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') 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') 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') 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') 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') 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') 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') 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') 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') 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') 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 7216dc077dfcd46e2e0143f57711c8dd2eb99e68 Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Tue, 6 Jan 2015 16:15:01 -0800 Subject: target: Drop left-over fabric_max_sectors attribute Now that fabric_max_sectors is no longer used to enforce the maximum I/O size, go ahead and drop it's left-over usage in target-core and associated backend drivers. Cc: Christoph Hellwig Cc: Martin K. Petersen Cc: Roland Dreier Signed-off-by: Nicholas Bellinger --- include/target/target_core_backend.h | 1 - include/target/target_core_backend_configfs.h | 2 -- include/target/target_core_base.h | 3 --- 3 files changed, 6 deletions(-) (limited to 'include') diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h index 430cfaf92285..db81c65b8f48 100644 --- a/include/target/target_core_backend.h +++ b/include/target/target_core_backend.h @@ -135,7 +135,6 @@ int se_dev_set_is_nonrot(struct se_device *, int); int se_dev_set_emulate_rest_reord(struct se_device *dev, int); int se_dev_set_queue_depth(struct se_device *, u32); int se_dev_set_max_sectors(struct se_device *, u32); -int se_dev_set_fabric_max_sectors(struct se_device *, u32); int se_dev_set_optimal_sectors(struct se_device *, u32); int se_dev_set_block_size(struct se_device *, u32); diff --git a/include/target/target_core_backend_configfs.h b/include/target/target_core_backend_configfs.h index 3247d7530107..186f7a923570 100644 --- a/include/target/target_core_backend_configfs.h +++ b/include/target/target_core_backend_configfs.h @@ -98,8 +98,6 @@ static struct target_backend_dev_attrib_attribute _backend##_dev_attrib_##_name TB_DEV_ATTR(_backend, block_size, S_IRUGO | S_IWUSR); \ DEF_TB_DEV_ATTRIB_RO(_backend, hw_max_sectors); \ TB_DEV_ATTR_RO(_backend, hw_max_sectors); \ - DEF_TB_DEV_ATTRIB(_backend, fabric_max_sectors); \ - TB_DEV_ATTR(_backend, fabric_max_sectors, S_IRUGO | S_IWUSR); \ DEF_TB_DEV_ATTRIB(_backend, optimal_sectors); \ TB_DEV_ATTR(_backend, optimal_sectors, S_IRUGO | S_IWUSR); \ DEF_TB_DEV_ATTRIB_RO(_backend, hw_queue_depth); \ diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 397fb635766a..4a8795a87b9e 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -77,8 +77,6 @@ #define DA_UNMAP_GRANULARITY_ALIGNMENT_DEFAULT 0 /* Default max_write_same_len, disabled by default */ #define DA_MAX_WRITE_SAME_LEN 0 -/* Default max transfer length */ -#define DA_FABRIC_MAX_SECTORS 8192 /* Use a model alias based on the configfs backend device name */ #define DA_EMULATE_MODEL_ALIAS 0 /* Emulation for Direct Page Out */ @@ -694,7 +692,6 @@ struct se_dev_attrib { u32 hw_block_size; u32 block_size; u32 hw_max_sectors; - u32 fabric_max_sectors; u32 optimal_sectors; u32 hw_queue_depth; u32 queue_depth; -- cgit v1.2.3 From 029b18361921a0a07b17bd89a2cf20df3d115de8 Mon Sep 17 00:00:00 2001 From: Gabriel Laskar Date: Sun, 11 Jan 2015 16:18:06 -0800 Subject: Input: uinput - fix ioctl nr overflow for UI_GET_SYSNAME/VERSION Request number for ioctls are encoded as 8bit numbers, but unfortunately UI_GET_SYSNAME and UI_GET_VERSION specifu values larger than that, so they get truncated to 44 (0x2c) and 45 (0x2d). This change makes requested values match their effective values (the ABI stays intact). Signed-off-by: Gabriel Laskar Signed-off-by: Dmitry Torokhov --- include/uapi/linux/uinput.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/uinput.h b/include/uapi/linux/uinput.h index baeab83deb64..013c9d8db372 100644 --- a/include/uapi/linux/uinput.h +++ b/include/uapi/linux/uinput.h @@ -82,7 +82,7 @@ struct uinput_ff_erase { * The complete sysfs path is then /sys/devices/virtual/input/--NAME-- * Usually, it is in the form "inputN" */ -#define UI_GET_SYSNAME(len) _IOC(_IOC_READ, UINPUT_IOCTL_BASE, 300, len) +#define UI_GET_SYSNAME(len) _IOC(_IOC_READ, UINPUT_IOCTL_BASE, 44, len) /** * UI_GET_VERSION - Return version of uinput protocol @@ -91,7 +91,7 @@ struct uinput_ff_erase { * the integer pointed to by the ioctl argument. The protocol version * is hard-coded in the kernel and is independent of the uinput device. */ -#define UI_GET_VERSION _IOR(UINPUT_IOCTL_BASE, 301, unsigned int) +#define UI_GET_VERSION _IOR(UINPUT_IOCTL_BASE, 45, unsigned int) /* * To write a force-feedback-capable driver, the upload_effect -- cgit v1.2.3 From b5540ce1512eede3bed68ab1e9949df9ad556091 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 5 Dec 2014 19:25:31 +0200 Subject: mmc: sdhci: Disable re-tuning for HS400 Re-tuning for HS400 mode must be done in HS200 mode. Currently there is no support for that. That needs to be reflected in the code. Specifically, if tuning is executed in HS400 mode then return an error, and do not start the tuning timer if HS200 tuning is being done prior to switching to HS400. Note that periodic re-tuning is not expected to be needed for HS400 but re-tuning is still needed after the host controller has lost power. In the case of suspend/resume that is not necessary because the card is fully re-initialised. That just leaves runtime suspend/resume with no support for HS400 re-tuning. Signed-off-by: Adrian Hunter Signed-off-by: Ulf Hansson --- include/linux/mmc/sdhci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h index 375af80bde7d..f767a0de611f 100644 --- a/include/linux/mmc/sdhci.h +++ b/include/linux/mmc/sdhci.h @@ -137,6 +137,7 @@ struct sdhci_host { #define SDHCI_SDR104_NEEDS_TUNING (1<<10) /* SDR104/HS200 needs tuning */ #define SDHCI_USING_RETUNING_TIMER (1<<11) /* Host is using a retuning timer for the card */ #define SDHCI_USE_64_BIT_DMA (1<<12) /* Use 64-bit DMA */ +#define SDHCI_HS400_TUNING (1<<13) /* Tuning for HS400 */ unsigned int version; /* SDHCI spec. version */ -- cgit v1.2.3 From 721c21c17ab958abf19a8fc611c3bd4743680e38 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Mon, 12 Jan 2015 19:10:55 +0000 Subject: mm: mmu_gather: use tlb->end != 0 only for TLB invalidation When batching up address ranges for TLB invalidation, we check tlb->end != 0 to indicate that some pages have actually been unmapped. As of commit f045bbb9fa1b ("mmu_gather: fix over-eager tlb_flush_mmu_free() calling"), we use the same check for freeing these pages in order to avoid a performance regression where we call free_pages_and_swap_cache even when no pages are actually queued up. Unfortunately, the range could have been reset (tlb->end = 0) by tlb_end_vma, which has been shown to cause memory leaks on arm64. Furthermore, investigation into these leaks revealed that the fullmm case on task exit no longer invalidates the TLB, by virtue of tlb->end == 0 (in 3.18, need_flush would have been set). This patch resolves the problem by reverting commit f045bbb9fa1b, using instead tlb->local.nr as the predicate for page freeing in tlb_flush_mmu_free and ensuring that tlb->end is initialised to a non-zero value in the fullmm case. Tested-by: Mark Langsdorf Tested-by: Dave Hansen Signed-off-by: Will Deacon Signed-off-by: Linus Torvalds --- include/asm-generic/tlb.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 08848050922e..db284bff29dc 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -136,8 +136,12 @@ static inline void __tlb_adjust_range(struct mmu_gather *tlb, static inline void __tlb_reset_range(struct mmu_gather *tlb) { - tlb->start = TASK_SIZE; - tlb->end = 0; + if (tlb->fullmm) { + tlb->start = tlb->end = ~0; + } else { + tlb->start = TASK_SIZE; + tlb->end = 0; + } } /* -- cgit v1.2.3 From f221b04fe07eb56c39935e31bb8e9ddacc00612f Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Tue, 13 Jan 2015 07:40:05 +0000 Subject: x86/xen: properly retrieve NMI reason Using the native code here can't work properly, as the hypervisor would normally have cleared the two reason bits by the time Dom0 gets to see the NMI (if passed to it at all). There's a shared info field for this, and there's an existing hook to use - just fit the two together. This is particularly relevant so that NMIs intended to be handled by APEI / GHES actually make it to the respective handler. Note that the hook can (and should) be used irrespective of whether being in Dom0, as accessing port 0x61 in a DomU would be even worse, while the shared info field would just hold zero all the time. Note further that hardware NMI handling for PVH doesn't currently work anyway due to missing code in the hypervisor (but it is expected to work the native rather than the PV way). Signed-off-by: Jan Beulich Reviewed-by: Boris Ostrovsky Signed-off-by: David Vrabel --- include/xen/interface/nmi.h | 51 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) create mode 100644 include/xen/interface/nmi.h (limited to 'include') diff --git a/include/xen/interface/nmi.h b/include/xen/interface/nmi.h new file mode 100644 index 000000000000..b47d9d06fade --- /dev/null +++ b/include/xen/interface/nmi.h @@ -0,0 +1,51 @@ +/****************************************************************************** + * nmi.h + * + * NMI callback registration and reason codes. + * + * Copyright (c) 2005, Keir Fraser + */ + +#ifndef __XEN_PUBLIC_NMI_H__ +#define __XEN_PUBLIC_NMI_H__ + +#include + +/* + * NMI reason codes: + * Currently these are x86-specific, stored in arch_shared_info.nmi_reason. + */ + /* I/O-check error reported via ISA port 0x61, bit 6. */ +#define _XEN_NMIREASON_io_error 0 +#define XEN_NMIREASON_io_error (1UL << _XEN_NMIREASON_io_error) + /* PCI SERR reported via ISA port 0x61, bit 7. */ +#define _XEN_NMIREASON_pci_serr 1 +#define XEN_NMIREASON_pci_serr (1UL << _XEN_NMIREASON_pci_serr) + /* Unknown hardware-generated NMI. */ +#define _XEN_NMIREASON_unknown 2 +#define XEN_NMIREASON_unknown (1UL << _XEN_NMIREASON_unknown) + +/* + * long nmi_op(unsigned int cmd, void *arg) + * NB. All ops return zero on success, else a negative error code. + */ + +/* + * Register NMI callback for this (calling) VCPU. Currently this only makes + * sense for domain 0, vcpu 0. All other callers will be returned EINVAL. + * arg == pointer to xennmi_callback structure. + */ +#define XENNMI_register_callback 0 +struct xennmi_callback { + unsigned long handler_address; + unsigned long pad; +}; +DEFINE_GUEST_HANDLE_STRUCT(xennmi_callback); + +/* + * Deregister NMI callback for this (calling) VCPU. + * arg == NULL. + */ +#define XENNMI_unregister_callback 1 + +#endif /* __XEN_PUBLIC_NMI_H__ */ -- 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') 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 43239cbe79fc369f5d2160bd7f69e28b5c50a58c Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Tue, 13 Jan 2015 10:46:42 +0100 Subject: kernel: Change ASSIGN_ONCE(val, x) to WRITE_ONCE(x, val) Feedback has shown that WRITE_ONCE(x, val) is easier to use than ASSIGN_ONCE(val,x). There are no in-tree users yet, so lets change it for 3.19. Signed-off-by: Christian Borntraeger Acked-by: Peter Zijlstra Acked-by: Davidlohr Bueso Acked-by: Paul E. McKenney --- include/linux/compiler.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index a1c81f80978e..33063f872ee3 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -215,7 +215,7 @@ static __always_inline void __read_once_size(volatile void *p, void *res, int si } } -static __always_inline void __assign_once_size(volatile void *p, void *res, int size) +static __always_inline void __write_once_size(volatile void *p, void *res, int size) { switch (size) { case 1: *(volatile __u8 *)p = *(__u8 *)res; break; @@ -235,15 +235,15 @@ static __always_inline void __assign_once_size(volatile void *p, void *res, int /* * Prevent the compiler from merging or refetching reads or writes. The * compiler is also forbidden from reordering successive instances of - * READ_ONCE, ASSIGN_ONCE and ACCESS_ONCE (see below), but only when the + * READ_ONCE, WRITE_ONCE and ACCESS_ONCE (see below), but only when the * compiler is aware of some particular ordering. One way to make the * compiler aware of ordering is to put the two invocations of READ_ONCE, - * ASSIGN_ONCE or ACCESS_ONCE() in different C statements. + * WRITE_ONCE or ACCESS_ONCE() in different C statements. * * In contrast to ACCESS_ONCE these two macros will also work on aggregate * data types like structs or unions. If the size of the accessed data * type exceeds the word size of the machine (e.g., 32 bits or 64 bits) - * READ_ONCE() and ASSIGN_ONCE() will fall back to memcpy and print a + * READ_ONCE() and WRITE_ONCE() will fall back to memcpy and print a * compile-time warning. * * Their two major use cases are: (1) Mediating communication between @@ -257,8 +257,8 @@ static __always_inline void __assign_once_size(volatile void *p, void *res, int #define READ_ONCE(x) \ ({ typeof(x) __val; __read_once_size(&x, &__val, sizeof(__val)); __val; }) -#define ASSIGN_ONCE(val, x) \ - ({ typeof(x) __val; __val = val; __assign_once_size(&x, &__val, sizeof(__val)); __val; }) +#define WRITE_ONCE(x, val) \ + ({ typeof(x) __val; __val = val; __write_once_size(&x, &__val, sizeof(__val)); __val; }) #endif /* __KERNEL__ */ -- 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') 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 1ba398041f5b5a15456ea20a9ba3ff80b6a4e7d1 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Wed, 14 Jan 2015 13:56:19 +0000 Subject: openvswitch: packet messages need their own probe attribtue User space is currently sending a OVS_FLOW_ATTR_PROBE for both flow and packet messages. This leads to an out-of-bounds access in ovs_packet_cmd_execute() because OVS_FLOW_ATTR_PROBE > OVS_PACKET_ATTR_MAX. Introduce a new OVS_PACKET_ATTR_PROBE with the same numeric value as OVS_FLOW_ATTR_PROBE to grow the range of accepted packet attributes while maintaining to be binary compatible with existing OVS binaries. Fixes: 05da589 ("openvswitch: Add support for OVS_FLOW_ATTR_PROBE.") Reported-by: Sander Eikelenboom Tracked-down-by: Florian Westphal Signed-off-by: Thomas Graf Reviewed-by: Jesse Gross Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 3a6dcaa359b7..f714e8633352 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -174,6 +174,10 @@ enum ovs_packet_attr { OVS_PACKET_ATTR_USERDATA, /* OVS_ACTION_ATTR_USERSPACE arg. */ OVS_PACKET_ATTR_EGRESS_TUN_KEY, /* Nested OVS_TUNNEL_KEY_ATTR_* attributes. */ + OVS_PACKET_ATTR_UNUSED1, + OVS_PACKET_ATTR_UNUSED2, + OVS_PACKET_ATTR_PROBE, /* Packet operation is a feature probe, + error logging should be suppressed. */ __OVS_PACKET_ATTR_MAX }; -- cgit v1.2.3 From 6cfda7fbebe8a4fd33ea5722fa0212f98f643c35 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Mon, 5 Jan 2015 19:47:43 +0100 Subject: can: m_can: tag current CAN FD controllers as non-ISO During the CAN FD standardization process within the ISO it turned out that the failure detection capability has to be improved. The CAN in Automation organization (CiA) defined the already implemented CAN FD controllers as 'non-ISO' and the upcoming improved CAN FD controllers as 'ISO' compliant. See at http://www.can-cia.com/index.php?id=1937 Finally there will be three types of CAN FD controllers in the future: 1. ISO compliant (fixed) 2. non-ISO compliant (fixed, like the M_CAN IP v3.0.1 in m_can.c) 3. ISO/non-ISO CAN FD controllers (switchable, like the PEAK USB FD) So the current M_CAN driver for the M_CAN IP v3.0.1 has to expose its non-ISO implementation by setting the CAN_CTRLMODE_FD_NON_ISO ctrlmode at startup. As this bit cannot be switched at configuration time CAN_CTRLMODE_FD_NON_ISO must not be set in ctrlmode_supported of the current M_CAN driver. Signed-off-by: Oliver Hartkopp Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can/netlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h index 3e4323a3918d..94ffe0c83ce7 100644 --- a/include/uapi/linux/can/netlink.h +++ b/include/uapi/linux/can/netlink.h @@ -98,6 +98,7 @@ struct can_ctrlmode { #define CAN_CTRLMODE_BERR_REPORTING 0x10 /* Bus-error reporting */ #define CAN_CTRLMODE_FD 0x20 /* CAN FD mode */ #define CAN_CTRLMODE_PRESUME_ACK 0x40 /* Ignore missing CAN ACKs */ +#define CAN_CTRLMODE_FD_NON_ISO 0x80 /* CAN FD in non-ISO mode */ /* * CAN device statistics -- 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') 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') 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 f555f3d76aaade29c7e221a37ee64fe722955c09 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 16 Jan 2015 11:37:12 +0100 Subject: genetlink: document parallel_ops The kernel-doc for the parallel_ops family struct member is missing, add it. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/net/genetlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 84125088c309..2ea2c55bdc87 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -27,6 +27,8 @@ struct genl_info; * @maxattr: maximum number of attributes supported * @netnsok: set to true if the family can handle network * namespaces and should be presented in all of them + * @parallel_ops: operations can be called in parallel and aren't + * synchronized by the core genetlink code * @pre_doit: called before an operation's doit callback, it may * do additional, common, filtering and return an error * @post_doit: called after an operation's doit callback, it may -- 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 ++++ include/net/genetlink.h | 5 ++++- 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include') 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 diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 2ea2c55bdc87..6c92415311ca 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -35,7 +35,10 @@ struct genl_info; * undo operations done by pre_doit, for example release locks * @mcast_bind: a socket bound to the given multicast group (which * is given as the offset into the groups array) - * @mcast_unbind: a socket was unbound from the given multicast group + * @mcast_unbind: a socket was unbound from the given multicast group. + * Note that unbind() will not be called symmetrically if the + * generic netlink family is removed while there are still open + * sockets. * @attrbuf: buffer to store parsed attributes * @family_list: family list * @mcgrps: multicast groups used by this family (private) -- cgit v1.2.3 From cdef511985374dd042a40bb32c1c346c2662c9dc Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Thu, 15 Jan 2015 15:21:19 +0100 Subject: KVM: fix sparse warning in include/trace/events/kvm.h sparse complains about include/trace/events/kvm.h:163:1: error: directive in argument list include/trace/events/kvm.h:167:1: error: directive in argument list include/trace/events/kvm.h:169:1: error: directive in argument list and sparse is right. Preprocessing directives in an argument of a macro are undefined behaviour as of C99 6.10.3p11. Lets use an indirection to fix this. Signed-off-by: Christian Borntraeger Signed-off-by: Paolo Bonzini --- include/trace/events/kvm.h | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index 6edf1f2028cd..86b399c66c3d 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -146,6 +146,14 @@ TRACE_EVENT(kvm_msi_set_irq, #if defined(CONFIG_HAVE_KVM_IRQFD) +#ifdef kvm_irqchips +#define kvm_ack_irq_string "irqchip %s pin %u" +#define kvm_ack_irq_parm __print_symbolic(__entry->irqchip, kvm_irqchips), __entry->pin +#else +#define kvm_ack_irq_string "irqchip %d pin %u" +#define kvm_ack_irq_parm __entry->irqchip, __entry->pin +#endif + TRACE_EVENT(kvm_ack_irq, TP_PROTO(unsigned int irqchip, unsigned int pin), TP_ARGS(irqchip, pin), @@ -160,13 +168,7 @@ TRACE_EVENT(kvm_ack_irq, __entry->pin = pin; ), -#ifdef kvm_irqchips - TP_printk("irqchip %s pin %u", - __print_symbolic(__entry->irqchip, kvm_irqchips), - __entry->pin) -#else - TP_printk("irqchip %d pin %u", __entry->irqchip, __entry->pin) -#endif + TP_printk(kvm_ack_irq_string, kvm_ack_irq_parm) ); #endif /* defined(CONFIG_HAVE_KVM_IRQFD) */ -- 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') 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') 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') 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') 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