From 35ac6f081f26e1b6b3482b9c8dfccebe7817c691 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Tue, 9 Nov 2010 13:57:29 +0000 Subject: mmc: sdhci: Fix crash on boot with C0 stepping Moorestown platforms SDHC2 is newly added in C0 stepping of Langwell. Without the Moorestown specific quirk, the default pci_probe will be called and crash the kernel. This patch unblocks the crash problem on C0 by using the same probing function as HC1, which limits the number of slots to one. Signed-off-by: Jacob Pan Signed-off-by: Alan Cox 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 c6bcfe93b9ca..d369b533dc2a 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2441,6 +2441,7 @@ #define PCI_DEVICE_ID_INTEL_MFD_SDIO2 0x0822 #define PCI_DEVICE_ID_INTEL_MFD_EMMC0 0x0823 #define PCI_DEVICE_ID_INTEL_MFD_EMMC1 0x0824 +#define PCI_DEVICE_ID_INTEL_MRST_SD2 0x084F #define PCI_DEVICE_ID_INTEL_I960 0x0960 #define PCI_DEVICE_ID_INTEL_I960RM 0x0962 #define PCI_DEVICE_ID_INTEL_8257X_SOL 0x1062 -- cgit v1.2.3 From e98b6fed84d0f0155d7b398e0dfeac74c792f2d0 Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Tue, 9 Nov 2010 12:24:53 -0800 Subject: ceph: fix comment, remove extraneous args The offset/length arguments aren't used. Signed-off-by: Sage Weil --- include/linux/ceph/libceph.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index f22b2e941686..9e76d35670d2 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -227,8 +227,7 @@ extern int ceph_open_session(struct ceph_client *client); extern void ceph_release_page_vector(struct page **pages, int num_pages); extern struct page **ceph_get_direct_page_vector(const char __user *data, - int num_pages, - loff_t off, size_t len); + int num_pages); extern void ceph_put_page_vector(struct page **pages, int num_pages); extern void ceph_release_page_vector(struct page **pages, int num_pages); extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags); -- cgit v1.2.3 From b7495fc2ff941db6a118a93ab8d61149e3f4cef8 Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Tue, 9 Nov 2010 12:43:12 -0800 Subject: ceph: make page alignment explicit in osd interface We used to infer alignment of IOs within a page based on the file offset, which assumed they matched. This broke with direct IO that was not aligned to pages (e.g., 512-byte aligned IO). We were also trusting the alignment specified in the OSD reply, which could have been adjusted by the server. Explicitly specify the page alignment when setting up OSD IO requests. Signed-off-by: Sage Weil --- include/linux/ceph/osd_client.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 6c91fb032c39..a1af29648fb5 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -79,6 +79,7 @@ struct ceph_osd_request { struct ceph_file_layout r_file_layout; struct ceph_snap_context *r_snapc; /* snap context for writes */ unsigned r_num_pages; /* size of page array (follows) */ + unsigned r_page_alignment; /* io offset in first page */ struct page **r_pages; /* pages for data payload */ int r_pages_from_pool; int r_own_pages; /* if true, i own page list */ @@ -194,7 +195,8 @@ extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *, int do_sync, u32 truncate_seq, u64 truncate_size, struct timespec *mtime, - bool use_mempool, int num_reply); + bool use_mempool, int num_reply, + int page_align); static inline void ceph_osdc_get_request(struct ceph_osd_request *req) { @@ -218,7 +220,8 @@ extern int ceph_osdc_readpages(struct ceph_osd_client *osdc, struct ceph_file_layout *layout, u64 off, u64 *plen, u32 truncate_seq, u64 truncate_size, - struct page **pages, int nr_pages); + struct page **pages, int nr_pages, + int page_align); extern int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino, -- cgit v1.2.3 From c5c6b19d4b8f5431fca05f28ae9e141045022149 Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Tue, 9 Nov 2010 12:40:00 -0800 Subject: ceph: explicitly specify page alignment in network messages The alignment used for reading data into or out of pages used to be taken from the data_off field in the message header. This only worked as long as the page alignment matched the object offset, breaking direct io to non-page aligned offsets. Instead, explicitly specify the page alignment next to the page vector in the ceph_msg struct, and use that instead of the message header (which probably shouldn't be trusted). The alloc_msg callback is responsible for filling in this field properly when it sets up the page vector. 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 5956d62c3057..a108b425fee2 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -82,6 +82,7 @@ struct ceph_msg { struct ceph_buffer *middle; struct page **pages; /* data payload. NOT OWNER. */ unsigned nr_pages; /* size of page array */ + unsigned page_alignment; /* io offset in first page */ struct ceph_pagelist *pagelist; /* instead of pages */ struct list_head list_head; struct kref kref; -- cgit v1.2.3 From aae6d3ddd8b90f5b2c8d79a2b914d1706d124193 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Fri, 17 Sep 2010 15:02:32 -0700 Subject: sched: Use group weight, idle cpu metrics to fix imbalances during idle Currently we consider a sched domain to be well balanced when the imbalance is less than the domain's imablance_pct. As the number of cores and threads are increasing, current values of imbalance_pct (for example 25% for a NUMA domain) are not enough to detect imbalances like: a) On a WSM-EP system (two sockets, each having 6 cores and 12 logical threads), 24 cpu-hogging tasks get scheduled as 13 on one socket and 11 on another socket. Leading to an idle HT cpu. b) On a hypothetial 2 socket NHM-EX system (each socket having 8 cores and 16 logical threads), 16 cpu-hogging tasks can get scheduled as 9 on one socket and 7 on another socket. Leaving one core in a socket idle whereas in another socket we have a core having both its HT siblings busy. While this issue can be fixed by decreasing the domain's imbalance_pct (by making it a function of number of logical cpus in the domain), it can potentially cause more task migrations across sched groups in an overloaded case. Fix this by using imbalance_pct only during newly_idle and busy load balancing. And during idle load balancing, check if there is an imbalance in number of idle cpu's across the busiest and this sched_group or if the busiest group has more tasks than its weight that the idle cpu in this_group can pull. Reported-by: Nikhil Rao Signed-off-by: Suresh Siddha Signed-off-by: Peter Zijlstra LKML-Reference: <1284760952.2676.11.camel@sbsiddha-MOBL3.sc.intel.com> 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 d0036e52a24a..2c79e921a68b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -862,6 +862,7 @@ struct sched_group { * single CPU. */ unsigned int cpu_power, cpu_power_orig; + unsigned int group_weight; /* * The CPUs this group covers. -- cgit v1.2.3 From b17cd8d69a75f921d9d444cc3ac9b5b1d0b66ca0 Mon Sep 17 00:00:00 2001 From: Brandon Philips Date: Sun, 7 Nov 2010 01:28:24 -0500 Subject: driver core: prune docs about device_interface drivers/base/intf.c was removed before the beginning of (git) time but its Documentation stuck around. Remove it. Signed-off-by: Brandon Philips Signed-off-by: Greg Kroah-Hartman --- include/linux/cpu.h | 5 ----- include/linux/node.h | 5 ----- 2 files changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 4823af64e9db..5f09323ee880 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -10,11 +10,6 @@ * * CPUs are exported via sysfs in the class/cpu/devices/ * directory. - * - * Per-cpu interfaces can be implemented using a struct device_interface. - * See the following for how to do this: - * - drivers/base/intf.c - * - Documentation/driver-model/interface.txt */ #ifndef _LINUX_CPU_H_ #define _LINUX_CPU_H_ diff --git a/include/linux/node.h b/include/linux/node.h index 06292dac3eab..1466945cc9ef 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -10,11 +10,6 @@ * * Nodes are exported via driverfs in the class/node/devices/ * directory. - * - * Per-node interfaces can be implemented using a struct device_interface. - * See the following for how to do this: - * - drivers/base/intf.c - * - Documentation/driver-model/interface.txt */ #ifndef _LINUX_NODE_H_ #define _LINUX_NODE_H_ -- cgit v1.2.3 From 318af55ddd38bdaaa2b57f5c3bd394f3ce3a2610 Mon Sep 17 00:00:00 2001 From: "Hans J. Koch" Date: Sat, 30 Oct 2010 00:36:47 +0200 Subject: uio: Change mail address of Hans J. Koch My old mail address doesn't exist anymore. This changes all occurrences to my new address. Signed-off-by: Hans J. Koch Signed-off-by: Greg Kroah-Hartman --- include/linux/uio_driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uio_driver.h b/include/linux/uio_driver.h index d6188e5a52df..665517c05eaf 100644 --- a/include/linux/uio_driver.h +++ b/include/linux/uio_driver.h @@ -3,7 +3,7 @@ * * Copyright(C) 2005, Benedikt Spranger * Copyright(C) 2005, Thomas Gleixner - * Copyright(C) 2006, Hans J. Koch + * Copyright(C) 2006, Hans J. Koch * Copyright(C) 2006, Greg Kroah-Hartman * * Userspace IO driver. -- cgit v1.2.3 From 3c502e7a0255d82621ff25d60cc816624830497e Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Thu, 4 Nov 2010 17:33:01 -0500 Subject: perf,hw_breakpoint: Initialize hardware api earlier When using early debugging, the kernel does not initialize the hw_breakpoint API early enough and causes the late initialization of the kernel debugger to fail. The boot arguments are: earlyprintk=vga ekgdboc=kbd kgdbwait Then simply type "go" at the kdb prompt and boot. The kernel will later emit the message: kgdb: Could not allocate hwbreakpoints And at that point the kernel debugger will cease to work correctly. The solution is to initialize the hw_breakpoint at the same time that all the other perf call backs are initialized instead of using a core_initcall() initialization which happens well after the kernel debugger can make use of hardware breakpoints. Signed-off-by: Jason Wessel CC: Frederic Weisbecker CC: Ingo Molnar CC: Peter Zijlstra LKML-Reference: <4CD3396D.1090308@windriver.com> Signed-off-by: Frederic Weisbecker --- include/linux/hw_breakpoint.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h index a2d6ea49ec56..d1e55fed2c7d 100644 --- a/include/linux/hw_breakpoint.h +++ b/include/linux/hw_breakpoint.h @@ -33,6 +33,8 @@ enum bp_type_idx { #ifdef CONFIG_HAVE_HW_BREAKPOINT +extern int __init init_hw_breakpoint(void); + static inline void hw_breakpoint_init(struct perf_event_attr *attr) { memset(attr, 0, sizeof(*attr)); @@ -108,6 +110,8 @@ static inline struct arch_hw_breakpoint *counter_arch_bp(struct perf_event *bp) #else /* !CONFIG_HAVE_HW_BREAKPOINT */ +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, -- cgit v1.2.3 From 9a1683d1dd14d6ed35d2884c6b79ff12fc6bef39 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Mon, 15 Nov 2010 18:14:43 +0900 Subject: sh: clkfwk: Kill off unused clk_set_rate_ex(). With the refactoring of the SH7722 clock framework some time ago this abstraction has become unecessary. Kill it off before anyone else gets the bright idea to start using it. Signed-off-by: Paul Mundt --- include/linux/sh_clk.h | 30 ------------------------------ 1 file changed, 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sh_clk.h b/include/linux/sh_clk.h index cea0c38e7a63..30885d928801 100644 --- a/include/linux/sh_clk.h +++ b/include/linux/sh_clk.h @@ -67,36 +67,6 @@ int clk_register(struct clk *); void clk_unregister(struct clk *); void clk_enable_init_clocks(void); -/** - * clk_set_rate_ex - set the clock rate for a clock source, with additional parameter - * @clk: clock source - * @rate: desired clock rate in Hz - * @algo_id: algorithm id to be passed down to ops->set_rate - * - * Returns success (0) or negative errno. - */ -int clk_set_rate_ex(struct clk *clk, unsigned long rate, int algo_id); - -enum clk_sh_algo_id { - NO_CHANGE = 0, - - IUS_N1_N1, - IUS_322, - IUS_522, - IUS_N11, - - SB_N1, - - SB3_N1, - SB3_32, - SB3_43, - SB3_54, - - BP_N1, - - IP_N1, -}; - struct clk_div_mult_table { unsigned int *divisors; unsigned int nr_divisors; -- cgit v1.2.3 From 35a96c739fd7624b8edff990a74b86b5a85342da Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Mon, 15 Nov 2010 18:18:32 +0900 Subject: sh: clkfwk: Kill off now unused algo_id in set_rate op. Now that clk_set_rate_ex() is gone, there is also no way to get at rate setting algo id, which is now also completely unused. Kill it off before new clock ops start using it. Signed-off-by: Paul Mundt --- include/linux/sh_clk.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sh_clk.h b/include/linux/sh_clk.h index 30885d928801..038475a2092f 100644 --- a/include/linux/sh_clk.h +++ b/include/linux/sh_clk.h @@ -23,7 +23,7 @@ struct clk_ops { int (*enable)(struct clk *clk); void (*disable)(struct clk *clk); unsigned long (*recalc)(struct clk *clk); - int (*set_rate)(struct clk *clk, unsigned long rate, int algo_id); + int (*set_rate)(struct clk *clk, unsigned long rate); int (*set_parent)(struct clk *clk, struct clk *parent); long (*round_rate)(struct clk *clk, unsigned long rate); }; -- cgit v1.2.3 From 549015c36baadc6e67861bba6e927259e34c4d59 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Mon, 15 Nov 2010 18:48:25 +0900 Subject: sh: clkfwk: Disable init clk op for non-legacy clocks. Presently it's only legacy users that are using this clock op, guard it with an ifdef to ensure that no new users start using it. Signed-off-by: Paul Mundt --- include/linux/sh_clk.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sh_clk.h b/include/linux/sh_clk.h index 038475a2092f..9a52f72527dc 100644 --- a/include/linux/sh_clk.h +++ b/include/linux/sh_clk.h @@ -19,7 +19,9 @@ struct clk_mapping { }; struct clk_ops { +#ifdef CONFIG_SH_CLK_CPG_LEGACY void (*init)(struct clk *clk); +#endif int (*enable)(struct clk *clk); void (*disable)(struct clk *clk); unsigned long (*recalc)(struct clk *clk); -- cgit v1.2.3 From 3b42a96dc7870c53d20b419185737d3b8f7a7b74 Mon Sep 17 00:00:00 2001 From: Andy Whitcroft Date: Mon, 15 Nov 2010 06:01:59 +0000 Subject: net: rtnetlink.h -- only include linux/netdevice.h when used by the kernel MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The commit below added a new helper dev_ingress_queue to cleanly obtain the ingress queue pointer. This necessitated including 'linux/netdevice.h': commit 24824a09e35402b8d58dcc5be803a5ad3937bdba Author: Eric Dumazet Date: Sat Oct 2 06:11:55 2010 +0000 net: dynamic ingress_queue allocation However this include triggers issues for applications in userspace which use the rtnetlink interfaces. Commonly this requires they include 'net/if.h' and 'linux/rtnetlink.h' leading to a compiler error as below: In file included from /usr/include/linux/netdevice.h:28:0, from /usr/include/linux/rtnetlink.h:9, from t.c:2: /usr/include/linux/if.h:135:8: error: redefinition of ‘struct ifmap’ /usr/include/net/if.h:112:8: note: originally defined here /usr/include/linux/if.h:169:8: error: redefinition of ‘struct ifreq’ /usr/include/net/if.h:127:8: note: originally defined here /usr/include/linux/if.h:218:8: error: redefinition of ‘struct ifconf’ /usr/include/net/if.h:177:8: note: originally defined here The new helper is only defined for the kernel and protected by __KERNEL__ therefore we can simply pull the include down into the same protected section. Signed-off-by: Andy Whitcroft Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index d42f274418b8..bbad657a3725 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -6,7 +6,6 @@ #include #include #include -#include /* rtnetlink families. Values up to 127 are reserved for real address * families, values above 128 may be used arbitrarily. @@ -606,6 +605,7 @@ struct tcamsg { #ifdef __KERNEL__ #include +#include static __inline__ int rtattr_strcmp(const struct rtattr *rta, const char *str) { -- cgit v1.2.3 From 8e35f8e7c61c88f9a979a4e6f7f4ffd4c158a88a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 2 Nov 2010 09:11:55 -0400 Subject: NLM: Fix a regression in lockd Nick Bowler reports: There are no unusual messages on the client... but I just logged into the server and I see lots of messages of the following form: nfsd: request from insecure port (192.168.8.199:35766)! nfsd: request from insecure port (192.168.8.199:35766)! nfsd: request from insecure port (192.168.8.199:35766)! nfsd: request from insecure port (192.168.8.199:35766)! nfsd: request from insecure port (192.168.8.199:35766)! Bisected to commit 9247685088398cf21bcb513bd2832b4cd42516c4 (SUNRPC: Properly initialize sock_xprt.srcaddr in all cases) Apparently, removing the 'transport->srcaddr.ss_family = family' from xs_create_sock() triggers this due to nlmclnt_lookup_host() incorrectly initialising the srcaddr family to AF_UNSPEC. Reported-by: Nick Bowler Signed-off-by: Trond Myklebust --- include/linux/lockd/lockd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index a34dea46b629..2dee05e5119a 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -43,6 +43,7 @@ struct nlm_host { struct sockaddr_storage h_addr; /* peer address */ size_t h_addrlen; struct sockaddr_storage h_srcaddr; /* our address (optional) */ + size_t h_srcaddrlen; struct rpc_clnt *h_rpcclnt; /* RPC client to talk to peer */ char *h_name; /* remote hostname */ u32 h_version; /* interface version */ -- cgit v1.2.3 From 5685b971362651ee3d99ff3cc512c3bbd049d34d Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 12 Nov 2010 09:23:04 -0500 Subject: nfs: trivial: remove unused nfs_wait_event macro Nothing uses this macro anymore. Signed-off-by: Jeff Layton Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index bba26684acdc..c66fdb7d6998 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -593,12 +593,6 @@ nfs_fileid_to_ino_t(u64 fileid) return ino; } -#define nfs_wait_event(clnt, wq, condition) \ -({ \ - int __retval = wait_event_killable(wq, condition); \ - __retval; \ -}) - #define NFS_JUKEBOX_RETRY_TIME (5 * HZ) #endif /* __KERNEL__ */ -- cgit v1.2.3 From f281233d3eba15fb225d21ae2e228fd4553d824a Mon Sep 17 00:00:00 2001 From: Jeff Garzik Date: Tue, 16 Nov 2010 02:10:29 -0500 Subject: SCSI host lock push-down Move the mid-layer's ->queuecommand() invocation from being locked with the host lock to being unlocked to facilitate speeding up the critical path for drivers who don't need this lock taken anyway. The patch below presents a simple SCSI host lock push-down as an equivalent transformation. No locking or other behavior should change with this patch. All existing bugs and locking orders are preserved. Additionally, add one parameter to queuecommand, struct Scsi_Host * and remove one parameter from queuecommand, void (*done)(struct scsi_cmnd *) Scsi_Host* is a convenient pointer that most host drivers need anyway, and 'done' is redundant to struct scsi_cmnd->scsi_done. Minimal code disturbance was attempted with this change. Most drivers needed only two one-line modifications for their host lock push-down. Signed-off-by: Jeff Garzik Acked-by: James Bottomley Signed-off-by: Linus Torvalds --- include/linux/libata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 15b77b8dc7e1..d947b1231662 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -986,7 +986,7 @@ extern void ata_host_init(struct ata_host *, struct device *, unsigned long, struct ata_port_operations *); extern int ata_scsi_detect(struct scsi_host_template *sht); extern int ata_scsi_ioctl(struct scsi_device *dev, int cmd, void __user *arg); -extern int ata_scsi_queuecmd(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *)); +extern int ata_scsi_queuecmd(struct Scsi_Host *h, struct scsi_cmnd *cmd); extern int ata_sas_scsi_ioctl(struct ata_port *ap, struct scsi_device *dev, int cmd, void __user *arg); extern void ata_sas_port_destroy(struct ata_port *); -- cgit v1.2.3 From 1e7c7804884fc5751e3872f13498fd533325f8b2 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 16 Nov 2010 12:11:02 +0300 Subject: fbcmap: integer overflow bug There is an integer overflow in fb_set_user_cmap() because cmap->len * 2 can wrap. It's basically harmless. Your terminal will be messed up until you type reset. This patch does three things to fix the bug. First, it checks the return value of fb_copy_cmap() in fb_alloc_cmap(). That is enough to fix address the overflow. Second it checks for the integer overflow in fb_set_user_cmap(). Lastly I wanted to cap "cmap->len" in fb_set_user_cmap() much lower because it gets used to determine the size of allocation. Unfortunately no one knows what the limit should be. Instead what this patch does is makes the allocation happen with GFP_KERNEL instead of GFP_ATOMIC and lets the kmalloc() decide what values of cmap->len are reasonable. To do this, the patch introduces a function called fb_alloc_cmap_gfp() which is like fb_alloc_cmap() except that it takes a GFP flag. Signed-off-by: Dan Carpenter Signed-off-by: Paul Mundt --- include/linux/fb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 7fca3dc4e475..d1631d37e9e0 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -1122,6 +1122,7 @@ extern const struct fb_videomode *fb_find_best_display(const struct fb_monspecs /* drivers/video/fbcmap.c */ extern int fb_alloc_cmap(struct fb_cmap *cmap, int len, int transp); +extern int fb_alloc_cmap_gfp(struct fb_cmap *cmap, int len, int transp, gfp_t flags); extern void fb_dealloc_cmap(struct fb_cmap *cmap); extern int fb_copy_cmap(const struct fb_cmap *from, struct fb_cmap *to); extern int fb_cmap_to_user(const struct fb_cmap *from, struct fb_cmap_user *to); -- cgit v1.2.3 From 451a3c24b0135bce54542009b5fde43846c7cf67 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 17 Nov 2010 16:26:55 +0100 Subject: BKL: remove extraneous #include The big kernel lock has been removed from all these files at some point, leaving only the #include. Remove this too as a cleanup. Signed-off-by: Arnd Bergmann Signed-off-by: Linus Torvalds --- include/linux/hardirq.h | 1 - include/linux/reiserfs_fs.h | 1 - include/linux/tty.h | 1 - 3 files changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 41cb31f14ee3..8f3f467c57c6 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -3,7 +3,6 @@ #include #ifdef CONFIG_PREEMPT -#include #endif #include #include diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 5ca47e59b727..c21072adbfad 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -22,7 +22,6 @@ #include #include #include -#include #include #include #include diff --git a/include/linux/tty.h b/include/linux/tty.h index c7ea9bc8897c..032d79ff1d9d 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -13,7 +13,6 @@ #include #include #include -#include #include -- cgit v1.2.3 From 7957f0a857754c555e07f58a3fb83ac29501478c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 17 Nov 2010 14:58:36 -0800 Subject: Fix build failure due to hwirq.h needing smp_lock.h Arnd Bergmann did an automated scripting run to find left-over instances of , and had made it trigger it on the normal BKL use of lock_kernel and unlock_lernel (and apparently release_kernel_lock and reacquire_kernel_lock too, used by the scheduler). That resulted in commit 451a3c24b013 ("BKL: remove extraneous #include "). However, hardirq.h was the only remaining user of the old 'kernel_locked()' interface, and Arnd's script hadn't checked for that. So depending on your configuration and what header files had been included, you would get errors like "implicit declaration of function 'kernel_locked'" during the build. The right fix is not to just re-instate the smp_lock.h include - it is to just remove 'kernel_locked()' entirely, since the only use was this one special low-level detail. Just make hardirq.h do it directly. In fact this simplifies and clarifies the code, because some trivial analysis makes it clear that hardirq.h only ever used _one_ of the two definitions of kernel_locked(), so we can remove the other one entirely. Reported-by: Zimny Lech Reported-and-acked-by: Randy Dunlap Acked-by: Arnd Bergmann Signed-off-by: Linus Torvalds --- include/linux/hardirq.h | 2 +- include/linux/smp_lock.h | 3 --- 2 files changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 8f3f467c57c6..bea1612d8f5c 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -96,7 +96,7 @@ #define in_nmi() (preempt_count() & NMI_MASK) #if defined(CONFIG_PREEMPT) && defined(CONFIG_BKL) -# define PREEMPT_INATOMIC_BASE kernel_locked() +# define PREEMPT_INATOMIC_BASE (current->lock_depth >= 0) #else # define PREEMPT_INATOMIC_BASE 0 #endif diff --git a/include/linux/smp_lock.h b/include/linux/smp_lock.h index 291f721144c2..3a1988202731 100644 --- a/include/linux/smp_lock.h +++ b/include/linux/smp_lock.h @@ -4,8 +4,6 @@ #ifdef CONFIG_LOCK_KERNEL #include -#define kernel_locked() (current->lock_depth >= 0) - extern int __lockfunc __reacquire_kernel_lock(void); extern void __lockfunc __release_kernel_lock(void); @@ -58,7 +56,6 @@ static inline void cycle_kernel_lock(void) #define lock_kernel() #define unlock_kernel() #define cycle_kernel_lock() do { } while(0) -#define kernel_locked() 1 #endif /* CONFIG_BKL */ #define release_kernel_lock(task) do { } while(0) -- cgit v1.2.3 From 0a5b871ea4c6bfb2723ac2ffc7ef5c32452abb89 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 17 Nov 2010 18:36:25 -0800 Subject: hardirq.h: remove now-empty #ifdef/#endif pair Commit 451a3c24b013 ("BKL: remove extraneous #include ") removed the #include line that was the only thing that was surrounded by the #ifdef/#endif. So now that #ifdef is guarding nothing at all. Just remove it. Reported-by: Byeong-ryeol Kim Signed-off-by: Linus Torvalds --- include/linux/hardirq.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index bea1612d8f5c..714da7e5d10c 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -2,8 +2,6 @@ #define LINUX_HARDIRQ_H #include -#ifdef CONFIG_PREEMPT -#endif #include #include #include -- cgit v1.2.3 From ed1d77b18c9f4ff06d5b42c65041aa55a1447053 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 18 Nov 2010 10:56:29 -0800 Subject: hardirq.h: needs sched.h if using BKL This really isn't the right thing to do, and strictly speaking we should have the BKL depth count in the thread info right next to the preempt count. The two really do go together. However, since that would involve a patch to all architectures, and the BKL is finally going away, it's simply not worth the effort to do the RightThing(tm). Just re-instate the include that we used to get accidentally from the smp_lock.h one. This is all fallout from the same old "BKL: remove extraneous #include " commit. Reported-by: Ingo Molnar Tested-by: Randy Dunlap Cc: Arnd Bergmann Signed-off-by: Linus Torvalds --- include/linux/hardirq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 714da7e5d10c..32f9fd6619b4 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -94,6 +94,7 @@ #define in_nmi() (preempt_count() & NMI_MASK) #if defined(CONFIG_PREEMPT) && defined(CONFIG_BKL) +# include # define PREEMPT_INATOMIC_BASE (current->lock_depth >= 0) #else # define PREEMPT_INATOMIC_BASE 0 -- cgit v1.2.3 From ed919b0125b26dcc052e44836f66e7e1f5c49c7e Mon Sep 17 00:00:00 2001 From: Ohad Ben-Cohen Date: Fri, 19 Nov 2010 09:29:09 +0200 Subject: mmc: sdio: fix runtime PM anomalies by introducing MMC_CAP_POWER_OFF_CARD Some board/card/host configurations are not capable of powering off the card after boot. To support such configurations, and to allow smoother transition to runtime PM behavior, MMC_CAP_POWER_OFF_CARD is added, so hosts need to explicitly indicate whether it's OK to power off their cards after boot. SDIO core will enable runtime PM for a card only if that cap is set. As a result, the card will be powered down after boot, and will only be powered up again when a driver is loaded (and then it's up to the driver to decide whether power will be kept or not). This will prevent sdio_bus_probe() failures with setups that do not support powering off the card. Reported-and-tested-by: Daniel Drake Reported-and-tested-by: Arnd Hannemann Signed-off-by: Ohad Ben-Cohen 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 6d87f68ce4b6..30f6fad99a58 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -168,6 +168,7 @@ struct mmc_host { /* DDR mode at 1.8V */ #define MMC_CAP_1_2V_DDR (1 << 12) /* can support */ /* DDR mode at 1.2V */ +#define MMC_CAP_POWER_OFF_CARD (1 << 13) /* Can power off after boot */ mmc_pm_flag_t pm_caps; /* supported pm features */ -- cgit v1.2.3 From 93bb41f4f8b89ac8b4d0a734bc59634cb0a29a89 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Fri, 19 Nov 2010 21:18:35 -0500 Subject: fs: Do not dispatch FITRIM through separate super_operation There was concern that FITRIM ioctl is not common enough to be included in core vfs ioctl, as Christoph Hellwig pointed out there's no real point in dispatching this out to a separate vector instead of just through ->ioctl. So this commit removes ioctl_fstrim() from vfs ioctl and trim_fs from super_operation structure. Signed-off-by: Lukas Czerner Signed-off-by: "Theodore Ts'o" --- 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 334d68a17108..eedc00b7b1ee 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1612,7 +1612,6 @@ 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 (*trim_fs) (struct super_block *, struct fstrim_range *); }; /* -- cgit v1.2.3 From 07a8cdd2bb17a4da68136d963b8bc71959bd31a5 Mon Sep 17 00:00:00 2001 From: Anand Gadiyar Date: Thu, 18 Nov 2010 18:54:17 +0530 Subject: usb: musb: do not use dma for control transfers The Inventra DMA engine used with the MUSB controller in many SoCs cannot use DMA for control transfers on EP0, but can use DMA for all other transfers. The USB core maps urbs for DMA if hcd->self.uses_dma is true. (hcd->self.uses_dma is true for MUSB as well). Split the uses_dma flag into two - one that says if the controller needs to use PIO for control transfers, and another which says if the controller uses DMA (for all other transfers). Also, populate this flag for all MUSB by default. (Tested on OMAP3 and OMAP4 boards, with EHCI and MUSB HCDs simultaneously in use). Signed-off-by: Maulik Mankad Signed-off-by: Santosh Shilimkar Signed-off-by: Anand Gadiyar Cc: Oliver Neukum Cc: Alan Stern Cc: Praveena NADAHALLY Cc: Ajay Kumar Gupta Signed-off-by: Felipe Balbi --- include/linux/usb.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 24300d8a1bc1..a28eb2592577 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -313,6 +313,10 @@ struct usb_bus { int busnum; /* Bus number (in order of reg) */ const char *bus_name; /* stable id (PCI slot_name etc) */ u8 uses_dma; /* Does the host controller use DMA? */ + u8 uses_pio_for_control; /* + * Does the host controller use PIO + * for control transfers? + */ u8 otg_port; /* 0, or number of OTG/HNP port */ unsigned is_b_host:1; /* true during some HNP roleswitches */ unsigned b_hnp_enable:1; /* OTG: did A-Host enable HNP? */ -- cgit v1.2.3 From 90600732d8b2fbc422bc9c57bdc73513d909367f Mon Sep 17 00:00:00 2001 From: David Daney Date: Fri, 19 Nov 2010 11:58:53 +0000 Subject: phylib: Add support for Marvell 88E1149R devices. The 88E1149R is 10/100/1000 quad-gigabit Ethernet PHY. The .config_aneg function can be shared with 88E1118, but it needs its own .config_init. Signed-off-by: David Daney Cc: Cyril Chemparathy Cc: Arnaud Patard Cc: Benjamin Herrenschmidt Cc: Wolfram Sang Signed-off-by: David S. Miller --- include/linux/marvell_phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h index 1ff81b51b656..dd3c34ebca9a 100644 --- a/include/linux/marvell_phy.h +++ b/include/linux/marvell_phy.h @@ -11,6 +11,7 @@ #define MARVELL_PHY_ID_88E1118 0x01410e10 #define MARVELL_PHY_ID_88E1121R 0x01410cb0 #define MARVELL_PHY_ID_88E1145 0x01410cd0 +#define MARVELL_PHY_ID_88E1149R 0x01410e50 #define MARVELL_PHY_ID_88E1240 0x01410e30 #define MARVELL_PHY_ID_88E1318S 0x01410e90 -- cgit v1.2.3 From 0b26a0bf6ff398185546432420bb772bcfdf8d94 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 20 Nov 2010 14:26:44 -0500 Subject: NFS: Ensure we return the dirent->d_type when it is known Store the dirent->d_type in the struct nfs_cache_array_entry so that we can use it in getdents() calls. This fixes a regression with the new readdir code. 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 ba6cc8f223c9..80f07198a31a 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -483,6 +483,7 @@ struct nfs_entry { int eof; struct nfs_fh * fh; struct nfs_fattr * fattr; + unsigned char d_type; }; /* -- cgit v1.2.3 From 1d8638d4038eb8709edc80e37a0bbb77253d86e9 Mon Sep 17 00:00:00 2001 From: Daniel Klaffenbach Date: Fri, 19 Nov 2010 21:25:21 -0600 Subject: ssb: b43-pci-bridge: Add new vendor for BCM4318 Add new vendor for Broadcom 4318. Signed-off-by: Daniel Klaffenbach Signed-off-by: Larry Finger Cc: Stable Signed-off-by: John W. Linville --- 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 d278dd9cb765..f29c25ede70d 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2043,6 +2043,7 @@ #define PCI_DEVICE_ID_AFAVLAB_P030 0x2182 #define PCI_SUBDEVICE_ID_AFAVLAB_P061 0x2150 +#define PCI_VENDOR_ID_BCM_GVC 0x14a4 #define PCI_VENDOR_ID_BROADCOM 0x14e4 #define PCI_DEVICE_ID_TIGON3_5752 0x1600 #define PCI_DEVICE_ID_TIGON3_5752M 0x1601 -- cgit v1.2.3 From dfd62d1d84d83f9421792c78bcf72de9bc2bb603 Mon Sep 17 00:00:00 2001 From: Anders Kaseorg Date: Wed, 24 Nov 2010 15:21:10 -0600 Subject: module: Update prototype for ref_module (formerly use_module) Commit 9bea7f23952d5948f8e5dfdff4de09bb9981fb5f renamed use_module to ref_module (and changed its return value), but forgot to update this prototype in module.h. Signed-off-by: Anders Kaseorg Acked-by: WANG Cong Signed-off-by: Rusty Russell --- include/linux/module.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index b29e7458b966..7575bbbdf2a2 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -517,7 +517,7 @@ static inline void __module_get(struct module *module) #define symbol_put_addr(p) do { } while(0) #endif /* CONFIG_MODULE_UNLOAD */ -int use_module(struct module *a, struct module *b); +int ref_module(struct module *a, struct module *b); /* This is a #define so the string doesn't get put in every .o file */ #define module_name(mod) \ -- cgit v1.2.3 From 3a3a1af37f0405d15c0b64a6ce7f4878084442e0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Lo=C3=AFc=20Minier?= Date: Wed, 24 Nov 2010 12:56:53 -0800 Subject: include/linux/fs.h: fix userspace build MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit dpkg uses fiemap but didn't particularly need to include stdint.h so far. Since 367a51a33902 ("fs: Add FITRIM ioctl"), build of linux/fs.h failed in dpkg with: In file included from ../../src/filesdb.c:27:0: /usr/include/linux/fs.h:37:2: error: expected specifier-qualifier-list before 'uint64_t' Use exportable type __u64 to avoid the dependency on stdint.h. b31d42a5af18 ("Fix compile brekage with !CONFIG_BLOCK") fixed only the kernel build by including linux/types.h, but this also fixed "make headers_check", so don't revert it. Signed-off-by: Loïc Minier Tested-by: Arnd Bergmann Cc: Lukas Czerner Cc: Dmitry Monakhov Cc: Theodore Ts'o Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index eedc00b7b1ee..c9e06cc70dad 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -34,9 +34,9 @@ #define SEEK_MAX SEEK_END struct fstrim_range { - uint64_t start; - uint64_t len; - uint64_t minlen; + __u64 start; + __u64 len; + __u64 minlen; }; /* And dynamically-tunable limits and defaults: */ -- cgit v1.2.3 From 112bc2e120a94a511858918d6866a4978f9c500e Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 24 Nov 2010 12:56:58 -0800 Subject: memcg: fix false positive VM_BUG on non-SMP Fix this: kernel BUG at mm/memcontrol.c:2155! invalid opcode: 0000 [#1] last sysfs file: Pid: 18, comm: sh Not tainted 2.6.37-rc3 #3 /Bochs EIP: 0060:[] EFLAGS: 00000246 CPU: 0 EIP is at mem_cgroup_move_account+0xe2/0xf0 EAX: 00000004 EBX: c6f931d4 ECX: c681c300 EDX: c681c000 ESI: c681c300 EDI: ffffffea EBP: c681c000 ESP: c46f3e30 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 0068 Process sh (pid: 18, ti=c46f2000 task=c6826e60 task.ti=c46f2000) Stack: 00000155 c681c000 0805f000 c46ee180 c46f3e5c c7058820 c1074d37 00000000 08060000 c46db9a0 c46ec080 c7058820 0805f000 08060000 c46f3e98 c1074c50 c106c75e c46f3e98 c46ec080 08060000 0805ffff c46db9a0 c46f3e98 c46e0340 Call Trace: [] ? mem_cgroup_move_charge_pte_range+0xe7/0x130 [] ? mem_cgroup_move_charge_pte_range+0x0/0x130 [] ? walk_page_range+0xee/0x1d0 [] ? mem_cgroup_move_task+0x66/0x90 [] ? mem_cgroup_move_charge_pte_range+0x0/0x130 [] ? mem_cgroup_move_task+0x0/0x90 [] ? cgroup_attach_task+0x136/0x200 [] ? cgroup_tasks_write+0x48/0xc0 [] ? cgroup_file_write+0xde/0x220 [] ? do_page_fault+0x17d/0x3f0 [] ? alloc_fd+0x2d/0xd0 [] ? cgroup_file_write+0x0/0x220 [] ? vfs_write+0x92/0xc0 [] ? sys_write+0x41/0x70 [] ? syscall_call+0x7/0xb Code: 03 00 74 09 8b 44 24 04 e8 1c f1 ff ff 89 73 04 8d 86 b0 00 00 00 b9 01 00 00 00 89 da 31 ff e8 65 f5 ff ff e9 4d ff ff ff 0f 0b <0f> 0b 0f 0b 0f 0b 90 8d b4 26 00 00 00 00 83 ec 10 8b 0d f4 e3 EIP: [] mem_cgroup_move_account+0xe2/0xf0 SS:ESP 0068:c46f3e30 ---[ end trace 7daa1582159b6532 ]--- lock_page_cgroup and unlock_page_cgroup are implemented using bit_spinlock. bit_spinlock doesn't touch the bit if we are on non-SMP machine, so we can't use the bit to check whether the lock was taken. Let's introduce is_page_cgroup_locked based on bit_spin_is_locked instead of PageCgroupLocked to fix it. [akpm@linux-foundation.org: s/is_page_cgroup_locked/page_is_cgroup_locked/] Signed-off-by: Kirill A. Shutemov Reviewed-by: Johannes Weiner Acked-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_cgroup.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h index 5bb13b3db84d..b02195dfc1b0 100644 --- a/include/linux/page_cgroup.h +++ b/include/linux/page_cgroup.h @@ -59,8 +59,6 @@ static inline void ClearPageCgroup##uname(struct page_cgroup *pc) \ static inline int TestClearPageCgroup##uname(struct page_cgroup *pc) \ { return test_and_clear_bit(PCG_##lname, &pc->flags); } -TESTPCGFLAG(Locked, LOCK) - /* Cache flag is set only once (at allocation) */ TESTPCGFLAG(Cache, CACHE) CLEARPCGFLAG(Cache, CACHE) @@ -104,6 +102,11 @@ static inline void unlock_page_cgroup(struct page_cgroup *pc) bit_spin_unlock(PCG_LOCK, &pc->flags); } +static inline int page_is_cgroup_locked(struct page_cgroup *pc) +{ + return bit_spin_is_locked(PCG_LOCK, &pc->flags); +} + #else /* CONFIG_CGROUP_MEM_RES_CTLR */ struct page_cgroup; -- cgit v1.2.3 From 4917b284db8607e414c334317b7d15239854d39c Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 22 Nov 2010 12:48:34 -0800 Subject: dmar, x86: Use function stubs when CONFIG_INTR_REMAP is disabled The stubs for CONFIG_INTR_REMAP disabled need to be functions instead of values to eliminate build warnings. arch/x86/kernel/apic/apic.c: In function 'lapic_suspend': arch/x86/kernel/apic/apic.c:2060:3: warning: statement with no effect arch/x86/kernel/apic/apic.c: In function 'lapic_resume': arch/x86/kernel/apic/apic.c:2137:3: warning: statement with no effect Reported-and-Tested-by: Fabio Comolli Signed-off-by: Randy Dunlap Cc: Suresh Siddha Cc: Yinghai Lu Cc: David Woodhouse Cc: Jesse Barnes LKML-Reference: <20101122124834.74429004.randy.dunlap@oracle.com> Signed-off-by: Ingo Molnar --- include/linux/dmar.h | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmar.h b/include/linux/dmar.h index a7d9dc21391d..7b776d71d36d 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -175,10 +175,21 @@ static inline int set_msi_sid(struct irte *irte, struct pci_dev *dev) return 0; } -#define enable_intr_remapping(mode) (-1) -#define disable_intr_remapping() (0) -#define reenable_intr_remapping(mode) (0) #define intr_remapping_enabled (0) + +static inline int enable_intr_remapping(int eim) +{ + return -1; +} + +static inline void disable_intr_remapping(void) +{ +} + +static inline int reenable_intr_remapping(int eim) +{ + return 0; +} #endif /* Can't use the common MSI interrupt functions -- cgit v1.2.3 From dddd3379a619a4cb8247bfd3c94ca9ae3797aa2e Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 24 Nov 2010 10:05:55 +0100 Subject: perf: Fix inherit vs. context rotation bug It was found that sometimes children of tasks with inherited events had one extra event. Eventually it turned out to be due to the list rotation no being exclusive with the list iteration in the inheritance code. Cure this by temporarily disabling the rotation while we inherit the events. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra LKML-Reference: Cc: Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 40150f345982..142e3d6042c7 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -850,6 +850,7 @@ struct perf_event_context { int nr_active; int is_active; int nr_stat; + int rotate_disable; atomic_t refcount; struct task_struct *task; -- cgit v1.2.3 From ee6dcfa40a50fe12a3ae0fb4d2653c66c3ed6556 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 26 Nov 2010 13:49:04 +0100 Subject: perf: Fix the software context switch counter Stephane noticed that because the perf_sw_event() call is inside the perf_event_task_sched_out() call it won't get called unless we have a per-task counter. Reported-by: Stephane Eranian Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 29 +++++++++++++++-------------- 1 file changed, 15 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 142e3d6042c7..de2c41758e29 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -909,20 +909,6 @@ extern int perf_num_counters(void); extern const char *perf_pmu_name(void); extern void __perf_event_task_sched_in(struct task_struct *task); extern void __perf_event_task_sched_out(struct task_struct *task, struct task_struct *next); - -extern atomic_t perf_task_events; - -static inline void perf_event_task_sched_in(struct task_struct *task) -{ - COND_STMT(&perf_task_events, __perf_event_task_sched_in(task)); -} - -static inline -void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next) -{ - COND_STMT(&perf_task_events, __perf_event_task_sched_out(task, next)); -} - extern int perf_event_init_task(struct task_struct *child); extern void perf_event_exit_task(struct task_struct *child); extern void perf_event_free_task(struct task_struct *task); @@ -1031,6 +1017,21 @@ have_event: __perf_sw_event(event_id, nr, nmi, regs, addr); } +extern atomic_t perf_task_events; + +static inline void perf_event_task_sched_in(struct task_struct *task) +{ + COND_STMT(&perf_task_events, __perf_event_task_sched_in(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); + + COND_STMT(&perf_task_events, __perf_event_task_sched_out(task, next)); +} + extern void perf_event_mmap(struct vm_area_struct *vma); extern struct perf_guest_info_callbacks *perf_guest_cbs; extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); -- cgit v1.2.3 From c66fb347946ebdd5b10908866ecc9fa05ee2cf3d Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 28 Nov 2010 14:09:57 -0800 Subject: Export 'get_pipe_info()' to other users And in particular, use it in 'pipe_fcntl()'. The other pipe functions do not need to use the 'careful' version, since they are only ever called for things that are already known to be pipes. The normal read/write/ioctl functions are called through the file operations structures, so if a file isn't a pipe, they'd never get called. But pipe_fcntl() is special, and called directly from the generic fcntl code, and needs to use the same careful function that the splice code is using. Cc: Jens Axboe Cc: Andrew Morton Cc: Al Viro Cc: Dave Jones Signed-off-by: Linus Torvalds --- include/linux/pipe_fs_i.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 445796945ac9..3c5ac3147428 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -161,4 +161,16 @@ void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); /* for F_SETPIPE_SZ and F_GETPIPE_SZ */ long pipe_fcntl(struct file *, unsigned int, unsigned long arg); +/* + * After the inode slimming patch, i_pipe/i_bdev/i_cdev share the same + * location, so checking ->i_pipe is not enough to verify that this is a + * pipe. + */ +static inline struct pipe_inode_info *get_pipe_info(struct file *file) +{ + struct inode *i = file->f_path.dentry->d_inode; + + return S_ISFIFO(i->i_mode) ? i->i_pipe : NULL; +} + #endif -- cgit v1.2.3 From 72083646528d4887b920deb71b37e09bc7d227bb Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 28 Nov 2010 16:27:19 -0800 Subject: Un-inline get_pipe_info() helper function This avoids some include-file hell, and the function isn't really important enough to be inlined anyway. Reported-by: Ingo Molnar Signed-off-by: Linus Torvalds --- include/linux/pipe_fs_i.h | 13 +------------ 1 file changed, 1 insertion(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 3c5ac3147428..bb27d7ec2fb9 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -160,17 +160,6 @@ void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); /* for F_SETPIPE_SZ and F_GETPIPE_SZ */ long pipe_fcntl(struct file *, unsigned int, unsigned long arg); - -/* - * After the inode slimming patch, i_pipe/i_bdev/i_cdev share the same - * location, so checking ->i_pipe is not enough to verify that this is a - * pipe. - */ -static inline struct pipe_inode_info *get_pipe_info(struct file *file) -{ - struct inode *i = file->f_path.dentry->d_inode; - - return S_ISFIFO(i->i_mode) ? i->i_pipe : NULL; -} +struct pipe_inode_info *get_pipe_info(struct file *file); #endif -- cgit v1.2.3 From acfa747baf73922021a047f2d87a2d866f5dbab5 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Mon, 29 Nov 2010 10:16:54 +0100 Subject: TTY: open/hangup race fixup Like in the "TTY: don't allow reopen when ldisc is changing" patch, this one fixes a TTY WARNING as described in the option 1) there: 1) __tty_hangup from tty_ldisc_hangup to tty_ldisc_enable. During this section tty_lock is held. However tty_lock is temporarily dropped in the middle of the function by tty_ldisc_hangup. The fix is to introduce a new flag which we set during the unlocked window and check it in tty_reopen too. The flag is TTY_HUPPING and is cleared after TTY_HUPPED is set. While at it, remove duplicate TTY_HUPPED set_bit. The one after calling ops->hangup seems to be more correct. But anyway, we hold tty_lock, so there should be no difference. Also document the function it does that kind of crap. Nicely reproducible with two forked children: static void do_work(const char *tty) { if (signal(SIGHUP, SIG_IGN) == SIG_ERR) exit(1); setsid(); while (1) { int fd = open(tty, O_RDWR|O_NOCTTY); if (fd < 0) continue; if (ioctl(fd, TIOCSCTTY)) continue; if (vhangup()) continue; close(fd); } exit(0); } Signed-off-by: Jiri Slaby Reported-by: Reported-by: Kyle McMartin Cc: Alan Cox Cc: stable Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index c7ea9bc8897c..021bfd2f0860 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -367,6 +367,7 @@ struct tty_file_private { #define TTY_HUPPED 18 /* Post driver->hangup() */ #define TTY_FLUSHING 19 /* Flushing to ldisc in progress */ #define TTY_FLUSHPENDING 20 /* Queued buffer flush pending */ +#define TTY_HUPPING 21 /* ->hangup() in progress */ #define TTY_WRITE_FLUSH(tty) tty_write_flush((tty)) -- cgit v1.2.3 From 3c77f845722158206a7209c45ccddc264d19319c Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 30 Nov 2010 20:55:34 +0100 Subject: exec: make argv/envp memory visible to oom-killer Brad Spengler published a local memory-allocation DoS that evades the OOM-killer (though not the virtual memory RLIMIT): http://www.grsecurity.net/~spender/64bit_dos.c execve()->copy_strings() can allocate a lot of memory, but this is not visible to oom-killer, nobody can see the nascent bprm->mm and take it into account. With this patch get_arg_page() increments current's MM_ANONPAGES counter every time we allocate the new page for argv/envp. When do_execve() succeds or fails, we change this counter back. Technically this is not 100% correct, we can't know if the new page is swapped out and turn MM_ANONPAGES into MM_SWAPENTS, but I don't think this really matters and everything becomes correct once exec changes ->mm or fails. Reported-by: Brad Spengler Reviewed-and-discussed-by: KOSAKI Motohiro Signed-off-by: Oleg Nesterov Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- 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 a065612fc928..7c87796d20da 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -29,6 +29,7 @@ struct linux_binprm{ char buf[BINPRM_BUF_SIZE]; #ifdef CONFIG_MMU struct vm_area_struct *vma; + unsigned long vma_pages; #else # define MAX_ARG_PAGES 32 struct page *page[MAX_ARG_PAGES]; -- cgit v1.2.3 From 114279be2120a916e8a04feeb2ac976a10016f2f Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 30 Nov 2010 20:56:02 +0100 Subject: exec: copy-and-paste the fixes into compat_do_execve() paths Note: this patch targets 2.6.37 and tries to be as simple as possible. That is why it adds more copy-and-paste horror into fs/compat.c and uglifies fs/exec.c, this will be cleanuped later. compat_copy_strings() plays with bprm->vma/mm directly and thus has two problems: it lacks the RLIMIT_STACK check and argv/envp memory is not visible to oom killer. Export acct_arg_size() and get_arg_page(), change compat_copy_strings() to use get_arg_page(), change compat_do_execve() to do acct_arg_size(0) as do_execve() does. Add the fatal_signal_pending/cond_resched checks into compat_count() and compat_copy_strings(), this matches the code in fs/exec.c and certainly makes sense. Signed-off-by: Oleg Nesterov Cc: KOSAKI Motohiro Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- include/linux/binfmts.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 7c87796d20da..64a7114a9394 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -60,6 +60,10 @@ struct linux_binprm{ unsigned long loader, exec; }; +extern void acct_arg_size(struct linux_binprm *bprm, unsigned long pages); +extern struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, + int write); + #define BINPRM_FLAGS_ENFORCE_NONDUMP_BIT 0 #define BINPRM_FLAGS_ENFORCE_NONDUMP (1 << BINPRM_FLAGS_ENFORCE_NONDUMP_BIT) -- cgit v1.2.3 From 64141da587241301ce8638cc945f8b67853156ec Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Thu, 2 Dec 2010 14:31:18 -0800 Subject: vmalloc: eagerly clear ptes on vunmap On stock 2.6.37-rc4, running: # mount lilith:/export /mnt/lilith # find /mnt/lilith/ -type f -print0 | xargs -0 file crashes the machine fairly quickly under Xen. Often it results in oops messages, but the couple of times I tried just now, it just hung quietly and made Xen print some rude messages: (XEN) mm.c:2389:d80 Bad type (saw 7400000000000001 != exp 3000000000000000) for mfn 1d7058 (pfn 18fa7) (XEN) mm.c:964:d80 Attempt to create linear p.t. with write perms (XEN) mm.c:2389:d80 Bad type (saw 7400000000000010 != exp 1000000000000000) for mfn 1d2e04 (pfn 1d1fb) (XEN) mm.c:2965:d80 Error while pinning mfn 1d2e04 Which means the domain tried to map a pagetable page RW, which would allow it to map arbitrary memory, so Xen stopped it. This is because vm_unmap_ram() left some pages mapped in the vmalloc area after NFS had finished with them, and those pages got recycled as pagetable pages while still having these RW aliases. Removing those mappings immediately removes the Xen-visible aliases, and so it has no problem with those pages being reused as pagetable pages. Deferring the TLB flush doesn't upset Xen because it can flush the TLB itself as needed to maintain its invariants. When unmapping a region in the vmalloc space, clear the ptes immediately. There's no point in deferring this because there's no amortization benefit. The TLBs are left dirty, and they are flushed lazily to amortize the cost of the IPIs. This specific motivation for this patch is an oops-causing regression since 2.6.36 when using NFS under Xen, triggered by the NFS client's use of vm_map_ram() introduced in 56e4ebf877b60 ("NFS: readdir with vmapped pages") . XFS also uses vm_map_ram() and could cause similar problems. Signed-off-by: Jeremy Fitzhardinge Cc: Nick Piggin Cc: Bryan Schumaker Cc: Trond Myklebust Cc: Alex Elder Cc: Dave Chinner Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index a03dcf62ca9d..44b54f619ac6 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -7,8 +7,6 @@ struct vm_area_struct; /* vma defining user mapping in mm_types.h */ -extern bool vmap_lazy_unmap; - /* bits in flags of vmalloc's vm_struct below */ #define VM_IOREMAP 0x00000001 /* ioremap() and friends */ #define VM_ALLOC 0x00000002 /* vmalloc() */ -- cgit v1.2.3 From 20d6c96b5f1cad5c5da4641945ec17a1d9a1afc8 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Thu, 2 Dec 2010 14:31:19 -0800 Subject: mem-hotplug: introduce {un}lock_memory_hotplug() Presently hwpoison is using lock_system_sleep() to prevent a race with memory hotplug. However lock_system_sleep() is a no-op if CONFIG_HIBERNATION=n. Therefore we need a new lock. Signed-off-by: KOSAKI Motohiro Cc: Andi Kleen Cc: Kamezawa Hiroyuki Suggested-by: Hugh Dickins Acked-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 4307231bd22f..31c237a00c48 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -161,6 +161,9 @@ extern void register_page_bootmem_info_node(struct pglist_data *pgdat); extern void put_page_bootmem(struct page *page); #endif +void lock_memory_hotplug(void); +void unlock_memory_hotplug(void); + #else /* ! CONFIG_MEMORY_HOTPLUG */ /* * Stub functions for when hotplug is off @@ -192,6 +195,9 @@ static inline void register_page_bootmem_info_node(struct pglist_data *pgdat) { } +static inline void lock_memory_hotplug(void) {} +static inline void unlock_memory_hotplug(void) {} + #endif /* ! CONFIG_MEMORY_HOTPLUG */ #ifdef CONFIG_MEMORY_HOTREMOVE -- cgit v1.2.3 From c9e664f1fdf34aa8cede047b206deaa8f1945af0 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 3 Dec 2010 22:57:45 +0100 Subject: PM / Hibernate: Fix memory corruption related to swap There is a problem that swap pages allocated before the creation of a hibernation image can be released and used for storing the contents of different memory pages while the image is being saved. Since the kernel stored in the image doesn't know of that, it causes memory corruption to occur after resume from hibernation, especially on systems with relatively small RAM that need to swap often. This issue can be addressed by keeping the GFP_IOFS bits clear in gfp_allowed_mask during the entire hibernation, including the saving of the image, until the system is finally turned off or the hibernation is aborted. Unfortunately, for this purpose it's necessary to rework the way in which the hibernate and suspend code manipulates gfp_allowed_mask. This change is based on an earlier patch from Hugh Dickins. Signed-off-by: Rafael J. Wysocki Reported-by: Ondrej Zary Acked-by: Hugh Dickins Reviewed-by: KAMEZAWA Hiroyuki Cc: stable@kernel.org --- include/linux/gfp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index e8713d55360a..f54adfcbec9c 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -360,7 +360,7 @@ void drain_local_pages(void *dummy); extern gfp_t gfp_allowed_mask; -extern void set_gfp_allowed_mask(gfp_t mask); -extern gfp_t clear_gfp_allowed_mask(gfp_t mask); +extern void pm_restrict_gfp_mask(void); +extern void pm_restore_gfp_mask(void); #endif /* __LINUX_GFP_H */ -- cgit v1.2.3