From a7b8829d242b1a58107e9c02b09e93aec446d55c Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Wed, 5 Jul 2017 20:30:01 +0200 Subject: iio: accel: st_accel: add SPI-3wire support Add SPI Serial Interface Mode (SIM) register information in st_sensor_settings look up table to support devices (like LSM303AGR accel sensor) that allow just SPI-3wire communication mode. SIM mode has to be configured before any other operation since it is not enabled by default and the driver is not able to read without that configuration Whilst a fairly substantial patch, the actual logic is simple and it is better to have the generic fix than a band aid. Fixes: ddc05fa28606 (iio: st-accel: add support for lsm303agr accel) Signed-off-by: Lorenzo Bianconi Cc: Signed-off-by: Jonathan Cameron --- include/linux/iio/common/st_sensors.h | 7 +++++++ include/linux/platform_data/st_sensors_pdata.h | 2 ++ 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index 497f2b3a5a62..97f1b465d04f 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -105,6 +105,11 @@ struct st_sensor_fullscale { struct st_sensor_fullscale_avl fs_avl[ST_SENSORS_FULLSCALE_AVL_MAX]; }; +struct st_sensor_sim { + u8 addr; + u8 value; +}; + /** * struct st_sensor_bdu - ST sensor device block data update * @addr: address of the register. @@ -197,6 +202,7 @@ struct st_sensor_transfer_function { * @bdu: Block data update register. * @das: Data Alignment Selection register. * @drdy_irq: Data ready register of the sensor. + * @sim: SPI serial interface mode register of the sensor. * @multi_read_bit: Use or not particular bit for [I2C/SPI] multi-read. * @bootime: samples to discard when sensor passing from power-down to power-up. */ @@ -213,6 +219,7 @@ struct st_sensor_settings { struct st_sensor_bdu bdu; struct st_sensor_das das; struct st_sensor_data_ready_irq drdy_irq; + struct st_sensor_sim sim; bool multi_read_bit; unsigned int bootime; }; diff --git a/include/linux/platform_data/st_sensors_pdata.h b/include/linux/platform_data/st_sensors_pdata.h index 79b0e4cdb814..f8274b0c6888 100644 --- a/include/linux/platform_data/st_sensors_pdata.h +++ b/include/linux/platform_data/st_sensors_pdata.h @@ -17,10 +17,12 @@ * Available only for accelerometer and pressure sensors. * Accelerometer DRDY on LSM330 available only on pin 1 (see datasheet). * @open_drain: set the interrupt line to be open drain if possible. + * @spi_3wire: enable spi-3wire mode. */ struct st_sensors_platform_data { u8 drdy_int_pin; bool open_drain; + bool spi_3wire; }; #endif /* ST_SENSORS_PDATA_H */ -- cgit v1.2.3 From 1937f8a29f4a650bc27e0311b43b53509a34fd22 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 24 Jul 2017 12:52:59 +0200 Subject: scsi: bnx2fc: Simplify CPU hotplug code The CPU hotplug related code of this driver can be simplified by: 1) Consolidating the callbacks into a single state. The CPU thread can be torn down on the CPU which goes offline. There is no point in delaying that to the CPU dead state 2) Let the core code invoke the online/offline callbacks and remove the extra for_each_online_cpu() loops. Signed-off-by: Thomas Gleixner Signed-off-by: Martin K. Petersen --- include/linux/cpuhotplug.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index b56573bf440d..2e7b1731ad12 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -39,7 +39,6 @@ enum cpuhp_state { CPUHP_PCI_XGENE_DEAD, CPUHP_IOMMU_INTEL_DEAD, CPUHP_LUSTRE_CFS_DEAD, - CPUHP_SCSI_BNX2FC_DEAD, CPUHP_SCSI_BNX2I_DEAD, CPUHP_WORKQUEUE_PREP, CPUHP_POWER_NUMA_PREPARE, -- cgit v1.2.3 From f9f22a86912f9d36b50e9b3b383fabfb9f22dd46 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 24 Jul 2017 12:53:00 +0200 Subject: scsi: bnx2i: Simplify cpu hotplug code The CPU hotplug related code of this driver can be simplified by: 1) Consolidating the callbacks into a single state. The CPU thread can be torn down on the CPU which goes offline. There is no point in delaying that to the CPU dead state 2) Let the core code invoke the online/offline callbacks and remove the extra for_each_online_cpu() loops. Signed-off-by: Thomas Gleixner Acked-by: Chad Dupuis Signed-off-by: Martin K. Petersen --- include/linux/cpuhotplug.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 2e7b1731ad12..82b30e638430 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -39,7 +39,6 @@ enum cpuhp_state { CPUHP_PCI_XGENE_DEAD, CPUHP_IOMMU_INTEL_DEAD, CPUHP_LUSTRE_CFS_DEAD, - CPUHP_SCSI_BNX2I_DEAD, CPUHP_WORKQUEUE_PREP, CPUHP_POWER_NUMA_PREPARE, CPUHP_HRTIMERS_PREPARE, -- cgit v1.2.3 From 37ef38f3f83891a2f413fb872bae7d0f9bb95b27 Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Thu, 27 Jul 2017 16:15:52 -0500 Subject: tty: pl011: fix initialization order of QDF2400 E44 The work-around for Qualcomm Technologies QDF2400 Erratum 44 hinges on a global variable defined in the pl011 driver. The ACPI SPCR parsing code determines whether the work-around is needed, and if so, it changes the console name from "pl011" to "qdf2400_e44". The expectation is that the pl011 driver will implement the work-around when it sees the console name. The global variable qdf2400_e44_present is set when that happens. The problem is that work-around needs to be enabled when the pl011 driver probes, not when the console name is queried. However, sbsa_probe() is called before pl011_console_match(). The work-around appeared to work previously because the default console on QDF2400 platforms was always ttyAMA1. The first time sbsa_probe() is called (for ttyAMA0), qdf2400_e44_present is still false. Then pl011_console_match() is called, and it sets qdf2400_e44_present to true. All subsequent calls to sbsa_probe() enable the work-around. The solution is to move the global variable into spcr.c and let the pl011 driver query it during probe time. This works because all QDF2400 platforms require SPCR, so parse_spcr() will always be called. pl011_console_match still checks for the "qdf2400_e44" console name, but it doesn't do anything else special. Fixes: 5a0722b898f8 ("tty: pl011: use "qdf2400_e44" as the earlycon name for QDF2400 E44") Tested-by: Jeffrey Hugo Signed-off-by: Timur Tabi Signed-off-by: Greg Kroah-Hartman --- include/linux/acpi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index c749eef1daa1..27b4b6615263 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1209,6 +1209,7 @@ static inline bool acpi_has_watchdog(void) { return false; } #endif #ifdef CONFIG_ACPI_SPCR_TABLE +extern bool qdf2400_e44_present; int parse_spcr(bool earlycon); #else static inline int parse_spcr(bool earlycon) { return 0; } -- cgit v1.2.3 From 99f828436788f0155798145853607ca8f0e6de93 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 28 Jul 2017 22:29:51 +0100 Subject: dma-buf/sync_file: Allow multiple sync_files to wrap a single dma-fence Up until recently sync_file were create to export a single dma-fence to userspace, and so we could canabalise a bit insie dma-fence to mark whether or not we had enable polling for the sync_file itself. However, with the advent of syncobj, we do allow userspace to create multiple sync_files for a single dma-fence. (Similarly, that the sw-sync validation framework also started returning multiple sync-files wrapping a single dma-fence for a syncpt also triggering the problem.) This patch reverts my suggestion in commit e24165537312 ("dma-buf/sync_file: only enable fence signalling on poll()") to use a single bit in the shared dma-fence and restores the sync_file->flags for tracking the bits individually. Reported-by: Gustavo Padovan Fixes: f1e8c67123cf ("dma-buf/sw-sync: Use an rbtree to sort fences in the timeline") Fixes: e9083420bbac ("drm: introduce sync objects (v4)") Signed-off-by: Chris Wilson Cc: Sumit Semwal Cc: Sean Paul Cc: Gustavo Padovan Cc: dri-devel@lists.freedesktop.org Cc: # v4.13-rc1+ Signed-off-by: Gustavo Padovan Link: http://patchwork.freedesktop.org/patch/msgid/20170728212951.7818-1-chris@chris-wilson.co.uk (cherry picked from commit db1fc97ca0c0d3fdeeadf314d99a26188438940a) --- include/linux/sync_file.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sync_file.h b/include/linux/sync_file.h index 5726107963b2..0ad87c434ae6 100644 --- a/include/linux/sync_file.h +++ b/include/linux/sync_file.h @@ -43,12 +43,13 @@ struct sync_file { #endif wait_queue_head_t wq; + unsigned long flags; struct dma_fence *fence; struct dma_fence_cb cb; }; -#define POLL_ENABLED DMA_FENCE_FLAG_USER_BITS +#define POLL_ENABLED 0 struct sync_file *sync_file_create(struct dma_fence *fence); struct dma_fence *sync_file_get_fence(int fd); -- cgit v1.2.3 From 9c80034921d1ece5c0e3241ba1645bce32387684 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Sat, 29 Jul 2017 14:11:43 +0200 Subject: i2c: rephrase explanation of I2C_CLASS_DEPRECATED Hopefully making clear that it is not needed for new drivers. Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 00ca5b86a753..d501d3956f13 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -689,7 +689,8 @@ i2c_unlock_adapter(struct i2c_adapter *adapter) #define I2C_CLASS_HWMON (1<<0) /* lm_sensors, ... */ #define I2C_CLASS_DDC (1<<3) /* DDC bus on graphics adapters */ #define I2C_CLASS_SPD (1<<7) /* Memory modules */ -#define I2C_CLASS_DEPRECATED (1<<8) /* Warn users that adapter will stop using classes */ +/* Warn users that the adapter doesn't support classes anymore */ +#define I2C_CLASS_DEPRECATED (1<<8) /* Internal numbers to terminate lists */ #define I2C_CLIENT_END 0xfffeU -- cgit v1.2.3 From d9535cb7b7603aeb549c697ecdf92024e4d0a650 Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Fri, 28 Jul 2017 17:30:02 -0500 Subject: ptp: introduce ptp auxiliary worker Many PTP drivers required to perform some asynchronous or periodic work, like periodically handling PHC counter overflow or handle delayed timestamp for RX/TX network packets. In most of the cases, such work is implemented using workqueues. Unfortunately, Kernel workqueues might introduce significant delay in work scheduling under high system load and on -RT, which could cause misbehavior of PTP drivers due to internal counter overflow, for example, and there is no way to tune its execution policy and priority manuallly. Hence, The kthread_worker can be used insted of workqueues, as it create separte named kthread for each worker and its its execution policy and priority can be configured using chrt tool. This prblem was reported for two drivers TI CPSW CPTS and dp83640, so instead of modifying each of these driver it was proposed to add PTP auxiliary worker to the PHC subsystem. The patch adds PTP auxiliary worker in PHC subsystem using kthread_worker and kthread_delayed_work and introduces two new PHC subsystem APIs: - long (*do_aux_work)(struct ptp_clock_info *ptp) callback in ptp_clock_info structure, which driver should assign if it require to perform asynchronous or periodic work. Driver should return the delay of the PTP next auxiliary work scheduling time (>=0) or negative value in case further scheduling is not required. - int ptp_schedule_worker(struct ptp_clock *ptp, unsigned long delay) which allows schedule PTP auxiliary work. The name of kthread_worker thread corresponds PTP PHC device name "ptp%d". Signed-off-by: Grygorii Strashko Signed-off-by: David S. Miller --- include/linux/ptp_clock_kernel.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index a026bfd089db..51349d124ee5 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -99,6 +99,11 @@ struct system_device_crosststamp; * parameter func: the desired function to use. * parameter chan: the function channel index to use. * + * @do_work: Request driver to perform auxiliary (periodic) operations + * Driver should return delay of the next auxiliary work scheduling + * time (>=0) or negative value in case further scheduling + * is not required. + * * Drivers should embed their ptp_clock_info within a private * structure, obtaining a reference to it using container_of(). * @@ -126,6 +131,7 @@ struct ptp_clock_info { struct ptp_clock_request *request, int on); int (*verify)(struct ptp_clock_info *ptp, unsigned int pin, enum ptp_pin_function func, unsigned int chan); + long (*do_aux_work)(struct ptp_clock_info *ptp); }; struct ptp_clock; @@ -211,6 +217,16 @@ extern int ptp_clock_index(struct ptp_clock *ptp); int ptp_find_pin(struct ptp_clock *ptp, enum ptp_pin_function func, unsigned int chan); +/** + * ptp_schedule_worker() - schedule ptp auxiliary work + * + * @ptp: The clock obtained from ptp_clock_register(). + * @delay: number of jiffies to wait before queuing + * See kthread_queue_delayed_work() for more info. + */ + +int ptp_schedule_worker(struct ptp_clock *ptp, unsigned long delay); + #else static inline struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, struct device *parent) @@ -225,6 +241,10 @@ static inline int ptp_clock_index(struct ptp_clock *ptp) static inline int ptp_find_pin(struct ptp_clock *ptp, enum ptp_pin_function func, unsigned int chan) { return -1; } +static inline int ptp_schedule_worker(struct ptp_clock *ptp, + unsigned long delay) +{ return -EOPNOTSUPP; } + #endif #endif -- cgit v1.2.3 From a477b9cd37aa81a490dfa3265b7ff4f2c5a92463 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 1 Aug 2017 20:11:02 -0500 Subject: PCI: Add pci_reset_function_locked() The implementation of PCI workarounds may require that the device is reset from its probe function. This implies that the PCI device lock is already held, and makes calling pci_reset_function() impossible (since it will itself try to take that lock). Add pci_reset_function_locked(), which is the equivalent of pci_reset_function(), except that it requires the PCI device lock to be already held by the caller. Tested-by: Ard Biesheuvel Signed-off-by: Marc Zyngier [bhelgaas: folded in fix for conflict with 52354b9d1f46 ("PCI: Remove __pci_dev_reset() and pci_dev_reset()")] Signed-off-by: Bjorn Helgaas Cc: stable@vger.kernel.org # 4.11: 52354b9d1f46: PCI: Remove __pci_dev_reset() and pci_dev_reset() Cc: stable@vger.kernel.org # 4.11 --- 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 4869e66dd659..a75c13673852 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1067,6 +1067,7 @@ void pcie_flr(struct pci_dev *dev); int __pci_reset_function(struct pci_dev *dev); int __pci_reset_function_locked(struct pci_dev *dev); int pci_reset_function(struct pci_dev *dev); +int pci_reset_function_locked(struct pci_dev *dev); int pci_try_reset_function(struct pci_dev *dev); int pci_probe_reset_slot(struct pci_slot *slot); int pci_reset_slot(struct pci_slot *slot); -- cgit v1.2.3 From 6d29231000bbe0fb9e4893a9c68151ffdd3b5469 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Mon, 31 Jul 2017 10:31:27 +0200 Subject: mtd: nand: Declare tBERS, tR and tPROG as u64 to avoid integer overflow All timings in nand_sdr_timings are expressed in picoseconds but some of them may not fit in an u32. Signed-off-by: Boris Brezillon Fixes: 204e7ecd47e2 ("mtd: nand: Add a few more timings to nand_sdr_timings") Reported-by: Alexander Dahl Cc: Reviewed-by: Alexander Dahl Tested-by: Alexander Dahl Signed-off-by: Boris Brezillon --- include/linux/mtd/nand.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 892148c448cc..5216d2eb2289 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -681,10 +681,10 @@ struct nand_buffers { * @tWW_min: WP# transition to WE# low */ struct nand_sdr_timings { - u32 tBERS_max; + u64 tBERS_max; u32 tCCS_min; - u32 tPROG_max; - u32 tR_max; + u64 tPROG_max; + u64 tR_max; u32 tALH_min; u32 tADL_min; u32 tALS_min; -- cgit v1.2.3 From c994f778bb1cca8ebe7a4e528cefec233e93b5cc Mon Sep 17 00:00:00 2001 From: Inbar Karmy Date: Tue, 1 Aug 2017 16:43:43 +0300 Subject: net/mlx4_en: Fix wrong indication of Wake-on-LAN (WoL) support Currently when WoL is supported but disabled, ethtool reports: "Supports Wake-on: d". Fix the indication of Wol support, so that the indication remains "g" all the time if the NIC supports WoL. Tested: As accepted, when NIC supports WoL- ethtool reports: Supports Wake-on: g Wake-on: d when NIC doesn't support WoL- ethtool reports: Supports Wake-on: d Wake-on: d Fixes: 14c07b1358ed ("mlx4: Wake on LAN support") Signed-off-by: Inbar Karmy Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index aad5d81dfb44..b54517c05e9a 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -620,6 +620,7 @@ struct mlx4_caps { u32 dmfs_high_rate_qpn_base; u32 dmfs_high_rate_qpn_range; u32 vf_caps; + bool wol_port[MLX4_MAX_PORTS + 1]; struct mlx4_rate_limit_caps rl_caps; }; -- cgit v1.2.3 From 931b3c1a832621b4bdcbaf783096fc267eb36fbe Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 1 Aug 2017 09:41:37 +0300 Subject: RDMA/mlx5: Fix existence check for extended address vector The extended address vector is the highest bit in be32 variable, but it was compared with the lowest. This patch fixes the endianness of that check and removes already declared define. Fixes: 17d2f88f92ce ("IB/mlx5: Add ODP atomics support") Reviewed-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/qp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 6f41270d80c0..f378dc0e7eaf 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -212,7 +212,6 @@ struct mlx5_wqe_ctrl_seg { #define MLX5_WQE_CTRL_OPCODE_MASK 0xff #define MLX5_WQE_CTRL_WQE_INDEX_MASK 0x00ffff00 #define MLX5_WQE_CTRL_WQE_INDEX_SHIFT 8 -#define MLX5_WQE_AV_EXT 0x80000000 enum { MLX5_ETH_WQE_L3_INNER_CSUM = 1 << 4, -- cgit v1.2.3 From 0cca6c8920ade95e2741b2062cf1397dc546fb0f Mon Sep 17 00:00:00 2001 From: Ludovic Desroches Date: Sun, 6 Aug 2017 16:00:05 +0200 Subject: pinctrl: generic: update references to Documentation/pinctrl.txt Update deprecated references to Documentation/pinctrl.txt since it has been moved to Documentation/driver-api/pinctl.rst. Signed-off-by: Ludovic Desroches Fixes: 5a9b73832e9e ("pinctrl.txt: move it to the driver-api book") Signed-off-by: Linus Walleij --- include/linux/device.h | 2 +- include/linux/pinctrl/pinconf-generic.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 723cd54b94da..beabdbc08420 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -843,7 +843,7 @@ struct dev_links_info { * hibernation, system resume and during runtime PM transitions * along with subsystem-level and driver-level callbacks. * @pins: For device pin management. - * See Documentation/pinctrl.txt for details. + * See Documentation/driver-api/pinctl.rst for details. * @msi_list: Hosts MSI descriptors * @msi_domain: The generic MSI domain this device is using. * @numa_node: NUMA node this device is close to. diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index 231d3075815a..e91d1b6a260d 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -81,8 +81,8 @@ * it. * @PIN_CONFIG_OUTPUT: this will configure the pin as an output and drive a * value on the line. Use argument 1 to indicate high level, argument 0 to - * indicate low level. (Please see Documentation/pinctrl.txt, section - * "GPIO mode pitfalls" for a discussion around this parameter.) + * indicate low level. (Please see Documentation/driver-api/pinctl.rst, + * section "GPIO mode pitfalls" for a discussion around this parameter.) * @PIN_CONFIG_POWER_SOURCE: if the pin can select between different power * supplies, the argument to this parameter (on a custom format) tells * the driver which alternative power source to use. -- cgit v1.2.3 From 0fb228d30b8d72bfee51f57e638d412324d44a11 Mon Sep 17 00:00:00 2001 From: James Smart Date: Tue, 1 Aug 2017 15:12:39 -0700 Subject: nvmet_fc: add defer_req callback for deferment of cmd buffer return At queue creation, the transport allocates a local job struct (struct nvmet_fc_fcp_iod) for each possible element of the queue. When a new CMD is received from the wire, a jobs struct is allocated from the queue and then used for the duration of the command. The job struct contains buffer space for the wire command iu. Thus, upon allocation of the job struct, the cmd iu buffer is copied to the job struct and the LLDD may immediately free/reuse the CMD IU buffer passed in the call. However, in some circumstances, due to the packetized nature of FC and the api of the FC LLDD which may issue a hw command to send the wire response, but the LLDD may not get the hw completion for the command and upcall the nvmet_fc layer before a new command may be asynchronously received on the wire. In other words, its possible for the initiator to get the response from the wire, thus believe a command slot free, and send a new command iu. The new command iu may be received by the LLDD and passed to the transport before the LLDD had serviced the hw completion and made the teardown calls for the original job struct. As such, there is no available job struct available for the new io. E.g. it appears like the host sent more queue elements than the queue size. It didn't based on it's understanding. Rather than treat this as a hard connection failure queue the new request until the job struct does free up. As the buffer isn't copied as there's no job struct, a special return value must be returned to the LLDD to signify to hold off on recycling the cmd iu buffer. And later, when a job struct is allocated and the buffer copied, a new LLDD callback is introduced to notify the LLDD and allow it to recycle it's command iu buffer. Signed-off-by: James Smart Reviewed-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig --- include/linux/nvme-fc-driver.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 6c8c5d8041b7..2591878c1d48 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -346,6 +346,11 @@ struct nvme_fc_remote_port { * indicating an FC transport Aborted status. * Entrypoint is Mandatory. * + * @defer_rcv: Called by the transport to signal the LLLD that it has + * begun processing of a previously received NVME CMD IU. The LLDD + * is now free to re-use the rcv buffer associated with the + * nvmefc_tgt_fcp_req. + * * @max_hw_queues: indicates the maximum number of hw queues the LLDD * supports for cpu affinitization. * Value is Mandatory. Must be at least 1. @@ -846,6 +851,8 @@ struct nvmet_fc_target_template { struct nvmefc_tgt_fcp_req *fcpreq); void (*fcp_req_release)(struct nvmet_fc_target_port *tgtport, struct nvmefc_tgt_fcp_req *fcpreq); + void (*defer_rcv)(struct nvmet_fc_target_port *tgtport, + struct nvmefc_tgt_fcp_req *fcpreq); u32 max_hw_queues; u16 max_sgl_segments; -- cgit v1.2.3 From bfe334924ccd9f4a53f30240c03cf2f43f5b2df1 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 2 Aug 2017 19:39:30 +0200 Subject: perf/x86: Fix RDPMC vs. mm_struct tracking Vince reported the following rdpmc() testcase failure: > Failing test case: > > fd=perf_event_open(); > addr=mmap(fd); > exec() // without closing or unmapping the event > fd=perf_event_open(); > addr=mmap(fd); > rdpmc() // GPFs due to rdpmc being disabled The problem is of course that exec() plays tricks with what is current->mm, only destroying the old mappings after having installed the new mm. Fix this confusion by passing along vma->vm_mm instead of relying on current->mm. Reported-by: Vince Weaver Tested-by: Vince Weaver Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Andy Lutomirski Cc: Arnaldo Carvalho de Melo Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: stable@vger.kernel.org Fixes: 1e0fb9ec679c ("perf: Add pmu callbacks to track event mapping and unmapping") Link: http://lkml.kernel.org/r/20170802173930.cstykcqefmqt7jau@hirez.programming.kicks-ass.net [ Minor cleanups. ] Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index a3b873fc59e4..b14095bcf4bb 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -310,8 +310,8 @@ struct pmu { * Notification that the event was mapped or unmapped. Called * in the context of the mapping task. */ - void (*event_mapped) (struct perf_event *event); /*optional*/ - void (*event_unmapped) (struct perf_event *event); /*optional*/ + void (*event_mapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ + void (*event_unmapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ /* * Flags for ->add()/->del()/ ->start()/->stop(). There are -- cgit v1.2.3 From 16af97dc5a8975371a83d9e30a64038b48f40a2d Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Thu, 10 Aug 2017 15:23:56 -0700 Subject: mm: migrate: prevent racy access to tlb_flush_pending Patch series "fixes of TLB batching races", v6. It turns out that Linux TLB batching mechanism suffers from various races. Races that are caused due to batching during reclamation were recently handled by Mel and this patch-set deals with others. The more fundamental issue is that concurrent updates of the page-tables allow for TLB flushes to be batched on one core, while another core changes the page-tables. This other core may assume a PTE change does not require a flush based on the updated PTE value, while it is unaware that TLB flushes are still pending. This behavior affects KSM (which may result in memory corruption) and MADV_FREE and MADV_DONTNEED (which may result in incorrect behavior). A proof-of-concept can easily produce the wrong behavior of MADV_DONTNEED. Memory corruption in KSM is harder to produce in practice, but was observed by hacking the kernel and adding a delay before flushing and replacing the KSM page. Finally, there is also one memory barrier missing, which may affect architectures with weak memory model. This patch (of 7): Setting and clearing mm->tlb_flush_pending can be performed by multiple threads, since mmap_sem may only be acquired for read in task_numa_work(). If this happens, tlb_flush_pending might be cleared while one of the threads still changes PTEs and batches TLB flushes. This can lead to the same race between migration and change_protection_range() that led to the introduction of tlb_flush_pending. The result of this race was data corruption, which means that this patch also addresses a theoretically possible data corruption. An actual data corruption was not observed, yet the race was was confirmed by adding assertion to check tlb_flush_pending is not set by two threads, adding artificial latency in change_protection_range() and using sysctl to reduce kernel.numa_balancing_scan_delay_ms. Link: http://lkml.kernel.org/r/20170802000818.4760-2-namit@vmware.com Fixes: 20841405940e ("mm: fix TLB flush race between migration, and change_protection_range") Signed-off-by: Nadav Amit Acked-by: Mel Gorman Acked-by: Rik van Riel Acked-by: Minchan Kim Cc: Andy Lutomirski Cc: Hugh Dickins Cc: "David S. Miller" Cc: Andrea Arcangeli Cc: Heiko Carstens Cc: Ingo Molnar Cc: Jeff Dike Cc: Martin Schwidefsky Cc: Mel Gorman Cc: Russell King Cc: Sergey Senozhatsky Cc: Tony Luck Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 31 ++++++++++++++++++++++--------- 1 file changed, 22 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7f384bb62d8e..f58f76ee1dfa 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -493,7 +493,7 @@ struct mm_struct { * can move process memory needs to flush the TLB when moving a * PROT_NONE or PROT_NUMA mapped page. */ - bool tlb_flush_pending; + atomic_t tlb_flush_pending; #endif #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* See flush_tlb_batched_pending() */ @@ -532,33 +532,46 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) static inline bool mm_tlb_flush_pending(struct mm_struct *mm) { barrier(); - return mm->tlb_flush_pending; + return atomic_read(&mm->tlb_flush_pending) > 0; } -static inline void set_tlb_flush_pending(struct mm_struct *mm) + +static inline void init_tlb_flush_pending(struct mm_struct *mm) { - mm->tlb_flush_pending = true; + atomic_set(&mm->tlb_flush_pending, 0); +} + +static inline void inc_tlb_flush_pending(struct mm_struct *mm) +{ + atomic_inc(&mm->tlb_flush_pending); /* - * Guarantee that the tlb_flush_pending store does not leak into the + * Guarantee that the tlb_flush_pending increase does not leak into the * critical section updating the page tables */ smp_mb__before_spinlock(); } + /* Clearing is done after a TLB flush, which also provides a barrier. */ -static inline void clear_tlb_flush_pending(struct mm_struct *mm) +static inline void dec_tlb_flush_pending(struct mm_struct *mm) { barrier(); - mm->tlb_flush_pending = false; + atomic_dec(&mm->tlb_flush_pending); } #else static inline bool mm_tlb_flush_pending(struct mm_struct *mm) { return false; } -static inline void set_tlb_flush_pending(struct mm_struct *mm) + +static inline void init_tlb_flush_pending(struct mm_struct *mm) { } -static inline void clear_tlb_flush_pending(struct mm_struct *mm) + +static inline void inc_tlb_flush_pending(struct mm_struct *mm) +{ +} + +static inline void dec_tlb_flush_pending(struct mm_struct *mm) { } #endif -- cgit v1.2.3 From 0a2c40487f3e4215c6ab46e7f837036badfb542b Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Thu, 10 Aug 2017 15:23:59 -0700 Subject: mm: migrate: fix barriers around tlb_flush_pending Reading tlb_flush_pending while the page-table lock is taken does not require a barrier, since the lock/unlock already acts as a barrier. Removing the barrier in mm_tlb_flush_pending() to address this issue. However, migrate_misplaced_transhuge_page() calls mm_tlb_flush_pending() while the page-table lock is already released, which may present a problem on architectures with weak memory model (PPC). To deal with this case, a new parameter is added to mm_tlb_flush_pending() to indicate if it is read without the page-table lock taken, and calling smp_mb__after_unlock_lock() in this case. Link: http://lkml.kernel.org/r/20170802000818.4760-3-namit@vmware.com Signed-off-by: Nadav Amit Acked-by: Rik van Riel Cc: Minchan Kim Cc: Sergey Senozhatsky Cc: Andy Lutomirski Cc: Mel Gorman Cc: "David S. Miller" Cc: Andrea Arcangeli Cc: Heiko Carstens Cc: Hugh Dickins Cc: Ingo Molnar Cc: Jeff Dike Cc: Martin Schwidefsky Cc: Mel Gorman Cc: Nadav Amit Cc: Russell King Cc: Tony Luck Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index f58f76ee1dfa..0e478ebd2706 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -526,12 +526,12 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) /* * Memory barriers to keep this state in sync are graciously provided by * the page table locks, outside of which no page table modifications happen. - * The barriers below prevent the compiler from re-ordering the instructions - * around the memory barriers that are already present in the code. + * The barriers are used to ensure the order between tlb_flush_pending updates, + * which happen while the lock is not taken, and the PTE updates, which happen + * while the lock is taken, are serialized. */ static inline bool mm_tlb_flush_pending(struct mm_struct *mm) { - barrier(); return atomic_read(&mm->tlb_flush_pending) > 0; } @@ -554,7 +554,13 @@ static inline void inc_tlb_flush_pending(struct mm_struct *mm) /* Clearing is done after a TLB flush, which also provides a barrier. */ static inline void dec_tlb_flush_pending(struct mm_struct *mm) { - barrier(); + /* + * Guarantee that the tlb_flush_pending does not not leak into the + * critical section, since we must order the PTE change and changes to + * the pending TLB flush indication. We could have relied on TLB flush + * as a memory barrier, but this behavior is not clearly documented. + */ + smp_mb__before_atomic(); atomic_dec(&mm->tlb_flush_pending); } #else -- cgit v1.2.3 From 56236a59556cfd3bae7bffb7e5f438b5ef0af880 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Thu, 10 Aug 2017 15:24:05 -0700 Subject: mm: refactor TLB gathering API This patch is a preparatory patch for solving race problems caused by TLB batch. For that, we will increase/decrease TLB flush pending count of mm_struct whenever tlb_[gather|finish]_mmu is called. Before making it simple, this patch separates architecture specific part and rename it to arch_tlb_[gather|finish]_mmu and generic part just calls it. It shouldn't change any behavior. Link: http://lkml.kernel.org/r/20170802000818.4760-5-namit@vmware.com Signed-off-by: Minchan Kim Signed-off-by: Nadav Amit Acked-by: Mel Gorman Cc: Ingo Molnar Cc: Russell King Cc: Tony Luck Cc: Martin Schwidefsky Cc: "David S. Miller" Cc: Heiko Carstens Cc: Yoshinori Sato Cc: Jeff Dike Cc: Andrea Arcangeli Cc: Andy Lutomirski Cc: Hugh Dickins Cc: Mel Gorman Cc: Nadav Amit Cc: Rik van Riel Cc: Sergey Senozhatsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 0e478ebd2706..c605f2a3a68e 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -522,6 +522,12 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) return mm->cpu_vm_mask_var; } +struct mmu_gather; +extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, + unsigned long start, unsigned long end); +extern void tlb_finish_mmu(struct mmu_gather *tlb, + unsigned long start, unsigned long end); + #if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION) /* * Memory barriers to keep this state in sync are graciously provided by -- cgit v1.2.3 From 0a2dd266dd6b7a31503b5bbe63af05961a6b446d Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Thu, 10 Aug 2017 15:24:09 -0700 Subject: mm: make tlb_flush_pending global Currently, tlb_flush_pending is used only for CONFIG_[NUMA_BALANCING| COMPACTION] but upcoming patches to solve subtle TLB flush batching problem will use it regardless of compaction/NUMA so this patch doesn't remove the dependency. [akpm@linux-foundation.org: remove more ifdefs from world's ugliest printk statement] Link: http://lkml.kernel.org/r/20170802000818.4760-6-namit@vmware.com Signed-off-by: Minchan Kim Signed-off-by: Nadav Amit Acked-by: Mel Gorman Cc: "David S. Miller" Cc: Andrea Arcangeli Cc: Andy Lutomirski Cc: Heiko Carstens Cc: Hugh Dickins Cc: Ingo Molnar Cc: Jeff Dike Cc: Martin Schwidefsky Cc: Mel Gorman Cc: Nadav Amit Cc: Rik van Riel Cc: Russell King Cc: Sergey Senozhatsky Cc: Tony Luck Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 21 --------------------- 1 file changed, 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index c605f2a3a68e..892a7b0196fd 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -487,14 +487,12 @@ struct mm_struct { /* numa_scan_seq prevents two threads setting pte_numa */ int numa_scan_seq; #endif -#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION) /* * An operation with batched TLB flushing is going on. Anything that * can move process memory needs to flush the TLB when moving a * PROT_NONE or PROT_NUMA mapped page. */ atomic_t tlb_flush_pending; -#endif #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* See flush_tlb_batched_pending() */ bool tlb_flush_batched; @@ -528,7 +526,6 @@ extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, extern void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end); -#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION) /* * Memory barriers to keep this state in sync are graciously provided by * the page table locks, outside of which no page table modifications happen. @@ -569,24 +566,6 @@ static inline void dec_tlb_flush_pending(struct mm_struct *mm) smp_mb__before_atomic(); atomic_dec(&mm->tlb_flush_pending); } -#else -static inline bool mm_tlb_flush_pending(struct mm_struct *mm) -{ - return false; -} - -static inline void init_tlb_flush_pending(struct mm_struct *mm) -{ -} - -static inline void inc_tlb_flush_pending(struct mm_struct *mm) -{ -} - -static inline void dec_tlb_flush_pending(struct mm_struct *mm) -{ -} -#endif struct vm_fault; -- cgit v1.2.3 From 99baac21e4585f4258f919502c6e23f1e5edc98c Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Thu, 10 Aug 2017 15:24:12 -0700 Subject: mm: fix MADV_[FREE|DONTNEED] TLB flush miss problem Nadav reported parallel MADV_DONTNEED on same range has a stale TLB problem and Mel fixed it[1] and found same problem on MADV_FREE[2]. Quote from Mel Gorman: "The race in question is CPU 0 running madv_free and updating some PTEs while CPU 1 is also running madv_free and looking at the same PTEs. CPU 1 may have writable TLB entries for a page but fail the pte_dirty check (because CPU 0 has updated it already) and potentially fail to flush. Hence, when madv_free on CPU 1 returns, there are still potentially writable TLB entries and the underlying PTE is still present so that a subsequent write does not necessarily propagate the dirty bit to the underlying PTE any more. Reclaim at some unknown time at the future may then see that the PTE is still clean and discard the page even though a write has happened in the meantime. I think this is possible but I could have missed some protection in madv_free that prevents it happening." This patch aims for solving both problems all at once and is ready for other problem with KSM, MADV_FREE and soft-dirty story[3]. TLB batch API(tlb_[gather|finish]_mmu] uses [inc|dec]_tlb_flush_pending and mmu_tlb_flush_pending so that when tlb_finish_mmu is called, we can catch there are parallel threads going on. In that case, forcefully, flush TLB to prevent for user to access memory via stale TLB entry although it fail to gather page table entry. I confirmed this patch works with [4] test program Nadav gave so this patch supersedes "mm: Always flush VMA ranges affected by zap_page_range v2" in current mmotm. NOTE: This patch modifies arch-specific TLB gathering interface(x86, ia64, s390, sh, um). It seems most of architecture are straightforward but s390 need to be careful because tlb_flush_mmu works only if mm->context.flush_mm is set to non-zero which happens only a pte entry really is cleared by ptep_get_and_clear and friends. However, this problem never changes the pte entries but need to flush to prevent memory access from stale tlb. [1] http://lkml.kernel.org/r/20170725101230.5v7gvnjmcnkzzql3@techsingularity.net [2] http://lkml.kernel.org/r/20170725100722.2dxnmgypmwnrfawp@suse.de [3] http://lkml.kernel.org/r/BD3A0EBE-ECF4-41D4-87FA-C755EA9AB6BD@gmail.com [4] https://patchwork.kernel.org/patch/9861621/ [minchan@kernel.org: decrease tlb flush pending count in tlb_finish_mmu] Link: http://lkml.kernel.org/r/20170808080821.GA31730@bbox Link: http://lkml.kernel.org/r/20170802000818.4760-7-namit@vmware.com Signed-off-by: Minchan Kim Signed-off-by: Nadav Amit Reported-by: Nadav Amit Reported-by: Mel Gorman Acked-by: Mel Gorman Cc: Ingo Molnar Cc: Russell King Cc: Tony Luck Cc: Martin Schwidefsky Cc: "David S. Miller" Cc: Heiko Carstens Cc: Yoshinori Sato Cc: Jeff Dike Cc: Andrea Arcangeli Cc: Andy Lutomirski Cc: Hugh Dickins Cc: Mel Gorman Cc: Nadav Amit Cc: Rik van Riel Cc: Sergey Senozhatsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 892a7b0196fd..3cadee0a3508 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -538,6 +538,14 @@ static inline bool mm_tlb_flush_pending(struct mm_struct *mm) return atomic_read(&mm->tlb_flush_pending) > 0; } +/* + * Returns true if there are two above TLB batching threads in parallel. + */ +static inline bool mm_tlb_flush_nested(struct mm_struct *mm) +{ + return atomic_read(&mm->tlb_flush_pending) > 1; +} + static inline void init_tlb_flush_pending(struct mm_struct *mm) { atomic_set(&mm->tlb_flush_pending, 0); -- cgit v1.2.3 From a99b646afa8a02571ea298bedca6592d818229cd Mon Sep 17 00:00:00 2001 From: dingtianhong Date: Tue, 15 Aug 2017 11:23:23 +0800 Subject: PCI: Disable PCIe Relaxed Ordering if unsupported When bit4 is set in the PCIe Device Control register, it indicates whether the device is permitted to use relaxed ordering. On some platforms using relaxed ordering can have performance issues or due to erratum can cause data-corruption. In such cases devices must avoid using relaxed ordering. The patch adds a new flag PCI_DEV_FLAGS_NO_RELAXED_ORDERING to indicate that Relaxed Ordering (RO) attribute should not be used for Transaction Layer Packets (TLP) targeted towards these affected root complexes. This patch checks if there is any node in the hierarchy that indicates that using relaxed ordering is not safe. In such cases the patch turns off the relaxed ordering by clearing the capability for this device. Signed-off-by: Casey Leedom Signed-off-by: Ding Tianhong Acked-by: Ashok Raj Acked-by: Alexander Duyck Acked-by: Casey Leedom Signed-off-by: David S. Miller --- include/linux/pci.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 4869e66dd659..29606fb89464 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -188,6 +188,8 @@ enum pci_dev_flags { * the direct_complete optimization. */ PCI_DEV_FLAGS_NEEDS_RESUME = (__force pci_dev_flags_t) (1 << 11), + /* Don't use Relaxed Ordering for TLPs directed at this device */ + PCI_DEV_FLAGS_NO_RELAXED_ORDERING = (__force pci_dev_flags_t) (1 << 12), }; enum pci_irq_reroute_variant { @@ -1125,6 +1127,7 @@ bool pci_check_pme_status(struct pci_dev *dev); void pci_pme_wakeup_bus(struct pci_bus *bus); void pci_d3cold_enable(struct pci_dev *dev); void pci_d3cold_disable(struct pci_dev *dev); +bool pcie_relaxed_ordering_enabled(struct pci_dev *dev); /* PCI Virtual Channel */ int pci_save_vc_state(struct pci_dev *dev); -- cgit v1.2.3 From b3dc8f772fab5b2d284b780830fd56494491e493 Mon Sep 17 00:00:00 2001 From: Tonghao Zhang Date: Tue, 15 Aug 2017 04:28:54 -0700 Subject: net: Fix a typo in comment about sock flags. Signed-off-by: Tonghao Zhang Signed-off-by: David S. Miller --- include/linux/net.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index dda2cc939a53..ebeb48c92005 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -37,7 +37,7 @@ struct net; /* Historically, SOCKWQ_ASYNC_NOSPACE & SOCKWQ_ASYNC_WAITDATA were located * in sock->flags, but moved into sk->sk_wq->flags to be RCU protected. - * Eventually all flags will be in sk->sk_wq_flags. + * Eventually all flags will be in sk->sk_wq->flags. */ #define SOCKWQ_ASYNC_NOSPACE 0 #define SOCKWQ_ASYNC_WAITDATA 1 -- cgit v1.2.3 From c8c03f1858331e85d397bacccd34ef409aae993c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 16 Aug 2017 17:08:07 -0700 Subject: pty: fix the cached path of the pty slave file descriptor in the master Christian Brauner reported that if you use the TIOCGPTPEER ioctl() to get a slave pty file descriptor, the resulting file descriptor doesn't look right in /proc//fd/. In particular, he wanted to use readlink() on /proc/self/fd/ to get the pathname of the slave pty (basically implementing "ptsname{_r}()"). The reason for that was that we had generated the wrong 'struct path' when we create the pty in ptmx_open(). In particular, the dentry was correct, but the vfsmount pointed to the mount of the ptmx node. That _can_ be correct - in case you use "/dev/pts/ptmx" to open the master - but usually is not. The normal case is to use /dev/ptmx, which then looks up the pts/ directory, and then the vfsmount of the ptmx node is obviously the /dev directory, not the /dev/pts/ directory. We actually did have the right vfsmount available, but in the wrong place (it gets looked up in 'devpts_acquire()' when we get a reference to the pts filesystem), and so ptmx_open() used the wrong mnt pointer. The end result of this confusion was that the pty worked fine, but when if you did TIOCGPTPEER to get the slave side of the pty, end end result would also work, but have that dodgy 'struct path'. And then when doing "d_path()" on to get the pathname, the vfsmount would not match the root of the pts directory, and d_path() would return an empty pathname thinking that the entry had escaped a bind mount into another mount. This fixes the problem by making devpts_acquire() return the vfsmount for the pts filesystem, allowing ptmx_open() to trivially just use the right mount for the pts dentry, and create the proper 'struct path'. Reported-by: Christian Brauner Cc: Al Viro Acked-by: Eric Biederman Signed-off-by: Linus Torvalds --- include/linux/devpts_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h index 277ab9af9ac2..7883e901f65c 100644 --- a/include/linux/devpts_fs.h +++ b/include/linux/devpts_fs.h @@ -19,7 +19,7 @@ struct pts_fs_info; -struct pts_fs_info *devpts_acquire(struct file *); +struct pts_fs_info *devpts_acquire(struct file *, struct vfsmount **ptsmnt); void devpts_release(struct pts_fs_info *); int devpts_new_index(struct pts_fs_info *); -- cgit v1.2.3 From 7edaeb6841dfb27e362288ab8466ebdc4972e867 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 15 Aug 2017 09:50:13 +0200 Subject: kernel/watchdog: Prevent false positives with turbo modes The hardlockup detector on x86 uses a performance counter based on unhalted CPU cycles and a periodic hrtimer. The hrtimer period is about 2/5 of the performance counter period, so the hrtimer should fire 2-3 times before the performance counter NMI fires. The NMI code checks whether the hrtimer fired since the last invocation. If not, it assumess a hard lockup. The calculation of those periods is based on the nominal CPU frequency. Turbo modes increase the CPU clock frequency and therefore shorten the period of the perf/NMI watchdog. With extreme Turbo-modes (3x nominal frequency) the perf/NMI period is shorter than the hrtimer period which leads to false positives. A simple fix would be to shorten the hrtimer period, but that comes with the side effect of more frequent hrtimer and softlockup thread wakeups, which is not desired. Implement a low pass filter, which checks the perf/NMI period against kernel time. If the perf/NMI fires before 4/5 of the watchdog period has elapsed then the event is ignored and postponed to the next perf/NMI. That solves the problem and avoids the overhead of shorter hrtimer periods and more frequent softlockup thread wakeups. Fixes: 58687acba592 ("lockup_detector: Combine nmi_watchdog and softlockup detector") Reported-and-tested-by: Kan Liang Signed-off-by: Thomas Gleixner Cc: dzickus@redhat.com Cc: prarit@redhat.com Cc: ak@linux.intel.com Cc: babu.moger@oracle.com Cc: peterz@infradead.org Cc: eranian@google.com Cc: acme@redhat.com Cc: stable@vger.kernel.org Cc: atomlin@redhat.com Cc: akpm@linux-foundation.org Cc: torvalds@linux-foundation.org Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1708150931310.1886@nanos --- include/linux/nmi.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 8aa01fd859fb..a36abe2da13e 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -168,6 +168,14 @@ extern int sysctl_hardlockup_all_cpu_backtrace; #define sysctl_softlockup_all_cpu_backtrace 0 #define sysctl_hardlockup_all_cpu_backtrace 0 #endif + +#if defined(CONFIG_HARDLOCKUP_CHECK_TIMESTAMP) && \ + defined(CONFIG_HARDLOCKUP_DETECTOR) +void watchdog_update_hrtimer_threshold(u64 period); +#else +static inline void watchdog_update_hrtimer_threshold(u64 period) { } +#endif + extern bool is_hardlockup(void); struct ctl_table; extern int proc_watchdog(struct ctl_table *, int , -- cgit v1.2.3 From 739f79fc9db1b38f96b5a5109b247a650fbebf6d Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 18 Aug 2017 15:15:48 -0700 Subject: mm: memcontrol: fix NULL pointer crash in test_clear_page_writeback() Jaegeuk and Brad report a NULL pointer crash when writeback ending tries to update the memcg stats: BUG: unable to handle kernel NULL pointer dereference at 00000000000003b0 IP: test_clear_page_writeback+0x12e/0x2c0 [...] RIP: 0010:test_clear_page_writeback+0x12e/0x2c0 Call Trace: end_page_writeback+0x47/0x70 f2fs_write_end_io+0x76/0x180 [f2fs] bio_endio+0x9f/0x120 blk_update_request+0xa8/0x2f0 scsi_end_request+0x39/0x1d0 scsi_io_completion+0x211/0x690 scsi_finish_command+0xd9/0x120 scsi_softirq_done+0x127/0x150 __blk_mq_complete_request_remote+0x13/0x20 flush_smp_call_function_queue+0x56/0x110 generic_smp_call_function_single_interrupt+0x13/0x30 smp_call_function_single_interrupt+0x27/0x40 call_function_single_interrupt+0x89/0x90 RIP: 0010:native_safe_halt+0x6/0x10 (gdb) l *(test_clear_page_writeback+0x12e) 0xffffffff811bae3e is in test_clear_page_writeback (./include/linux/memcontrol.h:619). 614 mod_node_page_state(page_pgdat(page), idx, val); 615 if (mem_cgroup_disabled() || !page->mem_cgroup) 616 return; 617 mod_memcg_state(page->mem_cgroup, idx, val); 618 pn = page->mem_cgroup->nodeinfo[page_to_nid(page)]; 619 this_cpu_add(pn->lruvec_stat->count[idx], val); 620 } 621 622 unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, 623 gfp_t gfp_mask, The issue is that writeback doesn't hold a page reference and the page might get freed after PG_writeback is cleared (and the mapping is unlocked) in test_clear_page_writeback(). The stat functions looking up the page's node or zone are safe, as those attributes are static across allocation and free cycles. But page->mem_cgroup is not, and it will get cleared if we race with truncation or migration. It appears this race window has been around for a while, but less likely to trigger when the memcg stats were updated first thing after PG_writeback is cleared. Recent changes reshuffled this code to update the global node stats before the memcg ones, though, stretching the race window out to an extent where people can reproduce the problem. Update test_clear_page_writeback() to look up and pin page->mem_cgroup before clearing PG_writeback, then not use that pointer afterward. It is a partial revert of 62cccb8c8e7a ("mm: simplify lock_page_memcg()") but leaves the pageref-holding callsites that aren't affected alone. Link: http://lkml.kernel.org/r/20170809183825.GA26387@cmpxchg.org Fixes: 62cccb8c8e7a ("mm: simplify lock_page_memcg()") Signed-off-by: Johannes Weiner Reported-by: Jaegeuk Kim Tested-by: Jaegeuk Kim Reported-by: Bradley Bolen Tested-by: Brad Bolen Cc: Vladimir Davydov Cc: Michal Hocko Cc: [4.6+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 3914e3dd6168..9b15a4bcfa77 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -484,7 +484,8 @@ bool mem_cgroup_oom_synchronize(bool wait); extern int do_swap_account; #endif -void lock_page_memcg(struct page *page); +struct mem_cgroup *lock_page_memcg(struct page *page); +void __unlock_page_memcg(struct mem_cgroup *memcg); void unlock_page_memcg(struct page *page); static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, @@ -809,7 +810,12 @@ mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) { } -static inline void lock_page_memcg(struct page *page) +static inline struct mem_cgroup *lock_page_memcg(struct page *page) +{ + return NULL; +} + +static inline void __unlock_page_memcg(struct mem_cgroup *memcg) { } -- cgit v1.2.3 From 8ada92799ec4de00f4bc0f10b1ededa256c1ab22 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Fri, 18 Aug 2017 15:15:55 -0700 Subject: wait: add wait_event_killable_timeout() These are the few pending fixes I have queued up for v4.13-final. One is a a generic regression fix for recursive loops on kmod and the other one is a trivial print out correction. During the v4.13 development we assumed that recursive kmod loops were no longer possible. Clearly that is not true. The regression fix makes use of a new killable wait. We use a killable wait to be paranoid in how signals might be sent to modprobe and only accept a proper SIGKILL. The signal will only be available to userspace to issue *iff* a thread has already entered a wait state, and that happens only if we've already throttled after 50 kmod threads have been hit. Note that although it may seem excessive to trigger a failure afer 5 seconds if all kmod thread remain busy, prior to the series of changes that went into v4.13 we would actually *always* fatally fail any request which came in if the limit was already reached. The new waiting implemented in v4.13 actually gives us *more* breathing room -- the wait for 5 seconds is a wait for *any* kmod thread to finish. We give up and fail *iff* no kmod thread has finished and they're *all* running straight for 5 consecutive seconds. If 50 kmod threads are running consecutively for 5 seconds something else must be really bad. Recursive loops with kmod are bad but they're also hard to implement properly as a selftest without currently fooling current userspace tools like kmod [1]. For instance kmod will complain when you run depmod if it finds a recursive loop with symbol dependency between modules as such this type of recursive loop cannot go upstream as the modules_install target will fail after running depmod. These tests already exist on userspace kmod upstream though (refer to the testsuite/module-playground/mod-loop-*.c files). The same is not true if request_module() is used though, or worst if aliases are used. Likewise the issue with 64-bit kernels booting 32-bit userspace without a binfmt handler built-in is also currently not detected and proactively avoided by userspace kmod tools, or kconfig for all architectures. Although we could complain in the kernel when some of these individual recursive issues creep up, proactively avoiding these situations in userspace at build time is what we should keep striving for. Lastly, since recursive loops could happen with kmod it may mean recursive loops may also be possible with other kernel usermode helpers, this should be investigated and long term if we can come up with a more sensible generic solution even better! [0] https://git.kernel.org/pub/scm/linux/kernel/git/mcgrof/linux.git/log/?h=20170809-kmod-for-v4.13-final [1] https://git.kernel.org/pub/scm/utils/kernel/kmod/kmod.git This patch (of 3): This wait is similar to wait_event_interruptible_timeout() but only accepts SIGKILL interrupt signal. Other signals are ignored. Link: http://lkml.kernel.org/r/20170809234635.13443-2-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez Acked-by: Peter Zijlstra (Intel) Cc: Ingo Molnar Cc: Kees Cook Cc: Dmitry Torokhov Cc: Jessica Yu Cc: Rusty Russell Cc: Michal Marek Cc: Petr Mladek Cc: Miroslav Benes Cc: Josh Poimboeuf Cc: "Eric W. Biederman" Cc: Shuah Khan Cc: Matt Redfearn Cc: Dan Carpenter Cc: Colin Ian King Cc: Daniel Mentz Cc: David Binderman Cc: Matt Redfearn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/wait.h | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index 5b74e36c0ca8..dc19880c02f5 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -757,6 +757,43 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_entry_t *); __ret; \ }) +#define __wait_event_killable_timeout(wq_head, condition, timeout) \ + ___wait_event(wq_head, ___wait_cond_timeout(condition), \ + TASK_KILLABLE, 0, timeout, \ + __ret = schedule_timeout(__ret)) + +/** + * wait_event_killable_timeout - sleep until a condition gets true or a timeout elapses + * @wq_head: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * @timeout: timeout, in jiffies + * + * The process is put to sleep (TASK_KILLABLE) until the + * @condition evaluates to true or a kill signal is received. + * The @condition is checked each time the waitqueue @wq_head is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + * + * Returns: + * 0 if the @condition evaluated to %false after the @timeout elapsed, + * 1 if the @condition evaluated to %true after the @timeout elapsed, + * the remaining jiffies (at least 1) if the @condition evaluated + * to %true before the @timeout elapsed, or -%ERESTARTSYS if it was + * interrupted by a kill signal. + * + * Only kill signals interrupt this process. + */ +#define wait_event_killable_timeout(wq_head, condition, timeout) \ +({ \ + long __ret = timeout; \ + might_sleep(); \ + if (!___wait_cond_timeout(condition)) \ + __ret = __wait_event_killable_timeout(wq_head, \ + condition, timeout); \ + __ret; \ +}) + #define __wait_event_lock_irq(wq_head, condition, lock, cmd) \ (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ -- cgit v1.2.3 From 3010f876500f9ba921afaeccec30c45ca6584dc8 Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Fri, 18 Aug 2017 15:16:05 -0700 Subject: mm: discard memblock data later There is existing use after free bug when deferred struct pages are enabled: The memblock_add() allocates memory for the memory array if more than 128 entries are needed. See comment in e820__memblock_setup(): * The bootstrap memblock region count maximum is 128 entries * (INIT_MEMBLOCK_REGIONS), but EFI might pass us more E820 entries * than that - so allow memblock resizing. This memblock memory is freed here: free_low_memory_core_early() We access the freed memblock.memory later in boot when deferred pages are initialized in this path: deferred_init_memmap() for_each_mem_pfn_range() __next_mem_pfn_range() type = &memblock.memory; One possible explanation for why this use-after-free hasn't been hit before is that the limit of INIT_MEMBLOCK_REGIONS has never been exceeded at least on systems where deferred struct pages were enabled. Tested by reducing INIT_MEMBLOCK_REGIONS down to 4 from the current 128, and verifying in qemu that this code is getting excuted and that the freed pages are sane. Link: http://lkml.kernel.org/r/1502485554-318703-2-git-send-email-pasha.tatashin@oracle.com Fixes: 7e18adb4f80b ("mm: meminit: initialise remaining struct pages in parallel with kswapd") Signed-off-by: Pavel Tatashin Reviewed-by: Steven Sistare Reviewed-by: Daniel Jordan Reviewed-by: Bob Picco Acked-by: Michal Hocko Cc: Mel Gorman Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 77d427974f57..bae11c7e7bf3 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -61,6 +61,7 @@ extern int memblock_debug; #ifdef CONFIG_ARCH_DISCARD_MEMBLOCK #define __init_memblock __meminit #define __initdata_memblock __meminitdata +void memblock_discard(void); #else #define __init_memblock #define __initdata_memblock @@ -74,8 +75,6 @@ phys_addr_t memblock_find_in_range_node(phys_addr_t size, phys_addr_t align, int nid, ulong flags); phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align); -phys_addr_t get_allocated_memblock_reserved_regions_info(phys_addr_t *addr); -phys_addr_t get_allocated_memblock_memory_regions_info(phys_addr_t *addr); void memblock_allow_resize(void); int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid); int memblock_add(phys_addr_t base, phys_addr_t size); @@ -110,6 +109,9 @@ void __next_mem_range_rev(u64 *idx, int nid, ulong flags, void __next_reserved_mem_region(u64 *idx, phys_addr_t *out_start, phys_addr_t *out_end); +void __memblock_free_early(phys_addr_t base, phys_addr_t size); +void __memblock_free_late(phys_addr_t base, phys_addr_t size); + /** * for_each_mem_range - iterate through memblock areas from type_a and not * included in type_b. Or just type_a if type_b is NULL. -- cgit v1.2.3 From 6b31d5955cb29a51c5baffee382f213d75e98fb8 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 18 Aug 2017 15:16:15 -0700 Subject: mm, oom: fix potential data corruption when oom_reaper races with writer Wenwei Tao has noticed that our current assumption that the oom victim is dying and never doing any visible changes after it dies, and so the oom_reaper can tear it down, is not entirely true. __task_will_free_mem consider a task dying when SIGNAL_GROUP_EXIT is set but do_group_exit sends SIGKILL to all threads _after_ the flag is set. So there is a race window when some threads won't have fatal_signal_pending while the oom_reaper could start unmapping the address space. Moreover some paths might not check for fatal signals before each PF/g-u-p/copy_from_user. We already have a protection for oom_reaper vs. PF races by checking MMF_UNSTABLE. This has been, however, checked only for kernel threads (use_mm users) which can outlive the oom victim. A simple fix would be to extend the current check in handle_mm_fault for all tasks but that wouldn't be sufficient because the current check assumes that a kernel thread would bail out after EFAULT from get_user*/copy_from_user and never re-read the same address which would succeed because the PF path has established page tables already. This seems to be the case for the only existing use_mm user currently (virtio driver) but it is rather fragile in general. This is even more fragile in general for more complex paths such as generic_perform_write which can re-read the same address more times (e.g. iov_iter_copy_from_user_atomic to fail and then iov_iter_fault_in_readable on retry). Therefore we have to implement MMF_UNSTABLE protection in a robust way and never make a potentially corrupted content visible. That requires to hook deeper into the PF path and check for the flag _every time_ before a pte for anonymous memory is established (that means all !VM_SHARED mappings). The corruption can be triggered artificially (http://lkml.kernel.org/r/201708040646.v746kkhC024636@www262.sakura.ne.jp) but there doesn't seem to be any real life bug report. The race window should be quite tight to trigger most of the time. Link: http://lkml.kernel.org/r/20170807113839.16695-3-mhocko@kernel.org Fixes: aac453635549 ("mm, oom: introduce oom reaper") Signed-off-by: Michal Hocko Reported-by: Wenwei Tao Tested-by: Tetsuo Handa Cc: "Kirill A. Shutemov" Cc: Andrea Argangeli Cc: David Rientjes Cc: Oleg Nesterov Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/oom.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/oom.h b/include/linux/oom.h index 8a266e2be5a6..76aac4ce39bc 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -6,6 +6,8 @@ #include #include #include +#include /* MMF_* */ +#include /* VM_FAULT* */ struct zonelist; struct notifier_block; @@ -63,6 +65,26 @@ static inline bool tsk_is_oom_victim(struct task_struct * tsk) return tsk->signal->oom_mm; } +/* + * Checks whether a page fault on the given mm is still reliable. + * This is no longer true if the oom reaper started to reap the + * address space which is reflected by MMF_UNSTABLE flag set in + * the mm. At that moment any !shared mapping would lose the content + * and could cause a memory corruption (zero pages instead of the + * original content). + * + * User should call this before establishing a page table entry for + * a !shared mapping and under the proper page table lock. + * + * Return 0 when the PF is safe VM_FAULT_SIGBUS otherwise. + */ +static inline int check_stable_address_space(struct mm_struct *mm) +{ + if (unlikely(test_bit(MMF_UNSTABLE, &mm->flags))) + return VM_FAULT_SIGBUS; + return 0; +} + extern unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, const nodemask_t *nodemask, unsigned long totalpages); -- cgit v1.2.3