From 6ecec74520d8a357726e6c12f99080dbe7b347dd Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 26 Sep 2012 12:49:27 -0600 Subject: NVMe: Define SMART log This data structure is defined in the NVMe specification. It's not used by the kernel, but is available for use by userspace software. Signed-off-by: Keith Busch Signed-off-by: Matthew Wilcox --- include/linux/nvme.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index c25cccaa555a..4fa3b0b9b071 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -137,6 +137,34 @@ enum { NVME_LBAF_RP_DEGRADED = 3, }; +struct nvme_smart_log { + __u8 critical_warning; + __u8 temperature[2]; + __u8 avail_spare; + __u8 spare_thresh; + __u8 percent_used; + __u8 rsvd6[26]; + __u8 data_units_read[16]; + __u8 data_units_written[16]; + __u8 host_reads[16]; + __u8 host_writes[16]; + __u8 ctrl_busy_time[16]; + __u8 power_cycles[16]; + __u8 power_on_hours[16]; + __u8 unsafe_shutdowns[16]; + __u8 media_errors[16]; + __u8 num_err_log_entries[16]; + __u8 rsvd192[320]; +}; + +enum { + NVME_SMART_CRIT_SPARE = 1 << 0, + NVME_SMART_CRIT_TEMPERATURE = 1 << 1, + NVME_SMART_CRIT_RELIABILITY = 1 << 2, + NVME_SMART_CRIT_MEDIA = 1 << 3, + NVME_SMART_CRIT_VOLATILE_MEMORY = 1 << 4, +}; + struct nvme_lba_range_type { __u8 type; __u8 attributes; -- cgit v1.2.3 From 5a4d729139b4e94f670288a3505657311f95c886 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Fri, 1 Mar 2013 15:57:00 +0000 Subject: iio: Fix build error seen if IIO_TRIGGER is defined but IIO_BUFFER is not MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If CONFIG_IIO_TRIGGER is defined but CONFIG_IIO_BUFFER is not, the following build error is seen. drivers/iio/common/st_sensors/st_sensors_trigger.c:21:5: error: redefinition of ‘st_sensors_allocate_trigger’ In file included from drivers/iio/common/st_sensors/st_sensors_trigger.c:18:0: include/linux/iio/common/st_sensors.h:239:19: note: previous definition of ‘st_sensors_allocate_trigger’ was here drivers/iio/common/st_sensors/st_sensors_trigger.c:65:6: error: redefinition of ‘st_sensors_deallocate_trigger’ In file included from drivers/iio/common/st_sensors/st_sensors_trigger.c:18:0: include/linux/iio/common/st_sensors.h:244:20: note: previous definition of ‘st_sensors_deallocate_trigger’ was here This occurs because st_sensors_deallocate_trigger is built if CONFIG_IIO_TRIGGER is defined, but the dummy function is compiled if CONFIG_IIO_BUFFER is defined. Signed-off-by: Guenter Roeck Acked-by: Denis Ciocca Signed-off-by: Jonathan Cameron --- include/linux/iio/common/st_sensors.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index 1f86a97ab2e2..8bd12be0b02f 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -227,14 +227,17 @@ struct st_sensor_data { }; #ifdef CONFIG_IIO_BUFFER +irqreturn_t st_sensors_trigger_handler(int irq, void *p); + +int st_sensors_get_buffer_element(struct iio_dev *indio_dev, u8 *buf); +#endif + +#ifdef CONFIG_IIO_TRIGGER int st_sensors_allocate_trigger(struct iio_dev *indio_dev, const struct iio_trigger_ops *trigger_ops); void st_sensors_deallocate_trigger(struct iio_dev *indio_dev); -irqreturn_t st_sensors_trigger_handler(int irq, void *p); - -int st_sensors_get_buffer_element(struct iio_dev *indio_dev, u8 *buf); #else static inline int st_sensors_allocate_trigger(struct iio_dev *indio_dev, const struct iio_trigger_ops *trigger_ops) -- cgit v1.2.3 From 43febb27dcdaf9a15e2f362a6d09b0f191c4dcea Mon Sep 17 00:00:00 2001 From: Nishanth Menon Date: Mon, 4 Mar 2013 16:52:38 -0600 Subject: usb: gadget: composite: fix kernel-doc warnings A few trivial fixes for composite driver: Warning(include/linux/usb/composite.h:165): No description found for parameter 'fs_descriptors' Warning(include/linux/usb/composite.h:165): Excess struct/union/enum/typedef member 'descriptors' description in 'usb_function' Warning(include/linux/usb/composite.h:321): No description found for parameter 'gadget_driver' Warning(drivers/usb/gadget/composite.c:1777): Excess function parameter 'bind' description in 'usb_composite_probe' Cc: Greg Kroah-Hartman Cc: Jiri Kosina Cc: linux-usb@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Nishanth Menon Signed-off-by: Felipe Balbi --- include/linux/usb/composite.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 3c671c1b37f6..8860594d6364 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -60,7 +60,7 @@ struct usb_configuration; * @name: For diagnostics, identifies the function. * @strings: tables of strings, keyed by identifiers assigned during bind() * and by language IDs provided in control requests - * @descriptors: Table of full (or low) speed descriptors, using interface and + * @fs_descriptors: Table of full (or low) speed descriptors, using interface and * string identifiers assigned during @bind(). If this pointer is null, * the function will not be available at full speed (or at low speed). * @hs_descriptors: Table of high speed descriptors, using interface and @@ -290,6 +290,7 @@ enum { * after function notifications * @resume: Notifies configuration when the host restarts USB traffic, * before function notifications + * @gadget_driver: Gadget driver controlling this driver * * Devices default to reporting self powered operation. Devices which rely * on bus powered operation should report this in their @bind method. -- cgit v1.2.3 From df545d1cd01aab3ba3f687d5423e6c3687b069d8 Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Fri, 1 Mar 2013 20:13:46 +0530 Subject: mfd: palmas: Provide irq flags through DT/platform data Currently driver sets the irq type to IRQF_TRIGGER_LOW which is causing interrupt registration failure in ARM based SoCs as: [ 0.208479] genirq: Setting trigger mode 8 for irq 118 failed (gic_set_type+0x0/0xf0) [ 0.208513] dummy 0-0059: Failed to request IRQ 118: -22 Provide the irq flags through platform data if device is registered through board file or get the irq type from DT node property in place of hardcoding the irq flag in driver to support multiple platforms. Also configure the device to generate the interrupt signal according to flag type. Signed-off-by: Laxman Dewangan Signed-off-by: Samuel Ortiz --- include/linux/mfd/palmas.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index a4d13d7cd001..3bbda22721ea 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -221,6 +221,7 @@ struct palmas_clk_platform_data { }; struct palmas_platform_data { + int irq_flags; int gpio_base; /* bit value to be loaded to the POWER_CTRL register */ -- cgit v1.2.3 From 80e4e6716e43500c5c7d4ff4f73fc1b56f024083 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Sat, 2 Mar 2013 15:25:50 +0800 Subject: mfd: tps65912: Declare and use tps65912_irq_exit() Clean up interrupts on exit, silencing a sparse warning caused by tps65912_irq_exit() being defined but not prototyped as we go. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/tps65912.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/tps65912.h b/include/linux/mfd/tps65912.h index aaceab402ec5..6d309032dc0d 100644 --- a/include/linux/mfd/tps65912.h +++ b/include/linux/mfd/tps65912.h @@ -323,5 +323,6 @@ int tps65912_device_init(struct tps65912 *tps65912); void tps65912_device_exit(struct tps65912 *tps65912); int tps65912_irq_init(struct tps65912 *tps65912, int irq, struct tps65912_platform_data *pdata); +int tps65912_irq_exit(struct tps65912 *tps65912); #endif /* __LINUX_MFD_TPS65912_H */ -- cgit v1.2.3 From fd860195a4f9d661754345bd06a3adb30d12d882 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 8 Mar 2013 10:47:21 +0800 Subject: mfd: wm831x: Don't forward declare enum wm831x_auxadc We can't forward declare enums. Signed-off-by: Andrew Morton Signed-off-by: Samuel Ortiz --- include/linux/mfd/wm831x/auxadc.h | 2 ++ include/linux/mfd/wm831x/core.h | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/wm831x/auxadc.h b/include/linux/mfd/wm831x/auxadc.h index b132067e9e99..867aa23f9370 100644 --- a/include/linux/mfd/wm831x/auxadc.h +++ b/include/linux/mfd/wm831x/auxadc.h @@ -15,6 +15,8 @@ #ifndef __MFD_WM831X_AUXADC_H__ #define __MFD_WM831X_AUXADC_H__ +struct wm831x; + /* * R16429 (0x402D) - AuxADC Data */ diff --git a/include/linux/mfd/wm831x/core.h b/include/linux/mfd/wm831x/core.h index 4a3b83a77614..76c22648436f 100644 --- a/include/linux/mfd/wm831x/core.h +++ b/include/linux/mfd/wm831x/core.h @@ -20,6 +20,7 @@ #include #include #include +#include /* * Register values. @@ -355,7 +356,6 @@ enum wm831x_parent { }; struct wm831x; -enum wm831x_auxadc; typedef int (*wm831x_auxadc_read_fn)(struct wm831x *wm831x, enum wm831x_auxadc input); -- cgit v1.2.3 From 5857f70c8a62377c2304d8ad27e579881728fc5a Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 4 Mar 2013 14:32:54 -0800 Subject: idr: fix new kernel-doc warnings Fix new kernel-doc warnings in idr: Warning(include/linux/idr.h:113): No description found for parameter 'idr' Warning(include/linux/idr.h:113): Excess function parameter 'idp' description in 'idr_find' Warning(lib/idr.c:232): Excess function parameter 'id' description in 'sub_alloc' Warning(lib/idr.c:232): Excess function parameter 'id' description in 'sub_alloc' Signed-off-by: Randy Dunlap Acked-by: Tejun Heo Signed-off-by: Linus Torvalds --- include/linux/idr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index a6f38b5c34e4..8c1f81f823c8 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -99,7 +99,7 @@ static inline void idr_preload_end(void) /** * idr_find - return pointer for given id - * @idp: idr handle + * @idr: idr handle * @id: lookup key * * Return the pointer given the id it has been registered with. A %NULL -- cgit v1.2.3 From 0ec83bd2460ed6aed0e7f29f9e0633b054621c02 Mon Sep 17 00:00:00 2001 From: Chanwoo Choi Date: Wed, 13 Mar 2013 17:38:57 +0900 Subject: extcon: max77693: Initialize register of MUIC device to bring up it without platform data This patch set default value of MUIC register to bring up MUIC device. If user don't set some initial value for MUIC device through platform data, extcon-max77693 driver use 'default_init_data' to bring up base operation of MAX77693 MUIC device. Signed-off-by: Chanwoo Choi Signed-off-by: Myungjoo Ham --- include/linux/mfd/max77693-private.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/max77693-private.h b/include/linux/mfd/max77693-private.h index 5b18ecde69b5..1aa4f13cdfa6 100644 --- a/include/linux/mfd/max77693-private.h +++ b/include/linux/mfd/max77693-private.h @@ -106,6 +106,29 @@ enum max77693_muic_reg { MAX77693_MUIC_REG_END, }; +/* MAX77693 INTMASK1~2 Register */ +#define INTMASK1_ADC1K_SHIFT 3 +#define INTMASK1_ADCERR_SHIFT 2 +#define INTMASK1_ADCLOW_SHIFT 1 +#define INTMASK1_ADC_SHIFT 0 +#define INTMASK1_ADC1K_MASK (1 << INTMASK1_ADC1K_SHIFT) +#define INTMASK1_ADCERR_MASK (1 << INTMASK1_ADCERR_SHIFT) +#define INTMASK1_ADCLOW_MASK (1 << INTMASK1_ADCLOW_SHIFT) +#define INTMASK1_ADC_MASK (1 << INTMASK1_ADC_SHIFT) + +#define INTMASK2_VIDRM_SHIFT 5 +#define INTMASK2_VBVOLT_SHIFT 4 +#define INTMASK2_DXOVP_SHIFT 3 +#define INTMASK2_DCDTMR_SHIFT 2 +#define INTMASK2_CHGDETRUN_SHIFT 1 +#define INTMASK2_CHGTYP_SHIFT 0 +#define INTMASK2_VIDRM_MASK (1 << INTMASK2_VIDRM_SHIFT) +#define INTMASK2_VBVOLT_MASK (1 << INTMASK2_VBVOLT_SHIFT) +#define INTMASK2_DXOVP_MASK (1 << INTMASK2_DXOVP_SHIFT) +#define INTMASK2_DCDTMR_MASK (1 << INTMASK2_DCDTMR_SHIFT) +#define INTMASK2_CHGDETRUN_MASK (1 << INTMASK2_CHGDETRUN_SHIFT) +#define INTMASK2_CHGTYP_MASK (1 << INTMASK2_CHGTYP_SHIFT) + /* MAX77693 MUIC - STATUS1~3 Register */ #define STATUS1_ADC_SHIFT (0) #define STATUS1_ADCLOW_SHIFT (5) -- cgit v1.2.3 From ebf47beb660e5580df7bee06d5cf9d37c0f22fac Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 13 Mar 2013 14:59:30 -0700 Subject: include/linux/res_counter.h needs errno.h alpha allmodconfig: In file included from mm/memcontrol.c:28: include/linux/res_counter.h: In function 'res_counter_set_limit': include/linux/res_counter.h:203: error: 'EBUSY' undeclared (first use in this function) include/linux/res_counter.h:203: error: (Each undeclared identifier is reported only once include/linux/res_counter.h:203: error: for each function it appears in.) Cc: Kamezawa Hiroyuki Cc: Glauber Costa Cc: Tejun Heo Cc: Frederic Weisbecker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/res_counter.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h index 5ae8456d9670..c23099413ad6 100644 --- a/include/linux/res_counter.h +++ b/include/linux/res_counter.h @@ -14,6 +14,7 @@ */ #include +#include /* * The core object. the cgroup that wishes to account for some -- cgit v1.2.3 From c8615d3716fe327c2540cf514a34b227dc9b39e8 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 13 Mar 2013 14:59:42 -0700 Subject: idr: deprecate idr_pre_get() and idr_get_new[_above]() Now that all in-kernel users are converted to ues the new alloc interface, mark the old interface deprecated. We should be able to remove these in a few releases. Signed-off-by: Tejun Heo Cc: Rusty Russell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/idr.h | 66 ++++++++++++++++++++++++++++++++++++++++------------- 1 file changed, 50 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index 8c1f81f823c8..2640c7e99e51 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -73,8 +73,6 @@ struct idr { */ void *idr_find_slowpath(struct idr *idp, int id); -int idr_pre_get(struct idr *idp, gfp_t gfp_mask); -int idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id); void idr_preload(gfp_t gfp_mask); int idr_alloc(struct idr *idp, void *ptr, int start, int end, gfp_t gfp_mask); int idr_for_each(struct idr *idp, @@ -119,19 +117,6 @@ static inline void *idr_find(struct idr *idr, int id) return idr_find_slowpath(idr, id); } -/** - * idr_get_new - allocate new idr entry - * @idp: idr handle - * @ptr: pointer you want associated with the id - * @id: pointer to the allocated handle - * - * Simple wrapper around idr_get_new_above() w/ @starting_id of zero. - */ -static inline int idr_get_new(struct idr *idp, void *ptr, int *id) -{ - return idr_get_new_above(idp, ptr, 0, id); -} - /** * idr_for_each_entry - iterate over an idr's elements of a given type * @idp: idr handle @@ -143,7 +128,56 @@ static inline int idr_get_new(struct idr *idp, void *ptr, int *id) entry != NULL; \ ++id, entry = (typeof(entry))idr_get_next((idp), &(id))) -void __idr_remove_all(struct idr *idp); /* don't use */ +/* + * Don't use the following functions. These exist only to suppress + * deprecated warnings on EXPORT_SYMBOL()s. + */ +int __idr_pre_get(struct idr *idp, gfp_t gfp_mask); +int __idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id); +void __idr_remove_all(struct idr *idp); + +/** + * idr_pre_get - reserve resources for idr allocation + * @idp: idr handle + * @gfp_mask: memory allocation flags + * + * Part of old alloc interface. This is going away. Use + * idr_preload[_end]() and idr_alloc() instead. + */ +static inline int __deprecated idr_pre_get(struct idr *idp, gfp_t gfp_mask) +{ + return __idr_pre_get(idp, gfp_mask); +} + +/** + * idr_get_new_above - allocate new idr entry above or equal to a start id + * @idp: idr handle + * @ptr: pointer you want associated with the id + * @starting_id: id to start search at + * @id: pointer to the allocated handle + * + * Part of old alloc interface. This is going away. Use + * idr_preload[_end]() and idr_alloc() instead. + */ +static inline int __deprecated idr_get_new_above(struct idr *idp, void *ptr, + int starting_id, int *id) +{ + return __idr_get_new_above(idp, ptr, starting_id, id); +} + +/** + * idr_get_new - allocate new idr entry + * @idp: idr handle + * @ptr: pointer you want associated with the id + * @id: pointer to the allocated handle + * + * Part of old alloc interface. This is going away. Use + * idr_preload[_end]() and idr_alloc() instead. + */ +static inline int __deprecated idr_get_new(struct idr *idp, void *ptr, int *id) +{ + return __idr_get_new_above(idp, ptr, 0, id); +} /** * idr_remove_all - remove all ids from the given idr tree -- cgit v1.2.3 From 5bc7c33ca93a285dcfe7b7fd64970f6314440ad1 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Wed, 13 Mar 2013 09:51:31 -0700 Subject: mtd: nand: reintroduce NAND_NO_READRDY as NAND_NEED_READRDY This partially reverts commit 1696e6bc2ae83734e64e206ac99766ea19e9a14e ("mtd: nand: kill NAND_NO_READRDY"). In that patch I overlooked a few things. The original documentation for NAND_NO_READRDY included "True for all large page devices, as they do not support autoincrement." I was conflating "not support autoincrement" with the NAND_NO_AUTOINCR option, which was in fact doing nothing. So, when I dropped NAND_NO_AUTOINCR, I concluded that I then could harmlessly drop NAND_NO_READRDY. But of course the fact the NAND_NO_AUTOINCR was doing nothing didn't mean NAND_NO_READRDY was doing nothing... So, NAND_NO_READRDY is re-introduced as NAND_NEED_READRDY and applied only to those few remaining small-page NAND which needed it in the first place. Cc: stable@kernel.org [3.5+] Reported-by: Alexander Shiyan Tested-by: Alexander Shiyan Signed-off-by: Brian Norris Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 7ccb3c59ed60..ef52d9c91459 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -187,6 +187,13 @@ typedef enum { * This happens with the Renesas AG-AND chips, possibly others. */ #define BBT_AUTO_REFRESH 0x00000080 +/* + * Chip requires ready check on read (for auto-incremented sequential read). + * True only for small page devices; large page devices do not support + * autoincrement. + */ +#define NAND_NEED_READRDY 0x00000100 + /* Chip does not allow subpage writes */ #define NAND_NO_SUBPAGE_WRITE 0x00000200 -- cgit v1.2.3 From 16fad69cfe4adbbfa813de516757b87bcae36d93 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 14 Mar 2013 05:40:32 +0000 Subject: tcp: fix skb_availroom() Chrome OS team reported a crash on a Pixel ChromeBook in TCP stack : https://code.google.com/p/chromium/issues/detail?id=182056 commit a21d45726acac (tcp: avoid order-1 allocations on wifi and tx path) did a poor choice adding an 'avail_size' field to skb, while what we really needed was a 'reserved_tailroom' one. It would have avoided commit 22b4a4f22da (tcp: fix retransmit of partially acked frames) and this commit. Crash occurs because skb_split() is not aware of the 'avail_size' management (and should not be aware) Signed-off-by: Eric Dumazet Reported-by: Mukesh Agrawal Signed-off-by: David S. Miller --- include/linux/skbuff.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 821c7f45d2a7..6f2bb860e051 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -500,7 +500,7 @@ struct sk_buff { union { __u32 mark; __u32 dropcount; - __u32 avail_size; + __u32 reserved_tailroom; }; sk_buff_data_t inner_transport_header; @@ -1447,7 +1447,10 @@ static inline int skb_tailroom(const struct sk_buff *skb) */ static inline int skb_availroom(const struct sk_buff *skb) { - return skb_is_nonlinear(skb) ? 0 : skb->avail_size - skb->len; + if (skb_is_nonlinear(skb)) + return 0; + + return skb->end - skb->tail - skb->reserved_tailroom; } /** -- cgit v1.2.3 From cca7af3889bfa343d33d5e657a38d876abd10e58 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Thu, 14 Mar 2013 03:29:40 +0000 Subject: skb: Propagate pfmemalloc on skb from head page only Hi. I'm trying to send big chunks of memory from application address space via TCP socket using vmsplice + splice like this mem = mmap(128Mb); vmsplice(pipe[1], mem); /* splice memory into pipe */ splice(pipe[0], tcp_socket); /* send it into network */ When I'm lucky and a huge page splices into the pipe and then into the socket _and_ client and server ends of the TCP connection are on the same host, communicating via lo, the whole connection gets stuck! The sending queue becomes full and app stops writing/splicing more into it, but the receiving queue remains empty, and that's why. The __skb_fill_page_desc observes a tail page of a huge page and erroneously propagates its page->pfmemalloc value onto socket (the pfmemalloc on tail pages contain garbage). Then this skb->pfmemalloc leaks through lo and due to the tcp_v4_rcv sk_filter if (skb->pfmemalloc && !sock_flag(sk, SOCK_MEMALLOC)) /* true */ return -ENOMEM goto release_and_discard; no packets reach the socket. Even TCP re-transmits are dropped by this, as skb cloning clones the pfmemalloc flag as well. That said, here's the proper page->pfmemalloc propagation onto socket: we must check the huge-page's head page only, other pages' pfmemalloc and mapping values do not contain what is expected in this place. However, I'm not sure whether this fix is _complete_, since pfmemalloc propagation via lo also oesn't look great. Both, bit propagation from page to skb and this check in sk_filter, were introduced by c48a11c7 (netvm: propagate page->pfmemalloc to skb), in v3.5 so Mel and stable@ are in Cc. Signed-off-by: Pavel Emelyanov Acked-by: Eric Dumazet Acked-by: Mel Gorman Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6f2bb860e051..441f5bfdab8e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1288,11 +1288,13 @@ static inline void __skb_fill_page_desc(struct sk_buff *skb, int i, * do not lose pfmemalloc information as the pages would not be * allocated using __GFP_MEMALLOC. */ - if (page->pfmemalloc && !page->mapping) - skb->pfmemalloc = true; frag->page.p = page; frag->page_offset = off; skb_frag_size_set(frag, size); + + page = compound_head(page); + if (page->pfmemalloc && !page->mapping) + skb->pfmemalloc = true; } /** -- cgit v1.2.3 From f65846a1800ef8c48d1ae1973c30dae4c356a800 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 9 Mar 2013 07:38:41 -0800 Subject: list: Fix double fetch of pointer in hlist_entry_safe() The current version of hlist_entry_safe() fetches the pointer twice, once to test for NULL and the other to compute the offset back to the enclosing structure. This is OK for normal lock-based use because in that case, the pointer cannot change. However, when the pointer is protected by RCU (as in "rcu_dereference(p)"), then the pointer can change at any time. This use case can result in the following sequence of events: 1. CPU 0 invokes hlist_entry_safe(), fetches the RCU-protected pointer as sees that it is non-NULL. 2. CPU 1 invokes hlist_del_rcu(), deleting the entry that CPU 0 just fetched a pointer to. Because this is the last entry in the list, the pointer fetched by CPU 0 is now NULL. 3. CPU 0 refetches the pointer, obtains NULL, and then gets a NULL-pointer crash. This commit therefore applies gcc's "({ })" statement expression to create a temporary variable so that the specified pointer is fetched only once, avoiding the above sequence of events. Please note that it is the caller's responsibility to use rcu_dereference() as needed. This allows RCU-protected uses to work correctly without imposing any additional overhead on the non-RCU case. Many thanks to Eric Dumazet for spotting root cause! Reported-by: CAI Qian Reported-by: Eric Dumazet Signed-off-by: Paul E. McKenney Tested-by: Li Zefan --- include/linux/list.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index d991cc147c98..6a1f8df9144b 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -667,7 +667,9 @@ static inline void hlist_move_list(struct hlist_head *old, pos = n) #define hlist_entry_safe(ptr, type, member) \ - (ptr) ? hlist_entry(ptr, type, member) : NULL + ({ typeof(ptr) ____ptr = (ptr); \ + ____ptr ? hlist_entry(____ptr, type, member) : NULL; \ + }) /** * hlist_for_each_entry - iterate over list of given type -- cgit v1.2.3 From 1d9d8639c063caf6efc2447f5f26aa637f844ff6 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Fri, 15 Mar 2013 14:26:07 +0100 Subject: perf,x86: fix kernel crash with PEBS/BTS after suspend/resume This patch fixes a kernel crash when using precise sampling (PEBS) after a suspend/resume. Turns out the CPU notifier code is not invoked on CPU0 (BP). Therefore, the DS_AREA (used by PEBS) is not restored properly by the kernel and keeps it power-on/resume value of 0 causing any PEBS measurement to crash when running on CPU0. The workaround is to add a hook in the actual resume code to restore the DS Area MSR value. It is invoked for all CPUS. So for all but CPU0, the DS_AREA will be restored twice but this is harmless. Reported-by: Linus Torvalds Signed-off-by: Stephane Eranian Signed-off-by: Linus Torvalds --- include/linux/perf_event.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index e47ee462c2f2..71caed8626be 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -758,6 +758,7 @@ extern void perf_event_enable(struct perf_event *event); extern void perf_event_disable(struct perf_event *event); extern int __perf_event_disable(void *info); extern void perf_event_task_tick(void); +extern void perf_restore_debug_store(void); #else static inline void perf_event_task_sched_in(struct task_struct *prev, @@ -797,6 +798,7 @@ static inline void perf_event_enable(struct perf_event *event) { } static inline void perf_event_disable(struct perf_event *event) { } static inline int __perf_event_disable(void *info) { return -1; } static inline void perf_event_task_tick(void) { } +static inline void perf_restore_debug_store(void) { } #endif #define perf_output_put(handle, x) perf_output_copy((handle), &(x), sizeof(x)) -- cgit v1.2.3 From 1eef1282549d7accdd33ee36d409b039b1f911fb Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 11 Mar 2013 09:07:46 -0300 Subject: amd64_edac: Correct DIMM sizes We were filling the csrow size with a wrong value. 16a528ee3975 ("EDAC: Fix csrow size reported in sysfs") tried to address the issue. It fixed the report with the old API but not with the new one. Correct it for the new API too. Signed-off-by: Mauro Carvalho Chehab [ make it a per-csrow accounting regardless of ->channel_count ] Signed-off-by: Borislav Petkov --- include/linux/edac.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/edac.h b/include/linux/edac.h index 4fd4999ccb5b..ab1ea98e767c 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -561,7 +561,6 @@ struct csrow_info { u32 ue_count; /* Uncorrectable Errors for this csrow */ u32 ce_count; /* Correctable Errors for this csrow */ - u32 nr_pages; /* combined pages count of all channels */ struct mem_ctl_info *mci; /* the parent */ -- cgit v1.2.3 From 9713faecff3d071de1208b081d4943b002e9cb1c Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 11 Mar 2013 09:28:48 -0300 Subject: EDAC: Merge mci.mem_is_per_rank with mci.csbased Both mci.mem_is_per_rank and mci.csbased denote the same thing: the memory controller is csrows based. Merge both fields into one. There's no need for the driver to actually fill it, as the core detects it by checking if one of the layers has the csrows type as part of the memory hierarchy: if (layers[i].type == EDAC_MC_LAYER_CHIP_SELECT) per_rank = true; Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Borislav Petkov --- include/linux/edac.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/edac.h b/include/linux/edac.h index ab1ea98e767c..0b763276f619 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -675,11 +675,11 @@ struct mem_ctl_info { * sees memory sticks ("dimms"), and the ones that sees memory ranks. * All old memory controllers enumerate memories per rank, but most * of the recent drivers enumerate memories per DIMM, instead. - * When the memory controller is per rank, mem_is_per_rank is true. + * When the memory controller is per rank, csbased is true. */ unsigned n_layers; struct edac_mc_layer *layers; - bool mem_is_per_rank; + bool csbased; /* * DIMM info. Will eventually remove the entire csrows_info some day @@ -740,8 +740,6 @@ struct mem_ctl_info { u32 fake_inject_ue; u16 fake_inject_count; #endif - __u8 csbased : 1, /* csrow-based memory controller */ - __resv : 7; }; #endif -- cgit v1.2.3 From 1e8bbe6cd02fc300c88bd48244ce61ad9c7d1776 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= Date: Thu, 14 Mar 2013 01:05:13 +0000 Subject: net: cdc_ncm, cdc_mbim: allow user to prefer NCM for backwards compatibility MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit bd329e1 ("net: cdc_ncm: do not bind to NCM compatible MBIM devices") introduced a new policy, preferring MBIM for dual NCM/MBIM functions if the cdc_mbim driver was enabled. This caused a regression for users wanting to use NCM. Devices implementing NCM backwards compatibility according to section 3.2 of the MBIM v1.0 specification allow either NCM or MBIM on a single USB function, using different altsettings. The cdc_ncm and cdc_mbim drivers will both probe such functions, and must agree on a common policy for selecting either MBIM or NCM. Until now, this policy has been set at build time based on CONFIG_USB_NET_CDC_MBIM. Use a module parameter to set the system policy at runtime, allowing the user to prefer NCM on systems with the cdc_mbim driver. Cc: Greg Suarez Cc: Alexey Orishko Reported-by: Geir Haatveit Reported-by: Tommi Kyntola Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=54791 Signed-off-by: Bjørn Mork Signed-off-by: David S. Miller --- include/linux/usb/cdc_ncm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h index 3b8f9d4fc3fe..cc25b70af33c 100644 --- a/include/linux/usb/cdc_ncm.h +++ b/include/linux/usb/cdc_ncm.h @@ -127,6 +127,7 @@ struct cdc_ncm_ctx { u16 connected; }; +extern u8 cdc_ncm_select_altsetting(struct usbnet *dev, struct usb_interface *intf); extern int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting); extern void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf); extern struct sk_buff *cdc_ncm_fill_tx_frame(struct cdc_ncm_ctx *ctx, struct sk_buff *skb, __le32 sign); -- cgit v1.2.3 From 6c4d3bc99b3341067775efd4d9d13cc8e655fd7c Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Sun, 17 Mar 2013 15:49:10 -0700 Subject: perf,x86: fix link failure for non-Intel configs Commit 1d9d8639c063 ("perf,x86: fix kernel crash with PEBS/BTS after suspend/resume") introduces a link failure since perf_restore_debug_store() is only defined for CONFIG_CPU_SUP_INTEL: arch/x86/power/built-in.o: In function `restore_processor_state': (.text+0x45c): undefined reference to `perf_restore_debug_store' Fix it by defining the dummy function appropriately. Signed-off-by: David Rientjes Cc: stable@vger.kernel.org Signed-off-by: Linus Torvalds --- include/linux/perf_event.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 71caed8626be..1d795df6f4cf 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -758,7 +758,6 @@ extern void perf_event_enable(struct perf_event *event); extern void perf_event_disable(struct perf_event *event); extern int __perf_event_disable(void *info); extern void perf_event_task_tick(void); -extern void perf_restore_debug_store(void); #else static inline void perf_event_task_sched_in(struct task_struct *prev, @@ -798,6 +797,11 @@ static inline void perf_event_enable(struct perf_event *event) { } static inline void perf_event_disable(struct perf_event *event) { } static inline int __perf_event_disable(void *info) { return -1; } static inline void perf_event_task_tick(void) { } +#endif + +#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) +extern void perf_restore_debug_store(void); +#else static inline void perf_restore_debug_store(void) { } #endif -- cgit v1.2.3 From 65c10553552b487a71bf5e4676743435046fae6f Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 14 Mar 2013 20:52:30 +0900 Subject: kprobes: Make hash_64() as always inlined Because hash_64() is called from the get_kprobe() inside int3 handler, kernel causes int3 recursion and crashes if kprobes user puts a probe on it. Usually hash_64() is inlined into caller function, but in some cases, it has instances by gcc's interprocedural constant propagation. This patch uses __always_inline instead of inline to prevent gcc from doing such things. Reported-by: Timo Juhani Lindfors Signed-off-by: Masami Hiramatsu Acked-by: Ananth N Mavinakayanahalli Cc: Pavel Emelyanov Cc: Jiri Kosina Cc: Nadia Yvette Chambers Cc: yrl.pp-manager.tt@hitachi.com Cc: David S. Miller Cc: Linus Torvalds Link: http://lkml.kernel.org/r/20130314115230.19690.39387.stgit@mhiramat-M0-7522 Signed-off-by: Ingo Molnar --- include/linux/hash.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hash.h b/include/linux/hash.h index 61c97ae22e01..f09a0ae4d858 100644 --- a/include/linux/hash.h +++ b/include/linux/hash.h @@ -15,6 +15,7 @@ */ #include +#include /* 2^31 + 2^29 - 2^25 + 2^22 - 2^19 - 2^16 + 1 */ #define GOLDEN_RATIO_PRIME_32 0x9e370001UL @@ -31,7 +32,7 @@ #error Wordsize not 32 or 64 #endif -static inline u64 hash_64(u64 val, unsigned int bits) +static __always_inline u64 hash_64(u64 val, unsigned int bits) { u64 hash = val; -- cgit v1.2.3 From f445f11eb2cc265dd47da5b2e864df46cd6e5a82 Mon Sep 17 00:00:00 2001 From: Kevin Hilman Date: Thu, 14 Mar 2013 17:13:46 -0700 Subject: KVM: allow host header to be included even for !CONFIG_KVM The new context tracking subsystem unconditionally includes kvm_host.h headers for the guest enter/exit macros. This causes a compile failure when KVM is not enabled. Fix by adding an IS_ENABLED(CONFIG_KVM) check to kvm_host so it can be included/compiled even when KVM is not enabled. Cc: Frederic Weisbecker Signed-off-by: Kevin Hilman Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index cad77fe09d77..a9428635c9fd 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1,6 +1,8 @@ #ifndef __KVM_HOST_H #define __KVM_HOST_H +#if IS_ENABLED(CONFIG_KVM) + /* * This work is licensed under the terms of the GNU GPL, version 2. See * the COPYING file in the top-level directory. @@ -1055,5 +1057,8 @@ static inline bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu) } #endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */ +#else +static inline void __guest_enter(void) { return; } +static inline void __guest_exit(void) { return; } +#endif /* IS_ENABLED(CONFIG_KVM) */ #endif - -- cgit v1.2.3 From 6a15075eced2d780fa6c5d83682410f47f2e800b Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Mon, 18 Mar 2013 19:24:02 +0100 Subject: ARM: video: mxs: Fix mxsfb misconfiguring VDCTRL0 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The issue fixed by this patch manifests only then using X11 with mxsfb driver. The X11 will display either shifted image or otherwise distorted image on the LCD. The problem is that the X11 tries to reconfigure the framebuffer and along the way calls fb_ops.fb_set_par() with X11's desired configuration values. The field of particular interest is fb_info->var.sync which contains non-standard values if configured by kernel. These are either FB_SYNC_DATA_ENABLE_HIGH_ACT, FB_SYNC_DOTCLK_FAILING_ACT or both, depending on the platform configuration. Both of these values are defined in the include/linux/mxsfb.h file. The driver interprets these values and configures the LCD controller accordingly. Yet X11 only has access to the standard values for this field defined in include/uapi/linux/fb.h and thus, unlike kernel, omits these special values. This results in distorted image on the LCD. This patch moves these non-standard values into new field of the mxsfb_platform_data structure so the driver can in turn check this field instead of the video mode field for these specific portions. Moreover, this patch prefixes these values with MXSFB_SYNC_ prefix instead of FB_SYNC_ prefix to prevent confusion of subsequent users. Signed-off-by: Marek Vasut Cc: Fabio Estevam Cc: Linux ARM Cc: Linux FBDEV Cc: Lothar Waßmann Cc: Sascha Hauer Tested-by: Fabio Estevam Signed-off-by: Shawn Guo --- include/linux/mxsfb.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mxsfb.h b/include/linux/mxsfb.h index f14943d55315..f80af8674342 100644 --- a/include/linux/mxsfb.h +++ b/include/linux/mxsfb.h @@ -24,8 +24,8 @@ #define STMLCDIF_18BIT 2 /** pixel data bus to the display is of 18 bit width */ #define STMLCDIF_24BIT 3 /** pixel data bus to the display is of 24 bit width */ -#define FB_SYNC_DATA_ENABLE_HIGH_ACT (1 << 6) -#define FB_SYNC_DOTCLK_FAILING_ACT (1 << 7) /* failing/negtive edge sampling */ +#define MXSFB_SYNC_DATA_ENABLE_HIGH_ACT (1 << 6) +#define MXSFB_SYNC_DOTCLK_FAILING_ACT (1 << 7) /* failing/negtive edge sampling */ struct mxsfb_platform_data { struct fb_videomode *mode_list; @@ -44,6 +44,9 @@ struct mxsfb_platform_data { * allocated. If specified,fb_size must also be specified. * fb_phys must be unused by Linux. */ + u32 sync; /* sync mask, contains MXSFB specifics not + * carried in fb_info->var.sync + */ }; #endif /* __LINUX_MXSFB_H */ -- cgit v1.2.3 From 2a1486981c1317dc4f4aad568f2cc6e49dfb8c82 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 19 Mar 2013 14:00:53 +0000 Subject: Fix breakage in MIPS siginfo handling MIPS's siginfo handling has been broken since this commit: commit 574c4866e33d648520a8bd5bf6f573ea6e554e88 Author: Al Viro Date: Sun Nov 25 22:24:19 2012 -0500 consolidate kernel-side struct sigaction declarations for 64-bit BE MIPS CPUs. The UAPI variant looks like this: struct sigaction { unsigned int sa_flags; __sighandler_t sa_handler; sigset_t sa_mask; }; but the core kernel's variant looks like this: struct sigaction { #ifndef __ARCH_HAS_ODD_SIGACTION __sighandler_t sa_handler; unsigned long sa_flags; #else unsigned long sa_flags; __sighandler_t sa_handler; #endif #ifdef __ARCH_HAS_SA_RESTORER __sigrestore_t sa_restorer; #endif sigset_t sa_mask; }; The problem is that sa_flags has been changed from an unsigned int to an unsigned long. Fix this by making sa_flags unsigned int if __ARCH_HAS_ODD_SIGACTION is defined. Whilst we're at it, rename __ARCH_HAS_ODD_SIGACTION to __ARCH_HAS_IRIX_SIGACTION. Signed-off-by: David Howells Cc: linux-mips@linux-mips.org Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org Acked-by: Al Viro Signed-off-by: Ralf Baechle --- include/linux/compat.h | 4 ++-- include/linux/signal.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 76a87fb57ac2..377cd8c3395e 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -141,11 +141,11 @@ typedef struct { } compat_sigset_t; struct compat_sigaction { -#ifndef __ARCH_HAS_ODD_SIGACTION +#ifndef __ARCH_HAS_IRIX_SIGACTION compat_uptr_t sa_handler; compat_ulong_t sa_flags; #else - compat_ulong_t sa_flags; + compat_uint_t sa_flags; compat_uptr_t sa_handler; #endif #ifdef __ARCH_HAS_SA_RESTORER diff --git a/include/linux/signal.h b/include/linux/signal.h index a2dcb94ea49d..9475c5cb28bc 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -250,11 +250,11 @@ extern int show_unhandled_signals; extern int sigsuspend(sigset_t *); struct sigaction { -#ifndef __ARCH_HAS_ODD_SIGACTION +#ifndef __ARCH_HAS_IRIX_SIGACTION __sighandler_t sa_handler; unsigned long sa_flags; #else - unsigned long sa_flags; + unsigned int sa_flags; __sighandler_t sa_handler; #endif #ifdef __ARCH_HAS_SA_RESTORER -- cgit v1.2.3 From 7fa4cd1a78ea5af688ffce45553abbee9d7afd84 Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Wed, 20 Mar 2013 10:35:44 -0300 Subject: usb: ulpi: Define a *otg_ulpi_create no-op Building a kernel for imx_v4_v5_defconfig with CONFIG_USB_ULPI disabled, results in the following error: arch/arm/mach-imx/built-in.o: In function 'pca100_init': platform-mx2-emma.c:(.init.text+0x6788): undefined reference to 'otg_ulpi_create' platform-mx2-emma.c:(.init.text+0x682c): undefined reference to 'mxc_ulpi_access_ops' Fix this by providing a no-op definition of *otg_ulpi_create for the case when CONFIG_USB_ULPI is not defined. Acked-by: Igor Grinberg Signed-off-by: Fabio Estevam Signed-off-by: Felipe Balbi --- include/linux/usb/ulpi.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/ulpi.h b/include/linux/usb/ulpi.h index 6f033a415ecb..5c295c26ad37 100644 --- a/include/linux/usb/ulpi.h +++ b/include/linux/usb/ulpi.h @@ -181,8 +181,16 @@ /*-------------------------------------------------------------------------*/ +#if IS_ENABLED(CONFIG_USB_ULPI) struct usb_phy *otg_ulpi_create(struct usb_phy_io_ops *ops, unsigned int flags); +#else +static inline struct usb_phy *otg_ulpi_create(struct usb_phy_io_ops *ops, + unsigned int flags) +{ + return NULL; +} +#endif #ifdef CONFIG_USB_ULPI_VIEWPORT /* access ops for controllers with a viewport register */ -- cgit v1.2.3 From 44046a593eb770dbecdabf1c82bcd252f2a8337b Mon Sep 17 00:00:00 2001 From: Tom Parkin Date: Tue, 19 Mar 2013 06:11:12 +0000 Subject: udp: add encap_destroy callback Users of udp encapsulation currently have an encap_rcv callback which they can use to hook into the udp receive path. In situations where a encapsulation user allocates resources associated with a udp encap socket, it may be convenient to be able to also hook the proto .destroy operation. For example, if an encap user holds a reference to the udp socket, the destroy hook might be used to relinquish this reference. This patch adds a socket destroy hook into udp, which is set and enabled in the same way as the existing encap_rcv hook. Signed-off-by: Tom Parkin Signed-off-by: James Chapman Signed-off-by: David S. Miller --- include/linux/udp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/udp.h b/include/linux/udp.h index 9d81de123c90..42278bbf7a88 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -68,6 +68,7 @@ struct udp_sock { * For encapsulation sockets. */ int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); + void (*encap_destroy)(struct sock *sk); }; static inline struct udp_sock *udp_sk(const struct sock *sk) -- cgit v1.2.3 From 73214f5d9f33b79918b1f7babddd5c8af28dd23d Mon Sep 17 00:00:00 2001 From: Masatake YAMATO Date: Tue, 19 Mar 2013 01:47:28 +0000 Subject: thermal: shorten too long mcast group name The original name is too long. Signed-off-by: Masatake YAMATO Signed-off-by: David S. Miller --- include/linux/thermal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index f0bd7f90a90d..e3c0ae9bb1fa 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -44,7 +44,7 @@ /* Adding event notification support elements */ #define THERMAL_GENL_FAMILY_NAME "thermal_event" #define THERMAL_GENL_VERSION 0x01 -#define THERMAL_GENL_MCAST_GROUP_NAME "thermal_mc_group" +#define THERMAL_GENL_MCAST_GROUP_NAME "thermal_mc_grp" /* Default Thermal Governor */ #if defined(CONFIG_THERMAL_DEFAULT_GOV_STEP_WISE) -- cgit v1.2.3 From e5b33dc9d16053c2ae4c2c669cf008829530364b Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 19 Mar 2013 09:21:10 +0100 Subject: USB: serial: add modem-status-change wait queue Add modem-status-change wait queue to struct usb_serial_port that subdrivers can use to implement TIOCMIWAIT. Currently subdrivers use a private wait queue which may have been released when waking up after device disconnected. Note that we're adding a new wait queue rather than reusing the tty-port one as we do not want to get woken up at hangup (yet). Cc: stable Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/serial.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index ef9be7e1e190..1819b59aab2a 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -66,6 +66,7 @@ * port. * @flags: usb serial port flags * @write_wait: a wait_queue_head_t used by the port. + * @delta_msr_wait: modem-status-change wait queue * @work: work queue entry for the line discipline waking up. * @throttled: nonzero if the read urb is inactive to throttle the device * @throttle_req: nonzero if the tty wants to throttle us @@ -112,6 +113,7 @@ struct usb_serial_port { unsigned long flags; wait_queue_head_t write_wait; + wait_queue_head_t delta_msr_wait; struct work_struct work; char throttled; char throttle_req; -- cgit v1.2.3 From 09a6e1f4ad32243989b30485f78985c0923284cd Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Fri, 22 Mar 2013 08:08:06 -0300 Subject: Revert "KVM: allow host header to be included even for !CONFIG_KVM" This reverts commit f445f11eb2cc265dd47da5b2e864df46cd6e5a82 as it breaks PPC with CONFIG_KVM=n. Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index a9428635c9fd..cad77fe09d77 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1,8 +1,6 @@ #ifndef __KVM_HOST_H #define __KVM_HOST_H -#if IS_ENABLED(CONFIG_KVM) - /* * This work is licensed under the terms of the GNU GPL, version 2. See * the COPYING file in the top-level directory. @@ -1057,8 +1055,5 @@ static inline bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu) } #endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */ -#else -static inline void __guest_enter(void) { return; } -static inline void __guest_exit(void) { return; } -#endif /* IS_ENABLED(CONFIG_KVM) */ #endif + -- cgit v1.2.3 From fe8d52614bd419cedef85ef55850fd090373f481 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Fri, 22 Mar 2013 15:04:37 -0700 Subject: irq_work.h: fix warning when CONFIG_IRQ_WORK=n A randconfig caught repeated compiler warnings when CONFIG_IRQ_WORK=n due to the definition of a non-inline static function in : include/linux/irq_work.h +40 : warning: 'irq_work_needs_cpu' defined but not used Make it inline to supress the warning. This is caused commit 00b42959106a ("irq_work: Don't stop the tick with pending works") merged in v3.9-rc1. Signed-off-by: James Hogan Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Paul Gortmaker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/irq_work.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h index f5dbce50466e..66017028dcb3 100644 --- a/include/linux/irq_work.h +++ b/include/linux/irq_work.h @@ -37,7 +37,7 @@ void irq_work_sync(struct irq_work *work); #ifdef CONFIG_IRQ_WORK bool irq_work_needs_cpu(void); #else -static bool irq_work_needs_cpu(void) { return false; } +static inline bool irq_work_needs_cpu(void) { return false; } #endif #endif /* _LINUX_IRQ_WORK_H */ -- cgit v1.2.3 From dc72c32e1fd872a9a4fdfe645283c9dcd68e556d Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 22 Mar 2013 15:04:39 -0700 Subject: printk: Provide a wake_up_klogd() off-case wake_up_klogd() is useless when CONFIG_PRINTK=n because neither printk() nor printk_sched() are in use and there are actually no waiter on log_wait waitqueue. It should be a stub in this case for users like bust_spinlocks(). Otherwise this results in this warning when CONFIG_PRINTK=n and CONFIG_IRQ_WORK=n: kernel/built-in.o In function `wake_up_klogd': (.text.wake_up_klogd+0xb4): undefined reference to `irq_work_queue' To fix this, provide an off-case for wake_up_klogd() when CONFIG_PRINTK=n. There is much more from console_unlock() and other console related code in printk.c that should be moved under CONFIG_PRINTK. But for now, focus on a minimal fix as we passed the merged window already. [akpm@linux-foundation.org: include printk.h in bust_spinlocks.c] Signed-off-by: Frederic Weisbecker Reported-by: James Hogan Cc: James Hogan Cc: Steven Rostedt Cc: Peter Zijlstra Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 1 - include/linux/printk.h | 6 ++++++ 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 80d36874689b..79fdd80a42d4 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -390,7 +390,6 @@ extern struct pid *session_of_pgrp(struct pid *pgrp); unsigned long int_sqrt(unsigned long); extern void bust_spinlocks(int yes); -extern void wake_up_klogd(void); extern int oops_in_progress; /* If set, an oops, panic(), BUG() or die() is in progress */ extern int panic_timeout; extern int panic_on_oops; diff --git a/include/linux/printk.h b/include/linux/printk.h index 1249a54d17e0..822171fcb1c8 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -134,6 +134,8 @@ extern int printk_delay_msec; extern int dmesg_restrict; extern int kptr_restrict; +extern void wake_up_klogd(void); + void log_buf_kexec_setup(void); void __init setup_log_buf(int early); #else @@ -162,6 +164,10 @@ static inline bool printk_timed_ratelimit(unsigned long *caller_jiffies, return false; } +static inline void wake_up_klogd(void) +{ +} + static inline void log_buf_kexec_setup(void) { } -- cgit v1.2.3 From f9228b204f789493117e458d2fefae937edb7272 Mon Sep 17 00:00:00 2001 From: Russ Anderson Date: Fri, 22 Mar 2013 15:04:43 -0700 Subject: mm: zone_end_pfn is too small Booting with 32 TBytes memory hits BUG at mm/page_alloc.c:552! (output below). The key hint is "page 4294967296 outside zone". 4294967296 = 0x100000000 (bit 32 is set). The problem is in include/linux/mmzone.h: 530 static inline unsigned zone_end_pfn(const struct zone *zone) 531 { 532 return zone->zone_start_pfn + zone->spanned_pages; 533 } zone_end_pfn is "unsigned" (32 bits). Changing it to "unsigned long" (64 bits) fixes the problem. zone_end_pfn() was added recently in commit 108bcc96ef70 ("mm: add & use zone_end_pfn() and zone_spans_pfn()") Output from the failure. No AGP bridge found page 4294967296 outside zone [ 4294967296 - 4327469056 ] ------------[ cut here ]------------ kernel BUG at mm/page_alloc.c:552! invalid opcode: 0000 [#1] SMP Modules linked in: CPU 0 Pid: 0, comm: swapper Not tainted 3.9.0-rc2.dtp+ #10 RIP: free_one_page+0x382/0x430 Process swapper (pid: 0, threadinfo ffffffff81942000, task ffffffff81955420) Call Trace: __free_pages_ok+0x96/0xb0 __free_pages+0x25/0x50 __free_pages_bootmem+0x8a/0x8c __free_memory_core+0xea/0x131 free_low_memory_core_early+0x4a/0x98 free_all_bootmem+0x45/0x47 mem_init+0x7b/0x14c start_kernel+0x216/0x433 x86_64_start_reservations+0x2a/0x2c x86_64_start_kernel+0x144/0x153 Code: 89 f1 ba 01 00 00 00 31 f6 d3 e2 4c 89 ef e8 66 a4 01 00 e9 2c fe ff ff 0f 0b eb fe 0f 0b 66 66 2e 0f 1f 84 00 00 00 00 00 eb f3 <0f> 0b eb fe 0f 0b 0f 1f 84 00 00 00 00 00 eb f6 0f 0b eb fe 49 Signed-off-by: Russ Anderson Reported-by: George Beshers Acked-by: Hedi Berriche Cc: Cody P Schafer Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index ede274957e05..c74092eebf5c 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -527,7 +527,7 @@ static inline int zone_is_oom_locked(const struct zone *zone) return test_bit(ZONE_OOM_LOCKED, &zone->flags); } -static inline unsigned zone_end_pfn(const struct zone *zone) +static inline unsigned long zone_end_pfn(const struct zone *zone) { return zone->zone_start_pfn + zone->spanned_pages; } -- cgit v1.2.3 From 130549fed828cc34c22624c6195afcf9e7ae56fe Mon Sep 17 00:00:00 2001 From: Gao feng Date: Thu, 21 Mar 2013 19:48:41 +0000 Subject: netfilter: reset nf_trace in nf_reset We forgot to clear the nf_trace of sk_buff in nf_reset, When we use veth device, this nf_trace information will be leaked from one net namespace to another net namespace. Signed-off-by: Gao feng Signed-off-by: Pablo Neira Ayuso --- include/linux/skbuff.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 441f5bfdab8e..72b396751de7 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2641,6 +2641,9 @@ static inline void nf_reset(struct sk_buff *skb) nf_bridge_put(skb->nf_bridge); skb->nf_bridge = NULL; #endif +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) + skb->nf_trace = 0; +#endif } /* Note: This doesn't put any conntrack and bridge info in dst. */ -- cgit v1.2.3 From 3f5eb14135ba9d97ba4b8514fc7ef5e0dac2abf4 Mon Sep 17 00:00:00 2001 From: Lan Tianyu Date: Tue, 19 Mar 2013 16:48:12 +0800 Subject: usb: add find_raw_port_number callback to struct hc_driver() xhci driver divides the root hub into two logical hubs which work respectively for usb 2.0 and usb 3.0 devices. They are independent devices in the usb core. But in the ACPI table, it's one device node and all usb2.0 and usb3.0 ports are under it. Binding usb port with its acpi node needs the raw port number which is reflected in the xhci extended capabilities table. This patch is to add find_raw_port_number callback to struct hc_driver(), fill it with xhci_find_raw_port_number() which will return raw port number and add a wrap usb_hcd_find_raw_port_number(). Otherwise, refactor xhci_find_real_port_number(). Using xhci_find_raw_port_number() to get real index in the HW port status registers instead of scanning through the xHCI roothub port array. This can help to speed up. All addresses in xhci->usb2_ports and xhci->usb3_ports array are kown good ports and don't include following bad ports in the extended capabilities talbe. (1) root port that doesn't have an entry (2) root port with unknown speed (3) root port that is listed twice and with different speeds. So xhci_find_raw_port_number() will only return port num of good ones and never touch bad ports above. Signed-off-by: Lan Tianyu Signed-off-by: Sarah Sharp --- include/linux/usb/hcd.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 0a78df5f6cfd..59694b5e5e90 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -357,6 +357,7 @@ struct hc_driver { */ int (*disable_usb3_lpm_timeout)(struct usb_hcd *, struct usb_device *, enum usb3_link_state state); + int (*find_raw_port_number)(struct usb_hcd *, int); }; extern int usb_hcd_link_urb_to_ep(struct usb_hcd *hcd, struct urb *urb); @@ -396,6 +397,7 @@ extern int usb_hcd_is_primary_hcd(struct usb_hcd *hcd); extern int usb_add_hcd(struct usb_hcd *hcd, unsigned int irqnum, unsigned long irqflags); extern void usb_remove_hcd(struct usb_hcd *hcd); +extern int usb_hcd_find_raw_port_number(struct usb_hcd *hcd, int port1); struct platform_device; extern void usb_hcd_platform_shutdown(struct platform_device *dev); -- cgit v1.2.3 From fffe01f7a768d07cc50ace71abe28fbf2f786a43 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Tue, 26 Mar 2013 17:25:54 -0400 Subject: PCI: Add PCI ROM helper for platform-provided ROM images MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It turns out that some UEFI systems provide apparently an apparently valid PCI ROM BAR that turns out to contain garbage, so the attempt in 547b52463 to prefer the ROM from the BAR actually breaks a different set of machines. As Linus pointed out, the graphics drivers are probably in the best position to make this judgement, so this basically reverts 547b52463 and f9a37be0f and adds a new helper function. Followup patches will add support to nouveau and radeon for probing this ROM source if they can't find a ROM from some other source. [bhelgaas: added reporter and bugzilla pointers, s/f4eb5ff05/547b52463] Reference: https://bugzilla.redhat.com/show_bug.cgi?id=927451 Reference: http://lkml.kernel.org/r/kg69ef$vdb$1@ger.gmane.org Reported-by: Mantas Mikulėnas Reported-by: Chris Murphy Signed-off-by: Matthew Garrett Signed-off-by: Bjorn Helgaas --- 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 2461033a7987..710067f3618c 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -916,6 +916,7 @@ void pci_disable_rom(struct pci_dev *pdev); void __iomem __must_check *pci_map_rom(struct pci_dev *pdev, size_t *size); void pci_unmap_rom(struct pci_dev *pdev, void __iomem *rom); size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size); +void __iomem __must_check *pci_platform_rom(struct pci_dev *pdev, size_t *size); /* Power management related routines */ int pci_save_state(struct pci_dev *dev); -- cgit v1.2.3 From 3151527ee007b73a0ebd296010f1c0454a919c7d Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 15 Mar 2013 01:45:51 -0700 Subject: userns: Don't allow creation if the user is chrooted Guarantee that the policy of which files may be access that is established by setting the root directory will not be violated by user namespaces by verifying that the root directory points to the root of the mount namespace at the time of user namespace creation. Changing the root is a privileged operation, and as a matter of policy it serves to limit unprivileged processes to files below the current root directory. For reasons of simplicity and comprehensibility the privilege to change the root directory is gated solely on the CAP_SYS_CHROOT capability in the user namespace. Therefore when creating a user namespace we must ensure that the policy of which files may be access can not be violated by changing the root directory. Anyone who runs a processes in a chroot and would like to use user namespace can setup the same view of filesystems with a mount namespace instead. With this result that this is not a practical limitation for using user namespaces. Cc: stable@vger.kernel.org Acked-by: Serge Hallyn Reported-by: Andy Lutomirski Signed-off-by: "Eric W. Biederman" --- include/linux/fs_struct.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h index 729eded4b24f..2b93a9a5a1e6 100644 --- a/include/linux/fs_struct.h +++ b/include/linux/fs_struct.h @@ -50,4 +50,6 @@ static inline void get_fs_root_and_pwd(struct fs_struct *fs, struct path *root, spin_unlock(&fs->lock); } +extern bool current_chrooted(void); + #endif /* _LINUX_FS_STRUCT_H */ -- cgit v1.2.3 From 90563b198e4c6674c63672fae1923da467215f45 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 22 Mar 2013 03:10:15 -0700 Subject: vfs: Add a mount flag to lock read only bind mounts When a read-only bind mount is copied from mount namespace in a higher privileged user namespace to a mount namespace in a lesser privileged user namespace, it should not be possible to remove the the read-only restriction. Add a MNT_LOCK_READONLY mount flag to indicate that a mount must remain read-only. CC: stable@vger.kernel.org Acked-by: Serge Hallyn Signed-off-by: "Eric W. Biederman" --- include/linux/mount.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mount.h b/include/linux/mount.h index d7029f4a191a..73005f9957ea 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -47,6 +47,8 @@ struct mnt_namespace; #define MNT_INTERNAL 0x4000 +#define MNT_LOCK_READONLY 0x400000 + struct vfsmount { struct dentry *mnt_root; /* root of the mounted tree */ struct super_block *mnt_sb; /* pointer to superblock */ -- cgit v1.2.3 From 87a8ebd637dafc255070f503909a053cf0d98d3f Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 24 Mar 2013 14:28:27 -0700 Subject: userns: Restrict when proc and sysfs can be mounted Only allow unprivileged mounts of proc and sysfs if they are already mounted when the user namespace is created. proc and sysfs are interesting because they have content that is per namespace, and so fresh mounts are needed when new namespaces are created while at the same time proc and sysfs have content that is shared between every instance. Respect the policy of who may see the shared content of proc and sysfs by only allowing new mounts if there was an existing mount at the time the user namespace was created. In practice there are only two interesting cases: proc and sysfs are mounted at their usual places, proc and sysfs are not mounted at all (some form of mount namespace jail). Cc: stable@vger.kernel.org Acked-by: Serge Hallyn Signed-off-by: "Eric W. Biederman" --- include/linux/user_namespace.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 4ce009324933..b6b215f13b45 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -26,6 +26,8 @@ struct user_namespace { kuid_t owner; kgid_t group; unsigned int proc_inum; + bool may_mount_sysfs; + bool may_mount_proc; }; extern struct user_namespace init_user_ns; @@ -82,4 +84,6 @@ static inline void put_user_ns(struct user_namespace *ns) #endif +void update_mnt_policy(struct user_namespace *userns); + #endif /* _LINUX_USER_H */ -- cgit v1.2.3 From 24f11a5cf538a8fcc10d61f457e9a2094fb965b4 Mon Sep 17 00:00:00 2001 From: Dmitry Kravkov Date: Wed, 27 Mar 2013 06:54:00 +0000 Subject: line up comment for ndo_bridge_getlink Signed-off-by: Dmitry Kravkov Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b3d00fa4b314..8bfa95600e48 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -895,7 +895,7 @@ struct netdev_fcoe_hbainfo { * * int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh) * int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq, - * struct net_device *dev) + * struct net_device *dev, u32 filter_mask) * * int (*ndo_change_carrier)(struct net_device *dev, bool new_carrier); * Called to change device carrier. Soft-devices (like dummy, team, etc) -- cgit v1.2.3 From 09a9f1d27892255cfb9c91203f19476765e2d8d1 Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Thu, 28 Mar 2013 16:26:23 -0700 Subject: Revert "mm: introduce VM_POPULATE flag to better deal with racy userspace programs" This reverts commit 186930500985 ("mm: introduce VM_POPULATE flag to better deal with racy userspace programs"). VM_POPULATE only has any effect when userspace plays racy games with vmas by trying to unmap and remap memory regions that mmap or mlock are operating on. Also, the only effect of VM_POPULATE when userspace plays such games is that it avoids populating new memory regions that get remapped into the address range that was being operated on by the original mmap or mlock calls. Let's remove VM_POPULATE as there isn't any strong argument to mandate a new vm_flag. Signed-off-by: Michel Lespinasse Signed-off-by: Hugh Dickins Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 - include/linux/mman.h | 4 +--- 2 files changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 7acc9dc73c9f..e19ff30ad0a2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -87,7 +87,6 @@ extern unsigned int kobjsize(const void *objp); #define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */ #define VM_DENYWRITE 0x00000800 /* ETXTBSY on write attempts.. */ -#define VM_POPULATE 0x00001000 #define VM_LOCKED 0x00002000 #define VM_IO 0x00004000 /* Memory mapped I/O or similar */ diff --git a/include/linux/mman.h b/include/linux/mman.h index 61c7a87e5d2b..9aa863da287f 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -79,8 +79,6 @@ calc_vm_flag_bits(unsigned long flags) { return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) | _calc_vm_trans(flags, MAP_DENYWRITE, VM_DENYWRITE ) | - ((flags & MAP_LOCKED) ? (VM_LOCKED | VM_POPULATE) : 0) | - (((flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE) ? - VM_POPULATE : 0); + _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ); } #endif /* _LINUX_MMAN_H */ -- cgit v1.2.3 From dbf520a9d7d4d5ba28d2947be11e34099a5e3e20 Mon Sep 17 00:00:00 2001 From: Paul Walmsley Date: Sun, 31 Mar 2013 00:04:40 +0000 Subject: Revert "lockdep: check that no locks held at freeze time" This reverts commit 6aa9707099c4b25700940eb3d016f16c4434360d. Commit 6aa9707099c4 ("lockdep: check that no locks held at freeze time") causes problems with NFS root filesystems. The failures were noticed on OMAP2 and 3 boards during kernel init: [ BUG: swapper/0/1 still has locks held! ] 3.9.0-rc3-00344-ga937536 #1 Not tainted ------------------------------------- 1 lock held by swapper/0/1: #0: (&type->s_umount_key#13/1){+.+.+.}, at: [] sget+0x248/0x574 stack backtrace: rpc_wait_bit_killable __wait_on_bit out_of_line_wait_on_bit __rpc_execute rpc_run_task rpc_call_sync nfs_proc_get_root nfs_get_root nfs_fs_mount_common nfs_try_mount nfs_fs_mount mount_fs vfs_kern_mount do_mount sys_mount do_mount_root mount_root prepare_namespace kernel_init_freeable kernel_init Although the rootfs mounts, the system is unstable. Here's a transcript from a PM test: http://www.pwsan.com/omap/testlogs/test_v3.9-rc3/20130317194234/pm/37xxevm/37xxevm_log.txt Here's what the test log should look like: http://www.pwsan.com/omap/testlogs/test_v3.8/20130218214403/pm/37xxevm/37xxevm_log.txt Mailing list discussion is here: http://lkml.org/lkml/2013/3/4/221 Deal with this for v3.9 by reverting the problem commit, until folks can figure out the right long-term course of action. Signed-off-by: Paul Walmsley Cc: Mandeep Singh Baines Cc: Jeff Layton Cc: Shawn Guo Cc: Cc: Fengguang Wu Cc: Trond Myklebust Cc: Ingo Molnar Cc: Ben Chan Cc: Oleg Nesterov Cc: Tejun Heo Cc: Rafael J. Wysocki Cc: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/debug_locks.h | 4 ++-- include/linux/freezer.h | 3 --- 2 files changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h index a975de1ff59f..3bd46f766751 100644 --- a/include/linux/debug_locks.h +++ b/include/linux/debug_locks.h @@ -51,7 +51,7 @@ struct task_struct; extern void debug_show_all_locks(void); extern void debug_show_held_locks(struct task_struct *task); extern void debug_check_no_locks_freed(const void *from, unsigned long len); -extern void debug_check_no_locks_held(void); +extern void debug_check_no_locks_held(struct task_struct *task); #else static inline void debug_show_all_locks(void) { @@ -67,7 +67,7 @@ debug_check_no_locks_freed(const void *from, unsigned long len) } static inline void -debug_check_no_locks_held(void) +debug_check_no_locks_held(struct task_struct *task) { } #endif diff --git a/include/linux/freezer.h b/include/linux/freezer.h index 043a5cf8b5ba..e70df40d84f6 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -3,7 +3,6 @@ #ifndef FREEZER_H_INCLUDED #define FREEZER_H_INCLUDED -#include #include #include #include @@ -49,8 +48,6 @@ extern void thaw_kernel_threads(void); static inline bool try_to_freeze(void) { - if (!(current->flags & PF_NOFREEZE)) - debug_check_no_locks_held(); might_sleep(); if (likely(!freezing(current))) return false; -- cgit v1.2.3 From 5faaa035ddc16d3d2e31c0bfc1c4756b6869dbcc Mon Sep 17 00:00:00 2001 From: Rajagopal Venkat Date: Thu, 21 Mar 2013 13:28:25 +0000 Subject: PM / devfreq: Fix compiler warnings for CONFIG_PM_DEVFREQ unset Fix compiler warnings generated when devfreq is not enabled (CONFIG_PM_DEVFREQ is not set). Signed-off-by: Rajagopal Venkat Acked-by: MyungJoo Ham Signed-off-by: Rafael J. Wysocki --- include/linux/devfreq.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index e83ef39b3bea..fe8c4476f7e4 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -213,7 +213,7 @@ struct devfreq_simple_ondemand_data { #endif #else /* !CONFIG_PM_DEVFREQ */ -static struct devfreq *devfreq_add_device(struct device *dev, +static inline struct devfreq *devfreq_add_device(struct device *dev, struct devfreq_dev_profile *profile, const char *governor_name, void *data) @@ -221,34 +221,34 @@ static struct devfreq *devfreq_add_device(struct device *dev, return NULL; } -static int devfreq_remove_device(struct devfreq *devfreq) +static inline int devfreq_remove_device(struct devfreq *devfreq) { return 0; } -static int devfreq_suspend_device(struct devfreq *devfreq) +static inline int devfreq_suspend_device(struct devfreq *devfreq) { return 0; } -static int devfreq_resume_device(struct devfreq *devfreq) +static inline int devfreq_resume_device(struct devfreq *devfreq) { return 0; } -static struct opp *devfreq_recommended_opp(struct device *dev, +static inline struct opp *devfreq_recommended_opp(struct device *dev, unsigned long *freq, u32 flags) { - return -EINVAL; + return ERR_PTR(-EINVAL); } -static int devfreq_register_opp_notifier(struct device *dev, +static inline int devfreq_register_opp_notifier(struct device *dev, struct devfreq *devfreq) { return -EINVAL; } -static int devfreq_unregister_opp_notifier(struct device *dev, +static inline int devfreq_unregister_opp_notifier(struct device *dev, struct devfreq *devfreq) { return -EINVAL; -- cgit v1.2.3 From d8668fcb0b257d9fdcfbe5c172a99b8d85e1cd82 Mon Sep 17 00:00:00 2001 From: Shan Hai Date: Mon, 18 Mar 2013 10:30:43 +0800 Subject: libata: Use integer return value for atapi_command_packet_set The function returns type of ATAPI drives so it should return integer value. The commit 4dce8ba94c7 (libata: Use 'bool' return value for ata_id_XXX) since v2.6.39 changed the type of return value from int to bool, the change would cause all of the ATAPI class drives to be treated as TYPE_TAPE and the max_sectors of the drives to be set to 65535 because of the commit f8d8e5799b7(libata: increase 128 KB / cmd limit for ATAPI tape drives), for the function would return true for all ATAPI class drives and the TYPE_TAPE is defined as 0x01. Cc: stable@vger.kernel.org Signed-off-by: Shan Hai Signed-off-by: Jeff Garzik --- include/linux/ata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index 8f7a3d68371a..ee0bd9524055 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -954,7 +954,7 @@ static inline int atapi_cdb_len(const u16 *dev_id) } } -static inline bool atapi_command_packet_set(const u16 *dev_id) +static inline int atapi_command_packet_set(const u16 *dev_id) { return (dev_id[ATA_ID_CONFIG] >> 8) & 0x1f; } -- cgit v1.2.3 From a32450e127fc6e5ca6d958ceb3cfea4d30a00846 Mon Sep 17 00:00:00 2001 From: Shan Hai Date: Mon, 18 Mar 2013 10:30:44 +0800 Subject: libata: Set max sector to 65535 for Slimtype DVD A DS8A8SH drive The Slimtype DVD A DS8A8SH drive locks up when max sector is smaller than 65535, and the blow backtrace is observed on locking up: INFO: task flush-8:32:1130 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. flush-8:32 D ffffffff8180cf60 0 1130 2 0x00000000 ffff880273aef618 0000000000000046 0000000000000005 ffff880273aee000 ffff880273aee000 ffff880273aeffd8 ffff880273aee010 ffff880273aee000 ffff880273aeffd8 ffff880273aee000 ffff88026e842ea0 ffff880274a10000 Call Trace: [] schedule+0x5d/0x70 [] io_schedule+0x8c/0xd0 [] get_request+0x731/0x7d0 [] ? cfq_allow_merge+0x50/0x90 [] ? wake_up_bit+0x40/0x40 [] ? bio_attempt_back_merge+0x33/0x110 [] blk_queue_bio+0x23a/0x3f0 [] generic_make_request+0xc6/0x120 [] submit_bio+0x138/0x160 [] ? bio_alloc_bioset+0x96/0x120 [] submit_bh+0x1f1/0x220 [] __block_write_full_page+0x228/0x340 [] ? attach_nobh_buffers+0xc0/0xc0 [] ? I_BDEV+0x10/0x10 [] ? I_BDEV+0x10/0x10 [] block_write_full_page_endio+0xe6/0x100 [] block_write_full_page+0x15/0x20 [] blkdev_writepage+0x18/0x20 [] __writepage+0x17/0x40 [] write_cache_pages+0x34a/0x4a0 [] ? set_page_dirty+0x70/0x70 [] generic_writepages+0x51/0x80 [] do_writepages+0x20/0x50 [] __writeback_single_inode+0xa6/0x2b0 [] writeback_sb_inodes+0x311/0x4d0 [] __writeback_inodes_wb+0x86/0xd0 [] wb_writeback+0x1a3/0x330 [] ? _raw_spin_lock_irqsave+0x3f/0x50 [] ? get_nr_inodes+0x52/0x70 [] wb_do_writeback+0x1dc/0x260 [] ? schedule_timeout+0x204/0x240 [] bdi_writeback_thread+0x102/0x2b0 [] ? wb_do_writeback+0x260/0x260 [] kthread+0xc0/0xd0 [] ? kthread_worker_fn+0x1b0/0x1b0 [] ret_from_fork+0x7c/0xb0 [] ? kthread_worker_fn+0x1b0/0x1b0 The above trace was triggered by "dd if=/dev/zero of=/dev/sr0 bs=2048 count=32768" It was previously working by accident, since another bug introduced by 4dce8ba94c7 (libata: Use 'bool' return value for ata_id_XXX) caused all drives to use maxsect=65535. Cc: stable@vger.kernel.org Signed-off-by: Shan Hai Signed-off-by: Jeff Garzik --- include/linux/libata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 91c9d109e5f1..eae7a053dc51 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -398,6 +398,7 @@ enum { ATA_HORKAGE_NOSETXFER = (1 << 14), /* skip SETXFER, SATA only */ ATA_HORKAGE_BROKEN_FPDMA_AA = (1 << 15), /* skip AA */ ATA_HORKAGE_DUMP_ID = (1 << 16), /* dump IDENTIFY data */ + ATA_HORKAGE_MAX_SEC_LBA48 = (1 << 17), /* Set max sects to 65535 */ /* DMA mask for user DMA control: User visible values; DO NOT renumber */ -- cgit v1.2.3 From 4543fbefe6e06a9e40d9f2b28d688393a299f079 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Tue, 2 Apr 2013 17:10:07 -0400 Subject: net: count hw_addr syncs so that unsync works properly. A few drivers use dev_uc_sync/unsync to synchronize the address lists from master down to slave/lower devices. In some cases (bond/team) a single address list is synched down to multiple devices. At the time of unsync, we have a leak in these lower devices, because "synced" is treated as a boolean and the address will not be unsynced for anything after the first device/call. Treat "synced" as a count (same as refcount) and allow all unsync calls to work. Signed-off-by: Vlad Yasevich Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 8bfa95600e48..6151e903eef0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -210,9 +210,9 @@ struct netdev_hw_addr { #define NETDEV_HW_ADDR_T_SLAVE 3 #define NETDEV_HW_ADDR_T_UNICAST 4 #define NETDEV_HW_ADDR_T_MULTICAST 5 - bool synced; bool global_use; int refcount; + int synced; struct rcu_head rcu_head; }; -- cgit v1.2.3 From 124dff01afbdbff251f0385beca84ba1b9adda68 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 5 Apr 2013 20:42:05 +0200 Subject: netfilter: don't reset nf_trace in nf_reset() Commit 130549fe ("netfilter: reset nf_trace in nf_reset") added code to reset nf_trace in nf_reset(). This is wrong and unnecessary. nf_reset() is used in the following cases: - when passing packets up the the socket layer, at which point we want to release all netfilter references that might keep modules pinned while the packet is queued. nf_trace doesn't matter anymore at this point. - when encapsulating or decapsulating IPsec packets. We want to continue tracing these packets after IPsec processing. - when passing packets through virtual network devices. Only devices on that encapsulate in IPv4/v6 matter since otherwise nf_trace is not used anymore. Its not entirely clear whether those packets should be traced after that, however we've always done that. - when passing packets through virtual network devices that make the packet cross network namespace boundaries. This is the only cases where we clearly want to reset nf_trace and is also what the original patch intended to fix. Add a new function nf_reset_trace() and use it in dev_forward_skb() to fix this properly. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 72b396751de7..b8292d8cc9fa 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2641,6 +2641,10 @@ static inline void nf_reset(struct sk_buff *skb) nf_bridge_put(skb->nf_bridge); skb->nf_bridge = NULL; #endif +} + +static inline void nf_reset_trace(struct sk_buff *skb) +{ #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) skb->nf_trace = 0; #endif -- cgit v1.2.3 From 8f964525a121f2ff2df948dac908dcc65be21b5b Mon Sep 17 00:00:00 2001 From: Andrew Honig Date: Fri, 29 Mar 2013 09:35:21 -0700 Subject: KVM: Allow cross page reads and writes from cached translations. This patch adds support for kvm_gfn_to_hva_cache_init functions for reads and writes that will cross a page. If the range falls within the same memslot, then this will be a fast operation. If the range is split between two memslots, then the slower kvm_read_guest and kvm_write_guest are used. Tested: Test against kvm_clock unit tests. Signed-off-by: Andrew Honig Signed-off-by: Gleb Natapov --- include/linux/kvm_host.h | 2 +- include/linux/kvm_types.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index cad77fe09d77..c13958251927 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -518,7 +518,7 @@ int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data, int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned long len); int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, - gpa_t gpa); + gpa_t gpa, unsigned long len); int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len); int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len); struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index fa7cc7244cbd..b0bcce0ddc95 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -71,6 +71,7 @@ struct gfn_to_hva_cache { u64 generation; gpa_t gpa; unsigned long hva; + unsigned long len; struct kvm_memory_slot *memslot; }; -- cgit v1.2.3 From 395b97a3aeff0b8d949ee3e67bf8c11c5ffd6861 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Wed, 27 Mar 2013 09:31:28 -0400 Subject: ftrace: Do not call stub functions in control loop The function tracing control loop used by perf spits out a warning if the called function is not a control function. This is because the control function references a per cpu allocated data structure on struct ftrace_ops that is not allocated for other types of functions. commit 0a016409e42 "ftrace: Optimize the function tracer list loop" Had an optimization done to all function tracing loops to optimize for a single registered ops. Unfortunately, this allows for a slight race when tracing starts or ends, where the stub function might be called after the current registered ops is removed. In this case we get the following dump: root# perf stat -e ftrace:function sleep 1 [ 74.339105] WARNING: at include/linux/ftrace.h:209 ftrace_ops_control_func+0xde/0xf0() [ 74.349522] Hardware name: PRIMERGY RX200 S6 [ 74.357149] Modules linked in: sg igb iTCO_wdt ptp pps_core iTCO_vendor_support i7core_edac dca lpc_ich i2c_i801 coretemp edac_core crc32c_intel mfd_core ghash_clmulni_intel dm_multipath acpi_power_meter pcspk r microcode vhost_net tun macvtap macvlan nfsd kvm_intel kvm auth_rpcgss nfs_acl lockd sunrpc uinput xfs libcrc32c sd_mod crc_t10dif sr_mod cdrom mgag200 i2c_algo_bit drm_kms_helper ttm qla2xxx mptsas ahci drm li bahci scsi_transport_sas mptscsih libata scsi_transport_fc i2c_core mptbase scsi_tgt dm_mirror dm_region_hash dm_log dm_mod [ 74.446233] Pid: 1377, comm: perf Tainted: G W 3.9.0-rc1 #1 [ 74.453458] Call Trace: [ 74.456233] [] warn_slowpath_common+0x7f/0xc0 [ 74.462997] [] ? rcu_note_context_switch+0xa0/0xa0 [ 74.470272] [] ? __unregister_ftrace_function+0xa2/0x1a0 [ 74.478117] [] warn_slowpath_null+0x1a/0x20 [ 74.484681] [] ftrace_ops_control_func+0xde/0xf0 [ 74.491760] [] ftrace_call+0x5/0x2f [ 74.497511] [] ? ftrace_call+0x5/0x2f [ 74.503486] [] ? ftrace_call+0x5/0x2f [ 74.509500] [] ? synchronize_sched+0x5/0x50 [ 74.516088] [] ? _cond_resched+0x5/0x40 [ 74.522268] [] ? synchronize_sched+0x5/0x50 [ 74.528837] [] ? __unregister_ftrace_function+0xa2/0x1a0 [ 74.536696] [] ? _cond_resched+0x5/0x40 [ 74.542878] [] ? mutex_lock+0x1d/0x50 [ 74.548869] [] unregister_ftrace_function+0x27/0x50 [ 74.556243] [] perf_ftrace_event_register+0x9f/0x140 [ 74.563709] [] ? _cond_resched+0x5/0x40 [ 74.569887] [] ? mutex_lock+0x1d/0x50 [ 74.575898] [] perf_trace_destroy+0x2e/0x50 [ 74.582505] [] tp_perf_event_destroy+0x9/0x10 [ 74.589298] [] free_event+0x70/0x1a0 [ 74.595208] [] perf_event_release_kernel+0x69/0xa0 [ 74.602460] [] ? _cond_resched+0x5/0x40 [ 74.608667] [] put_event+0x90/0xc0 [ 74.614373] [] perf_release+0x10/0x20 [ 74.620367] [] __fput+0xf4/0x280 [ 74.625894] [] ____fput+0xe/0x10 [ 74.631387] [] task_work_run+0xa7/0xe0 [ 74.637452] [] do_notify_resume+0x71/0xb0 [ 74.643843] [] int_signal+0x12/0x17 To fix this a new ftrace_ops flag is added that denotes the ftrace_list_end ftrace_ops stub as just that, a stub. This flag is now checked in the control loop and the function is not called if the flag is set. Thanks to Jovi for not just reporting the bug, but also pointing out where the bug was in the code. Link: http://lkml.kernel.org/r/514A8855.7090402@redhat.com Link: http://lkml.kernel.org/r/1364377499-1900-15-git-send-email-jovi.zhangwei@huawei.com Tested-by: WANG Chao Reported-by: WANG Chao Reported-by: zhangwei(Jovi) Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index e5ca8ef50e9b..167abf907802 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -89,6 +89,7 @@ typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip, * that the call back has its own recursion protection. If it does * not set this, then the ftrace infrastructure will add recursion * protection for the caller. + * STUB - The ftrace_ops is just a place holder. */ enum { FTRACE_OPS_FL_ENABLED = 1 << 0, @@ -98,6 +99,7 @@ enum { FTRACE_OPS_FL_SAVE_REGS = 1 << 4, FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED = 1 << 5, FTRACE_OPS_FL_RECURSION_SAFE = 1 << 6, + FTRACE_OPS_FL_STUB = 1 << 7, }; struct ftrace_ops { -- cgit v1.2.3 From a6e4d5a03e9e3587e88aba687d8f225f4f04c792 Mon Sep 17 00:00:00 2001 From: Matt Fleming Date: Mon, 25 Mar 2013 09:14:30 +0000 Subject: x86, efivars: firmware bug workarounds should be in platform code Let's not burden ia64 with checks in the common efivars code that we're not writing too much data to the variable store. That kind of thing is an x86 firmware bug, plain and simple. efi_query_variable_store() provides platforms with a wrapper in which they can perform checks and workarounds for EFI variable storage bugs. Cc: H. Peter Anvin Cc: Matthew Garrett Signed-off-by: Matt Fleming --- include/linux/efi.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 9bf2f1fcae27..3d7df3d32c66 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -333,6 +333,7 @@ typedef efi_status_t efi_query_capsule_caps_t(efi_capsule_header_t **capsules, unsigned long count, u64 *max_size, int *reset_type); +typedef efi_status_t efi_query_variable_store_t(u32 attributes, unsigned long size); /* * EFI Configuration Table and GUID definitions @@ -575,9 +576,15 @@ extern void efi_enter_virtual_mode (void); /* switch EFI to virtual mode, if pos #ifdef CONFIG_X86 extern void efi_late_init(void); extern void efi_free_boot_services(void); +extern efi_status_t efi_query_variable_store(u32 attributes, unsigned long size); #else static inline void efi_late_init(void) {} static inline void efi_free_boot_services(void) {} + +static inline efi_status_t efi_query_variable_store(u32 attributes, unsigned long size) +{ + return EFI_SUCCESS; +} #endif extern void __iomem *efi_lookup_mapped_addr(u64 phys_addr); extern u64 efi_get_iobase (void); @@ -731,7 +738,7 @@ struct efivar_operations { efi_get_variable_t *get_variable; efi_get_next_variable_t *get_next_variable; efi_set_variable_t *set_variable; - efi_query_variable_info_t *query_variable_info; + efi_query_variable_store_t *query_variable_store; }; struct efivars { -- cgit v1.2.3 From ca10b9e9a8ca7342ee07065289cbe74ac128c169 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 8 Apr 2013 17:58:11 +0000 Subject: selinux: add a skb_owned_by() hook Commit 90ba9b1986b5ac (tcp: tcp_make_synack() can use alloc_skb()) broke certain SELinux/NetLabel configurations by no longer correctly assigning the sock to the outgoing SYNACK packet. Cost of atomic operations on the LISTEN socket is quite big, and we would like it to happen only if really needed. This patch introduces a new security_ops->skb_owned_by() method, that is a void operation unless selinux is active. Reported-by: Miroslav Vadkerti Diagnosed-by: Paul Moore Signed-off-by: Eric Dumazet Cc: "David S. Miller" Cc: linux-security-module@vger.kernel.org Acked-by: James Morris Tested-by: Paul Moore Acked-by: Paul Moore Signed-off-by: David S. Miller --- include/linux/security.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index eee7478cda70..6c3a78ace051 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1638,6 +1638,7 @@ struct security_operations { int (*tun_dev_attach_queue) (void *security); int (*tun_dev_attach) (struct sock *sk, void *security); int (*tun_dev_open) (void *security); + void (*skb_owned_by) (struct sk_buff *skb, struct sock *sk); #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM @@ -2588,6 +2589,8 @@ int security_tun_dev_attach_queue(void *security); int security_tun_dev_attach(struct sock *sk, void *security); int security_tun_dev_open(void *security); +void security_skb_owned_by(struct sk_buff *skb, struct sock *sk); + #else /* CONFIG_SECURITY_NETWORK */ static inline int security_unix_stream_connect(struct sock *sock, struct sock *other, @@ -2779,6 +2782,11 @@ static inline int security_tun_dev_open(void *security) { return 0; } + +static inline void security_skb_owned_by(struct sk_buff *skb, struct sock *sk) +{ +} + #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM -- cgit v1.2.3 From 386afc91144b36b42117b0092893f15bc8798a80 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 9 Apr 2013 10:48:33 -0700 Subject: spinlocks and preemption points need to be at least compiler barriers In UP and non-preempt respectively, the spinlocks and preemption disable/enable points are stubbed out entirely, because there is no regular code that can ever hit the kind of concurrency they are meant to protect against. However, while there is no regular code that can cause scheduling, we _do_ end up having some exceptional (literally!) code that can do so, and that we need to make sure does not ever get moved into the critical region by the compiler. In particular, get_user() and put_user() is generally implemented as inline asm statements (even if the inline asm may then make a call instruction to call out-of-line), and can obviously cause a page fault and IO as a result. If that inline asm has been scheduled into the middle of a preemption-safe (or spinlock-protected) code region, we obviously lose. Now, admittedly this is *very* unlikely to actually ever happen, and we've not seen examples of actual bugs related to this. But partly exactly because it's so hard to trigger and the resulting bug is so subtle, we should be extra careful to get this right. So make sure that even when preemption is disabled, and we don't have to generate any actual *code* to explicitly tell the system that we are in a preemption-disabled region, we need to at least tell the compiler not to move things around the critical region. This patch grew out of the same discussion that caused commits 79e5f05edcbf ("ARC: Add implicit compiler barrier to raw_local_irq* functions") and 3e2e0d2c222b ("tile: comment assumption about __insn_mtspr for ") to come about. Note for stable: use discretion when/if applying this. As mentioned, this bug may never have actually bitten anybody, and gcc may never have done the required code motion for it to possibly ever trigger in practice. Cc: stable@vger.kernel.org Cc: Steven Rostedt Cc: Peter Zijlstra Signed-off-by: Linus Torvalds --- include/linux/preempt.h | 22 ++++++++++++++-------- include/linux/spinlock_up.h | 29 ++++++++++++++++++----------- 2 files changed, 32 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 5a710b9c578e..87a03c746f17 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -93,14 +93,20 @@ do { \ #else /* !CONFIG_PREEMPT_COUNT */ -#define preempt_disable() do { } while (0) -#define sched_preempt_enable_no_resched() do { } while (0) -#define preempt_enable_no_resched() do { } while (0) -#define preempt_enable() do { } while (0) - -#define preempt_disable_notrace() do { } while (0) -#define preempt_enable_no_resched_notrace() do { } while (0) -#define preempt_enable_notrace() do { } while (0) +/* + * Even if we don't have any preemption, we need preempt disable/enable + * to be barriers, so that we don't have things like get_user/put_user + * that can cause faults and scheduling migrate into our preempt-protected + * region. + */ +#define preempt_disable() barrier() +#define sched_preempt_enable_no_resched() barrier() +#define preempt_enable_no_resched() barrier() +#define preempt_enable() barrier() + +#define preempt_disable_notrace() barrier() +#define preempt_enable_no_resched_notrace() barrier() +#define preempt_enable_notrace() barrier() #endif /* CONFIG_PREEMPT_COUNT */ diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h index a26e2fb604e6..e2369c167dbd 100644 --- a/include/linux/spinlock_up.h +++ b/include/linux/spinlock_up.h @@ -16,7 +16,10 @@ * In the debug case, 1 means unlocked, 0 means locked. (the values * are inverted, to catch initialization bugs) * - * No atomicity anywhere, we are on UP. + * No atomicity anywhere, we are on UP. However, we still need + * the compiler barriers, because we do not want the compiler to + * move potentially faulting instructions (notably user accesses) + * into the locked sequence, resulting in non-atomic execution. */ #ifdef CONFIG_DEBUG_SPINLOCK @@ -25,6 +28,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock) { lock->slock = 0; + barrier(); } static inline void @@ -32,6 +36,7 @@ arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags) { local_irq_save(flags); lock->slock = 0; + barrier(); } static inline int arch_spin_trylock(arch_spinlock_t *lock) @@ -39,32 +44,34 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock) char oldval = lock->slock; lock->slock = 0; + barrier(); return oldval > 0; } static inline void arch_spin_unlock(arch_spinlock_t *lock) { + barrier(); lock->slock = 1; } /* * Read-write spinlocks. No debug version. */ -#define arch_read_lock(lock) do { (void)(lock); } while (0) -#define arch_write_lock(lock) do { (void)(lock); } while (0) -#define arch_read_trylock(lock) ({ (void)(lock); 1; }) -#define arch_write_trylock(lock) ({ (void)(lock); 1; }) -#define arch_read_unlock(lock) do { (void)(lock); } while (0) -#define arch_write_unlock(lock) do { (void)(lock); } while (0) +#define arch_read_lock(lock) do { barrier(); (void)(lock); } while (0) +#define arch_write_lock(lock) do { barrier(); (void)(lock); } while (0) +#define arch_read_trylock(lock) ({ barrier(); (void)(lock); 1; }) +#define arch_write_trylock(lock) ({ barrier(); (void)(lock); 1; }) +#define arch_read_unlock(lock) do { barrier(); (void)(lock); } while (0) +#define arch_write_unlock(lock) do { barrier(); (void)(lock); } while (0) #else /* DEBUG_SPINLOCK */ #define arch_spin_is_locked(lock) ((void)(lock), 0) /* for sched.c and kernel_lock.c: */ -# define arch_spin_lock(lock) do { (void)(lock); } while (0) -# define arch_spin_lock_flags(lock, flags) do { (void)(lock); } while (0) -# define arch_spin_unlock(lock) do { (void)(lock); } while (0) -# define arch_spin_trylock(lock) ({ (void)(lock); 1; }) +# define arch_spin_lock(lock) do { barrier(); (void)(lock); } while (0) +# define arch_spin_lock_flags(lock, flags) do { barrier(); (void)(lock); } while (0) +# define arch_spin_unlock(lock) do { barrier(); (void)(lock); } while (0) +# define arch_spin_trylock(lock) ({ barrier(); (void)(lock); 1; }) #endif /* DEBUG_SPINLOCK */ #define arch_spin_is_contended(lock) (((void)(lock), 0)) -- cgit v1.2.3 From 8ce584c7416d8a85a6f3edc17d1cddefe331e87e Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 30 Mar 2013 20:13:46 -0400 Subject: procfs: add proc_remove_subtree() just what it sounds like; do that only to procfs subtrees you've created - doing that to something shared with another driver is not only antisocial, but might cause interesting races with proc_create() and its ilk. Signed-off-by: Al Viro --- include/linux/proc_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 8307f2f94d86..94dfb2aa5533 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -117,6 +117,7 @@ struct proc_dir_entry *proc_create_data(const char *name, umode_t mode, const struct file_operations *proc_fops, void *data); extern void remove_proc_entry(const char *name, struct proc_dir_entry *parent); +extern int remove_proc_subtree(const char *name, struct proc_dir_entry *parent); struct pid_namespace; @@ -202,6 +203,7 @@ static inline struct proc_dir_entry *proc_create_data(const char *name, return NULL; } #define remove_proc_entry(name, parent) do {} while (0) +#define remove_proc_subtree(name, parent) do {} while (0) static inline struct proc_dir_entry *proc_symlink(const char *name, struct proc_dir_entry *parent,const char *dest) {return NULL;} -- cgit v1.2.3 From 6eb4c7e96e19fd2c38a103472048fc0e0e0a3ec3 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Tue, 9 Apr 2013 08:57:20 +0000 Subject: netfilter: ipset: hash:*net*: nomatch flag not excluded on set resize If a resize is triggered the nomatch flag is not excluded at hashing, which leads to the element missed at lookup in the resized set. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set_ahash.h | 30 +++++++++++++++++++++------- 1 file changed, 23 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h index 01d25e6fc792..0214c4c146fa 100644 --- a/include/linux/netfilter/ipset/ip_set_ahash.h +++ b/include/linux/netfilter/ipset/ip_set_ahash.h @@ -291,6 +291,7 @@ ip_set_hash_destroy(struct ip_set *set) #define type_pf_data_tlist TOKEN(TYPE, PF, _data_tlist) #define type_pf_data_next TOKEN(TYPE, PF, _data_next) #define type_pf_data_flags TOKEN(TYPE, PF, _data_flags) +#define type_pf_data_reset_flags TOKEN(TYPE, PF, _data_reset_flags) #ifdef IP_SET_HASH_WITH_NETS #define type_pf_data_match TOKEN(TYPE, PF, _data_match) #else @@ -385,9 +386,9 @@ type_pf_resize(struct ip_set *set, bool retried) struct ip_set_hash *h = set->data; struct htable *t, *orig = h->table; u8 htable_bits = orig->htable_bits; - const struct type_pf_elem *data; + struct type_pf_elem *data; struct hbucket *n, *m; - u32 i, j; + u32 i, j, flags = 0; int ret; retry: @@ -412,9 +413,16 @@ retry: n = hbucket(orig, i); for (j = 0; j < n->pos; j++) { data = ahash_data(n, j); +#ifdef IP_SET_HASH_WITH_NETS + flags = 0; + type_pf_data_reset_flags(data, &flags); +#endif m = hbucket(t, HKEY(data, h->initval, htable_bits)); - ret = type_pf_elem_add(m, data, AHASH_MAX(h), 0); + ret = type_pf_elem_add(m, data, AHASH_MAX(h), flags); if (ret < 0) { +#ifdef IP_SET_HASH_WITH_NETS + type_pf_data_flags(data, flags); +#endif read_unlock_bh(&set->lock); ahash_destroy(t); if (ret == -EAGAIN) @@ -836,9 +844,9 @@ type_pf_tresize(struct ip_set *set, bool retried) struct ip_set_hash *h = set->data; struct htable *t, *orig = h->table; u8 htable_bits = orig->htable_bits; - const struct type_pf_elem *data; + struct type_pf_elem *data; struct hbucket *n, *m; - u32 i, j; + u32 i, j, flags = 0; int ret; /* Try to cleanup once */ @@ -873,10 +881,17 @@ retry: n = hbucket(orig, i); for (j = 0; j < n->pos; j++) { data = ahash_tdata(n, j); +#ifdef IP_SET_HASH_WITH_NETS + flags = 0; + type_pf_data_reset_flags(data, &flags); +#endif m = hbucket(t, HKEY(data, h->initval, htable_bits)); - ret = type_pf_elem_tadd(m, data, AHASH_MAX(h), 0, - ip_set_timeout_get(type_pf_data_timeout(data))); + ret = type_pf_elem_tadd(m, data, AHASH_MAX(h), flags, + ip_set_timeout_get(type_pf_data_timeout(data))); if (ret < 0) { +#ifdef IP_SET_HASH_WITH_NETS + type_pf_data_flags(data, flags); +#endif read_unlock_bh(&set->lock); ahash_destroy(t); if (ret == -EAGAIN) @@ -1187,6 +1202,7 @@ type_pf_gc_init(struct ip_set *set) #undef type_pf_data_tlist #undef type_pf_data_next #undef type_pf_data_flags +#undef type_pf_data_reset_flags #undef type_pf_data_match #undef type_pf_elem -- cgit v1.2.3 From 46fc4c909339f5a84d1679045297d9d2fb596987 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Tue, 2 Apr 2013 15:57:26 +0200 Subject: ssb: implement spurious tone avoidance MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit And make use of it in b43. This fixes a regression introduced with 49d55cef5b1925a5c1efb6aaddaa40fc7c693335 b43: N-PHY: implement spurious tone avoidance This commit made BCM4322 use only MCS 0 on channel 13, which of course resulted in performance drop (down to 0.7Mb/s). Reported-by: Stefan Brüns Signed-off-by: Rafał Miłecki Cc: Stable Signed-off-by: John W. Linville --- include/linux/ssb/ssb_driver_chipcommon.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ssb/ssb_driver_chipcommon.h b/include/linux/ssb/ssb_driver_chipcommon.h index 9e492be5244b..6fcfe99bd999 100644 --- a/include/linux/ssb/ssb_driver_chipcommon.h +++ b/include/linux/ssb/ssb_driver_chipcommon.h @@ -219,6 +219,7 @@ #define SSB_CHIPCO_PMU_CTL 0x0600 /* PMU control */ #define SSB_CHIPCO_PMU_CTL_ILP_DIV 0xFFFF0000 /* ILP div mask */ #define SSB_CHIPCO_PMU_CTL_ILP_DIV_SHIFT 16 +#define SSB_CHIPCO_PMU_CTL_PLL_UPD 0x00000400 #define SSB_CHIPCO_PMU_CTL_NOILPONW 0x00000200 /* No ILP on wait */ #define SSB_CHIPCO_PMU_CTL_HTREQEN 0x00000100 /* HT req enable */ #define SSB_CHIPCO_PMU_CTL_ALPREQEN 0x00000080 /* ALP req enable */ @@ -667,5 +668,6 @@ enum ssb_pmu_ldo_volt_id { void ssb_pmu_set_ldo_voltage(struct ssb_chipcommon *cc, enum ssb_pmu_ldo_volt_id id, u32 voltage); void ssb_pmu_set_ldo_paref(struct ssb_chipcommon *cc, bool on); +void ssb_pmu_spuravoid_pllupdate(struct ssb_chipcommon *cc, int spuravoid); #endif /* LINUX_SSB_CHIPCO_H_ */ -- cgit v1.2.3 From 6b07a24fc38476e04f591cc17594bc1835b9efdd Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Wed, 10 Apr 2013 15:34:14 -0400 Subject: lsm: add the missing documentation for the security_skb_owned_by() hook Unfortunately we didn't catch the missing comments earlier when the patch was merged. Signed-off-by: Paul Moore Signed-off-by: David S. Miller --- include/linux/security.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 6c3a78ace051..032c366ef1c6 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1012,6 +1012,10 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * This hook can be used by the module to update any security state * associated with the TUN device's security structure. * @security pointer to the TUN devices's security structure. + * @skb_owned_by: + * This hook sets the packet's owning sock. + * @skb is the packet. + * @sk the sock which owns the packet. * * Security hooks for XFRM operations. * -- cgit v1.2.3 From f2530dc71cf0822f90bb63ea4600caaef33a66bb Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 9 Apr 2013 09:33:34 +0200 Subject: kthread: Prevent unpark race which puts threads on the wrong cpu The smpboot threads rely on the park/unpark mechanism which binds per cpu threads on a particular core. Though the functionality is racy: CPU0 CPU1 CPU2 unpark(T) wake_up_process(T) clear(SHOULD_PARK) T runs leave parkme() due to !SHOULD_PARK bind_to(CPU2) BUG_ON(wrong CPU) We cannot let the tasks move themself to the target CPU as one of those tasks is actually the migration thread itself, which requires that it starts running on the target cpu right away. The solution to this problem is to prevent wakeups in park mode which are not from unpark(). That way we can guarantee that the association of the task to the target cpu is working correctly. Add a new task state (TASK_PARKED) which prevents other wakeups and use this state explicitly for the unpark wakeup. Peter noticed: Also, since the task state is visible to userspace and all the parked tasks are still in the PID space, its a good hint in ps and friends that these tasks aren't really there for the moment. The migration thread has another related issue. CPU0 CPU1 Bring up CPU2 create_thread(T) park(T) wait_for_completion() parkme() complete() sched_set_stop_task() schedule(TASK_PARKED) The sched_set_stop_task() call is issued while the task is on the runqueue of CPU1 and that confuses the hell out of the stop_task class on that cpu. So we need the same synchronizaion before sched_set_stop_task(). Reported-by: Dave Jones Reported-and-tested-by: Dave Hansen Reported-and-tested-by: Borislav Petkov Acked-by: Peter Ziljstra Cc: Srivatsa S. Bhat Cc: dhillf@gmail.com Cc: Ingo Molnar Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1304091635430.21884@ionos Signed-off-by: Thomas Gleixner --- include/linux/sched.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index d35d2b6ddbfb..e692a022527b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -163,9 +163,10 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) #define TASK_DEAD 64 #define TASK_WAKEKILL 128 #define TASK_WAKING 256 -#define TASK_STATE_MAX 512 +#define TASK_PARKED 512 +#define TASK_STATE_MAX 1024 -#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKW" +#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWP" extern char ___assert_task_state[1 - 2*!!( sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)]; -- cgit v1.2.3 From 6a76f8c0ab19f215af2a3442870eeb5f0e81998d Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 11 Apr 2013 15:55:01 +0900 Subject: tracing: Fix possible NULL pointer dereferences Currently set_ftrace_pid and set_graph_function files use seq_lseek for their fops. However seq_open() is called only for FMODE_READ in the fops->open() so that if an user tries to seek one of those file when she open it for writing, it sees NULL seq_file and then panic. It can be easily reproduced with following command: $ cd /sys/kernel/debug/tracing $ echo 1234 | sudo tee -a set_ftrace_pid In this example, GNU coreutils' tee opens the file with fopen(, "a") and then the fopen() internally calls lseek(). Link: http://lkml.kernel.org/r/1365663302-2170-1-git-send-email-namhyung@kernel.org Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Namhyung Kim Cc: stable@vger.kernel.org Signed-off-by: Namhyung Kim Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 167abf907802..eb3ce327b975 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -396,7 +396,7 @@ ssize_t ftrace_filter_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos); ssize_t ftrace_notrace_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos); -loff_t ftrace_regex_lseek(struct file *file, loff_t offset, int whence); +loff_t ftrace_filter_lseek(struct file *file, loff_t offset, int whence); int ftrace_regex_release(struct inode *inode, struct file *file); void __init -- cgit v1.2.3 From 7f49ef69db6bbf756c0abca7e9b65b32e999eec8 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Fri, 12 Apr 2013 16:40:13 -0400 Subject: ftrace: Move ftrace_filter_lseek out of CONFIG_DYNAMIC_FTRACE section As ftrace_filter_lseek is now used with ftrace_pid_fops, it needs to be moved out of the #ifdef CONFIG_DYNAMIC_FTRACE section as the ftrace_pid_fops is defined when DYNAMIC_FTRACE is not. Cc: stable@vger.kernel.org Cc: Namhyung Kim Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index eb3ce327b975..52da2a250795 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -396,7 +396,6 @@ ssize_t ftrace_filter_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos); ssize_t ftrace_notrace_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos); -loff_t ftrace_filter_lseek(struct file *file, loff_t offset, int whence); int ftrace_regex_release(struct inode *inode, struct file *file); void __init @@ -569,6 +568,8 @@ static inline int ftrace_regex_release(struct inode *inode, struct file *file) { return -ENODEV; } #endif /* CONFIG_DYNAMIC_FTRACE */ +loff_t ftrace_filter_lseek(struct file *file, loff_t offset, int whence); + /* totally disable ftrace - can not re-enable after this */ void ftrace_kill(void); -- cgit v1.2.3 From 935d8aabd4331f47a89c3e1daa5779d23cf244ee Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 14 Apr 2013 10:06:31 -0700 Subject: Add file_ns_capable() helper function for open-time capability checking Nothing is using it yet, but this will allow us to delay the open-time checks to use time, without breaking the normal UNIX permission semantics where permissions are determined by the opener (and the file descriptor can then be passed to a different process, or the process can drop capabilities). Signed-off-by: Linus Torvalds --- include/linux/capability.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/capability.h b/include/linux/capability.h index 98503b792369..d9a4f7f40f32 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -35,6 +35,7 @@ struct cpu_vfs_cap_data { #define _KERNEL_CAP_T_SIZE (sizeof(kernel_cap_t)) +struct file; struct inode; struct dentry; struct user_namespace; @@ -211,6 +212,7 @@ extern bool capable(int cap); extern bool ns_capable(struct user_namespace *ns, int cap); extern bool nsown_capable(int cap); extern bool inode_capable(const struct inode *inode, int cap); +extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap); /* audit system wants to get cap info from files as well */ extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps); -- cgit v1.2.3 From 0635eb8a54cf0fea64b174bb68bc36b9c3d622db Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Mon, 15 Apr 2013 13:09:45 -0700 Subject: Move utf16 functions to kernel core and rename We want to be able to use the utf16 functions that are currently present in the EFI variables code in platform-specific code as well. Move them to the kernel core, and in the process rename them to accurately describe what they do - they don't handle UTF16, only UCS2. Signed-off-by: Matthew Garrett Signed-off-by: Matt Fleming --- include/linux/ucs2_string.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) create mode 100644 include/linux/ucs2_string.h (limited to 'include/linux') diff --git a/include/linux/ucs2_string.h b/include/linux/ucs2_string.h new file mode 100644 index 000000000000..cbb20afdbc01 --- /dev/null +++ b/include/linux/ucs2_string.h @@ -0,0 +1,14 @@ +#ifndef _LINUX_UCS2_STRING_H_ +#define _LINUX_UCS2_STRING_H_ + +#include /* for size_t */ +#include /* for NULL */ + +typedef u16 ucs2_char_t; + +unsigned long ucs2_strnlen(const ucs2_char_t *s, size_t maxlength); +unsigned long ucs2_strlen(const ucs2_char_t *s); +unsigned long ucs2_strsize(const ucs2_char_t *data, unsigned long maxlength); +int ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len); + +#endif /* _LINUX_UCS2_STRING_H_ */ -- cgit v1.2.3 From b4cbb197c7e7a68dbad0d491242e3ca67420c13e Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 16 Apr 2013 13:45:37 -0700 Subject: vm: add vm_iomap_memory() helper function Various drivers end up replicating the code to mmap() their memory buffers into user space, and our core memory remapping function may be very flexible but it is unnecessarily complicated for the common cases to use. Our internal VM uses pfn's ("page frame numbers") which simplifies things for the VM, and allows us to pass physical addresses around in a denser and more efficient format than passing a "phys_addr_t" around, and having to shift it up and down by the page size. But it just means that drivers end up doing that shifting instead at the interface level. It also means that drivers end up mucking around with internal VM things like the vma details (vm_pgoff, vm_start/end) way more than they really need to. So this just exports a function to map a certain physical memory range into user space (using a phys_addr_t based interface that is much more natural for a driver) and hides all the complexity from the driver. Some drivers will still end up tweaking the vm_page_prot details for things like prefetching or cacheability etc, but that's actually relevant to the driver, rather than caring about what the page offset of the mapping is into the particular IO memory region. Acked-by: Greg Kroah-Hartman Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index e19ff30ad0a2..e2091b88d24c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1611,6 +1611,8 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); +int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len); + struct page *follow_page_mask(struct vm_area_struct *vma, unsigned long address, unsigned int foll_flags, -- cgit v1.2.3 From c729de8fcea37a1c444e81857eace12494c804a9 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Mon, 15 Apr 2013 22:23:45 -0700 Subject: x86, kdump: Set crashkernel_low automatically Chao said that kdump does does work well on his system on 3.8 without extra parameter, even iommu does not work with kdump. And now have to append crashkernel_low=Y in first kernel to make kdump work. We have now modified crashkernel=X to allocate memory beyong 4G (if available) and do not allocate low range for crashkernel if the user does not specify that with crashkernel_low=Y. This causes regression if iommu is not enabled. Without iommu, swiotlb needs to be setup in first 4G and there is no low memory available to second kernel. Set crashkernel_low automatically if the user does not specify that. For system that does support IOMMU with kdump properly, user could specify crashkernel_low=0 to save that 72M low ram. -v3: add swiotlb_size() according to Konrad. -v4: add comments what 8M is for according to hpa. also update more crashkernel_low= in kernel-parameters.txt -v5: update changelog according to Vivek. -v6: Change description about swiotlb referring according to HATAYAMA. Reported-by: WANG Chao Tested-by: WANG Chao Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1366089828-19692-2-git-send-email-yinghai@kernel.org Acked-by: Vivek Goyal Signed-off-by: H. Peter Anvin --- include/linux/swiotlb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 2de42f9401d2..a5ffd32642fd 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -25,6 +25,7 @@ extern int swiotlb_force; extern void swiotlb_init(int verbose); int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose); extern unsigned long swiotlb_nr_tbl(void); +unsigned long swiotlb_size_or_default(void); extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs); /* -- cgit v1.2.3 From 55a20ee7804ab64ac90bcdd4e2868a42829e2784 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Mon, 15 Apr 2013 22:23:47 -0700 Subject: x86, kdump: Retore crashkernel= to allocate under 896M Vivek found old kexec-tools does not work new kernel anymore. So change back crashkernel= back to old behavoir, and add crashkernel_high= to let user decide if buffer could be above 4G, and also new kexec-tools will be needed. -v2: let crashkernel=X override crashkernel_high= update description about _high will be ignored by crashkernel=X -v3: update description about kernel-parameters.txt according to Vivek. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1366089828-19692-4-git-send-email-yinghai@kernel.org Acked-by: Vivek Goyal Signed-off-by: H. Peter Anvin --- include/linux/kexec.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index d2e6927bbaae..d78d28a733b1 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -200,6 +200,8 @@ extern size_t vmcoreinfo_max_size; int __init parse_crashkernel(char *cmdline, unsigned long long system_ram, unsigned long long *crash_size, unsigned long long *crash_base); +int parse_crashkernel_high(char *cmdline, unsigned long long system_ram, + unsigned long long *crash_size, unsigned long long *crash_base); int parse_crashkernel_low(char *cmdline, unsigned long long system_ram, unsigned long long *crash_size, unsigned long long *crash_base); int crash_shrink_memory(unsigned long new_size); -- cgit v1.2.3 From 0a82a8d132b26d438eb90b3ab35a7016e7227a1d Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 18 Apr 2013 09:00:26 -0700 Subject: Revert "block: add missing block_bio_complete() tracepoint" This reverts commit 3a366e614d0837d9fc23f78cdb1a1186ebc3387f. Wanlong Gao reports that it causes a kernel panic on his machine several minutes after boot. Reverting it removes the panic. Jens says: "It's not quite clear why that is yet, so I think we should just revert the commit for 3.9 final (which I'm assuming is pretty close). The wifi is crap at the LSF hotel, so sending this email instead of queueing up a revert and pull request." Reported-by: Wanlong Gao Requested-by: Jens Axboe Cc: Tejun Heo Cc: Steven Rostedt Signed-off-by: Linus Torvalds --- include/linux/blktrace_api.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 0ea61e07a91c..7c2e030e72f1 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -12,7 +12,6 @@ struct blk_trace { int trace_state; - bool rq_based; struct rchan *rchan; unsigned long __percpu *sequence; unsigned char __percpu *msg_data; -- cgit v1.2.3