include/linux/mmc/sdio.h b/include/linux/mmc/sdio.h index 245cdacee544..2a2e9905a247 100644 --- a/include/linux/mmc/sdio.h +++ b/include/linux/mmc/sdio.h @@ -9,8 +9,8 @@ * your option) any later version. */ -#ifndef MMC_SDIO_H -#define MMC_SDIO_H +#ifndef LINUX_MMC_SDIO_H +#define LINUX_MMC_SDIO_H /* SDIO commands type argument response */ #define SD_IO_SEND_OP_COND 5 /* bcr [23:0] OCR R4 */ @@ -161,5 +161,4 @@ #define SDIO_FBR_BLKSIZE 0x10 /* block size (2 bytes) */ -#endif - +#endif /* LINUX_MMC_SDIO_H */ diff --git a/include/linux/mmc/sdio_func.h b/include/linux/mmc/sdio_func.h index 31baaf82f458..50f0bc952328 100644 --- a/include/linux/mmc/sdio_func.h +++ b/include/linux/mmc/sdio_func.h @@ -9,8 +9,8 @@ * your option) any later version. */ -#ifndef MMC_SDIO_FUNC_H -#define MMC_SDIO_FUNC_H +#ifndef LINUX_MMC_SDIO_FUNC_H +#define LINUX_MMC_SDIO_FUNC_H #include #include @@ -161,5 +161,4 @@ extern void sdio_f0_writeb(struct sdio_func *func, unsigned char b, extern mmc_pm_flag_t sdio_get_host_pm_caps(struct sdio_func *func); extern int sdio_set_host_pm_flags(struct sdio_func *func, mmc_pm_flag_t flags); -#endif - +#endif /* LINUX_MMC_SDIO_FUNC_H */ diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index a36ab3bc7b03..9f03feedc8e7 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -2,8 +2,8 @@ * SDIO Classes, Interface Types, Manufacturer IDs, etc. */ -#ifndef MMC_SDIO_IDS_H -#define MMC_SDIO_IDS_H +#ifndef LINUX_MMC_SDIO_IDS_H +#define LINUX_MMC_SDIO_IDS_H /* * Standard SDIO Function Interfaces @@ -44,4 +44,4 @@ #define SDIO_DEVICE_ID_SIANO_NOVA_A0 0x1100 #define SDIO_DEVICE_ID_SIANO_STELLAR 0x5347 -#endif +#endif /* LINUX_MMC_SDIO_IDS_H */ diff --git a/include/linux/mmc/sh_mmcif.h b/include/linux/mmc/sh_mmcif.h index 9eb9b4b96f55..0222cd8ebe76 100644 --- a/include/linux/mmc/sh_mmcif.h +++ b/include/linux/mmc/sh_mmcif.h @@ -11,8 +11,8 @@ * */ -#ifndef __SH_MMCIF_H__ -#define __SH_MMCIF_H__ +#ifndef LINUX_MMC_SH_MMCIF_H +#define LINUX_MMC_SH_MMCIF_H #include #include @@ -220,4 +220,4 @@ static inline void sh_mmcif_boot_init(void __iomem *base) sh_mmcif_boot_cmd(base, 0x03400040, 0x00010000); } -#endif /* __SH_MMCIF_H__ */ +#endif /* LINUX_MMC_SH_MMCIF_H */ diff --git a/include/linux/mmc/sh_mobile_sdhi.h b/include/linux/mmc/sh_mobile_sdhi.h index faf32b6ec185..bd50b365167f 100644 --- a/include/linux/mmc/sh_mobile_sdhi.h +++ b/include/linux/mmc/sh_mobile_sdhi.h @@ -1,5 +1,5 @@ -#ifndef __SH_MOBILE_SDHI_H__ -#define __SH_MOBILE_SDHI_H__ +#ifndef LINUX_MMC_SH_MOBILE_SDHI_H +#define LINUX_MMC_SH_MOBILE_SDHI_H #include @@ -17,4 +17,4 @@ struct sh_mobile_sdhi_info { int (*get_cd)(struct platform_device *pdev); }; -#endif /* __SH_MOBILE_SDHI_H__ */ +#endif /* LINUX_MMC_SH_MOBILE_SDHI_H */ diff --git a/include/linux/mmc/tmio.h b/include/linux/mmc/tmio.h index 19490b942db0..551490f0613d 100644 --- a/include/linux/mmc/tmio.h +++ b/include/linux/mmc/tmio.h @@ -12,8 +12,8 @@ * * TC6393XB TC6391XB TC6387XB T7L66XB ASIC3 */ -#ifndef _LINUX_MMC_TMIO_H_ -#define _LINUX_MMC_TMIO_H_ +#ifndef LINUX_MMC_TMIO_H +#define LINUX_MMC_TMIO_H #define CTL_SD_CMD 0x00 #define CTL_ARG_REG 0x04 @@ -60,4 +60,4 @@ #define TMIO_BBS 512 /* Boot block size */ -#endif /* _LINUX_MMC_TMIO_H_ */ +#endif /* LINUX_MMC_TMIO_H */ -- cgit v1.2.3 From bfed345edfe05b291f7e5d396d4b447b6e8e66fa Mon Sep 17 00:00:00 2001 From: Zhangfei Gao Date: Mon, 20 Jun 2011 22:11:52 +0800 Subject: mmc: sdhci-pxa: move platform data to include/linux/platform_data As suggested by Arnd, move platform data to include/linux/platform_data in order to improve build coverage for the driver. Signed-off-by: Zhangfei Gao Acked-by: Arnd Bergmann Signed-off-by: Chris Ball --- include/linux/platform_data/pxa_sdhci.h | 60 +++++++++++++++++++++++++++++++++ 1 file changed, 60 insertions(+) create mode 100644 include/linux/platform_data/pxa_sdhci.h (limited to 'include/linux') diff --git a/include/linux/platform_data/pxa_sdhci.h b/include/linux/platform_data/pxa_sdhci.h new file mode 100644 index 000000000000..51ad0995abac --- /dev/null +++ b/include/linux/platform_data/pxa_sdhci.h @@ -0,0 +1,60 @@ +/* + * include/linux/platform_data/pxa_sdhci.h + * + * Copyright 2010 Marvell + * Zhangfei Gao + * + * PXA Platform - SDHCI platform data definitions + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _PXA_SDHCI_H_ +#define _PXA_SDHCI_H_ + +/* pxa specific flag */ +/* Require clock free running */ +#define PXA_FLAG_ENABLE_CLOCK_GATING (1<<0) +/* card always wired to host, like on-chip emmc */ +#define PXA_FLAG_CARD_PERMANENT (1<<1) +/* Board design supports 8-bit data on SD/SDIO BUS */ +#define PXA_FLAG_SD_8_BIT_CAPABLE_SLOT (1<<2) + +/* + * struct pxa_sdhci_platdata() - Platform device data for PXA SDHCI + * @flags: flags for platform requirement + * @clk_delay_cycles: + * mmp2: each step is roughly 100ps, 5bits width + * pxa910: each step is 1ns, 4bits width + * @clk_delay_sel: select clk_delay, used on pxa910 + * 0: choose feedback clk + * 1: choose feedback clk + delay value + * 2: choose internal clk + * @clk_delay_enable: enable clk_delay or not, used on pxa910 + * @ext_cd_gpio: gpio pin used for external CD line + * @ext_cd_gpio_invert: invert values for external CD gpio line + * @max_speed: the maximum speed supported + * @host_caps: Standard MMC host capabilities bit field. + * @quirks: quirks of platfrom + * @pm_caps: pm_caps of platfrom + */ +struct sdhci_pxa_platdata { + unsigned int flags; + unsigned int clk_delay_cycles; + unsigned int clk_delay_sel; + bool clk_delay_enable; + unsigned int ext_cd_gpio; + bool ext_cd_gpio_invert; + unsigned int max_speed; + unsigned int host_caps; + unsigned int quirks; + unsigned int pm_caps; +}; + +struct sdhci_pxa { + u8 clk_enable; + u8 power_mode; +}; +#endif /* _PXA_SDHCI_H_ */ -- cgit v1.2.3 From 0a2d4048a22079d7e79d6654bbacbef57bd5728a Mon Sep 17 00:00:00 2001 From: Russell King - ARM Linux Date: Mon, 20 Jun 2011 20:10:08 +0100 Subject: mmc: block: allow get_card_status() to return error status If the MMC_SEND_STATUS command is not successful, we should not return a zero status word, but instead allow the caller to know positively that an error occurred. Convert the open-coded get_card_status() to use the helper function, and provide definitions for the card state field. Signed-off-by: Russell King Acked-by: Linus Walleij Tested-by: Pawel Moll Signed-off-by: Chris Ball --- include/linux/mmc/mmc.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index 5bade0605641..5a794cb503ea 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -140,6 +140,16 @@ static inline bool mmc_op_multi(u32 opcode) #define R1_SWITCH_ERROR (1 << 7) /* sx, c */ #define R1_APP_CMD (1 << 5) /* sr, c */ +#define R1_STATE_IDLE 0 +#define R1_STATE_READY 1 +#define R1_STATE_IDENT 2 +#define R1_STATE_STBY 3 +#define R1_STATE_TRAN 4 +#define R1_STATE_DATA 5 +#define R1_STATE_RCV 6 +#define R1_STATE_PRG 7 +#define R1_STATE_DIS 8 + /* * MMC/SD in SPI mode reports R1 status always, and R2 for SEND_STATUS * R1 is the low order byte; R2 is the next highest byte, when present. -- cgit v1.2.3 From 95c7348d948dc4832434ddfaeba804ac14732f02 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Tue, 21 Jun 2011 08:00:08 +0900 Subject: mmc: tmio: name 0xd8 as CTL_DMA_ENABLE This reflects at least the current usage of this register and I think it improves the readability of the code ever so slightly. Cc: Guennadi Liakhovetski Cc: Magnus Damm Signed-off-by: Simon Horman Signed-off-by: Chris Ball --- include/linux/mmc/tmio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/tmio.h b/include/linux/mmc/tmio.h index 551490f0613d..3ae377623db0 100644 --- a/include/linux/mmc/tmio.h +++ b/include/linux/mmc/tmio.h @@ -30,6 +30,7 @@ #define CTL_TRANSACTION_CTL 0x34 #define CTL_SDIO_STATUS 0x36 #define CTL_SDIO_IRQ_MASK 0x38 +#define CTL_DMA_ENABLE 0xd8 #define CTL_RESET_SD 0xe0 #define CTL_SDIO_REGS 0x100 #define CTL_CLK_AND_WAIT_CTL 0x138 -- cgit v1.2.3 From 973ed3af1a570612771ed10dec6506c757767668 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Tue, 21 Jun 2011 08:00:10 +0900 Subject: mmc: sdhi: Add write16_hook Some controllers require waiting for the bus to become idle before writing to some registers. I have implemented this by adding a hook to sd_ctrl_write16() and implementing a hook for SDHI which waits for the bus to become idle. Cc: Guennadi Liakhovetski Cc: Magnus Damm Signed-off-by: Simon Horman Signed-off-by: Chris Ball --- include/linux/mfd/tmio.h | 8 ++++++++ include/linux/mmc/tmio.h | 1 + 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 5a90266c3a5a..0dc98044d8b7 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -68,6 +68,11 @@ * controller and report the event to the driver. */ #define TMIO_MMC_HAS_COLD_CD (1 << 3) +/* + * Some controllers require waiting for the SD bus to become + * idle before writing to some registers. + */ +#define TMIO_MMC_HAS_IDLE_WAIT (1 << 4) int tmio_core_mmc_enable(void __iomem *cnf, int shift, unsigned long base); int tmio_core_mmc_resume(void __iomem *cnf, int shift, unsigned long base); @@ -80,6 +85,8 @@ struct tmio_mmc_dma { int alignment_shift; }; +struct tmio_mmc_host; + /* * data for the MMC controller */ @@ -94,6 +101,7 @@ struct tmio_mmc_data { void (*set_pwr)(struct platform_device *host, int state); void (*set_clk_div)(struct platform_device *host, int state); int (*get_cd)(struct platform_device *host); + int (*write16_hook)(struct tmio_mmc_host *host, int addr); }; static inline void tmio_mmc_cd_wakeup(struct tmio_mmc_data *pdata) diff --git a/include/linux/mmc/tmio.h b/include/linux/mmc/tmio.h index 3ae377623db0..a1c1f321e519 100644 --- a/include/linux/mmc/tmio.h +++ b/include/linux/mmc/tmio.h @@ -21,6 +21,7 @@ #define CTL_XFER_BLK_COUNT 0xa #define CTL_RESPONSE 0x0c #define CTL_STATUS 0x1c +#define CTL_STATUS2 0x1e #define CTL_IRQ_MASK 0x20 #define CTL_SD_CARD_CLK_CTL 0x24 #define CTL_SD_XFER_LEN 0x26 -- cgit v1.2.3 From 1791b13ea4d97a6a7c162edd54485e932ad92f1b Mon Sep 17 00:00:00 2001 From: James Hogan Date: Fri, 24 Jun 2011 13:55:55 +0100 Subject: mmc: dw_mmc: convert card tasklet to workqueue Convert the card insert/remove tasklet to a workqueue, and call the setpower platform specific callback without the spinlock held. This means neither of the setpower or get_cd callbacks are called from atomic context which allows them to sleep. Signed-off-by: James Hogan Acked-by: Will Newton Signed-off-by: Chris Ball --- include/linux/mmc/dw_mmc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h index 55d9909c7abd..dea48475c436 100644 --- a/include/linux/mmc/dw_mmc.h +++ b/include/linux/mmc/dw_mmc.h @@ -131,7 +131,7 @@ struct dw_mci { u32 stop_cmdr; u32 dir_status; struct tasklet_struct tasklet; - struct tasklet_struct card_tasklet; + struct work_struct card_work; unsigned long pending_events; unsigned long completed_events; enum dw_mci_state state; -- cgit v1.2.3 From b86d825323b4c5d0c406e5b1a85af614acf0cf5a Mon Sep 17 00:00:00 2001 From: James Hogan Date: Fri, 24 Jun 2011 13:57:18 +0100 Subject: mmc: dw_mmc: don't hard code fifo depth, fix usage The FIFO_DEPTH hardware configuration parameter can be found from the power-on value of RX_WMark in the FIFOTH register. This is used to initialise the watermarks, but when calculating the number of free fifo spaces a preprocessor definition is used which is hard coded to 32. Fix reading the value out of FIFOTH (the default value in the RX_WMark field is FIFO_DEPTH-1 not FIFO_DEPTH). Allow the fifo depth to be overriden by platform data (since a bootloader may have changed FIFOTH making auto-detection unreliable). Store the fifo_depth for later use. Also fix the calculation to find the number of free bytes in the fifo to include the fifo depth in the left shift by the data shift, since the fifo depth is measured in fifo items not bytes. Signed-off-by: James Hogan Acked-by: Will Newton Signed-off-by: Chris Ball --- include/linux/mmc/dw_mmc.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h index dea48475c436..01db1a0b3dd1 100644 --- a/include/linux/mmc/dw_mmc.h +++ b/include/linux/mmc/dw_mmc.h @@ -74,6 +74,7 @@ struct mmc_data; * @pdev: Platform device associated with the MMC controller. * @pdata: Platform data associated with the MMC controller. * @slot: Slots sharing this MMC controller. + * @fifo_depth: depth of FIFO. * @data_shift: log2 of FIFO item size. * @push_data: Pointer to FIFO push function. * @pull_data: Pointer to FIFO pull function. @@ -146,6 +147,7 @@ struct dw_mci { struct dw_mci_slot *slot[MAX_MCI_SLOTS]; /* FIFO push and pull */ + int fifo_depth; int data_shift; void (*push_data)(struct dw_mci *host, void *buf, int cnt); void (*pull_data)(struct dw_mci *host, void *buf, int cnt); @@ -196,6 +198,12 @@ struct dw_mci_board { unsigned int bus_hz; /* Bus speed */ unsigned int caps; /* Capabilities */ + /* + * Override fifo depth. If 0, autodetect it from the FIFOTH register, + * but note that this may not be reliable after a bootloader has used + * it. + */ + unsigned int fifo_depth; /* delay in mS before detecting cards after interrupt */ u32 detect_delay_ms; -- cgit v1.2.3 From 34b664a20e2664de0d0d7990ca60276b96c08c75 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Fri, 24 Jun 2011 13:57:56 +0100 Subject: mmc: dw_mmc: handle unaligned buffers and sizes Update functions for PIO pushing and pulling data to and from the FIFO so that they can handle unaligned output buffers and unaligned buffer lengths. This makes more of the tests in mmc_test pass. Unaligned lengths in pulls are handled by reading the full FIFO item, and storing the remaining bytes in a small internal buffer (part_buf). The next data pull will copy data out of this buffer first before accessing the FIFO again. Similarly, for pushes the final bytes that don't fill a FIFO item are stored in the part_buf (or sent anyway if it's the last transfer), and then the part_buf is included at the beginning of the next buffer pushed. Unaligned buffers in pulls are handled specially if the architecture cannot do efficient unaligned accesses, by reading FIFO items into a aligned local buffer, and memcpy'ing them into the output buffer, again storing any remaining bytes in the internal buffer. Similarly for pushes the buffer is memcpy'd into an aligned local buffer then written to the FIFO. Signed-off-by: James Hogan Acked-by: Will Newton Signed-off-by: Chris Ball --- include/linux/mmc/dw_mmc.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h index 01db1a0b3dd1..f3f68ee08a1e 100644 --- a/include/linux/mmc/dw_mmc.h +++ b/include/linux/mmc/dw_mmc.h @@ -76,6 +76,9 @@ struct mmc_data; * @slot: Slots sharing this MMC controller. * @fifo_depth: depth of FIFO. * @data_shift: log2 of FIFO item size. + * @part_buf_start: Start index in part_buf. + * @part_buf_count: Bytes of partial data in part_buf. + * @part_buf: Simple buffer for partial fifo reads/writes. * @push_data: Pointer to FIFO push function. * @pull_data: Pointer to FIFO pull function. * @quirks: Set of quirks that apply to specific versions of the IP. @@ -149,6 +152,13 @@ struct dw_mci { /* FIFO push and pull */ int fifo_depth; int data_shift; + u8 part_buf_start; + u8 part_buf_count; + union { + u16 part_buf16; + u32 part_buf32; + u64 part_buf; + }; void (*push_data)(struct dw_mci *host, void *buf, int cnt); void (*pull_data)(struct dw_mci *host, void *buf, int cnt); -- cgit v1.2.3 From e056a1b5b67b4e4bfad00bf143ab14f634777705 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 28 Jun 2011 17:16:02 +0300 Subject: mmc: queue: let host controllers specify maximum discard timeout Some host controllers will not operate without a hardware timeout that is limited in value. However large discards require large timeouts, so there needs to be a way to specify the maximum discard size. A host controller driver may now specify the maximum discard timeout possible so that max_discard_sectors can be calculated. However, for eMMC when the High Capacity Erase Group Size is not in use, the timeout calculation depends on clock rate which may change. For that case Preferred Erase Size is used instead. Signed-off-by: Adrian Hunter Signed-off-by: Chris Ball --- include/linux/mmc/core.h | 1 + include/linux/mmc/host.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 791f060a6f1d..86d81cf75b70 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -155,6 +155,7 @@ extern int mmc_can_trim(struct mmc_card *card); extern int mmc_can_secure_erase_trim(struct mmc_card *card); extern int mmc_erase_group_aligned(struct mmc_card *card, unsigned int from, unsigned int nr); +extern unsigned int mmc_calc_max_discard(struct mmc_card *card); extern int mmc_set_blocklen(struct mmc_card *card, unsigned int blocklen); diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index fc24b38b48cb..c67d19b5542a 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -231,6 +231,7 @@ struct mmc_host { unsigned int max_req_size; /* maximum number of bytes in one req */ unsigned int max_blk_size; /* maximum size of one mmc block */ unsigned int max_blk_count; /* maximum number of blocks in one req */ + unsigned int max_discard_to; /* max. discard timeout in ms */ /* private data */ spinlock_t lock; /* lock for claim and bus ops */ -- cgit v1.2.3 From 03e8cb534e7cc3f71a07528a44da7ce68e5b5708 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Wed, 29 Jun 2011 09:28:43 +0100 Subject: mmc: dw_mmc: fix stop when fallen back to PIO There are several situations when dw_mci_submit_data_dma() decides to fall back to PIO mode instead of using DMA, due to a short (to avoid overhead) or "complex" (e.g. with unaligned buffers) transaction, even though host->use_dma is set. However dw_mci_stop_dma() decides whether to stop DMA or set the EVENT_XFER_COMPLETE event based on host->use_dma. When falling back to PIO mode this results in data timeout errors getting missed and the driver locking up. Therefore add host->using_dma to indicate whether the current transaction is using dma or not, and adjust dw_mci_stop_dma() to use that instead. Signed-off-by: James Hogan Acked-by: Will Newton Tested-by: Jaehoon Chung Signed-off-by: Chris Ball --- include/linux/mmc/dw_mmc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h index f3f68ee08a1e..6b46819705d1 100644 --- a/include/linux/mmc/dw_mmc.h +++ b/include/linux/mmc/dw_mmc.h @@ -48,6 +48,7 @@ struct mmc_data; * @data: The data currently being transferred, or NULL if no data * transfer is in progress. * @use_dma: Whether DMA channel is initialized or not. + * @using_dma: Whether DMA is in use for the current transfer. * @sg_dma: Bus address of DMA buffer. * @sg_cpu: Virtual address of DMA buffer. * @dma_ops: Pointer to platform-specific DMA callbacks. @@ -121,6 +122,7 @@ struct dw_mci { /* DMA interface members*/ int use_dma; + int using_dma; dma_addr_t sg_dma; void *sg_cpu; -- cgit v1.2.3 From aa8b683a7d392271ed349c6ab9f36b8c313794b7 Mon Sep 17 00:00:00 2001 From: Per Forlin Date: Fri, 1 Jul 2011 18:55:22 +0200 Subject: mmc: core: add non-blocking mmc request function Previously there has only been one function mmc_wait_for_req() to start and wait for a request. This patch adds: * mmc_start_req() - starts a request wihtout waiting If there is on ongoing request wait for completion of that request and start the new one and return. Does not wait for the new command to complete. This patch also adds new function members in struct mmc_host_ops only called from core.c: * pre_req - asks the host driver to prepare for the next job * post_req - asks the host driver to clean up after a completed job The intention is to use pre_req() and post_req() to do cache maintenance while a request is active. pre_req() can be called while a request is active to minimize latency to start next job. post_req() can be used after the next job is started to clean up the request. This will minimize the host driver request end latency. post_req() is typically used before ending the block request and handing over the buffer to the block layer. Add a host-private member in mmc_data to be used by pre_req to mark the data. The host driver will then check this mark to see if the data is prepared or not. Signed-off-by: Per Forlin Acked-by: Kyungmin Park Acked-by: Arnd Bergmann Reviewed-by: Venkatraman S Tested-by: Sourav Poddar Tested-by: Linus Walleij Signed-off-by: Chris Ball --- include/linux/mmc/core.h | 6 +++++- include/linux/mmc/host.h | 21 +++++++++++++++++++++ 2 files changed, 26 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 86d81cf75b70..b8b1b7a311f1 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -117,6 +117,7 @@ struct mmc_data { unsigned int sg_len; /* size of scatter list */ struct scatterlist *sg; /* I/O scatter list */ + s32 host_cookie; /* host private data */ }; struct mmc_request { @@ -125,13 +126,16 @@ struct mmc_request { struct mmc_data *data; struct mmc_command *stop; - void *done_data; /* completion data */ + struct completion completion; void (*done)(struct mmc_request *);/* completion function */ }; struct mmc_host; struct mmc_card; +struct mmc_async_req; +extern struct mmc_async_req *mmc_start_req(struct mmc_host *, + struct mmc_async_req *, int *); extern void mmc_wait_for_req(struct mmc_host *, struct mmc_request *); extern int mmc_wait_for_cmd(struct mmc_host *, struct mmc_command *, int); extern int mmc_app_cmd(struct mmc_host *, struct mmc_card *); diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index c67d19b5542a..9f9a4c64cde7 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -106,6 +106,15 @@ struct mmc_host_ops { */ int (*enable)(struct mmc_host *host); int (*disable)(struct mmc_host *host, int lazy); + /* + * It is optional for the host to implement pre_req and post_req in + * order to support double buffering of requests (prepare one + * request while another request is active). + */ + void (*post_req)(struct mmc_host *host, struct mmc_request *req, + int err); + void (*pre_req)(struct mmc_host *host, struct mmc_request *req, + bool is_first_req); void (*request)(struct mmc_host *host, struct mmc_request *req); /* * Avoid calling these three functions too often or in a "fast path", @@ -144,6 +153,16 @@ struct mmc_host_ops { struct mmc_card; struct device; +struct mmc_async_req { + /* active mmc request */ + struct mmc_request *mrq; + /* + * Check error status of completed mmc request. + * Returns 0 if success otherwise non zero. + */ + int (*err_check) (struct mmc_card *, struct mmc_async_req *); +}; + struct mmc_host { struct device *parent; struct device class_dev; @@ -282,6 +301,8 @@ struct mmc_host { struct dentry *debugfs_root; + struct mmc_async_req *areq; /* active async req */ + unsigned long private[0] ____cacheline_aligned; }; -- cgit v1.2.3 From ca8e99b32e3863c98ac958617cc157a00bf445b8 Mon Sep 17 00:00:00 2001 From: Philip Rakity Date: Wed, 6 Jul 2011 08:51:32 -0700 Subject: mmc: core: Set non-default Drive Strength via platform hook Non default Drive Strength cannot be set automatically. It is a function of the board design and only if there is a specific platform handler can it be set. The platform handler needs to take into account the board design. Pass to the platform code the necessary information. For example: The card and host controller may indicate they support HIGH and LOW drive strength. There is no way to know what should be chosen without specific board knowledge. Setting HIGH may lead to reflections and setting LOW may not suffice. There is no mechanism (like ethernet duplex or speed pulses) to determine what should be done automatically. If no platform handler is defined -- use the default value. Signed-off-by: Philip Rakity Reviewed-by: Arindam Nath Signed-off-by: Chris Ball --- include/linux/mmc/host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 9f9a4c64cde7..0f83858147a6 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -148,6 +148,7 @@ struct mmc_host_ops { int (*start_signal_voltage_switch)(struct mmc_host *host, struct mmc_ios *ios); int (*execute_tuning)(struct mmc_host *host); void (*enable_preset_value)(struct mmc_host *host, bool enable); + int (*select_drive_strength)(unsigned int max_dtr, int host_drv, int card_drv); }; struct mmc_card; -- cgit v1.2.3 From 8fb47a4fbf858a164e973b8ea8ef5e83e61f2e50 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Wed, 20 Jul 2011 20:21:59 -0400 Subject: locks: rename lock-manager ops Both the filesystem and the lock manager can associate operations with a lock. Confusingly, one of them (fl_release_private) actually has the same name in both operation structures. It would save some confusion to give the lock-manager ops different names. Signed-off-by: J. Bruce Fields --- include/linux/fs.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index b5b979247863..cf719beb2016 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1069,12 +1069,12 @@ struct file_lock_operations { }; struct lock_manager_operations { - int (*fl_compare_owner)(struct file_lock *, struct file_lock *); - void (*fl_notify)(struct file_lock *); /* unblock callback */ - int (*fl_grant)(struct file_lock *, struct file_lock *, int); - void (*fl_release_private)(struct file_lock *); - void (*fl_break)(struct file_lock *); - int (*fl_change)(struct file_lock **, int); + int (*lm_compare_owner)(struct file_lock *, struct file_lock *); + void (*lm_notify)(struct file_lock *); /* unblock callback */ + int (*lm_grant)(struct file_lock *, struct file_lock *, int); + void (*lm_release_private)(struct file_lock *); + void (*lm_break)(struct file_lock *); + int (*lm_change)(struct file_lock **, int); }; struct lock_manager { -- cgit v1.2.3 From b0d40c92adafde7c2d81203ce7c1c69275f41140 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Fri, 8 Jul 2011 14:14:42 +1000 Subject: superblock: introduce per-sb cache shrinker infrastructure With context based shrinkers, we can implement a per-superblock shrinker that shrinks the caches attached to the superblock. We currently have global shrinkers for the inode and dentry caches that split up into per-superblock operations via a coarse proportioning method that does not batch very well. The global shrinkers also have a dependency - dentries pin inodes - so we have to be very careful about how we register the global shrinkers so that the implicit call order is always correct. With a per-sb shrinker callout, we can encode this dependency directly into the per-sb shrinker, hence avoiding the need for strictly ordering shrinker registrations. We also have no need for any proportioning code for the shrinker subsystem already provides this functionality across all shrinkers. Allowing the shrinker to operate on a single superblock at a time means that we do less superblock list traversals and locking and reclaim should batch more effectively. This should result in less CPU overhead for reclaim and potentially faster reclaim of items from each filesystem. Signed-off-by: Dave Chinner Signed-off-by: Al Viro --- include/linux/fs.h | 7 +++++++ include/linux/mm.h | 40 +--------------------------------------- include/linux/shrinker.h | 42 ++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 50 insertions(+), 39 deletions(-) create mode 100644 include/linux/shrinker.h (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 460d2cc21ec6..d7f35e90b84a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -393,6 +393,7 @@ struct inodes_stat_t { #include #include #include +#include #include #include @@ -1444,8 +1445,14 @@ struct super_block { * Saved pool identifier for cleancache (-1 means none) */ int cleancache_poolid; + + struct shrinker s_shrink; /* per-sb shrinker handle */ }; +/* superblock cache pruning functions */ +extern void prune_icache_sb(struct super_block *sb, int nr_to_scan); +extern void prune_dcache_sb(struct super_block *sb, int nr_to_scan); + extern struct timespec current_fs_time(struct super_block *sb); /* diff --git a/include/linux/mm.h b/include/linux/mm.h index 9b9777ac726d..e3a1a9eec0b1 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -15,6 +15,7 @@ #include #include #include +#include struct mempolicy; struct anon_vma; @@ -1121,45 +1122,6 @@ static inline void sync_mm_rss(struct task_struct *task, struct mm_struct *mm) } #endif -/* - * This struct is used to pass information from page reclaim to the shrinkers. - * We consolidate the values for easier extention later. - */ -struct shrink_control { - gfp_t gfp_mask; - - /* How many slab objects shrinker() should scan and try to reclaim */ - unsigned long nr_to_scan; -}; - -/* - * A callback you can register to apply pressure to ageable caches. - * - * 'sc' is passed shrink_control which includes a count 'nr_to_scan' - * and a 'gfpmask'. It should look through the least-recently-used - * 'nr_to_scan' entries and attempt to free them up. It should return - * the number of objects which remain in the cache. If it returns -1, it means - * it cannot do any scanning at this time (eg. there is a risk of deadlock). - * - * The 'gfpmask' refers to the allocation we are currently trying to - * fulfil. - * - * Note that 'shrink' will be passed nr_to_scan == 0 when the VM is - * querying the cache size, so a fastpath for that case is appropriate. - */ -struct shrinker { - int (*shrink)(struct shrinker *, struct shrink_control *sc); - int seeks; /* seeks to recreate an obj */ - long batch; /* reclaim batch size, 0 = default */ - - /* These are for internal use */ - struct list_head list; - long nr; /* objs pending delete */ -}; -#define DEFAULT_SEEKS 2 /* A good number if you don't know better. */ -extern void register_shrinker(struct shrinker *); -extern void unregister_shrinker(struct shrinker *); - int vma_wants_writenotify(struct vm_area_struct *vma); extern pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h new file mode 100644 index 000000000000..790651b4e5ba --- /dev/null +++ b/include/linux/shrinker.h @@ -0,0 +1,42 @@ +#ifndef _LINUX_SHRINKER_H +#define _LINUX_SHRINKER_H + +/* + * This struct is used to pass information from page reclaim to the shrinkers. + * We consolidate the values for easier extention later. + */ +struct shrink_control { + gfp_t gfp_mask; + + /* How many slab objects shrinker() should scan and try to reclaim */ + unsigned long nr_to_scan; +}; + +/* + * A callback you can register to apply pressure to ageable caches. + * + * 'sc' is passed shrink_control which includes a count 'nr_to_scan' + * and a 'gfpmask'. It should look through the least-recently-used + * 'nr_to_scan' entries and attempt to free them up. It should return + * the number of objects which remain in the cache. If it returns -1, it means + * it cannot do any scanning at this time (eg. there is a risk of deadlock). + * + * The 'gfpmask' refers to the allocation we are currently trying to + * fulfil. + * + * Note that 'shrink' will be passed nr_to_scan == 0 when the VM is + * querying the cache size, so a fastpath for that case is appropriate. + */ +struct shrinker { + int (*shrink)(struct shrinker *, struct shrink_control *sc); + int seeks; /* seeks to recreate an obj */ + long batch; /* reclaim batch size, 0 = default */ + + /* These are for internal use */ + struct list_head list; + long nr; /* objs pending delete */ +}; +#define DEFAULT_SEEKS 2 /* A good number if you don't know better. */ +extern void register_shrinker(struct shrinker *); +extern void unregister_shrinker(struct shrinker *); +#endif -- cgit v1.2.3 From 0e1fdafd93980eac62e778798549ce0f6073905c Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Fri, 8 Jul 2011 14:14:44 +1000 Subject: superblock: add filesystem shrinker operations Now we have a per-superblock shrinker implementation, we can add a filesystem specific callout to it to allow filesystem internal caches to be shrunk by the superblock shrinker. Rather than perpetuate the multipurpose shrinker callback API (i.e. nr_to_scan == 0 meaning "tell me how many objects freeable in the cache), two operations will be added. The first will return the number of objects that are freeable, the second is the actual shrinker call. Signed-off-by: Dave Chinner Signed-off-by: Al Viro --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index d7f35e90b84a..1393742bba9b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1655,6 +1655,8 @@ struct super_operations { ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); #endif int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t); + int (*nr_cached_objects)(struct super_block *); + void (*free_cached_objects)(struct super_block *, int); }; /* -- cgit v1.2.3 From e46ebd27823b27273da780376d54c080250ff1a2 Mon Sep 17 00:00:00 2001 From: Tomasz Stanislawski Date: Tue, 12 Jul 2011 11:27:20 +0200 Subject: anonfd: fix missing declaration The forward declaration of struct file_operations is added to avoid compilation warnings. Signed-off-by: Tomasz Stanislawski Signed-off-by: Al Viro --- include/linux/anon_inodes.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/anon_inodes.h b/include/linux/anon_inodes.h index 69a21e0ebd33..8013a45242fe 100644 --- a/include/linux/anon_inodes.h +++ b/include/linux/anon_inodes.h @@ -8,6 +8,8 @@ #ifndef _LINUX_ANON_INODES_H #define _LINUX_ANON_INODES_H +struct file_operations; + struct file *anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags); -- cgit v1.2.3 From bd5fe6c5eb9c548d7f07fe8f89a150bb6705e8e3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 24 Jun 2011 14:29:43 -0400 Subject: fs: kill i_alloc_sem i_alloc_sem is a rather special rw_semaphore. It's the last one that may be released by a non-owner, and it's write side is always mirrored by real exclusion. It's intended use it to wait for all pending direct I/O requests to finish before starting a truncate. Replace it with a hand-grown construct: - exclusion for truncates is already guaranteed by i_mutex, so it can simply fall way - the reader side is replaced by an i_dio_count member in struct inode that counts the number of pending direct I/O requests. Truncate can't proceed as long as it's non-zero - when i_dio_count reaches non-zero we wake up a pending truncate using wake_up_bit on a new bit in i_flags - new references to i_dio_count can't appear while we are waiting for it to read zero because the direct I/O count always needs i_mutex (or an equivalent like XFS's i_iolock) for starting a new operation. This scheme is much simpler, and saves the space of a spinlock_t and a struct list_head in struct inode (typically 160 bits on a non-debug 64-bit system). Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 1393742bba9b..2fe920774abf 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -779,7 +779,7 @@ struct inode { struct timespec i_ctime; blkcnt_t i_blocks; unsigned short i_bytes; - struct rw_semaphore i_alloc_sem; + atomic_t i_dio_count; const struct file_operations *i_fop; /* former ->i_op->default_file_ops */ struct file_lock *i_flock; struct address_space *i_mapping; @@ -1705,6 +1705,10 @@ struct super_operations { * set during data writeback, and cleared with a wakeup * on the bit address once it is done. * + * I_REFERENCED Marks the inode as recently references on the LRU list. + * + * I_DIO_WAKEUP Never set. Only used as a key for wait_on_bit(). + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -1718,6 +1722,8 @@ struct super_operations { #define __I_SYNC 7 #define I_SYNC (1 << __I_SYNC) #define I_REFERENCED (1 << 8) +#define __I_DIO_WAKEUP 9 +#define I_DIO_WAKEUP (1 << I_DIO_WAKEUP) #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES) @@ -1828,7 +1834,6 @@ struct file_system_type { struct lock_class_key i_lock_key; struct lock_class_key i_mutex_key; struct lock_class_key i_mutex_dir_key; - struct lock_class_key i_alloc_sem_key; }; extern struct dentry *mount_ns(struct file_system_type *fs_type, int flags, @@ -2404,6 +2409,8 @@ enum { }; void dio_end_io(struct bio *bio, int error); +void inode_dio_wait(struct inode *inode); +void inode_dio_done(struct inode *inode); ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, struct block_device *bdev, const struct iovec *iov, loff_t offset, -- cgit v1.2.3 From 11b80f459adaf91a712f95e7734a17655a36bf30 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 24 Jun 2011 14:29:44 -0400 Subject: rw_semaphore: remove up/down_read_non_owner Now that the last users is gone these can be removed. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/rwsem.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index a8afe9cd000c..77950dfa0a9e 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -124,19 +124,9 @@ extern void downgrade_write(struct rw_semaphore *sem); */ extern void down_read_nested(struct rw_semaphore *sem, int subclass); extern void down_write_nested(struct rw_semaphore *sem, int subclass); -/* - * Take/release a lock when not the owner will release it. - * - * [ This API should be avoided as much as possible - the - * proper abstraction for this case is completions. ] - */ -extern void down_read_non_owner(struct rw_semaphore *sem); -extern void up_read_non_owner(struct rw_semaphore *sem); #else # define down_read_nested(sem, subclass) down_read(sem) # define down_write_nested(sem, subclass) down_write(sem) -# define down_read_non_owner(sem) down_read(sem) -# define up_read_non_owner(sem) up_read(sem) #endif #endif /* _LINUX_RWSEM_H */ -- cgit v1.2.3 From aacfc19c626ebd3daa675652457d71019a1f583f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 24 Jun 2011 14:29:47 -0400 Subject: fs: simplify the blockdev_direct_IO prototype Simple filesystems always pass inode->i_sb_bdev as the block device argument, and never need a end_io handler. Let's simply things for them and for my grepping activity by dropping these arguments. The only thing not falling into that scheme is ext4, which passes and end_io handler without needing special flags (yet), but given how messy the direct I/O code there is use of __blockdev_direct_IO in one instead of two out of three cases isn't going to make a large difference anyway. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 2fe920774abf..824453be9fee 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2418,12 +2418,11 @@ ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, dio_submit_t submit_io, int flags); static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb, - struct inode *inode, struct block_device *bdev, const struct iovec *iov, - loff_t offset, unsigned long nr_segs, get_block_t get_block, - dio_iodone_t end_io) + struct inode *inode, const struct iovec *iov, loff_t offset, + unsigned long nr_segs, get_block_t get_block) { - return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset, - nr_segs, get_block, end_io, NULL, + return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov, + offset, nr_segs, get_block, NULL, NULL, DIO_LOCKING | DIO_SKIP_HOLES); } #endif -- cgit v1.2.3 From f15146380d28b746df3c8b81b392812eb982382a Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Tue, 12 Jul 2011 20:48:39 +0200 Subject: fs: seq_file - add event counter to simplify poll() support Moving the event counter into the dynamically allocated 'struc seq_file' allows poll() support without the need to allocate its own tracking structure. All current users are switched over to use the new counter. Requested-by: Andrew Morton akpm@linux-foundation.org Acked-by: NeilBrown Tested-by: Lucas De Marchi lucas.demarchi@profusion.mobi Signed-off-by: Kay Sievers Signed-off-by: Al Viro --- include/linux/mnt_namespace.h | 1 - include/linux/seq_file.h | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h index 0b89efc6f215..29304855652d 100644 --- a/include/linux/mnt_namespace.h +++ b/include/linux/mnt_namespace.h @@ -18,7 +18,6 @@ struct proc_mounts { struct seq_file m; /* must be the first element */ struct mnt_namespace *ns; struct path root; - int event; }; struct fs_struct; diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 03c0232b4169..be720cd2038d 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -23,6 +23,7 @@ struct seq_file { u64 version; struct mutex lock; const struct seq_operations *op; + int poll_event; void *private; }; -- cgit v1.2.3 From 982d816581eeeacfe5b2b7c6d47d13a157616eff Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 18 Jul 2011 13:21:35 -0400 Subject: fs: add SEEK_HOLE and SEEK_DATA flags This just gets us ready to support the SEEK_HOLE and SEEK_DATA flags. Turns out using fiemap in things like cp cause more problems than it solves, so lets try and give userspace an interface that doesn't suck. We need to match solaris here, and the definitions are *o* If /whence/ is SEEK_HOLE, the offset of the start of the next hole greater than or equal to the supplied offset is returned. The definition of a hole is provided near the end of the DESCRIPTION. *o* If /whence/ is SEEK_DATA, the file pointer is set to the start of the next non-hole file region greater than or equal to the supplied offset. So in the generic case the entire file is data and there is a virtual hole at the end. That means we will just return i_size for SEEK_HOLE and will return the same offset for SEEK_DATA. This is how Solaris does it so we have to do it the same way. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Al Viro --- include/linux/fs.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 824453be9fee..4a61f98823a6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -32,7 +32,9 @@ #define SEEK_SET 0 /* seek relative to beginning of file */ #define SEEK_CUR 1 /* seek relative to current file position */ #define SEEK_END 2 /* seek relative to end of file */ -#define SEEK_MAX SEEK_END +#define SEEK_DATA 3 /* seek to the next data */ +#define SEEK_HOLE 4 /* seek to the next hole */ +#define SEEK_MAX SEEK_HOLE struct fstrim_range { __u64 start; -- cgit v1.2.3 From 02c24a82187d5a628c68edfe71ae60dc135cd178 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Sat, 16 Jul 2011 20:44:56 -0400 Subject: fs: push i_mutex and filemap_write_and_wait down into ->fsync() handlers Btrfs needs to be able to control how filemap_write_and_wait_range() is called in fsync to make it less of a painful operation, so push down taking i_mutex and the calling of filemap_write_and_wait() down into the ->fsync() handlers. Some file systems can drop taking the i_mutex altogether it seems, like ext3 and ocfs2. For correctness sake I just pushed everything down in all cases to make sure that we keep the current behavior the same for everybody, and then each individual fs maintainer can make up their mind about what to do from there. Thanks, Acked-by: Jan Kara Signed-off-by: Josef Bacik Signed-off-by: Al Viro --- include/linux/ext3_fs.h | 2 +- include/linux/fb.h | 3 ++- include/linux/fs.h | 9 +++++---- 3 files changed, 8 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index 5e06acf95d0f..0c473fd79acb 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -877,7 +877,7 @@ extern int ext3_htree_store_dirent(struct file *dir_file, __u32 hash, extern void ext3_htree_free_dir_info(struct dir_private_info *p); /* fsync.c */ -extern int ext3_sync_file(struct file *, int); +extern int ext3_sync_file(struct file *, loff_t, loff_t, int); /* hash.c */ extern int ext3fs_dirhash(const char *name, int len, struct diff --git a/include/linux/fb.h b/include/linux/fb.h index 6a8274877171..1d6836c498dd 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -1043,7 +1043,8 @@ extern void fb_deferred_io_open(struct fb_info *info, struct inode *inode, struct file *file); extern void fb_deferred_io_cleanup(struct fb_info *info); -extern int fb_deferred_io_fsync(struct file *file, int datasync); +extern int fb_deferred_io_fsync(struct file *file, loff_t start, + loff_t end, int datasync); static inline bool fb_be_math(struct fb_info *info) { diff --git a/include/linux/fs.h b/include/linux/fs.h index 4a61f98823a6..9cd2075c4a39 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1572,7 +1572,7 @@ struct file_operations { int (*open) (struct inode *, struct file *); int (*flush) (struct file *, fl_owner_t id); int (*release) (struct inode *, struct file *); - int (*fsync) (struct file *, int datasync); + int (*fsync) (struct file *, loff_t, loff_t, int datasync); int (*aio_fsync) (struct kiocb *, int datasync); int (*fasync) (int, struct file *, int); int (*lock) (struct file *, int, struct file_lock *); @@ -2360,7 +2360,8 @@ extern int generic_segment_checks(const struct iovec *iov, /* fs/block_dev.c */ extern ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos); -extern int blkdev_fsync(struct file *filp, int datasync); +extern int blkdev_fsync(struct file *filp, loff_t start, loff_t end, + int datasync); /* fs/splice.c */ extern ssize_t generic_file_splice_read(struct file *, loff_t *, @@ -2490,7 +2491,7 @@ extern int simple_link(struct dentry *, struct inode *, struct dentry *); extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); extern int simple_rename(struct inode *, struct dentry *, struct inode *, struct dentry *); -extern int noop_fsync(struct file *, int); +extern int noop_fsync(struct file *, loff_t, loff_t, int); extern int simple_empty(struct dentry *); extern int simple_readpage(struct file *file, struct page *page); extern int simple_write_begin(struct file *file, struct address_space *mapping, @@ -2515,7 +2516,7 @@ extern ssize_t simple_read_from_buffer(void __user *to, size_t count, extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos, const void __user *from, size_t count); -extern int generic_file_fsync(struct file *, int); +extern int generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_check_addressable(unsigned, u64); -- cgit v1.2.3 From 295cc522c2b2834b302424e41ebb5846df6d61bd Mon Sep 17 00:00:00 2001 From: Wanlong Gao Date: Tue, 19 Jul 2011 09:48:39 +0800 Subject: fs:update the NOTE of the file_operations structure Big kernel lock had been removed and setlease now use the lock_flocks() to hold a special spin lock file_lock_lock by Matthew. So just remove the out-of-date NOTE. Signed-off-by: Wanlong Gao Signed-off-by: Al Viro --- include/linux/fs.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 9cd2075c4a39..e0569e4ab2d5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1552,11 +1552,6 @@ struct block_device_operations; #define HAVE_COMPAT_IOCTL 1 #define HAVE_UNLOCKED_IOCTL 1 -/* - * NOTE: - * all file operations except setlease can be called without - * the big kernel lock held in all filesystems. - */ struct file_operations { struct module *owner; loff_t (*llseek) (struct file *, loff_t, int); -- cgit v1.2.3 From 4582c0a4866ea70c35aa9279e1f91834d3348a93 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Sat, 16 Jul 2011 17:42:00 +0200 Subject: mutex: Make mutex_destroy() an inline function The non-debug variant of mutex_destroy is a no-op, currently implemented as a macro which does nothing. This approach fails to check the type of the parameter, so an error would only show when debugging gets enabled. Using an inline function instead, offers type checking for earlier bug catching. Signed-off-by: Jean Delvare Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20110716174200.41002352@endymion.delvare Signed-off-by: Ingo Molnar --- include/linux/mutex.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mutex.h b/include/linux/mutex.h index a940fe435aca..7f87217e9d1f 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -92,7 +92,7 @@ do { \ \ __mutex_init((mutex), #mutex, &__key); \ } while (0) -# define mutex_destroy(mutex) do { } while (0) +static inline void mutex_destroy(struct mutex *lock) {} #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC -- cgit v1.2.3 From a6a7b759ba62e62542308e091f7fc9cfac4f978e Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Thu, 21 Jul 2011 12:05:31 +0200 Subject: netfilter: ipset: make possible to hash some part of the data element only Signed-off-by: Jozsef Kadlecsik Signed-off-by: Patrick McHardy --- include/linux/netfilter/ipset/ip_set_ahash.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h index c5b06aaa205c..42b7d25a1b2e 100644 --- a/include/linux/netfilter/ipset/ip_set_ahash.h +++ b/include/linux/netfilter/ipset/ip_set_ahash.h @@ -211,12 +211,16 @@ ip_set_hash_destroy(struct ip_set *set) set->data = NULL; } -#define HKEY(data, initval, htable_bits) \ -(jhash2((u32 *)(data), sizeof(struct type_pf_elem)/sizeof(u32), initval) \ - & jhash_mask(htable_bits)) - #endif /* _IP_SET_AHASH_H */ +#ifndef HKEY_DATALEN +#define HKEY_DATALEN sizeof(struct type_pf_elem) +#endif + +#define HKEY(data, initval, htable_bits) \ +(jhash2((u32 *)(data), HKEY_DATALEN/sizeof(u32), initval) \ + & jhash_mask(htable_bits)) + #define CONCAT(a, b, c) a##b##c #define TOKEN(a, b, c) CONCAT(a, b, c) @@ -1054,6 +1058,8 @@ type_pf_gc_init(struct ip_set *set) IPSET_GC_PERIOD(h->timeout)); } +#undef HKEY_DATALEN +#undef HKEY #undef type_pf_data_equal #undef type_pf_data_isnull #undef type_pf_data_copy -- cgit v1.2.3 From 89dc79b787d20e4b6c4077dcee1c5b1be4ab55b8 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Thu, 21 Jul 2011 12:06:18 +0200 Subject: netfilter: ipset: hash:net,iface fixed to handle overlapping nets behind different interfaces If overlapping networks with different interfaces was added to the set, the type did not handle it properly. Example ipset create test hash:net,iface ipset add test 192.168.0.0/16,eth0 ipset add test 192.168.0.0/24,eth1 Now, if a packet was sent from 192.168.0.0/24,eth0, the type returned a match. In the patch the algorithm is fixed in order to correctly handle overlapping networks. Limitation: the same network cannot be stored with more than 64 different interfaces in a single set. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Patrick McHardy --- include/linux/netfilter/ipset/ip_set_ahash.h | 92 ++++++++++++++++++---------- 1 file changed, 61 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h index 42b7d25a1b2e..1e7f7594cd02 100644 --- a/include/linux/netfilter/ipset/ip_set_ahash.h +++ b/include/linux/netfilter/ipset/ip_set_ahash.h @@ -28,7 +28,32 @@ /* Number of elements to store in an initial array block */ #define AHASH_INIT_SIZE 4 /* Max number of elements to store in an array block */ -#define AHASH_MAX_SIZE (3*4) +#define AHASH_MAX_SIZE (3*AHASH_INIT_SIZE) + +/* Max number of elements can be tuned */ +#ifdef IP_SET_HASH_WITH_MULTI +#define AHASH_MAX(h) ((h)->ahash_max) + +static inline u8 +tune_ahash_max(u8 curr, u32 multi) +{ + u32 n; + + if (multi < curr) + return curr; + + n = curr + AHASH_INIT_SIZE; + /* Currently, at listing one hash bucket must fit into a message. + * Therefore we have a hard limit here. + */ + return n > curr && n <= 64 ? n : curr; +} +#define TUNE_AHASH_MAX(h, multi) \ + ((h)->ahash_max = tune_ahash_max((h)->ahash_max, multi)) +#else +#define AHASH_MAX(h) AHASH_MAX_SIZE +#define TUNE_AHASH_MAX(h, multi) +#endif /* A hash bucket */ struct hbucket { @@ -60,6 +85,9 @@ struct ip_set_hash { u32 timeout; /* timeout value, if enabled */ struct timer_list gc; /* garbage collection when timeout enabled */ struct type_pf_next next; /* temporary storage for uadd */ +#ifdef IP_SET_HASH_WITH_MULTI + u8 ahash_max; /* max elements in an array block */ +#endif #ifdef IP_SET_HASH_WITH_NETMASK u8 netmask; /* netmask value for subnets to store */ #endif @@ -279,12 +307,13 @@ ip_set_hash_destroy(struct ip_set *set) /* Add an element to the hash table when resizing the set: * we spare the maintenance of the internal counters. */ static int -type_pf_elem_add(struct hbucket *n, const struct type_pf_elem *value) +type_pf_elem_add(struct hbucket *n, const struct type_pf_elem *value, + u8 ahash_max) { if (n->pos >= n->size) { void *tmp; - if (n->size >= AHASH_MAX_SIZE) + if (n->size >= ahash_max) /* Trigger rehashing */ return -EAGAIN; @@ -339,7 +368,7 @@ retry: for (j = 0; j < n->pos; j++) { data = ahash_data(n, j); m = hbucket(t, HKEY(data, h->initval, htable_bits)); - ret = type_pf_elem_add(m, data); + ret = type_pf_elem_add(m, data, AHASH_MAX(h)); if (ret < 0) { read_unlock_bh(&set->lock); ahash_destroy(t); @@ -376,7 +405,7 @@ type_pf_add(struct ip_set *set, void *value, u32 timeout, u32 flags) const struct type_pf_elem *d = value; struct hbucket *n; int i, ret = 0; - u32 key; + u32 key, multi = 0; if (h->elements >= h->maxelem) return -IPSET_ERR_HASH_FULL; @@ -386,12 +415,12 @@ type_pf_add(struct ip_set *set, void *value, u32 timeout, u32 flags) key = HKEY(value, h->initval, t->htable_bits); n = hbucket(t, key); for (i = 0; i < n->pos; i++) - if (type_pf_data_equal(ahash_data(n, i), d)) { + if (type_pf_data_equal(ahash_data(n, i), d, &multi)) { ret = -IPSET_ERR_EXIST; goto out; } - - ret = type_pf_elem_add(n, value); + TUNE_AHASH_MAX(h, multi); + ret = type_pf_elem_add(n, value, AHASH_MAX(h)); if (ret != 0) { if (ret == -EAGAIN) type_pf_data_next(h, d); @@ -419,13 +448,13 @@ type_pf_del(struct ip_set *set, void *value, u32 timeout, u32 flags) struct hbucket *n; int i; struct type_pf_elem *data; - u32 key; + u32 key, multi = 0; key = HKEY(value, h->initval, t->htable_bits); n = hbucket(t, key); for (i = 0; i < n->pos; i++) { data = ahash_data(n, i); - if (!type_pf_data_equal(data, d)) + if (!type_pf_data_equal(data, d, &multi)) continue; if (i != n->pos - 1) /* Not last one */ @@ -466,17 +495,17 @@ type_pf_test_cidrs(struct ip_set *set, struct type_pf_elem *d, u32 timeout) struct hbucket *n; const struct type_pf_elem *data; int i, j = 0; - u32 key; + u32 key, multi = 0; u8 host_mask = SET_HOST_MASK(set->family); pr_debug("test by nets\n"); - for (; j < host_mask && h->nets[j].cidr; j++) { + for (; j < host_mask && h->nets[j].cidr && !multi; j++) { type_pf_data_netmask(d, h->nets[j].cidr); key = HKEY(d, h->initval, t->htable_bits); n = hbucket(t, key); for (i = 0; i < n->pos; i++) { data = ahash_data(n, i); - if (type_pf_data_equal(data, d)) + if (type_pf_data_equal(data, d, &multi)) return 1; } } @@ -494,7 +523,7 @@ type_pf_test(struct ip_set *set, void *value, u32 timeout, u32 flags) struct hbucket *n; const struct type_pf_elem *data; int i; - u32 key; + u32 key, multi = 0; #ifdef IP_SET_HASH_WITH_NETS /* If we test an IP address and not a network address, @@ -507,7 +536,7 @@ type_pf_test(struct ip_set *set, void *value, u32 timeout, u32 flags) n = hbucket(t, key); for (i = 0; i < n->pos; i++) { data = ahash_data(n, i); - if (type_pf_data_equal(data, d)) + if (type_pf_data_equal(data, d, &multi)) return 1; } return 0; @@ -664,14 +693,14 @@ type_pf_data_timeout_set(struct type_pf_elem *data, u32 timeout) static int type_pf_elem_tadd(struct hbucket *n, const struct type_pf_elem *value, - u32 timeout) + u8 ahash_max, u32 timeout) { struct type_pf_elem *data; if (n->pos >= n->size) { void *tmp; - if (n->size >= AHASH_MAX_SIZE) + if (n->size >= ahash_max) /* Trigger rehashing */ return -EAGAIN; @@ -776,7 +805,7 @@ retry: for (j = 0; j < n->pos; j++) { data = ahash_tdata(n, j); m = hbucket(t, HKEY(data, h->initval, htable_bits)); - ret = type_pf_elem_tadd(m, data, + ret = type_pf_elem_tadd(m, data, AHASH_MAX(h), type_pf_data_timeout(data)); if (ret < 0) { read_unlock_bh(&set->lock); @@ -807,9 +836,9 @@ type_pf_tadd(struct ip_set *set, void *value, u32 timeout, u32 flags) const struct type_pf_elem *d = value; struct hbucket *n; struct type_pf_elem *data; - int ret = 0, i, j = AHASH_MAX_SIZE + 1; + int ret = 0, i, j = AHASH_MAX(h) + 1; bool flag_exist = flags & IPSET_FLAG_EXIST; - u32 key; + u32 key, multi = 0; if (h->elements >= h->maxelem) /* FIXME: when set is full, we slow down here */ @@ -823,18 +852,18 @@ type_pf_tadd(struct ip_set *set, void *value, u32 timeout, u32 flags) n = hbucket(t, key); for (i = 0; i < n->pos; i++) { data = ahash_tdata(n, i); - if (type_pf_data_equal(data, d)) { + if (type_pf_data_equal(data, d, &multi)) { if (type_pf_data_expired(data) || flag_exist) j = i; else { ret = -IPSET_ERR_EXIST; goto out; } - } else if (j == AHASH_MAX_SIZE + 1 && + } else if (j == AHASH_MAX(h) + 1 && type_pf_data_expired(data)) j = i; } - if (j != AHASH_MAX_SIZE + 1) { + if (j != AHASH_MAX(h) + 1) { data = ahash_tdata(n, j); #ifdef IP_SET_HASH_WITH_NETS del_cidr(h, data->cidr, HOST_MASK); @@ -844,7 +873,8 @@ type_pf_tadd(struct ip_set *set, void *value, u32 timeout, u32 flags) type_pf_data_timeout_set(data, timeout); goto out; } - ret = type_pf_elem_tadd(n, d, timeout); + TUNE_AHASH_MAX(h, multi); + ret = type_pf_elem_tadd(n, d, AHASH_MAX(h), timeout); if (ret != 0) { if (ret == -EAGAIN) type_pf_data_next(h, d); @@ -869,13 +899,13 @@ type_pf_tdel(struct ip_set *set, void *value, u32 timeout, u32 flags) struct hbucket *n; int i; struct type_pf_elem *data; - u32 key; + u32 key, multi = 0; key = HKEY(value, h->initval, t->htable_bits); n = hbucket(t, key); for (i = 0; i < n->pos; i++) { data = ahash_tdata(n, i); - if (!type_pf_data_equal(data, d)) + if (!type_pf_data_equal(data, d, &multi)) continue; if (type_pf_data_expired(data)) return -IPSET_ERR_EXIST; @@ -915,16 +945,16 @@ type_pf_ttest_cidrs(struct ip_set *set, struct type_pf_elem *d, u32 timeout) struct type_pf_elem *data; struct hbucket *n; int i, j = 0; - u32 key; + u32 key, multi = 0; u8 host_mask = SET_HOST_MASK(set->family); - for (; j < host_mask && h->nets[j].cidr; j++) { + for (; j < host_mask && h->nets[j].cidr && !multi; j++) { type_pf_data_netmask(d, h->nets[j].cidr); key = HKEY(d, h->initval, t->htable_bits); n = hbucket(t, key); for (i = 0; i < n->pos; i++) { data = ahash_tdata(n, i); - if (type_pf_data_equal(data, d)) + if (type_pf_data_equal(data, d, &multi)) return !type_pf_data_expired(data); } } @@ -940,7 +970,7 @@ type_pf_ttest(struct ip_set *set, void *value, u32 timeout, u32 flags) struct type_pf_elem *data, *d = value; struct hbucket *n; int i; - u32 key; + u32 key, multi = 0; #ifdef IP_SET_HASH_WITH_NETS if (d->cidr == SET_HOST_MASK(set->family)) @@ -950,7 +980,7 @@ type_pf_ttest(struct ip_set *set, void *value, u32 timeout, u32 flags) n = hbucket(t, key); for (i = 0; i < n->pos; i++) { data = ahash_tdata(n, i); - if (type_pf_data_equal(data, d)) + if (type_pf_data_equal(data, d, &multi)) return !type_pf_data_expired(data); } return 0; -- cgit v1.2.3 From 0f598f0b4c3b2259366cfa8adc01bd8e714c82d0 Mon Sep 17 00:00:00 2001 From: Chris Friesen Date: Thu, 21 Jul 2011 12:07:10 +0200 Subject: netfilter: ipset: fix compiler warnings "'hash_ip4_data_next' declared inline after being called" Some gcc versions warn about prototypes without "inline" when the declaration includes the "inline" keyword. The fix generates a false error message "marked inline, but without a definition" with sparse below 0.4.2. Signed-off-by: Chris Friesen Signed-off-by: Jozsef Kadlecsik Signed-off-by: Patrick McHardy --- include/linux/netfilter/ipset/ip_set_ahash.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h index 1e7f7594cd02..b89fb79cb44f 100644 --- a/include/linux/netfilter/ipset/ip_set_ahash.h +++ b/include/linux/netfilter/ipset/ip_set_ahash.h @@ -392,7 +392,7 @@ retry: return 0; } -static void +static inline void type_pf_data_next(struct ip_set_hash *h, const struct type_pf_elem *d); /* Add an element to a hash and update the internal counters when succeeded, -- cgit v1.2.3 From 497888cf69bf607ac1fe061a6437e0a670b0022f Mon Sep 17 00:00:00 2001 From: Phil Carmody Date: Thu, 14 Jul 2011 15:07:13 +0300 Subject: treewide: fix potentially dangerous trailing ';' in #defined values/expressions All these are instances of #define NAME value; or #define NAME(params_opt) value; These of course fail to build when used in contexts like if(foo $OP NAME) while(bar $OP NAME) and may silently generate the wrong code in contexts such as foo = NAME + 1; /* foo = value; + 1; */ bar = NAME - 1; /* bar = value; - 1; */ baz = NAME & quux; /* baz = value; & quux; */ Reported on comp.lang.c, Message-ID: Initial analysis of the dangers provided by Keith Thompson in that thread. There are many more instances of more complicated macros having unnecessary trailing semicolons, but this pile seems to be all of the cases of simple values suffering from the problem. (Thus things that are likely to be found in one of the contexts above, more complicated ones aren't.) Signed-off-by: Phil Carmody Signed-off-by: Jiri Kosina --- include/linux/ceph/libceph.h | 2 +- include/linux/mfd/tps65910.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 6365f041745b..563755181c1e 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -35,7 +35,7 @@ #define CEPH_OPT_MYIP (1<<2) /* specified my ip */ #define CEPH_OPT_NOCRC (1<<3) /* no data crc on writes */ -#define CEPH_OPT_DEFAULT (0); +#define CEPH_OPT_DEFAULT (0) #define ceph_set_opt(client, opt) \ (client)->options->flags |= CEPH_OPT_##opt; diff --git a/include/linux/mfd/tps65910.h b/include/linux/mfd/tps65910.h index 8bb85b930c07..73572c65d04f 100644 --- a/include/linux/mfd/tps65910.h +++ b/include/linux/mfd/tps65910.h @@ -269,7 +269,7 @@ #define LDO1_SEL_MASK 0xFC #define LDO3_SEL_MASK 0x7C #define LDO_MIN_VOLT 1000 -#define LDO_MAX_VOLT 3300; +#define LDO_MAX_VOLT 3300 /*Register VDIG1 (0x80) register.RegisterDescription */ -- cgit v1.2.3 From ae7bd11b471931752e5609094ca0a49386590524 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Thu, 21 Jul 2011 13:34:05 -0700 Subject: clocksource: Change __ARCH_HAS_CLOCKSOURCE_DATA to a CONFIG option The machinery for __ARCH_HAS_CLOCKSOURCE_DATA assumed a file in asm-generic would be the default for architectures without their own file in asm/, but that is not how it works. Replace it with a Kconfig option instead. Link: http://lkml.kernel.org/r/4E288AA6.7090804@zytor.com Signed-off-by: H. Peter Anvin Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Tony Luck --- include/linux/clocksource.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 6bb69702c4fa..59ee970cf89e 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -22,7 +22,9 @@ typedef u64 cycle_t; struct clocksource; +#ifdef CONFIG_ARCH_CLOCKSOURCE_DATA #include +#endif /** * struct cyclecounter - hardware abstraction for a free running counter @@ -171,7 +173,7 @@ struct clocksource { u32 shift; u64 max_idle_ns; -#ifdef __ARCH_HAS_CLOCKSOURCE_DATA +#ifdef CONFIG_ARCH_CLOCKSOURCE_DATA struct arch_clocksource_data archdata; #endif -- cgit v1.2.3 From f605234066852b11096ab071124e3fe415e94420 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 20 Jul 2011 04:54:04 +0000 Subject: vlan: finish removing vlan_find_dev from public header else case remained forgotten. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index bc03e40fd7fd..cfb0cf2230a9 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -135,12 +135,6 @@ vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp, unsigned int vlan_tci); #else -static inline struct net_device *vlan_find_dev(struct net_device *real_dev, - u16 vlan_id) -{ - return NULL; -} - static inline struct net_device *vlan_dev_real_dev(const struct net_device *dev) { BUG(); -- cgit v1.2.3 From cec9c133631039f82e4a5ff3bf47b3eba14ff1aa Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 20 Jul 2011 04:54:05 +0000 Subject: vlan: introduce __vlan_find_dev_deep() Since vlan_group_get_device and vlan_group is not going to be accessible from device drivers, introduce function which substitutes it. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index cfb0cf2230a9..69391cc20f3d 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -120,6 +120,8 @@ static inline int is_vlan_dev(struct net_device *dev) #if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE) +extern struct net_device *__vlan_find_dev_deep(struct net_device *real_dev, + u16 vlan_id); extern struct net_device *vlan_dev_real_dev(const struct net_device *dev); extern u16 vlan_dev_vlan_id(const struct net_device *dev); @@ -135,6 +137,12 @@ vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp, unsigned int vlan_tci); #else +static inline struct net_device * +__vlan_find_dev_deep(struct net_device *real_dev, u16 vlan_id) +{ + return NULL; +} + static inline struct net_device *vlan_dev_real_dev(const struct net_device *dev) { BUG(); -- cgit v1.2.3 From 7756a96e1925addedc87db21ca6646e03b3c674f Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 20 Jul 2011 04:54:08 +0000 Subject: lro: kill lro_vlan_hwaccel_receive_skb no longer used Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/inet_lro.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/inet_lro.h b/include/linux/inet_lro.h index c4335faebb63..940bbde05a52 100644 --- a/include/linux/inet_lro.h +++ b/include/linux/inet_lro.h @@ -136,16 +136,6 @@ void lro_receive_skb(struct net_lro_mgr *lro_mgr, struct sk_buff *skb, void *priv); -/* - * Processes a SKB with VLAN HW acceleration support - */ - -void lro_vlan_hwaccel_receive_skb(struct net_lro_mgr *lro_mgr, - struct sk_buff *skb, - struct vlan_group *vgrp, - u16 vlan_tag, - void *priv); - /* * Processes a fragment list * -- cgit v1.2.3 From 0f7257281dcbc9bcb46b882c23fa57b6738fce5e Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 20 Jul 2011 04:54:09 +0000 Subject: lro: kill lro_vlan_hwaccel_receive_frags Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/inet_lro.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/inet_lro.h b/include/linux/inet_lro.h index 940bbde05a52..b27e773e7144 100644 --- a/include/linux/inet_lro.h +++ b/include/linux/inet_lro.h @@ -155,13 +155,6 @@ void lro_receive_frags(struct net_lro_mgr *lro_mgr, struct skb_frag_struct *frags, int len, int true_size, void *priv, __wsum sum); -void lro_vlan_hwaccel_receive_frags(struct net_lro_mgr *lro_mgr, - struct skb_frag_struct *frags, - int len, int true_size, - struct vlan_group *vgrp, - u16 vlan_tag, - void *priv, __wsum sum); - /* * Forward all aggregated SKBs held by lro_mgr to network stack */ -- cgit v1.2.3 From 9fea03302ada3291fb3066a3c276e3f43556548b Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 20 Jul 2011 04:54:10 +0000 Subject: lro: do vlan cleanup - remove useless vlan parameters and pointers Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/inet_lro.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/inet_lro.h b/include/linux/inet_lro.h index b27e773e7144..2cf55afbcd4e 100644 --- a/include/linux/inet_lro.h +++ b/include/linux/inet_lro.h @@ -50,7 +50,6 @@ struct net_lro_desc { struct skb_frag_struct *next_frag; struct iphdr *iph; struct tcphdr *tcph; - struct vlan_group *vgrp; __wsum data_csum; __be32 tcp_rcv_tsecr; __be32 tcp_rcv_tsval; @@ -60,7 +59,6 @@ struct net_lro_desc { u16 ip_tot_len; u16 tcp_saw_tstamp; /* timestamps enabled */ __be16 tcp_window; - u16 vlan_tag; int pkt_aggr_cnt; /* counts aggregated packets */ int vlan_packet; int mss; -- cgit v1.2.3 From 6dacaddd4850cbd6390d4f87548262b5ed79b4a5 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 20 Jul 2011 04:54:27 +0000 Subject: vlan: kill vlan_hwaccel_receive_skb Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 69391cc20f3d..3996713caaec 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -202,19 +202,6 @@ static inline int vlan_hwaccel_rx(struct sk_buff *skb, return __vlan_hwaccel_rx(skb, grp, vlan_tci, 0); } -/** - * vlan_hwaccel_receive_skb - netif_receive_skb wrapper for VLAN RX acceleration - * @skb: buffer - * @grp: vlan group - * @vlan_tci: VLAN TCI as received from the card - */ -static inline int vlan_hwaccel_receive_skb(struct sk_buff *skb, - struct vlan_group *grp, - u16 vlan_tci) -{ - return __vlan_hwaccel_rx(skb, grp, vlan_tci, 1); -} - /** * vlan_insert_tag - regular VLAN tag inserting * @skb: skbuff to tag -- cgit v1.2.3 From a4aeb26628b5184386f99cf202ac837b0e56c975 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 20 Jul 2011 04:54:36 +0000 Subject: vlan: kill __vlan_hwaccel_rx and vlan_hwaccel_rx Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 3996713caaec..d81beced0dae 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -125,8 +125,6 @@ extern struct net_device *__vlan_find_dev_deep(struct net_device *real_dev, extern struct net_device *vlan_dev_real_dev(const struct net_device *dev); extern u16 vlan_dev_vlan_id(const struct net_device *dev); -extern int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp, - u16 vlan_tci, int polling); extern bool vlan_do_receive(struct sk_buff **skb); extern struct sk_buff *vlan_untag(struct sk_buff *skb); extern gro_result_t @@ -155,13 +153,6 @@ static inline u16 vlan_dev_vlan_id(const struct net_device *dev) return 0; } -static inline int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp, - u16 vlan_tci, int polling) -{ - BUG(); - return NET_XMIT_SUCCESS; -} - static inline bool vlan_do_receive(struct sk_buff **skb) { if ((*skb)->vlan_tci & VLAN_VID_MASK) @@ -189,19 +180,6 @@ vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp, } #endif -/** - * vlan_hwaccel_rx - netif_rx wrapper for VLAN RX acceleration - * @skb: buffer - * @grp: vlan group - * @vlan_tci: VLAN TCI as received from the card - */ -static inline int vlan_hwaccel_rx(struct sk_buff *skb, - struct vlan_group *grp, - u16 vlan_tci) -{ - return __vlan_hwaccel_rx(skb, grp, vlan_tci, 0); -} - /** * vlan_insert_tag - regular VLAN tag inserting * @skb: skbuff to tag -- cgit v1.2.3 From ffcf9b767293ebc3e59e639cd4ec0dff5ca39798 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 20 Jul 2011 04:54:42 +0000 Subject: vlan: kill vlan_gro_frags and vlan_gro_receive Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index d81beced0dae..f40369e09f5c 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -127,12 +127,6 @@ extern u16 vlan_dev_vlan_id(const struct net_device *dev); extern bool vlan_do_receive(struct sk_buff **skb); extern struct sk_buff *vlan_untag(struct sk_buff *skb); -extern gro_result_t -vlan_gro_receive(struct napi_struct *napi, struct vlan_group *grp, - unsigned int vlan_tci, struct sk_buff *skb); -extern gro_result_t -vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp, - unsigned int vlan_tci); #else static inline struct net_device * @@ -164,20 +158,6 @@ static inline struct sk_buff *vlan_untag(struct sk_buff *skb) { return skb; } - -static inline gro_result_t -vlan_gro_receive(struct napi_struct *napi, struct vlan_group *grp, - unsigned int vlan_tci, struct sk_buff *skb) -{ - return GRO_DROP; -} - -static inline gro_result_t -vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp, - unsigned int vlan_tci) -{ - return GRO_DROP; -} #endif /** -- cgit v1.2.3 From 7890a5b9cbfd159c81ffd7866b5b2d4425886e7f Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 20 Jul 2011 04:54:48 +0000 Subject: vlan: kill ndo_vlan_rx_register has no users so remove it Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 25c805b2c9e5..44f96b24e869 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -768,12 +768,6 @@ struct netdev_tc_txq { * 3. Update dev->stats asynchronously and atomically, and define * neither operation. * - * void (*ndo_vlan_rx_register)(struct net_device *dev, struct vlan_group *grp); - * If device support VLAN receive acceleration - * (ie. dev->features & NETIF_F_HW_VLAN_RX), then this function is called - * when vlan groups for the device changes. Note: grp is NULL - * if no vlan's groups are being used. - * * void (*ndo_vlan_rx_add_vid)(struct net_device *dev, unsigned short vid); * If device support VLAN filtering (dev->features & NETIF_F_HW_VLAN_FILTER) * this function is called when a VLAN id is registered. @@ -892,8 +886,6 @@ struct net_device_ops { struct rtnl_link_stats64 *storage); struct net_device_stats* (*ndo_get_stats)(struct net_device *dev); - void (*ndo_vlan_rx_register)(struct net_device *dev, - struct vlan_group *grp); void (*ndo_vlan_rx_add_vid)(struct net_device *dev, unsigned short vid); void (*ndo_vlan_rx_kill_vid)(struct net_device *dev, -- cgit v1.2.3 From 536d1d4a076210f763b60d7c3823f2edbddf3a9c Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 20 Jul 2011 04:54:49 +0000 Subject: vlan: move vlan_group_[gs]et_device to public header there are no users outside vlan code Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 19 ------------------- 1 file changed, 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index f40369e09f5c..44da4822bcab 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -91,25 +91,6 @@ struct vlan_group { struct rcu_head rcu; }; -static inline struct net_device *vlan_group_get_device(struct vlan_group *vg, - u16 vlan_id) -{ - struct net_device **array; - array = vg->vlan_devices_arrays[vlan_id / VLAN_GROUP_ARRAY_PART_LEN]; - return array ? array[vlan_id % VLAN_GROUP_ARRAY_PART_LEN] : NULL; -} - -static inline void vlan_group_set_device(struct vlan_group *vg, - u16 vlan_id, - struct net_device *dev) -{ - struct net_device **array; - if (!vg) - return; - array = vg->vlan_devices_arrays[vlan_id / VLAN_GROUP_ARRAY_PART_LEN]; - array[vlan_id % VLAN_GROUP_ARRAY_PART_LEN] = dev; -} - static inline int is_vlan_dev(struct net_device *dev) { return dev->priv_flags & IFF_802_1Q_VLAN; -- cgit v1.2.3 From 36bcfe7d74782c07f601edc4831f6b1ef40e9e43 Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Wed, 20 Jul 2011 00:05:23 +0000 Subject: stmmac: unify MAC and PHY configuration parameters (V2) Prior to this change, most PHY configuration parameters were passed into the STMMAC device as a separate PHY device. As well as being unusual, this made it difficult to make changes to the MAC/PHY relationship. This patch moves all the PHY parameters into the MAC configuration structure, mainly as a separate structure. This allows us to completely ignore the MDIO bus attached to a stmmac if desired, and not create the PHY bus. It also allows the stmmac driver to use a different PHY from the one it is connected to, for example a fixed PHY or bit banging PHY. Also derive the stmmac/PHY connection type (MII/RMII etc) from the mode can be passed into _configure_ethernet. STLinux kernel at git://git.stlinux.com/stm/linux-sh4-2.6.32.y.git provides several examples how to use this new infrastructure (that actually is easier to maintain and clearer). Signed-off-by: Stuart Menefy Signed-off-by: Giuseppe Cavallaro Signed-off-by: David S. Miller --- include/linux/stmmac.h | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 05d775690b72..0dddc9e42b6b 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -28,11 +28,21 @@ #include -/* platform data for platform device structure's platform_data field */ +/* Platfrom data for platform device structure's platform_data field */ + +struct stmmac_mdio_bus_data { + int bus_id; + int (*phy_reset)(void *priv); + unsigned int phy_mask; + int *irqs; + int probed_phy_irq; +}; -/* Private data for the STM on-board ethernet driver */ struct plat_stmmacenet_data { int bus_id; + int phy_addr; + int interface; + struct stmmac_mdio_bus_data *mdio_bus_data; int pbl; int clk_csr; int has_gmac; @@ -48,14 +58,4 @@ struct plat_stmmacenet_data { void *custom_cfg; void *bsp_priv; }; - -struct plat_stmmacphy_data { - int bus_id; - int phy_addr; - unsigned int phy_mask; - int interface; - int (*phy_reset)(void *priv); - void *priv; -}; #endif - -- cgit v1.2.3 From e3dbc46c2a62688d1aaa1f7291a054fb2b502849 Mon Sep 17 00:00:00 2001 From: "Choi, Jong-Hwan" Date: Wed, 20 Jul 2011 20:33:03 +0000 Subject: net: Kobj and queues_kset should be used when CONFIG_XPS is enabled Kobj and queues_kset are used with CONFIG_XPS=y. Signed-off-by: Choi, Jong-Hwan Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 44f96b24e869..34f3abc6457a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -530,7 +530,7 @@ struct netdev_queue { struct Qdisc *qdisc; unsigned long state; struct Qdisc *qdisc_sleeping; -#ifdef CONFIG_RPS +#if defined(CONFIG_RPS) || defined(CONFIG_XPS) struct kobject kobj; #endif #if defined(CONFIG_XPS) && defined(CONFIG_NUMA) @@ -1179,7 +1179,7 @@ struct net_device { unsigned char broadcast[MAX_ADDR_LEN]; /* hw bcast add */ -#ifdef CONFIG_RPS +#if defined(CONFIG_RPS) || defined(CONFIG_XPS) struct kset *queues_kset; struct netdev_rx_queue *_rx; -- cgit v1.2.3 From 87c48fa3b4630905f98268dde838ee43626a060c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 21 Jul 2011 21:25:58 -0700 Subject: ipv6: make fragment identifications less predictable IPv6 fragment identification generation is way beyond what we use for IPv4 : It uses a single generator. Its not scalable and allows DOS attacks. Now inetpeer is IPv6 aware, we can use it to provide a more secure and scalable frag ident generator (per destination, instead of system wide) This patch : 1) defines a new secure_ipv6_id() helper 2) extends inet_getid() to provide 32bit results 3) extends ipv6_select_ident() with a new dest parameter Reported-by: Fernando Gont Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/random.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/random.h b/include/linux/random.h index fb7ab9de5f36..ce29a040c8dc 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -58,6 +58,7 @@ extern void get_random_bytes(void *buf, int nbytes); void generate_random_uuid(unsigned char uuid_out[16]); extern __u32 secure_ip_id(__be32 daddr); +extern __u32 secure_ipv6_id(const __be32 daddr[4]); extern u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); extern u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport); -- cgit v1.2.3 From 5dea1c88ed11a1221581c4b202f053c4fc138704 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Fri, 22 Jul 2011 14:39:48 +0930 Subject: lguest: use a special 1:1 linear pagetable mode until first switch. The Host used to create some page tables for the Guest to use at the top of Guest memory; it would then tell the Guest where this was. In particular, it created linear mappings for 0 and 0xC0000000 addresses because lguest used to switch to its real page tables quite late in boot. However, since d50d8fe19 Linux initialized boot page tables in head_32.S even before the "are we lguest?" boot jump. So, now we can simplify things: the Host pagetable code assumes 1:1 linear mapping until it first calls the LHCALL_NEW_PGTABLE hypercall, which we now do before we reach C code. This also means that the Host doesn't need to know anything about the Guest's PAGE_OFFSET. (Non-Linux guests might not even have such a thing). Signed-off-by: Rusty Russell --- include/linux/lguest.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lguest.h b/include/linux/lguest.h index 2fb1dcbcb5aa..9962c6bb1311 100644 --- a/include/linux/lguest.h +++ b/include/linux/lguest.h @@ -59,8 +59,6 @@ struct lguest_data { unsigned long reserve_mem; /* KHz for the TSC clock. */ u32 tsc_khz; - /* Page where the top-level pagetable is */ - unsigned long pgdir; /* Fields initialized by the Guest at boot: */ /* Instruction range to suppress interrupts even if enabled */ -- cgit v1.2.3 From 05aec233367262a43dbf0b615099757162e36f88 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Wed, 20 Jul 2011 19:52:15 +0200 Subject: bcma: inform drivers about translation bits needed for the core MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When using DMA, drivers need to pass special translation info to the hardware. Signed-off-by: Rafał Miłecki Signed-off-by: John W. Linville --- include/linux/bcma/bcma.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index cc1582d24fbc..8c96654bef16 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -262,5 +262,10 @@ extern void bcma_core_set_clockmode(struct bcma_device *core, enum bcma_clkmode clkmode); extern void bcma_core_pll_ctl(struct bcma_device *core, u32 req, u32 status, bool on); +#define BCMA_DMA_TRANSLATION_MASK 0xC0000000 +#define BCMA_DMA_TRANSLATION_NONE 0x00000000 +#define BCMA_DMA_TRANSLATION_DMA32_CMT 0x40000000 /* Client Mode Translation for 32-bit DMA */ +#define BCMA_DMA_TRANSLATION_DMA64_CMT 0x80000000 /* Client Mode Translation for 64-bit DMA */ +extern u32 bcma_core_dma_translation(struct bcma_device *core); #endif /* LINUX_BCMA_H_ */ -- cgit v1.2.3 From 0918472ceeffad234df5589e45b646a94476f835 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Tue, 17 May 2011 16:08:37 +0800 Subject: PCI: PCIe AER: add aer_recover_queue In addition to native PCIe AER, now APEI (ACPI Platform Error Interface) GHES (Generic Hardware Error Source) can be used to report PCIe AER errors too. To add support to APEI GHES PCIe AER recovery, aer_recover_queue is added to export the recovery function in native PCIe AER driver. Recoverable PCIe AER errors are reported via NMI in APEI GHES. Then APEI GHES uses irq_work to delay the error processing into an IRQ handler. But PCIe AER recovery can be very time-consuming, so aer_recover_queue, which can be used in IRQ handler, delays the real recovery action into the process context, that is, work queue. Signed-off-by: Huang Ying Signed-off-by: Jesse Barnes --- include/linux/aer.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/aer.h b/include/linux/aer.h index 8414de22a779..544abdb2238c 100644 --- a/include/linux/aer.h +++ b/include/linux/aer.h @@ -51,5 +51,8 @@ static inline int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev) extern void cper_print_aer(const char *prefix, int cper_severity, struct aer_capability_regs *aer); +extern int cper_severity_to_aer(int cper_severity); +extern void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn, + int severity); #endif //_AER_H_ -- cgit v1.2.3 From 688398bb7b9c6ac115da7749ea808d3ef69e029f Mon Sep 17 00:00:00 2001 From: Myron Stowe Date: Thu, 7 Jul 2011 15:00:36 -0600 Subject: PCI: Assign values to 'pci_obff_signal_type' enumeration constants 'pci_obff_signal_type' is passed between drivers and the kernel API. This patch explicitly assigns values to the enumeration type's constants which aids in detecting any future changes or additions that would break the kernel's ABI. No functional change. Signed-off-by: Myron Stowe Signed-off-by: Jesse Barnes --- include/linux/pci.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index c446b5ca2d38..6e96015e9362 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -843,8 +843,8 @@ void pci_enable_ido(struct pci_dev *dev, unsigned long type); void pci_disable_ido(struct pci_dev *dev, unsigned long type); enum pci_obff_signal_type { - PCI_EXP_OBFF_SIGNAL_L0, - PCI_EXP_OBFF_SIGNAL_ALWAYS, + PCI_EXP_OBFF_SIGNAL_L0 = 0, + PCI_EXP_OBFF_SIGNAL_ALWAYS = 1, }; int pci_enable_obff(struct pci_dev *dev, enum pci_obff_signal_type); void pci_disable_obff(struct pci_dev *dev); -- cgit v1.2.3 From d5341942d784134f2997b3ff82cd63cf71d1f932 Mon Sep 17 00:00:00 2001 From: Ralf Baechle Date: Fri, 10 Jun 2011 15:30:21 +0100 Subject: PCI: Make the struct pci_dev * argument of pci_fixup_irqs const. Aside of the usual motivation for constification, this function has a history of being abused a hook for interrupt and other fixups so I turned this function const ages ago in the MIPS code but it should be done treewide. Due to function pointer passing in varous places a few other functions had to be constified as well. Signed-off-by: Ralf Baechle To: Anton Vorontsov To: Chris Metcalf To: Colin Cross Acked-by: "David S. Miller" To: Eric Miao To: Erik Gilling Acked-by: Guan Xuetao To: "H. Peter Anvin" To: Imre Kaloz To: Ingo Molnar To: Ivan Kokshaysky To: Jesse Barnes To: Krzysztof Halasa To: Lennert Buytenhek To: Matt Turner To: Nicolas Pitre To: Olof Johansson Acked-by: Paul Mundt To: Richard Henderson To: Russell King To: Thomas Gleixner Cc: Andrew Morton Cc: linux-alpha@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Cc: linux-mips@linux-mips.org Cc: linux-pci@vger.kernel.org Cc: linux-sh@vger.kernel.org Cc: linux-tegra@vger.kernel.org Cc: sparclinux@vger.kernel.org Cc: x86@kernel.org Signed-off-by: Jesse Barnes --- include/linux/pci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 6e96015e9362..7053248a2cd1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -879,7 +879,7 @@ void pdev_enable_device(struct pci_dev *); void pdev_sort_resources(struct pci_dev *, struct resource_list *); int pci_enable_resources(struct pci_dev *, int mask); void pci_fixup_irqs(u8 (*)(struct pci_dev *, u8 *), - int (*)(struct pci_dev *, u8, u8)); + int (*)(const struct pci_dev *, u8, u8)); #define HAVE_PCI_REQ_REGIONS 2 int __must_check pci_request_regions(struct pci_dev *, const char *); int __must_check pci_request_regions_exclusive(struct pci_dev *, const char *); -- cgit v1.2.3 From 3baef940f289f08e4aada1fd481ab9ee3f070144 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Fri, 22 Jul 2011 14:04:56 -0700 Subject: ioat: Adding PCI IDs for IOAT devices on SandyBridge platforms Adding to pci_id.h and the device table for ioat. Signed-off-by: Dave Jiang Signed-off-by: Dan Williams --- include/linux/pci_ids.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index f8910e155566..a8571b36ae97 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2699,6 +2699,16 @@ #define PCI_DEVICE_ID_INTEL_ICH10_5 0x3a60 #define PCI_DEVICE_ID_INTEL_5_3400_SERIES_LPC_MIN 0x3b00 #define PCI_DEVICE_ID_INTEL_5_3400_SERIES_LPC_MAX 0x3b1f +#define PCI_DEVICE_ID_INTEL_IOAT_SNB0 0x3c20 +#define PCI_DEVICE_ID_INTEL_IOAT_SNB1 0x3c21 +#define PCI_DEVICE_ID_INTEL_IOAT_SNB2 0x3c22 +#define PCI_DEVICE_ID_INTEL_IOAT_SNB3 0x3c23 +#define PCI_DEVICE_ID_INTEL_IOAT_SNB4 0x3c24 +#define PCI_DEVICE_ID_INTEL_IOAT_SNB5 0x3c25 +#define PCI_DEVICE_ID_INTEL_IOAT_SNB6 0x3c26 +#define PCI_DEVICE_ID_INTEL_IOAT_SNB7 0x3c27 +#define PCI_DEVICE_ID_INTEL_IOAT_SNB8 0x3c2e +#define PCI_DEVICE_ID_INTEL_IOAT_SNB9 0x3c2f #define PCI_DEVICE_ID_INTEL_IOAT_SNB 0x402f #define PCI_DEVICE_ID_INTEL_5100_16 0x65f0 #define PCI_DEVICE_ID_INTEL_5100_21 0x65f5 -- cgit v1.2.3 From 638c1fd3033c76778e6d9975ad8a4a9cdd5b96d9 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Thu, 21 Jul 2011 16:57:52 -0400 Subject: pstore: Extend API for more flexibility in new backends Some pstore implementations may not have a static context, so extend the API to pass the pstore_info struct to all calls and allow for a context pointer. Signed-off-by: Matthew Garrett Signed-off-by: Tony Luck --- include/linux/pstore.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pstore.h b/include/linux/pstore.h index 2455ef2683f0..b2f1d97f6909 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -38,9 +38,11 @@ struct pstore_info { int (*open)(struct pstore_info *psi); int (*close)(struct pstore_info *psi); ssize_t (*read)(u64 *id, enum pstore_type_id *type, - struct timespec *time); - u64 (*write)(enum pstore_type_id type, size_t size); - int (*erase)(u64 id); + struct timespec *time, struct pstore_info *psi); + u64 (*write)(enum pstore_type_id type, size_t size, + struct pstore_info *psi); + int (*erase)(u64 id, struct pstore_info *psi); + void *data; }; #ifdef CONFIG_PSTORE -- cgit v1.2.3 From 56280682ceeef74b692b3e21d1872049eea7c887 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Thu, 21 Jul 2011 16:57:53 -0400 Subject: pstore: Add extra context for writes and erases EFI only provides small amounts of individual storage, and conventionally puts metadata in the storage variable name. Rather than add a metadata header to the (already limited) variable storage, it's easier for us to modify pstore to pass all the information we need to construct a unique variable name to the appropriate functions. Signed-off-by: Matthew Garrett Signed-off-by: Tony Luck --- include/linux/pstore.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pstore.h b/include/linux/pstore.h index b2f1d97f6909..12be8f193d09 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -39,9 +39,10 @@ struct pstore_info { int (*close)(struct pstore_info *psi); ssize_t (*read)(u64 *id, enum pstore_type_id *type, struct timespec *time, struct pstore_info *psi); - u64 (*write)(enum pstore_type_id type, size_t size, + u64 (*write)(enum pstore_type_id type, int part, + size_t size, struct pstore_info *psi); + int (*erase)(enum pstore_type_id type, u64 id, struct pstore_info *psi); - int (*erase)(u64 id, struct pstore_info *psi); void *data; }; -- cgit v1.2.3 From b94fdd077eef5e6cab56836bf62695b497946716 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Thu, 21 Jul 2011 16:57:54 -0400 Subject: pstore: Make "part" unsigned We'll never have a negative part, so just make this an unsigned int. Signed-off-by: Matthew Garrett Signed-off-by: Tony Luck --- include/linux/pstore.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pstore.h b/include/linux/pstore.h index 12be8f193d09..cc03bbf5c4b8 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -39,7 +39,7 @@ struct pstore_info { int (*close)(struct pstore_info *psi); ssize_t (*read)(u64 *id, enum pstore_type_id *type, struct timespec *time, struct pstore_info *psi); - u64 (*write)(enum pstore_type_id type, int part, + u64 (*write)(enum pstore_type_id type, unsigned int part, size_t size, struct pstore_info *psi); int (*erase)(enum pstore_type_id type, u64 id, struct pstore_info *psi); -- cgit v1.2.3 From 5ee9c198a4208d7760275d48e4c4f6c89dcd2ef0 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Thu, 21 Jul 2011 16:57:56 -0400 Subject: efi: Add support for using efivars as a pstore backend EFI provides an area of nonvolatile storage managed by the firmware. We can use this as a pstore backend to maintain copies of oopses, aiding diagnosis. Signed-off-by: Matthew Garrett Signed-off-by: Tony Luck --- include/linux/efi.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index e376270cd26e..c1f5107338c6 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -211,6 +212,9 @@ typedef efi_status_t efi_set_virtual_address_map_t (unsigned long memory_map_siz #define UV_SYSTEM_TABLE_GUID \ EFI_GUID( 0x3b13a7d4, 0x633e, 0x11dd, 0x93, 0xec, 0xda, 0x25, 0x56, 0xd8, 0x95, 0x93 ) +#define LINUX_EFI_CRASH_GUID \ + EFI_GUID( 0xcfc8fc79, 0xbe2e, 0x4ddc, 0x97, 0xf0, 0x9f, 0x98, 0xbf, 0xe2, 0x98, 0xa0 ) + typedef struct { efi_guid_t guid; unsigned long table; @@ -426,6 +430,8 @@ struct efivars { struct kset *kset; struct bin_attribute *new_var, *del_var; const struct efivar_operations *ops; + struct efivar_entry *walk_entry; + struct pstore_info efi_pstore_info; }; int register_efivars(struct efivars *efivars, -- cgit v1.2.3 From ed70afcd6e795e3de98df56f1cd0f898fbf641a7 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 21 Jul 2011 13:55:37 -0700 Subject: mm/truncate.c: fix build for CONFIG_BLOCK not enabled Fix build error when CONFIG_BLOCK is not enabled by providing a stub inode_dio_wait() function. mm/truncate.c:612: error: implicit declaration of function 'inode_dio_wait' Signed-off-by: Randy Dunlap Signed-off-by: Al Viro --- include/linux/fs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index e0569e4ab2d5..b224dc468a23 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2423,6 +2423,10 @@ static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb, offset, nr_segs, get_block, NULL, NULL, DIO_LOCKING | DIO_SKIP_HOLES); } +#else +static inline void inode_dio_wait(struct inode *inode) +{ +} #endif extern const struct file_operations generic_ro_fops; -- cgit v1.2.3 From b83a313bf2520183641cf485d68cc273323597d2 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 11 May 2011 19:59:58 +0200 Subject: regmap: Add generic non-memory mapped register access API There are many places in the tree where we implement register access for devices on non-memory mapped buses, especially I2C and SPI. Since hardware designers seem to have settled on a relatively consistent set of register interfaces this can be effectively factored out into shared code. There are a standard set of formats for marshalling data for exchange with the device, with the actual I/O mechanisms generally being simple byte streams. We create an abstraction for marshaling data into formats which can be sent on the control interfaces, and create a standard method for plugging in actual transport underneath that. This is mostly a refactoring and renaming of the bottom level of the existing code for sharing register I/O which we have in ASoC. A subsequent patch in this series converts ASoC to use this. The main difference in interface is that reads return values by writing to a location provided by a pointer rather than in the return value, ensuring we can use the full range of the type for register data. We also use unsigned types rather than ints for the same reason. As some of the devices can have very large register maps the existing ASoC code also contains infrastructure for managing register caches. This cache work will be moved over in a future stage to allow for separate review, the current patch only deals with the physical I/O. Signed-off-by: Mark Brown Acked-by: Liam Girdwood Acked-by: Greg Kroah-Hartman Acked-by: Wolfram Sang Acked-by: Grant Likely --- include/linux/regmap.h | 74 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 74 insertions(+) create mode 100644 include/linux/regmap.h (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h new file mode 100644 index 000000000000..a26c1d001401 --- /dev/null +++ b/include/linux/regmap.h @@ -0,0 +1,74 @@ +#ifndef __LINUX_REGMAP_H +#define __LINUX_REGMAP_H + +/* + * Register map access API + * + * Copyright 2011 Wolfson Microelectronics plc + * + * Author: Mark Brown + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include + +struct regmap_config { + int reg_bits; + int val_bits; +}; + +typedef int (*regmap_hw_write)(struct device *dev, const void *data, + size_t count); +typedef int (*regmap_hw_gather_write)(struct device *dev, + const void *reg, size_t reg_len, + const void *val, size_t val_len); +typedef int (*regmap_hw_read)(struct device *dev, + const void *reg_buf, size_t reg_size, + void *val_buf, size_t val_size); + +/** + * Description of a hardware bus for the register map infrastructure. + * + * @list: Internal use. + * @type: Bus type, used to identify bus to be used for a device. + * @write: Write operation. + * @gather_write: Write operation with split register/value, return -ENOTSUPP + * if not implemented on a given device. + * @read: Read operation. Data is returned in the buffer used to transmit + * data. + * @owner: Module with the bus implementation, used to pin the implementation + * in memory. + * @read_flag_mask: Mask to be set in the top byte of the register when doing + * a read. + */ +struct regmap_bus { + struct list_head list; + struct bus_type *type; + regmap_hw_write write; + regmap_hw_gather_write gather_write; + regmap_hw_read read; + struct module *owner; + u8 read_flag_mask; +}; + +struct regmap *regmap_init(struct device *dev, + const struct regmap_bus *bus, + const struct regmap_config *config); +void regmap_exit(struct regmap *map); +int regmap_write(struct regmap *map, unsigned int reg, unsigned int val); +int regmap_raw_write(struct regmap *map, unsigned int reg, + const void *val, size_t val_len); +int regmap_read(struct regmap *map, unsigned int reg, unsigned int *val); +int regmap_raw_read(struct regmap *map, unsigned int reg, + void *val, size_t val_len); +int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val, + size_t val_count); +int regmap_update_bits(struct regmap *map, unsigned int reg, + unsigned int mask, unsigned int val); + +#endif -- cgit v1.2.3 From 9943fa300a5dcd4536e9a4aa5c09cf94e5e7b28c Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 20 Jun 2011 19:02:29 +0100 Subject: regmap: Add I2C bus support Signed-off-by: Mark Brown Acked-by: Liam Girdwood Acked-by: Wolfram Sang Acked-by: Grant Likely --- include/linux/regmap.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index a26c1d001401..5ba61f22c703 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -17,6 +17,8 @@ #include #include +struct i2c_client; + struct regmap_config { int reg_bits; int val_bits; @@ -59,6 +61,8 @@ struct regmap_bus { struct regmap *regmap_init(struct device *dev, const struct regmap_bus *bus, const struct regmap_config *config); +struct regmap *regmap_init_i2c(struct i2c_client *i2c, + const struct regmap_config *config); void regmap_exit(struct regmap *map); int regmap_write(struct regmap *map, unsigned int reg, unsigned int val); int regmap_raw_write(struct regmap *map, unsigned int reg, -- cgit v1.2.3 From a676f083068b08e676c557279effbd7f4d590812 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 12 May 2011 11:42:10 +0200 Subject: regmap: Add SPI bus support Signed-off-by: Mark Brown Acked-by: Liam Girdwood Acked-by: Wolfram Sang Acked-by: Grant Likely --- include/linux/regmap.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 5ba61f22c703..60a65cd7e1a0 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -18,6 +18,7 @@ #include struct i2c_client; +struct spi_device; struct regmap_config { int reg_bits; @@ -63,6 +64,9 @@ struct regmap *regmap_init(struct device *dev, const struct regmap_config *config); struct regmap *regmap_init_i2c(struct i2c_client *i2c, const struct regmap_config *config); +struct regmap *regmap_init_spi(struct spi_device *dev, + const struct regmap_config *config); + void regmap_exit(struct regmap *map); int regmap_write(struct regmap *map, unsigned int reg, unsigned int val); int regmap_raw_write(struct regmap *map, unsigned int reg, -- cgit v1.2.3 From 5757a6d76cdf6dda2a492c09b985c015e86779b1 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Sat, 23 Jul 2011 20:44:25 +0200 Subject: block: strict rq_affinity Some systems benefit from completions always being steered to the strict requester cpu rather than the looser "per-socket" steering that blk_cpu_to_group() attempts by default. This is because the first CPU in the group mask ends up being completely overloaded with work, while the others (including the original submitter) has power left to spare. Allow the strict mode to be set by writing '2' to the sysfs control file. This is identical to the scheme used for the nomerges file, where '2' is a more aggressive setting than just being turned on. echo 2 > /sys/block//queue/rq_affinity Cc: Christoph Hellwig Cc: Roland Dreier Tested-by: Dave Jiang Signed-off-by: Dan Williams Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c0cd9a2f22ef..0e67c45b3bc9 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -392,7 +392,7 @@ struct request_queue { #define QUEUE_FLAG_ELVSWITCH 6 /* don't use elevator, just do FIFO */ #define QUEUE_FLAG_BIDI 7 /* queue supports bidi requests */ #define QUEUE_FLAG_NOMERGES 8 /* disable merge attempts */ -#define QUEUE_FLAG_SAME_COMP 9 /* force complete on same CPU */ +#define QUEUE_FLAG_SAME_COMP 9 /* complete on same CPU-group */ #define QUEUE_FLAG_FAIL_IO 10 /* fake timeout */ #define QUEUE_FLAG_STACKABLE 11 /* supports request stacking */ #define QUEUE_FLAG_NONROT 12 /* non-rotational device (SSD) */ @@ -402,6 +402,7 @@ struct request_queue { #define QUEUE_FLAG_NOXMERGES 15 /* No extended merges */ #define QUEUE_FLAG_ADD_RANDOM 16 /* Contributes to random pool */ #define QUEUE_FLAG_SECDISCARD 17 /* supports SECDISCARD */ +#define QUEUE_FLAG_SAME_FORCE 18 /* force complete on same CPU */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_STACKABLE) | \ -- cgit v1.2.3 From a9a79dfec239568bdbf778242f8fcd10bcc5b9e2 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Fri, 15 Apr 2011 15:51:59 -0700 Subject: ata: Convert ata__printk(KERN_ to ata__ Saves text by removing nearly duplicated text format strings by creating ata__printk functions and printf extension %pV. ata defconfig size shrinks ~5% (~8KB), allyesconfig ~2.5% (~13KB) Format string duplication comes from: #define ata_link_printk(link, lv, fmt, args...) do { \ if (sata_pmp_attached((link)->ap) || (link)->ap->slave_link) \ printk("%sata%u.%02u: "fmt, lv, (link)->ap->print_id, \ (link)->pmp , ##args); \ else \ printk("%sata%u: "fmt, lv, (link)->ap->print_id , ##args); \ } while(0) Coalesce long formats. $ size drivers/ata/built-in.* text data bss dec hex filename 544969 73893 116584 735446 b38d6 drivers/ata/built-in.allyesconfig.ata.o 558429 73893 117864 750186 b726a drivers/ata/built-in.allyesconfig.dev_level.o 141328 14689 4220 160237 271ed drivers/ata/built-in.defconfig.ata.o 149567 14689 4220 168476 2921c drivers/ata/built-in.defconfig.dev_level.o Signed-off-by: Joe Perches Signed-off-by: Jeff Garzik --- include/linux/libata.h | 56 +++++++++++++++++++++++++++++++++++++------------- 1 file changed, 42 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 5a9926b34072..4e72a6af70b5 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1244,20 +1244,48 @@ static inline int sata_srst_pmp(struct ata_link *link) /* * printk helpers */ -#define ata_port_printk(ap, lv, fmt, args...) \ - printk("%sata%u: "fmt, lv, (ap)->print_id , ##args) - -#define ata_link_printk(link, lv, fmt, args...) do { \ - if (sata_pmp_attached((link)->ap) || (link)->ap->slave_link) \ - printk("%sata%u.%02u: "fmt, lv, (link)->ap->print_id, \ - (link)->pmp , ##args); \ - else \ - printk("%sata%u: "fmt, lv, (link)->ap->print_id , ##args); \ - } while(0) - -#define ata_dev_printk(dev, lv, fmt, args...) \ - printk("%sata%u.%02u: "fmt, lv, (dev)->link->ap->print_id, \ - (dev)->link->pmp + (dev)->devno , ##args) +__attribute__((format (printf, 3, 4))) +int ata_port_printk(const struct ata_port *ap, const char *level, + const char *fmt, ...); +__attribute__((format (printf, 3, 4))) +int ata_link_printk(const struct ata_link *link, const char *level, + const char *fmt, ...); +__attribute__((format (printf, 3, 4))) +int ata_dev_printk(const struct ata_device *dev, const char *level, + const char *fmt, ...); + +#define ata_port_err(ap, fmt, ...) \ + ata_port_printk(ap, KERN_ERR, fmt, ##__VA_ARGS__) +#define ata_port_warn(ap, fmt, ...) \ + ata_port_printk(ap, KERN_WARNING, fmt, ##__VA_ARGS__) +#define ata_port_notice(ap, fmt, ...) \ + ata_port_printk(ap, KERN_NOTICE, fmt, ##__VA_ARGS__) +#define ata_port_info(ap, fmt, ...) \ + ata_port_printk(ap, KERN_INFO, fmt, ##__VA_ARGS__) +#define ata_port_dbg(ap, fmt, ...) \ + ata_port_printk(ap, KERN_DEBUG, fmt, ##__VA_ARGS__) + +#define ata_link_err(link, fmt, ...) \ + ata_link_printk(link, KERN_ERR, fmt, ##__VA_ARGS__) +#define ata_link_warn(link, fmt, ...) \ + ata_link_printk(link, KERN_WARNING, fmt, ##__VA_ARGS__) +#define ata_link_notice(link, fmt, ...) \ + ata_link_printk(link, KERN_NOTICE, fmt, ##__VA_ARGS__) +#define ata_link_info(link, fmt, ...) \ + ata_link_printk(link, KERN_INFO, fmt, ##__VA_ARGS__) +#define ata_link_dbg(link, fmt, ...) \ + ata_link_printk(link, KERN_DEBUG, fmt, ##__VA_ARGS__) + +#define ata_dev_err(dev, fmt, ...) \ + ata_dev_printk(dev, KERN_ERR, fmt, ##__VA_ARGS__) +#define ata_dev_warn(dev, fmt, ...) \ + ata_dev_printk(dev, KERN_WARNING, fmt, ##__VA_ARGS__) +#define ata_dev_notice(dev, fmt, ...) \ + ata_dev_printk(dev, KERN_NOTICE, fmt, ##__VA_ARGS__) +#define ata_dev_info(dev, fmt, ...) \ + ata_dev_printk(dev, KERN_INFO, fmt, ##__VA_ARGS__) +#define ata_dev_dbg(dev, fmt, ...) \ + ata_dev_printk(dev, KERN_DEBUG, fmt, ##__VA_ARGS__) /* * ata_eh_info helpers -- cgit v1.2.3 From 06296a1e684bcd40b9a28d5d8030809e4295528b Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Fri, 15 Apr 2011 15:52:00 -0700 Subject: ata: Add and use ata_print_version_once Use a single mechanism to show driver version. Reduces text a tiny bit too. Remove uses of static int printed_version Add and use ata_print_version(const struct device *, const char *ver) and ata_print_version_once. $ size drivers/ata/built-in.* text data bss dec hex filename 544969 73893 116584 735446 b38d6 drivers/ata/built-in.allyesconfig.ata.o 543870 73893 116592 734355 b34ad drivers/ata/built-in.allyesconfig.print_once.o 141328 14689 4220 160237 271ed drivers/ata/built-in.defconfig.ata.o 141212 14689 4220 160121 27179 drivers/ata/built-in.defconfig.print_once.o Signed-off-by: Joe Perches Signed-off-by: Jeff Garzik --- include/linux/libata.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 4e72a6af70b5..efd6f9800762 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -74,6 +74,16 @@ #define BPRINTK(fmt, args...) if (ap->flags & ATA_FLAG_DEBUGMSG) printk(KERN_ERR "%s: " fmt, __func__, ## args) +#define ata_print_version_once(dev, version) \ +({ \ + static bool __print_once; \ + \ + if (!__print_once) { \ + __print_once = true; \ + ata_print_version(dev, version); \ + } \ +}) + /* NEW: debug levels */ #define HAVE_LIBATA_MSG 1 @@ -1287,6 +1297,8 @@ int ata_dev_printk(const struct ata_device *dev, const char *level, #define ata_dev_dbg(dev, fmt, ...) \ ata_dev_printk(dev, KERN_DEBUG, fmt, ##__VA_ARGS__) +void ata_print_version(const struct device *dev, const char *version); + /* * ata_eh_info helpers */ -- cgit v1.2.3 From fce92dce79dbf5fff39c7ac2fb149729d79b7a39 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Tue, 12 Jul 2011 03:28:54 +0800 Subject: KVM: MMU: filter out the mmio pfn from the fault pfn If the page fault is caused by mmio, the gfn can not be found in memslots, and 'bad_pfn' is returned on gfn_to_hva path, so we can use 'bad_pfn' to identify the mmio page fault. And, to clarify the meaning of mmio pfn, we return fault page instead of bad page when the gfn is not allowd to prefetch Signed-off-by: Xiao Guangrong Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c8e023902f79..eabb21a30c34 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -327,12 +327,17 @@ static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm) static inline int is_error_hpa(hpa_t hpa) { return hpa >> HPA_MSB; } extern struct page *bad_page; +extern struct page *fault_page; + extern pfn_t bad_pfn; +extern pfn_t fault_pfn; int is_error_page(struct page *page); int is_error_pfn(pfn_t pfn); int is_hwpoison_pfn(pfn_t pfn); int is_fault_pfn(pfn_t pfn); +int is_noslot_pfn(pfn_t pfn); +int is_invalid_pfn(pfn_t pfn); int kvm_is_error_hva(unsigned long addr); int kvm_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, -- cgit v1.2.3 From 74e08fcf7bef973512a1f813700f802a93678670 Mon Sep 17 00:00:00 2001 From: Jonas Bonn Date: Thu, 30 Jun 2011 21:22:11 +0200 Subject: modules: add default loader hook implementations The module loader code allows architectures to hook into the code by providing a small number of entry points that each arch must implement. This patch provides __weakly linked generic implementations of these entry points for architectures that don't need to do anything special. Signed-off-by: Jonas Bonn Signed-off-by: Rusty Russell --- include/linux/moduleloader.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h index c1f40c2f7ffb..b2be02ebf453 100644 --- a/include/linux/moduleloader.h +++ b/include/linux/moduleloader.h @@ -5,7 +5,12 @@ #include #include -/* These must be implemented by the specific architecture */ +/* These may be implemented by architectures that need to hook into the + * module loader code. Architectures that don't need to do anything special + * can just rely on the 'weak' default hooks defined in kernel/module.c. + * Note, however, that at least one of apply_relocate or apply_relocate_add + * must be implemented by each architecture. + */ /* Adjust arch-specific sections. Return 0 on success. */ int module_frob_arch_sections(Elf_Ehdr *hdr, -- cgit v1.2.3 From 4befb026cf74b52fc7d382142bbfc0e9b6aab5e7 Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Sun, 24 Jul 2011 22:06:04 +0930 Subject: module: change attr callbacks to take struct module_kobject This simplifies the next patch, where we have an attribute on a builtin module (ie. module == NULL). Signed-off-by: Kay Sievers Signed-off-by: Rusty Russell (split into 2) --- include/linux/module.h | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index d9ca2d5dc6d0..b87e7625a98c 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -48,10 +48,18 @@ struct modversion_info struct module; +struct module_kobject { + struct kobject kobj; + struct module *mod; + struct kobject *drivers_dir; + struct module_param_attrs *mp; +}; + struct module_attribute { - struct attribute attr; - ssize_t (*show)(struct module_attribute *, struct module *, char *); - ssize_t (*store)(struct module_attribute *, struct module *, + struct attribute attr; + ssize_t (*show)(struct module_attribute *, struct module_kobject *, + char *); + ssize_t (*store)(struct module_attribute *, struct module_kobject *, const char *, size_t count); void (*setup)(struct module *, const char *); int (*test)(struct module *); @@ -65,15 +73,8 @@ struct module_version_attribute { } __attribute__ ((__aligned__(sizeof(void *)))); extern ssize_t __modver_version_show(struct module_attribute *, - struct module *, char *); + struct module_kobject *, char *); -struct module_kobject -{ - struct kobject kobj; - struct module *mod; - struct kobject *drivers_dir; - struct module_param_attrs *mp; -}; /* These are either module local, or the kernel's dummy ones. */ extern int init_module(void); -- cgit v1.2.3 From 88bfa3247961fe5f3623f4d2cf1cd5dc72457598 Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Sun, 24 Jul 2011 22:06:04 +0930 Subject: module: add /sys/module//uevent files Userspace wants to manage module parameters with udev rules. This currently only works for loaded modules, but not for built-in ones. To allow access to the built-in modules we need to re-trigger all module load events that happened before any userspace was running. We already do the same thing for all devices, subsystems(buses) and drivers. This adds the currently missing /sys/module//uevent files to all module entries. Signed-off-by: Kay Sievers Signed-off-by: Rusty Russell (split & trivial fix) --- include/linux/module.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index b87e7625a98c..1c30087a2d81 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -75,6 +75,7 @@ struct module_version_attribute { extern ssize_t __modver_version_show(struct module_attribute *, struct module_kobject *, char *); +extern struct module_attribute module_uevent; /* These are either module local, or the kernel's dummy ones. */ extern int init_module(void); -- cgit v1.2.3 From 423e0ab086ad8b33626e45fa94ac7613146b7ffa Mon Sep 17 00:00:00 2001 From: Tim Chen Date: Tue, 19 Jul 2011 09:32:38 -0700 Subject: VFS : mount lock scalability for internal mounts For a number of file systems that don't have a mount point (e.g. sockfs and pipefs), they are not marked as long term. Therefore in mntput_no_expire, all locks in vfs_mount lock are taken instead of just local cpu's lock to aggregate reference counts when we release reference to file objects. In fact, only local lock need to have been taken to update ref counts as these file systems are in no danger of going away until we are ready to unregister them. The attached patch marks file systems using kern_mount without mount point as long term. The contentions of vfs_mount lock is now eliminated. Before un-registering such file system, kern_unmount should be called to remove the long term flag and make the mount point ready to be freed. Signed-off-by: Tim Chen Signed-off-by: Al Viro --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index b224dc468a23..7a757a48a5c6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1885,6 +1885,7 @@ extern int register_filesystem(struct file_system_type *); extern int unregister_filesystem(struct file_system_type *); extern struct vfsmount *kern_mount_data(struct file_system_type *, void *data); #define kern_mount(type) kern_mount_data(type, NULL) +extern void kern_unmount(struct vfsmount *mnt); extern int may_umount_tree(struct vfsmount *); extern int may_umount(struct vfsmount *); extern long do_mount(char *, char *, char *, unsigned long, void *); -- cgit v1.2.3 From 5cf49d763eb141d236e92be6d4a0dc94e31fa886 Mon Sep 17 00:00:00 2001 From: Wang Sheng-Hui Date: Mon, 25 Jul 2011 21:02:25 +0800 Subject: jbd: change the field "b_cow_tid" of struct journal_head from type unsigned to tid_t In the definition of struct journal_head, the comment for the field "unsigned b_cow_tid" says the field tracks the last transaction id in which this buffer has been cowed. In the header part of file journal-head.h, it defines typedef unsigned int tid_t; We should use type tid_t to define transaction id fields. Change the field "b_cow_tid" of struct journal_head from type unsigned to tid_t. Signed-off-by: Wang Sheng-Hui Acked-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/journal-head.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/journal-head.h b/include/linux/journal-head.h index 44e95d0a721f..423cb6d78ee0 100644 --- a/include/linux/journal-head.h +++ b/include/linux/journal-head.h @@ -45,7 +45,7 @@ struct journal_head { * has been cowed * [jbd_lock_bh_state()] */ - unsigned b_cow_tid; + tid_t b_cow_tid; /* * Copy of the buffer data frozen for writing to the log. -- cgit v1.2.3 From bc26ab5f65ae41b71df86ea46df3c3833d1d8d83 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 23 Jul 2011 00:18:02 -0400 Subject: kill boilerplate around posix_acl_chmod_masq() new helper: posix_acl_chmod(&acl, gfp, mode). Replaces acl with modified clone or with NULL if that has failed; returns 0 or -ve on error. All callers of posix_acl_chmod_masq() switched to that - they'd been doing exactly the same thing. Signed-off-by: Al Viro --- include/linux/posix_acl.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 54211c1cd926..7a74d37482e8 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -80,6 +80,7 @@ extern struct posix_acl *posix_acl_from_mode(mode_t, gfp_t); extern int posix_acl_equiv_mode(const struct posix_acl *, mode_t *); extern int posix_acl_create_masq(struct posix_acl *, mode_t *); extern int posix_acl_chmod_masq(struct posix_acl *, mode_t); +extern int posix_acl_chmod(struct posix_acl **, gfp_t, mode_t); extern struct posix_acl *get_posix_acl(struct inode *, int); extern int set_posix_acl(struct inode *, int, struct posix_acl *); -- cgit v1.2.3 From 826cae2f2b4d726b925f43bc208a571639da4761 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 23 Jul 2011 03:10:32 -0400 Subject: kill boilerplates around posix_acl_create_masq() new helper: posix_acl_create(&acl, gfp, mode_p). Replaces acl with modified clone, on failure releases acl and replaces with NULL. Returns 0 or -ve on error. All callers of posix_acl_create_masq() switched. Signed-off-by: Al Viro --- include/linux/posix_acl.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 7a74d37482e8..0ae0e4a3e20c 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -80,6 +80,7 @@ extern struct posix_acl *posix_acl_from_mode(mode_t, gfp_t); extern int posix_acl_equiv_mode(const struct posix_acl *, mode_t *); extern int posix_acl_create_masq(struct posix_acl *, mode_t *); extern int posix_acl_chmod_masq(struct posix_acl *, mode_t); +extern int posix_acl_create(struct posix_acl **, gfp_t, mode_t *); extern int posix_acl_chmod(struct posix_acl **, gfp_t, mode_t); extern struct posix_acl *get_posix_acl(struct inode *, int); -- cgit v1.2.3 From edde854e8bb34a7f32fa993d721f1da0faf64165 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 23 Jul 2011 03:27:37 -0400 Subject: bury posix_acl_..._masq() variants made static; no callers left outside of posix_acl.c. posix_acl_clone() also has lost all external callers and became static... Signed-off-by: Al Viro --- include/linux/posix_acl.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 0ae0e4a3e20c..9a53b99818e2 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -73,13 +73,10 @@ posix_acl_release(struct posix_acl *acl) extern void posix_acl_init(struct posix_acl *, int); extern struct posix_acl *posix_acl_alloc(int, gfp_t); -extern struct posix_acl *posix_acl_clone(const struct posix_acl *, gfp_t); extern int posix_acl_valid(const struct posix_acl *); extern int posix_acl_permission(struct inode *, const struct posix_acl *, int); extern struct posix_acl *posix_acl_from_mode(mode_t, gfp_t); extern int posix_acl_equiv_mode(const struct posix_acl *, mode_t *); -extern int posix_acl_create_masq(struct posix_acl *, mode_t *); -extern int posix_acl_chmod_masq(struct posix_acl *, mode_t); extern int posix_acl_create(struct posix_acl **, gfp_t, mode_t *); extern int posix_acl_chmod(struct posix_acl **, gfp_t, mode_t); -- cgit v1.2.3 From 4e34e719e457f2e031297175410fc0bd4016a085 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 23 Jul 2011 17:37:31 +0200 Subject: fs: take the ACL checks to common code Replace the ->check_acl method with a ->get_acl method that simply reads an ACL from disk after having a cache miss. This means we can replace the ACL checking boilerplate code with a single implementation in namei.c. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- include/linux/generic_acl.h | 1 - include/linux/reiserfs_acl.h | 6 +----- include/linux/reiserfs_xattr.h | 2 -- 4 files changed, 2 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7a757a48a5c6..12f84b30c3ca 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1586,7 +1586,7 @@ struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameidata *); void * (*follow_link) (struct dentry *, struct nameidata *); int (*permission) (struct inode *, int); - int (*check_acl)(struct inode *, int); + struct posix_acl * (*get_acl)(struct inode *, int); int (*readlink) (struct dentry *, char __user *,int); void (*put_link) (struct dentry *, struct nameidata *, void *); diff --git a/include/linux/generic_acl.h b/include/linux/generic_acl.h index 574bea4013b6..b6d657544ef1 100644 --- a/include/linux/generic_acl.h +++ b/include/linux/generic_acl.h @@ -10,6 +10,5 @@ extern const struct xattr_handler generic_acl_default_handler; int generic_acl_init(struct inode *, struct inode *); int generic_acl_chmod(struct inode *); -int generic_check_acl(struct inode *inode, int mask); #endif /* LINUX_GENERIC_ACL_H */ diff --git a/include/linux/reiserfs_acl.h b/include/linux/reiserfs_acl.h index 3fd8c4506bbb..f096b80e73d8 100644 --- a/include/linux/reiserfs_acl.h +++ b/include/linux/reiserfs_acl.h @@ -59,11 +59,7 @@ extern const struct xattr_handler reiserfs_posix_acl_access_handler; #else #define reiserfs_cache_default_acl(inode) 0 - -static inline struct posix_acl *reiserfs_get_acl(struct inode *inode, int type) -{ - return NULL; -} +#define reiserfs_get_acl NULL static inline int reiserfs_acl_chmod(struct inode *inode) { diff --git a/include/linux/reiserfs_xattr.h b/include/linux/reiserfs_xattr.h index 57958c0e1d38..c2b71473266e 100644 --- a/include/linux/reiserfs_xattr.h +++ b/include/linux/reiserfs_xattr.h @@ -45,7 +45,6 @@ int reiserfs_permission(struct inode *inode, int mask); #ifdef CONFIG_REISERFS_FS_XATTR #define has_xattr_dir(inode) (REISERFS_I(inode)->i_flags & i_has_xattr_dir) -int reiserfs_check_acl(struct inode *inode, int mask); ssize_t reiserfs_getxattr(struct dentry *dentry, const char *name, void *buffer, size_t size); int reiserfs_setxattr(struct dentry *dentry, const char *name, @@ -123,7 +122,6 @@ static inline void reiserfs_init_xattr_rwsem(struct inode *inode) #define reiserfs_setxattr NULL #define reiserfs_listxattr NULL #define reiserfs_removexattr NULL -#define reiserfs_check_acl NULL static inline void reiserfs_init_xattr_rwsem(struct inode *inode) { -- cgit v1.2.3 From 2d348d1f569f051d2609b04d27bb55cd25eda8fe Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 25 Jul 2011 16:17:35 -0700 Subject: net: Convert struct net_device uc_promisc to bool No need to use int, its uses are boolean. May save a few bytes one day. Signed-off-by: Joe Perches Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 34f3abc6457a..1d92acc0777b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1132,7 +1132,7 @@ struct net_device { spinlock_t addr_list_lock; struct netdev_hw_addr_list uc; /* Unicast mac addresses */ struct netdev_hw_addr_list mc; /* Multicast mac addresses */ - int uc_promisc; + bool uc_promisc; unsigned int promiscuity; unsigned int allmulti; -- cgit v1.2.3 From ee8f248d266ec6966c0ce6b7dec24de43dcc1b58 Mon Sep 17 00:00:00 2001 From: Becky Bruce Date: Mon, 25 Jul 2011 17:11:50 -0700 Subject: hugetlb: add phys addr to struct huge_bootmem_page This is needed on HIGHMEM systems - we don't always have a virtual address so store the physical address and map it in as needed. [akpm@linux-foundation.org: cleanup] Signed-off-by: Becky Bruce Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 59225ef27d15..19644e0016bd 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -231,6 +231,9 @@ struct hstate { struct huge_bootmem_page { struct list_head list; struct hstate *hstate; +#ifdef CONFIG_HIGHMEM + phys_addr_t phys; +#endif }; struct page *alloc_huge_page_node(struct hstate *h, int nid); -- cgit v1.2.3 From 33dd4e0ec91138c3d80e790c08a3db47426c81f2 Mon Sep 17 00:00:00 2001 From: Ian Campbell Date: Mon, 25 Jul 2011 17:11:51 -0700 Subject: mm: make some struct page's const These uses are read-only and in a subsequent patch I have a const struct page in my hand... [akpm@linux-foundation.org: fix warnings in lowmem_page_address()] Signed-off-by: Ian Campbell Cc: Rik van Riel Cc: Andrea Arcangeli Cc: Mel Gorman Cc: Michel Lespinasse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 8a45ad22a170..6321e840e21d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -637,7 +637,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) #define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1) #define ZONEID_MASK ((1UL << ZONEID_SHIFT) - 1) -static inline enum zone_type page_zonenum(struct page *page) +static inline enum zone_type page_zonenum(const struct page *page) { return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; } @@ -665,15 +665,15 @@ static inline int zone_to_nid(struct zone *zone) } #ifdef NODE_NOT_IN_PAGE_FLAGS -extern int page_to_nid(struct page *page); +extern int page_to_nid(const struct page *page); #else -static inline int page_to_nid(struct page *page) +static inline int page_to_nid(const struct page *page) { return (page->flags >> NODES_PGSHIFT) & NODES_MASK; } #endif -static inline struct zone *page_zone(struct page *page) +static inline struct zone *page_zone(const struct page *page) { return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)]; } @@ -718,9 +718,9 @@ static inline void set_page_links(struct page *page, enum zone_type zone, */ #include -static __always_inline void *lowmem_page_address(struct page *page) +static __always_inline void *lowmem_page_address(const struct page *page) { - return __va(PFN_PHYS(page_to_pfn(page))); + return __va(PFN_PHYS(page_to_pfn((struct page *)page))); } #if defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL) -- cgit v1.2.3 From 67db392d1124e14684e23deb572de2a63b9b3b69 Mon Sep 17 00:00:00 2001 From: Ian Campbell Date: Mon, 25 Jul 2011 17:11:52 -0700 Subject: mm: use const struct page for r/o page-flag accessor methods In a subsquent patch I have a const struct page in my hand... [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Ian Campbell Cc: Andrea Arcangeli Cc: Rik van Riel Cc: Martin Schwidefsky Cc: Michel Lespinasse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 6081493db68f..3e5a1b189a41 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -135,7 +135,7 @@ enum pageflags { * Macros to create function definitions for page flags */ #define TESTPAGEFLAG(uname, lname) \ -static inline int Page##uname(struct page *page) \ +static inline int Page##uname(const struct page *page) \ { return test_bit(PG_##lname, &page->flags); } #define SETPAGEFLAG(uname, lname) \ @@ -173,7 +173,7 @@ static inline int __TestClearPage##uname(struct page *page) \ __SETPAGEFLAG(uname, lname) __CLEARPAGEFLAG(uname, lname) #define PAGEFLAG_FALSE(uname) \ -static inline int Page##uname(struct page *page) \ +static inline int Page##uname(const struct page *page) \ { return 0; } #define TESTSCFLAG(uname, lname) \ -- cgit v1.2.3 From 9d0ad8ca43ce8023bb834a409c2258bd7197fb05 Mon Sep 17 00:00:00 2001 From: Daniel Kiper Date: Mon, 25 Jul 2011 17:12:05 -0700 Subject: mm: extend memory hotplug API to allow memory hotplug in virtual machines This patch contains online_page_callback and apropriate functions for registering/unregistering online page callbacks. It allows to do some machine specific tasks during online page stage which is required to implement memory hotplug in virtual machines. Currently this patch is required by latest memory hotplug support for Xen balloon driver patch which will be posted soon. Additionally, originial online_page() function was splited into following functions doing "atomic" operations: - __online_page_set_limits() - set new limits for memory management code, - __online_page_increment_counters() - increment totalram_pages and totalhigh_pages, - __online_page_free() - free page to allocator. It was done to: - not duplicate existing code, - ease hotplug code devolpment by usage of well defined interface, - avoid stupid bugs which are unavoidable when the same code (by design) is developed in many places. [akpm@linux-foundation.org: use explicit indirect-call syntax] Signed-off-by: Daniel Kiper Reviewed-by: Konrad Rzeszutek Wilk Cc: Ian Campbell Cc: Jeremy Fitzhardinge Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 8122018d3000..0b8e2a742600 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -68,12 +68,19 @@ static inline void zone_seqlock_init(struct zone *zone) extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages); extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages); extern int add_one_highpage(struct page *page, int pfn, int bad_ppro); -/* need some defines for these for archs that don't support it */ -extern void online_page(struct page *page); /* VM interface that may be used by firmware interface */ extern int online_pages(unsigned long, unsigned long); extern void __offline_isolated_pages(unsigned long, unsigned long); +typedef void (*online_page_callback_t)(struct page *page); + +extern int set_online_page_callback(online_page_callback_t callback); +extern int restore_online_page_callback(online_page_callback_t callback); + +extern void __online_page_set_limits(struct page *page); +extern void __online_page_increment_counters(struct page *page); +extern void __online_page_free(struct page *page); + #ifdef CONFIG_MEMORY_HOTREMOVE extern bool is_pageblock_removable_nolock(struct page *page); #endif /* CONFIG_MEMORY_HOTREMOVE */ -- cgit v1.2.3 From c27fe4c8942d3ca715986f79cc26f44608d7d9fb Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Mon, 25 Jul 2011 17:12:10 -0700 Subject: pagewalk: add locking-rule comments Originally, walk_hugetlb_range() didn't require a caller take any lock. But commit d33b9f45bd ("mm: hugetlb: fix hugepage memory leak in walk_page_range") changed its rule. Because it added find_vma() call in walk_hugetlb_range(). Any locking-rule change commit should write a doc too. [akpm@linux-foundation.org: clarify comment] Signed-off-by: KOSAKI Motohiro Cc: Naoya Horiguchi Cc: Hiroyuki Kamezawa Cc: Andrea Arcangeli Cc: Matt Mackall Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 6321e840e21d..3c5505a3bc49 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -911,6 +911,8 @@ unsigned long unmap_vmas(struct mmu_gather *tlb, * @pte_entry: if set, called for each non-empty PTE (4th-level) entry * @pte_hole: if set, called for each hole at all levels * @hugetlb_entry: if set, called for each hugetlb entry + * *Caution*: The caller must hold mmap_sem() if @hugetlb_entry + * is used. * * (see walk_page_range for more details) */ -- cgit v1.2.3 From 11239836c04b50ba8453ec58ca7a7bd716ef02c1 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Mon, 25 Jul 2011 17:12:17 -0700 Subject: oom: remove references to old badness() function The badness() function in the oom killer was renamed to oom_badness() in a63d83f427fb ("oom: badness heuristic rewrite") since it is a globally exported function for clarity. The prototype for the old function still existed in linux/oom.h, so remove it. There are no existing users. Also fixes documentation and comment references to badness() and adjusts them accordingly. Signed-off-by: David Rientjes Reviewed-by: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/oom.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/oom.h b/include/linux/oom.h index 4952fb874ad3..13b7b02e599a 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -64,10 +64,6 @@ static inline void oom_killer_enable(void) oom_killer_disabled = false; } -/* The badness from the OOM killer */ -extern unsigned long badness(struct task_struct *p, struct mem_cgroup *mem, - const nodemask_t *nodemask, unsigned long uptime); - extern struct task_struct *find_lock_task_mm(struct task_struct *p); /* sysctls */ -- cgit v1.2.3 From c9d8c3d0896bfa5b57531ecc41a85ffbc6d87dbe Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Mon, 25 Jul 2011 17:12:18 -0700 Subject: mm/memblock.c: avoid abuse of RED_INACTIVE RED_INACTIVE is a slab thing, and reusing it for memblock was inappropriate, because memblock is dealing with phys_addr_t's which have a Kconfigurable sizeof(). Create a new poison type for this application. Fixes the sparse warning warning: cast truncates bits from constant value (9f911029d74e35b becomes 9d74e35b) Reported-by: H Hartley Sweeten Tested-by: H Hartley Sweeten Acked-by: Pekka Enberg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/poison.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/poison.h b/include/linux/poison.h index 2110a81c5e2a..79159de0e341 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -40,6 +40,12 @@ #define RED_INACTIVE 0x09F911029D74E35BULL /* when obj is inactive */ #define RED_ACTIVE 0xD84156C5635688C0ULL /* when obj is active */ +#ifdef CONFIG_PHYS_ADDR_T_64BIT +#define MEMBLOCK_INACTIVE 0x3a84fb0144c9e71bULL +#else +#define MEMBLOCK_INACTIVE 0x44c9e71bUL +#endif + #define SLUB_RED_INACTIVE 0xbb #define SLUB_RED_ACTIVE 0xcc -- cgit v1.2.3 From 5e5358e7cf48aa079b8761a7d806ad536023745c Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 25 Jul 2011 17:12:23 -0700 Subject: mm: cleanup descriptions of filler arg The often-NULL data arg to read_cache_page() and read_mapping_page() functions is misdescribed as "destination for read data": no, it's the first arg to the filler function, often struct file * to ->readpage(). Satisfy checkpatch.pl on those filler prototypes, and tidy up the declarations in linux/pagemap.h. Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 8e38d4c140ff..cfaaa6949b8b 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -255,26 +255,24 @@ static inline struct page *grab_cache_page(struct address_space *mapping, extern struct page * grab_cache_page_nowait(struct address_space *mapping, pgoff_t index); extern struct page * read_cache_page_async(struct address_space *mapping, - pgoff_t index, filler_t *filler, - void *data); + pgoff_t index, filler_t *filler, void *data); extern struct page * read_cache_page(struct address_space *mapping, - pgoff_t index, filler_t *filler, - void *data); + pgoff_t index, filler_t *filler, void *data); extern struct page * read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); extern int read_cache_pages(struct address_space *mapping, struct list_head *pages, filler_t *filler, void *data); static inline struct page *read_mapping_page_async( - struct address_space *mapping, - pgoff_t index, void *data) + struct address_space *mapping, + pgoff_t index, void *data) { filler_t *filler = (filler_t *)mapping->a_ops->readpage; return read_cache_page_async(mapping, index, filler, data); } static inline struct page *read_mapping_page(struct address_space *mapping, - pgoff_t index, void *data) + pgoff_t index, void *data) { filler_t *filler = (filler_t *)mapping->a_ops->readpage; return read_cache_page(mapping, index, filler, data); -- cgit v1.2.3 From 85821aab39b3403a8b5731812a930b78684d1642 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 25 Jul 2011 17:12:23 -0700 Subject: mm: truncate functions are in truncate.c Correct comment on truncate_inode_pages*() in linux/mm.h; and remove declaration of page_unuse(), it didn't exist even in 2.2.26 or 2.4.0! Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3c5505a3bc49..3cccd053850f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1411,8 +1411,7 @@ extern int do_munmap(struct mm_struct *, unsigned long, size_t); extern unsigned long do_brk(unsigned long, unsigned long); -/* filemap.c */ -extern unsigned long page_unuse(struct page *); +/* truncate.c */ extern void truncate_inode_pages(struct address_space *, loff_t); extern void truncate_inode_pages_range(struct address_space *, loff_t lstart, loff_t lend); -- cgit v1.2.3 From 2efaca927f5cd7ecd0f1554b8f9b6a9a2c329c03 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 25 Jul 2011 17:12:32 -0700 Subject: mm/futex: fix futex writes on archs with SW tracking of dirty & young I haven't reproduced it myself but the fail scenario is that on such machines (notably ARM and some embedded powerpc), if you manage to hit that futex path on a writable page whose dirty bit has gone from the PTE, you'll livelock inside the kernel from what I can tell. It will go in a loop of trying the atomic access, failing, trying gup to "fix it up", getting succcess from gup, go back to the atomic access, failing again because dirty wasn't fixed etc... So I think you essentially hang in the kernel. The scenario is probably rare'ish because affected architecture are embedded and tend to not swap much (if at all) so we probably rarely hit the case where dirty is missing or young is missing, but I think Shan has a piece of SW that can reliably reproduce it using a shared writable mapping & fork or something like that. On archs who use SW tracking of dirty & young, a page without dirty is effectively mapped read-only and a page without young unaccessible in the PTE. Additionally, some architectures might lazily flush the TLB when relaxing write protection (by doing only a local flush), and expect a fault to invalidate the stale entry if it's still present on another processor. The futex code assumes that if the "in_atomic()" access -EFAULT's, it can "fix it up" by causing get_user_pages() which would then be equivalent to taking the fault. However that isn't the case. get_user_pages() will not call handle_mm_fault() in the case where the PTE seems to have the right permissions, regardless of the dirty and young state. It will eventually update those bits ... in the struct page, but not in the PTE. Additionally, it will not handle the lazy TLB flushing that can be required by some architectures in the fault case. Basically, gup is the wrong interface for the job. The patch provides a more appropriate one which boils down to just calling handle_mm_fault() since what we are trying to do is simulate a real page fault. The futex code currently attempts to write to user memory within a pagefault disabled section, and if that fails, tries to fix it up using get_user_pages(). This doesn't work on archs where the dirty and young bits are maintained by software, since they will gate access permission in the TLB, and will not be updated by gup(). In addition, there's an expectation on some archs that a spurious write fault triggers a local TLB flush, and that is missing from the picture as well. I decided that adding those "features" to gup() would be too much for this already too complex function, and instead added a new simpler fixup_user_fault() which is essentially a wrapper around handle_mm_fault() which the futex code can call. [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix some nits Darren saw, fiddle comment layout] Signed-off-by: Benjamin Herrenschmidt Reported-by: Shan Hai Tested-by: Shan Hai Cc: David Laight Acked-by: Peter Zijlstra Cc: Darren Hart Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3cccd053850f..3172a1c0f08e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -988,6 +988,8 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, int get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages); struct page *get_dump_page(unsigned long addr); +extern int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, + unsigned long address, unsigned int fault_flags); extern int try_to_release_page(struct page * page, gfp_t gfp_mask); extern void do_invalidatepage(struct page *page, unsigned long offset); -- cgit v1.2.3 From 708e3508c2a2204cc276dcdb543009a441bfe91b Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 25 Jul 2011 17:12:32 -0700 Subject: tmpfs: clone shmem_file_splice_read() Copy __generic_file_splice_read() and generic_file_splice_read() from fs/splice.c to shmem_file_splice_read() in mm/shmem.c. Make page_cache_pipe_buf_ops and spd_release_page() accessible to it. Signed-off-by: Hugh Dickins Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/splice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/splice.h b/include/linux/splice.h index 997c3b4c212b..26e5b613deda 100644 --- a/include/linux/splice.h +++ b/include/linux/splice.h @@ -88,5 +88,7 @@ extern ssize_t splice_direct_to_actor(struct file *, struct splice_desc *, extern int splice_grow_spd(struct pipe_inode_info *, struct splice_pipe_desc *); extern void splice_shrink_spd(struct pipe_inode_info *, struct splice_pipe_desc *); +extern void spd_release_page(struct splice_pipe_desc *, unsigned int); +extern const struct pipe_buf_operations page_cache_pipe_buf_ops; #endif -- cgit v1.2.3 From a0e44d4a7a3935afe425ec8dd1a5b63895e1f9c3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 25 Jul 2011 17:13:00 -0700 Subject: include/linux/ioport.h: new helper to define common struct resource constructs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Resource definitions that just define start, end and flags = IORESOURCE_MEM or IORESOURCE_IRQ (with start=end) are quite common. So introduce a shortcut for them. For completeness add macros for IORESOURCE_DMA and IORESOURCE_IO, too and also make available a set of macros to specify named resources of all types which are less common. Signed-off-by: Uwe Kleine-König Cc: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ioport.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index e9bb22cba764..c2ebfe66177c 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -109,6 +109,36 @@ struct resource_list { /* PCI control bits. Shares IORESOURCE_BITS with above PCI ROM. */ #define IORESOURCE_PCI_FIXED (1<<4) /* Do not move resource */ + +/* helpers to define resources */ +#define DEFINE_RES_NAMED(_start, _size, _name, _flags) \ + { \ + .start = (_start), \ + .end = (_start) + (_size) - 1, \ + .name = (_name), \ + .flags = (_flags), \ + } + +#define DEFINE_RES_IO_NAMED(_start, _size, _name) \ + DEFINE_RES_NAMED((_start), (_size), (_name), IORESOURCE_IO) +#define DEFINE_RES_IO(_start, _size) \ + DEFINE_RES_IO_NAMED((_start), (_size), NULL) + +#define DEFINE_RES_MEM_NAMED(_start, _size, _name) \ + DEFINE_RES_NAMED((_start), (_size), (_name), IORESOURCE_MEM) +#define DEFINE_RES_MEM(_start, _size) \ + DEFINE_RES_MEM_NAMED((_start), (_size), NULL) + +#define DEFINE_RES_IRQ_NAMED(_irq, _name) \ + DEFINE_RES_NAMED((_irq), 1, (_name), IORESOURCE_IRQ) +#define DEFINE_RES_IRQ(_irq) \ + DEFINE_RES_IRQ_NAMED((_irq), NULL) + +#define DEFINE_RES_DMA_NAMED(_dma, _name) \ + DEFINE_RES_NAMED((_dma), 1, (_name), IORESOURCE_DMA) +#define DEFINE_RES_DMA(_dma) \ + DEFINE_RES_DMA_NAMED((_dma), NULL) + /* PC/ISA/whatever - the normal PC address spaces: IO and memory */ extern struct resource ioport_resource; extern struct resource iomem_resource; -- cgit v1.2.3 From 9d00f92f437f0ff682876cab9f2d94cf3b6e5d17 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Mon, 25 Jul 2011 17:13:02 -0700 Subject: include/linux/kernel.h: fix a headers_check warning Fix the warning: usr/include/linux/kernel.h:65: userspace cannot reference function or variable defined in the kernel As Michal noted, BUILD_BUG_ON stuffs should be moved under #ifdef __KERNEL__. Signed-off-by: WANG Cong Cc: Michal Marek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 47 ++++++++++++++++++++++++----------------------- 1 file changed, 24 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 567a6f7bbeed..bf66f068368b 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -646,29 +646,6 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } const typeof( ((type *)0)->member ) *__mptr = (ptr); \ (type *)( (char *)__mptr - offsetof(type,member) );}) -struct sysinfo; -extern int do_sysinfo(struct sysinfo *info); - -#endif /* __KERNEL__ */ - -#define SI_LOAD_SHIFT 16 -struct sysinfo { - long uptime; /* Seconds since boot */ - unsigned long loads[3]; /* 1, 5, and 15 minute load averages */ - unsigned long totalram; /* Total usable main memory size */ - unsigned long freeram; /* Available memory size */ - unsigned long sharedram; /* Amount of shared memory */ - unsigned long bufferram; /* Memory used by buffers */ - unsigned long totalswap; /* Total swap space size */ - unsigned long freeswap; /* swap space still available */ - unsigned short procs; /* Number of current processes */ - unsigned short pad; /* explicit padding for m68k */ - unsigned long totalhigh; /* Total high memory size */ - unsigned long freehigh; /* Available high memory size */ - unsigned int mem_unit; /* Memory unit size in bytes */ - char _f[20-2*sizeof(long)-sizeof(int)]; /* Padding: libc5 uses this.. */ -}; - #ifdef __CHECKER__ #define BUILD_BUG_ON_NOT_POWER_OF_2(n) #define BUILD_BUG_ON_ZERO(e) (0) @@ -714,6 +691,30 @@ extern int __build_bug_on_failed; #endif #endif /* __CHECKER__ */ + +struct sysinfo; +extern int do_sysinfo(struct sysinfo *info); + +#endif /* __KERNEL__ */ + +#define SI_LOAD_SHIFT 16 +struct sysinfo { + long uptime; /* Seconds since boot */ + unsigned long loads[3]; /* 1, 5, and 15 minute load averages */ + unsigned long totalram; /* Total usable main memory size */ + unsigned long freeram; /* Available memory size */ + unsigned long sharedram; /* Amount of shared memory */ + unsigned long bufferram; /* Memory used by buffers */ + unsigned long totalswap; /* Total swap space size */ + unsigned long freeswap; /* swap space still available */ + unsigned short procs; /* Number of current processes */ + unsigned short pad; /* explicit padding for m68k */ + unsigned long totalhigh; /* Total high memory size */ + unsigned long freehigh; /* Available high memory size */ + unsigned int mem_unit; /* Memory unit size in bytes */ + char _f[20-2*sizeof(long)-sizeof(int)]; /* Padding: libc5 uses this.. */ +}; + /* Trap pasters of __FUNCTION__ at compile-time */ #define __FUNCTION__ (__func__) -- cgit v1.2.3 From b9d4f426689765d1e066913f6872c8d59e0f2ac9 Mon Sep 17 00:00:00 2001 From: Arnaud Lacombe Date: Mon, 25 Jul 2011 17:13:03 -0700 Subject: include/linux/kernel.h: hide internal macros from userspace Unexpose to userland the following macros - __FUNCTION__ - NUMA_BUILD - COMPACTION_BUILD - REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD Signed-off-by: Arnaud Lacombe Cc: Rusty Russell Cc: KOSAKI Motohiro Cc: Christoph Lameter Cc: Mel Gorman Cc: Steven Rostedt Acked-by: WANG Cong Cc: Michal Marek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 43 +++++++++++++++++++++---------------------- 1 file changed, 21 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index bf66f068368b..9a43ad792cfc 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -691,6 +691,27 @@ extern int __build_bug_on_failed; #endif #endif /* __CHECKER__ */ +/* Trap pasters of __FUNCTION__ at compile-time */ +#define __FUNCTION__ (__func__) + +/* This helps us to avoid #ifdef CONFIG_NUMA */ +#ifdef CONFIG_NUMA +#define NUMA_BUILD 1 +#else +#define NUMA_BUILD 0 +#endif + +/* This helps us avoid #ifdef CONFIG_COMPACTION */ +#ifdef CONFIG_COMPACTION +#define COMPACTION_BUILD 1 +#else +#define COMPACTION_BUILD 0 +#endif + +/* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */ +#ifdef CONFIG_FTRACE_MCOUNT_RECORD +# define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD +#endif struct sysinfo; extern int do_sysinfo(struct sysinfo *info); @@ -715,26 +736,4 @@ struct sysinfo { char _f[20-2*sizeof(long)-sizeof(int)]; /* Padding: libc5 uses this.. */ }; -/* Trap pasters of __FUNCTION__ at compile-time */ -#define __FUNCTION__ (__func__) - -/* This helps us to avoid #ifdef CONFIG_NUMA */ -#ifdef CONFIG_NUMA -#define NUMA_BUILD 1 -#else -#define NUMA_BUILD 0 -#endif - -/* This helps us avoid #ifdef CONFIG_COMPACTION */ -#ifdef CONFIG_COMPACTION -#define COMPACTION_BUILD 1 -#else -#define COMPACTION_BUILD 0 -#endif - -/* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */ -#ifdef CONFIG_FTRACE_MCOUNT_RECORD -# define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD -#endif - #endif -- cgit v1.2.3 From a1bb73d76bc814e9385390e6aa9880d884322e2e Mon Sep 17 00:00:00 2001 From: Donggeun Kim Date: Mon, 25 Jul 2011 17:13:07 -0700 Subject: drivers/misc: add support the FSA9480 USB Switch The FSA9480 is a USB port accessory detector and switch. This patch adds support the FSA9480 USB Switch. [akpm@linux-foundation.org: make a couple of things static] Signed-off-by: Donggeun Kim Signed-off-by: Minkyu Kang Signed-off-by: Kyungmin Park Cc: Greg KH Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/platform_data/fsa9480.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) create mode 100644 include/linux/platform_data/fsa9480.h (limited to 'include/linux') diff --git a/include/linux/platform_data/fsa9480.h b/include/linux/platform_data/fsa9480.h new file mode 100644 index 000000000000..72dddcb4bed1 --- /dev/null +++ b/include/linux/platform_data/fsa9480.h @@ -0,0 +1,27 @@ +/* + * Copyright (C) 2010 Samsung Electronics + * Minkyu Kang + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _FSA9480_H_ +#define _FSA9480_H_ + +#define FSA9480_ATTACHED 1 +#define FSA9480_DETACHED 0 + +struct fsa9480_platform_data { + void (*cfg_gpio) (void); + void (*usb_cb) (u8 attached); + void (*uart_cb) (u8 attached); + void (*charger_cb) (u8 attached); + void (*jig_cb) (u8 attached); + void (*reset_cb) (void); + void (*usb_power) (u8 on); + int wakeup; +}; + +#endif /* _FSA9480_H_ */ -- cgit v1.2.3 From 80f1ff97d0a9d92f44d2b2dd9425afa950e58f2b Mon Sep 17 00:00:00 2001 From: Amerigo Wang Date: Mon, 25 Jul 2011 17:13:08 -0700 Subject: notifiers: cpu: move cpu notifiers into cpu.h We presently define all kinds of notifiers in notifier.h. This is not necessary at all, since different subsystems use different notifiers, they are almost non-related with each other. This can also save much build time. Suppose I add a new netdevice event, really I don't have to recompile all the source, just network related. Without this patch, all the source will be recompiled. I move the notify events near to their subsystem notifier registers, so that they can be found more easily. This patch: It is not necessary to share the same notifier.h. Signed-off-by: WANG Cong Cc: David Miller Cc: "Rafael J. Wysocki" Cc: Greg KH Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpu.h | 33 +++++++++++++++++++++++++++++++++ include/linux/notifier.h | 34 ++-------------------------------- 2 files changed, 35 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 5f09323ee880..b1a635acf72a 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -70,6 +70,39 @@ enum { CPU_PRI_WORKQUEUE = 5, }; +#define CPU_ONLINE 0x0002 /* CPU (unsigned)v is up */ +#define CPU_UP_PREPARE 0x0003 /* CPU (unsigned)v coming up */ +#define CPU_UP_CANCELED 0x0004 /* CPU (unsigned)v NOT coming up */ +#define CPU_DOWN_PREPARE 0x0005 /* CPU (unsigned)v going down */ +#define CPU_DOWN_FAILED 0x0006 /* CPU (unsigned)v NOT going down */ +#define CPU_DEAD 0x0007 /* CPU (unsigned)v dead */ +#define CPU_DYING 0x0008 /* CPU (unsigned)v not running any task, + * not handling interrupts, soon dead. + * Called on the dying cpu, interrupts + * are already disabled. Must not + * sleep, must not fail */ +#define CPU_POST_DEAD 0x0009 /* CPU (unsigned)v dead, cpu_hotplug + * lock is dropped */ +#define CPU_STARTING 0x000A /* CPU (unsigned)v soon running. + * Called on the new cpu, just before + * enabling interrupts. Must not sleep, + * must not fail */ + +/* Used for CPU hotplug events occurring while tasks are frozen due to a suspend + * operation in progress + */ +#define CPU_TASKS_FROZEN 0x0010 + +#define CPU_ONLINE_FROZEN (CPU_ONLINE | CPU_TASKS_FROZEN) +#define CPU_UP_PREPARE_FROZEN (CPU_UP_PREPARE | CPU_TASKS_FROZEN) +#define CPU_UP_CANCELED_FROZEN (CPU_UP_CANCELED | CPU_TASKS_FROZEN) +#define CPU_DOWN_PREPARE_FROZEN (CPU_DOWN_PREPARE | CPU_TASKS_FROZEN) +#define CPU_DOWN_FAILED_FROZEN (CPU_DOWN_FAILED | CPU_TASKS_FROZEN) +#define CPU_DEAD_FROZEN (CPU_DEAD | CPU_TASKS_FROZEN) +#define CPU_DYING_FROZEN (CPU_DYING | CPU_TASKS_FROZEN) +#define CPU_STARTING_FROZEN (CPU_STARTING | CPU_TASKS_FROZEN) + + #ifdef CONFIG_SMP /* Need to know about CPUs going up/down? */ #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) diff --git a/include/linux/notifier.h b/include/linux/notifier.h index c0688b0168b3..9eb25fc0145b 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -185,6 +185,8 @@ static inline int notifier_to_errno(int ret) * VC switch chains (for loadable kernel svgalib VC switch helpers) etc... */ +/* CPU notfiers are defined in include/linux/cpu.h. */ + /* netdevice notifier chain. Please remember to update the rtnetlink * notification exclusion list in rtnetlink_event() when adding new * types. @@ -220,38 +222,6 @@ static inline int notifier_to_errno(int ret) #define NETLINK_URELEASE 0x0001 /* Unicast netlink socket released */ -#define CPU_ONLINE 0x0002 /* CPU (unsigned)v is up */ -#define CPU_UP_PREPARE 0x0003 /* CPU (unsigned)v coming up */ -#define CPU_UP_CANCELED 0x0004 /* CPU (unsigned)v NOT coming up */ -#define CPU_DOWN_PREPARE 0x0005 /* CPU (unsigned)v going down */ -#define CPU_DOWN_FAILED 0x0006 /* CPU (unsigned)v NOT going down */ -#define CPU_DEAD 0x0007 /* CPU (unsigned)v dead */ -#define CPU_DYING 0x0008 /* CPU (unsigned)v not running any task, - * not handling interrupts, soon dead. - * Called on the dying cpu, interrupts - * are already disabled. Must not - * sleep, must not fail */ -#define CPU_POST_DEAD 0x0009 /* CPU (unsigned)v dead, cpu_hotplug - * lock is dropped */ -#define CPU_STARTING 0x000A /* CPU (unsigned)v soon running. - * Called on the new cpu, just before - * enabling interrupts. Must not sleep, - * must not fail */ - -/* Used for CPU hotplug events occurring while tasks are frozen due to a suspend - * operation in progress - */ -#define CPU_TASKS_FROZEN 0x0010 - -#define CPU_ONLINE_FROZEN (CPU_ONLINE | CPU_TASKS_FROZEN) -#define CPU_UP_PREPARE_FROZEN (CPU_UP_PREPARE | CPU_TASKS_FROZEN) -#define CPU_UP_CANCELED_FROZEN (CPU_UP_CANCELED | CPU_TASKS_FROZEN) -#define CPU_DOWN_PREPARE_FROZEN (CPU_DOWN_PREPARE | CPU_TASKS_FROZEN) -#define CPU_DOWN_FAILED_FROZEN (CPU_DOWN_FAILED | CPU_TASKS_FROZEN) -#define CPU_DEAD_FROZEN (CPU_DEAD | CPU_TASKS_FROZEN) -#define CPU_DYING_FROZEN (CPU_DYING | CPU_TASKS_FROZEN) -#define CPU_STARTING_FROZEN (CPU_STARTING | CPU_TASKS_FROZEN) - /* Hibernation and suspend events */ #define PM_HIBERNATION_PREPARE 0x0001 /* Going to hibernate */ #define PM_POST_HIBERNATION 0x0002 /* Hibernation finished */ -- cgit v1.2.3 From dcfe1421c916345b068f43749263b94270324500 Mon Sep 17 00:00:00 2001 From: Amerigo Wang Date: Mon, 25 Jul 2011 17:13:09 -0700 Subject: notifiers: net: move netdevice notifiers into netdevice.h It is not necessary to share the same notifier.h. Signed-off-by: WANG Cong Acked-by: David Miller Cc: "Rafael J. Wysocki" Cc: Greg KH Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/netdevice.h | 36 +++++++++++++++++++++++++++++++++--- include/linux/notifier.h | 28 +--------------------------- 2 files changed, 34 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 34f3abc6457a..ea6f4aa479d4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1521,6 +1521,39 @@ struct packet_type { #include +/* netdevice notifier chain. Please remember to update the rtnetlink + * notification exclusion list in rtnetlink_event() when adding new + * types. + */ +#define NETDEV_UP 0x0001 /* For now you can't veto a device up/down */ +#define NETDEV_DOWN 0x0002 +#define NETDEV_REBOOT 0x0003 /* Tell a protocol stack a network interface + detected a hardware crash and restarted + - we can use this eg to kick tcp sessions + once done */ +#define NETDEV_CHANGE 0x0004 /* Notify device state change */ +#define NETDEV_REGISTER 0x0005 +#define NETDEV_UNREGISTER 0x0006 +#define NETDEV_CHANGEMTU 0x0007 +#define NETDEV_CHANGEADDR 0x0008 +#define NETDEV_GOING_DOWN 0x0009 +#define NETDEV_CHANGENAME 0x000A +#define NETDEV_FEAT_CHANGE 0x000B +#define NETDEV_BONDING_FAILOVER 0x000C +#define NETDEV_PRE_UP 0x000D +#define NETDEV_PRE_TYPE_CHANGE 0x000E +#define NETDEV_POST_TYPE_CHANGE 0x000F +#define NETDEV_POST_INIT 0x0010 +#define NETDEV_UNREGISTER_BATCH 0x0011 +#define NETDEV_RELEASE 0x0012 +#define NETDEV_NOTIFY_PEERS 0x0013 +#define NETDEV_JOIN 0x0014 + +extern int register_netdevice_notifier(struct notifier_block *nb); +extern int unregister_netdevice_notifier(struct notifier_block *nb); +extern int call_netdevice_notifiers(unsigned long val, struct net_device *dev); + + extern rwlock_t dev_base_lock; /* Device list lock */ @@ -1603,12 +1636,9 @@ static inline void unregister_netdevice(struct net_device *dev) extern int netdev_refcnt_read(const struct net_device *dev); extern void free_netdev(struct net_device *dev); extern void synchronize_net(void); -extern int register_netdevice_notifier(struct notifier_block *nb); -extern int unregister_netdevice_notifier(struct notifier_block *nb); extern int init_dummy_netdev(struct net_device *dev); extern void netdev_resync_ops(struct net_device *dev); -extern int call_netdevice_notifiers(unsigned long val, struct net_device *dev); extern struct net_device *dev_get_by_index(struct net *net, int ifindex); extern struct net_device *__dev_get_by_index(struct net *net, int ifindex); extern struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); diff --git a/include/linux/notifier.h b/include/linux/notifier.h index 9eb25fc0145b..e8a858a1d391 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -187,33 +187,7 @@ static inline int notifier_to_errno(int ret) /* CPU notfiers are defined in include/linux/cpu.h. */ -/* netdevice notifier chain. Please remember to update the rtnetlink - * notification exclusion list in rtnetlink_event() when adding new - * types. - */ -#define NETDEV_UP 0x0001 /* For now you can't veto a device up/down */ -#define NETDEV_DOWN 0x0002 -#define NETDEV_REBOOT 0x0003 /* Tell a protocol stack a network interface - detected a hardware crash and restarted - - we can use this eg to kick tcp sessions - once done */ -#define NETDEV_CHANGE 0x0004 /* Notify device state change */ -#define NETDEV_REGISTER 0x0005 -#define NETDEV_UNREGISTER 0x0006 -#define NETDEV_CHANGEMTU 0x0007 -#define NETDEV_CHANGEADDR 0x0008 -#define NETDEV_GOING_DOWN 0x0009 -#define NETDEV_CHANGENAME 0x000A -#define NETDEV_FEAT_CHANGE 0x000B -#define NETDEV_BONDING_FAILOVER 0x000C -#define NETDEV_PRE_UP 0x000D -#define NETDEV_PRE_TYPE_CHANGE 0x000E -#define NETDEV_POST_TYPE_CHANGE 0x000F -#define NETDEV_POST_INIT 0x0010 -#define NETDEV_UNREGISTER_BATCH 0x0011 -#define NETDEV_RELEASE 0x0012 -#define NETDEV_NOTIFY_PEERS 0x0013 -#define NETDEV_JOIN 0x0014 +/* netdevice notifiers are defined in include/linux/netdevice.h */ #define SYS_DOWN 0x0001 /* Notify of system down */ #define SYS_RESTART SYS_DOWN -- cgit v1.2.3 From c5f41752fd37979dbaec61dc59c7ece0606ddf7e Mon Sep 17 00:00:00 2001 From: Amerigo Wang Date: Mon, 25 Jul 2011 17:13:10 -0700 Subject: notifiers: sys: move reboot notifiers into reboot.h It is not necessary to share the same notifier.h. This patch already moves register_reboot_notifier() and unregister_reboot_notifier() from kernel/notifier.c to kernel/sys.c. [amwang@redhat.com: make allyesconfig succeed on ppc64] Signed-off-by: WANG Cong Cc: David Miller Cc: "Rafael J. Wysocki" Cc: Greg KH Signed-off-by: WANG Cong Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/notifier.h | 5 +---- include/linux/reboot.h | 5 +++++ 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/notifier.h b/include/linux/notifier.h index e8a858a1d391..145c43658db0 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -189,10 +189,7 @@ static inline int notifier_to_errno(int ret) /* netdevice notifiers are defined in include/linux/netdevice.h */ -#define SYS_DOWN 0x0001 /* Notify of system down */ -#define SYS_RESTART SYS_DOWN -#define SYS_HALT 0x0002 /* Notify of system halt */ -#define SYS_POWER_OFF 0x0003 /* Notify of system power off */ +/* reboot notifiers are defined in include/linux/reboot.h. */ #define NETLINK_URELEASE 0x0001 /* Unicast netlink socket released */ diff --git a/include/linux/reboot.h b/include/linux/reboot.h index 3005d5a7fce5..e0879a70e830 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -39,6 +39,11 @@ #include +#define SYS_DOWN 0x0001 /* Notify of system down */ +#define SYS_RESTART SYS_DOWN +#define SYS_HALT 0x0002 /* Notify of system halt */ +#define SYS_POWER_OFF 0x0003 /* Notify of system power off */ + extern int register_reboot_notifier(struct notifier_block *); extern int unregister_reboot_notifier(struct notifier_block *); -- cgit v1.2.3 From 35eb6db11ed9cbf9702ec90a28779a51fe4a21a9 Mon Sep 17 00:00:00 2001 From: Amerigo Wang Date: Mon, 25 Jul 2011 17:13:11 -0700 Subject: notifiers: pm: move pm notifiers into suspend.h It is not necessary to share the same notifier.h. Signed-off-by: WANG Cong Cc: David Miller Acked-by: "Rafael J. Wysocki" Cc: Greg KH Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/notifier.h | 10 ++-------- include/linux/suspend.h | 8 ++++++++ 2 files changed, 10 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/notifier.h b/include/linux/notifier.h index 145c43658db0..ae8f7d9f8def 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -191,15 +191,9 @@ static inline int notifier_to_errno(int ret) /* reboot notifiers are defined in include/linux/reboot.h. */ -#define NETLINK_URELEASE 0x0001 /* Unicast netlink socket released */ +/* Hibernation and suspend events are defined in include/linux/suspend.h. */ -/* Hibernation and suspend events */ -#define PM_HIBERNATION_PREPARE 0x0001 /* Going to hibernate */ -#define PM_POST_HIBERNATION 0x0002 /* Hibernation finished */ -#define PM_SUSPEND_PREPARE 0x0003 /* Going to suspend the system */ -#define PM_POST_SUSPEND 0x0004 /* Suspend finished */ -#define PM_RESTORE_PREPARE 0x0005 /* Going to restore a saved image */ -#define PM_POST_RESTORE 0x0006 /* Restore failed */ +#define NETLINK_URELEASE 0x0001 /* Unicast netlink socket released */ /* Console keyboard events. * Note: KBD_KEYCODE is always sent before KBD_UNBOUND_KEYCODE, KBD_UNICODE and diff --git a/include/linux/suspend.h b/include/linux/suspend.h index e1e3742733be..6bbcef22e105 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -268,6 +268,14 @@ static inline int hibernate(void) { return -ENOSYS; } static inline bool system_entering_hibernation(void) { return false; } #endif /* CONFIG_HIBERNATION */ +/* Hibernation and suspend events */ +#define PM_HIBERNATION_PREPARE 0x0001 /* Going to hibernate */ +#define PM_POST_HIBERNATION 0x0002 /* Hibernation finished */ +#define PM_SUSPEND_PREPARE 0x0003 /* Going to suspend the system */ +#define PM_POST_SUSPEND 0x0004 /* Suspend finished */ +#define PM_RESTORE_PREPARE 0x0005 /* Going to restore a saved image */ +#define PM_POST_RESTORE 0x0006 /* Restore failed */ + #ifdef CONFIG_PM_SLEEP void save_processor_state(void); void restore_processor_state(void); -- cgit v1.2.3 From a376d3d6727b2f05ef4c6670cc74afbd8110df89 Mon Sep 17 00:00:00 2001 From: Amerigo Wang Date: Mon, 25 Jul 2011 17:13:12 -0700 Subject: notifiers: vt: move vt notifiers into vt.h It is not necessary to share the same notifier.h. Signed-off-by: WANG Cong Cc: David Miller Cc: "Rafael J. Wysocki" Cc: Greg KH Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/notifier.h | 9 ++------- include/linux/vt.h | 7 +++++++ 2 files changed, 9 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/notifier.h b/include/linux/notifier.h index ae8f7d9f8def..d65746efc954 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -193,6 +193,8 @@ static inline int notifier_to_errno(int ret) /* Hibernation and suspend events are defined in include/linux/suspend.h. */ +/* Virtual Terminal events are defined in include/linux/vt.h. */ + #define NETLINK_URELEASE 0x0001 /* Unicast netlink socket released */ /* Console keyboard events. @@ -206,12 +208,5 @@ static inline int notifier_to_errno(int ret) extern struct blocking_notifier_head reboot_notifier_list; -/* Virtual Terminal events. */ -#define VT_ALLOCATE 0x0001 /* Console got allocated */ -#define VT_DEALLOCATE 0x0002 /* Console will be deallocated */ -#define VT_WRITE 0x0003 /* A char got output */ -#define VT_UPDATE 0x0004 /* A bigger update occurred */ -#define VT_PREWRITE 0x0005 /* A char is about to be written to the console */ - #endif /* __KERNEL__ */ #endif /* _LINUX_NOTIFIER_H */ diff --git a/include/linux/vt.h b/include/linux/vt.h index d5dd0bc408fd..30a8dd9c83ff 100644 --- a/include/linux/vt.h +++ b/include/linux/vt.h @@ -86,6 +86,13 @@ struct vt_setactivate { #ifdef __KERNEL__ +/* Virtual Terminal events. */ +#define VT_ALLOCATE 0x0001 /* Console got allocated */ +#define VT_DEALLOCATE 0x0002 /* Console will be deallocated */ +#define VT_WRITE 0x0003 /* A char got output */ +#define VT_UPDATE 0x0004 /* A bigger update occurred */ +#define VT_PREWRITE 0x0005 /* A char is about to be written to the console */ + #ifdef CONFIG_VT_CONSOLE extern int vt_kmsg_redirect(int new); -- cgit v1.2.3 From 40b1445b1b6afc1ddac6ac31f4533277a0fb75dc Mon Sep 17 00:00:00 2001 From: Shreshtha Kumar Sahu Date: Mon, 25 Jul 2011 17:13:17 -0700 Subject: arch/arm/mach-ux500/board-u5500.c: calibrate ALS input voltage Provide the support for auto calibration of ALS Zone boundaries based on min/max ALS input voltage. Signed-off-by: Shreshtha Kumar Sahu Signed-off-by: Linus Walleij Cc: Richard Purdie Cc: Lee Jones Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/led-lm3530.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/led-lm3530.h b/include/linux/led-lm3530.h index 58592fa67d24..8eb12357a110 100644 --- a/include/linux/led-lm3530.h +++ b/include/linux/led-lm3530.h @@ -84,6 +84,8 @@ enum lm3530_als_mode { * @brt_ramp_rise: rate of rise of led current * @als1_resistor_sel: internal resistance from ALS1 input to ground * @als2_resistor_sel: internal resistance from ALS2 input to ground + * @als_vmin: als input voltage calibrated for max brightness in mV + * @als_vmax: als input voltage calibrated for min brightness in mV * @brt_val: brightness value (0-255) */ struct lm3530_platform_data { @@ -101,6 +103,9 @@ struct lm3530_platform_data { u8 als1_resistor_sel; u8 als2_resistor_sel; + u32 als_vmin; + u32 als_vmax; + u8 brt_val; }; -- cgit v1.2.3 From 75fb8f269305fc066c4c6ec6e7232df0c92f434d Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 25 Jul 2011 17:13:20 -0700 Subject: lib: make _tolower() public This function is required by *printf and kstrto* functions that are located in the different modules. This patch makes _tolower() public. However, it's good idea to not use the helper outside of mentioned functions. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Andy Shevchenko Acked-by: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ctype.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ctype.h b/include/linux/ctype.h index a3d6ee0044f9..8acfe312f947 100644 --- a/include/linux/ctype.h +++ b/include/linux/ctype.h @@ -52,4 +52,13 @@ static inline unsigned char __toupper(unsigned char c) #define tolower(c) __tolower(c) #define toupper(c) __toupper(c) +/* + * Fast implementation of tolower() for internal usage. Do not use in your + * code. + */ +static inline char _tolower(const char c) +{ + return c | 0x20; +} + #endif -- cgit v1.2.3 From 06b4501e88ad10f02849a3f9d7408ed6ae15a53f Mon Sep 17 00:00:00 2001 From: Anatolij Gustschin Date: Mon, 25 Jul 2011 17:13:27 -0700 Subject: misc/eeprom: add driver for microwire 93xx46 EEPROMs Add EEPROM driver for 93xx46 chips. It can also be used with spi_gpio driver to access 93xx46 EEPROMs connected over GPIO lines. This driver supports read/write/erase access to the EEPROM chips over sysfs files. [rdunlap@xenotime.net: fix printk format] Signed-off-by: Anatolij Gustschin Cc: Jonathan Cameron Cc: Grant Likely Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/eeprom_93xx46.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) create mode 100644 include/linux/eeprom_93xx46.h (limited to 'include/linux') diff --git a/include/linux/eeprom_93xx46.h b/include/linux/eeprom_93xx46.h new file mode 100644 index 000000000000..06791811e49d --- /dev/null +++ b/include/linux/eeprom_93xx46.h @@ -0,0 +1,18 @@ +/* + * Module: eeprom_93xx46 + * platform description for 93xx46 EEPROMs. + */ + +struct eeprom_93xx46_platform_data { + unsigned char flags; +#define EE_ADDR8 0x01 /* 8 bit addr. cfg */ +#define EE_ADDR16 0x02 /* 16 bit addr. cfg */ +#define EE_READONLY 0x08 /* forbid writing */ + + /* + * optional hooks to control additional logic + * before and after spi transfer. + */ + void (*prepare)(void *); + void (*finish)(void *); +}; -- cgit v1.2.3 From 9a9a54ad7aa2c7420c96c6fd33538f55d81775cb Mon Sep 17 00:00:00 2001 From: Anirudh Ghayal Date: Mon, 25 Jul 2011 17:13:33 -0700 Subject: drivers/rtc: add support for Qualcomm PMIC8xxx RTC Add support for PMIC8xxx based RTC. PMIC8xxx is Qualcomm's power management IC that internally houses an RTC module. This driver communicates with the PMIC module over SSBI bus. [akpm@linux-foundation.org: cosmetic tweaks] Acked-by: Wan ZongShun Reviewed-by: Stephen Boyd Signed-off-by: Anirudh Ghayal Signed-off-by: Ashay Jaiswal Cc: Samuel Ortiz Cc: Wan ZongShun Cc: Alessandro Zummo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mfd/pm8xxx/rtc.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) create mode 100644 include/linux/mfd/pm8xxx/rtc.h (limited to 'include/linux') diff --git a/include/linux/mfd/pm8xxx/rtc.h b/include/linux/mfd/pm8xxx/rtc.h new file mode 100644 index 000000000000..14f1983eaecc --- /dev/null +++ b/include/linux/mfd/pm8xxx/rtc.h @@ -0,0 +1,25 @@ +/* Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __RTC_PM8XXX_H__ +#define __RTC_PM8XXX_H__ + +#define PM8XXX_RTC_DEV_NAME "rtc-pm8xxx" +/** + * struct pm8xxx_rtc_pdata - RTC driver platform data + * @rtc_write_enable: variable stating RTC write capability + */ +struct pm8xxx_rtc_platform_data { + bool rtc_write_enable; +}; + +#endif /* __RTC_PM8XXX_H__ */ -- cgit v1.2.3 From 0c2fd1bfb155947a821fdaeb3c46aa1cfa20ad64 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Mon, 25 Jul 2011 17:13:37 -0700 Subject: reiserfs: use proper little-endian bitops Using __test_and_{set,clear}_bit_le() with ignoring its return value can be replaced with __{set,clear}_bit_le(). This introduces reiserfs_{set,clear}_le_bit for __{set,clear}_bit_le and does the above change with them. Signed-off-by: Akinobu Mita Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index eca75df00fed..96d465f8d3e6 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -2332,7 +2332,9 @@ __u32 keyed_hash(const signed char *msg, int len); __u32 yura_hash(const signed char *msg, int len); __u32 r5_hash(const signed char *msg, int len); +#define reiserfs_set_le_bit __set_bit_le #define reiserfs_test_and_set_le_bit __test_and_set_bit_le +#define reiserfs_clear_le_bit __clear_bit_le #define reiserfs_test_and_clear_le_bit __test_and_clear_bit_le #define reiserfs_test_le_bit test_bit_le #define reiserfs_find_next_zero_le_bit find_next_zero_bit_le -- cgit v1.2.3 From 36a26c69b4c70396ef569c3452690fba0c1dec08 Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Tue, 26 Jul 2011 00:35:26 -0700 Subject: kernel.h: Add DIV_ROUND_UP_ULL and DIV_ROUND_UP_SECTOR_T macro usage Add new DIV_ROUND_UP_SECTOR_T macro usage for 32-bit architectures requiring a new DIV_ROUND_UP_ULL, and existing 64-bit usage with DIV_ROUND_UP. Reported-by: Linus Torvalds Reported-by: Andrew Morton Signed-off-by: Nicholas A. Bellinger --- include/linux/kernel.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 567a6f7bbeed..2642497c36fb 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -56,6 +56,14 @@ #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) #define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) +#define DIV_ROUND_UP_ULL(ll,d) \ + ({ unsigned long long _tmp = (ll)+(d)-1; do_div(_tmp, d); _tmp; }) + +#if BITS_PER_LONG == 32 +# define DIV_ROUND_UP_SECTOR_T(ll,d) DIV_ROUND_UP_ULL(ll, d) +#else +# define DIV_ROUND_UP_SECTOR_T(ll,d) DIV_ROUND_UP(ll,d) +#endif /* The `const' in roundup() prevents gcc-3.3 from calling __divdi3 */ #define roundup(x, y) ( \ -- cgit v1.2.3 From b207b4d02beb06059478339bbe4672ba715605d6 Mon Sep 17 00:00:00 2001 From: Russell King - ARM Linux Date: Thu, 21 Jul 2011 17:12:27 +0100 Subject: DMA: PL08x: separately store source/destination slave address Store the source/destination slave address separately into the channel structure. This moves us towards being able to avoid a configuration call each time we use the channel. Acked-by: Linus Walleij Signed-off-by: Russell King Signed-off-by: Vinod Koul --- include/linux/amba/pl08x.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h index 3111385b8ca7..072ab28bbb57 100644 --- a/include/linux/amba/pl08x.h +++ b/include/linux/amba/pl08x.h @@ -173,7 +173,8 @@ struct pl08x_dma_chan { struct tasklet_struct tasklet; char *name; struct pl08x_channel_data *cd; - dma_addr_t runtime_addr; + dma_addr_t src_addr; + dma_addr_t dst_addr; enum dma_data_direction runtime_direction; dma_cookie_t lc; struct list_head pend_list; -- cgit v1.2.3 From f14c426c723634d223344ad820997d92a3e355b6 Mon Sep 17 00:00:00 2001 From: Russell King - ARM Linux Date: Thu, 21 Jul 2011 17:12:47 +0100 Subject: DMA: PL08x: separately store source/destination cctl Store the source/destination cctl values into the channel structure. This moves us towards being able to avoid a configuration call each time we use the channel. Acked-by: Linus Walleij Signed-off-by: Russell King Signed-off-by: Vinod Koul --- include/linux/amba/pl08x.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h index 072ab28bbb57..47cfe31e5c35 100644 --- a/include/linux/amba/pl08x.h +++ b/include/linux/amba/pl08x.h @@ -175,6 +175,8 @@ struct pl08x_dma_chan { struct pl08x_channel_data *cd; dma_addr_t src_addr; dma_addr_t dst_addr; + u32 src_cctl; + u32 dst_cctl; enum dma_data_direction runtime_direction; dma_cookie_t lc; struct list_head pend_list; -- cgit v1.2.3 From fa020e7d046436cb6642b23dc95012a3064d77e2 Mon Sep 17 00:00:00 2001 From: Russell King - ARM Linux Date: Thu, 21 Jul 2011 17:13:07 +0100 Subject: DMA: PL08x: constify plchan->cd and plat->slave_channels We no longer write to the channel data structure, so we can make it const throughout the driver. Acked-by: Linus Walleij Signed-off-by: Russell King Signed-off-by: Vinod Koul --- include/linux/amba/pl08x.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h index 47cfe31e5c35..e6e28f37d8ec 100644 --- a/include/linux/amba/pl08x.h +++ b/include/linux/amba/pl08x.h @@ -172,7 +172,7 @@ struct pl08x_dma_chan { int phychan_hold; struct tasklet_struct tasklet; char *name; - struct pl08x_channel_data *cd; + const struct pl08x_channel_data *cd; dma_addr_t src_addr; dma_addr_t dst_addr; u32 src_cctl; @@ -205,7 +205,7 @@ struct pl08x_dma_chan { * @mem_buses: buses which memory can be accessed from: PL08X_AHB1 | PL08X_AHB2 */ struct pl08x_platform_data { - struct pl08x_channel_data *slave_channels; + const struct pl08x_channel_data *slave_channels; unsigned int num_slave_channels; struct pl08x_channel_data memcpy_channel; int (*get_signal)(struct pl08x_dma_chan *); -- cgit v1.2.3 From a209dfc7b0d94bd6fa94553c097836a2e6d0f0ba Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 26 Jul 2011 11:36:34 +0200 Subject: vfs: dont chain pipe/anon/socket on superblock s_inodes list Workloads using pipes and sockets hit inode_sb_list_lock contention. superblock s_inodes list is needed for quota, dirty, pagecache and fsnotify management. pipe/anon/socket fs are clearly not candidates for these. Signed-off-by: Eric Dumazet Reviewed-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index a6658043258a..cc363fa7bb82 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2310,7 +2310,8 @@ extern void __iget(struct inode * inode); extern void iget_failed(struct inode *); extern void end_writeback(struct inode *); extern void __destroy_inode(struct inode *); -extern struct inode *new_inode(struct super_block *); +extern struct inode *new_inode_pseudo(struct super_block *sb); +extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); extern int should_remove_suid(struct dentry *); extern int file_remove_suid(struct file *); -- cgit v1.2.3 From 4cf9d544631c92809cb94ea680c71df56e9437aa Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Tue, 26 Jul 2011 11:27:24 -0700 Subject: libceph: don't time out osd requests that haven't been received Keep track of when an outgoing message is ACKed (i.e., the server fully received it and, presumably, queued it for processing). Time out OSD requests only if it's been too long since they've been received. This prevents timeouts and connection thrashing when the OSDs are simply busy and are throttling the requests they read off the network. Reviewed-by: Yehuda Sadeh Signed-off-by: Sage Weil --- include/linux/ceph/messenger.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 31d91a64838b..d7adf151d335 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -94,6 +94,7 @@ struct ceph_msg { bool more_to_follow; bool needs_out_seq; int front_max; + unsigned long ack_stamp; /* tx: when we were acked */ struct ceph_msgpool *pool; }; -- cgit v1.2.3 From 1f4c025b5a5520fd2571244196b1b01ad96d18f6 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 26 Jul 2011 16:08:21 -0700 Subject: memcg: export memory cgroup's swappiness with mem_cgroup_swappiness() Each memory cgroup has a 'swappiness' value which can be accessed by get_swappiness(memcg). The major user is try_to_free_mem_cgroup_pages() and swappiness is passed by argument. It's propagated by scan_control. get_swappiness() is a static function but some planned updates will need to get swappiness from files other than memcontrol.c This patch exports get_swappiness() as mem_cgroup_swappiness(). With this, we can remove the argument of swapiness from try_to_free... and drop swappiness from scan_control. only memcg uses it. Signed-off-by: KAMEZAWA Hiroyuki Cc: Daisuke Nishimura Cc: Balbir Singh Cc: Michal Hocko Cc: Ying Han Cc: Shaohua Li Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index a273468f8285..44558b600ee3 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -252,11 +252,9 @@ static inline void lru_cache_add_file(struct page *page) extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem, - gfp_t gfp_mask, bool noswap, - unsigned int swappiness); + gfp_t gfp_mask, bool noswap); extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, - unsigned int swappiness, struct zone *zone, unsigned long *nr_scanned); extern int __isolate_lru_page(struct page *page, int mode, int file); @@ -299,7 +297,14 @@ static inline void scan_unevictable_unregister_node(struct node *node) extern int kswapd_run(int nid); extern void kswapd_stop(int nid); - +#ifdef CONFIG_CGROUP_MEM_RES_CTLR +extern int mem_cgroup_swappiness(struct mem_cgroup *mem); +#else +static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) +{ + return vm_swappiness; +} +#endif #ifdef CONFIG_SWAP /* linux/mm/page_io.c */ extern int swap_readpage(struct page *); -- cgit v1.2.3 From bb2a0de92c891b8feeedc0178acb3ae009d899a8 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 26 Jul 2011 16:08:22 -0700 Subject: memcg: consolidate memory cgroup lru stat functions In mm/memcontrol.c, there are many lru stat functions as.. mem_cgroup_zone_nr_lru_pages mem_cgroup_node_nr_file_lru_pages mem_cgroup_nr_file_lru_pages mem_cgroup_node_nr_anon_lru_pages mem_cgroup_nr_anon_lru_pages mem_cgroup_node_nr_unevictable_lru_pages mem_cgroup_nr_unevictable_lru_pages mem_cgroup_node_nr_lru_pages mem_cgroup_nr_lru_pages mem_cgroup_get_local_zonestat Some of them are under #ifdef MAX_NUMNODES >1 and others are not. This seems bad. This patch consolidates all functions into mem_cgroup_zone_nr_lru_pages() mem_cgroup_node_nr_lru_pages() mem_cgroup_nr_lru_pages() For these functions, "which LRU?" information is passed by a mask. example: mem_cgroup_nr_lru_pages(mem, BIT(LRU_ACTIVE_ANON)) And I added some macro as ALL_LRU, ALL_LRU_FILE, ALL_LRU_ANON. example: mem_cgroup_nr_lru_pages(mem, ALL_LRU) BTW, considering layout of NUMA memory placement of counters, this patch seems to be better. Now, when we gather all LRU information, we scan in following orer for_each_lru -> for_each_node -> for_each_zone. This means we'll touch cache lines in different node in turn. After patch, we'll scan for_each_node -> for_each_zone -> for_each_lru(mask) Then, we'll gather information in the same cacheline at once. [akpm@linux-foundation.org: fix warnigns, build error] Signed-off-by: KAMEZAWA Hiroyuki Cc: Daisuke Nishimura Cc: Balbir Singh Cc: Michal Hocko Cc: Ying Han Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 7 +++---- include/linux/mmzone.h | 6 ++++++ 2 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 50940da6adf3..affd5b19b86c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -111,8 +111,7 @@ int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg); int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg); int mem_cgroup_select_victim_node(struct mem_cgroup *memcg); unsigned long mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg, - struct zone *zone, - enum lru_list lru); + int nid, int zid, unsigned int lrumask); struct zone_reclaim_stat *mem_cgroup_get_reclaim_stat(struct mem_cgroup *memcg, struct zone *zone); struct zone_reclaim_stat* @@ -313,8 +312,8 @@ mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg) } static inline unsigned long -mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg, struct zone *zone, - enum lru_list lru) +mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg, int nid, int zid, + unsigned int lru_mask) { return 0; } diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 9f7c3ebcbbad..0a2d3d620feb 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -158,6 +158,12 @@ static inline int is_unevictable_lru(enum lru_list l) return (l == LRU_UNEVICTABLE); } +/* Mask used at gathering information at once (see memcontrol.c) */ +#define LRU_ALL_FILE (BIT(LRU_INACTIVE_FILE) | BIT(LRU_ACTIVE_FILE)) +#define LRU_ALL_ANON (BIT(LRU_INACTIVE_ANON) | BIT(LRU_ACTIVE_ANON)) +#define LRU_ALL_EVICTABLE (LRU_ALL_FILE | LRU_ALL_ANON) +#define LRU_ALL ((1 << NR_LRU_LISTS) - 1) + enum zone_watermarks { WMARK_MIN, WMARK_LOW, -- cgit v1.2.3 From 82f9d486e59f588c7d100865c36510644abda356 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 26 Jul 2011 16:08:26 -0700 Subject: memcg: add memory.vmscan_stat The commit log of 0ae5e89c60c9 ("memcg: count the soft_limit reclaim in...") says it adds scanning stats to memory.stat file. But it doesn't because we considered we needed to make a concensus for such new APIs. This patch is a trial to add memory.scan_stat. This shows - the number of scanned pages(total, anon, file) - the number of rotated pages(total, anon, file) - the number of freed pages(total, anon, file) - the number of elaplsed time (including sleep/pause time) for both of direct/soft reclaim. The biggest difference with oringinal Ying's one is that this file can be reset by some write, as # echo 0 ...../memory.scan_stat Example of output is here. This is a result after make -j 6 kernel under 300M limit. [kamezawa@bluextal ~]$ cat /cgroup/memory/A/memory.scan_stat [kamezawa@bluextal ~]$ cat /cgroup/memory/A/memory.vmscan_stat scanned_pages_by_limit 9471864 scanned_anon_pages_by_limit 6640629 scanned_file_pages_by_limit 2831235 rotated_pages_by_limit 4243974 rotated_anon_pages_by_limit 3971968 rotated_file_pages_by_limit 272006 freed_pages_by_limit 2318492 freed_anon_pages_by_limit 962052 freed_file_pages_by_limit 1356440 elapsed_ns_by_limit 351386416101 scanned_pages_by_system 0 scanned_anon_pages_by_system 0 scanned_file_pages_by_system 0 rotated_pages_by_system 0 rotated_anon_pages_by_system 0 rotated_file_pages_by_system 0 freed_pages_by_system 0 freed_anon_pages_by_system 0 freed_file_pages_by_system 0 elapsed_ns_by_system 0 scanned_pages_by_limit_under_hierarchy 9471864 scanned_anon_pages_by_limit_under_hierarchy 6640629 scanned_file_pages_by_limit_under_hierarchy 2831235 rotated_pages_by_limit_under_hierarchy 4243974 rotated_anon_pages_by_limit_under_hierarchy 3971968 rotated_file_pages_by_limit_under_hierarchy 272006 freed_pages_by_limit_under_hierarchy 2318492 freed_anon_pages_by_limit_under_hierarchy 962052 freed_file_pages_by_limit_under_hierarchy 1356440 elapsed_ns_by_limit_under_hierarchy 351386416101 scanned_pages_by_system_under_hierarchy 0 scanned_anon_pages_by_system_under_hierarchy 0 scanned_file_pages_by_system_under_hierarchy 0 rotated_pages_by_system_under_hierarchy 0 rotated_anon_pages_by_system_under_hierarchy 0 rotated_file_pages_by_system_under_hierarchy 0 freed_pages_by_system_under_hierarchy 0 freed_anon_pages_by_system_under_hierarchy 0 freed_file_pages_by_system_under_hierarchy 0 elapsed_ns_by_system_under_hierarchy 0 total_xxxx is for hierarchy management. This will be useful for further memcg developments and need to be developped before we do some complicated rework on LRU/softlimit management. This patch adds a new struct memcg_scanrecord into scan_control struct. sc->nr_scanned at el is not designed for exporting information. For example, nr_scanned is reset frequentrly and incremented +2 at scanning mapped pages. To avoid complexity, I added a new param in scan_control which is for exporting scanning score. Signed-off-by: KAMEZAWA Hiroyuki Cc: Daisuke Nishimura Cc: Michal Hocko Cc: Ying Han Cc: Andrew Bresticker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 19 +++++++++++++++++++ include/linux/swap.h | 6 ------ 2 files changed, 19 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index affd5b19b86c..b96600786913 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -39,6 +39,16 @@ extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, struct mem_cgroup *mem_cont, int active, int file); +struct memcg_scanrecord { + struct mem_cgroup *mem; /* scanend memory cgroup */ + struct mem_cgroup *root; /* scan target hierarchy root */ + int context; /* scanning context (see memcontrol.c) */ + unsigned long nr_scanned[2]; /* the number of scanned pages */ + unsigned long nr_rotated[2]; /* the number of rotated pages */ + unsigned long nr_freed[2]; /* the number of freed pages */ + unsigned long elapsed; /* nsec of time elapsed while scanning */ +}; + #ifdef CONFIG_CGROUP_MEM_RES_CTLR /* * All "charge" functions with gfp_mask should use GFP_KERNEL or @@ -119,6 +129,15 @@ mem_cgroup_get_reclaim_stat_from_page(struct page *page); extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p); +extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem, + gfp_t gfp_mask, bool noswap, + struct memcg_scanrecord *rec); +extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem, + gfp_t gfp_mask, bool noswap, + struct zone *zone, + struct memcg_scanrecord *rec, + unsigned long *nr_scanned); + #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP extern int do_swap_account; #endif diff --git a/include/linux/swap.h b/include/linux/swap.h index 44558b600ee3..91d5fcc83116 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -251,12 +251,6 @@ static inline void lru_cache_add_file(struct page *page) /* linux/mm/vmscan.c */ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); -extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem, - gfp_t gfp_mask, bool noswap); -extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem, - gfp_t gfp_mask, bool noswap, - struct zone *zone, - unsigned long *nr_scanned); extern int __isolate_lru_page(struct page *page, int mode, int file); extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; -- cgit v1.2.3 From 778d3b0ff0654ad7092bf823fd32010066b12365 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 26 Jul 2011 16:08:30 -0700 Subject: cpusets: randomize node rotor used in cpuset_mem_spread_node() [ This patch has already been accepted as commit 0ac0c0d0f837 but later reverted (commit 35926ff5fba8) because it itroduced arch specific __node_random which was defined only for x86 code so it broke other archs. This is a followup without any arch specific code. Other than that there are no functional changes.] Some workloads that create a large number of small files tend to assign too many pages to node 0 (multi-node systems). Part of the reason is that the rotor (in cpuset_mem_spread_node()) used to assign nodes starts at node 0 for newly created tasks. This patch changes the rotor to be initialized to a random node number of the cpuset. [akpm@linux-foundation.org: fix layout] [Lee.Schermerhorn@hp.com: Define stub numa_random() for !NUMA configuration] [mhocko@suse.cz: Make it arch independent] [akpm@linux-foundation.org: fix CONFIG_NUMA=y, MAX_NUMNODES>1 build] Signed-off-by: Jack Steiner Signed-off-by: Lee Schermerhorn Signed-off-by: Michal Hocko Reviewed-by: KOSAKI Motohiro Cc: Christoph Lameter Cc: Pekka Enberg Cc: Paul Menage Cc: Jack Steiner Cc: Robin Holt Cc: David Rientjes Cc: Christoph Lameter Cc: David Rientjes Cc: Jack Steiner Cc: KOSAKI Motohiro Cc: Lee Schermerhorn Cc: Michal Hocko Cc: Paul Menage Cc: Pekka Enberg Cc: Robin Holt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 1 + include/linux/nodemask.h | 13 +++++++++++++ 2 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index dcafe0bf0005..3bac44cce142 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -144,6 +144,7 @@ extern int bitmap_find_free_region(unsigned long *bitmap, int bits, int order); extern void bitmap_release_region(unsigned long *bitmap, int pos, int order); extern int bitmap_allocate_region(unsigned long *bitmap, int pos, int order); extern void bitmap_copy_le(void *dst, const unsigned long *src, int nbits); +extern int bitmap_ord_to_pos(const unsigned long *bitmap, int n, int bits); #define BITMAP_LAST_WORD_MASK(nbits) \ ( \ diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index dba35e413371..7afc36334d52 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -66,6 +66,8 @@ * int num_online_nodes() Number of online Nodes * int num_possible_nodes() Number of all possible Nodes * + * int node_random(mask) Random node with set bit in mask + * * int node_online(node) Is some node online? * int node_possible(node) Is some node possible? * @@ -430,6 +432,7 @@ static inline void node_set_offline(int nid) node_clear_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); } + #else static inline int node_state(int node, enum node_states state) @@ -460,6 +463,16 @@ static inline int num_node_state(enum node_states state) #define node_set_online(node) node_set_state((node), N_ONLINE) #define node_set_offline(node) node_clear_state((node), N_ONLINE) + +#endif + +#if defined(CONFIG_NUMA) && (MAX_NUMNODES > 1) +extern int node_random(const nodemask_t *maskp); +#else +static inline int node_random(const nodemask_t *mask) +{ + return 0; +} #endif #define node_online_map node_states[N_ONLINE] -- cgit v1.2.3 From a64a26e822ddb739de464540dfd2cbb6abce47d5 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Tue, 26 Jul 2011 16:08:45 -0700 Subject: cpumask: add cpumask_var_t documentation cpumask_var_t has one notable difference from cpumask_t. Add the explanation. Signed-off-by: KOSAKI Motohiro Cc: Thiago Farina Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpumask.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index b24ac56477b4..4f7a63237471 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -617,6 +617,20 @@ static inline size_t cpumask_size(void) * ... use 'tmpmask' like a normal struct cpumask * ... * * free_cpumask_var(tmpmask); + * + * + * However, one notable exception is there. alloc_cpumask_var() allocates + * only nr_cpumask_bits bits (in the other hand, real cpumask_t always has + * NR_CPUS bits). Therefore you don't have to dereference cpumask_var_t. + * + * cpumask_var_t tmpmask; + * if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL)) + * return -ENOMEM; + * + * var = *tmpmask; + * + * This code makes NR_CPUS length memcopy and brings to a memory corruption. + * cpumask_copy() provide safe copy functionality. */ #ifdef CONFIG_CPUMASK_OFFSTACK typedef struct cpumask *cpumask_var_t; -- cgit v1.2.3 From b34a6b1da371ed8af1221459a18c67970f7e3d53 Mon Sep 17 00:00:00 2001 From: Vasiliy Kulikov Date: Tue, 26 Jul 2011 16:08:48 -0700 Subject: ipc: introduce shm_rmid_forced sysctl Add support for the shm_rmid_forced sysctl. If set to 1, all shared memory objects in current ipc namespace will be automatically forced to use IPC_RMID. The POSIX way of handling shmem allows one to create shm objects and call shmdt(), leaving shm object associated with no process, thus consuming memory not counted via rlimits. With shm_rmid_forced=1 the shared memory object is counted at least for one process, so OOM killer may effectively kill the fat process holding the shared memory. It obviously breaks POSIX - some programs relying on the feature would stop working. So set shm_rmid_forced=1 only if you're sure nobody uses "orphaned" memory. Use shm_rmid_forced=0 by default for compatability reasons. The feature was previously impemented in -ow as a configure option. [akpm@linux-foundation.org: fix documentation, per Randy] [akpm@linux-foundation.org: fix warning] [akpm@linux-foundation.org: readability/conventionality tweaks] [akpm@linux-foundation.org: fix shm_rmid_forced/shm_forced_rmid confusion, use standard comment layout] Signed-off-by: Vasiliy Kulikov Cc: Randy Dunlap Cc: "Eric W. Biederman" Cc: "Serge E. Hallyn" Cc: Daniel Lezcano Cc: Oleg Nesterov Cc: Tejun Heo Cc: Ingo Molnar Cc: Alan Cox Cc: Solar Designer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipc_namespace.h | 7 +++++++ include/linux/shm.h | 4 ++++ 2 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index a6d1655f9607..8a297a5e794c 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -44,6 +44,11 @@ struct ipc_namespace { size_t shm_ctlall; int shm_ctlmni; int shm_tot; + /* + * Defines whether IPC_RMID is forced for _all_ shm segments regardless + * of shmctl() + */ + int shm_rmid_forced; struct notifier_block ipcns_nb; @@ -72,6 +77,7 @@ extern int register_ipcns_notifier(struct ipc_namespace *); extern int cond_register_ipcns_notifier(struct ipc_namespace *); extern void unregister_ipcns_notifier(struct ipc_namespace *); extern int ipcns_notify(unsigned long); +extern void shm_destroy_orphaned(struct ipc_namespace *ns); #else /* CONFIG_SYSVIPC */ static inline int register_ipcns_notifier(struct ipc_namespace *ns) { return 0; } @@ -79,6 +85,7 @@ static inline int cond_register_ipcns_notifier(struct ipc_namespace *ns) { return 0; } static inline void unregister_ipcns_notifier(struct ipc_namespace *ns) { } static inline int ipcns_notify(unsigned long l) { return 0; } +static inline void shm_destroy_orphaned(struct ipc_namespace *ns) {} #endif /* CONFIG_SYSVIPC */ #ifdef CONFIG_POSIX_MQUEUE diff --git a/include/linux/shm.h b/include/linux/shm.h index eca6235a46c0..7d27ffde0190 100644 --- a/include/linux/shm.h +++ b/include/linux/shm.h @@ -106,6 +106,7 @@ struct shmid_kernel /* private to the kernel */ #ifdef CONFIG_SYSVIPC long do_shmat(int shmid, char __user *shmaddr, int shmflg, unsigned long *addr); extern int is_file_shm_hugepages(struct file *file); +extern void exit_shm(struct task_struct *task); #else static inline long do_shmat(int shmid, char __user *shmaddr, int shmflg, unsigned long *addr) @@ -116,6 +117,9 @@ static inline int is_file_shm_hugepages(struct file *file) { return 0; } +static inline void exit_shm(struct task_struct *task) +{ +} #endif #endif /* __KERNEL__ */ -- cgit v1.2.3 From 91f6cdf86e8a2bd9b9c292a750179dc2c728a2d4 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Tue, 26 Jul 2011 16:08:50 -0700 Subject: include/linux/dma-mapping.h: remove DMA_xxBIT_MASK macros git grep shows there are no users in tree, so we can remove them safely. Signed-off-by: WANG Cong Acked-by: FUJITA Tomonori Acked-by: Jiri Slaby Acked-by: Vinod Koul Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dma-mapping.h | 21 --------------------- 1 file changed, 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 1a167c48d84d..347fdc32177a 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -46,27 +46,6 @@ struct dma_map_ops { #define DMA_BIT_MASK(n) (((n) == 64) ? ~0ULL : ((1ULL<<(n))-1)) -typedef u64 DMA_nnBIT_MASK __deprecated; - -/* - * NOTE: do not use the below macros in new code and do not add new definitions - * here. - * - * Instead, just open-code DMA_BIT_MASK(n) within your driver - */ -#define DMA_64BIT_MASK (DMA_nnBIT_MASK)DMA_BIT_MASK(64) -#define DMA_48BIT_MASK (DMA_nnBIT_MASK)DMA_BIT_MASK(48) -#define DMA_47BIT_MASK (DMA_nnBIT_MASK)DMA_BIT_MASK(47) -#define DMA_40BIT_MASK (DMA_nnBIT_MASK)DMA_BIT_MASK(40) -#define DMA_39BIT_MASK (DMA_nnBIT_MASK)DMA_BIT_MASK(39) -#define DMA_35BIT_MASK (DMA_nnBIT_MASK)DMA_BIT_MASK(35) -#define DMA_32BIT_MASK (DMA_nnBIT_MASK)DMA_BIT_MASK(32) -#define DMA_31BIT_MASK (DMA_nnBIT_MASK)DMA_BIT_MASK(31) -#define DMA_30BIT_MASK (DMA_nnBIT_MASK)DMA_BIT_MASK(30) -#define DMA_29BIT_MASK (DMA_nnBIT_MASK)DMA_BIT_MASK(29) -#define DMA_28BIT_MASK (DMA_nnBIT_MASK)DMA_BIT_MASK(28) -#define DMA_24BIT_MASK (DMA_nnBIT_MASK)DMA_BIT_MASK(24) - #define DMA_MASK_NONE 0x0ULL static inline int valid_dma_direction(int dma_direction) -- cgit v1.2.3 From c958474b6d721ff09e4abf143efc07365d63aea5 Mon Sep 17 00:00:00 2001 From: Mandeep Singh Baines Date: Tue, 26 Jul 2011 16:08:54 -0700 Subject: panic, vt: do not force oops output when panic_timeout < 0 Don't force output if you intend to reboot immediately. In this patch, I'm disabling the functionality enabled by vc->vc_panic_force_write if panic_timeout < 0 (i.e. no timeout). vc_panic_force_write is only enabled for fb video consoles if the FBINFO_CAN_FORCE_OUTPUT flag is set. For our application, we're using ram_oops to preserved the panic in memory. We want to reliably, and as fast as possible, machine_restart. The vc_panic_force_write flag results in a bunch of graphics driver code to be invoked which slows down restart and decreases reliability. Since we're already storing the panic in RAM and are going to reboot immediately, there is no benefit in mode switching back to the vc in order to display the panic output. The log buffer will get flushed by the console_unblank() call so remote management consoles should see all output. Signed-off-by: Mandeep Singh Baines Cc: Huang Ying Cc: Andi Kleen Cc: Hugh Dickins Cc: Olaf Hering Cc: Jesse Barnes Cc: Dave Airlie Cc: Greg Kroah-Hartman Acked-by: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vt_kern.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index 4d05e14ea60c..c2164fad0083 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -137,7 +137,7 @@ int vty_init(const struct file_operations *console_fops); static inline bool vt_force_oops_output(struct vc_data *vc) { - if (oops_in_progress && vc->vc_panic_force_write) + if (oops_in_progress && vc->vc_panic_force_write && panic_timeout >= 0) return true; return false; } -- cgit v1.2.3 From 6b4d2a2733b9a17112f746d498c9f9a0427dcdd8 Mon Sep 17 00:00:00 2001 From: Sergiu Iordache Date: Tue, 26 Jul 2011 16:08:58 -0700 Subject: ramoops: move dump_oops into platform data The platform driver currently allows setting the mem_size and mem_address. ince dump_oops is also a module parameter it would be more consistent if it could be set through platform data as well. Signed-off-by: Sergiu Iordache Acked-by: Marco Stornelli Cc: "Ahmed S. Darwish" Cc: Artem Bityutskiy Cc: Kyungmin Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ramoops.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ramoops.h b/include/linux/ramoops.h index 0ae68a2c1212..7105c4b3a24e 100644 --- a/include/linux/ramoops.h +++ b/include/linux/ramoops.h @@ -10,6 +10,7 @@ struct ramoops_platform_data { unsigned long mem_size; unsigned long mem_address; + int dump_oops; }; #endif -- cgit v1.2.3 From 3e5c4fadb9943c7539364d0c8425db071a2020e4 Mon Sep 17 00:00:00 2001 From: Sergiu Iordache Date: Tue, 26 Jul 2011 16:08:59 -0700 Subject: ramoops: make record_size a module parameter The size of the dump is currently set using the RECORD_SIZE macro which is set to a page size. This patch makes the record size a module parameter and allows it to be set through platform data as well to allow larger dumps if needed. Signed-off-by: Sergiu Iordache Acked-by: Marco Stornelli Cc: "Ahmed S. Darwish" Cc: Artem Bityutskiy Cc: Kyungmin Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ramoops.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ramoops.h b/include/linux/ramoops.h index 7105c4b3a24e..484fef81cd3a 100644 --- a/include/linux/ramoops.h +++ b/include/linux/ramoops.h @@ -10,6 +10,7 @@ struct ramoops_platform_data { unsigned long mem_size; unsigned long mem_address; + unsigned long record_size; int dump_oops; }; -- cgit v1.2.3 From 6b16f748a0d4546726bb53cad58525adfd6425e9 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Tue, 26 Jul 2011 16:09:00 -0700 Subject: fault-injection: remove nonexistent function extern should_fail_srandom() does not exist. Signed-off-by: Akinobu Mita Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fault-inject.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h index 7b64ad40e4ce..7b72328cc8fe 100644 --- a/include/linux/fault-inject.h +++ b/include/linux/fault-inject.h @@ -57,7 +57,6 @@ struct fault_attr { #define DECLARE_FAULT_ATTR(name) struct fault_attr name = FAULT_ATTR_INITIALIZER int setup_fault_attr(struct fault_attr *attr, char *str); -void should_fail_srandom(unsigned long entropy); bool should_fail(struct fault_attr *attr, ssize_t size); #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS -- cgit v1.2.3 From 7f5ddcc8d3eaccd5e169fda738530f937509645e Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Tue, 26 Jul 2011 16:09:02 -0700 Subject: fault-injection: use debugfs_remove_recursive Use debugfs_remove_recursive() to simplify initialization and deinitialization of fault injection debugfs files. Signed-off-by: Akinobu Mita Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fault-inject.h | 18 +----------------- 1 file changed, 1 insertion(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h index 7b72328cc8fe..a842db638380 100644 --- a/include/linux/fault-inject.h +++ b/include/linux/fault-inject.h @@ -27,23 +27,7 @@ struct fault_attr { unsigned long count; #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS - - struct { - struct dentry *dir; - - struct dentry *probability_file; - struct dentry *interval_file; - struct dentry *times_file; - struct dentry *space_file; - struct dentry *verbose_file; - struct dentry *task_filter_file; - struct dentry *stacktrace_depth_file; - struct dentry *require_start_file; - struct dentry *require_end_file; - struct dentry *reject_start_file; - struct dentry *reject_end_file; - } dentries; - + struct dentry *dir; #endif }; -- cgit v1.2.3 From 60063497a95e716c9a689af3be2687d261f115b4 Mon Sep 17 00:00:00 2001 From: Arun Sharma Date: Tue, 26 Jul 2011 16:09:06 -0700 Subject: atomic: use This allows us to move duplicated code in (atomic_inc_not_zero() for now) to Signed-off-by: Arun Sharma Reviewed-by: Eric Dumazet Cc: Ingo Molnar Cc: David Miller Cc: Eric Dumazet Acked-by: Mike Frysinger Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 2 +- include/linux/atmdev.h | 2 +- include/linux/atomic.h | 9 +++++++++ include/linux/backing-dev.h | 2 +- include/linux/bit_spinlock.h | 2 +- include/linux/buffer_head.h | 2 +- include/linux/configfs.h | 2 +- include/linux/connector.h | 2 +- include/linux/cred.h | 2 +- include/linux/crypto.h | 2 +- include/linux/dcache.h | 2 +- include/linux/debug_locks.h | 2 +- include/linux/device.h | 2 +- include/linux/edac.h | 2 +- include/linux/fault-inject.h | 2 +- include/linux/fdtable.h | 2 +- include/linux/filter.h | 2 +- include/linux/firewire.h | 2 +- include/linux/fsnotify_backend.h | 2 +- include/linux/interrupt.h | 2 +- include/linux/jump_label.h | 2 +- include/linux/kdb.h | 2 +- include/linux/key.h | 2 +- include/linux/kgdb.h | 2 +- include/linux/kobject.h | 2 +- include/linux/mlx4/device.h | 2 +- include/linux/mman.h | 2 +- include/linux/mmzone.h | 2 +- include/linux/mount.h | 2 +- include/linux/mutex.h | 2 +- include/linux/netdevice.h | 2 +- include/linux/nfs_fs_sb.h | 2 +- include/linux/oprofile.h | 2 +- include/linux/pci.h | 2 +- include/linux/perf_event.h | 2 +- include/linux/phy.h | 2 +- include/linux/proc_fs.h | 2 +- include/linux/quota.h | 2 +- include/linux/rwsem.h | 2 +- include/linux/sem.h | 2 +- include/linux/skbuff.h | 2 +- include/linux/sonet.h | 2 +- include/linux/spinlock.h | 2 +- include/linux/sunrpc/auth.h | 2 +- include/linux/sunrpc/cache.h | 2 +- include/linux/sunrpc/timer.h | 2 +- include/linux/swap.h | 2 +- include/linux/sysfs.h | 2 +- include/linux/vmstat.h | 2 +- include/linux/workqueue.h | 2 +- 50 files changed, 58 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index 7a8db4155281..2dcb72bff4b6 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -7,7 +7,7 @@ #include #include -#include +#include #define AIO_MAXSEGS 4 #define AIO_KIOGRP_NR_ATOMIC 8 diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h index 381f4cec8260..49a83ca900ba 100644 --- a/include/linux/atmdev.h +++ b/include/linux/atmdev.h @@ -220,7 +220,7 @@ struct atm_cirange { #include /* struct sk_buff */ #include #include -#include +#include #ifdef CONFIG_PROC_FS #include diff --git a/include/linux/atomic.h b/include/linux/atomic.h index bc6615d4132b..66fed6364122 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -2,6 +2,15 @@ #define _LINUX_ATOMIC_H #include +/** + * atomic_inc_not_zero - increment unless the number is zero + * @v: pointer of type atomic_t + * + * Atomically increments @v by 1, so long as @v is non-zero. + * Returns non-zero if @v was non-zero, and zero otherwise. + */ +#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0) + /** * atomic_inc_not_zero_hint - increment if not null * @v: pointer of type atomic_t diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index a008982e7c08..3b2f9cb82986 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -16,7 +16,7 @@ #include #include #include -#include +#include struct page; struct device; diff --git a/include/linux/bit_spinlock.h b/include/linux/bit_spinlock.h index 564d997e2168..ac4d9f8b52e9 100644 --- a/include/linux/bit_spinlock.h +++ b/include/linux/bit_spinlock.h @@ -3,7 +3,7 @@ #include #include -#include +#include /* * bit-based spin_lock() diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 503c8a6b3079..458f497738a4 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -12,7 +12,7 @@ #include #include #include -#include +#include #ifdef CONFIG_BLOCK diff --git a/include/linux/configfs.h b/include/linux/configfs.h index 645778ad899b..3081c58d696e 100644 --- a/include/linux/configfs.h +++ b/include/linux/configfs.h @@ -42,7 +42,7 @@ #include #include -#include +#include #define CONFIGFS_ITEM_NAME_LEN 20 diff --git a/include/linux/connector.h b/include/linux/connector.h index f696bccd48cb..0c69ad825b39 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -75,7 +75,7 @@ struct cn_msg { #ifdef __KERNEL__ -#include +#include #include #include diff --git a/include/linux/cred.h b/include/linux/cred.h index f240f2fa0197..48e82af1159b 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -16,7 +16,7 @@ #include #include #include -#include +#include struct user_struct; struct cred; diff --git a/include/linux/crypto.h b/include/linux/crypto.h index a6a7a1c83f54..e5e468e9133d 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -17,7 +17,7 @@ #ifndef _LINUX_CRYPTO_H #define _LINUX_CRYPTO_H -#include +#include #include #include #include diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 3f22d8d6d8a3..d37d2a793099 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -1,7 +1,7 @@ #ifndef __LINUX_DCACHE_H #define __LINUX_DCACHE_H -#include +#include #include #include #include diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h index 2833452ea01c..5033fb88c107 100644 --- a/include/linux/debug_locks.h +++ b/include/linux/debug_locks.h @@ -2,7 +2,7 @@ #define __LINUX_DEBUG_LOCKING_H #include -#include +#include #include struct task_struct; diff --git a/include/linux/device.h b/include/linux/device.h index 160d4ddb2499..c20dfbfc49b4 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -22,7 +22,7 @@ #include #include #include -#include +#include #include struct device; diff --git a/include/linux/edac.h b/include/linux/edac.h index 36c66443bdfd..4a73257b47d0 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -12,7 +12,7 @@ #ifndef _LINUX_EDAC_H_ #define _LINUX_EDAC_H_ -#include +#include #include #define EDAC_OPSTATE_INVAL -1 diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h index a842db638380..3ff060ac7810 100644 --- a/include/linux/fault-inject.h +++ b/include/linux/fault-inject.h @@ -5,7 +5,7 @@ #include #include -#include +#include /* * For explanation of the elements of this struct, see diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index df7e3cf82e97..82163c4b32c9 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -13,7 +13,7 @@ #include #include -#include +#include /* * The default fd array needs to be at least BITS_PER_LONG, diff --git a/include/linux/filter.h b/include/linux/filter.h index 9ee3f9fb0b4a..741956fa5bfd 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -9,7 +9,7 @@ #include #ifdef __KERNEL__ -#include +#include #endif /* diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 5e6f42789afe..84ccf8e04fa6 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -14,7 +14,7 @@ #include #include -#include +#include #include #define fw_notify(s, args...) printk(KERN_NOTICE KBUILD_MODNAME ": " s, ## args) diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 69ad89b50489..91d0e0a34ef3 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -16,7 +16,7 @@ #include #include -#include +#include /* * IN_* from inotfy.h lines up EXACTLY with FS_*, this is so we can easily diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index f6efed0039ed..a103732b7588 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -17,7 +17,7 @@ #include #include -#include +#include #include #include #include diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 83e745f3ead7..66f23dc5e76a 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -54,7 +54,7 @@ extern void jump_label_apply_nops(struct module *mod); #else -#include +#include #define JUMP_LABEL_INIT {ATOMIC_INIT(0)} diff --git a/include/linux/kdb.h b/include/linux/kdb.h index aadff7cc2b84..529d9a0c75a5 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -16,7 +16,7 @@ #ifdef CONFIG_KGDB_KDB #include #include -#include +#include #define KDB_POLL_FUNC_MAX 5 extern int kdb_poll_idx; diff --git a/include/linux/key.h b/include/linux/key.h index 6ea4eebd3467..183a6af7715d 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -21,7 +21,7 @@ #include #include #include -#include +#include #ifdef __KERNEL__ diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 10ca03d0a250..fa391835508d 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -16,7 +16,7 @@ #include #include #include -#include +#include #ifdef CONFIG_HAVE_ARCH_KGDB #include #endif diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 9229b64ee3aa..668729cc0fe9 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -25,7 +25,7 @@ #include #include #include -#include +#include #define UEVENT_HELPER_PATH_LEN 256 #define UEVENT_NUM_ENVP 32 /* number of env pointers */ diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 387329e02303..53ef894bfa05 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -37,7 +37,7 @@ #include #include -#include +#include #define MAX_MSIX_P_PORT 17 #define MAX_MSIX 64 diff --git a/include/linux/mman.h b/include/linux/mman.h index 9872d6ca58ae..8b74e9b1d0ad 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -14,7 +14,7 @@ #include #include -#include +#include extern int sysctl_overcommit_memory; extern int sysctl_overcommit_ratio; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 0a2d3d620feb..be1ac8d7789b 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include /* Free memory management - zoned buddy allocator. */ diff --git a/include/linux/mount.h b/include/linux/mount.h index 604f122a2326..33fe53d78110 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -14,7 +14,7 @@ #include #include #include -#include +#include struct super_block; struct vfsmount; diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 7f87217e9d1f..9121595a8ebf 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -15,7 +15,7 @@ #include #include -#include +#include /* * Simple, straightforward mutexes with strict semantics: diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ea6f4aa479d4..2ed0b6cf11c5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -34,7 +34,7 @@ #include #include #include -#include +#include #include #include diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 87694ca86914..08c444aa0411 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -7,7 +7,7 @@ #include #include -#include +#include struct nfs4_session; struct nfs_iostats; diff --git a/include/linux/oprofile.h b/include/linux/oprofile.h index 7f5cfd3b37dd..49c8727eeb57 100644 --- a/include/linux/oprofile.h +++ b/include/linux/oprofile.h @@ -18,7 +18,7 @@ #include #include #include -#include +#include /* Each escaped entry is prefixed by ESCAPE_CODE * then one of the following codes, then the diff --git a/include/linux/pci.h b/include/linux/pci.h index 4e4203a96312..3a5626df37ce 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -49,7 +49,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 3f2711ccf910..245bafdafd5e 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -509,7 +509,7 @@ struct perf_guest_info_callbacks { #include #include #include -#include +#include #include #define PERF_MAX_STACK_DEPTH 255 diff --git a/include/linux/phy.h b/include/linux/phy.h index 7da5fa845959..ad5186354d92 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -26,7 +26,7 @@ #include #include -#include +#include #define PHY_BASIC_FEATURES (SUPPORTED_10baseT_Half | \ SUPPORTED_10baseT_Full | \ diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index e7576cf9e32d..650af6deaf8f 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -5,7 +5,7 @@ #include #include #include -#include +#include struct net; struct completion; diff --git a/include/linux/quota.h b/include/linux/quota.h index 313b7defc088..cb7855699037 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -180,7 +180,7 @@ enum { #include #include -#include +#include typedef __kernel_uid32_t qid_t; /* Type in which we store ids in memory */ typedef long long qsize_t; /* Type in which we store sizes */ diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index 77950dfa0a9e..6a6741440cb7 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -15,7 +15,7 @@ #include #include -#include +#include struct rw_semaphore; diff --git a/include/linux/sem.h b/include/linux/sem.h index f2961afa2f66..1feb2de2ee57 100644 --- a/include/linux/sem.h +++ b/include/linux/sem.h @@ -77,7 +77,7 @@ struct seminfo { #define SEMUSZ 20 /* sizeof struct sem_undo */ #ifdef __KERNEL__ -#include +#include #include #include diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a24218c9c84b..7b996ed86d5b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -20,7 +20,7 @@ #include #include -#include +#include #include #include #include diff --git a/include/linux/sonet.h b/include/linux/sonet.h index 67ad11fcf88b..de8832dd272b 100644 --- a/include/linux/sonet.h +++ b/include/linux/sonet.h @@ -58,7 +58,7 @@ struct sonet_stats { #ifdef __KERNEL__ -#include +#include struct k_sonet_stats { #define __HANDLE_ITEM(i) atomic_t i diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 0b22d51258e6..7df6c17b0281 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -384,7 +384,7 @@ static inline void assert_spin_locked(spinlock_t *lock) * Pull the atomic_t declaration: * (asm-mips/atomic.h needs above definitions) */ -#include +#include /** * atomic_dec_and_lock - lock on reaching reference count zero * @atomic: the atomic counter diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 8521067ed4f7..febc4dbec2ca 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -15,7 +15,7 @@ #include #include -#include +#include #include /* size of the nodename buffer */ diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index d1c79a906397..5efd8cef389e 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -15,7 +15,7 @@ #include #include -#include +#include #include /* diff --git a/include/linux/sunrpc/timer.h b/include/linux/sunrpc/timer.h index a67fd734c73b..697d6e69d61f 100644 --- a/include/linux/sunrpc/timer.h +++ b/include/linux/sunrpc/timer.h @@ -9,7 +9,7 @@ #ifndef _LINUX_SUNRPC_TIMER_H #define _LINUX_SUNRPC_TIMER_H -#include +#include struct rpc_rtt { unsigned long timeo; /* default timeout value */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 91d5fcc83116..14d62490922e 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -9,7 +9,7 @@ #include #include -#include +#include #include struct notifier_block; diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index e2696d76a599..d7d2f2158142 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -17,7 +17,7 @@ #include #include #include -#include +#include struct kobject; struct module; diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index bcd942fa611c..65efb92da996 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -6,7 +6,7 @@ #include #include #include -#include +#include extern int sysctl_stat_interval; diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 2be2887c6958..0d556deb497b 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -10,7 +10,7 @@ #include #include #include -#include +#include struct workqueue_struct; -- cgit v1.2.3 From f24219b4e90cf70ec4a211b17fbabc725a0ddf3c Mon Sep 17 00:00:00 2001 From: Arun Sharma Date: Tue, 26 Jul 2011 16:09:07 -0700 Subject: atomic: move atomic_add_unless to generic code This is in preparation for more generic atomic primitives based on __atomic_add_unless. Signed-off-by: Arun Sharma Signed-off-by: Hans-Christian Egtvedt Reviewed-by: Eric Dumazet Cc: Ingo Molnar Cc: David Miller Acked-by: Mike Frysinger Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/atomic.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 66fed6364122..d5e167a6a398 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -2,6 +2,20 @@ #define _LINUX_ATOMIC_H #include +/** + * atomic_add_unless - add unless the number is already a given value + * @v: pointer of type atomic_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, so long as @v was not already @u. + * Returns non-zero if @v was not @u, and zero otherwise. + */ +static inline int atomic_add_unless(atomic_t *v, int a, int u) +{ + return __atomic_add_unless(v, a, u) != u; +} + /** * atomic_inc_not_zero - increment unless the number is zero * @v: pointer of type atomic_t -- cgit v1.2.3 From 7847777a45f9f8bfc8617dbf107bde1ecb59caee Mon Sep 17 00:00:00 2001 From: Arun Sharma Date: Tue, 26 Jul 2011 16:09:08 -0700 Subject: atomic: cleanup asm-generic atomic*.h inclusion After changing all consumers of atomics to include , we ran into some compile time errors due to this dependency chain: linux/atomic.h -> asm/atomic.h -> asm-generic/atomic-long.h where atomic-long.h could use funcs defined later in linux/atomic.h without a prototype. This patches moves the code that includes asm-generic/atomic*.h to linux/atomic.h. Archs that need need to select CONFIG_GENERIC_ATOMIC64 from now on (some of them used to include it unconditionally). Compile tested on i386 and x86_64 with allnoconfig. Signed-off-by: Arun Sharma Cc: Eric Dumazet Cc: Ingo Molnar Cc: David Miller Acked-by: Mike Frysinger Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/atomic.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/atomic.h b/include/linux/atomic.h index d5e167a6a398..42e7f6372ce2 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -96,4 +96,8 @@ static inline void atomic_or(int i, atomic_t *v) } #endif /* #ifndef CONFIG_ARCH_HAS_ATOMIC_OR */ +#include +#ifdef CONFIG_GENERIC_ATOMIC64 +#include +#endif #endif /* _LINUX_ATOMIC_H */ -- cgit v1.2.3 From acac43e2fc4b14ecf1ff229eaa8d1e011d063749 Mon Sep 17 00:00:00 2001 From: Arun Sharma Date: Tue, 26 Jul 2011 16:09:08 -0700 Subject: atomic: Update comments in atomic.h This clarifies the differences between and Signed-off-by: Arun Sharma Suggested-by: Mike Frysinger Cc: Eric Dumazet Cc: Ingo Molnar Cc: David Miller Acked-by: Mike Frysinger Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/atomic.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 42e7f6372ce2..42b77b5446d2 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -1,3 +1,4 @@ +/* Atomic operations usable in machine independent code */ #ifndef _LINUX_ATOMIC_H #define _LINUX_ATOMIC_H #include -- cgit v1.2.3 From 6ca1a113791eb09dac8c48b2b264c4d72aab410f Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Mon, 4 Jul 2011 14:03:17 +0800 Subject: dt/net: add helper function of_get_phy_mode It adds the helper function of_get_phy_mode getting phy interface from device tree. Signed-off-by: Shawn Guo Cc: Grant Likely Acked-by: Grant Likely Acked-by: David Miller --- include/linux/of_net.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/of_net.h b/include/linux/of_net.h index e913081fb52a..f47464188710 100644 --- a/include/linux/of_net.h +++ b/include/linux/of_net.h @@ -9,6 +9,7 @@ #ifdef CONFIG_OF_NET #include +extern const int of_get_phy_mode(struct device_node *np); extern const void *of_get_mac_address(struct device_node *np); #endif -- cgit v1.2.3 From 4157ef1b8779b34581ee8b9dc8f7f95188008eca Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Tue, 5 Jul 2011 16:42:09 +0800 Subject: net: ibm_newemac: convert it to use of_get_phy_mode The patch extends 'enum phy_interface_t' and of_get_phy_mode a little bit with PHY_INTERFACE_MODE_NA and PHY_INTERFACE_MODE_SMII added, and then converts ibm_newemac net driver to use of_get_phy_mode getting phy mode from device tree. It also resolves the namespace conflict on phy_read/write between common mdiobus interface and ibm_newemac private one. Signed-off-by: Shawn Guo Cc: David S. Miller Cc: Grant Likely Acked-by: Grant Likely Acked-by: David Miller --- include/linux/phy.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index ad5186354d92..54fc4138955f 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -53,6 +53,7 @@ /* Interface Mode definitions */ typedef enum { + PHY_INTERFACE_MODE_NA, PHY_INTERFACE_MODE_MII, PHY_INTERFACE_MODE_GMII, PHY_INTERFACE_MODE_SGMII, @@ -62,7 +63,8 @@ typedef enum { PHY_INTERFACE_MODE_RGMII_ID, PHY_INTERFACE_MODE_RGMII_RXID, PHY_INTERFACE_MODE_RGMII_TXID, - PHY_INTERFACE_MODE_RTBI + PHY_INTERFACE_MODE_RTBI, + PHY_INTERFACE_MODE_SMII, } phy_interface_t; -- cgit v1.2.3 From 17dd759c67f21e34f2156abcf415e1f60605a188 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 27 Jul 2011 06:16:28 -0700 Subject: gro: Only reset frag0 when skb can be pulled Currently skb_gro_header_slow unconditionally resets frag0 and frag0_len. However, when we can't pull on the skb this leaves the GRO fields in an inconsistent state. This patch fixes this by only resetting those fields after the pskb_may_pull test. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1d92acc0777b..661a07746e94 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1649,9 +1649,12 @@ static inline int skb_gro_header_hard(struct sk_buff *skb, unsigned int hlen) static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen, unsigned int offset) { + if (!pskb_may_pull(skb, hlen)) + return NULL; + NAPI_GRO_CB(skb)->frag0 = NULL; NAPI_GRO_CB(skb)->frag0_len = 0; - return pskb_may_pull(skb, hlen) ? skb->data + offset : NULL; + return skb->data + offset; } static inline void *skb_gro_mac_header(struct sk_buff *skb) -- cgit v1.2.3 From 09570f914914d2beb0db29c5a9c7344934f2fa8c Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 27 Jul 2011 21:47:03 +0300 Subject: proc: make struct proc_dir_entry::name a terminal array rather than a pointer Since __proc_create() appends the name it is given to the end of the PDE structure that it allocates, there isn't a need to store a name pointer. Instead we can just replace the name pointer with a terminal char array of _unspecified_ length. The compiler will simply append the string to statically defined variables of PDE type overlapping any hole at the end of the structure and, unlike specifying an explicitly _zero_ length array, won't give a warning if you try to statically initialise it with a string of more than zero length. Also, whilst we're at it: (1) Move namelen to end just prior to name and reduce it to a single byte (name shouldn't be longer than NAME_MAX). (2) Move pde_unload_lock two places further on so that if it's four bytes in size on a 64-bit machine, it won't cause an unused hole in the PDE struct. Signed-off-by: David Howells Signed-off-by: Alexey Dobriyan Signed-off-by: Linus Torvalds --- include/linux/proc_fs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 650af6deaf8f..643b96c7a94f 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -50,8 +50,6 @@ typedef int (write_proc_t)(struct file *file, const char __user *buffer, struct proc_dir_entry { unsigned int low_ino; - unsigned int namelen; - const char *name; mode_t mode; nlink_t nlink; uid_t uid; @@ -73,9 +71,11 @@ struct proc_dir_entry { write_proc_t *write_proc; atomic_t count; /* use count */ int pde_users; /* number of callers into module in progress */ - spinlock_t pde_unload_lock; /* proc_fops checks and pde_users bumps */ struct completion *pde_unload_completion; struct list_head pde_openers; /* who did ->open, but not ->release */ + spinlock_t pde_unload_lock; /* proc_fops checks and pde_users bumps */ + u8 namelen; + char name[]; }; enum kcore_type { -- cgit v1.2.3 From 34452432d125a846591523cf4999311c987c0bf4 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 8 Jun 2011 10:55:57 -0300 Subject: [media] DocBook/audio.xml: synchronize attribute changes Some attributes suffered some changes since DVBv1. Sync them with the current API header files. Signed-off-by: Mauro Carvalho Chehab --- include/linux/dvb/audio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dvb/audio.h b/include/linux/dvb/audio.h index fec66bd24f22..d47bccd604e4 100644 --- a/include/linux/dvb/audio.h +++ b/include/linux/dvb/audio.h @@ -67,7 +67,7 @@ typedef struct audio_status { typedef -struct audio_karaoke{ /* if Vocal1 or Vocal2 are non-zero, they get mixed */ +struct audio_karaoke { /* if Vocal1 or Vocal2 are non-zero, they get mixed */ int vocal1; /* into left and right t at 70% each */ int vocal2; /* if both, Vocal1 and Vocal2 are non-zero, Vocal1 gets*/ int melody; /* mixed into the left channel and */ -- cgit v1.2.3 From fa24198897ff0e8d34876be0e61f9b35d3c0d467 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 8 Jun 2011 11:25:26 -0300 Subject: [media] dvb/audio.h: Remove definition for AUDIO_GET_PTS While this ioctl is defined inside dvb/audio.h, it is not docummented at the API specs, nor implemented on any driver inside the Linux Kernel. So, it doesn't make sense to keep it here. As this is not used anywere, removing it is not a regression. So, there's no need to use the normal features-to-be-removed process. Signed-off-by: Mauro Carvalho Chehab --- include/linux/dvb/audio.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dvb/audio.h b/include/linux/dvb/audio.h index d47bccd604e4..c1b35550899a 100644 --- a/include/linux/dvb/audio.h +++ b/include/linux/dvb/audio.h @@ -118,18 +118,6 @@ typedef __u16 audio_attributes_t; #define AUDIO_SET_ATTRIBUTES _IOW('o', 17, audio_attributes_t) #define AUDIO_SET_KARAOKE _IOW('o', 18, audio_karaoke_t) -/** - * AUDIO_GET_PTS - * - * Read the 33 bit presentation time stamp as defined - * in ITU T-REC-H.222.0 / ISO/IEC 13818-1. - * - * The PTS should belong to the currently played - * frame if possible, but may also be a value close to it - * like the PTS of the last decoded frame or the last PTS - * extracted by the PES parser. - */ -#define AUDIO_GET_PTS _IOR('o', 19, __u64) #define AUDIO_BILINGUAL_CHANNEL_SELECT _IO('o', 20) #endif /* _DVBAUDIO_H_ */ -- cgit v1.2.3 From 7a2b66b1bd26d717763985bad401410665fa0672 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 9 Jun 2011 16:26:32 -0300 Subject: Revert "[media] dvb/audio.h: Remove definition for AUDIO_GET_PTS" Based on those feedback: http://www.spinics.net/lists/linux-media/msg33704.html http://www.spinics.net/lists/linux-media/msg33700.html I'm reverting the removal of this unused ioctl, as it seems that some drivers under development may be using. So, I'll wait until the next merge window before removing those unused ioctls, to give a chance for developers to submit their pending work. This reverts commit db48923da6c528d461b5e764692239eb9c1b7a00. Cc: Andreas Oberritter Cc: Manu Abraham Signed-off-by: Mauro Carvalho Chehab --- include/linux/dvb/audio.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dvb/audio.h b/include/linux/dvb/audio.h index c1b35550899a..d47bccd604e4 100644 --- a/include/linux/dvb/audio.h +++ b/include/linux/dvb/audio.h @@ -118,6 +118,18 @@ typedef __u16 audio_attributes_t; #define AUDIO_SET_ATTRIBUTES _IOW('o', 17, audio_attributes_t) #define AUDIO_SET_KARAOKE _IOW('o', 18, audio_karaoke_t) +/** + * AUDIO_GET_PTS + * + * Read the 33 bit presentation time stamp as defined + * in ITU T-REC-H.222.0 / ISO/IEC 13818-1. + * + * The PTS should belong to the currently played + * frame if possible, but may also be a value close to it + * like the PTS of the last decoded frame or the last PTS + * extracted by the PES parser. + */ +#define AUDIO_GET_PTS _IOR('o', 19, __u64) #define AUDIO_BILINGUAL_CHANNEL_SELECT _IO('o', 20) #endif /* _DVBAUDIO_H_ */ -- cgit v1.2.3 From 6e239399e5807132f86f64af6c659411c6a3d1a5 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 7 Jun 2011 11:13:44 -0300 Subject: [media] v4l2-ctrls: add control events Whenever a control changes value or state an event is sent to anyone that subscribed to it. This functionality is useful for control panels but also for applications that need to wait for (usually status) controls to change value. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 29 +++++++++++++++++++++++++++-- 1 file changed, 27 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index 8a4c309d2344..baafe2f2e02a 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -1791,6 +1791,7 @@ struct v4l2_streamparm { #define V4L2_EVENT_ALL 0 #define V4L2_EVENT_VSYNC 1 #define V4L2_EVENT_EOS 2 +#define V4L2_EVENT_CTRL 3 #define V4L2_EVENT_PRIVATE_START 0x08000000 /* Payload for V4L2_EVENT_VSYNC */ @@ -1799,21 +1800,45 @@ struct v4l2_event_vsync { __u8 field; } __attribute__ ((packed)); +/* Payload for V4L2_EVENT_CTRL */ +#define V4L2_EVENT_CTRL_CH_VALUE (1 << 0) +#define V4L2_EVENT_CTRL_CH_FLAGS (1 << 1) + +struct v4l2_event_ctrl { + __u32 changes; + __u32 type; + union { + __s32 value; + __s64 value64; + }; + __u32 flags; + __s32 minimum; + __s32 maximum; + __s32 step; + __s32 default_value; +}; + struct v4l2_event { __u32 type; union { struct v4l2_event_vsync vsync; + struct v4l2_event_ctrl ctrl; __u8 data[64]; } u; __u32 pending; __u32 sequence; struct timespec timestamp; - __u32 reserved[9]; + __u32 id; + __u32 reserved[8]; }; +#define V4L2_EVENT_SUB_FL_SEND_INITIAL (1 << 0) + struct v4l2_event_subscription { __u32 type; - __u32 reserved[7]; + __u32 id; + __u32 flags; + __u32 reserved[5]; }; /* -- cgit v1.2.3 From 60c0732244164f14e376cfae493dba368f761514 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 29 Jun 2011 08:56:22 -0300 Subject: [media] v4l2-ctrls.c: add support for V4L2_EVENT_SUB_FL_ALLOW_FEEDBACK Normally no control events will go to the filehandle that called the VIDIOC_S_CTRL/VIDIOC_S_EXT_CTRLS ioctls. This is to prevent a feedback loop. This can now be overridden by setting the new V4L2_EVENT_SUB_FL_ALLOW_FEEDBACK flag. Based on suggestions from Mauro Carvalho Chehab and Laurent Pinchart . Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index baafe2f2e02a..2c4e83796301 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -1832,7 +1832,8 @@ struct v4l2_event { __u32 reserved[8]; }; -#define V4L2_EVENT_SUB_FL_SEND_INITIAL (1 << 0) +#define V4L2_EVENT_SUB_FL_SEND_INITIAL (1 << 0) +#define V4L2_EVENT_SUB_FL_ALLOW_FEEDBACK (1 << 1) struct v4l2_event_subscription { __u32 type; -- cgit v1.2.3 From 21144ea601f1fea37c7add15a099affec7c08425 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sun, 5 Jun 2011 08:32:27 -0300 Subject: [media] videodev2.h Add SE401 compressed RGB format Signed-off-by: Hans de Goede Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index 2c4e83796301..f002006fc0a9 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -402,6 +402,7 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_CIT_YYVYUY v4l2_fourcc('C', 'I', 'T', 'V') /* one line of Y then 1 line of VYUY */ #define V4L2_PIX_FMT_KONICA420 v4l2_fourcc('K', 'O', 'N', 'I') /* YUV420 planar in blocks of 256 pixels */ #define V4L2_PIX_FMT_JPGL v4l2_fourcc('J', 'P', 'G', 'L') /* JPEG-Lite */ +#define V4L2_PIX_FMT_SE401 v4l2_fourcc('S', '4', '0', '1') /* se401 janggu compressed rgb */ /* * F O R M A T E N U M E R A T I O N -- cgit v1.2.3 From fa4d7096d1fb7c012ebaacefee132007a21e0965 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Mon, 23 May 2011 04:07:05 -0300 Subject: [media] v4l2-ctrls: add new bitmask control type Signed-off-by: Hans Verkuil Reviewed-by: Laurent Pinchart Acked-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index f002006fc0a9..148d1a51ca22 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -1040,6 +1040,7 @@ enum v4l2_ctrl_type { V4L2_CTRL_TYPE_INTEGER64 = 5, V4L2_CTRL_TYPE_CTRL_CLASS = 6, V4L2_CTRL_TYPE_STRING = 7, + V4L2_CTRL_TYPE_BITMASK = 8, }; /* Used in the VIDIOC_QUERYCTRL ioctl for querying controls */ -- cgit v1.2.3 From 0b159acdd577dfd961ad14177c23e97d3ad33009 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Mon, 21 Mar 2011 12:52:51 -0300 Subject: [media] v4l: Add a class and a set of controls for flash devices Add a control class and a set of controls to support LED and Xenon flash devices. An example of such a device is the adp1653. Signed-off-by: Sakari Ailus Acked-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index 148d1a51ca22..8b1224c1c536 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -1027,6 +1027,7 @@ struct v4l2_ext_controls { #define V4L2_CTRL_CLASS_MPEG 0x00990000 /* MPEG-compression controls */ #define V4L2_CTRL_CLASS_CAMERA 0x009a0000 /* Camera class controls */ #define V4L2_CTRL_CLASS_FM_TX 0x009b0000 /* FM Modulator control class */ +#define V4L2_CTRL_CLASS_FLASH 0x009c0000 /* Camera flash controls */ #define V4L2_CTRL_ID_MASK (0x0fffffff) #define V4L2_CTRL_ID2CLASS(id) ((id) & 0x0fff0000UL) @@ -1429,6 +1430,41 @@ enum v4l2_preemphasis { #define V4L2_CID_TUNE_POWER_LEVEL (V4L2_CID_FM_TX_CLASS_BASE + 113) #define V4L2_CID_TUNE_ANTENNA_CAPACITOR (V4L2_CID_FM_TX_CLASS_BASE + 114) +/* Flash and privacy (indicator) light controls */ +#define V4L2_CID_FLASH_CLASS_BASE (V4L2_CTRL_CLASS_FLASH | 0x900) +#define V4L2_CID_FLASH_CLASS (V4L2_CTRL_CLASS_FLASH | 1) + +#define V4L2_CID_FLASH_LED_MODE (V4L2_CID_FLASH_CLASS_BASE + 1) +enum v4l2_flash_led_mode { + V4L2_FLASH_LED_MODE_NONE, + V4L2_FLASH_LED_MODE_FLASH, + V4L2_FLASH_LED_MODE_TORCH, +}; + +#define V4L2_CID_FLASH_STROBE_SOURCE (V4L2_CID_FLASH_CLASS_BASE + 2) +enum v4l2_flash_strobe_source { + V4L2_FLASH_STROBE_SOURCE_SOFTWARE, + V4L2_FLASH_STROBE_SOURCE_EXTERNAL, +}; + +#define V4L2_CID_FLASH_STROBE (V4L2_CID_FLASH_CLASS_BASE + 3) +#define V4L2_CID_FLASH_STROBE_STOP (V4L2_CID_FLASH_CLASS_BASE + 4) +#define V4L2_CID_FLASH_STROBE_STATUS (V4L2_CID_FLASH_CLASS_BASE + 5) + +#define V4L2_CID_FLASH_TIMEOUT (V4L2_CID_FLASH_CLASS_BASE + 6) +#define V4L2_CID_FLASH_INTENSITY (V4L2_CID_FLASH_CLASS_BASE + 7) +#define V4L2_CID_FLASH_TORCH_INTENSITY (V4L2_CID_FLASH_CLASS_BASE + 8) +#define V4L2_CID_FLASH_INDICATOR_INTENSITY (V4L2_CID_FLASH_CLASS_BASE + 9) + +#define V4L2_CID_FLASH_FAULT (V4L2_CID_FLASH_CLASS_BASE + 10) +#define V4L2_FLASH_FAULT_OVER_VOLTAGE (1 << 0) +#define V4L2_FLASH_FAULT_TIMEOUT (1 << 1) +#define V4L2_FLASH_FAULT_OVER_TEMPERATURE (1 << 2) +#define V4L2_FLASH_FAULT_SHORT_CIRCUIT (1 << 3) + +#define V4L2_CID_FLASH_CHARGE (V4L2_CID_FLASH_CLASS_BASE + 11) +#define V4L2_CID_FLASH_READY (V4L2_CID_FLASH_CLASS_BASE + 12) + /* * T U N I N G */ -- cgit v1.2.3 From 4fa64dae8c55ea9d3be4eb5f23ad0c9a60fa6d95 Mon Sep 17 00:00:00 2001 From: Kamil Debski Date: Mon, 4 Jul 2011 13:25:50 -0300 Subject: [media] v4l: add fourcc definitions for compressed formats Add fourcc definitions and documentation for the following compressed formats: H264, H264 without start codes, MPEG1/2/4 ES, XVID, VC1 Annex G and Annex L compliant. Signed-off-by: Kamil Debski Signed-off-by: Kyungmin Park Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index 8b1224c1c536..cb22a2c7a467 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -376,7 +376,16 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_MJPEG v4l2_fourcc('M', 'J', 'P', 'G') /* Motion-JPEG */ #define V4L2_PIX_FMT_JPEG v4l2_fourcc('J', 'P', 'E', 'G') /* JFIF JPEG */ #define V4L2_PIX_FMT_DV v4l2_fourcc('d', 'v', 's', 'd') /* 1394 */ -#define V4L2_PIX_FMT_MPEG v4l2_fourcc('M', 'P', 'E', 'G') /* MPEG-1/2/4 */ +#define V4L2_PIX_FMT_MPEG v4l2_fourcc('M', 'P', 'E', 'G') /* MPEG-1/2/4 Multiplexed */ +#define V4L2_PIX_FMT_H264 v4l2_fourcc('H', '2', '6', '4') /* H264 with start codes */ +#define V4L2_PIX_FMT_H264_NO_SC v4l2_fourcc('A', 'V', 'C', '1') /* H264 without start codes */ +#define V4L2_PIX_FMT_H263 v4l2_fourcc('H', '2', '6', '3') /* H263 */ +#define V4L2_PIX_FMT_MPEG1 v4l2_fourcc('M', 'P', 'G', '1') /* MPEG-1 ES */ +#define V4L2_PIX_FMT_MPEG2 v4l2_fourcc('M', 'P', 'G', '2') /* MPEG-2 ES */ +#define V4L2_PIX_FMT_MPEG4 v4l2_fourcc('M', 'P', 'G', '4') /* MPEG-4 ES */ +#define V4L2_PIX_FMT_XVID v4l2_fourcc('X', 'V', 'I', 'D') /* Xvid */ +#define V4L2_PIX_FMT_VC1_ANNEX_G v4l2_fourcc('V', 'C', '1', 'G') /* SMPTE 421M Annex G compliant stream */ +#define V4L2_PIX_FMT_VC1_ANNEX_L v4l2_fourcc('V', 'C', '1', 'L') /* SMPTE 421M Annex L compliant stream */ /* Vendor-specific formats */ #define V4L2_PIX_FMT_CPIA1 v4l2_fourcc('C', 'P', 'I', 'A') /* cpia1 YUV */ @@ -1154,7 +1163,7 @@ enum v4l2_colorfx { #define V4L2_CID_MPEG_BASE (V4L2_CTRL_CLASS_MPEG | 0x900) #define V4L2_CID_MPEG_CLASS (V4L2_CTRL_CLASS_MPEG | 1) -/* MPEG streams */ +/* MPEG streams, specific to multiplexed streams */ #define V4L2_CID_MPEG_STREAM_TYPE (V4L2_CID_MPEG_BASE+0) enum v4l2_mpeg_stream_type { V4L2_MPEG_STREAM_TYPE_MPEG2_PS = 0, /* MPEG-2 program stream */ @@ -1176,7 +1185,7 @@ enum v4l2_mpeg_stream_vbi_fmt { V4L2_MPEG_STREAM_VBI_FMT_IVTV = 1, /* VBI in private packets, IVTV format */ }; -/* MPEG audio */ +/* MPEG audio controls specific to multiplexed streams */ #define V4L2_CID_MPEG_AUDIO_SAMPLING_FREQ (V4L2_CID_MPEG_BASE+100) enum v4l2_mpeg_audio_sampling_freq { V4L2_MPEG_AUDIO_SAMPLING_FREQ_44100 = 0, @@ -1292,7 +1301,7 @@ enum v4l2_mpeg_audio_ac3_bitrate { V4L2_MPEG_AUDIO_AC3_BITRATE_640K = 18, }; -/* MPEG video */ +/* MPEG video controls specific to multiplexed streams */ #define V4L2_CID_MPEG_VIDEO_ENCODING (V4L2_CID_MPEG_BASE+200) enum v4l2_mpeg_video_encoding { V4L2_MPEG_VIDEO_ENCODING_MPEG_1 = 0, -- cgit v1.2.3 From e65e4f134db36c70f13e9703d8e253e6b196ca47 Mon Sep 17 00:00:00 2001 From: Kamil Debski Date: Tue, 14 Jun 2011 10:31:04 -0300 Subject: [media] v4l: add control definitions for codec devices Add control definitions and documentation for controls specific to codec devices. Signed-off-by: Kamil Debski Signed-off-by: Kyungmin Park Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 169 +++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 168 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index cb22a2c7a467..fca24cc50436 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -1156,8 +1156,13 @@ enum v4l2_colorfx { #define V4L2_CID_ILLUMINATORS_1 (V4L2_CID_BASE+37) #define V4L2_CID_ILLUMINATORS_2 (V4L2_CID_BASE+38) +#define V4L2_CID_MIN_BUFFERS_FOR_CAPTURE (V4L2_CID_BASE+39) +#define V4L2_CID_MIN_BUFFERS_FOR_OUTPUT (V4L2_CID_BASE+40) + /* last CID + 1 */ -#define V4L2_CID_LASTP1 (V4L2_CID_BASE+39) +#define V4L2_CID_LASTP1 (V4L2_CID_BASE+41) + +/* Minimum number of buffer neede by the device */ /* MPEG-class control IDs defined by V4L2 */ #define V4L2_CID_MPEG_BASE (V4L2_CTRL_CLASS_MPEG | 0x900) @@ -1329,6 +1334,141 @@ enum v4l2_mpeg_video_bitrate_mode { #define V4L2_CID_MPEG_VIDEO_TEMPORAL_DECIMATION (V4L2_CID_MPEG_BASE+209) #define V4L2_CID_MPEG_VIDEO_MUTE (V4L2_CID_MPEG_BASE+210) #define V4L2_CID_MPEG_VIDEO_MUTE_YUV (V4L2_CID_MPEG_BASE+211) +#define V4L2_CID_MPEG_VIDEO_DECODER_SLICE_INTERFACE (V4L2_CID_MPEG_BASE+212) +#define V4L2_CID_MPEG_VIDEO_DECODER_MPEG4_DEBLOCK_FILTER (V4L2_CID_MPEG_BASE+213) +#define V4L2_CID_MPEG_VIDEO_CYCLIC_INTRA_REFRESH_MB (V4L2_CID_MPEG_BASE+214) +#define V4L2_CID_MPEG_VIDEO_FRAME_RC_ENABLE (V4L2_CID_MPEG_BASE+215) +#define V4L2_CID_MPEG_VIDEO_HEADER_MODE (V4L2_CID_MPEG_BASE+216) +enum v4l2_mpeg_video_header_mode { + V4L2_MPEG_VIDEO_HEADER_MODE_SEPARATE = 0, + V4L2_MPEG_VIDEO_HEADER_MODE_JOINED_WITH_1ST_FRAME = 1, + +}; +#define V4L2_CID_MPEG_VIDEO_MAX_REF_PIC (V4L2_CID_MPEG_BASE+217) +#define V4L2_CID_MPEG_VIDEO_MB_RC_ENABLE (V4L2_CID_MPEG_BASE+218) +#define V4L2_CID_MPEG_VIDEO_MULTI_SLICE_MAX_BYTES (V4L2_CID_MPEG_BASE+219) +#define V4L2_CID_MPEG_VIDEO_MULTI_SLICE_MAX_MB (V4L2_CID_MPEG_BASE+220) +#define V4L2_CID_MPEG_VIDEO_MULTI_SLICE_MODE (V4L2_CID_MPEG_BASE+221) +enum v4l2_mpeg_video_multi_slice_mode { + V4L2_MPEG_VIDEO_MULTI_SLICE_MODE_SINGLE = 0, + V4L2_MPEG_VIDEO_MULTI_SICE_MODE_MAX_MB = 1, + V4L2_MPEG_VIDEO_MULTI_SICE_MODE_MAX_BYTES = 2, +}; +#define V4L2_CID_MPEG_VIDEO_VBV_SIZE (V4L2_CID_MPEG_BASE+222) +#define V4L2_CID_MPEG_VIDEO_H263_I_FRAME_QP (V4L2_CID_MPEG_BASE+300) +#define V4L2_CID_MPEG_VIDEO_H263_P_FRAME_QP (V4L2_CID_MPEG_BASE+301) +#define V4L2_CID_MPEG_VIDEO_H263_B_FRAME_QP (V4L2_CID_MPEG_BASE+302) +#define V4L2_CID_MPEG_VIDEO_H263_MIN_QP (V4L2_CID_MPEG_BASE+303) +#define V4L2_CID_MPEG_VIDEO_H263_MAX_QP (V4L2_CID_MPEG_BASE+304) +#define V4L2_CID_MPEG_VIDEO_H264_I_FRAME_QP (V4L2_CID_MPEG_BASE+350) +#define V4L2_CID_MPEG_VIDEO_H264_P_FRAME_QP (V4L2_CID_MPEG_BASE+351) +#define V4L2_CID_MPEG_VIDEO_H264_B_FRAME_QP (V4L2_CID_MPEG_BASE+352) +#define V4L2_CID_MPEG_VIDEO_H264_MIN_QP (V4L2_CID_MPEG_BASE+353) +#define V4L2_CID_MPEG_VIDEO_H264_MAX_QP (V4L2_CID_MPEG_BASE+354) +#define V4L2_CID_MPEG_VIDEO_H264_8X8_TRANSFORM (V4L2_CID_MPEG_BASE+355) +#define V4L2_CID_MPEG_VIDEO_H264_CPB_SIZE (V4L2_CID_MPEG_BASE+356) +#define V4L2_CID_MPEG_VIDEO_H264_ENTROPY_MODE (V4L2_CID_MPEG_BASE+357) +enum v4l2_mpeg_video_h264_entropy_mode { + V4L2_MPEG_VIDEO_H264_ENTROPY_MODE_CAVLC = 0, + V4L2_MPEG_VIDEO_H264_ENTROPY_MODE_CABAC = 1, +}; +#define V4L2_CID_MPEG_VIDEO_H264_I_PERIOD (V4L2_CID_MPEG_BASE+358) +#define V4L2_CID_MPEG_VIDEO_H264_LEVEL (V4L2_CID_MPEG_BASE+359) +enum v4l2_mpeg_video_h264_level { + V4L2_MPEG_VIDEO_H264_LEVEL_1_0 = 0, + V4L2_MPEG_VIDEO_H264_LEVEL_1B = 1, + V4L2_MPEG_VIDEO_H264_LEVEL_1_1 = 2, + V4L2_MPEG_VIDEO_H264_LEVEL_1_2 = 3, + V4L2_MPEG_VIDEO_H264_LEVEL_1_3 = 4, + V4L2_MPEG_VIDEO_H264_LEVEL_2_0 = 5, + V4L2_MPEG_VIDEO_H264_LEVEL_2_1 = 6, + V4L2_MPEG_VIDEO_H264_LEVEL_2_2 = 7, + V4L2_MPEG_VIDEO_H264_LEVEL_3_0 = 8, + V4L2_MPEG_VIDEO_H264_LEVEL_3_1 = 9, + V4L2_MPEG_VIDEO_H264_LEVEL_3_2 = 10, + V4L2_MPEG_VIDEO_H264_LEVEL_4_0 = 11, + V4L2_MPEG_VIDEO_H264_LEVEL_4_1 = 12, + V4L2_MPEG_VIDEO_H264_LEVEL_4_2 = 13, + V4L2_MPEG_VIDEO_H264_LEVEL_5_0 = 14, + V4L2_MPEG_VIDEO_H264_LEVEL_5_1 = 15, +}; +#define V4L2_CID_MPEG_VIDEO_H264_LOOP_FILTER_ALPHA (V4L2_CID_MPEG_BASE+360) +#define V4L2_CID_MPEG_VIDEO_H264_LOOP_FILTER_BETA (V4L2_CID_MPEG_BASE+361) +#define V4L2_CID_MPEG_VIDEO_H264_LOOP_FILTER_MODE (V4L2_CID_MPEG_BASE+362) +enum v4l2_mpeg_video_h264_loop_filter_mode { + V4L2_MPEG_VIDEO_H264_LOOP_FILTER_MODE_ENABLED = 0, + V4L2_MPEG_VIDEO_H264_LOOP_FILTER_MODE_DISABLED = 1, + V4L2_MPEG_VIDEO_H264_LOOP_FILTER_MODE_DISABLED_AT_SLICE_BOUNDARY = 2, +}; +#define V4L2_CID_MPEG_VIDEO_H264_PROFILE (V4L2_CID_MPEG_BASE+363) +enum v4l2_mpeg_video_h264_profile { + V4L2_MPEG_VIDEO_H264_PROFILE_BASELINE = 0, + V4L2_MPEG_VIDEO_H264_PROFILE_CONSTRAINED_BASELINE = 1, + V4L2_MPEG_VIDEO_H264_PROFILE_MAIN = 2, + V4L2_MPEG_VIDEO_H264_PROFILE_EXTENDED = 3, + V4L2_MPEG_VIDEO_H264_PROFILE_HIGH = 4, + V4L2_MPEG_VIDEO_H264_PROFILE_HIGH_10 = 5, + V4L2_MPEG_VIDEO_H264_PROFILE_HIGH_422 = 6, + V4L2_MPEG_VIDEO_H264_PROFILE_HIGH_444_PREDICTIVE = 7, + V4L2_MPEG_VIDEO_H264_PROFILE_HIGH_10_INTRA = 8, + V4L2_MPEG_VIDEO_H264_PROFILE_HIGH_422_INTRA = 9, + V4L2_MPEG_VIDEO_H264_PROFILE_HIGH_444_INTRA = 10, + V4L2_MPEG_VIDEO_H264_PROFILE_CAVLC_444_INTRA = 11, + V4L2_MPEG_VIDEO_H264_PROFILE_SCALABLE_BASELINE = 12, + V4L2_MPEG_VIDEO_H264_PROFILE_SCALABLE_HIGH = 13, + V4L2_MPEG_VIDEO_H264_PROFILE_SCALABLE_HIGH_INTRA = 14, + V4L2_MPEG_VIDEO_H264_PROFILE_STEREO_HIGH = 15, + V4L2_MPEG_VIDEO_H264_PROFILE_MULTIVIEW_HIGH = 16, +}; +#define V4L2_CID_MPEG_VIDEO_H264_VUI_EXT_SAR_HEIGHT (V4L2_CID_MPEG_BASE+364) +#define V4L2_CID_MPEG_VIDEO_H264_VUI_EXT_SAR_WIDTH (V4L2_CID_MPEG_BASE+365) +#define V4L2_CID_MPEG_VIDEO_H264_VUI_SAR_ENABLE (V4L2_CID_MPEG_BASE+366) +#define V4L2_CID_MPEG_VIDEO_H264_VUI_SAR_IDC (V4L2_CID_MPEG_BASE+367) +enum v4l2_mpeg_video_h264_vui_sar_idc { + V4L2_MPEG_VIDEO_H264_VUI_SAR_IDC_UNSPECIFIED = 0, + V4L2_MPEG_VIDEO_H264_VUI_SAR_IDC_1x1 = 1, + V4L2_MPEG_VIDEO_H264_VUI_SAR_IDC_12x11 = 2, + V4L2_MPEG_VIDEO_H264_VUI_SAR_IDC_10x11 = 3, + V4L2_MPEG_VIDEO_H264_VUI_SAR_IDC_16x11 = 4, + V4L2_MPEG_VIDEO_H264_VUI_SAR_IDC_40x33 = 5, + V4L2_MPEG_VIDEO_H264_VUI_SAR_IDC_24x11 = 6, + V4L2_MPEG_VIDEO_H264_VUI_SAR_IDC_20x11 = 7, + V4L2_MPEG_VIDEO_H264_VUI_SAR_IDC_32x11 = 8, + V4L2_MPEG_VIDEO_H264_VUI_SAR_IDC_80x33 = 9, + V4L2_MPEG_VIDEO_H264_VUI_SAR_IDC_18x11 = 10, + V4L2_MPEG_VIDEO_H264_VUI_SAR_IDC_15x11 = 11, + V4L2_MPEG_VIDEO_H264_VUI_SAR_IDC_64x33 = 12, + V4L2_MPEG_VIDEO_H264_VUI_SAR_IDC_160x99 = 13, + V4L2_MPEG_VIDEO_H264_VUI_SAR_IDC_4x3 = 14, + V4L2_MPEG_VIDEO_H264_VUI_SAR_IDC_3x2 = 15, + V4L2_MPEG_VIDEO_H264_VUI_SAR_IDC_2x1 = 16, + V4L2_MPEG_VIDEO_H264_VUI_SAR_IDC_EXTENDED = 17, +}; +#define V4L2_CID_MPEG_VIDEO_MPEG4_I_FRAME_QP (V4L2_CID_MPEG_BASE+400) +#define V4L2_CID_MPEG_VIDEO_MPEG4_P_FRAME_QP (V4L2_CID_MPEG_BASE+401) +#define V4L2_CID_MPEG_VIDEO_MPEG4_B_FRAME_QP (V4L2_CID_MPEG_BASE+402) +#define V4L2_CID_MPEG_VIDEO_MPEG4_MIN_QP (V4L2_CID_MPEG_BASE+403) +#define V4L2_CID_MPEG_VIDEO_MPEG4_MAX_QP (V4L2_CID_MPEG_BASE+404) +#define V4L2_CID_MPEG_VIDEO_MPEG4_LEVEL (V4L2_CID_MPEG_BASE+405) +enum v4l2_mpeg_video_mpeg4_level { + V4L2_MPEG_VIDEO_MPEG4_LEVEL_0 = 0, + V4L2_MPEG_VIDEO_MPEG4_LEVEL_0B = 1, + V4L2_MPEG_VIDEO_MPEG4_LEVEL_1 = 2, + V4L2_MPEG_VIDEO_MPEG4_LEVEL_2 = 3, + V4L2_MPEG_VIDEO_MPEG4_LEVEL_3 = 4, + V4L2_MPEG_VIDEO_MPEG4_LEVEL_3B = 5, + V4L2_MPEG_VIDEO_MPEG4_LEVEL_4 = 6, + V4L2_MPEG_VIDEO_MPEG4_LEVEL_5 = 7, +}; +#define V4L2_CID_MPEG_VIDEO_MPEG4_PROFILE (V4L2_CID_MPEG_BASE+406) +enum v4l2_mpeg_video_mpeg4_profile { + V4L2_MPEG_VIDEO_MPEG4_PROFILE_SIMPLE = 0, + V4L2_MPEG_VIDEO_MPEG4_PROFILE_ADVANCED_SIMPLE = 1, + V4L2_MPEG_VIDEO_MPEG4_PROFILE_CORE = 2, + V4L2_MPEG_VIDEO_MPEG4_PROFILE_SIMPLE_SCALABLE = 3, + V4L2_MPEG_VIDEO_MPEG4_PROFILE_ADVANCED_CODING_EFFICIENCY = 4, +}; +#define V4L2_CID_MPEG_VIDEO_MPEG4_QPEL (V4L2_CID_MPEG_BASE+407) /* MPEG-class control IDs specific to the CX2341x driver as defined by V4L2 */ #define V4L2_CID_MPEG_CX2341X_BASE (V4L2_CTRL_CLASS_MPEG | 0x1000) @@ -1371,6 +1511,33 @@ enum v4l2_mpeg_cx2341x_video_median_filter_type { #define V4L2_CID_MPEG_CX2341X_VIDEO_CHROMA_MEDIAN_FILTER_TOP (V4L2_CID_MPEG_CX2341X_BASE+10) #define V4L2_CID_MPEG_CX2341X_STREAM_INSERT_NAV_PACKETS (V4L2_CID_MPEG_CX2341X_BASE+11) +/* MPEG-class control IDs specific to the Samsung MFC 5.1 driver as defined by V4L2 */ +#define V4L2_CID_MPEG_MFC51_BASE (V4L2_CTRL_CLASS_MPEG | 0x1100) + +#define V4L2_CID_MPEG_MFC51_VIDEO_DECODER_H264_DISPLAY_DELAY (V4L2_CID_MPEG_MFC51_BASE+0) +#define V4L2_CID_MPEG_MFC51_VIDEO_DECODER_H264_DISPLAY_DELAY_ENABLE (V4L2_CID_MPEG_MFC51_BASE+1) +#define V4L2_CID_MPEG_MFC51_VIDEO_FRAME_SKIP_MODE (V4L2_CID_MPEG_MFC51_BASE+2) +enum v4l2_mpeg_mfc51_video_frame_skip_mode { + V4L2_MPEG_MFC51_VIDEO_FRAME_SKIP_MODE_DISABLED = 0, + V4L2_MPEG_MFC51_VIDEO_FRAME_SKIP_MODE_LEVEL_LIMIT = 1, + V4L2_MPEG_MFC51_VIDEO_FRAME_SKIP_MODE_BUF_LIMIT = 2, +}; +#define V4L2_CID_MPEG_MFC51_VIDEO_FORCE_FRAME_TYPE (V4L2_CID_MPEG_MFC51_BASE+3) +enum v4l2_mpeg_mfc51_video_force_frame_type { + V4L2_MPEG_MFC51_VIDEO_FORCE_FRAME_TYPE_DISABLED = 0, + V4L2_MPEG_MFC51_VIDEO_FORCE_FRAME_TYPE_I_FRAME = 1, + V4L2_MPEG_MFC51_VIDEO_FORCE_FRAME_TYPE_NOT_CODED = 2, +}; +#define V4L2_CID_MPEG_MFC51_VIDEO_PADDING (V4L2_CID_MPEG_MFC51_BASE+4) +#define V4L2_CID_MPEG_MFC51_VIDEO_PADDING_YUV (V4L2_CID_MPEG_MFC51_BASE+5) +#define V4L2_CID_MPEG_MFC51_VIDEO_RC_FIXED_TARGET_BIT (V4L2_CID_MPEG_MFC51_BASE+6) +#define V4L2_CID_MPEG_MFC51_VIDEO_RC_REACTION_COEFF (V4L2_CID_MPEG_MFC51_BASE+7) +#define V4L2_CID_MPEG_MFC51_VIDEO_H264_ADAPTIVE_RC_ACTIVITY (V4L2_CID_MPEG_MFC51_BASE+50) +#define V4L2_CID_MPEG_MFC51_VIDEO_H264_ADAPTIVE_RC_DARK (V4L2_CID_MPEG_MFC51_BASE+51) +#define V4L2_CID_MPEG_MFC51_VIDEO_H264_ADAPTIVE_RC_SMOOTH (V4L2_CID_MPEG_MFC51_BASE+52) +#define V4L2_CID_MPEG_MFC51_VIDEO_H264_ADAPTIVE_RC_STATIC (V4L2_CID_MPEG_MFC51_BASE+53) +#define V4L2_CID_MPEG_MFC51_VIDEO_H264_NUM_REF_PIC_FOR_P (V4L2_CID_MPEG_MFC51_BASE+54) + /* Camera class control IDs */ #define V4L2_CID_CAMERA_CLASS_BASE (V4L2_CTRL_CLASS_CAMERA | 0x900) #define V4L2_CID_CAMERA_CLASS (V4L2_CTRL_CLASS_CAMERA | 1) -- cgit v1.2.3 From 2699b67223aca6b1450fc2f72e40fada952afc85 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 28 Jul 2011 11:31:47 +1000 Subject: md: load/store badblock list from v1.x metadata Space must have been allocated when array was created. A feature flag is set when the badblock list is non-empty, to ensure old kernels don't load and trust the whole device. We only update the on-disk badblocklist when it has changed. If the badblocklist (or other metadata) is stored on a bad block, we don't cope very well. If metadata has no room for bad block, flag bad-blocks as disabled, and do the same for 0.90 metadata. Signed-off-by: NeilBrown --- include/linux/raid/md_p.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/raid/md_p.h b/include/linux/raid/md_p.h index 75cbf4f62fe8..9e65d9e20662 100644 --- a/include/linux/raid/md_p.h +++ b/include/linux/raid/md_p.h @@ -245,10 +245,16 @@ struct mdp_superblock_1 { __u8 device_uuid[16]; /* user-space setable, ignored by kernel */ __u8 devflags; /* per-device flags. Only one defined...*/ #define WriteMostly1 1 /* mask for writemostly flag in above */ - __u8 pad2[64-57]; /* set to 0 when writing */ + /* Bad block log. If there are any bad blocks the feature flag is set. + * If offset and size are non-zero, that space is reserved and available + */ + __u8 bblog_shift; /* shift from sectors to block size */ + __le16 bblog_size; /* number of sectors reserved for list */ + __le32 bblog_offset; /* sector offset from superblock to bblog, + * signed - not unsigned */ /* array state information - 64 bytes */ - __le64 utime; /* 40 bits second, 24 btes microseconds */ + __le64 utime; /* 40 bits second, 24 bits microseconds */ __le64 events; /* incremented when superblock updated */ __le64 resync_offset; /* data before this offset (from data_offset) known to be in sync */ __le32 sb_csum; /* checksum up to devs[max_dev] */ @@ -270,8 +276,8 @@ struct mdp_superblock_1 { * must be honoured */ #define MD_FEATURE_RESHAPE_ACTIVE 4 +#define MD_FEATURE_BAD_BLOCKS 8 /* badblock list is not empty */ -#define MD_FEATURE_ALL (1|2|4) +#define MD_FEATURE_ALL (1|2|4|8) #endif - -- cgit v1.2.3 From d8873315065f1f527c7c380402cf59b1e1d0ae36 Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Tue, 26 Jul 2011 06:05:37 +0000 Subject: net: add IFF_SKB_TX_SHARED flag to priv_flags Pktgen attempts to transmit shared skbs to net devices, which can't be used by some drivers as they keep state information in skbs. This patch adds a flag marking drivers as being able to handle shared skbs in their tx path. Drivers are defaulted to being unable to do so, but calling ether_setup enables this flag, as 90% of the drivers calling ether_setup touch real hardware and can handle shared skbs. A subsequent patch will audit drivers to ensure that the flag is set properly Signed-off-by: Neil Horman Reported-by: Jiri Pirko CC: Robert Olsson CC: Eric Dumazet CC: Alexey Dobriyan CC: David S. Miller Signed-off-by: David S. Miller --- include/linux/if.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if.h b/include/linux/if.h index 3bc63e6a02f7..03489ca92ded 100644 --- a/include/linux/if.h +++ b/include/linux/if.h @@ -76,6 +76,8 @@ #define IFF_BRIDGE_PORT 0x4000 /* device used as bridge port */ #define IFF_OVS_DATAPATH 0x8000 /* device used as Open vSwitch * datapath port */ +#define IFF_TX_SKB_SHARING 0x10000 /* The interface supports sharing + * skbs on transmit */ #define IF_GET_IFACE 0x0001 /* for querying only */ #define IF_GET_PROTO 0x0002 -- cgit v1.2.3 From f22aaaa70d8c24e5dc7d23a219c4beace8354b65 Mon Sep 17 00:00:00 2001 From: Donggeun Kim Date: Mon, 20 Jun 2011 16:48:19 +0900 Subject: hwmon: Driver for NTC Thermistors Add support for NTC Thermistor series. In this release, the following thermistors are supported: NCP15WB473, NCP18WB473, NCP03WB473, and NCP15WL333. This driver is based on the datasheet of MURATA. The driver in the patch does conversion from the raw ADC value (either voltage or resistence) to temperature. In order to use voltage values as input, the circuit schematics should be provided with the platform data. A compensation table for each type of thermistor is provided for the conversion. Signed-off-by: Donggeun Kim Signed-off-by: MyungJoo Ham Signed-off-by: KyungMin Park Reviewed-by: Shubhrajyoti D Signed-off-by: Guenter Roeck --- include/linux/platform_data/ntc_thermistor.h | 53 ++++++++++++++++++++++++++++ 1 file changed, 53 insertions(+) create mode 100644 include/linux/platform_data/ntc_thermistor.h (limited to 'include/linux') diff --git a/include/linux/platform_data/ntc_thermistor.h b/include/linux/platform_data/ntc_thermistor.h new file mode 100644 index 000000000000..abd286215279 --- /dev/null +++ b/include/linux/platform_data/ntc_thermistor.h @@ -0,0 +1,53 @@ +/* + * ntc_thermistor.h - NTC Thermistors + * + * Copyright (C) 2010 Samsung Electronics + * MyungJoo Ham + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ +#ifndef _LINUX_NTC_H +#define _LINUX_NTC_H + +enum ntc_thermistor_type { + TYPE_NCPXXWB473, + TYPE_NCPXXWL333, +}; + +struct ntc_thermistor_platform_data { + /* + * One (not both) of read_uV and read_ohm should be provided and only + * one of the two should be provided. + * Both functions should return negative value for an error case. + * + * pullup_uV, pullup_ohm, pulldown_ohm, and connect are required to use + * read_uV() + * + * How to setup pullup_ohm, pulldown_ohm, and connect is + * described at Documentation/hwmon/ntc + * + * pullup/down_ohm: 0 for infinite / not-connected + */ + int (*read_uV)(void); + unsigned int pullup_uV; + + unsigned int pullup_ohm; + unsigned int pulldown_ohm; + enum { NTC_CONNECTED_POSITIVE, NTC_CONNECTED_GROUND } connect; + + int (*read_ohm)(void); +}; + +#endif /* _LINUX_NTC_H */ -- cgit v1.2.3 From 08a543ad33fc188650801bd36eed4ffe272643e1 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 26 Jul 2011 03:19:06 -0600 Subject: irq: add irq_domain translation infrastructure This patch adds irq_domain infrastructure for translating from hardware irq numbers to linux irqs. This is particularly important for architectures adding device tree support because the current implementation (excluding PowerPC and SPARC) cannot handle translation for more than a single interrupt controller. irq_domain supports device tree translation for any number of interrupt controllers. This patch converts x86, Microblaze, ARM and MIPS to use irq_domain for device tree irq translation. x86 is untested beyond compiling it, irq_domain is enabled for MIPS and Microblaze, but the old behaviour is preserved until the core code is modified to actually register an irq_domain yet. On ARM it works and is required for much of the new ARM device tree board support. PowerPC has /not/ been converted to use this new infrastructure. It is still missing some features before it can replace the virq infrastructure already in powerpc (see documentation on irq_domain_map/unmap for details). Followup patches will add the missing pieces and migrate PowerPC to use irq_domain. SPARC has its own method of managing interrupts from the device tree and is unaffected by this change. Acked-by: Ralf Baechle Signed-off-by: Grant Likely --- include/linux/irq.h | 6 ++++ include/linux/irqdomain.h | 81 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/of_irq.h | 4 +++ 3 files changed, 91 insertions(+) create mode 100644 include/linux/irqdomain.h (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 5f695041090c..87a06f345bd2 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -108,14 +108,18 @@ enum { }; struct msi_desc; +struct irq_domain; /** * struct irq_data - per irq and irq chip data passed down to chip functions * @irq: interrupt number + * @hwirq: hardware interrupt number, local to the interrupt domain * @node: node index useful for balancing * @state_use_accessors: status information for irq chip functions. * Use accessor functions to deal with it * @chip: low level interrupt hardware access + * @domain: Interrupt translation domain; responsible for mapping + * between hwirq number and linux irq number. * @handler_data: per-IRQ data for the irq_chip methods * @chip_data: platform-specific per-chip private data for the chip * methods, to allow shared chip implementations @@ -128,9 +132,11 @@ struct msi_desc; */ struct irq_data { unsigned int irq; + unsigned long hwirq; unsigned int node; unsigned int state_use_accessors; struct irq_chip *chip; + struct irq_domain *domain; void *handler_data; void *chip_data; struct msi_desc *msi_desc; diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h new file mode 100644 index 000000000000..8f2c10a784a4 --- /dev/null +++ b/include/linux/irqdomain.h @@ -0,0 +1,81 @@ +/* + * irq_domain - IRQ translation domains + * + * Translation infrastructure between hw and linux irq numbers. This is + * helpful for interrupt controllers to implement mapping between hardware + * irq numbers and the Linux irq number space. + * + * irq_domains also have a hook for translating device tree interrupt + * representation into a hardware irq number that can be mapped back to a + * Linux irq number without any extra platform support code. + * + * irq_domain is expected to be embedded in an interrupt controller's private + * data structure. + */ +#ifndef _LINUX_IRQDOMAIN_H +#define _LINUX_IRQDOMAIN_H + +#include + +#ifdef CONFIG_IRQ_DOMAIN +struct device_node; +struct irq_domain; + +/** + * struct irq_domain_ops - Methods for irq_domain objects + * @to_irq: (optional) given a local hardware irq number, return the linux + * irq number. If to_irq is not implemented, then the irq_domain + * will use this translation: irq = (domain->irq_base + hwirq) + * @dt_translate: Given a device tree node and interrupt specifier, decode + * the hardware irq number and linux irq type value. + */ +struct irq_domain_ops { + unsigned int (*to_irq)(struct irq_domain *d, unsigned long hwirq); + +#ifdef CONFIG_OF + int (*dt_translate)(struct irq_domain *d, struct device_node *node, + const u32 *intspec, unsigned int intsize, + unsigned long *out_hwirq, unsigned int *out_type); +#endif /* CONFIG_OF */ +}; + +/** + * struct irq_domain - Hardware interrupt number translation object + * @list: Element in global irq_domain list. + * @irq_base: Start of irq_desc range assigned to the irq_domain. The creator + * of the irq_domain is responsible for allocating the array of + * irq_desc structures. + * @nr_irq: Number of irqs managed by the irq domain + * @ops: pointer to irq_domain methods + * @priv: private data pointer for use by owner. Not touched by irq_domain + * core code. + * @of_node: (optional) Pointer to device tree nodes associated with the + * irq_domain. Used when decoding device tree interrupt specifiers. + */ +struct irq_domain { + struct list_head list; + unsigned int irq_base; + unsigned int nr_irq; + const struct irq_domain_ops *ops; + void *priv; + struct device_node *of_node; +}; + +/** + * irq_domain_to_irq() - Translate from a hardware irq to a linux irq number + * + * Returns the linux irq number associated with a hardware irq. By default, + * the mapping is irq == domain->irq_base + hwirq, but this mapping can + * be overridden if the irq_domain implements a .to_irq() hook. + */ +static inline unsigned int irq_domain_to_irq(struct irq_domain *d, + unsigned long hwirq) +{ + return d->ops->to_irq ? d->ops->to_irq(d, hwirq) : d->irq_base + hwirq; +} + +extern void irq_domain_add(struct irq_domain *domain); +extern void irq_domain_del(struct irq_domain *domain); +#endif /* CONFIG_IRQ_DOMAIN */ + +#endif /* _LINUX_IRQDOMAIN_H */ diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index e6955f5d1f08..cd2e61ce4e83 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -63,6 +63,9 @@ extern int of_irq_map_one(struct device_node *device, int index, extern unsigned int irq_create_of_mapping(struct device_node *controller, const u32 *intspec, unsigned int intsize); +#ifdef CONFIG_IRQ_DOMAIN +extern void irq_dispose_mapping(unsigned int irq); +#endif extern int of_irq_to_resource(struct device_node *dev, int index, struct resource *r); extern int of_irq_count(struct device_node *dev); @@ -70,6 +73,7 @@ extern int of_irq_to_resource_table(struct device_node *dev, struct resource *res, int nr_irqs); extern struct device_node *of_irq_find_parent(struct device_node *child); + #endif /* CONFIG_OF_IRQ */ #endif /* CONFIG_OF */ #endif /* __OF_IRQ_H */ -- cgit v1.2.3 From 7e71330169d8056536b299290544980bccc6b300 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 26 Jul 2011 03:19:06 -0600 Subject: dt/irq: add irq_domain_generate_simple() helper irq_domain_generate_simple() is an easy way to generate an irq translation domain for simple irq controllers. It assumes a flat 1:1 mapping from hardware irq number to an offset of the first linux irq number assigned to the controller Signed-off-by: Grant Likely --- include/linux/irqdomain.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 8f2c10a784a4..e807ad687a07 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -16,6 +16,7 @@ #define _LINUX_IRQDOMAIN_H #include +#include #ifdef CONFIG_IRQ_DOMAIN struct device_node; @@ -78,4 +79,13 @@ extern void irq_domain_add(struct irq_domain *domain); extern void irq_domain_del(struct irq_domain *domain); #endif /* CONFIG_IRQ_DOMAIN */ +#if defined(CONFIG_IRQ_DOMAIN) && defined(CONFIG_OF_IRQ) +extern void irq_domain_add_simple(struct device_node *controller, int irq_base); +extern void irq_domain_generate_simple(const struct of_device_id *match, + u64 phys_base, unsigned int irq_start); +#else /* CONFIG_IRQ_DOMAIN && CONFIG_OF_IRQ */ +static inline void irq_domain_generate_simple(const struct of_device_id *match, + u64 phys_base, unsigned int irq_start) { } +#endif /* CONFIG_IRQ_DOMAIN && CONFIG_OF_IRQ */ + #endif /* _LINUX_IRQDOMAIN_H */ -- cgit v1.2.3 From 43316044d4f64da008d6aca7d4b60771b9a24eb8 Mon Sep 17 00:00:00 2001 From: Wim Van Sebroeck Date: Fri, 22 Jul 2011 18:55:18 +0000 Subject: watchdog: WatchDog Timer Driver Core - Add basic framework The WatchDog Timer Driver Core is a framework that contains the common code for all watchdog-driver's. It also introduces a watchdog device structure and the operations that go with it. This is the introduction of this framework. This part supports the minimal watchdog userspace API (or with other words: the functionality to use /dev/watchdog's open, release and write functionality as defined in the simplest watchdog API). Extra functionality will follow in the next set of patches. Signed-off-by: Alan Cox Signed-off-by: Wim Van Sebroeck Acked-by: Arnd Bergmann Acked-by: Wolfram Sang --- include/linux/watchdog.h | 61 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 61 insertions(+) (limited to 'include/linux') diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h index 011bcfeb9f09..5ab31bfd2906 100644 --- a/include/linux/watchdog.h +++ b/include/linux/watchdog.h @@ -59,6 +59,67 @@ struct watchdog_info { #define WATCHDOG_NOWAYOUT 0 #endif +struct watchdog_ops; +struct watchdog_device; + +/** struct watchdog_ops - The watchdog-devices operations + * + * @owner: The module owner. + * @start: The routine for starting the watchdog device. + * @stop: The routine for stopping the watchdog device. + * @ping: The routine that sends a keepalive ping to the watchdog device. + * + * The watchdog_ops structure contains a list of low-level operations + * that control a watchdog device. It also contains the module that owns + * these operations. The start and stop function are mandatory, all other + * functions are optonal. + */ +struct watchdog_ops { + struct module *owner; + /* mandatory operations */ + int (*start)(struct watchdog_device *); + int (*stop)(struct watchdog_device *); + /* optional operations */ + int (*ping)(struct watchdog_device *); +}; + +/** struct watchdog_device - The structure that defines a watchdog device + * + * @info: Pointer to a watchdog_info structure. + * @ops: Pointer to the list of watchdog operations. + * @driver-data:Pointer to the drivers private data. + * @status: Field that contains the devices internal status bits. + * + * The watchdog_device structure contains all information about a + * watchdog timer device. + * + * The driver-data field may not be accessed directly. It must be accessed + * via the watchdog_set_drvdata and watchdog_get_drvdata helpers. + */ +struct watchdog_device { + const struct watchdog_info *info; + const struct watchdog_ops *ops; + void *driver_data; + unsigned long status; +/* Bit numbers for status flags */ +#define WDOG_DEV_OPEN 1 /* Opened via /dev/watchdog ? */ +}; + +/* Use the following functions to manipulate watchdog driver specific data */ +static inline void watchdog_set_drvdata(struct watchdog_device *wdd, void *data) +{ + wdd->driver_data = data; +} + +static inline void *watchdog_get_drvdata(struct watchdog_device *wdd) +{ + return wdd->driver_data; +} + +/* drivers/watchdog/core/watchdog_core.c */ +extern int watchdog_register_device(struct watchdog_device *); +extern void watchdog_unregister_device(struct watchdog_device *); + #endif /* __KERNEL__ */ #endif /* ifndef _LINUX_WATCHDOG_H */ -- cgit v1.2.3 From 2fa03560ab3a6dd83cad9bfd5692179fc2ceabb3 Mon Sep 17 00:00:00 2001 From: Wim Van Sebroeck Date: Fri, 22 Jul 2011 18:56:38 +0000 Subject: watchdog: WatchDog Timer Driver Core - Add basic ioctl functionality This part add's the basic ioctl functionality to the WatchDog Timer Driver Core framework. The supported ioctl call's are: WDIOC_GETSUPPORT WDIOC_GETSTATUS WDIOC_GETBOOTSTATUS Signed-off-by: Alan Cox Signed-off-by: Wim Van Sebroeck Acked-by: Arnd Bergmann Acked-by: Wolfram Sang --- include/linux/watchdog.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h index 5ab31bfd2906..29ff80807dd4 100644 --- a/include/linux/watchdog.h +++ b/include/linux/watchdog.h @@ -68,6 +68,7 @@ struct watchdog_device; * @start: The routine for starting the watchdog device. * @stop: The routine for stopping the watchdog device. * @ping: The routine that sends a keepalive ping to the watchdog device. + * @status: The routine that shows the status of the watchdog device. * * The watchdog_ops structure contains a list of low-level operations * that control a watchdog device. It also contains the module that owns @@ -81,12 +82,14 @@ struct watchdog_ops { int (*stop)(struct watchdog_device *); /* optional operations */ int (*ping)(struct watchdog_device *); + unsigned int (*status)(struct watchdog_device *); }; /** struct watchdog_device - The structure that defines a watchdog device * * @info: Pointer to a watchdog_info structure. * @ops: Pointer to the list of watchdog operations. + * @bootstatus: Status of the watchdog device at boot. * @driver-data:Pointer to the drivers private data. * @status: Field that contains the devices internal status bits. * @@ -99,6 +102,7 @@ struct watchdog_ops { struct watchdog_device { const struct watchdog_info *info; const struct watchdog_ops *ops; + unsigned int bootstatus; void *driver_data; unsigned long status; /* Bit numbers for status flags */ -- cgit v1.2.3 From 234445b4e4542f3e0f216459245ab369a18adcf2 Mon Sep 17 00:00:00 2001 From: Wim Van Sebroeck Date: Fri, 22 Jul 2011 18:57:55 +0000 Subject: watchdog: WatchDog Timer Driver Core - Add WDIOC_SETOPTIONS ioctl This part add's the WDIOC_SETOPTIONS ioctl functionality to the WatchDog Timer Driver Core framework. Signed-off-by: Alan Cox Signed-off-by: Wim Van Sebroeck Acked-by: Arnd Bergmann Acked-by: Wolfram Sang --- include/linux/watchdog.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h index 29ff80807dd4..db46fe89563e 100644 --- a/include/linux/watchdog.h +++ b/include/linux/watchdog.h @@ -106,6 +106,7 @@ struct watchdog_device { void *driver_data; unsigned long status; /* Bit numbers for status flags */ +#define WDOG_ACTIVE 0 /* Is the watchdog running/active */ #define WDOG_DEV_OPEN 1 /* Opened via /dev/watchdog ? */ }; -- cgit v1.2.3 From 014d694e5d59e4219803cd14deaae496d86e4910 Mon Sep 17 00:00:00 2001 From: Wim Van Sebroeck Date: Fri, 22 Jul 2011 18:58:21 +0000 Subject: watchdog: WatchDog Timer Driver Core - Add WDIOC_SETTIMEOUT and WDIOC_GETTIMEOUT ioctl This part add's the WDIOC_SETTIMEOUT and WDIOC_GETTIMEOUT ioctl functionality to the WatchDog Timer Driver Core framework. Signed-off-by: Alan Cox Signed-off-by: Wim Van Sebroeck Acked-by: Arnd Bergmann Acked-by: Wolfram Sang --- include/linux/watchdog.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h index db46fe89563e..9f33efe199d1 100644 --- a/include/linux/watchdog.h +++ b/include/linux/watchdog.h @@ -69,6 +69,7 @@ struct watchdog_device; * @stop: The routine for stopping the watchdog device. * @ping: The routine that sends a keepalive ping to the watchdog device. * @status: The routine that shows the status of the watchdog device. + * @set_timeout:The routine for setting the watchdog devices timeout value. * * The watchdog_ops structure contains a list of low-level operations * that control a watchdog device. It also contains the module that owns @@ -83,6 +84,7 @@ struct watchdog_ops { /* optional operations */ int (*ping)(struct watchdog_device *); unsigned int (*status)(struct watchdog_device *); + int (*set_timeout)(struct watchdog_device *, unsigned int); }; /** struct watchdog_device - The structure that defines a watchdog device @@ -90,6 +92,7 @@ struct watchdog_ops { * @info: Pointer to a watchdog_info structure. * @ops: Pointer to the list of watchdog operations. * @bootstatus: Status of the watchdog device at boot. + * @timeout: The watchdog devices timeout value. * @driver-data:Pointer to the drivers private data. * @status: Field that contains the devices internal status bits. * @@ -103,6 +106,7 @@ struct watchdog_device { const struct watchdog_info *info; const struct watchdog_ops *ops; unsigned int bootstatus; + unsigned int timeout; void *driver_data; unsigned long status; /* Bit numbers for status flags */ -- cgit v1.2.3 From 017cf0805105496ab1880e236cb3e4bf156fb915 Mon Sep 17 00:00:00 2001 From: Wim Van Sebroeck Date: Fri, 22 Jul 2011 18:58:54 +0000 Subject: watchdog: WatchDog Timer Driver Core - Add Magic Close feature Add support for the Magic Close feature to the WatchDog Timer Driver Core framework. Signed-off-by: Alan Cox Signed-off-by: Wim Van Sebroeck Acked-by: Arnd Bergmann Acked-by: Wolfram Sang --- include/linux/watchdog.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h index 9f33efe199d1..e9881ca2452b 100644 --- a/include/linux/watchdog.h +++ b/include/linux/watchdog.h @@ -112,6 +112,7 @@ struct watchdog_device { /* Bit numbers for status flags */ #define WDOG_ACTIVE 0 /* Is the watchdog running/active */ #define WDOG_DEV_OPEN 1 /* Opened via /dev/watchdog ? */ +#define WDOG_ALLOW_RELEASE 2 /* Did we receive the magic char ? */ }; /* Use the following functions to manipulate watchdog driver specific data */ -- cgit v1.2.3 From 7e192b9c4234d29bdc20ac8d0a67edf7624b4206 Mon Sep 17 00:00:00 2001 From: Wim Van Sebroeck Date: Fri, 22 Jul 2011 18:59:17 +0000 Subject: watchdog: WatchDog Timer Driver Core - Add nowayout feature Add support for the nowayout feature to the WatchDog Timer Driver Core framework. This feature prevents the watchdog timer from being stopped. Signed-off-by: Alan Cox Signed-off-by: Wim Van Sebroeck Acked-by: Arnd Bergmann Acked-by: Wolfram Sang --- include/linux/watchdog.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h index e9881ca2452b..f719883c5141 100644 --- a/include/linux/watchdog.h +++ b/include/linux/watchdog.h @@ -113,6 +113,7 @@ struct watchdog_device { #define WDOG_ACTIVE 0 /* Is the watchdog running/active */ #define WDOG_DEV_OPEN 1 /* Opened via /dev/watchdog ? */ #define WDOG_ALLOW_RELEASE 2 /* Did we receive the magic char ? */ +#define WDOG_NO_WAY_OUT 3 /* Is 'nowayout' feature set ? */ }; /* Use the following functions to manipulate watchdog driver specific data */ -- cgit v1.2.3 From 78d88fc01202b088573c962e2885556a5e99bf74 Mon Sep 17 00:00:00 2001 From: Wim Van Sebroeck Date: Fri, 22 Jul 2011 18:59:49 +0000 Subject: watchdog: WatchDog Timer Driver Core - Add ioctl call Add support for extra ioctl calls by adding a ioctl watchdog operation. This operation will be called before we do our own handling of ioctl commands. This way we can override the internal ioctl command handling and we can also add extra ioctl commands. The ioctl watchdog operation should return the appropriate error codes or -ENOIOCTLCMD if the ioctl command should be handled through the internal ioctl handling of the framework. Signed-off-by: Alan Cox Signed-off-by: Wim Van Sebroeck Acked-by: Arnd Bergmann Acked-by: Wolfram Sang --- include/linux/watchdog.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h index f719883c5141..325d90b6641b 100644 --- a/include/linux/watchdog.h +++ b/include/linux/watchdog.h @@ -70,6 +70,7 @@ struct watchdog_device; * @ping: The routine that sends a keepalive ping to the watchdog device. * @status: The routine that shows the status of the watchdog device. * @set_timeout:The routine for setting the watchdog devices timeout value. + * @ioctl: The routines that handles extra ioctl calls. * * The watchdog_ops structure contains a list of low-level operations * that control a watchdog device. It also contains the module that owns @@ -85,6 +86,7 @@ struct watchdog_ops { int (*ping)(struct watchdog_device *); unsigned int (*status)(struct watchdog_device *); int (*set_timeout)(struct watchdog_device *, unsigned int); + long (*ioctl)(struct watchdog_device *, unsigned int, unsigned long); }; /** struct watchdog_device - The structure that defines a watchdog device -- cgit v1.2.3 From 3f43f68e29f1dcb853d70280c7412fc0ef9a0da6 Mon Sep 17 00:00:00 2001 From: Wim Van Sebroeck Date: Fri, 22 Jul 2011 19:00:16 +0000 Subject: watchdog: WatchDog Timer Driver Core - Add minimum and max timeout Add min_timeout (minimum timeout) and max_timeout values so that the framework can check if the new timeout value is between the minimum and maximum timeout values. If both values are 0, then the framework will leave the check for the watchdog device driver itself. Signed-off-by: Alan Cox Signed-off-by: Wim Van Sebroeck Acked-by: Arnd Bergmann Acked-by: Wolfram Sang --- include/linux/watchdog.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h index 325d90b6641b..111843f88b2a 100644 --- a/include/linux/watchdog.h +++ b/include/linux/watchdog.h @@ -95,6 +95,8 @@ struct watchdog_ops { * @ops: Pointer to the list of watchdog operations. * @bootstatus: Status of the watchdog device at boot. * @timeout: The watchdog devices timeout value. + * @min_timeout:The watchdog devices minimum timeout value. + * @max_timeout:The watchdog devices maximum timeout value. * @driver-data:Pointer to the drivers private data. * @status: Field that contains the devices internal status bits. * @@ -109,6 +111,8 @@ struct watchdog_device { const struct watchdog_ops *ops; unsigned int bootstatus; unsigned int timeout; + unsigned int min_timeout; + unsigned int max_timeout; void *driver_data; unsigned long status; /* Bit numbers for status flags */ -- cgit v1.2.3 From 3038bbdf7404ae3948385cbde30df946579d4e3a Mon Sep 17 00:00:00 2001 From: Jamie Iles Date: Thu, 28 Jul 2011 16:25:41 +0100 Subject: of/gpio: export of_gpio_simple_xlate Allow GPIO drivers to use of_gpio_simple_xlate. This is useful for the generic GPIO driver for example where gpio_chip is embedded in bgpio_chip and doesn't need of_mm_gpio_chip but has a simple 1:1 GPIO mapping. Cc: Anton Vorontsov Cc: Grant Likely Signed-off-by: Jamie Iles Signed-off-by: Grant Likely --- include/linux/of_gpio.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_gpio.h b/include/linux/of_gpio.h index aec8025c786a..52280a2b5e63 100644 --- a/include/linux/of_gpio.h +++ b/include/linux/of_gpio.h @@ -57,6 +57,8 @@ extern int of_mm_gpiochip_add(struct device_node *np, extern void of_gpiochip_add(struct gpio_chip *gc); extern void of_gpiochip_remove(struct gpio_chip *gc); extern struct gpio_chip *of_node_to_gpiochip(struct device_node *np); +extern int of_gpio_simple_xlate(struct gpio_chip *gc, struct device_node *np, + const void *gpio_spec, u32 *flags); #else /* CONFIG_OF_GPIO */ @@ -72,6 +74,13 @@ static inline unsigned int of_gpio_count(struct device_node *np) return 0; } +static inline int of_gpio_simple_xlate(struct gpio_chip *gc, + struct device_node *np, + const void *gpio_spec, u32 *flags) +{ + return -ENOSYS; +} + static inline void of_gpiochip_add(struct gpio_chip *gc) { } static inline void of_gpiochip_remove(struct gpio_chip *gc) { } -- cgit v1.2.3 From 2a11c8ea20bf850b3a2c60db8c2e7497d28aba99 Mon Sep 17 00:00:00 2001 From: Michal Marek Date: Wed, 20 Jul 2011 17:38:57 +0200 Subject: kconfig: Introduce IS_ENABLED(), IS_BUILTIN() and IS_MODULE() Replace the config_is_*() macros with a variant that allows for grepping for usage of CONFIG_* options in the code. Usage: if (IS_ENABLED(CONFIG_NUMA)) or #if IS_ENABLED(CONFIG_NUMA) The IS_ENABLED() macro evaluates to 1 if the argument is set (to either 'y' or 'm'), IS_BUILTIN() tests if the option is 'y' and IS_MODULE() test if the option is 'm'. Only boolean and tristate options are supported. Reviewed-by: Arnaud Lacombe Acked-by: Randy Dunlap Signed-off-by: Michal Marek --- include/linux/kconfig.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) create mode 100644 include/linux/kconfig.h (limited to 'include/linux') diff --git a/include/linux/kconfig.h b/include/linux/kconfig.h new file mode 100644 index 000000000000..067eda0e4b32 --- /dev/null +++ b/include/linux/kconfig.h @@ -0,0 +1,32 @@ +#ifndef __LINUX_KCONFIG_H +#define __LINUX_KCONFIG_H + +#include + +/* + * Helper macros to use CONFIG_ options in C expressions. Note that + * these only work with boolean and tristate options. + */ + +/* + * IS_ENABLED(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y' or 'm', + * 0 otherwise. + * + */ +#define IS_ENABLED(option) \ + (__enabled_ ## option || __enabled_ ## option ## _MODULE) + +/* + * IS_BUILTIN(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y', 0 + * otherwise. For boolean options, this is equivalent to + * IS_ENABLED(CONFIG_FOO). + */ +#define IS_BUILTIN(option) __enabled_ ## option + +/* + * IS_MODULE(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'm', 0 + * otherwise. + */ +#define IS_MODULE(option) __enabled_ ## option ## _MODULE + +#endif /* __LINUX_KCONFIG_H */ -- cgit v1.2.3 From 0c0308066ca53fdf1423895f3a42838b67b3a5a8 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 30 Jul 2011 12:45:35 -0400 Subject: NFS: Fix spurious readdir cookie loop messages If the directory contents change, then we have to accept that the file->f_pos value may shrink if we do a 'search-by-cookie'. In that case, we should turn off the loop detection and let the NFS client try to recover. The patch also fixes a second loop detection bug by ensuring that after turning on the ctx->duped flag, we read at least one new cookie into ctx->dir_cookie before attempting to match with ctx->dup_cookie. Reported-by: Petr Vandrovec Cc: stable@kernel.org [2.6.39+] Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 8b579beb6358..b96fb99072ff 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -99,9 +99,10 @@ struct nfs_open_context { struct nfs_open_dir_context { struct rpc_cred *cred; + unsigned long attr_gencount; __u64 dir_cookie; __u64 dup_cookie; - int duped; + signed char duped; }; /* -- cgit v1.2.3 From 5774ed014f02120db9a6945a1ecebeb97c2acccb Mon Sep 17 00:00:00 2001 From: Vasiliy Kulikov Date: Fri, 29 Jul 2011 03:55:31 +0400 Subject: shm: handle separate PID namespaces case shm_try_destroy_orphaned() and shm_try_destroy_current() didn't handle the case of separate PID namespaces, but a single IPC namespace. If there are tasks with the same PID values using the same shmem object, the wrong destroy decision could be reached. On shm segment creation store the pointer to the creator task in shmid_kernel->shm_creator field and zero it on task exit. Then use the ->shm_creator insread of shm_cprid in both functions. As shmid_kernel object is already locked at this stage, no additional locking is needed. Signed-off-by: Vasiliy Kulikov Acked-by: Serge Hallyn Signed-off-by: Linus Torvalds --- include/linux/shm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/shm.h b/include/linux/shm.h index 7d27ffde0190..92808b86703b 100644 --- a/include/linux/shm.h +++ b/include/linux/shm.h @@ -95,6 +95,9 @@ struct shmid_kernel /* private to the kernel */ pid_t shm_cprid; pid_t shm_lprid; struct user_struct *mlock_user; + + /* The task created the shm object. NULL if the task is dead. */ + struct task_struct *shm_creator; }; /* shm_mode upper byte flags */ -- cgit v1.2.3 From 1c388919d89ca35741e9c4d3255adf87f76f0c06 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Sat, 7 May 2011 20:53:16 +0200 Subject: resources: Add lookup_resource() Add a function to find an existing resource by a resource start address. This allows to implement simple allocators (with a malloc/free-alike API) on top of the resource system. Signed-off-by: Geert Uytterhoeven --- include/linux/ioport.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index e9bb22cba764..63eb429ecbe6 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -132,6 +132,7 @@ extern int allocate_resource(struct resource *root, struct resource *new, resource_size_t, resource_size_t), void *alignf_data); +struct resource *lookup_resource(struct resource *root, resource_size_t start); int adjust_resource(struct resource *res, resource_size_t start, resource_size_t size); resource_size_t resource_alignment(struct resource *res); -- cgit v1.2.3 From a9bae5666d0510ad69bdb437371c9a3e6b770705 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Sat, 30 Jul 2011 20:52:33 -0400 Subject: pnfs: let layoutcommit handle a list of lseg There can be multiple lseg per file, so layoutcommit should be able to handle it. [Needed in v3.0] CC: Stable Tree Signed-off-by: Peng Tao Signed-off-by: Boaz Harrosh Signed-off-by: Jim Rees Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 5b115956abac..feb312716c07 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -262,7 +262,7 @@ struct nfs4_layoutcommit_res { struct nfs4_layoutcommit_data { struct rpc_task task; struct nfs_fattr fattr; - struct pnfs_layout_segment *lseg; + struct list_head lseg_list; struct rpc_cred *cred; struct nfs4_layoutcommit_args args; struct nfs4_layoutcommit_res res; -- cgit v1.2.3 From 7f11d8d38d64739e190581e015a2a2730ff54e2a Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Sat, 30 Jul 2011 20:52:35 -0400 Subject: pnfs: GETDEVICELIST The block driver uses GETDEVICELIST Signed-off-by: Andy Adamson [pass struct nfs_server * to getdevicelist] [get machince creds for getdevicelist] [fix getdevicelist decode sizing] Signed-off-by: Benny Halevy Signed-off-by: Benny Halevy Signed-off-by: Jim Rees Signed-off-by: Trond Myklebust --- include/linux/nfs4.h | 1 + include/linux/nfs_xdr.h | 11 +++++++++++ 2 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index a3c4bc800dce..76f99e8714f3 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -566,6 +566,7 @@ enum { NFSPROC4_CLNT_SECINFO_NO_NAME, NFSPROC4_CLNT_TEST_STATEID, NFSPROC4_CLNT_FREE_STATEID, + NFSPROC4_CLNT_GETDEVICELIST, }; /* nfs41 types */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index feb312716c07..21f333eae3c8 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -235,6 +235,17 @@ struct nfs4_layoutget { gfp_t gfp_flags; }; +struct nfs4_getdevicelist_args { + const struct nfs_fh *fh; + u32 layoutclass; + struct nfs4_sequence_args seq_args; +}; + +struct nfs4_getdevicelist_res { + struct pnfs_devicelist *devlist; + struct nfs4_sequence_res seq_res; +}; + struct nfs4_getdeviceinfo_args { struct pnfs_device *pdev; struct nfs4_sequence_args seq_args; -- cgit v1.2.3 From dae100c2b1b9463996aab9162f2258145c43f7df Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Sat, 30 Jul 2011 20:52:37 -0400 Subject: pnfs: ask for layout_blksize and save it in nfs_server Block layout needs it to determine IO size. Signed-off-by: Fred Isaman Signed-off-by: Tao Guo Signed-off-by: Benny Halevy Signed-off-by: Benny Halevy Signed-off-by: Jim Rees Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 3 ++- include/linux/nfs_xdr.h | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 4faeac8f448a..b2ea8b82d2cb 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -132,7 +132,7 @@ struct nfs_server { #endif #ifdef CONFIG_NFS_V4 - u32 attr_bitmask[2];/* V4 bitmask representing the set + u32 attr_bitmask[3];/* V4 bitmask representing the set of attributes supported on this filesystem */ u32 cache_consistency_bitmask[2]; @@ -145,6 +145,7 @@ struct nfs_server { filesystem */ struct pnfs_layoutdriver_type *pnfs_curr_ld; /* Active layout driver */ struct rpc_wait_queue roc_rpcwaitq; + u32 pnfs_blksize; /* layout_blksize attr */ /* the following fields are protected by nfs_client->cl_lock */ struct rb_root state_owners; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 21f333eae3c8..94f27e56df9c 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -122,6 +122,7 @@ struct nfs_fsinfo { struct timespec time_delta; /* server time granularity */ __u32 lease_time; /* in seconds */ __u32 layouttype; /* supported pnfs layout driver */ + __u32 blksize; /* preferred pnfs io block size */ }; struct nfs_fsstat { @@ -954,7 +955,7 @@ struct nfs4_server_caps_arg { }; struct nfs4_server_caps_res { - u32 attr_bitmask[2]; + u32 attr_bitmask[3]; u32 acl_bitmask; u32 has_links; u32 has_symlinks; -- cgit v1.2.3 From db29c089094b2e686ebc9ed9f002be4a4f94b1f8 Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Sat, 30 Jul 2011 20:52:38 -0400 Subject: pnfs: cleanup_layoutcommit This gives layout driver a chance to cleanup structures they put in at encode_layoutcommit. Signed-off-by: Andy Adamson [fixup layout header pointer for layoutcommit] Signed-off-by: Benny Halevy Signed-off-by: Benny Halevy [rm inode and pnfs_layout_hdr args from cleanup_layoutcommit()] Signed-off-by: Jim Rees Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 94f27e56df9c..569ea5b76fda 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -269,6 +269,7 @@ struct nfs4_layoutcommit_res { struct nfs_fattr *fattr; const struct nfs_server *server; struct nfs4_sequence_res seq_res; + int status; }; struct nfs4_layoutcommit_data { -- cgit v1.2.3 From fe0a9b740881d181e3c96c1f6f6043e252692ffe Mon Sep 17 00:00:00 2001 From: Jim Rees Date: Sat, 30 Jul 2011 20:52:42 -0400 Subject: pnfsblock: add device operations Signed-off-by: Jim Rees Signed-off-by: Fred Isaman Signed-off-by: Benny Halevy Signed-off-by: Benny Halevy [upcall bugfixes] Signed-off-by: Peng Tao Signed-off-by: Trond Myklebust --- include/linux/nfs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs.h b/include/linux/nfs.h index f387919bbc59..8c6ee44914cb 100644 --- a/include/linux/nfs.h +++ b/include/linux/nfs.h @@ -29,6 +29,8 @@ #define NFS_MNT_VERSION 1 #define NFS_MNT3_VERSION 3 +#define NFS_PIPE_DIRNAME "/nfs" + /* * NFS stats. The good thing with these values is that NFSv3 errors are * a superset of NFSv2 errors (with the exception of NFSERR_WFLUSH which -- cgit v1.2.3 From 2f9fd182607e7b3bdca35f6ed7f2fae539f7c46b Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Sat, 30 Jul 2011 20:52:46 -0400 Subject: pnfsblock: call and parse getdevicelist Call GETDEVICELIST during mount, then call and parse GETDEVICEINFO for each device returned. [pnfsblock: get rid of deprecated xdr macros] Signed-off-by: Jim Rees [pnfsblock: fix pnfs_deviceid references] Signed-off-by: Fred Isaman [pnfsblock: fix print format warnings for sector_t and size_t] [pnfs-block: #include ] [pnfsblock: no PNFS_NFS_SERVER] Signed-off-by: Benny Halevy [pnfsblock: fix bug determining size of striped volume] [pnfsblock: fix oops when using multiple devices] Signed-off-by: Fred Isaman Signed-off-by: Benny Halevy Signed-off-by: Benny Halevy [pnfsblock: get rid of vmap and deviceid->area structure] Signed-off-by: Peng Tao Signed-off-by: Jim Rees Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index b2ea8b82d2cb..cc03fc1dfb72 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -146,6 +146,7 @@ struct nfs_server { struct pnfs_layoutdriver_type *pnfs_curr_ld; /* Active layout driver */ struct rpc_wait_queue roc_rpcwaitq; u32 pnfs_blksize; /* layout_blksize attr */ + void *pnfs_ld_data; /* per mount point data */ /* the following fields are protected by nfs_client->cl_lock */ struct rb_root state_owners; -- cgit v1.2.3 From ca7a71824ac957b1b9d3322656c05aad38d7275c Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 2 Jun 2011 19:18:47 +0100 Subject: mfd: Fix bus lock interaction for WM831x IRQ set_type() operation The WM831x IRQ set_type() operation is doing a direct register write when called but since set_type() is called with the bus lock held this isn't legal and could cause deadlocks in the IRQ core. Fix this by posting the updates into an array and syncing in the bus_sync_unlock() callback. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/wm831x/core.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/wm831x/core.h b/include/linux/mfd/wm831x/core.h index 0d515ee1c247..ebead1c401aa 100644 --- a/include/linux/mfd/wm831x/core.h +++ b/include/linux/mfd/wm831x/core.h @@ -237,6 +237,7 @@ struct regulator_dev; #define WM831X_NUM_IRQ_REGS 5 +#define WM831X_NUM_GPIO_REGS 16 enum wm831x_parent { WM8310 = 0x8310, @@ -272,6 +273,9 @@ struct wm831x { int num_gpio; + /* Used by the interrupt controller code to post writes */ + int gpio_update[WM831X_NUM_GPIO_REGS]; + struct mutex auxadc_lock; struct completion auxadc_done; -- cgit v1.2.3 From 266a5e02fe2690637b2318c9fc5c3513937128f4 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 2 Jun 2011 19:18:49 +0100 Subject: mfd: Allow touchscreen to be disabled on wm831x devices Allow platform data to flag the touchscreen as disabled so that if the touch driver is built in we don't end up causing lots of work by spuriously detecting touchscreen activity on systems where it isn't in use. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/wm831x/pdata.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/wm831x/pdata.h b/include/linux/mfd/wm831x/pdata.h index ff42d700293f..0ba24599fe51 100644 --- a/include/linux/mfd/wm831x/pdata.h +++ b/include/linux/mfd/wm831x/pdata.h @@ -120,6 +120,9 @@ struct wm831x_pdata { /** Put the /IRQ line into CMOS mode */ bool irq_cmos; + /** Disable the touchscreen */ + bool disable_touch; + int irq_base; int gpio_base; int gpio_defaults[WM831X_GPIO_NUM]; -- cgit v1.2.3 From 5c05a8d1f0105ada3cb04be5b70686fc6b272619 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 2 Jun 2011 19:18:51 +0100 Subject: mfd: Support dynamic allocation of IRQ range for wm831x Use irq_allocate_desc() to get the IRQ range, which turns into a noop on non-sparse systems. Since all existing users are non-sparse there should be no compatibility issues. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/wm831x/core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/wm831x/core.h b/include/linux/mfd/wm831x/core.h index ebead1c401aa..9564cf315276 100644 --- a/include/linux/mfd/wm831x/core.h +++ b/include/linux/mfd/wm831x/core.h @@ -262,7 +262,7 @@ struct wm831x { int irq; /* Our chip IRQ */ struct mutex irq_lock; - unsigned int irq_base; + int irq_base; int irq_masks_cur[WM831X_NUM_IRQ_REGS]; /* Currently active value */ int irq_masks_cache[WM831X_NUM_IRQ_REGS]; /* Cached hardware value */ -- cgit v1.2.3 From c1a82780b41e78f31636c49279ce940afe60a453 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 2 Jun 2011 19:18:52 +0100 Subject: mfd: Read wm831x AUXADC conversion results before acknowledging interrupt Ensure that there's no possibility of loosing an AUXADC interrupt by reading the conversion result in the IRQ handler when using interrupts. Otherwise it's possible that under very heavy load a new conversion could be initiated before the acknowledgement for a previous interrupt has happened. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/wm831x/core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/wm831x/core.h b/include/linux/mfd/wm831x/core.h index 9564cf315276..592e4fd6ab3f 100644 --- a/include/linux/mfd/wm831x/core.h +++ b/include/linux/mfd/wm831x/core.h @@ -278,6 +278,7 @@ struct wm831x { struct mutex auxadc_lock; struct completion auxadc_done; + u16 auxadc_data; /* The WM831x has a security key blocking access to certain * registers. The mutex is taken by the accessors for locking -- cgit v1.2.3 From 78bb3688ea1830672b8095fb6388593f582cd591 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 7 Jun 2011 11:47:28 +0100 Subject: mfd: Support multiple active WM831x AUXADC conversions The WM831x AUXADC hardware can schedule multiple conversions at once, allowing higher performance when more than one source is in use as we can have the hardware start new conversions without having to wait for a register write. Take advantage of this in the interrupt driven case, maintaining a list of callers that are waiting for AUXADC conversions and completing them all simultaneously. The external interface of the AUXADC is not changed so there will be limited use of the feature immediately. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/wm831x/core.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/wm831x/core.h b/include/linux/mfd/wm831x/core.h index 592e4fd6ab3f..9fa14cdc1590 100644 --- a/include/linux/mfd/wm831x/core.h +++ b/include/linux/mfd/wm831x/core.h @@ -17,6 +17,7 @@ #include #include +#include /* * Register values. @@ -249,6 +250,12 @@ enum wm831x_parent { WM8326 = 0x8326, }; +struct wm831x; +enum wm831x_auxadc; + +typedef int (*wm831x_auxadc_read_fn)(struct wm831x *wm831x, + enum wm831x_auxadc input); + struct wm831x { struct mutex io_lock; @@ -277,8 +284,9 @@ struct wm831x { int gpio_update[WM831X_NUM_GPIO_REGS]; struct mutex auxadc_lock; - struct completion auxadc_done; - u16 auxadc_data; + struct list_head auxadc_pending; + u16 auxadc_active; + wm831x_auxadc_read_fn auxadc_read; /* The WM831x has a security key blocking access to certain * registers. The mutex is taken by the accessors for locking @@ -305,5 +313,6 @@ void wm831x_device_exit(struct wm831x *wm831x); int wm831x_device_suspend(struct wm831x *wm831x); int wm831x_irq_init(struct wm831x *wm831x, int irq); void wm831x_irq_exit(struct wm831x *wm831x); +void wm831x_auxadc_init(struct wm831x *wm831x); #endif -- cgit v1.2.3 From 36e52873c6393b569f2befcdd1847929211892b8 Mon Sep 17 00:00:00 2001 From: Margarita Olaya Date: Thu, 9 Jun 2011 14:50:00 -0500 Subject: mfd: tps65912: Add new mfd device The tps65912 chip is a power management IC. It contains the following components: - Regulators - GPIO controller The core driver is registered as a platform driver, it provides communication through I2C and SPI interfaces. Signed-off-by: Margarita Olaya Cabrera Acked-by: Samuel Ortiz Acked-by: Liam Girdwood Signed-off-by: Samuel Ortiz --- include/linux/mfd/tps65912.h | 321 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 321 insertions(+) create mode 100644 include/linux/mfd/tps65912.h (limited to 'include/linux') diff --git a/include/linux/mfd/tps65912.h b/include/linux/mfd/tps65912.h new file mode 100644 index 000000000000..48d3b53316a9 --- /dev/null +++ b/include/linux/mfd/tps65912.h @@ -0,0 +1,321 @@ +/* + * tps65912.h -- TI TPS6591x + * + * Copyright 2011 Texas Instruments Inc. + * + * Author: Margarita Olaya + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + */ + +#ifndef __LINUX_MFD_TPS65912_H +#define __LINUX_MFD_TPS65912_H + +/* TPS regulator type list */ +#define REGULATOR_LDO 0 +#define REGULATOR_DCDC 1 + +/* + * List of registers for TPS65912 + */ + +#define TPS65912_DCDC1_CTRL 0x00 +#define TPS65912_DCDC2_CTRL 0x01 +#define TPS65912_DCDC3_CTRL 0x02 +#define TPS65912_DCDC4_CTRL 0x03 +#define TPS65912_DCDC1_OP 0x04 +#define TPS65912_DCDC1_AVS 0x05 +#define TPS65912_DCDC1_LIMIT 0x06 +#define TPS65912_DCDC2_OP 0x07 +#define TPS65912_DCDC2_AVS 0x08 +#define TPS65912_DCDC2_LIMIT 0x09 +#define TPS65912_DCDC3_OP 0x0A +#define TPS65912_DCDC3_AVS 0x0B +#define TPS65912_DCDC3_LIMIT 0x0C +#define TPS65912_DCDC4_OP 0x0D +#define TPS65912_DCDC4_AVS 0x0E +#define TPS65912_DCDC4_LIMIT 0x0F +#define TPS65912_LDO1_OP 0x10 +#define TPS65912_LDO1_AVS 0x11 +#define TPS65912_LDO1_LIMIT 0x12 +#define TPS65912_LDO2_OP 0x13 +#define TPS65912_LDO2_AVS 0x14 +#define TPS65912_LDO2_LIMIT 0x15 +#define TPS65912_LDO3_OP 0x16 +#define TPS65912_LDO3_AVS 0x17 +#define TPS65912_LDO3_LIMIT 0x18 +#define TPS65912_LDO4_OP 0x19 +#define TPS65912_LDO4_AVS 0x1A +#define TPS65912_LDO4_LIMIT 0x1B +#define TPS65912_LDO5 0x1C +#define TPS65912_LDO6 0x1D +#define TPS65912_LDO7 0x1E +#define TPS65912_LDO8 0x1F +#define TPS65912_LDO9 0x20 +#define TPS65912_LDO10 0x21 +#define TPS65912_THRM 0x22 +#define TPS65912_CLK32OUT 0x23 +#define TPS65912_DEVCTRL 0x24 +#define TPS65912_DEVCTRL2 0x25 +#define TPS65912_I2C_SPI_CFG 0x26 +#define TPS65912_KEEP_ON 0x27 +#define TPS65912_KEEP_ON2 0x28 +#define TPS65912_SET_OFF1 0x29 +#define TPS65912_SET_OFF2 0x2A +#define TPS65912_DEF_VOLT 0x2B +#define TPS65912_DEF_VOLT_MAPPING 0x2C +#define TPS65912_DISCHARGE 0x2D +#define TPS65912_DISCHARGE2 0x2E +#define TPS65912_EN1_SET1 0x2F +#define TPS65912_EN1_SET2 0x30 +#define TPS65912_EN2_SET1 0x31 +#define TPS65912_EN2_SET2 0x32 +#define TPS65912_EN3_SET1 0x33 +#define TPS65912_EN3_SET2 0x34 +#define TPS65912_EN4_SET1 0x35 +#define TPS65912_EN4_SET2 0x36 +#define TPS65912_PGOOD 0x37 +#define TPS65912_PGOOD2 0x38 +#define TPS65912_INT_STS 0x39 +#define TPS65912_INT_MSK 0x3A +#define TPS65912_INT_STS2 0x3B +#define TPS65912_INT_MSK2 0x3C +#define TPS65912_INT_STS3 0x3D +#define TPS65912_INT_MSK3 0x3E +#define TPS65912_INT_STS4 0x3F +#define TPS65912_INT_MSK4 0x40 +#define TPS65912_GPIO1 0x41 +#define TPS65912_GPIO2 0x42 +#define TPS65912_GPIO3 0x43 +#define TPS65912_GPIO4 0x44 +#define TPS65912_GPIO5 0x45 +#define TPS65912_VMON 0x46 +#define TPS65912_LEDA_CTRL1 0x47 +#define TPS65912_LEDA_CTRL2 0x48 +#define TPS65912_LEDA_CTRL3 0x49 +#define TPS65912_LEDA_CTRL4 0x4A +#define TPS65912_LEDA_CTRL5 0x4B +#define TPS65912_LEDA_CTRL6 0x4C +#define TPS65912_LEDA_CTRL7 0x4D +#define TPS65912_LEDA_CTRL8 0x4E +#define TPS65912_LEDB_CTRL1 0x4F +#define TPS65912_LEDB_CTRL2 0x50 +#define TPS65912_LEDB_CTRL3 0x51 +#define TPS65912_LEDB_CTRL4 0x52 +#define TPS65912_LEDB_CTRL5 0x53 +#define TPS65912_LEDB_CTRL6 0x54 +#define TPS65912_LEDB_CTRL7 0x55 +#define TPS65912_LEDB_CTRL8 0x56 +#define TPS65912_LEDC_CTRL1 0x57 +#define TPS65912_LEDC_CTRL2 0x58 +#define TPS65912_LEDC_CTRL3 0x59 +#define TPS65912_LEDC_CTRL4 0x5A +#define TPS65912_LEDC_CTRL5 0x5B +#define TPS65912_LEDC_CTRL6 0x5C +#define TPS65912_LEDC_CTRL7 0x5D +#define TPS65912_LEDC_CTRL8 0x5E +#define TPS65912_LED_RAMP_UP_TIME 0x5F +#define TPS65912_LED_RAMP_DOWN_TIME 0x60 +#define TPS65912_LED_SEQ_EN 0x61 +#define TPS65912_LOADSWITCH 0x62 +#define TPS65912_SPARE 0x63 +#define TPS65912_VERNUM 0x64 +#define TPS6591X_MAX_REGISTER 0x64 + +/* IRQ Definitions */ +#define TPS65912_IRQ_PWRHOLD_F 0 +#define TPS65912_IRQ_VMON 1 +#define TPS65912_IRQ_PWRON 2 +#define TPS65912_IRQ_PWRON_LP 3 +#define TPS65912_IRQ_PWRHOLD_R 4 +#define TPS65912_IRQ_HOTDIE 5 +#define TPS65912_IRQ_GPIO1_R 6 +#define TPS65912_IRQ_GPIO1_F 7 +#define TPS65912_IRQ_GPIO2_R 8 +#define TPS65912_IRQ_GPIO2_F 9 +#define TPS65912_IRQ_GPIO3_R 10 +#define TPS65912_IRQ_GPIO3_F 11 +#define TPS65912_IRQ_GPIO4_R 12 +#define TPS65912_IRQ_GPIO4_F 13 +#define TPS65912_IRQ_GPIO5_R 14 +#define TPS65912_IRQ_GPIO5_F 15 +#define TPS65912_IRQ_PGOOD_DCDC1 16 +#define TPS65912_IRQ_PGOOD_DCDC2 17 +#define TPS65912_IRQ_PGOOD_DCDC3 18 +#define TPS65912_IRQ_PGOOD_DCDC4 19 +#define TPS65912_IRQ_PGOOD_LDO1 20 +#define TPS65912_IRQ_PGOOD_LDO2 21 +#define TPS65912_IRQ_PGOOD_LDO3 22 +#define TPS65912_IRQ_PGOOD_LDO4 23 +#define TPS65912_IRQ_PGOOD_LDO5 24 +#define TPS65912_IRQ_PGOOD_LDO6 25 +#define TPS65912_IRQ_PGOOD_LDO7 26 +#define TPS65912_IRQ_PGOOD_LD08 27 +#define TPS65912_IRQ_PGOOD_LDO9 28 +#define TPS65912_IRQ_PGOOD_LDO10 29 + +#define TPS65912_NUM_IRQ 30 + +/* GPIO 1 and 2 Register Definitions */ +#define GPIO_SLEEP_MASK 0x80 +#define GPIO_SLEEP_SHIFT 7 +#define GPIO_DEB_MASK 0x10 +#define GPIO_DEB_SHIFT 4 +#define GPIO_CFG_MASK 0x04 +#define GPIO_CFG_SHIFT 2 +#define GPIO_STS_MASK 0x02 +#define GPIO_STS_SHIFT 1 +#define GPIO_SET_MASK 0x01 +#define GPIO_SET_SHIFT 0 + +/* GPIO 3 Register Definitions */ +#define GPIO3_SLEEP_MASK 0x80 +#define GPIO3_SLEEP_SHIFT 7 +#define GPIO3_SEL_MASK 0x40 +#define GPIO3_SEL_SHIFT 6 +#define GPIO3_ODEN_MASK 0x20 +#define GPIO3_ODEN_SHIFT 5 +#define GPIO3_DEB_MASK 0x10 +#define GPIO3_DEB_SHIFT 4 +#define GPIO3_PDEN_MASK 0x08 +#define GPIO3_PDEN_SHIFT 3 +#define GPIO3_CFG_MASK 0x04 +#define GPIO3_CFG_SHIFT 2 +#define GPIO3_STS_MASK 0x02 +#define GPIO3_STS_SHIFT 1 +#define GPIO3_SET_MASK 0x01 +#define GPIO3_SET_SHIFT 0 + +/* GPIO 4 Register Definitions */ +#define GPIO4_SLEEP_MASK 0x80 +#define GPIO4_SLEEP_SHIFT 7 +#define GPIO4_SEL_MASK 0x40 +#define GPIO4_SEL_SHIFT 6 +#define GPIO4_ODEN_MASK 0x20 +#define GPIO4_ODEN_SHIFT 5 +#define GPIO4_DEB_MASK 0x10 +#define GPIO4_DEB_SHIFT 4 +#define GPIO4_PDEN_MASK 0x08 +#define GPIO4_PDEN_SHIFT 3 +#define GPIO4_CFG_MASK 0x04 +#define GPIO4_CFG_SHIFT 2 +#define GPIO4_STS_MASK 0x02 +#define GPIO4_STS_SHIFT 1 +#define GPIO4_SET_MASK 0x01 +#define GPIO4_SET_SHIFT 0 + +/* Register THERM (0x80) register.RegisterDescription */ +#define THERM_THERM_HD_MASK 0x20 +#define THERM_THERM_HD_SHIFT 5 +#define THERM_THERM_TS_MASK 0x10 +#define THERM_THERM_TS_SHIFT 4 +#define THERM_THERM_HDSEL_MASK 0x0C +#define THERM_THERM_HDSEL_SHIFT 2 +#define THERM_RSVD1_MASK 0x02 +#define THERM_RSVD1_SHIFT 1 +#define THERM_THERM_STATE_MASK 0x01 +#define THERM_THERM_STATE_SHIFT 0 + +/* Register DCDCCTRL1 register.RegisterDescription */ +#define DCDCCTRL_VCON_ENABLE_MASK 0x80 +#define DCDCCTRL_VCON_ENABLE_SHIFT 7 +#define DCDCCTRL_VCON_RANGE1_MASK 0x40 +#define DCDCCTRL_VCON_RANGE1_SHIFT 6 +#define DCDCCTRL_VCON_RANGE0_MASK 0x20 +#define DCDCCTRL_VCON_RANGE0_SHIFT 5 +#define DCDCCTRL_TSTEP2_MASK 0x10 +#define DCDCCTRL_TSTEP2_SHIFT 4 +#define DCDCCTRL_TSTEP1_MASK 0x08 +#define DCDCCTRL_TSTEP1_SHIFT 3 +#define DCDCCTRL_TSTEP0_MASK 0x04 +#define DCDCCTRL_TSTEP0_SHIFT 2 +#define DCDCCTRL_DCDC1_MODE_MASK 0x02 +#define DCDCCTRL_DCDC1_MODE_SHIFT 1 + +/* Register DCDCCTRL2 and DCDCCTRL3 register.RegisterDescription */ +#define DCDCCTRL_TSTEP2_MASK 0x10 +#define DCDCCTRL_TSTEP2_SHIFT 4 +#define DCDCCTRL_TSTEP1_MASK 0x08 +#define DCDCCTRL_TSTEP1_SHIFT 3 +#define DCDCCTRL_TSTEP0_MASK 0x04 +#define DCDCCTRL_TSTEP0_SHIFT 2 +#define DCDCCTRL_DCDC_MODE_MASK 0x02 +#define DCDCCTRL_DCDC_MODE_SHIFT 1 +#define DCDCCTRL_RSVD0_MASK 0x01 +#define DCDCCTRL_RSVD0_SHIFT 0 + +/* Register DCDCCTRL4 register.RegisterDescription */ +#define DCDCCTRL_RAMP_TIME_MASK 0x01 +#define DCDCCTRL_RAMP_TIME_SHIFT 0 + +/* Register DCDCx_AVS */ +#define DCDC_AVS_ENABLE_MASK 0x80 +#define DCDC_AVS_ENABLE_SHIFT 7 +#define DCDC_AVS_ECO_MASK 0x40 +#define DCDC_AVS_ECO_SHIFT 6 + +/* Register DCDCx_LIMIT */ +#define DCDC_LIMIT_RANGE_MASK 0xC0 +#define DCDC_LIMIT_RANGE_SHIFT 6 +#define DCDC_LIMIT_MAX_SEL_MASK 0x3F +#define DCDC_LIMIT_MAX_SEL_SHIFT 0 + +/** + * struct tps65912_board + * Board platform dat may be used to initialize regulators. + */ +struct tps65912_board { + int is_dcdc1_avs; + int is_dcdc2_avs; + int is_dcdc3_avs; + int is_dcdc4_avs; + struct regulator_init_data *tps65912_pmic_init_data; +}; + +/** + * struct tps65912 - tps65912 sub-driver chip access routines + */ + +struct tps65912 { + struct device *dev; + /* for read/write acces */ + struct mutex io_mutex; + + /* For device IO interfaces: I2C or SPI */ + void *control_data; + + int (*read)(struct tps65912 *tps65912, u8 reg, int size, void *dest); + int (*write)(struct tps65912 *tps65912, u8 reg, int size, void *src); + + /* Client devices */ + struct tps65912_pmic *pmic; + + /* GPIO Handling */ + struct gpio_chip gpio; + + /* IRQ Handling */ + struct mutex irq_lock; + int chip_irq; + int irq_base; + int irq_num; + u32 irq_mask; +}; + +struct tps65912_platform_data { + int irq_base; +}; + +unsigned int tps_chip(void); + +int tps65912_set_bits(struct tps65912 *tps65912, u8 reg, u8 mask); +int tps65912_clear_bits(struct tps65912 *tps65912, u8 reg, u8 mask); +int tps65912_reg_read(struct tps65912 *tps65912, u8 reg); +int tps65912_reg_write(struct tps65912 *tps65912, u8 reg, u8 val); +int tps65912_device_init(struct tps65912 *tps65912); +void tps65912_device_exit(struct tps65912 *tps65912); + +#endif /* __LINUX_MFD_TPS65912_H */ -- cgit v1.2.3 From d49a0f3f14a763242b71244019d7881ee06e0658 Mon Sep 17 00:00:00 2001 From: Margarita Olaya Date: Thu, 9 Jun 2011 14:50:13 -0500 Subject: tps65912: irq: add interrupt controller This module controls the interrupt handling for the tps65912. The interrupt sources can be the following: - GPIO - PWRON signal - PWRHOLD signal - Temperature detection Signed-off-by: Margarita Olaya Cabrera Acked-by: Samuel Ortiz Acked-by: Liam Girdwood Signed-off-by: Samuel Ortiz --- include/linux/mfd/tps65912.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/tps65912.h b/include/linux/mfd/tps65912.h index 48d3b53316a9..be60fb23b583 100644 --- a/include/linux/mfd/tps65912.h +++ b/include/linux/mfd/tps65912.h @@ -273,6 +273,8 @@ struct tps65912_board { int is_dcdc2_avs; int is_dcdc3_avs; int is_dcdc4_avs; + int irq; + int irq_base; struct regulator_init_data *tps65912_pmic_init_data; }; @@ -306,6 +308,7 @@ struct tps65912 { }; struct tps65912_platform_data { + int irq; int irq_base; }; @@ -317,5 +320,7 @@ int tps65912_reg_read(struct tps65912 *tps65912, u8 reg); int tps65912_reg_write(struct tps65912 *tps65912, u8 reg, u8 val); int tps65912_device_init(struct tps65912 *tps65912); void tps65912_device_exit(struct tps65912 *tps65912); +int tps65912_irq_init(struct tps65912 *tps65912, int irq, + struct tps65912_platform_data *pdata); #endif /* __LINUX_MFD_TPS65912_H */ -- cgit v1.2.3 From 668a6cc710ee054af2b059d27bbec746ead0fbca Mon Sep 17 00:00:00 2001 From: Margarita Olaya Date: Thu, 9 Jun 2011 14:50:19 -0500 Subject: tps65912: gpio: add gpio driver TPS65912 has five GPIOs that can be configured for different purposes. Signed-off-by: Margarita Olaya Cabrera Acked-by: Grant Likely Acked-by: Liam Girdwood Signed-off-by: Samuel Ortiz --- include/linux/mfd/tps65912.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/tps65912.h b/include/linux/mfd/tps65912.h index be60fb23b583..aaceab402ec5 100644 --- a/include/linux/mfd/tps65912.h +++ b/include/linux/mfd/tps65912.h @@ -275,6 +275,7 @@ struct tps65912_board { int is_dcdc4_avs; int irq; int irq_base; + int gpio_base; struct regulator_init_data *tps65912_pmic_init_data; }; -- cgit v1.2.3 From 0a1b089738cf2165ee8678e2483fce3c40389d4a Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 9 Jun 2011 23:57:57 +0200 Subject: mfd: Clean-up ab8500 register file This adds a previously undefined test register and removed a number of double-defined accessory detect registers (they are already defined higher up in the file. Signed-off-by: Linus Walleij Signed-off-by: Samuel Ortiz --- include/linux/mfd/ab8500.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/ab8500.h b/include/linux/mfd/ab8500.h index b31843075198..838c6b487cc5 100644 --- a/include/linux/mfd/ab8500.h +++ b/include/linux/mfd/ab8500.h @@ -28,6 +28,7 @@ #define AB8500_INTERRUPT 0xE #define AB8500_RTC 0xF #define AB8500_MISC 0x10 +#define AB8500_DEVELOPMENT 0x11 #define AB8500_DEBUG 0x12 #define AB8500_PROD_TEST 0x13 #define AB8500_OTP_EMUL 0x15 @@ -74,13 +75,6 @@ #define AB8500_INT_ACC_DETECT_21DB_F 37 #define AB8500_INT_ACC_DETECT_21DB_R 38 #define AB8500_INT_GP_SW_ADC_CONV_END 39 -#define AB8500_INT_ACC_DETECT_1DB_F 33 -#define AB8500_INT_ACC_DETECT_1DB_R 34 -#define AB8500_INT_ACC_DETECT_22DB_F 35 -#define AB8500_INT_ACC_DETECT_22DB_R 36 -#define AB8500_INT_ACC_DETECT_21DB_F 37 -#define AB8500_INT_ACC_DETECT_21DB_R 38 -#define AB8500_INT_GP_SW_ADC_CONV_END 39 #define AB8500_INT_GPIO6R 40 #define AB8500_INT_GPIO7R 41 #define AB8500_INT_GPIO8R 42 -- cgit v1.2.3 From ec2328c30bf09fe31e77889090eeb1a965325f53 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 20 Jun 2011 11:47:55 +0100 Subject: mfd: Implement tps65910 IRQ cleanup The tps65910_irq_exit() cleanup function was generating a warning from sparse due to the lack of a prototype. This wasn't causing GCC warnings as the driver wasn't cleaning up its IRQs on exit at all so there was no use of an unprototyped function. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/tps65910.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/tps65910.h b/include/linux/mfd/tps65910.h index 73572c65d04f..82b4c8801a4f 100644 --- a/include/linux/mfd/tps65910.h +++ b/include/linux/mfd/tps65910.h @@ -791,6 +791,7 @@ int tps65910_clear_bits(struct tps65910 *tps65910, u8 reg, u8 mask); void tps65910_gpio_init(struct tps65910 *tps65910, int gpio_base); int tps65910_irq_init(struct tps65910 *tps65910, int irq, struct tps65910_platform_data *pdata); +int tps65910_irq_exit(struct tps65910 *tps65910); static inline int tps65910_chip_id(struct tps65910 *tps65910) { -- cgit v1.2.3 From c7e1da477293b4b5e0bef3639b3734e28d5d55f7 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 21 Jun 2011 11:12:23 +0100 Subject: mfd: Add WM831x clock control register definitions Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/wm831x/core.h | 101 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 101 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/wm831x/core.h b/include/linux/mfd/wm831x/core.h index 9fa14cdc1590..8dda8ded5cda 100644 --- a/include/linux/mfd/wm831x/core.h +++ b/include/linux/mfd/wm831x/core.h @@ -235,6 +235,107 @@ #define WM831X_ON_PIN_TO_SHIFT 0 /* ON_PIN_TO - [1:0] */ #define WM831X_ON_PIN_TO_WIDTH 2 /* ON_PIN_TO - [1:0] */ +/* + * R16528 (0x4090) - Clock Control 1 + */ +#define WM831X_CLKOUT_ENA 0x8000 /* CLKOUT_ENA */ +#define WM831X_CLKOUT_ENA_MASK 0x8000 /* CLKOUT_ENA */ +#define WM831X_CLKOUT_ENA_SHIFT 15 /* CLKOUT_ENA */ +#define WM831X_CLKOUT_ENA_WIDTH 1 /* CLKOUT_ENA */ +#define WM831X_CLKOUT_OD 0x2000 /* CLKOUT_OD */ +#define WM831X_CLKOUT_OD_MASK 0x2000 /* CLKOUT_OD */ +#define WM831X_CLKOUT_OD_SHIFT 13 /* CLKOUT_OD */ +#define WM831X_CLKOUT_OD_WIDTH 1 /* CLKOUT_OD */ +#define WM831X_CLKOUT_SLOT_MASK 0x0700 /* CLKOUT_SLOT - [10:8] */ +#define WM831X_CLKOUT_SLOT_SHIFT 8 /* CLKOUT_SLOT - [10:8] */ +#define WM831X_CLKOUT_SLOT_WIDTH 3 /* CLKOUT_SLOT - [10:8] */ +#define WM831X_CLKOUT_SLPSLOT_MASK 0x0070 /* CLKOUT_SLPSLOT - [6:4] */ +#define WM831X_CLKOUT_SLPSLOT_SHIFT 4 /* CLKOUT_SLPSLOT - [6:4] */ +#define WM831X_CLKOUT_SLPSLOT_WIDTH 3 /* CLKOUT_SLPSLOT - [6:4] */ +#define WM831X_CLKOUT_SRC 0x0001 /* CLKOUT_SRC */ +#define WM831X_CLKOUT_SRC_MASK 0x0001 /* CLKOUT_SRC */ +#define WM831X_CLKOUT_SRC_SHIFT 0 /* CLKOUT_SRC */ +#define WM831X_CLKOUT_SRC_WIDTH 1 /* CLKOUT_SRC */ + +/* + * R16529 (0x4091) - Clock Control 2 + */ +#define WM831X_XTAL_INH 0x8000 /* XTAL_INH */ +#define WM831X_XTAL_INH_MASK 0x8000 /* XTAL_INH */ +#define WM831X_XTAL_INH_SHIFT 15 /* XTAL_INH */ +#define WM831X_XTAL_INH_WIDTH 1 /* XTAL_INH */ +#define WM831X_XTAL_ENA 0x2000 /* XTAL_ENA */ +#define WM831X_XTAL_ENA_MASK 0x2000 /* XTAL_ENA */ +#define WM831X_XTAL_ENA_SHIFT 13 /* XTAL_ENA */ +#define WM831X_XTAL_ENA_WIDTH 1 /* XTAL_ENA */ +#define WM831X_XTAL_BKUPENA 0x1000 /* XTAL_BKUPENA */ +#define WM831X_XTAL_BKUPENA_MASK 0x1000 /* XTAL_BKUPENA */ +#define WM831X_XTAL_BKUPENA_SHIFT 12 /* XTAL_BKUPENA */ +#define WM831X_XTAL_BKUPENA_WIDTH 1 /* XTAL_BKUPENA */ +#define WM831X_FLL_AUTO 0x0080 /* FLL_AUTO */ +#define WM831X_FLL_AUTO_MASK 0x0080 /* FLL_AUTO */ +#define WM831X_FLL_AUTO_SHIFT 7 /* FLL_AUTO */ +#define WM831X_FLL_AUTO_WIDTH 1 /* FLL_AUTO */ +#define WM831X_FLL_AUTO_FREQ_MASK 0x0007 /* FLL_AUTO_FREQ - [2:0] */ +#define WM831X_FLL_AUTO_FREQ_SHIFT 0 /* FLL_AUTO_FREQ - [2:0] */ +#define WM831X_FLL_AUTO_FREQ_WIDTH 3 /* FLL_AUTO_FREQ - [2:0] */ + +/* + * R16530 (0x4092) - FLL Control 1 + */ +#define WM831X_FLL_FRAC 0x0004 /* FLL_FRAC */ +#define WM831X_FLL_FRAC_MASK 0x0004 /* FLL_FRAC */ +#define WM831X_FLL_FRAC_SHIFT 2 /* FLL_FRAC */ +#define WM831X_FLL_FRAC_WIDTH 1 /* FLL_FRAC */ +#define WM831X_FLL_OSC_ENA 0x0002 /* FLL_OSC_ENA */ +#define WM831X_FLL_OSC_ENA_MASK 0x0002 /* FLL_OSC_ENA */ +#define WM831X_FLL_OSC_ENA_SHIFT 1 /* FLL_OSC_ENA */ +#define WM831X_FLL_OSC_ENA_WIDTH 1 /* FLL_OSC_ENA */ +#define WM831X_FLL_ENA 0x0001 /* FLL_ENA */ +#define WM831X_FLL_ENA_MASK 0x0001 /* FLL_ENA */ +#define WM831X_FLL_ENA_SHIFT 0 /* FLL_ENA */ +#define WM831X_FLL_ENA_WIDTH 1 /* FLL_ENA */ + +/* + * R16531 (0x4093) - FLL Control 2 + */ +#define WM831X_FLL_OUTDIV_MASK 0x3F00 /* FLL_OUTDIV - [13:8] */ +#define WM831X_FLL_OUTDIV_SHIFT 8 /* FLL_OUTDIV - [13:8] */ +#define WM831X_FLL_OUTDIV_WIDTH 6 /* FLL_OUTDIV - [13:8] */ +#define WM831X_FLL_CTRL_RATE_MASK 0x0070 /* FLL_CTRL_RATE - [6:4] */ +#define WM831X_FLL_CTRL_RATE_SHIFT 4 /* FLL_CTRL_RATE - [6:4] */ +#define WM831X_FLL_CTRL_RATE_WIDTH 3 /* FLL_CTRL_RATE - [6:4] */ +#define WM831X_FLL_FRATIO_MASK 0x0007 /* FLL_FRATIO - [2:0] */ +#define WM831X_FLL_FRATIO_SHIFT 0 /* FLL_FRATIO - [2:0] */ +#define WM831X_FLL_FRATIO_WIDTH 3 /* FLL_FRATIO - [2:0] */ + +/* + * R16532 (0x4094) - FLL Control 3 + */ +#define WM831X_FLL_K_MASK 0xFFFF /* FLL_K - [15:0] */ +#define WM831X_FLL_K_SHIFT 0 /* FLL_K - [15:0] */ +#define WM831X_FLL_K_WIDTH 16 /* FLL_K - [15:0] */ + +/* + * R16533 (0x4095) - FLL Control 4 + */ +#define WM831X_FLL_N_MASK 0x7FE0 /* FLL_N - [14:5] */ +#define WM831X_FLL_N_SHIFT 5 /* FLL_N - [14:5] */ +#define WM831X_FLL_N_WIDTH 10 /* FLL_N - [14:5] */ +#define WM831X_FLL_GAIN_MASK 0x000F /* FLL_GAIN - [3:0] */ +#define WM831X_FLL_GAIN_SHIFT 0 /* FLL_GAIN - [3:0] */ +#define WM831X_FLL_GAIN_WIDTH 4 /* FLL_GAIN - [3:0] */ + +/* + * R16534 (0x4096) - FLL Control 5 + */ +#define WM831X_FLL_CLK_REF_DIV_MASK 0x0018 /* FLL_CLK_REF_DIV - [4:3] */ +#define WM831X_FLL_CLK_REF_DIV_SHIFT 3 /* FLL_CLK_REF_DIV - [4:3] */ +#define WM831X_FLL_CLK_REF_DIV_WIDTH 2 /* FLL_CLK_REF_DIV - [4:3] */ +#define WM831X_FLL_CLK_SRC_MASK 0x0003 /* FLL_CLK_SRC - [1:0] */ +#define WM831X_FLL_CLK_SRC_SHIFT 0 /* FLL_CLK_SRC - [1:0] */ +#define WM831X_FLL_CLK_SRC_WIDTH 2 /* FLL_CLK_SRC - [1:0] */ + struct regulator_dev; #define WM831X_NUM_IRQ_REGS 5 -- cgit v1.2.3 From 4dcaa6b6df354fa44b3072bed3cb13aad7e5fbd4 Mon Sep 17 00:00:00 2001 From: Om Prakash Date: Mon, 27 Jun 2011 09:54:22 +0200 Subject: mfd: Fix missing stmpe kerneldoc Generating kerneldoc for STMPE result in warnings, so fix this by adding missing documentation. Signed-off-by: Om Prakash Reviewed-by: Rabin Vincent Reviewed-by: Jonas Aberg Reviewed-by: Srinidhi Kasagar Signed-off-by: Linus Walleij Signed-off-by: Samuel Ortiz --- include/linux/mfd/stmpe.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/stmpe.h b/include/linux/mfd/stmpe.h index e762c270d8d4..be1af7c42e57 100644 --- a/include/linux/mfd/stmpe.h +++ b/include/linux/mfd/stmpe.h @@ -57,6 +57,7 @@ struct stmpe_variant_info; * @irq_lock: IRQ bus lock * @dev: device, mostly for dev_dbg() * @i2c: i2c client + * @partnum: part number * @variant: the detected STMPE model number * @regs: list of addresses of registers which are at different addresses on * different variants. Indexed by one of STMPE_IDX_*. @@ -121,6 +122,8 @@ struct stmpe_keypad_platform_data { * @norequest_mask: bitmask specifying which GPIOs should _not_ be * requestable due to different usage (e.g. touch, keypad) * STMPE_GPIO_NOREQ_* macros can be used here. + * @setup: board specific setup callback. + * @remove: board specific remove callback */ struct stmpe_gpio_platform_data { int gpio_base; -- cgit v1.2.3 From 09d6292befba8c6319d9471803149573ea6ed170 Mon Sep 17 00:00:00 2001 From: Jin Park Date: Mon, 4 Jul 2011 19:48:12 +0200 Subject: mfd: Add AAT2870 mfd driver Add mfd core driver for AnalogicTech AAT2870. The AAT2870 is communication through I2C and contains backlight and regulator components. Signed-off-by: Jin Park Signed-off-by: Samuel Ortiz --- include/linux/mfd/aat2870.h | 181 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 181 insertions(+) create mode 100644 include/linux/mfd/aat2870.h (limited to 'include/linux') diff --git a/include/linux/mfd/aat2870.h b/include/linux/mfd/aat2870.h new file mode 100644 index 000000000000..89212df05622 --- /dev/null +++ b/include/linux/mfd/aat2870.h @@ -0,0 +1,181 @@ +/* + * linux/include/linux/mfd/aat2870.h + * + * Copyright (c) 2011, NVIDIA Corporation. + * Author: Jin Park + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA + * 02110-1301 USA + */ + +#ifndef __LINUX_MFD_AAT2870_H +#define __LINUX_MFD_AAT2870_H + +#include +#include + +/* Register offsets */ +#define AAT2870_BL_CH_EN 0x00 +#define AAT2870_BLM 0x01 +#define AAT2870_BLS 0x02 +#define AAT2870_BL1 0x03 +#define AAT2870_BL2 0x04 +#define AAT2870_BL3 0x05 +#define AAT2870_BL4 0x06 +#define AAT2870_BL5 0x07 +#define AAT2870_BL6 0x08 +#define AAT2870_BL7 0x09 +#define AAT2870_BL8 0x0A +#define AAT2870_FLR 0x0B +#define AAT2870_FM 0x0C +#define AAT2870_FS 0x0D +#define AAT2870_ALS_CFG0 0x0E +#define AAT2870_ALS_CFG1 0x0F +#define AAT2870_ALS_CFG2 0x10 +#define AAT2870_AMB 0x11 +#define AAT2870_ALS0 0x12 +#define AAT2870_ALS1 0x13 +#define AAT2870_ALS2 0x14 +#define AAT2870_ALS3 0x15 +#define AAT2870_ALS4 0x16 +#define AAT2870_ALS5 0x17 +#define AAT2870_ALS6 0x18 +#define AAT2870_ALS7 0x19 +#define AAT2870_ALS8 0x1A +#define AAT2870_ALS9 0x1B +#define AAT2870_ALSA 0x1C +#define AAT2870_ALSB 0x1D +#define AAT2870_ALSC 0x1E +#define AAT2870_ALSD 0x1F +#define AAT2870_ALSE 0x20 +#define AAT2870_ALSF 0x21 +#define AAT2870_SUB_SET 0x22 +#define AAT2870_SUB_CTRL 0x23 +#define AAT2870_LDO_AB 0x24 +#define AAT2870_LDO_CD 0x25 +#define AAT2870_LDO_EN 0x26 +#define AAT2870_REG_NUM 0x27 + +/* Device IDs */ +enum aat2870_id { + AAT2870_ID_BL, + AAT2870_ID_LDOA, + AAT2870_ID_LDOB, + AAT2870_ID_LDOC, + AAT2870_ID_LDOD +}; + +/* Backlight channels */ +#define AAT2870_BL_CH1 0x01 +#define AAT2870_BL_CH2 0x02 +#define AAT2870_BL_CH3 0x04 +#define AAT2870_BL_CH4 0x08 +#define AAT2870_BL_CH5 0x10 +#define AAT2870_BL_CH6 0x20 +#define AAT2870_BL_CH7 0x40 +#define AAT2870_BL_CH8 0x80 +#define AAT2870_BL_CH_ALL 0xFF + +/* Backlight current magnitude (mA) */ +enum aat2870_current { + AAT2870_CURRENT_0_45, + AAT2870_CURRENT_0_90, + AAT2870_CURRENT_1_80, + AAT2870_CURRENT_2_70, + AAT2870_CURRENT_3_60, + AAT2870_CURRENT_4_50, + AAT2870_CURRENT_5_40, + AAT2870_CURRENT_6_30, + AAT2870_CURRENT_7_20, + AAT2870_CURRENT_8_10, + AAT2870_CURRENT_9_00, + AAT2870_CURRENT_9_90, + AAT2870_CURRENT_10_8, + AAT2870_CURRENT_11_7, + AAT2870_CURRENT_12_6, + AAT2870_CURRENT_13_5, + AAT2870_CURRENT_14_4, + AAT2870_CURRENT_15_3, + AAT2870_CURRENT_16_2, + AAT2870_CURRENT_17_1, + AAT2870_CURRENT_18_0, + AAT2870_CURRENT_18_9, + AAT2870_CURRENT_19_8, + AAT2870_CURRENT_20_7, + AAT2870_CURRENT_21_6, + AAT2870_CURRENT_22_5, + AAT2870_CURRENT_23_4, + AAT2870_CURRENT_24_3, + AAT2870_CURRENT_25_2, + AAT2870_CURRENT_26_1, + AAT2870_CURRENT_27_0, + AAT2870_CURRENT_27_9 +}; + +struct aat2870_register { + bool readable; + bool writeable; + u8 value; +}; + +struct aat2870_data { + struct device *dev; + struct i2c_client *client; + + struct mutex io_lock; + struct aat2870_register *reg_cache; /* register cache */ + int en_pin; /* enable GPIO pin (if < 0, ignore this value) */ + bool is_enable; + + /* init and uninit for platform specified */ + int (*init)(struct aat2870_data *aat2870); + void (*uninit)(struct aat2870_data *aat2870); + + /* i2c io funcntions */ + int (*read)(struct aat2870_data *aat2870, u8 addr, u8 *val); + int (*write)(struct aat2870_data *aat2870, u8 addr, u8 val); + int (*update)(struct aat2870_data *aat2870, u8 addr, u8 mask, u8 val); + + /* for debugfs */ + struct dentry *dentry_root; + struct dentry *dentry_reg; +}; + +struct aat2870_subdev_info { + int id; + const char *name; + void *platform_data; +}; + +struct aat2870_platform_data { + int en_pin; /* enable GPIO pin (if < 0, ignore this value) */ + + struct aat2870_subdev_info *subdevs; + int num_subdevs; + + /* init and uninit for platform specified */ + int (*init)(struct aat2870_data *aat2870); + void (*uninit)(struct aat2870_data *aat2870); +}; + +struct aat2870_bl_platform_data { + /* backlight channels, default is AAT2870_BL_CH_ALL */ + int channels; + /* backlight current magnitude, default is AAT2870_CURRENT_27_9 */ + int max_current; + /* maximum brightness, default is 255 */ + int max_brightness; +}; + +#endif /* __LINUX_MFD_AAT2870_H */ -- cgit v1.2.3 From a00ed25cce6fe856388f89c7cd40da0eee7666a6 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 31 Jul 2011 16:39:04 -0400 Subject: NFS: Re-enable compilation of nfs with !CONFIG_NFS_V4 || !CONFIG_NFS_V4_1 Fix two recently introduced compile problems: Fix a typo in fs/nfs/pnfs.h Move the pnfs_blksize declaration outside the CONFIG_NFS_V4 section in struct nfs_server. Reported-by: Jens Axboe Signed-off-by: Trond Myklebust Signed-off-by: Linus Torvalds --- include/linux/nfs_fs_sb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 82fdfc7987d6..b5479df8378d 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -131,6 +131,7 @@ struct nfs_server { struct fscache_cookie *fscache; /* superblock cookie */ #endif + u32 pnfs_blksize; /* layout_blksize attr */ #ifdef CONFIG_NFS_V4 u32 attr_bitmask[3];/* V4 bitmask representing the set of attributes supported on this @@ -145,7 +146,6 @@ struct nfs_server { filesystem */ struct pnfs_layoutdriver_type *pnfs_curr_ld; /* Active layout driver */ struct rpc_wait_queue roc_rpcwaitq; - u32 pnfs_blksize; /* layout_blksize attr */ void *pnfs_ld_data; /* per mount point data */ /* the following fields are protected by nfs_client->cl_lock */ -- cgit v1.2.3 From f2ee7abf4c40c8e6bffced923a7c01ea2d1f6c97 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 28 Jul 2011 06:41:09 +0200 Subject: vfs: avoid taking inode_hash_lock on pipes and sockets Some inodes (pipes, sockets, ...) are not hashed, no need to take contended inode_hash_lock at dismantle time. nice speedup on SMP machines on socket intensive workloads. Signed-off-by: Eric Dumazet Signed-off-by: Al Viro --- include/linux/fs.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index f23bcb77260c..786b3b1113cf 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2317,11 +2317,18 @@ extern int should_remove_suid(struct dentry *); extern int file_remove_suid(struct file *); extern void __insert_inode_hash(struct inode *, unsigned long hashval); -extern void remove_inode_hash(struct inode *); static inline void insert_inode_hash(struct inode *inode) { __insert_inode_hash(inode, inode->i_ino); } + +extern void __remove_inode_hash(struct inode *); +static inline void remove_inode_hash(struct inode *inode) +{ + if (!inode_unhashed(inode)) + __remove_inode_hash(inode); +} + extern void inode_sb_list_add(struct inode *inode); #ifdef CONFIG_BLOCK -- cgit v1.2.3 From d3fb612076eebec6f67257db0c7a9666ac7e5892 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 23 Jul 2011 18:37:50 -0400 Subject: switch posix_acl_create() to umode_t * so we can pass &inode->i_mode to it Signed-off-by: Al Viro --- include/linux/nfs_fs.h | 4 ++-- include/linux/posix_acl.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 8b579beb6358..dda2ac8a5f7b 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -568,12 +568,12 @@ extern struct posix_acl *nfs3_proc_getacl(struct inode *inode, int type); extern int nfs3_proc_setacl(struct inode *inode, int type, struct posix_acl *acl); extern int nfs3_proc_set_default_acl(struct inode *dir, struct inode *inode, - mode_t mode); + umode_t mode); extern void nfs3_forget_cached_acls(struct inode *inode); #else static inline int nfs3_proc_set_default_acl(struct inode *dir, struct inode *inode, - mode_t mode) + umode_t mode) { return 0; } diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 9a53b99818e2..bd8d0050d725 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -77,7 +77,7 @@ extern int posix_acl_valid(const struct posix_acl *); extern int posix_acl_permission(struct inode *, const struct posix_acl *, int); extern struct posix_acl *posix_acl_from_mode(mode_t, gfp_t); extern int posix_acl_equiv_mode(const struct posix_acl *, mode_t *); -extern int posix_acl_create(struct posix_acl **, gfp_t, mode_t *); +extern int posix_acl_create(struct posix_acl **, gfp_t, umode_t *); extern int posix_acl_chmod(struct posix_acl **, gfp_t, mode_t); extern struct posix_acl *get_posix_acl(struct inode *, int); -- cgit v1.2.3 From d6952123b53cc8b334df69bba2cd0063b0d88f68 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 23 Jul 2011 18:56:36 -0400 Subject: switch posix_acl_equiv_mode() to umode_t * ... so that &inode->i_mode could be passed to it Signed-off-by: Al Viro --- include/linux/posix_acl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index bd8d0050d725..529c32ad58c0 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -76,7 +76,7 @@ extern struct posix_acl *posix_acl_alloc(int, gfp_t); extern int posix_acl_valid(const struct posix_acl *); extern int posix_acl_permission(struct inode *, const struct posix_acl *, int); extern struct posix_acl *posix_acl_from_mode(mode_t, gfp_t); -extern int posix_acl_equiv_mode(const struct posix_acl *, mode_t *); +extern int posix_acl_equiv_mode(const struct posix_acl *, umode_t *); extern int posix_acl_create(struct posix_acl **, gfp_t, umode_t *); extern int posix_acl_chmod(struct posix_acl **, gfp_t, mode_t); -- cgit v1.2.3 From 3a5fba19b080b365d67866db38e32e6a4a2089e8 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 23 Jul 2011 19:01:48 -0400 Subject: switch posix_acl_from_mode() to umode_t ... seeing that this is what all callers pass to it anyway. Signed-off-by: Al Viro --- include/linux/posix_acl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 529c32ad58c0..16ecfb485d28 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -75,7 +75,7 @@ extern void posix_acl_init(struct posix_acl *, int); extern struct posix_acl *posix_acl_alloc(int, gfp_t); extern int posix_acl_valid(const struct posix_acl *); extern int posix_acl_permission(struct inode *, const struct posix_acl *, int); -extern struct posix_acl *posix_acl_from_mode(mode_t, gfp_t); +extern struct posix_acl *posix_acl_from_mode(umode_t, gfp_t); extern int posix_acl_equiv_mode(const struct posix_acl *, umode_t *); extern int posix_acl_create(struct posix_acl **, gfp_t, umode_t *); extern int posix_acl_chmod(struct posix_acl **, gfp_t, mode_t); -- cgit v1.2.3 From 86bc704db0ab7e69230f79bc7d124e063259abc6 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 23 Jul 2011 19:03:11 -0400 Subject: switch posix_acl_chmod() to umode_t again, that's what all callers pass to it Signed-off-by: Al Viro --- include/linux/posix_acl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 16ecfb485d28..951bba82d50d 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -78,7 +78,7 @@ extern int posix_acl_permission(struct inode *, const struct posix_acl *, int); extern struct posix_acl *posix_acl_from_mode(umode_t, gfp_t); extern int posix_acl_equiv_mode(const struct posix_acl *, umode_t *); extern int posix_acl_create(struct posix_acl **, gfp_t, umode_t *); -extern int posix_acl_chmod(struct posix_acl **, gfp_t, mode_t); +extern int posix_acl_chmod(struct posix_acl **, gfp_t, umode_t); extern struct posix_acl *get_posix_acl(struct inode *, int); extern int set_posix_acl(struct inode *, int, struct posix_acl *); -- cgit v1.2.3 From a6e50b409d3f9e0833e69c3c9cca822e8fa4adbb Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Tue, 2 Aug 2011 12:32:04 +0100 Subject: dm snapshot: skip reading origin when overwriting complete chunk If we write a full chunk in the snapshot, skip reading the origin device because the whole chunk will be overwritten anyway. This patch changes the snapshot write logic when a full chunk is written. In this case: 1. allocate the exception 2. dispatch the bio (but don't report the bio completion to device mapper) 3. write the exception record 4. report bio completed Callbacks must be done through the kcopyd thread, because callbacks must not race with each other. So we create two new functions: dm_kcopyd_prepare_callback: allocate a job structure and prepare the callback. (This function must not be called from interrupt context.) dm_kcopyd_do_callback: submit callback. (This function may be called from interrupt context.) Performance test (on snapshots with 4k chunk size): without the patch: non-direct-io sequential write (dd): 17.7MB/s direct-io sequential write (dd): 20.9MB/s non-direct-io random write (mkfs.ext2): 0.44s with the patch: non-direct-io sequential write (dd): 26.5MB/s direct-io sequential write (dd): 33.2MB/s non-direct-io random write (mkfs.ext2): 0.27s Signed-off-by: Mikulas Patocka Signed-off-by: Alasdair G Kergon --- include/linux/dm-kcopyd.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dm-kcopyd.h b/include/linux/dm-kcopyd.h index 298d587e349b..5e54458e920f 100644 --- a/include/linux/dm-kcopyd.h +++ b/include/linux/dm-kcopyd.h @@ -42,5 +42,20 @@ int dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from, unsigned num_dests, struct dm_io_region *dests, unsigned flags, dm_kcopyd_notify_fn fn, void *context); +/* + * Prepare a callback and submit it via the kcopyd thread. + * + * dm_kcopyd_prepare_callback allocates a callback structure and returns it. + * It must not be called from interrupt context. + * The returned value should be passed into dm_kcopyd_do_callback. + * + * dm_kcopyd_do_callback submits the callback. + * It may be called from interrupt context. + * The callback is issued from the kcopyd thread. + */ +void *dm_kcopyd_prepare_callback(struct dm_kcopyd_client *kc, + dm_kcopyd_notify_fn fn, void *context); +void dm_kcopyd_do_callback(void *job, int read_err, unsigned long write_err); + #endif /* __KERNEL__ */ #endif /* _LINUX_DM_KCOPYD_H */ -- cgit v1.2.3 From 498f0103ea13123e007660def9072a0b7dd1c599 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Tue, 2 Aug 2011 12:32:04 +0100 Subject: dm table: share target argument parsing functions Move multipath target argument parsing code into dm-table so other targets can share it. Signed-off-by: Mike Snitzer Signed-off-by: Alasdair G Kergon --- include/linux/device-mapper.h | 43 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 4427e0454051..3fa1f3d90ce0 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -208,6 +208,49 @@ struct dm_target_callbacks { int dm_register_target(struct target_type *t); void dm_unregister_target(struct target_type *t); +/* + * Target argument parsing. + */ +struct dm_arg_set { + unsigned argc; + char **argv; +}; + +/* + * The minimum and maximum value of a numeric argument, together with + * the error message to use if the number is found to be outside that range. + */ +struct dm_arg { + unsigned min; + unsigned max; + char *error; +}; + +/* + * Validate the next argument, either returning it as *value or, if invalid, + * returning -EINVAL and setting *error. + */ +int dm_read_arg(struct dm_arg *arg, struct dm_arg_set *arg_set, + unsigned *value, char **error); + +/* + * Process the next argument as the start of a group containing between + * arg->min and arg->max further arguments. Either return the size as + * *num_args or, if invalid, return -EINVAL and set *error. + */ +int dm_read_arg_group(struct dm_arg *arg, struct dm_arg_set *arg_set, + unsigned *num_args, char **error); + +/* + * Return the current argument and shift to the next. + */ +const char *dm_shift_arg(struct dm_arg_set *as); + +/* + * Move through num_args arguments. + */ +void dm_consume_args(struct dm_arg_set *as, unsigned num_args); + /*----------------------------------------------------------------- * Functions for creating and manipulating mapped devices. * Drop the reference with dm_put when you finish with the object. -- cgit v1.2.3 From 0ddf9644cc26e74ed671525e61a17bdbebf18da6 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Tue, 2 Aug 2011 12:32:06 +0100 Subject: dm ioctl: fill in device parameters in more ioctls Move parameter filling from find_device to __find_device_hash_cell. This patch causes ioctls using __find_device_hash_cell (DM_DEV_REMOVE_CMD, DM_DEV_SUSPEND_CMD - resume, DM_TABLE_CLEAR_CMD) to return device parameters, bringing them into line with the other ioctls. Signed-off-by: Mikulas Patocka Signed-off-by: Alasdair G Kergon --- include/linux/dm-ioctl.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dm-ioctl.h b/include/linux/dm-ioctl.h index 3708455ee6c3..0cb8eff76bd6 100644 --- a/include/linux/dm-ioctl.h +++ b/include/linux/dm-ioctl.h @@ -267,9 +267,9 @@ enum { #define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) #define DM_VERSION_MAJOR 4 -#define DM_VERSION_MINOR 20 +#define DM_VERSION_MINOR 21 #define DM_VERSION_PATCHLEVEL 0 -#define DM_VERSION_EXTRA "-ioctl (2011-02-02)" +#define DM_VERSION_EXTRA "-ioctl (2011-07-06)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ -- cgit v1.2.3 From aac285c6cb9622f1cc05ed162604bf5ad2da9a8d Mon Sep 17 00:00:00 2001 From: Jamie Iles Date: Tue, 2 Aug 2011 15:45:07 +0100 Subject: of: constify property name parameters for helper functions The helper functions for reading u32 integers, u32 arrays and strings should have the property name as a const pointer. Cc: Grant Likely Signed-off-by: Jamie Iles Signed-off-by: Grant Likely --- include/linux/of.h | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index bd716f8908de..0085bb01c041 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -196,12 +196,13 @@ extern struct property *of_find_property(const struct device_node *np, const char *name, int *lenp); extern int of_property_read_u32_array(const struct device_node *np, - char *propname, + const char *propname, u32 *out_values, size_t sz); -extern int of_property_read_string(struct device_node *np, char *propname, - const char **out_string); +extern int of_property_read_string(struct device_node *np, + const char *propname, + const char **out_string); extern int of_device_is_compatible(const struct device_node *device, const char *); extern int of_device_is_available(const struct device_node *device); @@ -242,13 +243,15 @@ static inline bool of_have_populated_dt(void) } static inline int of_property_read_u32_array(const struct device_node *np, - char *propname, u32 *out_values, size_t sz) + const char *propname, + u32 *out_values, size_t sz) { return -ENOSYS; } static inline int of_property_read_string(struct device_node *np, - char *propname, const char **out_string) + const char *propname, + const char **out_string) { return -ENOSYS; } @@ -256,7 +259,7 @@ static inline int of_property_read_string(struct device_node *np, #endif /* CONFIG_OF */ static inline int of_property_read_u32(const struct device_node *np, - char *propname, + const char *propname, u32 *out_value) { return of_property_read_u32_array(np, propname, out_value, 1); -- cgit v1.2.3 From 31f5396ad3bde23c8416e8d23ba425e27f413314 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Thu, 28 Jul 2011 13:48:42 -0700 Subject: thermal: make THERMAL_HWMON implementation fully internal THERMAL_HWMON is implemented inside the thermal_sys driver and has no effect on drivers implementing thermal zones, so they shouldn't see anything related to it in . Making the THERMAL_HWMON implementation fully internal has two advantages beyond the cleaner design: * This avoids rebuilding all thermal drivers if the THERMAL_HWMON implementation changes, or if CONFIG_THERMAL_HWMON gets enabled or disabled. * This avoids breaking the thermal kABI in these cases too, which should make distributions happy. The only drawback I can see is slightly higher memory fragmentation, as the number of kzalloc() calls will increase by one per thermal zone. But I doubt it will be a problem in practice, as I've never seen a system with more than two thermal zones. Signed-off-by: Jean Delvare Cc: Rene Herman Acked-by: Guenter Roeck Signed-off-by: Andrew Morton Signed-off-by: Len Brown --- include/linux/thermal.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index d3ec89fb4122..47b4a27e6e97 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -85,22 +85,6 @@ struct thermal_cooling_device { ((long)t-2732+5)/10 : ((long)t-2732-5)/10) #define CELSIUS_TO_KELVIN(t) ((t)*10+2732) -#if defined(CONFIG_THERMAL_HWMON) -/* thermal zone devices with the same type share one hwmon device */ -struct thermal_hwmon_device { - char type[THERMAL_NAME_LENGTH]; - struct device *device; - int count; - struct list_head tz_list; - struct list_head node; -}; - -struct thermal_hwmon_attr { - struct device_attribute attr; - char name[16]; -}; -#endif - struct thermal_zone_device { int id; char type[THERMAL_NAME_LENGTH]; @@ -120,12 +104,6 @@ struct thermal_zone_device { struct mutex lock; /* protect cooling devices list */ struct list_head node; struct delayed_work poll_queue; -#if defined(CONFIG_THERMAL_HWMON) - struct list_head hwmon_node; - struct thermal_hwmon_device *hwmon; - struct thermal_hwmon_attr temp_input; /* hwmon sys attr */ - struct thermal_hwmon_attr temp_crit; /* hwmon sys attr */ -#endif }; /* Adding event notification support elements */ #define THERMAL_GENL_FAMILY_NAME "thermal_event" -- cgit v1.2.3 From f52e00c668669c9c290e84adf859c76db6d92a5a Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Thu, 28 Jul 2011 13:48:43 -0700 Subject: ACPI: remove NID_INVAL b552a8c56db8 ("ACPI: remove NID_INVAL") removed the left over uses of NID_INVAL, but didn't actually remove the definition. Remove it. Signed-off-by: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Len Brown --- include/linux/acpi.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 1deb2a73c2da..2312e850aab8 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -238,7 +238,6 @@ extern int acpi_paddr_to_node(u64 start_addr, u64 size); extern int pnpacpi_disabled; #define PXM_INVAL (-1) -#define NID_INVAL (-1) int acpi_check_resource_conflict(const struct resource *res); -- cgit v1.2.3 From 951c0d660a7c35286e401ca6d6ef38c9d49643c7 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 3 Aug 2011 00:47:21 -0400 Subject: get rid of boilerplate switches in posix_acl.h the only potentially subtle thing here: get_cached_acl() is never called with the second argument other than ACL_TYPE_{ACCESS,DEFAULT}. IOW, that return ERR_PTR(-EINVAL) in there might as well be BUG(). Signed-off-by: Al Viro --- include/linux/posix_acl.h | 62 +++++++++++++++-------------------------------- 1 file changed, 20 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 951bba82d50d..a9c2fb29be96 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -84,20 +84,22 @@ extern struct posix_acl *get_posix_acl(struct inode *, int); extern int set_posix_acl(struct inode *, int, struct posix_acl *); #ifdef CONFIG_FS_POSIX_ACL -static inline struct posix_acl *get_cached_acl(struct inode *inode, int type) +static inline struct posix_acl **acl_by_type(struct inode *inode, int type) { - struct posix_acl **p, *acl; switch (type) { case ACL_TYPE_ACCESS: - p = &inode->i_acl; - break; + return &inode->i_acl; case ACL_TYPE_DEFAULT: - p = &inode->i_default_acl; - break; + return &inode->i_default_acl; default: - return ERR_PTR(-EINVAL); + BUG(); } - acl = ACCESS_ONCE(*p); +} + +static inline struct posix_acl *get_cached_acl(struct inode *inode, int type) +{ + struct posix_acl **p = acl_by_type(inode, type); + struct posix_acl *acl = ACCESS_ONCE(*p); if (acl) { spin_lock(&inode->i_lock); acl = *p; @@ -110,18 +112,8 @@ static inline struct posix_acl *get_cached_acl(struct inode *inode, int type) static inline int negative_cached_acl(struct inode *inode, int type) { - struct posix_acl **p, *acl; - switch (type) { - case ACL_TYPE_ACCESS: - p = &inode->i_acl; - break; - case ACL_TYPE_DEFAULT: - p = &inode->i_default_acl; - break; - default: - BUG(); - } - acl = ACCESS_ONCE(*p); + struct posix_acl **p = acl_by_type(inode, type); + struct posix_acl *acl = ACCESS_ONCE(*p); if (acl) return 0; return 1; @@ -131,18 +123,11 @@ static inline void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl) { - struct posix_acl *old = NULL; + struct posix_acl **p = acl_by_type(inode, type); + struct posix_acl *old; spin_lock(&inode->i_lock); - switch (type) { - case ACL_TYPE_ACCESS: - old = inode->i_acl; - inode->i_acl = posix_acl_dup(acl); - break; - case ACL_TYPE_DEFAULT: - old = inode->i_default_acl; - inode->i_default_acl = posix_acl_dup(acl); - break; - } + old = *p; + *p = posix_dup_acl(acl); spin_unlock(&inode->i_lock); if (old != ACL_NOT_CACHED) posix_acl_release(old); @@ -150,18 +135,11 @@ static inline void set_cached_acl(struct inode *inode, static inline void forget_cached_acl(struct inode *inode, int type) { - struct posix_acl *old = NULL; + struct posix_acl **p = acl_by_type(inode, type); + struct posix_acl *old; spin_lock(&inode->i_lock); - switch (type) { - case ACL_TYPE_ACCESS: - old = inode->i_acl; - inode->i_acl = ACL_NOT_CACHED; - break; - case ACL_TYPE_DEFAULT: - old = inode->i_default_acl; - inode->i_default_acl = ACL_NOT_CACHED; - break; - } + old = *p; + *p = ACL_NOT_CACHED; spin_unlock(&inode->i_lock); if (old != ACL_NOT_CACHED) posix_acl_release(old); -- cgit v1.2.3 From 3567866bf26190d1e734c975c907eb06e923ba23 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 2 Aug 2011 21:32:13 -0400 Subject: RCUify freeing acls, let check_acl() go ahead in RCU mode if acl is cached Signed-off-by: Al Viro --- include/linux/posix_acl.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index a9c2fb29be96..b7681102a4b9 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -9,6 +9,7 @@ #define __LINUX_POSIX_ACL_H #include +#include #define ACL_UNDEFINED_ID (-1) @@ -38,7 +39,10 @@ struct posix_acl_entry { }; struct posix_acl { - atomic_t a_refcount; + union { + atomic_t a_refcount; + struct rcu_head a_rcu; + }; unsigned int a_count; struct posix_acl_entry a_entries[0]; }; @@ -65,7 +69,7 @@ static inline void posix_acl_release(struct posix_acl *acl) { if (acl && atomic_dec_and_test(&acl->a_refcount)) - kfree(acl); + kfree_rcu(acl, a_rcu); } @@ -110,13 +114,9 @@ static inline struct posix_acl *get_cached_acl(struct inode *inode, int type) return acl; } -static inline int negative_cached_acl(struct inode *inode, int type) +static inline struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type) { - struct posix_acl **p = acl_by_type(inode, type); - struct posix_acl *acl = ACCESS_ONCE(*p); - if (acl) - return 0; - return 1; + return rcu_dereference(*acl_by_type(inode, type)); } static inline void set_cached_acl(struct inode *inode, @@ -127,7 +127,7 @@ static inline void set_cached_acl(struct inode *inode, struct posix_acl *old; spin_lock(&inode->i_lock); old = *p; - *p = posix_dup_acl(acl); + rcu_assign_pointer(*p, posix_acl_dup(acl)); spin_unlock(&inode->i_lock); if (old != ACL_NOT_CACHED) posix_acl_release(old); -- cgit v1.2.3 From 750f463a749e28464151ad26938d11b07b1c43cb Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Wed, 3 Aug 2011 11:28:14 +0100 Subject: dt: add of_alias_scan and of_alias_get_id The patch adds function of_alias_scan to populate a global lookup table with the properties of 'aliases' node and function of_alias_get_id for drivers to find alias id from the lookup table. Signed-off-by: Shawn Guo [grant.likely: add locking and rework parse loop] Signed-off-by: Grant Likely --- include/linux/of.h | 8 ++++++++ include/linux/of_fdt.h | 1 - 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 0085bb01c041..bc3dc6399547 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -68,6 +68,7 @@ struct device_node { /* Pointer for first entry in chain of all nodes. */ extern struct device_node *allnodes; extern struct device_node *of_chosen; +extern struct device_node *of_aliases; extern rwlock_t devtree_lock; static inline bool of_have_populated_dt(void) @@ -209,6 +210,9 @@ extern int of_device_is_available(const struct device_node *device); extern const void *of_get_property(const struct device_node *node, const char *name, int *lenp); +#define for_each_property(pp, properties) \ + for (pp = properties; pp != NULL; pp = pp->next) + extern int of_n_addr_cells(struct device_node *np); extern int of_n_size_cells(struct device_node *np); extern const struct of_device_id *of_match_node( @@ -221,6 +225,10 @@ extern int of_parse_phandles_with_args(struct device_node *np, const char *list_name, const char *cells_name, int index, struct device_node **out_node, const void **out_args); +extern void *early_init_dt_alloc_memory_arch(u64 size, u64 align); +extern void of_alias_scan(void); +extern int of_alias_get_id(struct device_node *np, const char *stem); + extern int of_machine_is_compatible(const char *compat); extern int prom_add_property(struct device_node* np, struct property* prop); diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index c84d900fbbb3..b74b74ffe0e7 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -97,7 +97,6 @@ extern void early_init_dt_check_for_initrd(unsigned long node); extern int early_init_dt_scan_memory(unsigned long node, const char *uname, int depth, void *data); extern void early_init_dt_add_memory_arch(u64 base, u64 size); -extern void * early_init_dt_alloc_memory_arch(u64 size, u64 align); extern u64 dt_mem_next_cell(int s, __be32 **cellp); /* -- cgit v1.2.3 From f49f23abf3dd786ddcac1c1e7db3c2013b07413f Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 13 Jul 2011 13:14:23 +0800 Subject: lib, Add lock-less NULL terminated single list Cmpxchg is used to implement adding new entry to the list, deleting all entries from the list, deleting first entry of the list and some other operations. Because this is a single list, so the tail can not be accessed in O(1). If there are multiple producers and multiple consumers, llist_add can be used in producers and llist_del_all can be used in consumers. They can work simultaneously without lock. But llist_del_first can not be used here. Because llist_del_first depends on list->first->next does not changed if list->first is not changed during its operation, but llist_del_first, llist_add, llist_add (or llist_del_all, llist_add, llist_add) sequence in another consumer may violate that. If there are multiple producers and one consumer, llist_add can be used in producers and llist_del_all or llist_del_first can be used in the consumer. This can be summarized as follow: | add | del_first | del_all add | - | - | - del_first | | L | L del_all | | | - Where "-" stands for no lock is needed, while "L" stands for lock is needed. The list entries deleted via llist_del_all can be traversed with traversing function such as llist_for_each etc. But the list entries can not be traversed safely before deleted from the list. The order of deleted entries is from the newest to the oldest added one. If you want to traverse from the oldest to the newest, you must reverse the order by yourself before traversing. The basic atomic operation of this list is cmpxchg on long. On architectures that don't have NMI-safe cmpxchg implementation, the list can NOT be used in NMI handler. So code uses the list in NMI handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. Signed-off-by: Huang Ying Reviewed-by: Andi Kleen Reviewed-by: Mathieu Desnoyers Cc: Andrew Morton Signed-off-by: Len Brown --- include/linux/llist.h | 126 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 126 insertions(+) create mode 100644 include/linux/llist.h (limited to 'include/linux') diff --git a/include/linux/llist.h b/include/linux/llist.h new file mode 100644 index 000000000000..aa0c8b5b3cd0 --- /dev/null +++ b/include/linux/llist.h @@ -0,0 +1,126 @@ +#ifndef LLIST_H +#define LLIST_H +/* + * Lock-less NULL terminated single linked list + * + * If there are multiple producers and multiple consumers, llist_add + * can be used in producers and llist_del_all can be used in + * consumers. They can work simultaneously without lock. But + * llist_del_first can not be used here. Because llist_del_first + * depends on list->first->next does not changed if list->first is not + * changed during its operation, but llist_del_first, llist_add, + * llist_add (or llist_del_all, llist_add, llist_add) sequence in + * another consumer may violate that. + * + * If there are multiple producers and one consumer, llist_add can be + * used in producers and llist_del_all or llist_del_first can be used + * in the consumer. + * + * This can be summarized as follow: + * + * | add | del_first | del_all + * add | - | - | - + * del_first | | L | L + * del_all | | | - + * + * Where "-" stands for no lock is needed, while "L" stands for lock + * is needed. + * + * The list entries deleted via llist_del_all can be traversed with + * traversing function such as llist_for_each etc. But the list + * entries can not be traversed safely before deleted from the list. + * The order of deleted entries is from the newest to the oldest added + * one. If you want to traverse from the oldest to the newest, you + * must reverse the order by yourself before traversing. + * + * The basic atomic operation of this list is cmpxchg on long. On + * architectures that don't have NMI-safe cmpxchg implementation, the + * list can NOT be used in NMI handler. So code uses the list in NMI + * handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. + */ + +struct llist_head { + struct llist_node *first; +}; + +struct llist_node { + struct llist_node *next; +}; + +#define LLIST_HEAD_INIT(name) { NULL } +#define LLIST_HEAD(name) struct llist_head name = LLIST_HEAD_INIT(name) + +/** + * init_llist_head - initialize lock-less list head + * @head: the head for your lock-less list + */ +static inline void init_llist_head(struct llist_head *list) +{ + list->first = NULL; +} + +/** + * llist_entry - get the struct of this entry + * @ptr: the &struct llist_node pointer. + * @type: the type of the struct this is embedded in. + * @member: the name of the llist_node within the struct. + */ +#define llist_entry(ptr, type, member) \ + container_of(ptr, type, member) + +/** + * llist_for_each - iterate over some deleted entries of a lock-less list + * @pos: the &struct llist_node to use as a loop cursor + * @node: the first entry of deleted list entries + * + * In general, some entries of the lock-less list can be traversed + * safely only after being deleted from list, so start with an entry + * instead of list head. + * + * If being used on entries deleted from lock-less list directly, the + * traverse order is from the newest to the oldest added entry. If + * you want to traverse from the oldest to the newest, you must + * reverse the order by yourself before traversing. + */ +#define llist_for_each(pos, node) \ + for ((pos) = (node); pos; (pos) = (pos)->next) + +/** + * llist_for_each_entry - iterate over some deleted entries of lock-less list of given type + * @pos: the type * to use as a loop cursor. + * @node: the fist entry of deleted list entries. + * @member: the name of the llist_node with the struct. + * + * In general, some entries of the lock-less list can be traversed + * safely only after being removed from list, so start with an entry + * instead of list head. + * + * If being used on entries deleted from lock-less list directly, the + * traverse order is from the newest to the oldest added entry. If + * you want to traverse from the oldest to the newest, you must + * reverse the order by yourself before traversing. + */ +#define llist_for_each_entry(pos, node, member) \ + for ((pos) = llist_entry((node), typeof(*(pos)), member); \ + &(pos)->member != NULL; \ + (pos) = llist_entry((pos)->member.next, typeof(*(pos)), member)) + +/** + * llist_empty - tests whether a lock-less list is empty + * @head: the list to test + * + * Not guaranteed to be accurate or up to date. Just a quick way to + * test whether the list is empty without deleting something from the + * list. + */ +static inline int llist_empty(const struct llist_head *head) +{ + return ACCESS_ONCE(head->first) == NULL; +} + +void llist_add(struct llist_node *new, struct llist_head *head); +void llist_add_batch(struct llist_node *new_first, struct llist_node *new_last, + struct llist_head *head); +struct llist_node *llist_del_first(struct llist_head *head); +struct llist_node *llist_del_all(struct llist_head *head); +#endif /* LLIST_H */ -- cgit v1.2.3 From 7f184275aa306046fe7edcbef3229754f0d97402 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 13 Jul 2011 13:14:24 +0800 Subject: lib, Make gen_pool memory allocator lockless This version of the gen_pool memory allocator supports lockless operation. This makes it safe to use in NMI handlers and other special unblockable contexts that could otherwise deadlock on locks. This is implemented by using atomic operations and retries on any conflicts. The disadvantage is that there may be livelocks in extreme cases. For better scalability, one gen_pool allocator can be used for each CPU. The lockless operation only works if there is enough memory available. If new memory is added to the pool a lock has to be still taken. So any user relying on locklessness has to ensure that sufficient memory is preallocated. The basic atomic operation of this allocator is cmpxchg on long. On architectures that don't have NMI-safe cmpxchg implementation, the allocator can NOT be used in NMI handler. So code uses the allocator in NMI handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. Signed-off-by: Huang Ying Reviewed-by: Andi Kleen Reviewed-by: Mathieu Desnoyers Cc: Andrew Morton Signed-off-by: Len Brown --- include/linux/bitmap.h | 1 + include/linux/genalloc.h | 34 ++++++++++++++++++++++++++++------ 2 files changed, 29 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index dcafe0bf0005..907dd58aa228 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -145,6 +145,7 @@ extern void bitmap_release_region(unsigned long *bitmap, int pos, int order); extern int bitmap_allocate_region(unsigned long *bitmap, int pos, int order); extern void bitmap_copy_le(void *dst, const unsigned long *src, int nbits); +#define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) % BITS_PER_LONG)) #define BITMAP_LAST_WORD_MASK(nbits) \ ( \ ((nbits) % BITS_PER_LONG) ? \ diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h index 5bbebda78b02..5e98eeb2af3b 100644 --- a/include/linux/genalloc.h +++ b/include/linux/genalloc.h @@ -1,8 +1,26 @@ /* - * Basic general purpose allocator for managing special purpose memory - * not managed by the regular kmalloc/kfree interface. - * Uses for this includes on-device special memory, uncached memory - * etc. + * Basic general purpose allocator for managing special purpose + * memory, for example, memory that is not managed by the regular + * kmalloc/kfree interface. Uses for this includes on-device special + * memory, uncached memory etc. + * + * It is safe to use the allocator in NMI handlers and other special + * unblockable contexts that could otherwise deadlock on locks. This + * is implemented by using atomic operations and retries on any + * conflicts. The disadvantage is that there may be livelocks in + * extreme cases. For better scalability, one allocator can be used + * for each CPU. + * + * The lockless operation only works if there is enough memory + * available. If new memory is added to the pool a lock has to be + * still taken. So any user relying on locklessness has to ensure + * that sufficient memory is preallocated. + * + * The basic atomic operation of this allocator is cmpxchg on long. + * On architectures that don't have NMI-safe cmpxchg implementation, + * the allocator can NOT be used in NMI handler. So code uses the + * allocator in NMI handler should depend on + * CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. * * This source code is licensed under the GNU General Public License, * Version 2. See the file COPYING for more details. @@ -15,7 +33,7 @@ * General purpose special memory pool descriptor. */ struct gen_pool { - rwlock_t lock; + spinlock_t lock; struct list_head chunks; /* list of chunks in this pool */ int min_alloc_order; /* minimum allocation order */ }; @@ -24,8 +42,8 @@ struct gen_pool { * General purpose special memory pool chunk descriptor. */ struct gen_pool_chunk { - spinlock_t lock; struct list_head next_chunk; /* next chunk in pool */ + atomic_t avail; phys_addr_t phys_addr; /* physical starting address of memory chunk */ unsigned long start_addr; /* starting address of memory chunk */ unsigned long end_addr; /* ending address of memory chunk */ @@ -56,4 +74,8 @@ static inline int gen_pool_add(struct gen_pool *pool, unsigned long addr, extern void gen_pool_destroy(struct gen_pool *); extern unsigned long gen_pool_alloc(struct gen_pool *, size_t); extern void gen_pool_free(struct gen_pool *, unsigned long, size_t); +extern void gen_pool_for_each_chunk(struct gen_pool *, + void (*)(struct gen_pool *, struct gen_pool_chunk *, void *), void *); +extern size_t gen_pool_avail(struct gen_pool *); +extern size_t gen_pool_size(struct gen_pool *); #endif /* __GENALLOC_H__ */ -- cgit v1.2.3 From ea8f5fb8a71fddaf5f3a17100d3247855701f732 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 13 Jul 2011 13:14:27 +0800 Subject: HWPoison: add memory_failure_queue() memory_failure() is the entry point for HWPoison memory error recovery. It must be called in process context. But commonly hardware memory errors are notified via MCE or NMI, so some delayed execution mechanism must be used. In MCE handler, a work queue + ring buffer mechanism is used. In addition to MCE, now APEI (ACPI Platform Error Interface) GHES (Generic Hardware Error Source) can be used to report memory errors too. To add support to APEI GHES memory recovery, a mechanism similar to that of MCE is implemented. memory_failure_queue() is the new entry point that can be called in IRQ context. The next step is to make MCE handler uses this interface too. Signed-off-by: Huang Ying Cc: Andi Kleen Cc: Wu Fengguang Cc: Andrew Morton Signed-off-by: Len Brown --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9670f71d7be9..303108eed28c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1633,6 +1633,7 @@ enum mf_flags { }; extern void memory_failure(unsigned long pfn, int trapno); extern int __memory_failure(unsigned long pfn, int trapno, int flags); +extern void memory_failure_queue(unsigned long pfn, int trapno, int flags); extern int unpoison_memory(unsigned long pfn); extern int sysctl_memory_failure_early_kill; extern int sysctl_memory_failure_recovery; -- cgit v1.2.3 From d91ee5863b71e8c90eaf6035bff3078a85e2e7b5 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Fri, 1 Apr 2011 18:28:35 -0400 Subject: cpuidle: replace xen access to x86 pm_idle and default_idle When a Xen Dom0 kernel boots on a hypervisor, it gets access to the raw-hardware ACPI tables. While it parses the idle tables for the hypervisor's beneift, it uses HLT for its own idle. Rather than have xen scribble on pm_idle and access default_idle, have it simply disable_cpuidle() so acpi_idle will not load and architecture default HLT will be used. cc: xen-devel@lists.xensource.com Tested-by: Konrad Rzeszutek Wilk Acked-by: H. Peter Anvin Signed-off-by: Len Brown --- include/linux/cpuidle.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 36719ead50e8..b89f67da919e 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -122,6 +122,7 @@ struct cpuidle_driver { }; #ifdef CONFIG_CPU_IDLE +extern void disable_cpuidle(void); extern int cpuidle_register_driver(struct cpuidle_driver *drv); struct cpuidle_driver *cpuidle_get_driver(void); @@ -135,6 +136,7 @@ extern int cpuidle_enable_device(struct cpuidle_device *dev); extern void cpuidle_disable_device(struct cpuidle_device *dev); #else +static inline void disable_cpuidle(void) { } static inline int cpuidle_register_driver(struct cpuidle_driver *drv) {return -ENODEV; } -- cgit v1.2.3 From a0bfa1373859e9d11dc92561a8667588803e42d8 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Fri, 1 Apr 2011 19:34:59 -0400 Subject: cpuidle: stop depending on pm_idle cpuidle users should call cpuidle_call_idle() directly rather than via (pm_idle)() function pointer. Architecture may choose to continue using (pm_idle)(), but cpuidle need not depend on it: my_arch_cpu_idle() ... if(cpuidle_call_idle()) pm_idle(); cc: Kevin Hilman cc: Paul Mundt cc: x86@kernel.org Acked-by: H. Peter Anvin Signed-off-by: Len Brown --- include/linux/cpuidle.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index b89f67da919e..b51629e15cfc 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -123,6 +123,7 @@ struct cpuidle_driver { #ifdef CONFIG_CPU_IDLE extern void disable_cpuidle(void); +extern int cpuidle_idle_call(void); extern int cpuidle_register_driver(struct cpuidle_driver *drv); struct cpuidle_driver *cpuidle_get_driver(void); @@ -137,6 +138,7 @@ extern void cpuidle_disable_device(struct cpuidle_device *dev); #else static inline void disable_cpuidle(void) { } +static inline int cpuidle_idle_call(void) { return -ENODEV; } static inline int cpuidle_register_driver(struct cpuidle_driver *drv) {return -ENODEV; } -- cgit v1.2.3 From dd48c085c1cdf9446f92826f1fd451167fb6c2fd Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Wed, 3 Aug 2011 16:21:01 -0700 Subject: fault-injection: add ability to export fault_attr in arbitrary directory init_fault_attr_dentries() is used to export fault_attr via debugfs. But it can only export it in debugfs root directory. Per Forlin is working on mmc_fail_request which adds support to inject data errors after a completed host transfer in MMC subsystem. The fault_attr for mmc_fail_request should be defined per mmc host and export it in debugfs directory per mmc host like /sys/kernel/debug/mmc0/mmc_fail_request. init_fault_attr_dentries() doesn't help for mmc_fail_request. So this introduces fault_create_debugfs_attr() which is able to create a directory in the arbitrary directory and replace init_fault_attr_dentries(). [akpm@linux-foundation.org: extraneous semicolon, per Randy] Signed-off-by: Akinobu Mita Tested-by: Per Forlin Cc: Jens Axboe Cc: Christoph Lameter Cc: Pekka Enberg Cc: Matt Mackall Cc: Randy Dunlap Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fault-inject.h | 18 +++++------------- 1 file changed, 5 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h index 3ff060ac7810..c6f996f2abb6 100644 --- a/include/linux/fault-inject.h +++ b/include/linux/fault-inject.h @@ -25,10 +25,6 @@ struct fault_attr { unsigned long reject_end; unsigned long count; - -#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS - struct dentry *dir; -#endif }; #define FAULT_ATTR_INITIALIZER { \ @@ -45,19 +41,15 @@ bool should_fail(struct fault_attr *attr, ssize_t size); #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS -int init_fault_attr_dentries(struct fault_attr *attr, const char *name); -void cleanup_fault_attr_dentries(struct fault_attr *attr); +struct dentry *fault_create_debugfs_attr(const char *name, + struct dentry *parent, struct fault_attr *attr); #else /* CONFIG_FAULT_INJECTION_DEBUG_FS */ -static inline int init_fault_attr_dentries(struct fault_attr *attr, - const char *name) -{ - return -ENODEV; -} - -static inline void cleanup_fault_attr_dentries(struct fault_attr *attr) +static inline struct dentry *fault_create_debugfs_attr(const char *name, + struct dentry *parent, struct fault_attr *attr) { + return ERR_PTR(-ENODEV); } #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ -- cgit v1.2.3 From 88eca0207cf1574328c3ce8c3be537a9317261bb Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 3 Aug 2011 16:21:06 -0700 Subject: ida: simplified functions for id allocation The current hyper-optimized functions are overkill if you simply want to allocate an id for a device. Create versions which use an internal lock. In followup patches, numerous drivers are converted to use this interface. Thanks to Tejun for feedback. Signed-off-by: Rusty Russell Acked-by: Tejun Heo Acked-by: Jonathan Cameron Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/idr.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index 13a801f3d028..255491cf522e 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -146,6 +146,10 @@ void ida_remove(struct ida *ida, int id); void ida_destroy(struct ida *ida); void ida_init(struct ida *ida); +int ida_simple_get(struct ida *ida, unsigned int start, unsigned int end, + gfp_t gfp_mask); +void ida_simple_remove(struct ida *ida, unsigned int id); + void __init idr_init_cache(void); #endif /* __IDR_H__ */ -- cgit v1.2.3 From 3dab1bce8e840606e76f1bad5a009328e2aa35c7 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Aug 2011 16:21:09 -0700 Subject: mm: page_alloc: increase __GFP_BITS_SHIFT to include __GFP_OTHER_NODE __GFP_OTHER_NODE is used for NUMA allocations on behalf of other nodes. It's supposed to be passed through from the page allocator to zone_statistics(), but it never gets there as gfp_allowed_mask is not wide enough and masks out the flag early in the allocation path. The result is an accounting glitch where successful NUMA allocations by-agent are not properly attributed as local. Increase __GFP_BITS_SHIFT so that it includes __GFP_OTHER_NODE. Signed-off-by: Johannes Weiner Acked-by: Andi Kleen Reviewed-by: Minchan Kim Acked-by: Mel Gorman Reviewed-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index cb4089254f01..3a76faf6a3ee 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -92,7 +92,7 @@ struct vm_area_struct; */ #define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK) -#define __GFP_BITS_SHIFT 23 /* Room for 23 __GFP_FOO bits */ +#define __GFP_BITS_SHIFT 24 /* Room for N __GFP_FOO bits */ #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) /* This equals 0, but use constants in case they ever change */ -- cgit v1.2.3 From 5d6f921b42749d1a70441685b7a4f2801e12ebfb Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Wed, 3 Aug 2011 16:21:17 -0700 Subject: drivers/video/backlight/aat2870_bl.c: fix setting max_current - Current implementation tests wrong value for setting aat2870_bl->max_current. - In the current implementation, we cannot differentiate between 2 cases: a) if pdata->max_current is not set , or b) pdata->max_current is set to AAT2870_CURRENT_0_45 (which is also 0). Fix it by setting AAT2870_CURRENT_0_45 to be 1 and adjust the equation in aat2870_brightness() accordingly. Signed-off-by: Axel Lin Cc: Richard Purdie Cc: Samuel Ortiz Tested-by: Jin Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mfd/aat2870.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/aat2870.h b/include/linux/mfd/aat2870.h index 89212df05622..f7316c29bdec 100644 --- a/include/linux/mfd/aat2870.h +++ b/include/linux/mfd/aat2870.h @@ -89,7 +89,7 @@ enum aat2870_id { /* Backlight current magnitude (mA) */ enum aat2870_current { - AAT2870_CURRENT_0_45, + AAT2870_CURRENT_0_45 = 1, AAT2870_CURRENT_0_90, AAT2870_CURRENT_1_80, AAT2870_CURRENT_2_70, -- cgit v1.2.3 From 6328650bb4d854a7dc1498d1c0048b838b0d340c Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Wed, 3 Aug 2011 16:21:18 -0700 Subject: radix_tree: exceptional entries and indices A patchset to extend tmpfs to MAX_LFS_FILESIZE by abandoning its peculiar swap vector, instead keeping a file's swap entries in the same radix tree as its struct page pointers: thus saving memory, and simplifying its code and locking. This patch: The radix_tree is used by several subsystems for different purposes. A major use is to store the struct page pointers of a file's pagecache for memory management. But what if mm wanted to store something other than page pointers there too? The low bit of a radix_tree entry is already used to denote an indirect pointer, for internal use, and the unlikely radix_tree_deref_retry() case. Define the next bit as denoting an exceptional entry, and supply inline functions radix_tree_exception() to return non-0 in either unlikely case, and radix_tree_exceptional_entry() to return non-0 in the second case. If a subsystem already uses radix_tree with that bit set, no problem: it does not affect internal workings at all, but is defined for the convenience of those storing well-aligned pointers in the radix_tree. The radix_tree_gang_lookups have an implicit assumption that the caller can deduce the offset of each entry returned e.g. by the page->index of a struct page. But that may not be feasible for some kinds of item to be stored there. radix_tree_gang_lookup_slot() allow for an optional indices argument, output array in which to return those offsets. The same could be added to other radix_tree_gang_lookups, but for now keep it to the only one for which we need it. Signed-off-by: Hugh Dickins Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 36 +++++++++++++++++++++++++++++++++--- 1 file changed, 33 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 23241c2fecce..b7edf8251455 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -39,7 +39,15 @@ * when it is shrunk, before we rcu free the node. See shrink code for * details. */ -#define RADIX_TREE_INDIRECT_PTR 1 +#define RADIX_TREE_INDIRECT_PTR 1 +/* + * A common use of the radix tree is to store pointers to struct pages; + * but shmem/tmpfs needs also to store swap entries in the same tree: + * those are marked as exceptional entries to distinguish them. + * EXCEPTIONAL_ENTRY tests the bit, EXCEPTIONAL_SHIFT shifts content past it. + */ +#define RADIX_TREE_EXCEPTIONAL_ENTRY 2 +#define RADIX_TREE_EXCEPTIONAL_SHIFT 2 #define radix_tree_indirect_to_ptr(ptr) \ radix_tree_indirect_to_ptr((void __force *)(ptr)) @@ -173,6 +181,28 @@ static inline int radix_tree_deref_retry(void *arg) return unlikely((unsigned long)arg & RADIX_TREE_INDIRECT_PTR); } +/** + * radix_tree_exceptional_entry - radix_tree_deref_slot gave exceptional entry? + * @arg: value returned by radix_tree_deref_slot + * Returns: 0 if well-aligned pointer, non-0 if exceptional entry. + */ +static inline int radix_tree_exceptional_entry(void *arg) +{ + /* Not unlikely because radix_tree_exception often tested first */ + return (unsigned long)arg & RADIX_TREE_EXCEPTIONAL_ENTRY; +} + +/** + * radix_tree_exception - radix_tree_deref_slot returned either exception? + * @arg: value returned by radix_tree_deref_slot + * Returns: 0 if well-aligned pointer, non-0 if either kind of exception. + */ +static inline int radix_tree_exception(void *arg) +{ + return unlikely((unsigned long)arg & + (RADIX_TREE_INDIRECT_PTR | RADIX_TREE_EXCEPTIONAL_ENTRY)); +} + /** * radix_tree_replace_slot - replace item in a slot * @pslot: pointer to slot, returned by radix_tree_lookup_slot @@ -194,8 +224,8 @@ void *radix_tree_delete(struct radix_tree_root *, unsigned long); unsigned int radix_tree_gang_lookup(struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items); -unsigned int -radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results, +unsigned int radix_tree_gang_lookup_slot(struct radix_tree_root *root, + void ***results, unsigned long *indices, unsigned long first_index, unsigned int max_items); unsigned long radix_tree_next_hole(struct radix_tree_root *root, unsigned long index, unsigned long max_scan); -- cgit v1.2.3 From a2c16d6cb0e478812829ca84aeabd02e36af35eb Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Wed, 3 Aug 2011 16:21:19 -0700 Subject: mm: let swap use exceptional entries If swap entries are to be stored along with struct page pointers in a radix tree, they need to be distinguished as exceptional entries. Most of the handling of swap entries in radix tree will be contained in shmem.c, but a few functions in filemap.c's common code need to check for their appearance: find_get_page(), find_lock_page(), find_get_pages() and find_get_pages_contig(). So as not to slow their fast paths, tuck those checks inside the existing checks for unlikely radix_tree_deref_slot(); except for find_lock_page(), where it is an added test. And make it a BUG in find_get_pages_tag(), which is not applied to tmpfs files. A part of the reason for eliminating shmem_readpage() earlier, was to minimize the places where common code would need to allow for swap entries. The swp_entry_t known to swapfile.c must be massaged into a slightly different form when stored in the radix tree, just as it gets massaged into a pte_t when stored in page tables. In an i386 kernel this limits its information (type and page offset) to 30 bits: given 32 "types" of swapfile and 4kB pagesize, that's a maximum swapfile size of 128GB. Which is less than the 512GB we previously allowed with X86_PAE (where the swap entry can occupy the entire upper 32 bits of a pte_t), but not a new limitation on 32-bit without PAE; and there's not a new limitation on 64-bit (where swap filesize is already limited to 16TB by a 32-bit page offset). Thirty areas of 128GB is probably still enough swap for a 64GB 32-bit machine. Provide swp_to_radix_entry() and radix_to_swp_entry() conversions, and enforce filesize limit in read_swap_header(), just as for ptes. Signed-off-by: Hugh Dickins Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swapops.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index cd42e30b7c6e..2189d3ffc85d 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -1,3 +1,8 @@ +#ifndef _LINUX_SWAPOPS_H +#define _LINUX_SWAPOPS_H + +#include + /* * swapcache pages are stored in the swapper_space radix tree. We want to * get good packing density in that tree, so the index should be dense in @@ -76,6 +81,22 @@ static inline pte_t swp_entry_to_pte(swp_entry_t entry) return __swp_entry_to_pte(arch_entry); } +static inline swp_entry_t radix_to_swp_entry(void *arg) +{ + swp_entry_t entry; + + entry.val = (unsigned long)arg >> RADIX_TREE_EXCEPTIONAL_SHIFT; + return entry; +} + +static inline void *swp_to_radix_entry(swp_entry_t entry) +{ + unsigned long value; + + value = entry.val << RADIX_TREE_EXCEPTIONAL_SHIFT; + return (void *)(value | RADIX_TREE_EXCEPTIONAL_ENTRY); +} + #ifdef CONFIG_MIGRATION static inline swp_entry_t make_migration_entry(struct page *page, int write) { @@ -169,3 +190,5 @@ static inline int non_swap_entry(swp_entry_t entry) return 0; } #endif + +#endif /* _LINUX_SWAPOPS_H */ -- cgit v1.2.3 From 285b2c4fdd69ea73b4762785d8c6be83b6c074a6 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Wed, 3 Aug 2011 16:21:20 -0700 Subject: tmpfs: demolish old swap vector support The maximum size of a shmem/tmpfs file has been limited by the maximum size of its triple-indirect swap vector. With 4kB page size, maximum filesize was just over 2TB on a 32-bit kernel, but sadly one eighth of that on a 64-bit kernel. (With 8kB page size, maximum filesize was just over 4TB on a 64-bit kernel, but 16TB on a 32-bit kernel, MAX_LFS_FILESIZE being then more restrictive than swap vector layout.) It's a shame that tmpfs should be more restrictive than ramfs, and this limitation has now been noticed. Add another level to the swap vector? No, it became obscure and hard to maintain, once I complicated it to make use of highmem pages nine years ago: better choose another way. Surely, if 2.4 had had the radix tree pagecache introduced in 2.5, then tmpfs would never have invented its own peculiar radix tree: we would have fitted swap entries into the common radix tree instead, in much the same way as we fit swap entries into page tables. And why should each file have a separate radix tree for its pages and for its swap entries? The swap entries are required precisely where and when the pages are not. We want to put them together in a single radix tree: which can then avoid much of the locking which was needed to prevent them from being exchanged underneath us. This also avoids the waste of memory devoted to swap vectors, first in the shmem_inode itself, then at least two more pages once a file grew beyond 16 data pages (pages accounted by df and du, but not by memcg). Allocated upfront, to avoid allocation when under swapping pressure, but pure waste when CONFIG_SWAP is not set - I have never spattered around the ifdefs to prevent that, preferring this move to sharing the common radix tree instead. There are three downsides to sharing the radix tree. One, that it binds tmpfs more tightly to the rest of mm, either requiring knowledge of swap entries in radix tree there, or duplication of its code here in shmem.c. I believe that the simplications and memory savings (and probable higher performance, not yet measured) justify that. Two, that on HIGHMEM systems with SWAP enabled, it's the lowmem radix nodes that cannot be freed under memory pressure - whereas before it was the less precious highmem swap vector pages that could not be freed. I'm hoping that 64-bit has now been accessible for long enough, that the highmem argument has grown much less persuasive. Three, that swapoff is slower than it used to be on tmpfs files, since it's using a simple generic mechanism not tailored to it: I find this noticeable, and shall want to improve, but maybe nobody else will notice. So... now remove most of the old swap vector code from shmem.c. But, for the moment, keep the simple i_direct vector of 16 pages, with simple accessors shmem_put_swap() and shmem_get_swap(), as a toy implementation to help mark where swap needs to be handled in subsequent patches. Signed-off-by: Hugh Dickins Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shmem_fs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index aa08fa8fd79b..80b695213fdb 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -17,9 +17,7 @@ struct shmem_inode_info { unsigned long flags; unsigned long alloced; /* data pages alloced to file */ unsigned long swapped; /* subtotal assigned to swap */ - unsigned long next_index; /* highest alloced index + 1 */ struct shared_policy policy; /* NUMA memory alloc policy */ - struct page *i_indirect; /* top indirect blocks page */ union { swp_entry_t i_direct[SHMEM_NR_DIRECT]; /* first blocks */ char inline_symlink[SHMEM_SYMLINK_INLINE_LEN]; -- cgit v1.2.3 From 41ffe5d5ceef7f7ff2ff18e320d88ca6d629efaf Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Wed, 3 Aug 2011 16:21:21 -0700 Subject: tmpfs: miscellaneous trivial cleanups While it's at its least, make a number of boring nitpicky cleanups to shmem.c, mostly for consistency of variable naming. Things like "swap" instead of "entry", "pgoff_t index" instead of "unsigned long idx". And since everything else here is prefixed "shmem_", better change init_tmpfs() to shmem_init(). Signed-off-by: Hugh Dickins Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shmem_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 80b695213fdb..3f05795dcf7b 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -47,7 +47,7 @@ static inline struct shmem_inode_info *SHMEM_I(struct inode *inode) /* * Functions in mm/shmem.c called directly from elsewhere: */ -extern int init_tmpfs(void); +extern int shmem_init(void); extern int shmem_fill_super(struct super_block *sb, void *data, int silent); extern struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags); -- cgit v1.2.3 From aa3b189551ad8e5cc1d9c663735c131650238278 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Wed, 3 Aug 2011 16:21:24 -0700 Subject: tmpfs: convert mem_cgroup shmem to radix-swap Remove mem_cgroup_shmem_charge_fallback(): it was only required when we had to move swappage to filecache with GFP_NOWAIT. Remove the GFP_NOWAIT special case from mem_cgroup_cache_charge(), by moving its call out from shmem_add_to_page_cache() to two of thats three callers. But leave it doing mem_cgroup_uncharge_cache_page() on error: although asymmetrical, it's easier for all 3 callers to handle. These two changes would also be appropriate if anyone were to start using shmem_read_mapping_page_gfp() with GFP_NOWAIT. Remove mem_cgroup_get_shmem_target(): mc_handle_file_pte() can test radix_tree_exceptional_entry() to get what it needs for itself. Signed-off-by: Hugh Dickins Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 8 -------- include/linux/shmem_fs.h | 2 -- 2 files changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index b96600786913..3b535db00a94 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -86,8 +86,6 @@ extern void mem_cgroup_uncharge_end(void); extern void mem_cgroup_uncharge_page(struct page *page); extern void mem_cgroup_uncharge_cache_page(struct page *page); -extern int mem_cgroup_shmem_charge_fallback(struct page *page, - struct mm_struct *mm, gfp_t gfp_mask); extern void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask); int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem); @@ -225,12 +223,6 @@ static inline void mem_cgroup_uncharge_cache_page(struct page *page) { } -static inline int mem_cgroup_shmem_charge_fallback(struct page *page, - struct mm_struct *mm, gfp_t gfp_mask) -{ - return 0; -} - static inline void mem_cgroup_add_lru_list(struct page *page, int lru) { } diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 3f05795dcf7b..0c8e952df594 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -57,8 +57,6 @@ extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); extern int shmem_unuse(swp_entry_t entry, struct page *page); -extern void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t pgoff, - struct page **pagep, swp_entry_t *ent); static inline struct page *shmem_read_mapping_page( struct address_space *mapping, pgoff_t index) -- cgit v1.2.3 From 69f07ec938712b58755add82dd3d0b35f01317cc Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Wed, 3 Aug 2011 16:21:26 -0700 Subject: tmpfs: use kmemdup for short symlinks But we've not yet removed the old swp_entry_t i_direct[16] from shmem_inode_info. That's because it was still being shared with the inline symlink. Remove it now (saving 64 or 128 bytes from shmem inode size), and use kmemdup() for short symlinks, say, those up to 128 bytes. I wonder why mpol_free_shared_policy() is done in shmem_destroy_inode() rather than shmem_evict_inode(), where we usually do such freeing? I guess it doesn't matter, and I'm not into NUMA mpol testing right now. Signed-off-by: Hugh Dickins Acked-by: Rik van Riel Reviewed-by: Pekka Enberg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shmem_fs.h | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 0c8e952df594..9291ac3cc627 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -8,20 +8,15 @@ /* inode in-kernel data */ -#define SHMEM_NR_DIRECT 16 - -#define SHMEM_SYMLINK_INLINE_LEN (SHMEM_NR_DIRECT * sizeof(swp_entry_t)) - struct shmem_inode_info { spinlock_t lock; unsigned long flags; unsigned long alloced; /* data pages alloced to file */ - unsigned long swapped; /* subtotal assigned to swap */ - struct shared_policy policy; /* NUMA memory alloc policy */ union { - swp_entry_t i_direct[SHMEM_NR_DIRECT]; /* first blocks */ - char inline_symlink[SHMEM_SYMLINK_INLINE_LEN]; + unsigned long swapped; /* subtotal assigned to swap */ + char *symlink; /* unswappable short symlink */ }; + struct shared_policy policy; /* NUMA memory alloc policy */ struct list_head swaplist; /* chain of maybes on swap */ struct list_head xattr_list; /* list of shmem_xattr */ struct inode vfs_inode; -- cgit v1.2.3 From e504f3fdd63d486d45b18009e5a65f2e329acb0a Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Wed, 3 Aug 2011 16:21:27 -0700 Subject: tmpfs radix_tree: locate_item to speed up swapoff We have already acknowledged that swapoff of a tmpfs file is slower than it was before conversion to the generic radix_tree: a little slower there will be acceptable, if the hotter paths are faster. But it was a shock to find swapoff of a 500MB file 20 times slower on my laptop, taking 10 minutes; and at that rate it significantly slows down my testing. Now, most of that turned out to be overhead from PROVE_LOCKING and PROVE_RCU: without those it was only 4 times slower than before; and more realistic tests on other machines don't fare as badly. I've tried a number of things to improve it, including tagging the swap entries, then doing lookup by tag: I'd expected that to halve the time, but in practice it's erratic, and often counter-productive. The only change I've so far found to make a consistent improvement, is to short-circuit the way we go back and forth, gang lookup packing entries into the array supplied, then shmem scanning that array for the target entry. Scanning in place doubles the speed, so it's now only twice as slow as before (or three times slower when the PROVEs are on). So, add radix_tree_locate_item() as an expedient, once-off, single-caller hack to do the lookup directly in place. #ifdef it on CONFIG_SHMEM and CONFIG_SWAP, as much to document its limited applicability as save space in other configurations. And, sadly, #include sched.h for cond_resched(). Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index b7edf8251455..9d4539c52e53 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -252,6 +252,7 @@ unsigned long radix_tree_range_tag_if_tagged(struct radix_tree_root *root, unsigned long nr_to_tag, unsigned int fromtag, unsigned int totag); int radix_tree_tagged(struct radix_tree_root *root, unsigned int tag); +unsigned long radix_tree_locate_item(struct radix_tree_root *root, void *item); static inline void radix_tree_preload_end(void) { -- cgit v1.2.3 From fe55c1844a1c106e9d9d3dd27cbfcf8caeb9e77e Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Thu, 4 Aug 2011 10:27:32 +0100 Subject: Revert "dt: add of_alias_scan and of_alias_get_id" This reverts commit 750f463a749e28464151ad26938d11b07b1c43cb. of_alias_* still needs work to be generalized for 'promtree' dt platforms, and to no implicitly create entries for available ids. Signed-off-by: Grant Likely --- include/linux/of.h | 8 -------- include/linux/of_fdt.h | 1 + 2 files changed, 1 insertion(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index bc3dc6399547..0085bb01c041 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -68,7 +68,6 @@ struct device_node { /* Pointer for first entry in chain of all nodes. */ extern struct device_node *allnodes; extern struct device_node *of_chosen; -extern struct device_node *of_aliases; extern rwlock_t devtree_lock; static inline bool of_have_populated_dt(void) @@ -210,9 +209,6 @@ extern int of_device_is_available(const struct device_node *device); extern const void *of_get_property(const struct device_node *node, const char *name, int *lenp); -#define for_each_property(pp, properties) \ - for (pp = properties; pp != NULL; pp = pp->next) - extern int of_n_addr_cells(struct device_node *np); extern int of_n_size_cells(struct device_node *np); extern const struct of_device_id *of_match_node( @@ -225,10 +221,6 @@ extern int of_parse_phandles_with_args(struct device_node *np, const char *list_name, const char *cells_name, int index, struct device_node **out_node, const void **out_args); -extern void *early_init_dt_alloc_memory_arch(u64 size, u64 align); -extern void of_alias_scan(void); -extern int of_alias_get_id(struct device_node *np, const char *stem); - extern int of_machine_is_compatible(const char *compat); extern int prom_add_property(struct device_node* np, struct property* prop); diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index b74b74ffe0e7..c84d900fbbb3 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -97,6 +97,7 @@ extern void early_init_dt_check_for_initrd(unsigned long node); extern int early_init_dt_scan_memory(unsigned long node, const char *uname, int depth, void *data); extern void early_init_dt_add_memory_arch(u64 base, u64 size); +extern void * early_init_dt_alloc_memory_arch(u64 size, u64 align); extern u64 dt_mem_next_cell(int s, __be32 **cellp); /* -- cgit v1.2.3 From 655b16128482fd12808f77a6799eea5419c93709 Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Sun, 29 May 2011 10:57:47 +0300 Subject: nfs_xdr: Move nfs4_string definition out of #ifdef CONFIG_NFS_V4 exofs file system wants to use pnfs_osd_xdr.h file instead of redefining pnfs-objects types in it's private "pnfs.h" headr. Before we do the switch we must make sure pnfs_osd_xdr.h is compilable also under NFS versions smaller than 4.1. Since now it is needed regardless of version, by the exofs code. nfs4_string is not the only nfs4 type out in the global scope. Ack-by: Trond Myklebust Signed-off-by: Boaz Harrosh --- include/linux/nfs_xdr.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 00848d86ffb2..d9f5e8d6ca84 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -759,6 +759,11 @@ struct nfs3_getaclres { struct posix_acl * acl_default; }; +struct nfs4_string { + unsigned int len; + char *data; +}; + #ifdef CONFIG_NFS_V4 typedef u64 clientid4; @@ -949,11 +954,6 @@ struct nfs4_server_caps_res { struct nfs4_sequence_res seq_res; }; -struct nfs4_string { - unsigned int len; - char *data; -}; - #define NFS4_PATHNAME_MAXCOMPONENTS 512 struct nfs4_pathname { unsigned int ncomponents; -- cgit v1.2.3 From 33009557bd9397c446a59e4cc91059a8e84c046b Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Tue, 24 May 2011 15:16:43 -0400 Subject: Add KEY_MICMUTE and enable it on Lenovo X220 I suspect that this works on T410. Signed-off-by: Andy Lutomirski Signed-off-by: Matthew Garrett --- include/linux/input.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/input.h b/include/linux/input.h index 068784e17972..a637e7814334 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -438,6 +438,8 @@ struct input_keymap_entry { #define KEY_WIMAX 246 #define KEY_RFKILL 247 /* Key that controls all radios */ +#define KEY_MICMUTE 248 /* Mute / unmute the microphone */ + /* Code 255 is reserved for special needs of AT keyboard driver */ #define BTN_MISC 0x100 -- cgit v1.2.3 From 1eb19a12bd2214cdcad5273d472b062a4ba97fa1 Mon Sep 17 00:00:00 2001 From: Mandeep Singh Baines Date: Fri, 5 Aug 2011 18:46:27 -0700 Subject: lib/sha1: use the git implementation of SHA-1 For ChromiumOS, we use SHA-1 to verify the integrity of the root filesystem. The speed of the kernel sha-1 implementation has a major impact on our boot performance. To improve boot performance, we investigated using the heavily optimized sha-1 implementation used in git. With the git sha-1 implementation, we see a 11.7% improvement in boot time. 10 reboots, remove slowest/fastest. Before: Mean: 6.58 seconds Stdev: 0.14 After (with git sha-1, this patch): Mean: 5.89 seconds Stdev: 0.07 The other cool thing about the git SHA-1 implementation is that it only needs 64 bytes of stack for the workspace while the original kernel implementation needed 320 bytes. Signed-off-by: Mandeep Singh Baines Cc: Ramsay Jones Cc: Nicolas Pitre Cc: Herbert Xu Cc: David S. Miller Cc: linux-crypto@vger.kernel.org Signed-off-by: Linus Torvalds --- include/linux/cryptohash.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cryptohash.h b/include/linux/cryptohash.h index ec78a4bbe1d5..f9452185b019 100644 --- a/include/linux/cryptohash.h +++ b/include/linux/cryptohash.h @@ -3,7 +3,7 @@ #define SHA_DIGEST_WORDS 5 #define SHA_MESSAGE_BYTES (512 /*bits*/ / 8) -#define SHA_WORKSPACE_WORDS 80 +#define SHA_WORKSPACE_WORDS 16 void sha_init(__u32 *buf); void sha_transform(__u32 *digest, const char *data, __u32 *W); -- cgit v1.2.3 From bc0b96b54a21246e377122d54569eef71cec535f Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 3 Aug 2011 19:45:10 -0700 Subject: crypto: Move md5_transform to lib/md5.c We are going to use this for TCP/IP sequence number and fragment ID generation. Signed-off-by: David S. Miller --- include/linux/cryptohash.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cryptohash.h b/include/linux/cryptohash.h index ec78a4bbe1d5..d2984fbebbc0 100644 --- a/include/linux/cryptohash.h +++ b/include/linux/cryptohash.h @@ -8,6 +8,11 @@ void sha_init(__u32 *buf); void sha_transform(__u32 *digest, const char *data, __u32 *W); +#define MD5_DIGEST_WORDS 4 +#define MD5_MESSAGE_BYTES 64 + +void md5_transform(__u32 *hash, __u32 const *in); + __u32 half_md4_transform(__u32 buf[4], __u32 const in[8]); #endif -- cgit v1.2.3 From 6e5714eaf77d79ae1c8b47e3e040ff5411b717ec Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 3 Aug 2011 20:50:44 -0700 Subject: net: Compute protocol sequence numbers and fragment IDs using MD5. Computers have become a lot faster since we compromised on the partial MD4 hash which we use currently for performance reasons. MD5 is a much safer choice, and is inline with both RFC1948 and other ISS generators (OpenBSD, Solaris, etc.) Furthermore, only having 24-bits of the sequence number be truly unpredictable is a very serious limitation. So the periodic regeneration and 8-bit counter have been removed. We compute and use a full 32-bit sequence number. For ipv6, DCCP was found to use a 32-bit truncated initial sequence number (it needs 43-bits) and that is fixed here as well. Reported-by: Dan Kaminsky Tested-by: Willy Tarreau Signed-off-by: David S. Miller --- include/linux/random.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/random.h b/include/linux/random.h index ce29a040c8dc..d13059f3ea32 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -57,18 +57,6 @@ extern void add_interrupt_randomness(int irq); extern void get_random_bytes(void *buf, int nbytes); void generate_random_uuid(unsigned char uuid_out[16]); -extern __u32 secure_ip_id(__be32 daddr); -extern __u32 secure_ipv6_id(const __be32 daddr[4]); -extern u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); -extern u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, - __be16 dport); -extern __u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr, - __be16 sport, __be16 dport); -extern __u32 secure_tcpv6_sequence_number(__be32 *saddr, __be32 *daddr, - __be16 sport, __be16 dport); -extern u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr, - __be16 sport, __be16 dport); - #ifndef MODULE extern const struct file_operations random_fops, urandom_fops; #endif -- cgit v1.2.3 From 830c0f0edca67403d361fe976a25b17356c11f19 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 6 Aug 2011 22:41:50 -0700 Subject: vfs: renumber DCACHE_xyz flags, remove some stale ones Gcc tends to generate better code with small integers, including the DCACHE_xyz flag tests - so move the common ones to be first in the list. Also just remove the unused DCACHE_INOTIFY_PARENT_WATCHED and DCACHE_AUTOFS_PENDING values, their users no longer exists in the source tree. And add a "unlikely()" to the DCACHE_OP_COMPARE test, since we want the common case to be a nice straight-line fall-through. Signed-off-by: Linus Torvalds --- include/linux/dcache.h | 30 +++++++++++++----------------- 1 file changed, 13 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index d37d2a793099..62157c03caf7 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -180,12 +180,12 @@ struct dentry_operations { */ /* d_flags entries */ -#define DCACHE_AUTOFS_PENDING 0x0001 /* autofs: "under construction" */ -#define DCACHE_NFSFS_RENAMED 0x0002 - /* this dentry has been "silly renamed" and has to be deleted on the last - * dput() */ +#define DCACHE_OP_HASH 0x0001 +#define DCACHE_OP_COMPARE 0x0002 +#define DCACHE_OP_REVALIDATE 0x0004 +#define DCACHE_OP_DELETE 0x0008 -#define DCACHE_DISCONNECTED 0x0004 +#define DCACHE_DISCONNECTED 0x0010 /* This dentry is possibly not currently connected to the dcache tree, in * which case its parent will either be itself, or will have this flag as * well. nfsd will not use a dentry with this bit set, but will first @@ -196,22 +196,18 @@ struct dentry_operations { * dentry into place and return that dentry rather than the passed one, * typically using d_splice_alias. */ -#define DCACHE_REFERENCED 0x0008 /* Recently used, don't discard. */ -#define DCACHE_RCUACCESS 0x0010 /* Entry has ever been RCU-visible */ -#define DCACHE_INOTIFY_PARENT_WATCHED 0x0020 - /* Parent inode is watched by inotify */ - -#define DCACHE_COOKIE 0x0040 /* For use by dcookie subsystem */ -#define DCACHE_FSNOTIFY_PARENT_WATCHED 0x0080 - /* Parent inode is watched by some fsnotify listener */ +#define DCACHE_REFERENCED 0x0020 /* Recently used, don't discard. */ +#define DCACHE_RCUACCESS 0x0040 /* Entry has ever been RCU-visible */ #define DCACHE_CANT_MOUNT 0x0100 #define DCACHE_GENOCIDE 0x0200 -#define DCACHE_OP_HASH 0x1000 -#define DCACHE_OP_COMPARE 0x2000 -#define DCACHE_OP_REVALIDATE 0x4000 -#define DCACHE_OP_DELETE 0x8000 +#define DCACHE_NFSFS_RENAMED 0x1000 + /* this dentry has been "silly renamed" and has to be deleted on the last + * dput() */ +#define DCACHE_COOKIE 0x2000 /* For use by dcookie subsystem */ +#define DCACHE_FSNOTIFY_PARENT_WATCHED 0x4000 + /* Parent inode is watched by some fsnotify listener */ #define DCACHE_MOUNTED 0x10000 /* is a mountpoint */ #define DCACHE_NEED_AUTOMOUNT 0x20000 /* handle automount on this dir */ -- cgit v1.2.3 From 3ddcd0569cd68f00f3beae9a7959b72918bb91f4 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 6 Aug 2011 22:45:50 -0700 Subject: vfs: optimize inode cache access patterns The inode structure layout is largely random, and some of the vfs paths really do care. The path lookup in particular is already quite D$ intensive, and profiles show that accessing the 'inode->i_op->xyz' fields is quite costly. We already optimized the dcache to not unnecessarily load the d_op structure for members that are often NULL using the DCACHE_OP_xyz bits in dentry->d_flags, and this does something very similar for the inode ops that are used during pathname lookup. It also re-orders the fields so that the fields accessed by 'stat' are together at the beginning of the inode structure, and roughly in the order accessed. The effect of this seems to be in the 1-2% range for an empty kernel "make -j" run (which is fairly kernel-intensive, mostly in filename lookup), so it's visible. The numbers are fairly noisy, though, and likely depend a lot on exact microarchitecture. So there's more tuning to be done. Signed-off-by: Linus Torvalds --- include/linux/fs.h | 59 ++++++++++++++++++++++++++++++++++-------------------- 1 file changed, 37 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 786b3b1113cf..178cdb4f1d4a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -738,22 +738,54 @@ static inline int mapping_writably_mapped(struct address_space *mapping) struct posix_acl; #define ACL_NOT_CACHED ((void *)(-1)) +#define IOP_FASTPERM 0x0001 +#define IOP_LOOKUP 0x0002 +#define IOP_NOFOLLOW 0x0004 + +/* + * Keep mostly read-only and often accessed (especially for + * the RCU path lookup and 'stat' data) fields at the beginning + * of the 'struct inode' + */ struct inode { - /* RCU path lookup touches following: */ umode_t i_mode; + unsigned short i_opflags; uid_t i_uid; gid_t i_gid; + unsigned int i_flags; + +#ifdef CONFIG_FS_POSIX_ACL + struct posix_acl *i_acl; + struct posix_acl *i_default_acl; +#endif + const struct inode_operations *i_op; struct super_block *i_sb; + struct address_space *i_mapping; - spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ - unsigned int i_flags; - unsigned long i_state; #ifdef CONFIG_SECURITY void *i_security; #endif - struct mutex i_mutex; + /* Stat data, not accessed from path walking */ + unsigned long i_ino; + unsigned int i_nlink; + dev_t i_rdev; + loff_t i_size; + struct timespec i_atime; + struct timespec i_mtime; + struct timespec i_ctime; + unsigned int i_blkbits; + blkcnt_t i_blocks; + +#ifdef __NEED_I_SIZE_ORDERED + seqcount_t i_size_seqcount; +#endif + + /* Misc */ + unsigned long i_state; + spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ + struct mutex i_mutex; unsigned long dirtied_when; /* jiffies of first dirtying */ @@ -765,25 +797,12 @@ struct inode { struct list_head i_dentry; struct rcu_head i_rcu; }; - unsigned long i_ino; atomic_t i_count; - unsigned int i_nlink; - dev_t i_rdev; - unsigned int i_blkbits; u64 i_version; - loff_t i_size; -#ifdef __NEED_I_SIZE_ORDERED - seqcount_t i_size_seqcount; -#endif - struct timespec i_atime; - struct timespec i_mtime; - struct timespec i_ctime; - blkcnt_t i_blocks; unsigned short i_bytes; atomic_t i_dio_count; const struct file_operations *i_fop; /* former ->i_op->default_file_ops */ struct file_lock *i_flock; - struct address_space *i_mapping; struct address_space i_data; #ifdef CONFIG_QUOTA struct dquot *i_dquot[MAXQUOTAS]; @@ -806,10 +825,6 @@ struct inode { atomic_t i_readcount; /* struct files open RO */ #endif atomic_t i_writecount; -#ifdef CONFIG_FS_POSIX_ACL - struct posix_acl *i_acl; - struct posix_acl *i_default_acl; -#endif void *i_private; /* fs or device private pointer */ }; -- cgit v1.2.3 From 3295514841c2112d94451ba5deaf54f5afb78ea9 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 7 Aug 2011 18:55:11 +0100 Subject: fix rcu annotations noise in cred.h task->cred is declared as __rcu, and access to other tasks' ->cred is, indeed, protected. Access to current->cred does not need rcu_dereference() at all, since only the task itself can change its ->cred. sparse, of course, has no way of knowing that... Add force-cast in current_cred(), make current_fsuid() et.al. use it. Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/cred.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cred.h b/include/linux/cred.h index 48e82af1159b..98f46efbe2d2 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -265,10 +265,11 @@ static inline void put_cred(const struct cred *_cred) /** * current_cred - Access the current task's subjective credentials * - * Access the subjective credentials of the current task. + * Access the subjective credentials of the current task. RCU-safe, + * since nobody else can modify it. */ #define current_cred() \ - (current->cred) + (*(__force struct cred **)¤t->cred) /** * __task_cred - Access a task's objective credentials @@ -307,7 +308,7 @@ static inline void put_cred(const struct cred *_cred) ({ \ struct user_struct *__u; \ struct cred *__cred; \ - __cred = (struct cred *) current_cred(); \ + __cred = current_cred(); \ __u = get_uid(__cred->user); \ __u; \ }) @@ -322,7 +323,7 @@ static inline void put_cred(const struct cred *_cred) ({ \ struct group_info *__groups; \ struct cred *__cred; \ - __cred = (struct cred *) current_cred(); \ + __cred = current_cred(); \ __groups = get_group_info(__cred->group_info); \ __groups; \ }) @@ -341,7 +342,7 @@ static inline void put_cred(const struct cred *_cred) #define current_cred_xxx(xxx) \ ({ \ - current->cred->xxx; \ + current_cred()->xxx; \ }) #define current_uid() (current_cred_xxx(uid)) -- cgit v1.2.3