From b4c6a028774bcf3f20ed1e66c27a05aa51a8cf55 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Fri, 19 Dec 2014 17:54:14 -0700 Subject: blk-mq: Export freeze/unfreeze functions Let drivers prevent entering a queue that isn't available. Signed-off-by: Keith Busch Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 8aded9ab2e4e..3b43f509432c 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -212,6 +212,8 @@ void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async); void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); void blk_mq_tag_busy_iter(struct blk_mq_hw_ctx *hctx, busy_iter_fn *fn, void *priv); +void blk_mq_unfreeze_queue(struct request_queue *q); +void blk_mq_freeze_queue_start(struct request_queue *q); /* * Driver command data is immediately after the request. So subtract request -- cgit v1.2.3 From 0bc09f9cdc589e0b54724096138996a00b19babb Mon Sep 17 00:00:00 2001 From: Vignesh R Date: Tue, 16 Dec 2014 14:52:50 +0530 Subject: phy: phy-ti-pipe3: fix inconsistent enumeration of PCIe gen2 cards Prior to DRA74x silicon rev 1.1, pcie_pcs register bits 8-15 and bits 16-23 were used to configure RC delay count for phy1 and phy2 respectively. phyid was used as index to distinguish the phys and to configure the delay values appropriately. As of DRA74x silicon rev 1.1, pcie_pcs register definition has changed. Bits 16-23 are used to configure delay values for *both* phy1 and phy2. Hence phyid is no longer required. So, drop id field from ti_pipe3 structure and its subsequent references for configuring pcie_pcs register. Also, pcie_pcs register now needs to be configured with delay value of 0x96 at bit positions 16-23. See register description of CTRL_CORE_PCIE_PCS in ARM572x TRM, SPRUHZ6, October 2014, section 18.5.2.2, table 18-1804. This is needed to ensure Gen2 cards are enumerated consistently. DRA72x silicon behaves same way as DRA74x rev 1.1 as far as this functionality is considered. Test results on DRA74x and DRA72x EVMs: Before patch ------------ DRA74x ES 1.0: Gen1 cards work, Gen2 cards do not work (expected result due to silicon errata) DRA74x ES 1.1: Gen1 cards work, Gen2 cards do not work sometimes due to incorrect programming of register DRA72x: Gen1 cards work, Gen2 cards do not work sometimes due to incorrect programming of register After patch ----------- DRA74x ES 1.0: Gen1 cards work, Gen2 cards do not work (expected result due to silicon errata) DRA74x ES 1.1: Gen1 cards work, Gen2 cards work consistently. DRA72x: Gen1 and Gen2 cards enumerate consistently. Signed-off-by: Vignesh R Signed-off-by: Kishon Vijay Abraham I --- include/linux/phy/omap_control_phy.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy/omap_control_phy.h b/include/linux/phy/omap_control_phy.h index e9e6cfbfbb58..eb7d4a135a9e 100644 --- a/include/linux/phy/omap_control_phy.h +++ b/include/linux/phy/omap_control_phy.h @@ -66,7 +66,7 @@ enum omap_control_usb_mode { #define OMAP_CTRL_PIPE3_PHY_TX_RX_POWEROFF 0x0 #define OMAP_CTRL_PCIE_PCS_MASK 0xff -#define OMAP_CTRL_PCIE_PCS_DELAY_COUNT_SHIFT 0x8 +#define OMAP_CTRL_PCIE_PCS_DELAY_COUNT_SHIFT 16 #define OMAP_CTRL_USB2_PHY_PD BIT(28) @@ -79,7 +79,7 @@ enum omap_control_usb_mode { void omap_control_phy_power(struct device *dev, int on); void omap_control_usb_set_mode(struct device *dev, enum omap_control_usb_mode mode); -void omap_control_pcie_pcs(struct device *dev, u8 id, u8 delay); +void omap_control_pcie_pcs(struct device *dev, u8 delay); #else static inline void omap_control_phy_power(struct device *dev, int on) @@ -91,7 +91,7 @@ static inline void omap_control_usb_set_mode(struct device *dev, { } -static inline void omap_control_pcie_pcs(struct device *dev, u8 id, u8 delay) +static inline void omap_control_pcie_pcs(struct device *dev, u8 delay) { } #endif -- cgit v1.2.3 From ceb3a16c070c403f5f9ca46b46cf2bb79ea11750 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 3 Jan 2015 15:16:04 -0500 Subject: NFSv4: Cache the NFSv4/v4.1 client owner_id in the struct nfs_client Ensure that we cache the NFSv4/v4.1 client owner_id so that we can verify it when we're doing trunking detection. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 1e37fbb78f7a..ddea982355f3 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -74,6 +74,9 @@ struct nfs_client { /* idmapper */ struct idmap * cl_idmap; + /* Client owner identifier */ + const char * cl_owner_id; + /* Our own IP address, as a null-terminated string. * This is used to generate the mv0 callback address. */ -- cgit v1.2.3 From 17ded320706c6316376059cfbe9dccab32c62b42 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 7 Jan 2015 10:44:04 -0700 Subject: blk-mq: get rid of ->cmd_size in the hardware queue We store it in the tag set, we don't need it in the hardware queue. While removing cmd_size, place ->queue_num further down to avoid a hole on 64-bit archs. It's not used in any fast paths, so we can safely move it. Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 3b43f509432c..d0de259e92b2 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -34,7 +34,6 @@ struct blk_mq_hw_ctx { unsigned long flags; /* BLK_MQ_F_* flags */ struct request_queue *queue; - unsigned int queue_num; struct blk_flush_queue *fq; void *driver_data; @@ -54,7 +53,7 @@ struct blk_mq_hw_ctx { unsigned long dispatched[BLK_MQ_MAX_DISPATCH_ORDER]; unsigned int numa_node; - unsigned int cmd_size; /* per-request extra data */ + unsigned int queue_num; atomic_t nr_active; -- cgit v1.2.3 From 6ada1fc0e1c4775de0e043e1bd3ae9d065491aa5 Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Wed, 3 Dec 2014 19:22:48 -0500 Subject: time: settimeofday: Validate the values of tv from user An unvalidated user input is multiplied by a constant, which can result in an undefined behaviour for large values. While this is validated later, we should avoid triggering undefined behaviour. Cc: Thomas Gleixner Cc: Ingo Molnar Cc: stable Signed-off-by: Sasha Levin [jstultz: include trivial milisecond->microsecond correction noticed by Andy] Signed-off-by: John Stultz --- include/linux/time.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/time.h b/include/linux/time.h index 8c42cf8d2444..5989b0ead1ec 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -99,6 +99,19 @@ static inline bool timespec_valid_strict(const struct timespec *ts) return true; } +static inline bool timeval_valid(const struct timeval *tv) +{ + /* Dates before 1970 are bogus */ + if (tv->tv_sec < 0) + return false; + + /* Can't have more microseconds then a second */ + if (tv->tv_usec < 0 || tv->tv_usec >= USEC_PER_SEC) + return false; + + return true; +} + extern struct timespec timespec_trunc(struct timespec t, unsigned gran); #define CURRENT_TIME (current_kernel_time()) -- cgit v1.2.3 From e61f7d1c3c07a7e51036b0796749edb00deff845 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Thu, 8 Jan 2015 10:34:27 -0500 Subject: libata: Whitelist SSDs that are known to properly return zeroes after TRIM As defined, the DRAT (Deterministic Read After Trim) and RZAT (Return Zero After Trim) flags in the ATA Command Set are unreliable in the sense that they only define what happens if the device successfully executed the DSM TRIM command. TRIM is only advisory, however, and the device is free to silently ignore all or parts of the request. In practice this renders the DRAT and RZAT flags completely useless and because the results are unpredictable we decided to disable discard in MD for 3.18 to avoid the risk of data corruption. Hardware vendors in the real world obviously need better guarantees than what the standards bodies provide. Unfortuntely those guarantees are encoded in product requirements documents rather than somewhere we can key off of them programatically. So we are compelled to disabling discard_zeroes_data for all devices unless we explicitly have data to support whitelisting them. This patch whitelists SSDs from a few of the main vendors. None of the whitelists are based on written guarantees. They are purely based on empirical evidence collected from internal and external users that have tested or qualified these drives in RAID deployments. The whitelist is only meant as a starting point and is by no means comprehensive: - All intel SSD models except for 510 - Micron M5?0/M600 - Samsung SSDs - Seagate SSDs Signed-off-by: Martin K. Petersen Reviewed-by: Christoph Hellwig Signed-off-by: Tejun Heo --- include/linux/libata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 2d182413b1db..f2b440e44fd7 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -422,6 +422,7 @@ enum { ATA_HORKAGE_NO_NCQ_TRIM = (1 << 19), /* don't use queued TRIM */ ATA_HORKAGE_NOLPM = (1 << 20), /* don't use LPM */ ATA_HORKAGE_WD_BROKEN_LPM = (1 << 21), /* some WDs have broken LPM */ + ATA_HORKAGE_ZERO_AFTER_TRIM = (1 << 22),/* guarantees zero after trim */ /* DMA mask for user DMA control: User visible values; DO NOT renumber */ -- cgit v1.2.3 From 973c01919bce7e3559b62a856b29211ec5ac325c Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 7 Jan 2015 18:55:43 -0700 Subject: blk-mq: Export if requests were started Drivers can iterate over all allocated request tags, but their callback needs a way to know if the driver started the request in the first place. Signed-off-by: Keith Busch Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index d0de259e92b2..addf8a19d806 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -194,6 +194,7 @@ static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag) struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *, const int ctx_index); struct blk_mq_hw_ctx *blk_mq_alloc_single_hw_queue(struct blk_mq_tag_set *, unsigned int, int); +int blk_mq_request_started(struct request *rq); void blk_mq_start_request(struct request *rq); void blk_mq_end_request(struct request *rq, int error); void __blk_mq_end_request(struct request *rq, int error); -- cgit v1.2.3 From c68ed59f534c318716c6189050af3c5ea03b8071 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 7 Jan 2015 18:55:44 -0700 Subject: blk-mq: Let drivers cancel requeue_work Kicking requeued requests will start h/w queues in a work_queue, which may alter the driver's requested state to temporarily stop them. This patch exports a method to cancel the q->requeue_work so a driver can be assured stopped h/w queues won't be started up before it is ready. Signed-off-by: Keith Busch Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index addf8a19d806..18684e0bdb8a 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -201,6 +201,7 @@ void __blk_mq_end_request(struct request *rq, int error); void blk_mq_requeue_request(struct request *rq); void blk_mq_add_to_requeue_list(struct request *rq, bool at_head); +void blk_mq_cancel_requeue_work(struct request_queue *q); void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_complete_request(struct request *rq); -- cgit v1.2.3 From 1885b24d23716e09b9c952822b05fd7f68099cdb Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 7 Jan 2015 18:55:45 -0700 Subject: blk-mq: Add helper to abort requeued requests Adds a helper function a driver can use to abort requeued requests in case any are pending when h/w queues are being removed. Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 18684e0bdb8a..5735e7130d63 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -203,6 +203,7 @@ void blk_mq_requeue_request(struct request *rq); void blk_mq_add_to_requeue_list(struct request *rq, bool at_head); void blk_mq_cancel_requeue_work(struct request_queue *q); void blk_mq_kick_requeue_list(struct request_queue *q); +void blk_mq_abort_requeue_list(struct request_queue *q); void blk_mq_complete_request(struct request *rq); void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx); -- cgit v1.2.3 From 5b3f25fc343690cafd3e27431a69a7bdaf9df001 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 7 Jan 2015 18:55:46 -0700 Subject: blk-mq: Allow requests to never expire Some types of requests may be started that are not gauranteed to ever complete. This adds a request flag that a driver can use so mark the request as such. Signed-off-by: Keith Busch Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 445d59231bc4..c294e3e25e37 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -190,6 +190,7 @@ enum rq_flag_bits { __REQ_PM, /* runtime pm request */ __REQ_HASHED, /* on IO scheduler merge hash */ __REQ_MQ_INFLIGHT, /* track inflight for MQ */ + __REQ_NO_TIMEOUT, /* requests may never expire */ __REQ_NR_BITS, /* stops here */ }; @@ -243,5 +244,6 @@ enum rq_flag_bits { #define REQ_PM (1ULL << __REQ_PM) #define REQ_HASHED (1ULL << __REQ_HASHED) #define REQ_MQ_INFLIGHT (1ULL << __REQ_MQ_INFLIGHT) +#define REQ_NO_TIMEOUT (1ULL << __REQ_NO_TIMEOUT) #endif /* __LINUX_BLK_TYPES_H */ -- cgit v1.2.3 From ad26aa6c60974acf3228ed0ade97ba5793093dbe Mon Sep 17 00:00:00 2001 From: Jonghwa Lee Date: Thu, 8 Jan 2015 11:04:07 +0900 Subject: regulator: s2mps11: Fix wrong calculation of register offset This patch adds missing registers('BUCK7_SW' & 'LDO29_CTRL'). Since BUCK7 has 1 more register (BUCK7_SW) than others, register offset should be added one more for which has bigger address than BUCK7 registers. Fixes: 76b9840b24ae04(regulator: s2mps11: Add support S2MPS13 regulator device) Signed-off-by: Jonghwa Lee Signed-off-by: Chanwoo Choi Signed-off-by: Mark Brown Cc: --- include/linux/mfd/samsung/s2mps13.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/samsung/s2mps13.h b/include/linux/mfd/samsung/s2mps13.h index ce5dda8958fe..b1fd675fa36f 100644 --- a/include/linux/mfd/samsung/s2mps13.h +++ b/include/linux/mfd/samsung/s2mps13.h @@ -59,6 +59,7 @@ enum s2mps13_reg { S2MPS13_REG_B6CTRL, S2MPS13_REG_B6OUT, S2MPS13_REG_B7CTRL, + S2MPS13_REG_B7SW, S2MPS13_REG_B7OUT, S2MPS13_REG_B8CTRL, S2MPS13_REG_B8OUT, @@ -102,6 +103,7 @@ enum s2mps13_reg { S2MPS13_REG_L26CTRL, S2MPS13_REG_L27CTRL, S2MPS13_REG_L28CTRL, + S2MPS13_REG_L29CTRL, S2MPS13_REG_L30CTRL, S2MPS13_REG_L31CTRL, S2MPS13_REG_L32CTRL, -- cgit v1.2.3 From 5d632cb70f454ac11158de40d563b08b0cd6e084 Mon Sep 17 00:00:00 2001 From: B Viswanath Date: Mon, 12 Jan 2015 14:46:25 +0530 Subject: net: Corrected the comment describing the ndo operations to reflect the actual prototype for couple of operations Corrected the comment describing the ndo operations to reflect the actual prototype for couple of operations Signed-off-by: B Viswanath 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 679e6e90aa4c..7f794db8e486 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -852,11 +852,11 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * 3. Update dev->stats asynchronously and atomically, and define * neither operation. * - * int (*ndo_vlan_rx_add_vid)(struct net_device *dev, __be16 proto, u16t vid); + * int (*ndo_vlan_rx_add_vid)(struct net_device *dev, __be16 proto, u16 vid); * If device support VLAN filtering this function is called when a * VLAN id is registered. * - * int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, unsigned short vid); + * int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, __be16 proto, u16 vid); * If device support VLAN filtering this function is called when a * VLAN id is unregistered. * -- cgit v1.2.3 From 4ccce02eb31b847dd6bf8486f037ba1db39403c5 Mon Sep 17 00:00:00 2001 From: Benjamin Poirier Date: Wed, 14 Jan 2015 16:52:35 +0900 Subject: netdevice: Add missing parentheses in macro For example, one could conceivably call for_each_netdev_in_bond_rcu(condition ? bond1 : bond2, slave) and get an unexpected result. Signed-off-by: Benjamin Poirier 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 7f794db8e486..52fd8e8694cf 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2085,7 +2085,7 @@ extern rwlock_t dev_base_lock; /* Device list lock */ list_for_each_entry_continue_rcu(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_in_bond_rcu(bond, slave) \ for_each_netdev_rcu(&init_net, slave) \ - if (netdev_master_upper_dev_get_rcu(slave) == bond) + if (netdev_master_upper_dev_get_rcu(slave) == (bond)) #define net_device_entry(lh) list_entry(lh, struct net_device, dev_list) static inline struct net_device *next_net_device(struct net_device *dev) -- cgit v1.2.3 From f331a859e0ee5a898c1f47596eddad4c4f02d657 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Thu, 15 Jan 2015 18:16:04 -0600 Subject: PCI: Add flag for devices where we can't use bus reset Enable a mechanism for devices to quirk that they do not behave when doing a PCI bus reset. We require a modest level of spec compliant behavior in order to do a reset, for instance the device should come out of reset without throwing errors and PCI config space should be accessible after reset. This is too much to ask for some devices. Link: http://lkml.kernel.org/r/20140923210318.498dacbd@dualc.maya.org Signed-off-by: Alex Williamson Signed-off-by: Bjorn Helgaas CC: stable@vger.kernel.org # v3.14+ --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 360a966a97a5..44627f1df4ca 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -175,6 +175,8 @@ enum pci_dev_flags { PCI_DEV_FLAGS_DMA_ALIAS_DEVFN = (__force pci_dev_flags_t) (1 << 4), /* Use a PCIe-to-PCI bridge alias even if !pci_is_pcie */ PCI_DEV_FLAG_PCIE_BRIDGE_ALIAS = (__force pci_dev_flags_t) (1 << 5), + /* Do not use bus resets for device */ + PCI_DEV_FLAGS_NO_BUS_RESET = (__force pci_dev_flags_t) (1 << 6), }; enum pci_irq_reroute_variant { -- cgit v1.2.3 From 8505e729a2f6eb0803ff943a15f133dd10afff3a Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 15 Jan 2015 16:21:49 -0600 Subject: PCI: Add pci_claim_bridge_resource() to clip window if necessary Add pci_claim_bridge_resource() to claim a PCI-PCI bridge window. This is like regular pci_claim_resource(), except that if we fail to claim the window, we check to see if we can reduce the size of the window and try again. This is for scenarios like this: pci_bus 0000:00: root bus resource [mem 0xc0000000-0xffffffff] pci 0000:00:01.0: bridge window [mem 0xbdf00000-0xddefffff 64bit pref] pci 0000:01:00.0: reg 0x10: [mem 0xc0000000-0xcfffffff pref] The 00:01.0 window is illegal: it starts before the host bridge window, so we have to assume the [0xbdf00000-0xbfffffff] region is inaccessible. We can make it legal by clipping it to [mem 0xc0000000-0xddefffff 64bit pref]. Previously we discarded the 00:01.0 window and tried to reassign that part of the hierarchy from scratch. That is a problem because Linux doesn't always assign things optimally. For example, in this case, BIOS put the 01:00.0 device in a prefetchable window below 4GB, but after 5b28541552ef, Linux puts the prefetchable window above 4GB where the 32-bit 01:00.0 device can't use it. Clipping the 00:01.0 window is less intrusive than completely reassigning things and is sufficient to let us use most of the BIOS configuration. Of course, it's possible that devices below 00:01.0 will no longer fit. If that's the case, we'll have to reassign things. But that's a separate problem. [bhelgaas: changelog, split into separate patch] Link: https://bugzilla.kernel.org/show_bug.cgi?id=85491 Reported-by: Marek Kordik Fixes: 5b28541552ef ("PCI: Restrict 64-bit prefetchable bridge windows to 64-bit resources") Signed-off-by: Yinghai Lu Signed-off-by: Bjorn Helgaas CC: stable@vger.kernel.org # v3.16+ --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 44627f1df4ca..9603094ed59b 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1067,6 +1067,7 @@ resource_size_t pcibios_retrieve_fw_addr(struct pci_dev *dev, int idx); void pci_bus_assign_resources(const struct pci_bus *bus); void pci_bus_size_bridges(struct pci_bus *bus); int pci_claim_resource(struct pci_dev *, int); +int pci_claim_bridge_resource(struct pci_dev *bridge, int i); void pci_assign_unassigned_resources(void); void pci_assign_unassigned_bridge_resources(struct pci_dev *bridge); void pci_assign_unassigned_bus_resources(struct pci_bus *bus); -- cgit v1.2.3 From ee1c244219fd652964710a6cc3e4f922e86aa492 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 16 Jan 2015 11:37:14 +0100 Subject: genetlink: synchronize socket closing and family removal In addition to the problem Jeff Layton reported, I looked at the code and reproduced the same warning by subscribing and removing the genl family with a socket still open. This is a fairly tricky race which originates in the fact that generic netlink allows the family to go away while sockets are still open - unlike regular netlink which has a module refcount for every open socket so in general this cannot be triggered. Trying to resolve this issue by the obvious locking isn't possible as it will result in deadlocks between unregistration and group unbind notification (which incidentally lockdep doesn't find due to the home grown locking in the netlink table.) To really resolve this, introduce a "closing socket" reference counter (for generic netlink only, as it's the only affected family) in the core netlink code and use that in generic netlink to wait for all the sockets that are being closed at the same time as a generic netlink family is removed. This fixes the race that when a socket is closed, it will should call the unbind, but if the family is removed at the same time the unbind will not find it, leading to the warning. The real problem though is that in this case the unbind could actually find a new family that is registered to have a multicast group with the same ID, and call its mcast_unbind() leading to confusing. Also remove the warning since it would still trigger, but is now no longer a problem. This also moves the code in af_netlink.c to before unreferencing the module to avoid having the same problem in the normal non-genl case. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/linux/genetlink.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/genetlink.h b/include/linux/genetlink.h index 55b685719d52..09460d6d6682 100644 --- a/include/linux/genetlink.h +++ b/include/linux/genetlink.h @@ -11,6 +11,10 @@ extern void genl_unlock(void); extern int lockdep_genl_is_held(void); #endif +/* for synchronisation between af_netlink and genetlink */ +extern atomic_t genl_sk_destructing_cnt; +extern wait_queue_head_t genl_sk_destructing_waitq; + /** * rcu_dereference_genl - rcu_dereference with debug checking * @p: The pointer to read, prior to dereferencing -- cgit v1.2.3 From 72dd299d5039a336493993dcc63413cf31d0e662 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 16 Jan 2015 15:13:02 -0800 Subject: libata: allow sata_sil24 to opt-out of tag ordered submission Ronny reports: https://bugzilla.kernel.org/show_bug.cgi?id=87101 "Since commit 8a4aeec8d "libata/ahci: accommodate tag ordered controllers" the access to the harddisk on the first SATA-port is failing on its first access. The access to the harddisk on the second port is working normal. When reverting the above commit, access to both harddisks is working fine again." Maintain tag ordered submission as the default, but allow sata_sil24 to continue with the old behavior. Cc: Cc: Tejun Heo Reported-by: Ronny Hegewald Signed-off-by: Dan Williams Signed-off-by: Tejun Heo --- include/linux/libata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index f2b440e44fd7..91f705de2c0b 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -231,6 +231,7 @@ enum { ATA_FLAG_SW_ACTIVITY = (1 << 22), /* driver supports sw activity * led */ ATA_FLAG_NO_DIPM = (1 << 23), /* host not happy with DIPM */ + ATA_FLAG_LOWTAG = (1 << 24), /* host wants lowest available tag */ /* bits 24:31 of ap->flags are reserved for LLD specific flags */ -- cgit v1.2.3 From d453cded05ee219b77815ea194dc36efa5398bca Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 20 Jan 2015 09:07:04 +1030 Subject: module_arch_freeing_init(): new hook for archs before module->module_init freed. Archs have been abusing module_free() to clean up their arch-specific allocations. Since module_free() is also (ab)used by BPF and trace code, let's keep it to simple allocations, and provide a hook called before that. This means that avr32, ia64, parisc and s390 no longer need to implement their own module_free() at all. avr32 doesn't need module_finalize() either. Signed-off-by: Rusty Russell Cc: Chris Metcalf Cc: Haavard Skinnemoen Cc: Hans-Christian Egtvedt Cc: Tony Luck Cc: Fenghua Yu Cc: "James E.J. Bottomley" Cc: Helge Deller Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: linux-kernel@vger.kernel.org Cc: linux-ia64@vger.kernel.org Cc: linux-parisc@vger.kernel.org Cc: linux-s390@vger.kernel.org --- include/linux/moduleloader.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h index 7eeb9bbfb816..054eac853090 100644 --- a/include/linux/moduleloader.h +++ b/include/linux/moduleloader.h @@ -82,4 +82,6 @@ int module_finalize(const Elf_Ehdr *hdr, /* Any cleanup needed when module leaves. */ void module_arch_cleanup(struct module *mod); +/* Any cleanup before freeing mod->module_init */ +void module_arch_freeing_init(struct module *mod); #endif -- cgit v1.2.3 From be1f221c0445a4157d177197c236f888d3581914 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 20 Jan 2015 09:07:05 +1030 Subject: module: remove mod arg from module_free, rename module_memfree(). Nothing needs the module pointer any more, and the next patch will call it from RCU, where the module itself might no longer exist. Removing the arg is the safest approach. This just codifies the use of the module_alloc/module_free pattern which ftrace and bpf use. Signed-off-by: Rusty Russell Acked-by: Alexei Starovoitov Cc: Mikael Starvik Cc: Jesper Nilsson Cc: Ralf Baechle Cc: Ley Foon Tan Cc: Benjamin Herrenschmidt Cc: Chris Metcalf Cc: Steven Rostedt Cc: x86@kernel.org Cc: Ananth N Mavinakayanahalli Cc: Anil S Keshavamurthy Cc: Masami Hiramatsu Cc: linux-cris-kernel@axis.com Cc: linux-kernel@vger.kernel.org Cc: linux-mips@linux-mips.org Cc: nios2-dev@lists.rocketboards.org Cc: linuxppc-dev@lists.ozlabs.org Cc: sparclinux@vger.kernel.org Cc: netdev@vger.kernel.org --- include/linux/moduleloader.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h index 054eac853090..f7556261fe3c 100644 --- a/include/linux/moduleloader.h +++ b/include/linux/moduleloader.h @@ -26,7 +26,7 @@ unsigned int arch_mod_section_prepend(struct module *mod, unsigned int section); void *module_alloc(unsigned long size); /* Free memory returned from module_alloc. */ -void module_free(struct module *mod, void *module_region); +void module_memfree(void *module_region); /* * Apply the given relocation to the (simplified) ELF. Return -error -- cgit v1.2.3 From d5db139ab3764640e0882a1746e7b9fdee33fd87 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 22 Jan 2015 11:13:14 +1030 Subject: module: make module_refcount() a signed integer. James Bottomley points out that it will be -1 during unload. It's only used for diagnostics, so let's not hide that as it could be a clue as to what's gone wrong. Cc: Jason Wessel Acked-and-documention-added-by: James Bottomley Reviewed-by: Masami Hiramatsu 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 ebfb0e153c6a..b653d7c0a05a 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -444,7 +444,7 @@ extern void __module_put_and_exit(struct module *mod, long code) #define module_put_and_exit(code) __module_put_and_exit(THIS_MODULE, code) #ifdef CONFIG_MODULE_UNLOAD -unsigned long module_refcount(struct module *mod); +int module_refcount(struct module *mod); void __symbol_put(const char *symbol); #define symbol_put(x) __symbol_put(VMLINUX_SYMBOL_STR(x)) void symbol_put_addr(void *addr); -- cgit v1.2.3 From 9879de7373fcfb466ec198293b6ccc1ad7a42dd8 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Mon, 26 Jan 2015 12:58:32 -0800 Subject: mm: page_alloc: embed OOM killing naturally into allocation slowpath The OOM killing invocation does a lot of duplicative checks against the task's allocation context. Rework it to take advantage of the existing checks in the allocator slowpath. The OOM killer is invoked when the allocator is unable to reclaim any pages but the allocation has to keep looping. Instead of having a check for __GFP_NORETRY hidden in oom_gfp_allowed(), just move the OOM invocation to the true branch of should_alloc_retry(). The __GFP_FS check from oom_gfp_allowed() can then be moved into the OOM avoidance branch in __alloc_pages_may_oom(), along with the PF_DUMPCORE test. __alloc_pages_may_oom() can then signal to the caller whether the OOM killer was invoked, instead of requiring it to duplicate the order and high_zoneidx checks to guess this when deciding whether to continue. Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/oom.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/oom.h b/include/linux/oom.h index 853698c721f7..76200984d1e2 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -85,11 +85,6 @@ static inline void oom_killer_enable(void) oom_killer_disabled = false; } -static inline bool oom_gfp_allowed(gfp_t gfp_mask) -{ - return (gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY); -} - extern struct task_struct *find_lock_task_mm(struct task_struct *p); static inline bool task_will_free_mem(struct task_struct *task) -- cgit v1.2.3 From 07261edb971492c6b41b44d7b1b51f76807d30ad Mon Sep 17 00:00:00 2001 From: Pranith Kumar Date: Mon, 26 Jan 2015 12:58:43 -0800 Subject: printk: add dummy routine for when CONFIG_PRINTK=n There are missing dummy routines for log_buf_addr_get() and log_buf_len_get() for when CONFIG_PRINTK is not set causing build failures. This patch adds these dummy routines at the appropriate location. Signed-off-by: Pranith Kumar Cc: Michael Ellerman Reviewed-by: Petr Mladek Acked-by: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index c8f170324e64..4d5bf5726578 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -10,9 +10,6 @@ extern const char linux_banner[]; extern const char linux_proc_banner[]; -extern char *log_buf_addr_get(void); -extern u32 log_buf_len_get(void); - static inline int printk_get_level(const char *buffer) { if (buffer[0] == KERN_SOH_ASCII && buffer[1]) { @@ -163,6 +160,8 @@ extern int kptr_restrict; extern void wake_up_klogd(void); +char *log_buf_addr_get(void); +u32 log_buf_len_get(void); void log_buf_kexec_setup(void); void __init setup_log_buf(int early); void dump_stack_set_arch_desc(const char *fmt, ...); @@ -198,6 +197,16 @@ static inline void wake_up_klogd(void) { } +static inline char *log_buf_addr_get(void) +{ + return NULL; +} + +static inline u32 log_buf_len_get(void) +{ + return 0; +} + static inline void log_buf_kexec_setup(void) { } -- cgit v1.2.3 From c3c87e770458aa004bd7ed3f29945ff436fd6511 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 23 Jan 2015 11:19:48 +0100 Subject: perf: Tighten (and fix) the grouping condition The fix from 9fc81d87420d ("perf: Fix events installation during moving group") was incomplete in that it failed to recognise that creating a group with events for different CPUs is semantically broken -- they cannot be co-scheduled. Furthermore, it leads to real breakage where, when we create an event for CPU Y and then migrate it to form a group on CPU X, the code gets confused where the counter is programmed -- triggered in practice as well by me via the perf fuzzer. Fix this by tightening the rules for creating groups. Only allow grouping of counters that can be co-scheduled in the same context. This means for the same task and/or the same cpu. Fixes: 9fc81d87420d ("perf: Fix events installation during moving group") Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Link: http://lkml.kernel.org/r/20150123125834.090683288@infradead.org Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 4f7a61ca4b39..664de5a4ec46 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -450,11 +450,6 @@ struct perf_event { #endif /* CONFIG_PERF_EVENTS */ }; -enum perf_event_context_type { - task_context, - cpu_context, -}; - /** * struct perf_event_context - event context structure * @@ -462,7 +457,6 @@ enum perf_event_context_type { */ struct perf_event_context { struct pmu *pmu; - enum perf_event_context_type type; /* * Protect the states of the events in the list, * nr_active, and the list: -- cgit v1.2.3