From a51805efae5dda0da66f79268ffcf0715f9dbea4 Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Mon, 8 Jul 2013 14:23:49 -0700 Subject: lockdep: Introduce lock_acquire_exclusive()/shared() helper macros In lockdep.h, the spinlock/mutex/rwsem/rwlock/lock_map acquire macros have different definitions based on the value of CONFIG_PROVE_LOCKING. We have separate ifdefs for each of these definitions, which seems redundant. Introduce lock_acquire_{exclusive,shared,shared_recursive} helpers which will have different definitions based on CONFIG_PROVE_LOCKING. Then all other helper macros can be defined based on the above ones, which reduces the amount of ifdefined code. Signed-off-by: Michel Lespinasse Signed-off-by: Andrew Morton Signed-off-by: Peter Zijlstra Cc: Oleg Nesterov Cc: Lai Jiangshan Cc: "Srivatsa S. Bhat" Cc: Rusty Russell Cc: Andi Kleen Cc: "Paul E. McKenney" Cc: Steven Rostedt Link: http://lkml.kernel.org/r/20130708212350.6DD1931C15E@corp2gmr1-1.hot.corp.google.com Signed-off-by: Ingo Molnar --- include/linux/lockdep.h | 92 +++++++++++++------------------------------------ 1 file changed, 23 insertions(+), 69 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index f1e877b79ed8..cfc2f119779a 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -365,7 +365,7 @@ extern void lockdep_trace_alloc(gfp_t mask); #define lockdep_recursing(tsk) ((tsk)->lockdep_recursion) -#else /* !LOCKDEP */ +#else /* !CONFIG_LOCKDEP */ static inline void lockdep_off(void) { @@ -479,82 +479,36 @@ static inline void print_irqtrace_events(struct task_struct *curr) * on the per lock-class debug mode: */ -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# ifdef CONFIG_PROVE_LOCKING -# define spin_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, NULL, i) -# define spin_acquire_nest(l, s, t, n, i) lock_acquire(l, s, t, 0, 2, n, i) -# else -# define spin_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, NULL, i) -# define spin_acquire_nest(l, s, t, n, i) lock_acquire(l, s, t, 0, 1, NULL, i) -# endif -# define spin_release(l, n, i) lock_release(l, n, i) +#ifdef CONFIG_PROVE_LOCKING + #define lock_acquire_exclusive(l, s, t, n, i) lock_acquire(l, s, t, 0, 2, n, i) + #define lock_acquire_shared(l, s, t, n, i) lock_acquire(l, s, t, 1, 2, n, i) + #define lock_acquire_shared_recursive(l, s, t, n, i) lock_acquire(l, s, t, 2, 2, n, i) #else -# define spin_acquire(l, s, t, i) do { } while (0) -# define spin_release(l, n, i) do { } while (0) + #define lock_acquire_exclusive(l, s, t, n, i) lock_acquire(l, s, t, 0, 1, n, i) + #define lock_acquire_shared(l, s, t, n, i) lock_acquire(l, s, t, 1, 1, n, i) + #define lock_acquire_shared_recursive(l, s, t, n, i) lock_acquire(l, s, t, 2, 1, n, i) #endif -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# ifdef CONFIG_PROVE_LOCKING -# define rwlock_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, NULL, i) -# define rwlock_acquire_read(l, s, t, i) lock_acquire(l, s, t, 2, 2, NULL, i) -# else -# define rwlock_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, NULL, i) -# define rwlock_acquire_read(l, s, t, i) lock_acquire(l, s, t, 2, 1, NULL, i) -# endif -# define rwlock_release(l, n, i) lock_release(l, n, i) -#else -# define rwlock_acquire(l, s, t, i) do { } while (0) -# define rwlock_acquire_read(l, s, t, i) do { } while (0) -# define rwlock_release(l, n, i) do { } while (0) -#endif +#define spin_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) +#define spin_acquire_nest(l, s, t, n, i) lock_acquire_exclusive(l, s, t, n, i) +#define spin_release(l, n, i) lock_release(l, n, i) -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# ifdef CONFIG_PROVE_LOCKING -# define mutex_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, NULL, i) -# define mutex_acquire_nest(l, s, t, n, i) lock_acquire(l, s, t, 0, 2, n, i) -# else -# define mutex_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, NULL, i) -# define mutex_acquire_nest(l, s, t, n, i) lock_acquire(l, s, t, 0, 1, n, i) -# endif -# define mutex_release(l, n, i) lock_release(l, n, i) -#else -# define mutex_acquire(l, s, t, i) do { } while (0) -# define mutex_acquire_nest(l, s, t, n, i) do { } while (0) -# define mutex_release(l, n, i) do { } while (0) -#endif +#define rwlock_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) +#define rwlock_acquire_read(l, s, t, i) lock_acquire_shared_recursive(l, s, t, NULL, i) +#define rwlock_release(l, n, i) lock_release(l, n, i) -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# ifdef CONFIG_PROVE_LOCKING -# define rwsem_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, NULL, i) -# define rwsem_acquire_nest(l, s, t, n, i) lock_acquire(l, s, t, 0, 2, n, i) -# define rwsem_acquire_read(l, s, t, i) lock_acquire(l, s, t, 1, 2, NULL, i) -# else -# define rwsem_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, NULL, i) -# define rwsem_acquire_nest(l, s, t, n, i) lock_acquire(l, s, t, 0, 1, n, i) -# define rwsem_acquire_read(l, s, t, i) lock_acquire(l, s, t, 1, 1, NULL, i) -# endif +#define mutex_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) +#define mutex_acquire_nest(l, s, t, n, i) lock_acquire_exclusive(l, s, t, n, i) +#define mutex_release(l, n, i) lock_release(l, n, i) + +#define rwsem_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) +#define rwsem_acquire_nest(l, s, t, n, i) lock_acquire_exclusive(l, s, t, n, i) +#define rwsem_acquire_read(l, s, t, i) lock_acquire_shared(l, s, t, NULL, i) # define rwsem_release(l, n, i) lock_release(l, n, i) -#else -# define rwsem_acquire(l, s, t, i) do { } while (0) -# define rwsem_acquire_nest(l, s, t, n, i) do { } while (0) -# define rwsem_acquire_read(l, s, t, i) do { } while (0) -# define rwsem_release(l, n, i) do { } while (0) -#endif -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# ifdef CONFIG_PROVE_LOCKING -# define lock_map_acquire(l) lock_acquire(l, 0, 0, 0, 2, NULL, _THIS_IP_) -# define lock_map_acquire_read(l) lock_acquire(l, 0, 0, 2, 2, NULL, _THIS_IP_) -# else -# define lock_map_acquire(l) lock_acquire(l, 0, 0, 0, 1, NULL, _THIS_IP_) -# define lock_map_acquire_read(l) lock_acquire(l, 0, 0, 2, 1, NULL, _THIS_IP_) -# endif +#define lock_map_acquire(l) lock_acquire_exclusive(l, 0, 0, NULL, _THIS_IP_) +#define lock_map_acquire_read(l) lock_acquire_shared_recursive(l, 0, 0, NULL, _THIS_IP_) # define lock_map_release(l) lock_release(l, 1, _THIS_IP_) -#else -# define lock_map_acquire(l) do { } while (0) -# define lock_map_acquire_read(l) do { } while (0) -# define lock_map_release(l) do { } while (0) -#endif #ifdef CONFIG_PROVE_LOCKING # define might_lock(lock) \ -- cgit v1.2.3 From 728ce22b696f9f1404a74d7b2279a65933553a1b Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 12 Jun 2013 15:08:51 +0200 Subject: cpuidle: Make cpuidle's sysfs directory dynamically allocated The cpuidle sysfs code is designed to have a single instance of per CPU cpuidle directory. It is not possible to remove the sysfs entry and create it again. This is not a problem with the current code but future changes will add CPU hotplug support to enable/disable the device, so it will need to remove the sysfs entry like other subsystems do. That won't be possible without this change, because the kobj is a static object which can't be reused for kobj_init_and_add(). Add cpuidle_device_kobj to be allocated dynamically when adding/removing a sysfs entry which is consistent with the other cpuidle's sysfs entries. An added benefit is that the sysfs code is now more self-contained and the includes needed for sysfs can be moved from cpuidle.h directly into sysfs.c so as to reduce the total number of headers dragged along with cpuidle.h. [rjw: Changelog] Signed-off-by: Daniel Lezcano Signed-off-by: Rafael J. Wysocki --- include/linux/cpuidle.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 0bc4b74668e9..b922db53b7ab 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -13,8 +13,6 @@ #include #include -#include -#include #include #define CPUIDLE_STATE_MAX 10 @@ -61,6 +59,8 @@ struct cpuidle_state { #define CPUIDLE_DRIVER_FLAGS_MASK (0xFFFF0000) +struct cpuidle_device_kobj; + struct cpuidle_device { unsigned int registered:1; unsigned int enabled:1; @@ -71,9 +71,8 @@ struct cpuidle_device { struct cpuidle_state_usage states_usage[CPUIDLE_STATE_MAX]; struct cpuidle_state_kobj *kobjs[CPUIDLE_STATE_MAX]; struct cpuidle_driver_kobj *kobj_driver; + struct cpuidle_device_kobj *kobj_dev; struct list_head device_list; - struct kobject kobj; - struct completion kobj_unregister; #ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED int safe_state_index; -- cgit v1.2.3 From 1a7064380e6639e1cc5ed609ceb1ed46f3f188e3 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 12 Jun 2013 15:08:52 +0200 Subject: cpuidle: Add missing forward declarations of structures Add missing forward declarations of struct cpuidle_state_kobj and struct cpuidle_driver_kobj in cpuidle.h. [rjw: Changelog] Signed-off-by: Daniel Lezcano Signed-off-by: Rafael J. Wysocki --- include/linux/cpuidle.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index b922db53b7ab..781addc66f03 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -60,6 +60,8 @@ struct cpuidle_state { #define CPUIDLE_DRIVER_FLAGS_MASK (0xFFFF0000) struct cpuidle_device_kobj; +struct cpuidle_state_kobj; +struct cpuidle_driver_kobj; struct cpuidle_device { unsigned int registered:1; -- cgit v1.2.3 From dc9ceed6a12aff627c81e01ada191e8a23fcbe3e Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 4 Jul 2013 17:27:14 +0100 Subject: regulator: core: Make set_voltage_tol() try for mid-range first The expected semantic for something expressed as a tolerance is that it should deliver the specified value with some deviation allowed but this is not what set_voltage_tol() currently does. Instead it just passes the maximum possible range to set_voltage() which will typically result in a voltage aimed at lower than the target voltage. Instead first try to set a voltage between the target voltage and the upper limit, then fall back on the full range. This will be much more robust against physical variation in systems and makes the API behave more like users would expect. Signed-off-by: Mark Brown --- include/linux/regulator/consumer.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 3a76389c6aaa..3610df8dd229 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -369,8 +369,11 @@ static inline int regulator_count_voltages(struct regulator *regulator) static inline int regulator_set_voltage_tol(struct regulator *regulator, int new_uV, int tol_uV) { - return regulator_set_voltage(regulator, - new_uV - tol_uV, new_uV + tol_uV); + if (regulator_set_voltage(regulator, new_uV, new_uV + tol_uV) == 0) + return 0; + else + return regulator_set_voltage(regulator, + new_uV - tol_uV, new_uV + tol_uV); } static inline int regulator_is_supported_voltage_tol(struct regulator *regulator, -- cgit v1.2.3 From 94d33c02c7186b69849c292e1216a08ad1c0d99d Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 2 Jul 2013 22:52:41 +0100 Subject: regulator: core: Add helpers for multiple linear ranges Many regulators have several linear ranges of selector with different step sizes, for example offering better resolution at lower voltages. Provide regulator_{map,list}_voltage_linear_range() allowing these regulators to use generic code. To do so a table of regulator_linear_range structs needs to be pointed to from the descriptor. This was inspired by similar code included in a driver submission from Chao Xie and Yi Zhang at Marvell. Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 6700cc94bdd1..67e13aa5a478 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -39,6 +39,24 @@ enum regulator_status { REGULATOR_STATUS_UNDEFINED, }; +/** + * Specify a range of voltages for regulator_map_linar_range() and + * regulator_list_linear_range(). + * + * @min_uV: Lowest voltage in range + * @max_uV: Highest voltage in range + * @min_sel: Lowest selector for range + * @max_sel: Highest selector for range + * @uV_step: Step size + */ +struct regulator_linear_range { + unsigned int min_uV; + unsigned int max_uV; + unsigned int min_sel; + unsigned int max_sel; + unsigned int uV_step; +}; + /** * struct regulator_ops - regulator operations. * @@ -223,6 +241,9 @@ struct regulator_desc { unsigned int linear_min_sel; unsigned int ramp_delay; + const struct regulator_linear_range *linear_ranges; + int n_linear_ranges; + const unsigned int *volt_table; unsigned int vsel_reg; @@ -326,10 +347,14 @@ int regulator_mode_to_status(unsigned int); int regulator_list_voltage_linear(struct regulator_dev *rdev, unsigned int selector); +int regulator_list_voltage_linear_range(struct regulator_dev *rdev, + unsigned int selector); int regulator_list_voltage_table(struct regulator_dev *rdev, unsigned int selector); int regulator_map_voltage_linear(struct regulator_dev *rdev, int min_uV, int max_uV); +int regulator_map_voltage_linear_range(struct regulator_dev *rdev, + int min_uV, int max_uV); int regulator_map_voltage_iterate(struct regulator_dev *rdev, int min_uV, int max_uV); int regulator_map_voltage_ascend(struct regulator_dev *rdev, -- cgit v1.2.3 From 1653ccf4c52df6a4abe8ec2f33f2cb2896d129ea Mon Sep 17 00:00:00 2001 From: Yadwinder Singh Brar Date: Sat, 29 Jun 2013 18:21:15 +0530 Subject: regulator: core: Add support for disabling ramp delay Some hardwares support disabling ramp delay, so adding ramp_disable flag to constraints. It will be used to figure out whether ramp_delay in constraints is explicitly set to zero or its unintialized (zero by default). And we don't need to call set_voltage_time_sel() for regulators for whom ramp delay is disabled in constraints. Signed-off-by: Yadwinder Singh Brar Signed-off-by: Mark Brown --- include/linux/regulator/machine.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index 36adbc82de6a..999b20ce06cf 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -134,6 +134,7 @@ struct regulation_constraints { unsigned always_on:1; /* regulator never off when system is on */ unsigned boot_on:1; /* bootloader/firmware enabled regulator */ unsigned apply_uV:1; /* apply uV constraint if min == max */ + unsigned ramp_disable:1; /* disable ramp delay */ }; /** -- cgit v1.2.3 From 874b31585650afa6745de5133849365e7e6af418 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 5 Jul 2013 11:44:49 +0100 Subject: spi/bitbang: Unexport spi_bitbang_transfer() Currently no drivers use the ability to override spi_bitbang_transfer() and if any started this would make it harder to convert the bitbang code to use transfer_one_message() so remove the export in order to prevent anyone starting. Signed-off-by: Mark Brown --- include/linux/spi/spi_bitbang.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi_bitbang.h b/include/linux/spi/spi_bitbang.h index f987a2bee16a..b5aa215493f6 100644 --- a/include/linux/spi/spi_bitbang.h +++ b/include/linux/spi/spi_bitbang.h @@ -41,7 +41,6 @@ struct spi_bitbang { */ extern int spi_bitbang_setup(struct spi_device *spi); extern void spi_bitbang_cleanup(struct spi_device *spi); -extern int spi_bitbang_transfer(struct spi_device *spi, struct spi_message *m); extern int spi_bitbang_setup_transfer(struct spi_device *spi, struct spi_transfer *t); -- cgit v1.2.3 From a2fd4f9fa3b9f051550b36c4dfa74bc32bda24ee Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 10 Jul 2013 14:57:26 +0100 Subject: spi: Support transfer speed checking in the core Allow drivers to avoid implementing their own checks for simple rates by specifying the limits in the master structure. Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 28e440be1c07..cdf668156154 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -233,6 +233,8 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * suported. If set, the SPI core will reject any transfer with an * unsupported bits_per_word. If not set, this value is simply ignored, * and it's up to the individual driver to perform any validation. + * @min_speed_hz: Lowest supported transfer speed + * @max_speed_hz: Highest supported transfer speed * @flags: other constraints relevant to this driver * @bus_lock_spinlock: spinlock for SPI bus locking * @bus_lock_mutex: mutex for SPI bus locking @@ -312,6 +314,10 @@ struct spi_master { #define SPI_BIT_MASK(bits) (((bits) == 32) ? ~0UL : (BIT(bits) - 1)) #define SPI_BPW_RANGE_MASK(min, max) (SPI_BIT_MASK(max) - SPI_BIT_MASK(min - 1)) + /* limits on transfer speed */ + u32 min_speed_hz; + u32 max_speed_hz; + /* other constraints relevant to this driver */ u16 flags; #define SPI_MASTER_HALF_DUPLEX BIT(0) /* can't do full duplex */ -- cgit v1.2.3 From 939c02777a27ea7915764ecca5263dbb60c664f3 Mon Sep 17 00:00:00 2001 From: Yadwinder Singh Brar Date: Sat, 29 Jun 2013 18:21:16 +0530 Subject: regulator: s2mps11: Implement set_ramp_rate callback for bucks Implementing set_ramp_rate() and using standard constraints for getting ramp_delay and ramp_disable, instead of getting it as s2mps11 specific data through platform data, makes driver more compliant with framework and reduces the complexity for adding DT support. Signed-off-by: Yadwinder Singh Brar Signed-off-by: Mark Brown --- include/linux/mfd/samsung/s2mps11.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/samsung/s2mps11.h b/include/linux/mfd/samsung/s2mps11.h index 4e94dc65f987..d0d52ea60074 100644 --- a/include/linux/mfd/samsung/s2mps11.h +++ b/include/linux/mfd/samsung/s2mps11.h @@ -191,6 +191,17 @@ enum s2mps11_regulators { #define S2MPS11_BUCK_N_VOLTAGES (S2MPS11_BUCK_VSEL_MASK + 1) #define S2MPS11_RAMP_DELAY 25000 /* uV/us */ + +#define S2MPS11_BUCK2_RAMP_SHIFT 6 +#define S2MPS11_BUCK34_RAMP_SHIFT 4 +#define S2MPS11_BUCK5_RAMP_SHIFT 6 +#define S2MPS11_BUCK16_RAMP_SHIFT 4 +#define S2MPS11_BUCK7810_RAMP_SHIFT 2 +#define S2MPS11_BUCK9_RAMP_SHIFT 0 +#define S2MPS11_BUCK2_RAMP_EN_SHIFT 3 +#define S2MPS11_BUCK3_RAMP_EN_SHIFT 2 +#define S2MPS11_BUCK4_RAMP_EN_SHIFT 1 +#define S2MPS11_BUCK6_RAMP_EN_SHIFT 0 #define S2MPS11_PMIC_EN_SHIFT 6 #define S2MPS11_REGULATOR_MAX (S2MPS11_REG_MAX - 3) -- cgit v1.2.3 From dc34e7e1a701134c2639dc7af78dc91055616477 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Mon, 1 Jul 2013 00:01:32 +0400 Subject: libata: move 'struct ata_taskfile' and friends from ata.h to libata.h Move 'struct ata_taskfile', ata_prot_flags() and their friends from to . They were misplaced from the beginning, as should cover ATA/ATAPI and related standards only -- to which the aforementioned structure and function have only remote relation. I would have moved 'enum ata_tf_protocols' closely related to 'struct ata_taskfile' but it unfortunately gets used by 'drivers/ide/ide-ioctls.c'... Signed-off-by: Sergei Shtylyov Signed-off-by: Tejun Heo --- include/linux/ata.h | 102 ------------------------------------------------- include/linux/libata.h | 102 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 102 insertions(+), 102 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index ee0bd9524055..f63fb1afc5cc 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -446,22 +446,6 @@ enum { SERR_TRANS_ST_ERROR = (1 << 24), /* Transport state trans. error */ SERR_UNRECOG_FIS = (1 << 25), /* Unrecognized FIS */ SERR_DEV_XCHG = (1 << 26), /* device exchanged */ - - /* struct ata_taskfile flags */ - ATA_TFLAG_LBA48 = (1 << 0), /* enable 48-bit LBA and "HOB" */ - ATA_TFLAG_ISADDR = (1 << 1), /* enable r/w to nsect/lba regs */ - ATA_TFLAG_DEVICE = (1 << 2), /* enable r/w to device reg */ - ATA_TFLAG_WRITE = (1 << 3), /* data dir: host->dev==1 (write) */ - ATA_TFLAG_LBA = (1 << 4), /* enable LBA */ - ATA_TFLAG_FUA = (1 << 5), /* enable FUA */ - ATA_TFLAG_POLLING = (1 << 6), /* set nIEN to 1 and use polling */ - - /* protocol flags */ - ATA_PROT_FLAG_PIO = (1 << 0), /* is PIO */ - ATA_PROT_FLAG_DMA = (1 << 1), /* is DMA */ - ATA_PROT_FLAG_DATA = ATA_PROT_FLAG_PIO | ATA_PROT_FLAG_DMA, - ATA_PROT_FLAG_NCQ = (1 << 2), /* is NCQ */ - ATA_PROT_FLAG_ATAPI = (1 << 3), /* is ATAPI */ }; enum ata_tf_protocols { @@ -488,83 +472,6 @@ struct ata_bmdma_prd { __le32 flags_len; }; -struct ata_taskfile { - unsigned long flags; /* ATA_TFLAG_xxx */ - u8 protocol; /* ATA_PROT_xxx */ - - u8 ctl; /* control reg */ - - u8 hob_feature; /* additional data */ - u8 hob_nsect; /* to support LBA48 */ - u8 hob_lbal; - u8 hob_lbam; - u8 hob_lbah; - - u8 feature; - u8 nsect; - u8 lbal; - u8 lbam; - u8 lbah; - - u8 device; - - u8 command; /* IO operation */ -}; - -/* - * protocol tests - */ -static inline unsigned int ata_prot_flags(u8 prot) -{ - switch (prot) { - case ATA_PROT_NODATA: - return 0; - case ATA_PROT_PIO: - return ATA_PROT_FLAG_PIO; - case ATA_PROT_DMA: - return ATA_PROT_FLAG_DMA; - case ATA_PROT_NCQ: - return ATA_PROT_FLAG_DMA | ATA_PROT_FLAG_NCQ; - case ATAPI_PROT_NODATA: - return ATA_PROT_FLAG_ATAPI; - case ATAPI_PROT_PIO: - return ATA_PROT_FLAG_ATAPI | ATA_PROT_FLAG_PIO; - case ATAPI_PROT_DMA: - return ATA_PROT_FLAG_ATAPI | ATA_PROT_FLAG_DMA; - } - return 0; -} - -static inline int ata_is_atapi(u8 prot) -{ - return ata_prot_flags(prot) & ATA_PROT_FLAG_ATAPI; -} - -static inline int ata_is_nodata(u8 prot) -{ - return !(ata_prot_flags(prot) & ATA_PROT_FLAG_DATA); -} - -static inline int ata_is_pio(u8 prot) -{ - return ata_prot_flags(prot) & ATA_PROT_FLAG_PIO; -} - -static inline int ata_is_dma(u8 prot) -{ - return ata_prot_flags(prot) & ATA_PROT_FLAG_DMA; -} - -static inline int ata_is_ncq(u8 prot) -{ - return ata_prot_flags(prot) & ATA_PROT_FLAG_NCQ; -} - -static inline int ata_is_data(u8 prot) -{ - return ata_prot_flags(prot) & ATA_PROT_FLAG_DATA; -} - /* * id tests */ @@ -1060,15 +967,6 @@ static inline unsigned ata_set_lba_range_entries(void *_buffer, return used_bytes; } -static inline int is_multi_taskfile(struct ata_taskfile *tf) -{ - return (tf->command == ATA_CMD_READ_MULTI) || - (tf->command == ATA_CMD_WRITE_MULTI) || - (tf->command == ATA_CMD_READ_MULTI_EXT) || - (tf->command == ATA_CMD_WRITE_MULTI_EXT) || - (tf->command == ATA_CMD_WRITE_MULTI_FUA_EXT); -} - static inline bool ata_ok(u8 status) { return ((status & (ATA_BUSY | ATA_DRDY | ATA_DF | ATA_DRQ | ATA_ERR)) diff --git a/include/linux/libata.h b/include/linux/libata.h index 4ea55bb45deb..283d66bc603c 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -138,6 +138,22 @@ enum { ATA_SHT_THIS_ID = -1, ATA_SHT_USE_CLUSTERING = 1, + /* struct ata_taskfile flags */ + ATA_TFLAG_LBA48 = (1 << 0), /* enable 48-bit LBA and "HOB" */ + ATA_TFLAG_ISADDR = (1 << 1), /* enable r/w to nsect/lba regs */ + ATA_TFLAG_DEVICE = (1 << 2), /* enable r/w to device reg */ + ATA_TFLAG_WRITE = (1 << 3), /* data dir: host->dev==1 (write) */ + ATA_TFLAG_LBA = (1 << 4), /* enable LBA */ + ATA_TFLAG_FUA = (1 << 5), /* enable FUA */ + ATA_TFLAG_POLLING = (1 << 6), /* set nIEN to 1 and use polling */ + + /* protocol flags */ + ATA_PROT_FLAG_PIO = (1 << 0), /* is PIO */ + ATA_PROT_FLAG_DMA = (1 << 1), /* is DMA */ + ATA_PROT_FLAG_DATA = ATA_PROT_FLAG_PIO | ATA_PROT_FLAG_DMA, + ATA_PROT_FLAG_NCQ = (1 << 2), /* is NCQ */ + ATA_PROT_FLAG_ATAPI = (1 << 3), /* is ATAPI */ + /* struct ata_device stuff */ ATA_DFLAG_LBA = (1 << 0), /* device supports LBA */ ATA_DFLAG_LBA48 = (1 << 1), /* device supports LBA48 */ @@ -518,6 +534,29 @@ enum sw_activity { BLINK_OFF, }; +struct ata_taskfile { + unsigned long flags; /* ATA_TFLAG_xxx */ + u8 protocol; /* ATA_PROT_xxx */ + + u8 ctl; /* control reg */ + + u8 hob_feature; /* additional data */ + u8 hob_nsect; /* to support LBA48 */ + u8 hob_lbal; + u8 hob_lbam; + u8 hob_lbah; + + u8 feature; + u8 nsect; + u8 lbal; + u8 lbam; + u8 lbah; + + u8 device; + + u8 command; /* IO operation */ +}; + #ifdef CONFIG_ATA_SFF struct ata_ioports { void __iomem *cmd_addr; @@ -959,6 +998,69 @@ extern const unsigned long sata_deb_timing_long[]; extern struct ata_port_operations ata_dummy_port_ops; extern const struct ata_port_info ata_dummy_port_info; +/* + * protocol tests + */ +static inline unsigned int ata_prot_flags(u8 prot) +{ + switch (prot) { + case ATA_PROT_NODATA: + return 0; + case ATA_PROT_PIO: + return ATA_PROT_FLAG_PIO; + case ATA_PROT_DMA: + return ATA_PROT_FLAG_DMA; + case ATA_PROT_NCQ: + return ATA_PROT_FLAG_DMA | ATA_PROT_FLAG_NCQ; + case ATAPI_PROT_NODATA: + return ATA_PROT_FLAG_ATAPI; + case ATAPI_PROT_PIO: + return ATA_PROT_FLAG_ATAPI | ATA_PROT_FLAG_PIO; + case ATAPI_PROT_DMA: + return ATA_PROT_FLAG_ATAPI | ATA_PROT_FLAG_DMA; + } + return 0; +} + +static inline int ata_is_atapi(u8 prot) +{ + return ata_prot_flags(prot) & ATA_PROT_FLAG_ATAPI; +} + +static inline int ata_is_nodata(u8 prot) +{ + return !(ata_prot_flags(prot) & ATA_PROT_FLAG_DATA); +} + +static inline int ata_is_pio(u8 prot) +{ + return ata_prot_flags(prot) & ATA_PROT_FLAG_PIO; +} + +static inline int ata_is_dma(u8 prot) +{ + return ata_prot_flags(prot) & ATA_PROT_FLAG_DMA; +} + +static inline int ata_is_ncq(u8 prot) +{ + return ata_prot_flags(prot) & ATA_PROT_FLAG_NCQ; +} + +static inline int ata_is_data(u8 prot) +{ + return ata_prot_flags(prot) & ATA_PROT_FLAG_DATA; +} + +static inline int is_multi_taskfile(struct ata_taskfile *tf) +{ + return (tf->command == ATA_CMD_READ_MULTI) || + (tf->command == ATA_CMD_WRITE_MULTI) || + (tf->command == ATA_CMD_READ_MULTI_EXT) || + (tf->command == ATA_CMD_WRITE_MULTI_EXT) || + (tf->command == ATA_CMD_WRITE_MULTI_FUA_EXT); +} + static inline const unsigned long * sata_ehc_deb_timing(struct ata_eh_context *ehc) { -- cgit v1.2.3 From 2025172e32808a327b00f968c72baa79adc594c2 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 5 Jul 2013 20:07:27 +0100 Subject: spi/bitbang: Use core message pump Convert drivers using bitbang to use the core mesasge pump infrastructure, saving some code and meaning that these drivers get to take advantage of work done on improving the core implementation. Signed-off-by: Mark Brown --- include/linux/spi/spi_bitbang.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi_bitbang.h b/include/linux/spi/spi_bitbang.h index b5aa215493f6..daebaba886aa 100644 --- a/include/linux/spi/spi_bitbang.h +++ b/include/linux/spi/spi_bitbang.h @@ -4,11 +4,7 @@ #include struct spi_bitbang { - struct workqueue_struct *workqueue; - struct work_struct work; - spinlock_t lock; - struct list_head queue; u8 busy; u8 use_dma; u8 flags; /* extra spi->mode support */ -- cgit v1.2.3 From e69f61862ab833e9b8d3c15b6ce07fd69f3bfecc Mon Sep 17 00:00:00 2001 From: Yacine Belkadi Date: Fri, 12 Jul 2013 20:45:47 +0200 Subject: sched: Fix some kernel-doc warnings When building the htmldocs (in verbose mode), scripts/kernel-doc reports the follwing type of warnings: Warning(kernel/sched/core.c:936): No description found for return value of 'task_curr' ... Fix those by: - adding the missing descriptions - using "Return" sections for the descriptions Signed-off-by: Yacine Belkadi Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1373654747-2389-1-git-send-email-yacine.belkadi.1@gmail.com [ While at it, fix the cpupri_set() explanation. ] Signed-off-by: Ingo Molnar --- include/linux/sched.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 50d04b92ceda..82300247974c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1532,6 +1532,8 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk) * Test if a process is not yet dead (at most zombie state) * If pid_alive fails, then pointers within the task structure * can be stale and must not be dereferenced. + * + * Return: 1 if the process is alive. 0 otherwise. */ static inline int pid_alive(struct task_struct *p) { @@ -1543,6 +1545,8 @@ static inline int pid_alive(struct task_struct *p) * @tsk: Task structure to be checked. * * Check if a task structure is the first user space task the kernel created. + * + * Return: 1 if the task structure is init. 0 otherwise. */ static inline int is_global_init(struct task_struct *tsk) { @@ -1893,6 +1897,8 @@ extern struct task_struct *idle_task(int cpu); /** * is_idle_task - is the specified task an idle task? * @p: the task in question. + * + * Return: 1 if @p is an idle task. 0 otherwise. */ static inline bool is_idle_task(const struct task_struct *p) { -- cgit v1.2.3 From 078726ce6d56a767533064e0f2f2100d7cb6fc22 Mon Sep 17 00:00:00 2001 From: Sourav Poddar Date: Thu, 18 Jul 2013 15:31:25 +0530 Subject: driver: spi: Modify core to compute the message length Make spi core calculate the message length while populating the other transfer parameters. Usecase, driver can use it to populate framelength filed in their controller. Signed-off-by: Sourav Poddar Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 28e440be1c07..aadd0a885a0f 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -578,6 +578,7 @@ struct spi_message { /* completion is reported through a callback */ void (*complete)(void *context); void *context; + unsigned frame_length; unsigned actual_length; int status; -- cgit v1.2.3 From a1a8e1dc111d6f05e7164e851e58219d428359e1 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Tue, 16 Jul 2013 15:28:00 +0100 Subject: iio:trigger: Fix use_count race condition When using more than one trigger consumer it can happen that multiple threads perform a read-modify-update cycle on 'use_count' concurrently. This can cause updates to be lost and use_count can get stuck at non-zero value, in which case the IIO core assumes that at least one thread is still running and will wait for it to finish before running any trigger handlers again. This effectively renders the trigger disabled and a reboot is necessary before it can be used again. To fix this make use_count an atomic variable. Also set it to the number of consumers before starting the first consumer, otherwise it might happen that use_count drops to 0 even though not all consumers have been run yet. Signed-off-by: Lars-Peter Clausen Tested-by: Denis Ciocca Signed-off-by: Jonathan Cameron --- include/linux/iio/trigger.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h index 3869c525b052..369cf2cd5144 100644 --- a/include/linux/iio/trigger.h +++ b/include/linux/iio/trigger.h @@ -8,6 +8,7 @@ */ #include #include +#include #ifndef _IIO_TRIGGER_H_ #define _IIO_TRIGGER_H_ @@ -61,7 +62,7 @@ struct iio_trigger { struct list_head list; struct list_head alloc_list; - int use_count; + atomic_t use_count; struct irq_chip subirq_chip; int subirq_base; -- cgit v1.2.3 From b1451e546899bc8f450773b2af02e0cd000cf1fa Mon Sep 17 00:00:00 2001 From: "Patil, Rachna" Date: Sat, 20 Jul 2013 17:27:00 +0100 Subject: iio: ti_am335x_adc: Fix wrong samples received on 1st read Previously we tried to read data form ADC even before ADC sequencer finished sampling. This led to wrong samples. We now wait on ADC status register idle bit to be set. Signed-off-by: Patil, Rachna Signed-off-by: Zubair Lutfullah Signed-off-by: Jonathan Cameron --- include/linux/mfd/ti_am335x_tscadc.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index 8d73fe29796a..db1791bb997a 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -113,11 +113,27 @@ #define CNTRLREG_8WIRE CNTRLREG_AFE_CTRL(3) #define CNTRLREG_TSCENB BIT(7) +/* FIFO READ Register */ +#define FIFOREAD_DATA_MASK (0xfff << 0) +#define FIFOREAD_CHNLID_MASK (0xf << 16) + +/* Sequencer Status */ +#define SEQ_STATUS BIT(5) + #define ADC_CLK 3000000 #define MAX_CLK_DIV 7 #define TOTAL_STEPS 16 #define TOTAL_CHANNELS 8 +/* +* ADC runs at 3MHz, and it takes +* 15 cycles to latch one data output. +* Hence the idle time for ADC to +* process one sample data would be +* around 5 micro seconds. +*/ +#define IDLE_TIMEOUT 5 /* microsec */ + #define TSCADC_CELLS 2 struct ti_tscadc_dev { -- cgit v1.2.3 From be1c9de98d8904c75a5ab8b2a0d97bea0f7c07cc Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 13 Jul 2013 23:27:23 +0200 Subject: ACPI / PCI: Make bus registration and unregistration symmetric Since acpi_pci_slot_enumerate() and acpiphp_enumerate_slots() can get the ACPI device handle they need from bus->bridge, it is not necessary to pass that handle to them as an argument. Drop the second argument of acpi_pci_slot_enumerate() and acpiphp_enumerate_slots(), rework them to obtain the ACPI handle from bus->bridge and make acpi_pci_add_bus() and acpi_pci_remove_bus() entirely symmetrical. Tested-by: Mika Westerberg Signed-off-by: Rafael J. Wysocki Acked-by: Yinghai Lu --- include/linux/pci-acpi.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index 170447977278..d006f0ca60f4 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -47,24 +47,22 @@ void acpi_pci_remove_bus(struct pci_bus *bus); #ifdef CONFIG_ACPI_PCI_SLOT void acpi_pci_slot_init(void); -void acpi_pci_slot_enumerate(struct pci_bus *bus, acpi_handle handle); +void acpi_pci_slot_enumerate(struct pci_bus *bus); void acpi_pci_slot_remove(struct pci_bus *bus); #else static inline void acpi_pci_slot_init(void) { } -static inline void acpi_pci_slot_enumerate(struct pci_bus *bus, - acpi_handle handle) { } +static inline void acpi_pci_slot_enumerate(struct pci_bus *bus) { } static inline void acpi_pci_slot_remove(struct pci_bus *bus) { } #endif #ifdef CONFIG_HOTPLUG_PCI_ACPI void acpiphp_init(void); -void acpiphp_enumerate_slots(struct pci_bus *bus, acpi_handle handle); +void acpiphp_enumerate_slots(struct pci_bus *bus); void acpiphp_remove_slots(struct pci_bus *bus); void acpiphp_check_host_bridge(acpi_handle handle); #else static inline void acpiphp_init(void) { } -static inline void acpiphp_enumerate_slots(struct pci_bus *bus, - acpi_handle handle) { } +static inline void acpiphp_enumerate_slots(struct pci_bus *bus) { } static inline void acpiphp_remove_slots(struct pci_bus *bus) { } static inline void acpiphp_check_host_bridge(acpi_handle handle) { } #endif -- cgit v1.2.3 From 62470419e993f8d9d93db0effd3af4296ecb79a5 Mon Sep 17 00:00:00 2001 From: Michael Wang Date: Thu, 4 Jul 2013 12:55:51 +0800 Subject: sched: Implement smarter wake-affine logic The wake-affine scheduler feature is currently always trying to pull the wakee close to the waker. In theory this should be beneficial if the waker's CPU caches hot data for the wakee, and it's also beneficial in the extreme ping-pong high context switch rate case. Testing shows it can benefit hackbench up to 15%. However, the feature is somewhat blind, from which some workloads such as pgbench suffer. It's also time-consuming algorithmically. Testing shows it can damage pgbench up to 50% - far more than the benefit it brings in the best case. So wake-affine should be smarter and it should realize when to stop its thankless effort at trying to find a suitable CPU to wake on. This patch introduces 'wakee_flips', which will be increased each time the task flips (switches) its wakee target. So a high 'wakee_flips' value means the task has more than one wakee, and the bigger the number, the higher the wakeup frequency. Now when making the decision on whether to pull or not, pay attention to the wakee with a high 'wakee_flips', pulling such a task may benefit the wakee. Also imply that the waker will face cruel competition later, it could be very cruel or very fast depends on the story behind 'wakee_flips', waker therefore suffers. Furthermore, if waker also has a high 'wakee_flips', that implies that multiple tasks rely on it, then waker's higher latency will damage all of them, so pulling wakee seems to be a bad deal. Thus, when 'waker->wakee_flips / wakee->wakee_flips' becomes higher and higher, the cost of pulling seems to be worse and worse. The patch therefore helps the wake-affine feature to stop its pulling work when: wakee->wakee_flips > factor && waker->wakee_flips > (factor * wakee->wakee_flips) The 'factor' here is the number of CPUs in the current CPU's NUMA node, so a bigger node will lead to more pulling since the trial becomes more severe. After applying the patch, pgbench shows up to 40% improvements and no regressions. Tested with 12 cpu x86 server and tip 3.10.0-rc7. The percentages in the final column highlight the areas with the biggest wins, all other areas improved as well: pgbench base smart | db_size | clients | tps | | tps | +---------+---------+-------+ +-------+ | 22 MB | 1 | 10598 | | 10796 | | 22 MB | 2 | 21257 | | 21336 | | 22 MB | 4 | 41386 | | 41622 | | 22 MB | 8 | 51253 | | 57932 | | 22 MB | 12 | 48570 | | 54000 | | 22 MB | 16 | 46748 | | 55982 | +19.75% | 22 MB | 24 | 44346 | | 55847 | +25.93% | 22 MB | 32 | 43460 | | 54614 | +25.66% | 7484 MB | 1 | 8951 | | 9193 | | 7484 MB | 2 | 19233 | | 19240 | | 7484 MB | 4 | 37239 | | 37302 | | 7484 MB | 8 | 46087 | | 50018 | | 7484 MB | 12 | 42054 | | 48763 | | 7484 MB | 16 | 40765 | | 51633 | +26.66% | 7484 MB | 24 | 37651 | | 52377 | +39.11% | 7484 MB | 32 | 37056 | | 51108 | +37.92% | 15 GB | 1 | 8845 | | 9104 | | 15 GB | 2 | 19094 | | 19162 | | 15 GB | 4 | 36979 | | 36983 | | 15 GB | 8 | 46087 | | 49977 | | 15 GB | 12 | 41901 | | 48591 | | 15 GB | 16 | 40147 | | 50651 | +26.16% | 15 GB | 24 | 37250 | | 52365 | +40.58% | 15 GB | 32 | 36470 | | 50015 | +37.14% Signed-off-by: Michael Wang Cc: Mike Galbraith Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/51D50057.9000809@linux.vnet.ibm.com [ Improved the changelog. ] Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 50d04b92ceda..4f163a8ffabf 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1034,6 +1034,9 @@ struct task_struct { #ifdef CONFIG_SMP struct llist_node wake_entry; int on_cpu; + struct task_struct *last_wakee; + unsigned long wakee_flips; + unsigned long wakee_flip_decay_ts; #endif int on_rq; -- cgit v1.2.3 From 2753e6f8207355ab72574d48287cec187272a151 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Mon, 22 Jul 2013 17:15:52 +0200 Subject: regmap: irq: Allow to acknowledge masked interrupts during initialization In case the hardware interrupt mask register does not prevent the chip level irq from being asserted by the corresponding interrupt status bit, already set interrupt bits should to be cleared once after masking them during initialization. Add a flag to let drivers enable this behavior. Signed-off-by: Philipp Zabel Signed-off-by: Mark Brown --- include/linux/regmap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 75981d0b57dc..34ebe7778033 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -470,6 +470,7 @@ struct regmap_irq { * @ack_base: Base ack address. If zero then the chip is clear on read. * @wake_base: Base address for wake enables. If zero unsupported. * @irq_reg_stride: Stride to use for chips where registers are not contiguous. + * @init_ack_masked: Ack all masked interrupts once during initalization. * @runtime_pm: Hold a runtime PM lock on the device when accessing it. * * @num_regs: Number of registers in each control bank. @@ -485,6 +486,7 @@ struct regmap_irq_chip { unsigned int ack_base; unsigned int wake_base; unsigned int irq_reg_stride; + bool init_ack_masked; unsigned int mask_invert; unsigned int wake_invert; bool runtime_pm; -- cgit v1.2.3 From 36697529b5bbe36911e39a6309e7a7c9250d280a Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 07:04:48 -0400 Subject: tty: Replace ldisc locking with ldisc_sem Line discipline locking was performed with a combination of a mutex, a status bit, a count, and a waitqueue -- basically, a rw semaphore. Replace the existing combination with an ld_semaphore. Fixes: 1) the 'reference acquire after ldisc locked' bug 2) the over-complicated halt mechanism 3) lock order wrt. tty_lock() 4) dropping locks while changing ldisc 5) previously unidentified deadlock while locking ldisc from both linked ttys concurrently 6) previously unidentified recursive deadlocks Adds much-needed lockdep diagnostics. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 4 +--- include/linux/tty_ldisc.h | 3 +-- 2 files changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 01ac30efd6a6..7269daf7632b 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -238,7 +238,7 @@ struct tty_struct { int index; /* Protects ldisc changes: Lock tty not pty */ - struct mutex ldisc_mutex; + struct ld_semaphore ldisc_sem; struct tty_ldisc *ldisc; struct mutex atomic_write_lock; @@ -305,8 +305,6 @@ struct tty_file_private { #define TTY_DO_WRITE_WAKEUP 5 /* Call write_wakeup after queuing new */ #define TTY_PUSH 6 /* n_tty private */ #define TTY_CLOSING 7 /* ->close() in progress */ -#define TTY_LDISC 9 /* Line discipline attached */ -#define TTY_LDISC_CHANGING 10 /* Line discipline changing */ #define TTY_LDISC_OPEN 11 /* Line discipline is open */ #define TTY_PTY_LOCK 16 /* pty private */ #define TTY_NO_WRITE_SPLIT 17 /* Preserve write boundaries to driver */ diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index a1b048999821..23bdd9debb84 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -203,8 +203,7 @@ struct tty_ldisc_ops { struct tty_ldisc { struct tty_ldisc_ops *ops; - atomic_t users; - wait_queue_head_t wq_idle; + struct tty_struct *tty; }; #define TTY_LDISC_MAGIC 0x5403 -- cgit v1.2.3 From 24a89d1cb69b6c488cf16d98dd02e7820f62b40c Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:14:15 -0400 Subject: tty: Make ldisc input flow control concurrency-friendly Although line discipline receiving is single-producer/single-consumer, using tty->receive_room to manage flow control creates unnecessary critical regions requiring additional lock use. Instead, introduce the optional .receive_buf2() ldisc method which returns the # of bytes actually received. Serialization is guaranteed by the caller. In turn, the line discipline should schedule the buffer work item whenever space becomes available; ie., when there is room to receive data and receive_room() previously returned 0 (the buffer work item stops processing if receive_buf2() returns 0). Note the 'no room' state need not be atomic despite concurrent use by two threads because only the buffer work thread can set the state and only the read() thread can clear the state. Add n_tty_receive_buf2() as the receive_buf2() method for N_TTY. Provide a public helper function, tty_ldisc_receive_buf(), to use when directly accessing the receive_buf() methods. Line disciplines not using input flow control can continue to set tty->receive_room to a fixed value and only provide the receive_buf() method. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 13 +++++++++++++ include/linux/tty_ldisc.h | 13 +++++++++++++ 2 files changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 7269daf7632b..8323ee4f95b9 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -557,6 +557,19 @@ extern void tty_ldisc_init(struct tty_struct *tty); extern void tty_ldisc_deinit(struct tty_struct *tty); extern void tty_ldisc_begin(void); +static inline int tty_ldisc_receive_buf(struct tty_ldisc *ld, unsigned char *p, + char *f, int count) +{ + if (ld->ops->receive_buf2) + count = ld->ops->receive_buf2(ld->tty, p, f, count); + else { + count = min_t(int, count, ld->tty->receive_room); + if (count) + ld->ops->receive_buf(ld->tty, p, f, count); + } + return count; +} + /* n_tty.c */ extern struct tty_ldisc_ops tty_ldisc_N_TTY; diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index 23bdd9debb84..f15c898ff462 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -109,6 +109,17 @@ * * Tells the discipline that the DCD pin has changed its status. * Used exclusively by the N_PPS (Pulse-Per-Second) line discipline. + * + * int (*receive_buf2)(struct tty_struct *, const unsigned char *cp, + * char *fp, int count); + * + * This function is called by the low-level tty driver to send + * characters received by the hardware to the line discpline for + * processing. is a pointer to the buffer of input + * character received by the device. is a pointer to a + * pointer of flag bytes which indicate whether a character was + * received with a parity error, etc. + * If assigned, prefer this function for automatic flow control. */ #include @@ -195,6 +206,8 @@ struct tty_ldisc_ops { void (*write_wakeup)(struct tty_struct *); void (*dcd_change)(struct tty_struct *, unsigned int); void (*fasync)(struct tty_struct *tty, int on); + int (*receive_buf2)(struct tty_struct *, const unsigned char *cp, + char *fp, int count); struct module *owner; -- cgit v1.2.3 From 6a1c0680cf3ba94356ecd58833e1540c93472a57 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:14:23 -0400 Subject: tty: Convert termios_mutex to termios_rwsem termios is commonly accessed unsafely (especially by N_TTY) because the existing mutex forces exclusive access. Convert existing usage. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 8323ee4f95b9..d3042076d163 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -10,6 +10,7 @@ #include #include #include +#include @@ -243,9 +244,9 @@ struct tty_struct { struct mutex atomic_write_lock; struct mutex legacy_mutex; - struct mutex termios_mutex; + struct rw_semaphore termios_rwsem; spinlock_t ctrl_lock; - /* Termios values are protected by the termios mutex */ + /* Termios values are protected by the termios rwsem */ struct ktermios termios, termios_locked; struct termiox *termiox; /* May be NULL for unsupported */ char name[64]; @@ -253,7 +254,7 @@ struct tty_struct { struct pid *session; unsigned long flags; int count; - struct winsize winsize; /* termios mutex */ + struct winsize winsize; /* termios rwsem */ unsigned char stopped:1, hw_stopped:1, flow_stopped:1, packet:1; unsigned char ctrl_status; /* ctrl_lock */ unsigned int receive_room; /* Bytes free for queue */ -- cgit v1.2.3 From d8c1f929aa8164cd8eaa830068d2fa3159c0764a Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:14:31 -0400 Subject: tty: Only guarantee termios read safety for throttle/unthrottle No tty driver modifies termios during throttle() or unthrottle(). Therefore, only read safety is required. However, tty_throttle_safe and tty_unthrottle_safe must still be mutually exclusive; introduce throttle_mutex for that purpose. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index d3042076d163..57a70d1d0412 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -244,6 +244,7 @@ struct tty_struct { struct mutex atomic_write_lock; struct mutex legacy_mutex; + struct mutex throttle_mutex; struct rw_semaphore termios_rwsem; spinlock_t ctrl_lock; /* Termios values are protected by the termios rwsem */ -- cgit v1.2.3 From 1fc359fc3ea72314cc3ebdfa94c60e020c152cd2 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:01 -0400 Subject: tty: Compute flip buffer ptrs The char_buf_ptr and flag_buf_ptr values are trivially derived from the .data field offset; compute values as needed. Fixes a long-standing type-mismatch with the char and flag ptrs. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 12 ++++++++++-- include/linux/tty_flip.h | 4 ++-- 2 files changed, 12 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 57a70d1d0412..87bbaa31ebf5 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -31,8 +31,6 @@ struct tty_buffer { struct tty_buffer *next; - char *char_buf_ptr; - unsigned char *flag_buf_ptr; int used; int size; int commit; @@ -41,6 +39,16 @@ struct tty_buffer { unsigned long data[0]; }; +static inline unsigned char *char_buf_ptr(struct tty_buffer *b, int ofs) +{ + return ((unsigned char *)b->data) + ofs; +} + +static inline char *flag_buf_ptr(struct tty_buffer *b, int ofs) +{ + return (char *)char_buf_ptr(b, ofs) + b->size; +} + /* * We default to dicing tty buffer allocations to this many characters * in order to avoid multiple page allocations. We know the size of diff --git a/include/linux/tty_flip.h b/include/linux/tty_flip.h index e0f252633b47..ad0303994c32 100644 --- a/include/linux/tty_flip.h +++ b/include/linux/tty_flip.h @@ -18,8 +18,8 @@ static inline int tty_insert_flip_char(struct tty_port *port, { struct tty_buffer *tb = port->buf.tail; if (tb && tb->used < tb->size) { - tb->flag_buf_ptr[tb->used] = flag; - tb->char_buf_ptr[tb->used++] = ch; + *flag_buf_ptr(tb, tb->used) = flag; + *char_buf_ptr(tb, tb->used++) = ch; return 1; } return tty_insert_flip_string_flags(port, &ch, &flag, 1); -- cgit v1.2.3 From 809850b7a5fcc0a96d023e1171a7944c60fd5a71 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:06 -0400 Subject: tty: Use lockless flip buffer free list In preparation for lockless flip buffers, make the flip buffer free list lockless. NB: using llist is not the optimal solution, as the driver and buffer work may contend over the llist head unnecessarily. However, test measurements indicate this contention is low. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/llist.h | 23 +++++++++++++++++++++++ include/linux/tty.h | 8 ++++++-- 2 files changed, 29 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/llist.h b/include/linux/llist.h index cdaa7f023899..8828a78dec9a 100644 --- a/include/linux/llist.h +++ b/include/linux/llist.h @@ -124,6 +124,29 @@ static inline void init_llist_head(struct llist_head *list) &(pos)->member != NULL; \ (pos) = llist_entry((pos)->member.next, typeof(*(pos)), member)) +/** + * llist_for_each_entry_safe - iterate over some deleted entries of lock-less list of given type + * safe against removal of list entry + * @pos: the type * to use as a loop cursor. + * @n: another type * to use as temporary storage + * @node: the first entry of deleted list entries. + * @member: the name of the llist_node with the struct. + * + * In general, some entries of the lock-less list can be traversed + * safely only after being removed from list, so start with an entry + * instead of list head. + * + * If being used on entries deleted from lock-less list directly, the + * traverse order is from the newest to the oldest added entry. If + * you want to traverse from the oldest to the newest, you must + * reverse the order by yourself before traversing. + */ +#define llist_for_each_entry_safe(pos, n, node, member) \ + for (pos = llist_entry((node), typeof(*pos), member); \ + &pos->member != NULL && \ + (n = llist_entry(pos->member.next, typeof(*n), member), true); \ + pos = n) + /** * llist_empty - tests whether a lock-less list is empty * @head: the list to test diff --git a/include/linux/tty.h b/include/linux/tty.h index 87bbaa31ebf5..5043b12f23ea 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -11,6 +11,7 @@ #include #include #include +#include @@ -30,7 +31,10 @@ #define __DISABLED_CHAR '\0' struct tty_buffer { - struct tty_buffer *next; + union { + struct tty_buffer *next; + struct llist_node free; + }; int used; int size; int commit; @@ -65,7 +69,7 @@ struct tty_bufhead { spinlock_t lock; struct tty_buffer *head; /* Queue head */ struct tty_buffer *tail; /* Active buffer */ - struct tty_buffer *free; /* Free queue head */ + struct llist_head free; /* Free queue head */ int memory_used; /* Buffer space used excluding free queue */ }; -- cgit v1.2.3 From 7391ee16950e772076d321792d9fbf030f921345 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:07 -0400 Subject: tty: Simplify flip buffer list with 0-sized sentinel Use a 0-sized sentinel to avoid assigning the head ptr from the driver side thread. This also eliminates testing head/tail for NULL. When the sentinel is first 'consumed' by the buffer work (or by tty_buffer_flush()), it is detached from the list but not freed nor added to the free list. Both buffer work and tty_buffer_flush() continue to preserve at least 1 flip buffer to which head & tail is pointed. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 5043b12f23ea..2e93eb831c61 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -67,6 +67,7 @@ static inline char *flag_buf_ptr(struct tty_buffer *b, int ofs) struct tty_bufhead { struct work_struct work; spinlock_t lock; + struct tty_buffer sentinel; struct tty_buffer *head; /* Queue head */ struct tty_buffer *tail; /* Active buffer */ struct llist_head free; /* Free queue head */ -- cgit v1.2.3 From 7bfe0b7116be207cf2204ae06335cc89d8f8ee02 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:08 -0400 Subject: tty: Track flip buffer memory limit atomically Lockless flip buffers require atomically updating the bytes-in-use watermark. The pty driver also peeks at the watermark value to limit memory consumption to a much lower value than the default; query the watermark with new fn, tty_buffer_space_avail(). Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 3 +-- include/linux/tty_flip.h | 1 + 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 2e93eb831c61..7c124541f011 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -71,8 +71,7 @@ struct tty_bufhead { struct tty_buffer *head; /* Queue head */ struct tty_buffer *tail; /* Active buffer */ struct llist_head free; /* Free queue head */ - int memory_used; /* Buffer space used excluding - free queue */ + atomic_t memory_used; /* In-use buffers excluding free list */ }; /* * When a break, frame error, or parity error happens, these codes are diff --git a/include/linux/tty_flip.h b/include/linux/tty_flip.h index ad0303994c32..6944ed2ce692 100644 --- a/include/linux/tty_flip.h +++ b/include/linux/tty_flip.h @@ -1,6 +1,7 @@ #ifndef _LINUX_TTY_FLIP_H #define _LINUX_TTY_FLIP_H +extern int tty_buffer_space_avail(struct tty_port *port); extern int tty_buffer_request_room(struct tty_port *port, size_t size); extern int tty_insert_flip_string_flags(struct tty_port *port, const unsigned char *chars, const char *flags, size_t size); -- cgit v1.2.3 From e9975fdec0138f1b2a85b9624e41660abd9865d4 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:10 -0400 Subject: tty: Ensure single-threaded flip buffer consumer with mutex The buffer work may race with parallel tty_buffer_flush. Use a mutex to guarantee exclusive modify access to the head flip buffer. Remove the unneeded spin lock. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 7c124541f011..1c8fef0e3ff6 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -66,7 +66,7 @@ static inline char *flag_buf_ptr(struct tty_buffer *b, int ofs) struct tty_bufhead { struct work_struct work; - spinlock_t lock; + struct mutex flush_mutex; struct tty_buffer sentinel; struct tty_buffer *head; /* Queue head */ struct tty_buffer *tail; /* Active buffer */ -- cgit v1.2.3 From d7a68be4f265be10e24be931c257af30ca55566b Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:11 -0400 Subject: tty: Only perform flip buffer flush from tty_buffer_flush() Now that dropping the buffer lock is not necessary (as result of converting the spin lock to a mutex), the flip buffer flush no longer needs to be handled by the buffer work. Simply signal a flush is required; the buffer work will exit the i/o loop, which allows tty_buffer_flush() to proceed. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 1c8fef0e3ff6..1d5bacca3652 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -213,7 +213,6 @@ struct tty_port { wait_queue_head_t delta_msr_wait; /* Modem status change */ unsigned long flags; /* TTY flags ASY_*/ unsigned long iflags; /* TTYP_ internal flags */ -#define TTYP_FLUSHING 1 /* Flushing to ldisc in progress */ #define TTYP_FLUSHPENDING 2 /* Queued buffer flush pending */ unsigned char console:1, /* port is a console */ low_latency:1; /* direct buffer flush */ -- cgit v1.2.3 From 8c1fb49ba107c7db9441ef6ec0ab5830d112cc2a Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:12 -0400 Subject: tty: Avoid false-sharing flip buffer ptrs Separate the head and tail ptrs to avoid cache-line contention (so called 'false-sharing') between concurrent threads. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 1d5bacca3652..b8e8adf95bf3 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -65,13 +65,13 @@ static inline char *flag_buf_ptr(struct tty_buffer *b, int ofs) struct tty_bufhead { + struct tty_buffer *head; /* Queue head */ struct work_struct work; struct mutex flush_mutex; struct tty_buffer sentinel; - struct tty_buffer *head; /* Queue head */ - struct tty_buffer *tail; /* Active buffer */ struct llist_head free; /* Free queue head */ atomic_t memory_used; /* In-use buffers excluding free list */ + struct tty_buffer *tail; /* Active buffer */ }; /* * When a break, frame error, or parity error happens, these codes are -- cgit v1.2.3 From 0f56bd2f6a97d8b0eb5c8f9bc04b83a6c16d1d48 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:13 -0400 Subject: tty: Use non-atomic state to signal flip buffer flush pending Atomic bit ops are no longer required to indicate a flip buffer flush is pending, as the flush_mutex is sufficient barrier. Remove the unnecessary port .iflags field and localize flip buffer state to struct tty_bufhead. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index b8e8adf95bf3..991575fe3451 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -68,6 +68,7 @@ struct tty_bufhead { struct tty_buffer *head; /* Queue head */ struct work_struct work; struct mutex flush_mutex; + unsigned int flushpending:1; struct tty_buffer sentinel; struct llist_head free; /* Free queue head */ atomic_t memory_used; /* In-use buffers excluding free list */ @@ -212,8 +213,6 @@ struct tty_port { wait_queue_head_t close_wait; /* Close waiters */ wait_queue_head_t delta_msr_wait; /* Modem status change */ unsigned long flags; /* TTY flags ASY_*/ - unsigned long iflags; /* TTYP_ internal flags */ -#define TTYP_FLUSHPENDING 2 /* Queued buffer flush pending */ unsigned char console:1, /* port is a console */ low_latency:1; /* direct buffer flush */ struct mutex mutex; /* Locking */ -- cgit v1.2.3 From a7c8d58c79853adeebf0a1ddc9c63e433b4d97f1 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:15 -0400 Subject: tty: Fix unsafe vt paste_selection() Convert the tty_buffer_flush() exclusion mechanism to a public interface - tty_buffer_lock/unlock_exclusive() - and use the interface to safely write the paste selection to the line discipline. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 4 ++-- include/linux/tty_flip.h | 3 +++ 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 991575fe3451..7a9a3b0a6b5a 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -67,8 +67,8 @@ static inline char *flag_buf_ptr(struct tty_buffer *b, int ofs) struct tty_bufhead { struct tty_buffer *head; /* Queue head */ struct work_struct work; - struct mutex flush_mutex; - unsigned int flushpending:1; + struct mutex lock; + atomic_t priority; struct tty_buffer sentinel; struct llist_head free; /* Free queue head */ atomic_t memory_used; /* In-use buffers excluding free list */ diff --git a/include/linux/tty_flip.h b/include/linux/tty_flip.h index 6944ed2ce692..21ddd7d9ea1f 100644 --- a/include/linux/tty_flip.h +++ b/include/linux/tty_flip.h @@ -32,4 +32,7 @@ static inline int tty_insert_flip_string(struct tty_port *port, return tty_insert_flip_string_fixed_flag(port, chars, TTY_NORMAL, size); } +extern void tty_buffer_lock_exclusive(struct tty_port *port); +extern void tty_buffer_unlock_exclusive(struct tty_port *port); + #endif /* _LINUX_TTY_FLIP_H */ -- cgit v1.2.3 From 9114fe8ccf1871f630d2c14cd60e5f455b015459 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:16 -0400 Subject: tty: Remove private constant from global namespace TTY_BUFFER_PAGE is only used within drivers/tty/tty_buffer.c; relocate to that file scope. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 7a9a3b0a6b5a..5fd5d6f1ebc4 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -53,17 +53,6 @@ static inline char *flag_buf_ptr(struct tty_buffer *b, int ofs) return (char *)char_buf_ptr(b, ofs) + b->size; } -/* - * We default to dicing tty buffer allocations to this many characters - * in order to avoid multiple page allocations. We know the size of - * tty_buffer itself but it must also be taken into account that the - * the buffer is 256 byte aligned. See tty_buffer_find for the allocation - * logic this must match - */ - -#define TTY_BUFFER_PAGE (((PAGE_SIZE - sizeof(struct tty_buffer)) / 2) & ~0xFF) - - struct tty_bufhead { struct tty_buffer *head; /* Queue head */ struct work_struct work; -- cgit v1.2.3 From 40d5e0905a03601d40cd4e46b8690093c2355d03 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 10:21:17 -0400 Subject: n_tty: Fix EOF push handling In canonical mode, an EOF which is not the first character of the line causes read() to complete and return the number of characters read so far (commonly referred to as EOF push). However, if the previous read() returned because the user buffer was full _and_ the next character is an EOF not at the beginning of the line, read() must not return 0, thus mistakenly indicating the end-of-file condition. The TTY_PUSH flag is used to indicate an EOF was received which is not at the beginning of the line. Because the EOF push condition is evaluated by a thread other than the read(), multiple EOF pushes can cause a premature end-of-file to be indicated. Instead, discover the 'EOF push as first read character' condition from the read() thread itself, and restart the i/o loop if detected. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 5fd5d6f1ebc4..554b732d8b55 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -304,7 +304,6 @@ struct tty_file_private { #define TTY_EXCLUSIVE 3 /* Exclusive open mode */ #define TTY_DEBUG 4 /* Debugging */ #define TTY_DO_WRITE_WAKEUP 5 /* Call write_wakeup after queuing new */ -#define TTY_PUSH 6 /* n_tty private */ #define TTY_CLOSING 7 /* ->close() in progress */ #define TTY_LDISC_OPEN 11 /* Line discipline is open */ #define TTY_PTY_LOCK 16 /* pty private */ -- cgit v1.2.3 From f484f7a6bc6f0f871627cc1f83f56077a5dc6e47 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Wed, 24 Jul 2013 10:26:42 +0200 Subject: regmap: irq: make flags bool and put them in a bitfield This patch makes mask/wake_invert bool and puts all flags into a bitfield for consistency and to save some space. Signed-off-by: Philipp Zabel Signed-off-by: Mark Brown --- include/linux/regmap.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 34ebe7778033..99b0f7cad75c 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -486,10 +486,10 @@ struct regmap_irq_chip { unsigned int ack_base; unsigned int wake_base; unsigned int irq_reg_stride; - bool init_ack_masked; - unsigned int mask_invert; - unsigned int wake_invert; - bool runtime_pm; + bool init_ack_masked:1; + bool mask_invert:1; + bool wake_invert:1; + bool runtime_pm:1; int num_regs; -- cgit v1.2.3 From 68622bdfefb969fd7cf710545d7e758a732ab01d Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Wed, 24 Jul 2013 10:26:48 +0200 Subject: regmap: irq: document mask/wake_invert flags Signed-off-by: Philipp Zabel Signed-off-by: Mark Brown --- include/linux/regmap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 99b0f7cad75c..a3c68aad2381 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -471,6 +471,8 @@ struct regmap_irq { * @wake_base: Base address for wake enables. If zero unsupported. * @irq_reg_stride: Stride to use for chips where registers are not contiguous. * @init_ack_masked: Ack all masked interrupts once during initalization. + * @mask_invert: Inverted mask register: cleared bits are masked out. + * @wake_invert: Inverted wake register: cleared bits are wake enabled. * @runtime_pm: Hold a runtime PM lock on the device when accessing it. * * @num_regs: Number of registers in each control bank. -- cgit v1.2.3 From dee4a0be69c0e2996188e0c46478eadc280a8954 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Wed, 24 Jul 2013 16:43:51 -0400 Subject: tty: Fix lock order in tty_do_resize() Commits 6a1c0680cf3ba94356ecd58833e1540c93472a57 and 9356b535fcb71db494fc434acceb79f56d15bda2, respectively 'tty: Convert termios_mutex to termios_rwsem' and 'n_tty: Access termios values safely' introduced a circular lock dependency with console_lock and termios_rwsem. The lockdep report [1] shows that n_tty_write() will attempt to claim console_lock while holding the termios_rwsem, whereas tty_do_resize() may already hold the console_lock while claiming the termios_rwsem. Since n_tty_write() and tty_do_resize() do not contend over the same data -- the tty->winsize structure -- correct the lock dependency by introducing a new lock which specifically serializes access to tty->winsize only. [1] Lockdep report ====================================================== [ INFO: possible circular locking dependency detected ] 3.10.0-0+tip-xeon+lockdep #0+tip Not tainted ------------------------------------------------------- modprobe/277 is trying to acquire lock: (&tty->termios_rwsem){++++..}, at: [] tty_do_resize+0x36/0xe0 but task is already holding lock: ((fb_notifier_list).rwsem){.+.+.+}, at: [] __blocking_notifier_call_chain+0x56/0xc0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 ((fb_notifier_list).rwsem){.+.+.+}: [] lock_acquire+0x92/0x1f0 [] down_read+0x47/0x5c [] __blocking_notifier_call_chain+0x56/0xc0 [] blocking_notifier_call_chain+0x16/0x20 [] fb_notifier_call_chain+0x1b/0x20 [] register_framebuffer+0x1e2/0x320 [] drm_fb_helper_initial_config+0x371/0x540 [drm_kms_helper] [] nouveau_fbcon_init+0x105/0x140 [nouveau] [] nouveau_drm_load+0x43f/0x610 [nouveau] [] drm_get_pci_dev+0x17e/0x2a0 [drm] [] nouveau_drm_probe+0x25a/0x2a0 [nouveau] [] local_pci_probe+0x4b/0x80 [] pci_device_probe+0x111/0x120 [] driver_probe_device+0x8b/0x3a0 [] __driver_attach+0xab/0xb0 [] bus_for_each_dev+0x5d/0xa0 [] driver_attach+0x1e/0x20 [] bus_add_driver+0x111/0x290 [] driver_register+0x77/0x170 [] __pci_register_driver+0x64/0x70 [] drm_pci_init+0x11a/0x130 [drm] [] nouveau_drm_init+0x4d/0x1000 [nouveau] [] do_one_initcall+0xea/0x1a0 [] load_module+0x123b/0x1bf0 [] SyS_init_module+0xd7/0x120 [] system_call_fastpath+0x16/0x1b -> #1 (console_lock){+.+.+.}: [] lock_acquire+0x92/0x1f0 [] console_lock+0x77/0x80 [] con_flush_chars+0x31/0x50 [] n_tty_write+0x1ec/0x4d0 [] tty_write+0x159/0x2e0 [] redirected_tty_write+0xb5/0xc0 [] vfs_write+0xc5/0x1f0 [] SyS_write+0x55/0xa0 [] system_call_fastpath+0x16/0x1b -> #0 (&tty->termios_rwsem){++++..}: [] __lock_acquire+0x1c43/0x1d30 [] lock_acquire+0x92/0x1f0 [] down_write+0x44/0x70 [] tty_do_resize+0x36/0xe0 [] vc_do_resize+0x3e1/0x4c0 [] vc_resize+0x1f/0x30 [] fbcon_init+0x385/0x5a0 [] visual_init+0xbc/0x120 [] do_bind_con_driver+0x163/0x320 [] do_take_over_console+0x61/0x70 [] do_fbcon_takeover+0x63/0xc0 [] fbcon_event_notify+0x715/0x820 [] notifier_call_chain+0x5d/0x110 [] __blocking_notifier_call_chain+0x6c/0xc0 [] blocking_notifier_call_chain+0x16/0x20 [] fb_notifier_call_chain+0x1b/0x20 [] register_framebuffer+0x1e2/0x320 [] drm_fb_helper_initial_config+0x371/0x540 [drm_kms_helper] [] nouveau_fbcon_init+0x105/0x140 [nouveau] [] nouveau_drm_load+0x43f/0x610 [nouveau] [] drm_get_pci_dev+0x17e/0x2a0 [drm] [] nouveau_drm_probe+0x25a/0x2a0 [nouveau] [] local_pci_probe+0x4b/0x80 [] pci_device_probe+0x111/0x120 [] driver_probe_device+0x8b/0x3a0 [] __driver_attach+0xab/0xb0 [] bus_for_each_dev+0x5d/0xa0 [] driver_attach+0x1e/0x20 [] bus_add_driver+0x111/0x290 [] driver_register+0x77/0x170 [] __pci_register_driver+0x64/0x70 [] drm_pci_init+0x11a/0x130 [drm] [] nouveau_drm_init+0x4d/0x1000 [nouveau] [] do_one_initcall+0xea/0x1a0 [] load_module+0x123b/0x1bf0 [] SyS_init_module+0xd7/0x120 [] system_call_fastpath+0x16/0x1b other info that might help us debug this: Chain exists of: &tty->termios_rwsem --> console_lock --> (fb_notifier_list).rwsem Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock((fb_notifier_list).rwsem); lock(console_lock); lock((fb_notifier_list).rwsem); lock(&tty->termios_rwsem); *** DEADLOCK *** 7 locks held by modprobe/277: #0: (&__lockdep_no_validate__){......}, at: [] __driver_attach+0x5b/0xb0 #1: (&__lockdep_no_validate__){......}, at: [] __driver_attach+0x69/0xb0 #2: (drm_global_mutex){+.+.+.}, at: [] drm_get_pci_dev+0xbd/0x2a0 [drm] #3: (registration_lock){+.+.+.}, at: [] register_framebuffer+0x25/0x320 #4: (&fb_info->lock){+.+.+.}, at: [] lock_fb_info+0x26/0x60 #5: (console_lock){+.+.+.}, at: [] register_framebuffer+0x1d4/0x320 #6: ((fb_notifier_list).rwsem){.+.+.+}, at: [] __blocking_notifier_call_chain+0x56/0xc0 stack backtrace: CPU: 0 PID: 277 Comm: modprobe Not tainted 3.10.0-0+tip-xeon+lockdep #0+tip Hardware name: Dell Inc. Precision WorkStation T5400 /0RW203, BIOS A11 04/30/2012 ffffffff8213e5e0 ffff8802aa2fb298 ffffffff81755f19 ffff8802aa2fb2e8 ffffffff8174f506 ffff8802aa2fa000 ffff8802aa2fb378 ffff8802aa2ea8e8 ffff8802aa2ea910 ffff8802aa2ea8e8 0000000000000006 0000000000000007 Call Trace: [] dump_stack+0x19/0x1b [] print_circular_bug+0x1fb/0x20c [] __lock_acquire+0x1c43/0x1d30 [] ? mark_held_locks+0xae/0x120 [] ? trace_hardirqs_on_caller+0x105/0x1d0 [] lock_acquire+0x92/0x1f0 [] ? tty_do_resize+0x36/0xe0 [] down_write+0x44/0x70 [] ? tty_do_resize+0x36/0xe0 [] tty_do_resize+0x36/0xe0 [] vc_do_resize+0x3e1/0x4c0 [] vc_resize+0x1f/0x30 [] fbcon_init+0x385/0x5a0 [] visual_init+0xbc/0x120 [] do_bind_con_driver+0x163/0x320 [] do_take_over_console+0x61/0x70 [] do_fbcon_takeover+0x63/0xc0 [] fbcon_event_notify+0x715/0x820 [] notifier_call_chain+0x5d/0x110 [] __blocking_notifier_call_chain+0x6c/0xc0 [] blocking_notifier_call_chain+0x16/0x20 [] fb_notifier_call_chain+0x1b/0x20 [] register_framebuffer+0x1e2/0x320 [] drm_fb_helper_initial_config+0x371/0x540 [drm_kms_helper] [] ? kmemleak_alloc+0x5b/0xc0 [] ? kmem_cache_alloc_trace+0x104/0x290 [] ? drm_fb_helper_single_add_all_connectors+0x81/0xf0 [drm_kms_helper] [] nouveau_fbcon_init+0x105/0x140 [nouveau] [] nouveau_drm_load+0x43f/0x610 [nouveau] [] drm_get_pci_dev+0x17e/0x2a0 [drm] [] nouveau_drm_probe+0x25a/0x2a0 [nouveau] [] ? _raw_spin_unlock_irqrestore+0x42/0x80 [] local_pci_probe+0x4b/0x80 [] pci_device_probe+0x111/0x120 [] driver_probe_device+0x8b/0x3a0 [] __driver_attach+0xab/0xb0 [] ? driver_probe_device+0x3a0/0x3a0 [] bus_for_each_dev+0x5d/0xa0 [] driver_attach+0x1e/0x20 [] bus_add_driver+0x111/0x290 [] ? 0xffffffffa0229fff [] driver_register+0x77/0x170 [] ? 0xffffffffa0229fff [] __pci_register_driver+0x64/0x70 [] drm_pci_init+0x11a/0x130 [drm] [] ? 0xffffffffa0229fff [] ? 0xffffffffa0229fff [] nouveau_drm_init+0x4d/0x1000 [nouveau] [] do_one_initcall+0xea/0x1a0 [] load_module+0x123b/0x1bf0 [] ? ddebug_proc_open+0xb0/0xb0 [] ? trace_hardirqs_on_thunk+0x3a/0x3f [] SyS_init_module+0xd7/0x120 [] system_call_fastpath+0x16/0x1b Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 554b732d8b55..64f864651d86 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -245,6 +245,7 @@ struct tty_struct { struct mutex legacy_mutex; struct mutex throttle_mutex; struct rw_semaphore termios_rwsem; + struct mutex winsize_mutex; spinlock_t ctrl_lock; /* Termios values are protected by the termios rwsem */ struct ktermios termios, termios_locked; @@ -254,7 +255,7 @@ struct tty_struct { struct pid *session; unsigned long flags; int count; - struct winsize winsize; /* termios rwsem */ + struct winsize winsize; /* winsize_mutex */ unsigned char stopped:1, hw_stopped:1, flow_stopped:1, packet:1; unsigned char ctrl_status; /* ctrl_lock */ unsigned int receive_room; /* Bytes free for queue */ -- cgit v1.2.3 From 10e232c597ac757e7f8600649f7e872e86de190f Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 28 Jun 2013 09:38:12 +0800 Subject: USB: check sg buffer size in usb_submit_urb USB spec stats that short packet can only appear at the end of transfer. Because lost of HC(EHCI/UHCI/OHCI/...) can't build a full packet from discontinuous buffers, we introduce the limit in usb_submit_urb() to avoid such kind of bad sg buffers coming from driver. The limit might be a bit strict: - platform has iommu to do sg list mapping - some host controllers may support to build full packet from discontinuous buffers. But considered that most of HCs don't support that, and driver need work well or keep consistent on different HCs and ARCHs, we have to introduce the limit. Currently, only usbtest is reported to pass such sg buffers to HC, and other users(mass storage, usbfs) don't have the problem. We don't check it on USB wireless device, because: - wireless devices can't be attached to common USB bus(EHCI/UHCI/OHCI/...) - the max packet size of endpoint may be odd, and often can't devide 4KB which is a typical usage in usb mass storage application Reported-by: Konstantin Filatov Reported-by: Denis V. Lunev Cc: Felipe Balbi Acked-by: Alan Stern Signed-off-by: Ming Lei Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index a232b7ece1f6..e99b2a114af4 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1258,7 +1258,9 @@ typedef void (*usb_complete_t)(struct urb *); * the device driver is saying that it provided this DMA address, * which the host controller driver should use in preference to the * transfer_buffer. - * @sg: scatter gather buffer list + * @sg: scatter gather buffer list, the buffer size of each element in + * the list (except the last) must be divisible by the endpoint's + * max packet size * @num_mapped_sgs: (internal) number of mapped sg entries * @num_sgs: number of entries in the sg list * @transfer_buffer_length: How big is transfer_buffer. The transfer may -- cgit v1.2.3 From 3784b6d64dc52ed3fbebad61a85ab9b7a687a167 Mon Sep 17 00:00:00 2001 From: Robin Gong Date: Thu, 25 Jul 2013 11:33:18 +0800 Subject: regulator: pfuze100: add pfuze100 regulator driver Add pfuze100 regulator driver. Signed-off-by: Robin Gong Tested-by: Steffen Trumtrar Signed-off-by: Mark Brown --- include/linux/regulator/pfuze100.h | 44 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) create mode 100644 include/linux/regulator/pfuze100.h (limited to 'include/linux') diff --git a/include/linux/regulator/pfuze100.h b/include/linux/regulator/pfuze100.h new file mode 100644 index 000000000000..65d550bf3954 --- /dev/null +++ b/include/linux/regulator/pfuze100.h @@ -0,0 +1,44 @@ +/* + * Copyright (C) 2011-2013 Freescale Semiconductor, Inc. All Rights Reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + */ +#ifndef __LINUX_REG_PFUZE100_H +#define __LINUX_REG_PFUZE100_H + +#define PFUZE100_SW1AB 0 +#define PFUZE100_SW1C 1 +#define PFUZE100_SW2 2 +#define PFUZE100_SW3A 3 +#define PFUZE100_SW3B 4 +#define PFUZE100_SW4 5 +#define PFUZE100_SWBST 6 +#define PFUZE100_VSNVS 7 +#define PFUZE100_VREFDDR 8 +#define PFUZE100_VGEN1 9 +#define PFUZE100_VGEN2 10 +#define PFUZE100_VGEN3 11 +#define PFUZE100_VGEN4 12 +#define PFUZE100_VGEN5 13 +#define PFUZE100_VGEN6 14 +#define PFUZE100_MAX_REGULATOR 15 + +struct regulator_init_data; + +struct pfuze_regulator_platform_data { + struct regulator_init_data *init_data[PFUZE100_MAX_REGULATOR]; +}; + +#endif /* __LINUX_REG_PFUZE100_H */ -- cgit v1.2.3 From 928bea964827d7824b548c1f8e06eccbbc4d0d7d Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Mon, 22 Jul 2013 14:37:17 -0700 Subject: PCI: Delay enabling bridges until they're needed We currently enable PCI bridges after scanning a bus and assigning resources. This is often done in arch code. This patch changes this so we don't enable a bridge until necessary, i.e., until we enable a PCI device behind the bridge. We do this in the generic pci_enable_device() path, so this also removes the arch-specific code to enable bridges. [bhelgaas: changelog] Signed-off-by: Yinghai Lu Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 0fd1f1582fa1..8cd1e6f30acd 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1043,7 +1043,6 @@ int __must_check pci_bus_alloc_resource(struct pci_bus *bus, resource_size_t, resource_size_t), void *alignf_data); -void pci_enable_bridges(struct pci_bus *bus); /* Proper probing supporting hot-pluggable devices */ int __must_check __pci_register_driver(struct pci_driver *, struct module *, -- cgit v1.2.3 From 39772038ea93e85ea4f1307ec9c1f48a063d89a0 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Mon, 22 Jul 2013 14:37:18 -0700 Subject: PCI: Assign resources for hot-added host bridge more aggressively When hot-adding an ACPI host bridge, use pci_assign_unassigned_root_bus_resources() instead of pci_assign_unassigned_bus_resources(). The former is more aggressive and will release and reassign existing resources if necessary. This is safe at hot-add time because no drivers are bound to devices below the new host bridge yet. [bhelgaas: changelog, split __init changes out for reviewability] Signed-off-by: Yinghai Lu 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 8cd1e6f30acd..e494c90a00d1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1003,6 +1003,7 @@ int pci_claim_resource(struct pci_dev *, int); void pci_assign_unassigned_resources(void); void pci_assign_unassigned_bridge_resources(struct pci_dev *bridge); void pci_assign_unassigned_bus_resources(struct pci_bus *bus); +void pci_assign_unassigned_root_bus_resources(struct pci_bus *bus); void pdev_enable_device(struct pci_dev *); int pci_enable_resources(struct pci_dev *, int mask); void pci_fixup_irqs(u8 (*)(struct pci_dev *, u8 *), -- cgit v1.2.3 From 42189d854f174e7b29e0fdb4da9984ba63126a92 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Tue, 2 Jul 2013 10:50:15 +0300 Subject: usb: clamp bInterval to allowed range bInterval must be within the range 1 - 16 when running at High/Super speed, and within the range 1 - 255 when running at Full/Low speed. In order to catch drivers passing a too large bInterval on Super/High speed scenarios (thus overflowing urb->interval), let's clamp() the argument to the allowed ranges. Signed-off-by: Felipe Balbi Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index e99b2a114af4..eb4252a0da7e 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1547,10 +1547,16 @@ static inline void usb_fill_int_urb(struct urb *urb, urb->transfer_buffer_length = buffer_length; urb->complete = complete_fn; urb->context = context; - if (dev->speed == USB_SPEED_HIGH || dev->speed == USB_SPEED_SUPER) + + if (dev->speed == USB_SPEED_HIGH || dev->speed == USB_SPEED_SUPER) { + /* make sure interval is within allowed range */ + interval = clamp(interval, 1, 16); + urb->interval = 1 << (interval - 1); - else + } else { urb->interval = interval; + } + urb->start_frame = -1; } -- cgit v1.2.3 From 323f54ed0f3ce20e9946c961fc928ccdb80d9345 Mon Sep 17 00:00:00 2001 From: Tom Rini Date: Thu, 25 Jul 2013 14:26:10 -0400 Subject: numa: Mark __node_set() as __always_inline It is posible for some compilers to decide that __node_set() does not need to be made turned into an inline function. When the compiler does this on an __init function calling it on __initdata we get a section mismatch warning now. Use __always_inline to ensure that we will be inlined. Reported-by: Paul Bolle Cc: Jianpeng Ma Cc: Rusty Russell Cc: Lai Jiangshan Cc: Yasuaki Ishimatsu Cc: Wen Congyang Cc: Jiang Liu Cc: KOSAKI Motohiro Cc: Minchan Kim Cc: Mel Gorman Cc: David Rientjes Cc: Yinghai Lu Cc: Greg KH Signed-off-by: Tom Rini Link: http://lkml.kernel.org/r/1374776770-32361-1-git-send-email-trini@ti.com Signed-off-by: Ingo Molnar --- include/linux/nodemask.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 4e2cbfa640b7..58b9a02c38d2 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -98,8 +98,17 @@ typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t; extern nodemask_t _unused_nodemask_arg_; +/* + * The inline keyword gives the compiler room to decide to inline, or + * not inline a function as it sees best. However, as these functions + * are called in both __init and non-__init functions, if they are not + * inlined we will end up with a section mis-match error (of the type of + * freeable items not being freed). So we must use __always_inline here + * to fix the problem. If other functions in the future also end up in + * this situation they will also need to be annotated as __always_inline + */ #define node_set(node, dst) __node_set((node), &(dst)) -static inline void __node_set(int node, volatile nodemask_t *dstp) +static __always_inline void __node_set(int node, volatile nodemask_t *dstp) { set_bit(node, dstp->bits); } -- cgit v1.2.3 From c817a67ecba7c3c2aaa104796d78f160af60920d Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 27 Jun 2013 15:06:14 +0100 Subject: kobject: delayed kobject release: help find buggy drivers Implement debugging for kobject release functions. kobjects are reference counted, so the drop of the last reference to them is not predictable. However, the common case is for the last reference to be the kobject's removal from a subsystem, which results in the release function being immediately called. This can hide subtle bugs, which can occur when another thread holds a reference to the kobject at the same time that a kobject is removed. This results in the release method being delayed. In order to make these kinds of problems more visible, the following patch implements a delayed release; this has the effect that the release function will be out of order with respect to the removal of the kobject in the same manner that it would be if a reference was being held. This provides us with an easy way to allow driver writers to debug their drivers and fix otherwise hidden problems. Signed-off-by: Russell King Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 939b11268c86..de6dcbcc6ef7 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -26,6 +26,7 @@ #include #include #include +#include #define UEVENT_HELPER_PATH_LEN 256 #define UEVENT_NUM_ENVP 32 /* number of env pointers */ @@ -65,6 +66,9 @@ struct kobject { struct kobj_type *ktype; struct sysfs_dirent *sd; struct kref kref; +#ifdef CONFIG_DEBUG_KOBJECT_RELEASE + struct delayed_work release; +#endif unsigned int state_initialized:1; unsigned int state_in_sysfs:1; unsigned int state_add_uevent_sent:1; -- cgit v1.2.3 From cffe4e0e7413eb29fb8bd035c8b12b33a4b8522a Mon Sep 17 00:00:00 2001 From: Stratos Karafotis Date: Wed, 5 Jun 2013 19:01:50 +0300 Subject: cpufreq: Remove unused function __cpufreq_driver_getavg() The target frequency calculation method in the ondemand governor has changed and it is now independent of the measured average frequency. Consequently, the __cpufreq_driver_getavg() function and getavg member of struct cpufreq_driver are not used any more, so drop them. [rjw: Changelog] Signed-off-by: Stratos Karafotis Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 90d5a15120d5..e1fd215e16c9 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -216,10 +216,6 @@ extern int cpufreq_driver_target(struct cpufreq_policy *policy, extern int __cpufreq_driver_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation); - -extern int __cpufreq_driver_getavg(struct cpufreq_policy *policy, - unsigned int cpu); - int cpufreq_register_governor(struct cpufreq_governor *governor); void cpufreq_unregister_governor(struct cpufreq_governor *governor); @@ -258,8 +254,6 @@ struct cpufreq_driver { unsigned int (*get) (unsigned int cpu); /* optional */ - unsigned int (*getavg) (struct cpufreq_policy *policy, - unsigned int cpu); int (*bios_limit) (int cpu, unsigned int *limit); int (*exit) (struct cpufreq_policy *policy); -- cgit v1.2.3 From 102c9323c35a83789ad5ebd3c45fa8fb389add88 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Fri, 12 Jul 2013 17:07:27 -0400 Subject: tracing: Add __tracepoint_string() to export string pointers There are several tracepoints (mostly in RCU), that reference a string pointer and uses the print format of "%s" to display the string that exists in the kernel, instead of copying the actual string to the ring buffer (saves time and ring buffer space). But this has an issue with userspace tools that read the binary buffers that has the address of the string but has no access to what the string itself is. The end result is just output that looks like: rcu_dyntick: ffffffff818adeaa 1 0 rcu_dyntick: ffffffff818adeb5 0 140000000000000 rcu_dyntick: ffffffff818adeb5 0 140000000000000 rcu_utilization: ffffffff8184333b rcu_utilization: ffffffff8184333b The above is pretty useless when read by the userspace tools. Ideally we would want something that looks like this: rcu_dyntick: Start 1 0 rcu_dyntick: End 0 140000000000000 rcu_dyntick: Start 140000000000000 0 rcu_callback: rcu_preempt rhp=0xffff880037aff710 func=put_cred_rcu 0/4 rcu_callback: rcu_preempt rhp=0xffff880078961980 func=file_free_rcu 0/5 rcu_dyntick: End 0 1 The trace_printk() which also only stores the address of the string format instead of recording the string into the buffer itself, exports the mapping of kernel addresses to format strings via the printk_format file in the debugfs tracing directory. The tracepoint strings can use this same method and output the format to the same file and the userspace tools will be able to decipher the address without any modification. The tracepoint strings need its own section to save the strings because the trace_printk section will cause the trace_printk() buffers to be allocated if anything exists within the section. trace_printk() is only used for debugging and should never exist in the kernel, we can not use the trace_printk sections. Add a new tracepoint_str section that will also be examined by the output of the printk_format file. Cc: Paul E. McKenney Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 4372658c73ae..81af18a75f4d 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -357,6 +357,40 @@ do { \ __trace_printk(ip, fmt, ##args); \ } while (0) +/** + * tracepoint_string - register constant persistent string to trace system + * @str - a constant persistent string that will be referenced in tracepoints + * + * If constant strings are being used in tracepoints, it is faster and + * more efficient to just save the pointer to the string and reference + * that with a printf "%s" instead of saving the string in the ring buffer + * and wasting space and time. + * + * The problem with the above approach is that userspace tools that read + * the binary output of the trace buffers do not have access to the string. + * Instead they just show the address of the string which is not very + * useful to users. + * + * With tracepoint_string(), the string will be registered to the tracing + * system and exported to userspace via the debugfs/tracing/printk_formats + * file that maps the string address to the string text. This way userspace + * tools that read the binary buffers have a way to map the pointers to + * the ASCII strings they represent. + * + * The @str used must be a constant string and persistent as it would not + * make sense to show a string that no longer exists. But it is still fine + * to be used with modules, because when modules are unloaded, if they + * had tracepoints, the ring buffers are cleared too. As long as the string + * does not change during the life of the module, it is fine to use + * tracepoint_string() within a module. + */ +#define tracepoint_string(str) \ + ({ \ + static const char *___tp_str __tracepoint_string = str; \ + ___tp_str; \ + }) +#define __tracepoint_string __attribute__((section("__tracepoint_str"))) + #ifdef CONFIG_PERF_EVENTS struct perf_event; -- cgit v1.2.3 From 10d8b34a421716d55a4ff7c2d427c35e88b8fd60 Mon Sep 17 00:00:00 2001 From: Alexander Shiyan Date: Sat, 29 Jun 2013 10:44:17 +0400 Subject: serial: max310x: Driver rework This patch rework max310x driver. Major changes have been made: - Prepare driver to support ICs with more than one UART. - Prepare driver to support work with I2C-bus. The patch changes almost every function and can not be divided into parts. Signed-off-by: Alexander Shiyan Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_data/max310x.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/max310x.h b/include/linux/platform_data/max310x.h index 91648bf5fc5c..1aec0b620ac3 100644 --- a/include/linux/platform_data/max310x.h +++ b/include/linux/platform_data/max310x.h @@ -42,9 +42,8 @@ /* MAX310X platform data structure */ struct max310x_pdata { /* Flags global to driver */ - const u8 driver_flags:2; + const u8 driver_flags; #define MAX310X_EXT_CLK (0x00000001) /* External clock enable */ -#define MAX310X_AUTOSLEEP (0x00000002) /* Enable AutoSleep mode */ /* Flags global to UART port */ const u8 uart_flags[MAX310X_MAX_UARTS]; #define MAX310X_LOOPBACK (0x00000001) /* Loopback mode enable */ @@ -60,8 +59,6 @@ struct max310x_pdata { void (*init)(void); /* Called before finish */ void (*exit)(void); - /* Suspend callback */ - void (*suspend)(int do_suspend); }; #endif -- cgit v1.2.3 From 21fc509f1194c2fa06eff4c72238210089c29453 Mon Sep 17 00:00:00 2001 From: Alexander Shiyan Date: Sat, 29 Jun 2013 10:44:18 +0400 Subject: serial: max310x: Add MAX3109 support This patch adds support for MAX3109 (advanced dual universal asynchronous receiver-transmitter) into max310x driver. Signed-off-by: Alexander Shiyan Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_data/max310x.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/max310x.h b/include/linux/platform_data/max310x.h index 1aec0b620ac3..4c128eda26ba 100644 --- a/include/linux/platform_data/max310x.h +++ b/include/linux/platform_data/max310x.h @@ -1,5 +1,5 @@ /* - * Maxim (Dallas) MAX3107/8 serial driver + * Maxim (Dallas) MAX3107/8/9 serial driver * * Copyright (C) 2012 Alexander Shiyan * @@ -37,7 +37,7 @@ * }; */ -#define MAX310X_MAX_UARTS 1 +#define MAX310X_MAX_UARTS 2 /* MAX310X platform data structure */ struct max310x_pdata { -- cgit v1.2.3 From 003236d9ac4d02721867e47f7ad4371ab7f74689 Mon Sep 17 00:00:00 2001 From: Alexander Shiyan Date: Sat, 29 Jun 2013 10:44:19 +0400 Subject: serial: max310x: Add MAX14830 support This patch adds support for MAX14830 (advanced quad universal asynchronous receiver-transmitter) into max310x driver. Signed-off-by: Alexander Shiyan Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_data/max310x.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/max310x.h b/include/linux/platform_data/max310x.h index 4c128eda26ba..dd11dcd1a184 100644 --- a/include/linux/platform_data/max310x.h +++ b/include/linux/platform_data/max310x.h @@ -1,5 +1,5 @@ /* - * Maxim (Dallas) MAX3107/8/9 serial driver + * Maxim (Dallas) MAX3107/8/9, MAX14830 serial driver * * Copyright (C) 2012 Alexander Shiyan * @@ -37,7 +37,7 @@ * }; */ -#define MAX310X_MAX_UARTS 2 +#define MAX310X_MAX_UARTS 4 /* MAX310X platform data structure */ struct max310x_pdata { -- cgit v1.2.3 From 12197de2cdb2ded83db7b5a3a06f4b275fb8e62c Mon Sep 17 00:00:00 2001 From: Ian Abbott Date: Tue, 16 Jul 2013 16:14:38 +0100 Subject: pci_ids.h: move PCI_VENDOR_ID_AMCC here PCI_VENDOR_ID_AMCC is defined locally in "drivers/staging/comedi/comedidev.h" for a few comedi hardware drivers, namely "adl_pci9118", "addi_apci_1500" and "addi_apci_3120" (also "addi_apci_1710" but that is not currently built and will probably be removed soon). Move the define into "include/linux/pci_ids.h" as it is shared by several drivers (albeit all comedi drivers currently). PCI_VENDOR_ID_AMCC happens to have the same value (0x10e8) as PCI_VENDOR_ID_ADDIDATA_OLD. The vendor ID is actually assigned to Applied Micro Circuits Corporation and Addi-Data were using device IDs assigned by AMCC on some of their earlier PCI boards. The PCI_VENDOR_ID_ADDIDATA_OLD define is still being used by the "8250_pci" PCI serial board driver. Signed-off-by: Ian Abbott Acked-by: Bjorn Helgaas Signed-off-by: Greg Kroah-Hartman --- include/linux/pci_ids.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 3bed2e89611b..9d9911926598 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1311,6 +1311,8 @@ #define PCI_DEVICE_ID_IMS_TT128 0x9128 #define PCI_DEVICE_ID_IMS_TT3D 0x9135 +#define PCI_VENDOR_ID_AMCC 0x10e8 + #define PCI_VENDOR_ID_INTERG 0x10ea #define PCI_DEVICE_ID_INTERG_1682 0x1682 #define PCI_DEVICE_ID_INTERG_2000 0x2000 @@ -2256,7 +2258,7 @@ /* * ADDI-DATA GmbH communication cards */ -#define PCI_VENDOR_ID_ADDIDATA_OLD 0x10E8 +#define PCI_VENDOR_ID_ADDIDATA_OLD 0x10E8 /* actually AMCC */ #define PCI_VENDOR_ID_ADDIDATA 0x15B8 #define PCI_DEVICE_ID_ADDIDATA_APCI7500 0x7000 #define PCI_DEVICE_ID_ADDIDATA_APCI7420 0x7001 -- cgit v1.2.3 From fee8bf4b74e37bfeb8998a349cb788680eb3f634 Mon Sep 17 00:00:00 2001 From: Ian Abbott Date: Tue, 16 Jul 2013 16:14:41 +0100 Subject: pci_ids.h: remove PCI_VENDOR_ID_ADDIDATA_OLD and PCI_DEVICE_ID_ADDIDATA_APCI7800 These two defines are no longer used. They were only used by the PCI serial driver "8250_pci" to support the original ADDI-DATA APCI-7800 card. In that driver, PCI_VENDOR_ID_ADDIDATA_OLD has been replaced with PCI_VENDOR_ID_AMCC which has the same value (0x10e8), and PCI_DEVICE_ID_ADDIDATA_APCI7800 has been replaced with a local #define PCI_DEVICE_ID_AMCC_ADDIDATA_APCI7800 with the same value (0x818e). Signed-off-by: Ian Abbott Acked-by: Bjorn Helgaas Signed-off-by: Greg Kroah-Hartman --- include/linux/pci_ids.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 9d9911926598..6dec3d6abe0b 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2258,12 +2258,10 @@ /* * ADDI-DATA GmbH communication cards */ -#define PCI_VENDOR_ID_ADDIDATA_OLD 0x10E8 /* actually AMCC */ #define PCI_VENDOR_ID_ADDIDATA 0x15B8 #define PCI_DEVICE_ID_ADDIDATA_APCI7500 0x7000 #define PCI_DEVICE_ID_ADDIDATA_APCI7420 0x7001 #define PCI_DEVICE_ID_ADDIDATA_APCI7300 0x7002 -#define PCI_DEVICE_ID_ADDIDATA_APCI7800 0x818E #define PCI_DEVICE_ID_ADDIDATA_APCI7500_2 0x7009 #define PCI_DEVICE_ID_ADDIDATA_APCI7420_2 0x700A #define PCI_DEVICE_ID_ADDIDATA_APCI7300_2 0x700B -- cgit v1.2.3 From cf940ebe98e693aec2d10f9af2fb84eb55234e3c Mon Sep 17 00:00:00 2001 From: Andreas Platschek Date: Fri, 26 Jul 2013 06:46:37 +0200 Subject: tty: Remove dead code -> The ledptrs[] array is never initialized. -> There is no place where kbd->ledmode is set to LED_SHOW_MEM therefore the if statement does not make much sense. -> Since LED_SHOW_MEM is not used, it can be removed from the header file as well. Signed-off-by: Andreas Platschek Signed-off-by: Greg Kroah-Hartman --- include/linux/kbd_kern.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kbd_kern.h b/include/linux/kbd_kern.h index b7c8cdc1d422..cbfb171bbcba 100644 --- a/include/linux/kbd_kern.h +++ b/include/linux/kbd_kern.h @@ -36,10 +36,9 @@ struct kbd_struct { #define VC_CTRLRLOCK KG_CTRLR /* ctrlr lock mode */ unsigned char slockstate; /* for `sticky' Shift, Ctrl, etc. */ - unsigned char ledmode:2; /* one 2-bit value */ + unsigned char ledmode:1; #define LED_SHOW_FLAGS 0 /* traditional state */ #define LED_SHOW_IOCTL 1 /* only change leds upon ioctl */ -#define LED_SHOW_MEM 2 /* `heartbeat': peek into memory */ unsigned char ledflagstate:4; /* flags, not lights */ unsigned char default_ledflagstate:4; -- cgit v1.2.3 From 6741335bc7294548ac95cb1f4671991ff30da193 Mon Sep 17 00:00:00 2001 From: "K. Y. Srinivasan" Date: Tue, 2 Jul 2013 10:31:30 -0700 Subject: Drivers: hv: util: Fix a bug in version negotiation code for util services The current code picked the highest version advertised by the host. WS2012 R2 has implemented a protocol version for KVP that is not compatible with prior protocol versions of KVP. Fix the bug in the current code by explicitly specifying the protocol version that the guest can support. Signed-off-by: K. Y. Srinivasan Reviewed-by: Haiyang Zhang Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index fae8bac907ef..49949079cf47 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -27,6 +27,14 @@ #include +/* + * Framework version for util services. + */ + +#define UTIL_FW_MAJOR 3 +#define UTIL_FW_MINOR 0 +#define UTIL_FW_MAJOR_MINOR (UTIL_FW_MAJOR << 16 | UTIL_FW_MINOR) + /* * Implementation of host controlled snapshot of the guest. @@ -1494,7 +1502,7 @@ struct hyperv_service_callback { }; #define MAX_SRV_VER 0x7ffffff -extern void vmbus_prep_negotiate_resp(struct icmsg_hdr *, +extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *, struct icmsg_negotiate *, u8 *, int, int); -- cgit v1.2.3 From 410aee70f06da60dd8f78c3ec3346cc74c9bed46 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Sun, 30 Jun 2013 15:27:26 +0300 Subject: usb: phy: protect against NULL phy pointers In order to decrease the amount of work done by PHY users, allow NULL phy pointers to be passed. Signed-off-by: Felipe Balbi --- include/linux/usb/phy.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/phy.h b/include/linux/usb/phy.h index 44036808bf0f..6c0b1c513db7 100644 --- a/include/linux/usb/phy.h +++ b/include/linux/usb/phy.h @@ -142,7 +142,7 @@ extern void usb_remove_phy(struct usb_phy *); /* helpers for direct access thru low-level io interface */ static inline int usb_phy_io_read(struct usb_phy *x, u32 reg) { - if (x->io_ops && x->io_ops->read) + if (x && x->io_ops && x->io_ops->read) return x->io_ops->read(x, reg); return -EINVAL; @@ -150,7 +150,7 @@ static inline int usb_phy_io_read(struct usb_phy *x, u32 reg) static inline int usb_phy_io_write(struct usb_phy *x, u32 val, u32 reg) { - if (x->io_ops && x->io_ops->write) + if (x && x->io_ops && x->io_ops->write) return x->io_ops->write(x, val, reg); return -EINVAL; @@ -159,7 +159,7 @@ static inline int usb_phy_io_write(struct usb_phy *x, u32 val, u32 reg) static inline int usb_phy_init(struct usb_phy *x) { - if (x->init) + if (x && x->init) return x->init(x); return 0; @@ -168,14 +168,14 @@ usb_phy_init(struct usb_phy *x) static inline void usb_phy_shutdown(struct usb_phy *x) { - if (x->shutdown) + if (x && x->shutdown) x->shutdown(x); } static inline int usb_phy_vbus_on(struct usb_phy *x) { - if (!x->set_vbus) + if (!x || !x->set_vbus) return 0; return x->set_vbus(x, true); @@ -184,7 +184,7 @@ usb_phy_vbus_on(struct usb_phy *x) static inline int usb_phy_vbus_off(struct usb_phy *x) { - if (!x->set_vbus) + if (!x || !x->set_vbus) return 0; return x->set_vbus(x, false); @@ -258,7 +258,7 @@ usb_phy_set_power(struct usb_phy *x, unsigned mA) static inline int usb_phy_set_suspend(struct usb_phy *x, int suspend) { - if (x->set_suspend != NULL) + if (x && x->set_suspend != NULL) return x->set_suspend(x, suspend); else return 0; @@ -267,7 +267,7 @@ usb_phy_set_suspend(struct usb_phy *x, int suspend) static inline int usb_phy_notify_connect(struct usb_phy *x, enum usb_device_speed speed) { - if (x->notify_connect) + if (x && x->notify_connect) return x->notify_connect(x, speed); else return 0; @@ -276,7 +276,7 @@ usb_phy_notify_connect(struct usb_phy *x, enum usb_device_speed speed) static inline int usb_phy_notify_disconnect(struct usb_phy *x, enum usb_device_speed speed) { - if (x->notify_disconnect) + if (x && x->notify_disconnect) return x->notify_disconnect(x, speed); else return 0; -- cgit v1.2.3 From 1494a1f62bf7cf57345e9282c8189fe2a21fab64 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Sun, 30 Jun 2013 13:56:45 +0300 Subject: usb: common: introduce of_usb_get_maximum_speed() this helper will be used for controllers which want to work at a lower speed even though they support higher USB transfer rates. One such case is Texas Instruments' AM437x SoC where it uses a USB3 controller without a USB3 PHY, rendering the controller USB2-only. Signed-off-by: Felipe Balbi --- include/linux/usb/of.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/of.h b/include/linux/usb/of.h index a0ef405368b8..5a7cb9ebf0ef 100644 --- a/include/linux/usb/of.h +++ b/include/linux/usb/of.h @@ -7,16 +7,24 @@ #ifndef __LINUX_USB_OF_H #define __LINUX_USB_OF_H +#include #include #include #if IS_ENABLED(CONFIG_OF) enum usb_dr_mode of_usb_get_dr_mode(struct device_node *np); +enum usb_device_speed of_usb_get_maximum_speed(struct device_node *np); #else static inline enum usb_dr_mode of_usb_get_dr_mode(struct device_node *np) { return USB_DR_MODE_UNKNOWN; } + +static inline enum usb_device_speed +of_usb_get_maximum_speed(struct device_node *np) +{ + return USB_SPEED_UNKNOWN; +} #endif #if IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_USB_PHY) -- cgit v1.2.3 From 5702f75375aa9ecf8ad3431aef3fe6ce8c8dbd15 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Wed, 17 Jul 2013 11:09:49 +0300 Subject: usb: gadget: udc-core: move sysfs_notify() to a workqueue usb_gadget_set_state() will call sysfs_notify() which might sleep. Some users might want to call usb_gadget_set_state() from the very IRQ handler which actually changes the gadget state. Instead of having every UDC driver add their own workqueue for such a simple notification, we're adding it generically to our struct usb_gadget, so the details are hidden from all UDC drivers. Acked-by: Alan Stern Signed-off-by: Felipe Balbi --- include/linux/usb/gadget.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index f1b0dca60f12..942ef5e053bf 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -22,6 +22,7 @@ #include #include #include +#include #include struct usb_ep; @@ -475,6 +476,7 @@ struct usb_gadget_ops { /** * struct usb_gadget - represents a usb slave device + * @work: (internal use) Workqueue to be used for sysfs_notify() * @ops: Function pointers used to access hardware-specific operations. * @ep0: Endpoint zero, used when reading or writing responses to * driver setup() requests @@ -520,6 +522,7 @@ struct usb_gadget_ops { * device is acting as a B-Peripheral (so is_a_peripheral is false). */ struct usb_gadget { + struct work_struct work; /* readonly to gadget driver */ const struct usb_gadget_ops *ops; struct usb_ep *ep0; @@ -538,6 +541,7 @@ struct usb_gadget { unsigned out_epnum; unsigned in_epnum; }; +#define work_to_gadget(w) (container_of((w), struct usb_gadget, work)) static inline void set_gadget_data(struct usb_gadget *gadget, void *data) { dev_set_drvdata(&gadget->dev, data); } -- cgit v1.2.3 From f5b8c8b6d3b4697f28b818d8784e3e4b2a290022 Mon Sep 17 00:00:00 2001 From: Mikko Perttunen Date: Wed, 17 Jul 2013 10:37:49 +0300 Subject: usb: tegra: Use regulators instead of GPIOs for USB PHY VBUS The tegra ehci driver has enabled USB vbus regulators directly using GPIOs and the device tree attribute nvidia,vbus-gpio. This is ugly and causes error messages on boot when both the regulator driver and the ehci driver want access to the same GPIO. After this patch, usb vbus regulators for tegra usb phy devices are specified with the device tree attribute vbus-supply = <&x> where x is a regulator defined in the device tree. The old nvidia,vbus-gpio property is no longer supported. Signed-off-by: Mikko Perttunen Reviewed-by: Stephen Warren Tested-by: Stephen Warren Signed-off-by: Felipe Balbi --- include/linux/usb/tegra_usb_phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index d2ca919a5b73..2b5fa947980a 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -55,6 +55,7 @@ struct tegra_usb_phy { struct clk *clk; struct clk *pll_u; struct clk *pad_clk; + struct regulator *vbus; enum tegra_usb_phy_mode mode; void *config; struct usb_phy *ulpi; -- cgit v1.2.3 From 185d0fd570c121c0c3d4527842a097e50e3e7a79 Mon Sep 17 00:00:00 2001 From: Tuomas Tynkkynen Date: Thu, 25 Jul 2013 21:38:01 +0300 Subject: usb: phy: tegra: Remove unnecessary 'dev' field struct usb_phy already has a field for the device pointer, so this unnecessary field can be removed. Signed-off-by: Tuomas Tynkkynen Reviewed-by: Stephen Warren Tested-by: Stephen Warren Signed-off-by: Felipe Balbi --- include/linux/usb/tegra_usb_phy.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index 2b5fa947980a..c2bc7106aaa8 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -60,7 +60,6 @@ struct tegra_usb_phy { void *config; struct usb_phy *ulpi; struct usb_phy u_phy; - struct device *dev; bool is_legacy_phy; bool is_ulpi_phy; int reset_gpio; -- cgit v1.2.3 From 5fed6828318119656e243c4f0a11955cefc8eebd Mon Sep 17 00:00:00 2001 From: Tuomas Tynkkynen Date: Thu, 25 Jul 2013 21:38:04 +0300 Subject: ARM: tegra: Remove USB platform data USB-related platform data is not used anymore in the Tegra USB drivers, so remove all of it. Signed-off-by: Tuomas Tynkkynen Reviewed-by: Stephen Warren Tested-by: Stephen Warren Acked-by: Stephen Warren Signed-off-by: Felipe Balbi --- include/linux/platform_data/tegra_usb.h | 32 -------------------------------- include/linux/usb/tegra_usb_phy.h | 5 ----- 2 files changed, 37 deletions(-) delete mode 100644 include/linux/platform_data/tegra_usb.h (limited to 'include/linux') diff --git a/include/linux/platform_data/tegra_usb.h b/include/linux/platform_data/tegra_usb.h deleted file mode 100644 index 66c673fef408..000000000000 --- a/include/linux/platform_data/tegra_usb.h +++ /dev/null @@ -1,32 +0,0 @@ -/* - * Copyright (C) 2010 Google, Inc. - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ - -#ifndef _TEGRA_USB_H_ -#define _TEGRA_USB_H_ - -enum tegra_usb_operating_modes { - TEGRA_USB_DEVICE, - TEGRA_USB_HOST, - TEGRA_USB_OTG, -}; - -struct tegra_ehci_platform_data { - enum tegra_usb_operating_modes operating_mode; - /* power down the phy on bus suspend */ - int power_down_on_bus_suspend; - void *phy_config; - int vbus_gpio; -}; - -#endif /* _TEGRA_USB_H_ */ diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index c2bc7106aaa8..847415313ad2 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -28,11 +28,6 @@ struct tegra_utmip_config { u8 xcvr_lsrslew; }; -struct tegra_ulpi_config { - int reset_gpio; - const char *clk; -}; - enum tegra_usb_phy_port_speed { TEGRA_USB_PHY_PORT_SPEED_FULL = 0, TEGRA_USB_PHY_PORT_SPEED_LOW, -- cgit v1.2.3 From 3b102e8bc0e49d417c7d376af857537080335dbf Mon Sep 17 00:00:00 2001 From: Tuomas Tynkkynen Date: Thu, 25 Jul 2013 21:38:07 +0300 Subject: usb: phy: tegra: Remove custom PHY locating APIs The Tegra EHCI driver is no longer using these custom functions, so they can be removed. Signed-off-by: Tuomas Tynkkynen Reviewed-by: Stephen Warren Tested-by: Stephen Warren Signed-off-by: Felipe Balbi --- include/linux/usb/tegra_usb_phy.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index 847415313ad2..a095c98184d0 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -60,8 +60,6 @@ struct tegra_usb_phy { int reset_gpio; }; -struct usb_phy *tegra_usb_get_phy(struct device_node *dn); - void tegra_usb_phy_preresume(struct usb_phy *phy); void tegra_usb_phy_postresume(struct usb_phy *phy); -- cgit v1.2.3 From 6558d7edbe069df1220b525362d4aa854a65a8bc Mon Sep 17 00:00:00 2001 From: Tuomas Tynkkynen Date: Thu, 25 Jul 2013 21:38:09 +0300 Subject: usb: phy: tegra: Use DT helpers for dr_mode Use the new of_usb_get_dr_mode helper function for parsing dr_mode from the device tree. Also replace the usage of the custom tegra_usb_phy_mode enum with the standard enum. Signed-off-by: Tuomas Tynkkynen Reviewed-by: Stephen Warren Tested-by: Stephen Warren Signed-off-by: Felipe Balbi --- include/linux/usb/tegra_usb_phy.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index a095c98184d0..d3db274610a1 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -34,12 +34,6 @@ enum tegra_usb_phy_port_speed { TEGRA_USB_PHY_PORT_SPEED_HIGH, }; -enum tegra_usb_phy_mode { - TEGRA_USB_PHY_MODE_DEVICE, - TEGRA_USB_PHY_MODE_HOST, - TEGRA_USB_PHY_MODE_OTG, -}; - struct tegra_xtal_freq; struct tegra_usb_phy { @@ -51,7 +45,7 @@ struct tegra_usb_phy { struct clk *pll_u; struct clk *pad_clk; struct regulator *vbus; - enum tegra_usb_phy_mode mode; + enum usb_dr_mode mode; void *config; struct usb_phy *ulpi; struct usb_phy u_phy; -- cgit v1.2.3 From 49834de234f3cf592c3d242c889ca603db8e7050 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Sun, 28 Jul 2013 14:47:02 +0100 Subject: spi: Provide core support for runtime PM during transfers Most SPI drivers that implement runtime PM support use identical code to do so: they acquire a runtime PM lock in prepare_transfer_hardware() and then they release it in unprepare_transfer_hardware(). The variations in this are mostly missing error checking and the choice to use autosuspend. Since these runtime PM calls are normally the only thing in the prepare and unprepare callbacks and the autosuspend API transparently does the right thing on devices with autosuspend disabled factor all of this out into the core with a flag to enable the behaviour. Signed-off-by: Mark Brown Reviewed-by: Stephen Warren Acked-by: Linus Walleij --- include/linux/spi/spi.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 28e440be1c07..bf0204c00053 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -254,6 +254,9 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * @busy: message pump is busy * @running: message pump is running * @rt: whether this queue is set to run as a realtime task + * @auto_runtime_pm: the core should ensure a runtime PM reference is held + * while the hardware is prepared, using the parent + * device for the spidev * @prepare_transfer_hardware: a message will soon arrive from the queue * so the subsystem requests the driver to prepare the transfer hardware * by issuing this call @@ -374,11 +377,13 @@ struct spi_master { bool busy; bool running; bool rt; + bool auto_runtime_pm; int (*prepare_transfer_hardware)(struct spi_master *master); int (*transfer_one_message)(struct spi_master *master, struct spi_message *mesg); int (*unprepare_transfer_hardware)(struct spi_master *master); + /* gpio chip select */ int *cs_gpios; }; -- cgit v1.2.3 From 055560b04a8cd063aea916fd083b7aec02c2adb8 Mon Sep 17 00:00:00 2001 From: Elen Song Date: Mon, 22 Jul 2013 16:30:29 +0800 Subject: serial: at91: distinguish usart and uart Distinguish usart and uart by read ip name register, The usart read name is "USAR", The uart and dbgu read name is "DBGU". Signed-off-by: Elen Song Signed-off-by: Greg Kroah-Hartman --- include/linux/atmel_serial.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/atmel_serial.h b/include/linux/atmel_serial.h index fd6833764d72..be201ca2990c 100644 --- a/include/linux/atmel_serial.h +++ b/include/linux/atmel_serial.h @@ -124,4 +124,6 @@ #define ATMEL_US_NER 0x44 /* Number of Errors Register */ #define ATMEL_US_IF 0x4c /* IrDA Filter Register */ +#define ATMEL_US_NAME 0xf0 /* Ip Name */ + #endif -- cgit v1.2.3 From e66c33d579ea566d10e8c8695a7168aae3e02992 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Fri, 12 Jul 2013 16:50:28 -0400 Subject: rcu: Add const annotation to char * for RCU tracepoints and functions All the RCU tracepoints and functions that reference char pointers do so with just 'char *' even though they do not modify the contents of the string itself. This will cause warnings if a const char * is used in one of these functions. The RCU tracepoints store the pointer to the string to refer back to them when the trace output is displayed. As this can be minutes, hours or even days later, those strings had better be constant. This change also opens the door to allow the RCU tracepoint strings and their addresses to be exported so that userspace tracing tools can translate the contents of the pointers of the RCU tracepoints. Signed-off-by: Steven Rostedt --- include/linux/rcupdate.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 4b14bdc911d7..0c38abbe6e35 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -52,7 +52,7 @@ extern int rcutorture_runnable; /* for sysctl */ #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) extern void rcutorture_record_test_transition(void); extern void rcutorture_record_progress(unsigned long vernum); -extern void do_trace_rcu_torture_read(char *rcutorturename, +extern void do_trace_rcu_torture_read(const char *rcutorturename, struct rcu_head *rhp, unsigned long secs, unsigned long c_old, @@ -65,7 +65,7 @@ static inline void rcutorture_record_progress(unsigned long vernum) { } #ifdef CONFIG_RCU_TRACE -extern void do_trace_rcu_torture_read(char *rcutorturename, +extern void do_trace_rcu_torture_read(const char *rcutorturename, struct rcu_head *rhp, unsigned long secs, unsigned long c_old, -- cgit v1.2.3 From 9cf7b244187bba5964d4bf7438946baa2a974466 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Tue, 30 Jul 2013 09:09:15 +0300 Subject: usb: of: fix build breakage caused by recent patches commit 052a11d (usb: phy: make PHY driver selection possible by controller drivers) changed the rules on how drivers/usb/phy/of.c would be compiled and failed to update include/linux/usb/of.h accordingly. Because of that, we can fall into situations where of_usb_get_phy_mode() is redefined. In order to fix the error, we update the IS_ENABLED() check in include/linux/usb/of.h to reflect the condition where of.c is built. Reported-by: Stephen Rothwell Signed-off-by: Felipe Balbi --- include/linux/usb/of.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/of.h b/include/linux/usb/of.h index 5a7cb9ebf0ef..8c38aa26b3bb 100644 --- a/include/linux/usb/of.h +++ b/include/linux/usb/of.h @@ -27,7 +27,7 @@ of_usb_get_maximum_speed(struct device_node *np) } #endif -#if IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_USB_PHY) +#if IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_USB_SUPPORT) enum usb_phy_interface of_usb_get_phy_mode(struct device_node *np); #else static inline enum usb_phy_interface of_usb_get_phy_mode(struct device_node *np) -- cgit v1.2.3 From 1207637304990374231fe4e9aeb527904f4ec1e6 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 30 Jul 2013 08:30:16 -0400 Subject: workqueue: mark WQ_NON_REENTRANT deprecated dbf2576e37 ("workqueue: make all workqueues non-reentrant") made WQ_NON_REENTRANT no-op but the following patches didn't remove the flag or update the documentation. Let's mark the flag deprecated and update the documentation accordingly. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index a0ed78ab54d7..594521ba0d43 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -295,7 +295,12 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } * Documentation/workqueue.txt. */ enum { - WQ_NON_REENTRANT = 1 << 0, /* guarantee non-reentrance */ + /* + * All wqs are now non-reentrant making the following flag + * meaningless. Will be removed. + */ + WQ_NON_REENTRANT = 1 << 0, /* DEPRECATED */ + WQ_UNBOUND = 1 << 1, /* not bound to any cpu */ WQ_FREEZABLE = 1 << 2, /* freeze during suspend */ WQ_MEM_RECLAIM = 1 << 3, /* may be used for memory reclaim */ -- cgit v1.2.3 From 4bdfb2729c3a396fe7400c9332c49aee2b971bd8 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 29 Jul 2013 21:00:53 +0100 Subject: regulator: core: Add missing stub for regulator_get_exclusive() Signed-off-by: Mark Brown --- include/linux/regulator/consumer.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 3a76389c6aaa..60da4a62c402 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -211,6 +211,13 @@ static inline struct regulator *__must_check regulator_get(struct device *dev, return NULL; } +static inline struct regulator *__must_check +regulator_get_exclusive(struct device *dev, const char *id) +{ + return NULL; +} + + static inline struct regulator *__must_check devm_regulator_get(struct device *dev, const char *id) { -- cgit v1.2.3 From de1dd9fd2156874b45803299b3b27e65d5defdd9 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 29 Jul 2013 21:42:42 +0100 Subject: regulator: core: Provide hints to the core about optional supplies While the majority of supplies on devices are mandatory and can't be physically omitted for electrical reasons some devices do have optional supplies and need to know if they are missing, MMC being the most common of these. Currently the core accurately reports all errors when regulators are requested since it does not know if the supply is one that must be provided even if by a regulator software does not know about or if it is one that may genuinely be disconnected. In order to allow this behaviour to be changed and stub regulators to be provided in the former case add a new regulator request function regulator_get_optional() which provides a hint to the core that the regulator may genuinely not be connected. Currently the implementation is identical to the current behaviour, future patches will add support in the core for returning stub regulators in the case where normal regulator_get() fails and the board has requested it. Signed-off-by: Mark Brown Acked-by: Chris Ball --- include/linux/regulator/consumer.h | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 60da4a62c402..e2bac6db4abc 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -137,6 +137,10 @@ struct regulator *__must_check devm_regulator_get(struct device *dev, const char *id); struct regulator *__must_check regulator_get_exclusive(struct device *dev, const char *id); +struct regulator *__must_check regulator_get_optional(struct device *dev, + const char *id); +struct regulator *__must_check devm_regulator_get_optional(struct device *dev, + const char *id); void regulator_put(struct regulator *regulator); void devm_regulator_put(struct regulator *regulator); @@ -211,15 +215,27 @@ static inline struct regulator *__must_check regulator_get(struct device *dev, return NULL; } +static inline struct regulator *__must_check +devm_regulator_get(struct device *dev, const char *id) +{ + return NULL; +} + static inline struct regulator *__must_check regulator_get_exclusive(struct device *dev, const char *id) { return NULL; } +static inline struct regulator *__must_check +regulator_get_optional(struct device *dev, const char *id) +{ + return NULL; +} + static inline struct regulator *__must_check -devm_regulator_get(struct device *dev, const char *id) +devm_regulator_get_optional(struct device *dev, const char *id) { return NULL; } -- cgit v1.2.3 From 6f4b7e632d78c2d91502211c430722cc66428492 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 31 Jul 2013 16:18:36 +0800 Subject: cgroup: more naming cleanups Constantly use @cset for css_set variables and use @cgrp as cgroup variables. Signed-off-by: Li Zefan Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 297462b9f41a..00a7e07a1567 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -394,8 +394,8 @@ struct cgroup_map_cb { /* cftype->flags */ enum { - CFTYPE_ONLY_ON_ROOT = (1 << 0), /* only create on root cg */ - CFTYPE_NOT_ON_ROOT = (1 << 1), /* don't create on root cg */ + CFTYPE_ONLY_ON_ROOT = (1 << 0), /* only create on root cgrp */ + CFTYPE_NOT_ON_ROOT = (1 << 1), /* don't create on root cgrp */ CFTYPE_INSANE = (1 << 2), /* don't create if sane_behavior */ }; @@ -513,7 +513,7 @@ struct cftype_set { }; struct cgroup_scanner { - struct cgroup *cg; + struct cgroup *cgrp; int (*test_task)(struct task_struct *p, struct cgroup_scanner *scan); void (*process_task)(struct task_struct *p, struct cgroup_scanner *scan); -- cgit v1.2.3 From 4e96ee8e981b5140a2bcc5fff0d5c0eef39a62ee Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 31 Jul 2013 09:50:50 +0800 Subject: cgroup: convert cgroup_ida to cgroup_idr This enables us to lookup a cgroup by its id. v4: - add a comment for idr_remove() in cgroup_offline_fn(). v3: - on success, idr_alloc() returns the id but not 0, so fix the BUG_ON() in cgroup_init(). - pass the right value to idr_alloc() so that the id for dummy cgroup is 0. Signed-off-by: Li Zefan Reviewed-by: Michal Hocko Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 00a7e07a1567..cca570e188fb 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -161,7 +161,7 @@ struct cgroup_name { struct cgroup { unsigned long flags; /* "unsigned long" so bitops work */ - int id; /* ida allocated in-hierarchy ID */ + int id; /* idr allocated in-hierarchy ID */ /* * We link our 'sibling' struct into our parent's 'children'. @@ -322,7 +322,7 @@ struct cgroupfs_root { unsigned long flags; /* IDs for cgroups in this hierarchy */ - struct ida cgroup_ida; + struct idr cgroup_idr; /* The path to use for release notifications. */ char release_agent_path[PATH_MAX]; -- cgit v1.2.3 From b414dc09a31d41d696093a4cce9fb2853a5ecd4e Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 31 Jul 2013 09:51:06 +0800 Subject: cgroup: document how cgroup IDs are assigned As cgroup id has been used in netprio cgroup and will be used in memcg, it's important to make it clear how a cgroup id is allocated. For example, in netprio cgroup, the id is used as index of anarray. Signed-off-by: Li Zefan Reviewed-by: Michal Hocko Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index cca570e188fb..4dfcd0e1b73e 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -161,7 +161,13 @@ struct cgroup_name { struct cgroup { unsigned long flags; /* "unsigned long" so bitops work */ - int id; /* idr allocated in-hierarchy ID */ + /* + * idr allocated in-hierarchy ID. + * + * The ID of the root cgroup is always 0, and a new cgroup + * will be assigned with a smallest available ID. + */ + int id; /* * We link our 'sibling' struct into our parent's 'children'. -- cgit v1.2.3 From e14880f7bb7e0dc0933af304998371dd543ceb40 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 31 Jul 2013 09:51:31 +0800 Subject: cgroup: implement cgroup_from_id() This will be used as a replacement for css_lookup(). There's a difference with cgroup id and css id. cgroup id starts with 0, while css id starts with 1. v4: - also check if cggroup_mutex is held. - make it an inline function. Signed-off-by: Li Zefan Reviewed-by: Michal Hocko Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 4dfcd0e1b73e..bbf4d89b56a8 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -720,6 +720,24 @@ static inline struct cgroup* task_cgroup(struct task_struct *task, return task_subsys_state(task, subsys_id)->cgroup; } +/** + * cgroup_from_id - lookup cgroup by id + * @ss: cgroup subsys to be looked into + * @id: the cgroup id + * + * Returns the cgroup if there's valid one with @id, otherwise returns NULL. + * Should be called under rcu_read_lock(). + */ +static inline struct cgroup *cgroup_from_id(struct cgroup_subsys *ss, int id) +{ +#ifdef CONFIG_PROVE_RCU + rcu_lockdep_assert(rcu_read_lock_held() || + lockdep_is_held(&cgroup_mutex), + "cgroup_from_id() needs proper protection"); +#endif + return idr_find(&ss->root->cgroup_idr, id); +} + struct cgroup *cgroup_next_sibling(struct cgroup *pos); /** -- cgit v1.2.3 From d6b47b122473885abc882e337ac2d321bbcfb378 Mon Sep 17 00:00:00 2001 From: Ben Guthro Date: Tue, 30 Jul 2013 08:24:52 -0400 Subject: ACPI / sleep: Introduce acpi_os_prepare_extended_sleep() for extended sleep path Like acpi_os_prepare_sleep(), register a callback for use in systems like tboot, and xen, which have system specific requirements outside of ACPICA. This mirrors the functionality in acpi_os_prepare_sleep(), called from acpi_hw_sleep() Signed-off-by: Ben Guthro Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 353ba256f368..a5db4aeefa36 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -481,6 +481,13 @@ void acpi_os_set_prepare_sleep(int (*func)(u8 sleep_state, acpi_status acpi_os_prepare_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control); + +void acpi_os_set_prepare_extended_sleep(int (*func)(u8 sleep_state, + u32 val_a, u32 val_b)); + +acpi_status acpi_os_prepare_extended_sleep(u8 sleep_state, + u32 val_a, u32 val_b); + #ifdef CONFIG_X86 void arch_reserve_mem_area(acpi_physical_address addr, size_t size); #else -- cgit v1.2.3 From 2816c551c796ec14620325b2c9ed75b9979d3125 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 29 Jul 2013 19:50:33 +0200 Subject: tracing: trace_remove_event_call() should fail if call/file is in use Change trace_remove_event_call(call) to return the error if this call is active. This is what the callers assume but can't verify outside of the tracing locks. Both trace_kprobe.c/trace_uprobe.c need the additional changes, unregister_trace_probe() should abort if trace_remove_event_call() fails. The caller is going to free this call/file so we must ensure that nobody can use them after trace_remove_event_call() succeeds. debugfs should be fine after the previous changes and event_remove() does TRACE_REG_UNREGISTER, but still there are 2 reasons why we need the additional checks: - There could be a perf_event(s) attached to this tp_event, so the patch checks ->perf_refcount. - TRACE_REG_UNREGISTER can be suppressed by FTRACE_EVENT_FL_SOFT_MODE, so we simply check FTRACE_EVENT_FL_ENABLED protected by event_mutex. Link: http://lkml.kernel.org/r/20130729175033.GB26284@redhat.com Reviewed-by: Masami Hiramatsu Signed-off-by: Oleg Nesterov Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 4372658c73ae..f98ab063e95e 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -332,7 +332,7 @@ extern int trace_define_field(struct ftrace_event_call *call, const char *type, const char *name, int offset, int size, int is_signed, int filter_type); extern int trace_add_event_call(struct ftrace_event_call *call); -extern void trace_remove_event_call(struct ftrace_event_call *call); +extern int trace_remove_event_call(struct ftrace_event_call *call); #define is_signed_type(type) (((type)(-1)) < (type)1) -- cgit v1.2.3 From 90efa75f7ab0be5677f0cca155dbf0b39eacdd03 Mon Sep 17 00:00:00 2001 From: Alexander Shiyan Date: Wed, 31 Jul 2013 14:56:30 +0400 Subject: serial: sccnxp: Using CLK API for getting UART clock This patch removes "frequency" parameter from SCCNXP platform_data and uses CLK API for getting clock. If CLK ommited, default IC frequency will be used instead. Signed-off-by: Alexander Shiyan Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_data/serial-sccnxp.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/serial-sccnxp.h b/include/linux/platform_data/serial-sccnxp.h index bdc510d03245..af0c8c3b89ae 100644 --- a/include/linux/platform_data/serial-sccnxp.h +++ b/include/linux/platform_data/serial-sccnxp.h @@ -60,7 +60,6 @@ * }; * * static struct sccnxp_pdata sc2892_info = { - * .frequency = 3686400, * .mctrl_cfg[0] = MCTRL_SIG(DIR_OP, LINE_OP0), * .mctrl_cfg[1] = MCTRL_SIG(DIR_OP, LINE_OP1), * }; @@ -78,8 +77,6 @@ /* SCCNXP platform data structure */ struct sccnxp_pdata { - /* Frequency (extrenal clock or crystal) */ - int frequency; /* Shift for A0 line */ const u8 reg_shift; /* Modem control lines configuration */ -- cgit v1.2.3 From 85c996907473e4ef824774b97b26499adf66521f Mon Sep 17 00:00:00 2001 From: Alexander Shiyan Date: Wed, 31 Jul 2013 14:55:45 +0400 Subject: serial: sccnxp: Add DT support Add DT support to the SCCNCP serial driver. Signed-off-by: Alexander Shiyan Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_data/serial-sccnxp.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/serial-sccnxp.h b/include/linux/platform_data/serial-sccnxp.h index af0c8c3b89ae..98373d6add27 100644 --- a/include/linux/platform_data/serial-sccnxp.h +++ b/include/linux/platform_data/serial-sccnxp.h @@ -78,11 +78,11 @@ /* SCCNXP platform data structure */ struct sccnxp_pdata { /* Shift for A0 line */ - const u8 reg_shift; + u32 reg_shift; /* Modem control lines configuration */ - const u32 mctrl_cfg[SCCNXP_MAX_UARTS]; + u32 mctrl_cfg[SCCNXP_MAX_UARTS]; /* Timer value for polling mode (usecs) */ - const unsigned int poll_time_us; + u32 poll_time_us; }; #endif -- cgit v1.2.3 From cfc25993e81f3fa68481d062be634d33184d5eae Mon Sep 17 00:00:00 2001 From: Olaf Hering Date: Wed, 29 May 2013 11:29:07 +0200 Subject: Drivers: hv: remove HV_DRV_VERSION Remove HV_DRV_VERSION, it has no meaning for upstream drivers. Initially it was supposed to show the "Linux Integration Services" version, now it is not in sync anymore with the out-of-tree drivers available from the MSFT website. The only place where a version string is still required is the KVP command "IntegrationServicesVersion" which is handled by tools/hv/hv_kvp_daemon.c. To satisfy such KVP request from the host pass the current string to the daemon during KVP userland registration. Signed-off-by: Olaf Hering Acked-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 21 --------------------- 1 file changed, 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 49949079cf47..a3b8b2e2d244 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -463,27 +463,6 @@ hv_get_ringbuffer_availbytes(struct hv_ring_buffer_info *rbi, *read = dsize - *write; } - -/* - * We use the same version numbering for all Hyper-V modules. - * - * Definition of versioning is as follows; - * - * Major Number Changes for these scenarios; - * 1. When a new version of Windows Hyper-V - * is released. - * 2. A Major change has occurred in the - * Linux IC's. - * (For example the merge for the first time - * into the kernel) Every time the Major Number - * changes, the Revision number is reset to 0. - * Minor Number Changes when new functionality is added - * to the Linux IC's that is not a bug fix. - * - * 3.1 - Added completed hv_utils driver. Shutdown/Heartbeat/Timesync - */ -#define HV_DRV_VERSION "3.1" - /* * VMBUS version is 32 bit entity broken up into * two 16 bit quantities: major_number. minor_number. -- cgit v1.2.3 From 461a8ecb2d76fb6f3ac1a90eb886697db869d387 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 2 Aug 2013 15:25:19 +0800 Subject: Revert "serial: sccnxp: Add DT support" This reverts commit 85c996907473e4ef824774b97b26499adf66521f. Alexander wishes to remove this patch as it is incorrect. Reported-by: Alexander Shiyan Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_data/serial-sccnxp.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/serial-sccnxp.h b/include/linux/platform_data/serial-sccnxp.h index 98373d6add27..af0c8c3b89ae 100644 --- a/include/linux/platform_data/serial-sccnxp.h +++ b/include/linux/platform_data/serial-sccnxp.h @@ -78,11 +78,11 @@ /* SCCNXP platform data structure */ struct sccnxp_pdata { /* Shift for A0 line */ - u32 reg_shift; + const u8 reg_shift; /* Modem control lines configuration */ - u32 mctrl_cfg[SCCNXP_MAX_UARTS]; + const u32 mctrl_cfg[SCCNXP_MAX_UARTS]; /* Timer value for polling mode (usecs) */ - u32 poll_time_us; + const unsigned int poll_time_us; }; #endif -- cgit v1.2.3 From b6aa23ccaea1548cfb404b41129717f13443bccf Mon Sep 17 00:00:00 2001 From: Stephen Warren Date: Thu, 1 Aug 2013 16:08:57 -0600 Subject: spi: fix SPI_BIT_MASK so it always fits into 32-bits On a 64-bit platform, ~0UL fills 64-bits, which causes SPI_BIT_MASK(32) not to fit into 32 bits. This causes a warning when the result is assigned to a 32-bit variable. Use ~0U instead to prevent this. This fixes: drivers/spi/spi-gpio.c: In function 'spi_gpio_probe': drivers/spi/spi-gpio.c:446:2: warning: large integer implicitly truncated to unsigned type [-Woverflow] Reported-by: kbuild test robot Signed-off-by: Stephen Warren Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 28e440be1c07..c920c2f4dad5 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -309,7 +309,7 @@ struct spi_master { /* bitmask of supported bits_per_word for transfers */ u32 bits_per_word_mask; #define SPI_BPW_MASK(bits) BIT((bits) - 1) -#define SPI_BIT_MASK(bits) (((bits) == 32) ? ~0UL : (BIT(bits) - 1)) +#define SPI_BIT_MASK(bits) (((bits) == 32) ? ~0U : (BIT(bits) - 1)) #define SPI_BPW_RANGE_MASK(min, max) (SPI_BIT_MASK(max) - SPI_BIT_MASK(min - 1)) /* other constraints relevant to this driver */ -- cgit v1.2.3 From abe4c51afda02423c81da6f1eaaa50b733f1ecc2 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Fri, 2 Aug 2013 12:59:44 +0200 Subject: regulators: max8660: add DT bindings This patch adds devicetree bindings for max8660, along with some documentation. Signed-off-by: Daniel Mack Signed-off-by: Mark Brown --- include/linux/regulator/max8660.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regulator/max8660.h b/include/linux/regulator/max8660.h index 9936763621c7..f8a6a4844864 100644 --- a/include/linux/regulator/max8660.h +++ b/include/linux/regulator/max8660.h @@ -39,7 +39,7 @@ enum { */ struct max8660_subdev_data { int id; - char *name; + const char *name; struct regulator_init_data *platform_data; }; -- cgit v1.2.3 From 5ef76da644bf346d29200007d8d3779e7009dabb Mon Sep 17 00:00:00 2001 From: David Herrmann Date: Fri, 2 Aug 2013 14:05:20 +0200 Subject: fbdev: simplefb: add init through platform_data If we create proper platform-devices in x86 boot-code, we can use simplefb for VBE or EFI framebuffers, too. However, there is normally no OF support so we introduce a platform_data object so x86 boot-code can pass the parameters via plain old platform-data. This also removes the OF dependency as it is not needed. The headers provide proper dummies for the case OF is disabled. Furthermore, we move the FORMAT-definitions to the common platform header so initialization code can use it to transform "struct screen_info" to the right format-name. Signed-off-by: David Herrmann Link: http://lkml.kernel.org/r/1375445127-15480-2-git-send-email-dh.herrmann@gmail.com Reviewed-by: Stephen Warren Signed-off-by: H. Peter Anvin --- include/linux/platform_data/simplefb.h | 56 ++++++++++++++++++++++++++++++++++ 1 file changed, 56 insertions(+) create mode 100644 include/linux/platform_data/simplefb.h (limited to 'include/linux') diff --git a/include/linux/platform_data/simplefb.h b/include/linux/platform_data/simplefb.h new file mode 100644 index 000000000000..5fa2c5e02ab8 --- /dev/null +++ b/include/linux/platform_data/simplefb.h @@ -0,0 +1,56 @@ +/* + * simplefb.h - Simple Framebuffer Device + * + * Copyright (C) 2013 David Herrmann + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef __PLATFORM_DATA_SIMPLEFB_H__ +#define __PLATFORM_DATA_SIMPLEFB_H__ + +#include +#include +#include + +/* format array, use it to initialize a "struct simplefb_format" array */ +#define SIMPLEFB_FORMATS \ +{ \ + { "r5g6b5", 16, {11, 5}, {5, 6}, {0, 5}, {0, 0}, DRM_FORMAT_RGB565 }, \ +} + +/* + * Data-Format for Simple-Framebuffers + * @name: unique 0-terminated name that can be used to identify the mode + * @red,green,blue: Offsets and sizes of the single RGB parts + * @transp: Offset and size of the alpha bits. length=0 means no alpha + * @fourcc: 32bit DRM four-CC code (see drm_fourcc.h) + */ +struct simplefb_format { + const char *name; + u32 bits_per_pixel; + struct fb_bitfield red; + struct fb_bitfield green; + struct fb_bitfield blue; + struct fb_bitfield transp; + u32 fourcc; +}; + +/* + * Simple-Framebuffer description + * If the arch-boot code creates simple-framebuffers without DT support, it + * can pass the width, height, stride and format via this platform-data object. + * The framebuffer location must be given as IORESOURCE_MEM resource. + * @format must be a format as described in "struct simplefb_format" above. + */ +struct simplefb_platform_data { + u32 width; + u32 height; + u32 stride; + const char *format; +}; + +#endif /* __PLATFORM_DATA_SIMPLEFB_H__ */ -- cgit v1.2.3 From 9a6a36d19c9d24479300511e23933876a4a9cf82 Mon Sep 17 00:00:00 2001 From: David Herrmann Date: Fri, 2 Aug 2013 14:05:24 +0200 Subject: fbdev: simplefb: add common x86 RGB formats 32bit XRGB and ARGB are used by modern x86 systems for EFI and VESA framebuffers. The other formats were reported by hpa to be most common. Add these so simplefb works on most common x86 systems. Signed-off-by: David Herrmann Link: http://lkml.kernel.org/r/1375445127-15480-6-git-send-email-dh.herrmann@gmail.com Signed-off-by: H. Peter Anvin --- include/linux/platform_data/simplefb.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/simplefb.h b/include/linux/platform_data/simplefb.h index 5fa2c5e02ab8..53774b0cd8e9 100644 --- a/include/linux/platform_data/simplefb.h +++ b/include/linux/platform_data/simplefb.h @@ -20,6 +20,13 @@ #define SIMPLEFB_FORMATS \ { \ { "r5g6b5", 16, {11, 5}, {5, 6}, {0, 5}, {0, 0}, DRM_FORMAT_RGB565 }, \ + { "x1r5g5b5", 16, {10, 5}, {5, 5}, {0, 5}, {0, 0}, DRM_FORMAT_XRGB1555 }, \ + { "a1r5g5b5", 16, {10, 5}, {5, 5}, {0, 5}, {15, 1}, DRM_FORMAT_ARGB1555 }, \ + { "r8g8b8", 24, {16, 8}, {8, 8}, {0, 8}, {0, 0}, DRM_FORMAT_RGB888 }, \ + { "x8r8g8b8", 32, {16, 8}, {8, 8}, {0, 8}, {0, 0}, DRM_FORMAT_XRGB8888 }, \ + { "a8r8g8b8", 32, {16, 8}, {8, 8}, {0, 8}, {24, 8}, DRM_FORMAT_ARGB8888 }, \ + { "x2r10g10b10", 32, {20, 10}, {10, 10}, {0, 10}, {0, 0}, DRM_FORMAT_XRGB2101010 }, \ + { "a2r10g10b10", 32, {20, 10}, {10, 10}, {0, 10}, {30, 2}, DRM_FORMAT_ARGB2101010 }, \ } /* -- cgit v1.2.3 From ed5467da0e369e65b247b99eb6403cb79172bcda Mon Sep 17 00:00:00 2001 From: Andrew Vagin Date: Fri, 2 Aug 2013 21:16:43 +0400 Subject: tracing: Fix fields of struct trace_iterator that are zeroed by mistake tracing_read_pipe zeros all fields bellow "seq". The declaration contains a comment about that, but it doesn't help. The first field is "snapshot", it's true when current open file is snapshot. Looks obvious, that it should not be zeroed. The second field is "started". It was converted from cpumask_t to cpumask_var_t (v2.6.28-4983-g4462344), in other words it was converted from cpumask to pointer on cpumask. Currently the reference on "started" memory is lost after the first read from tracing_read_pipe and a proper object will never be freed. The "started" is never dereferenced for trace_pipe, because trace_pipe can't have the TRACE_FILE_ANNOTATE options. Link: http://lkml.kernel.org/r/1375463803-3085183-1-git-send-email-avagin@openvz.org Cc: stable@vger.kernel.org # 2.6.30 Signed-off-by: Andrew Vagin Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index f98ab063e95e..120d57a1c3a5 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -78,6 +78,11 @@ struct trace_iterator { /* trace_seq for __print_flags() and __print_symbolic() etc. */ struct trace_seq tmp_seq; + cpumask_var_t started; + + /* it's true when current open file is snapshot */ + bool snapshot; + /* The below is zeroed out in pipe_read */ struct trace_seq seq; struct trace_entry *ent; @@ -90,10 +95,7 @@ struct trace_iterator { loff_t pos; long idx; - cpumask_var_t started; - - /* it's true when current open file is snapshot */ - bool snapshot; + /* All new field here will be zeroed out in pipe_read */ }; enum trace_iter_flags { -- cgit v1.2.3 From e67bc51e574ffe3c4bc1e09cab7658b1e780b4ce Mon Sep 17 00:00:00 2001 From: Dhaval Giani Date: Fri, 2 Aug 2013 14:47:29 -0400 Subject: tracing: Fix trace_dump_stack() proto when CONFIG_TRACING is not set When CONFIG_TRACING is not enabled, the stub prototype for trace_dump_stack() is incorrect. It has (void) when it should be (int). Link: http://lkml.kernel.org/r/CAPhKKr_H=ukFnBL4WgDOVT5ay2xeF-Ho+CA0DWZX0E2JW-=vSQ@mail.gmail.com Signed-off-by: Dhaval Giani Signed-off-by: Steven Rostedt --- include/linux/kernel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 3bef14c6586b..482ad2d84a32 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -629,7 +629,7 @@ extern void ftrace_dump(enum ftrace_dump_mode oops_dump_mode); static inline void tracing_start(void) { } static inline void tracing_stop(void) { } static inline void ftrace_off_permanent(void) { } -static inline void trace_dump_stack(void) { } +static inline void trace_dump_stack(int skip) { } static inline void tracing_on(void) { } static inline void tracing_off(void) { } -- cgit v1.2.3 From 626f090c5cbbe557379978c7a9525011ad7fbbf6 Mon Sep 17 00:00:00 2001 From: Yacine Belkadi Date: Fri, 2 Aug 2013 20:10:04 +0200 Subject: usb: fix some scripts/kernel-doc warnings When building the htmldocs (in verbose mode), scripts/kernel-doc reports the following type of warnings: Warning(drivers/usb/core/usb.c:76): No description found for return value of 'usb_find_alt_setting' Fix them by: - adding some missing descriptions of return values - using "Return" sections for those descriptions Signed-off-by: Yacine Belkadi Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 6efdab089014..acb1b0aa77d8 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -708,7 +708,10 @@ extern int usb_driver_claim_interface(struct usb_driver *driver, * usb_interface_claimed - returns true iff an interface is claimed * @iface: the interface being checked * - * Returns true (nonzero) iff the interface is claimed, else false (zero). + * Return: %true (nonzero) iff the interface is claimed, else %false + * (zero). + * + * Note: * Callers must own the driver model's usb bus readlock. So driver * probe() entries don't need extra locking, but other call contexts * may need to explicitly claim that lock. @@ -745,8 +748,9 @@ extern struct usb_host_interface *usb_find_alt_setting( * @buf: where to put the string * @size: how big is "buf"? * - * Returns length of the string (> 0) or negative if size was too small. + * Return: Length of the string (> 0) or negative if size was too small. * + * Note: * This identifier is intended to be "stable", reflecting physical paths in * hardware such as physical bus addresses for host controllers or ports on * USB hubs. That makes it stay the same until systems are physically @@ -1578,7 +1582,7 @@ extern int usb_anchor_empty(struct usb_anchor *anchor); * usb_urb_dir_in - check if an URB describes an IN transfer * @urb: URB to be checked * - * Returns 1 if @urb describes an IN transfer (device-to-host), + * Return: 1 if @urb describes an IN transfer (device-to-host), * otherwise 0. */ static inline int usb_urb_dir_in(struct urb *urb) @@ -1590,7 +1594,7 @@ static inline int usb_urb_dir_in(struct urb *urb) * usb_urb_dir_out - check if an URB describes an OUT transfer * @urb: URB to be checked * - * Returns 1 if @urb describes an OUT transfer (host-to-device), + * Return: 1 if @urb describes an OUT transfer (host-to-device), * otherwise 0. */ static inline int usb_urb_dir_out(struct urb *urb) -- cgit v1.2.3 From 23cde4d65cc7d11e2048d2b240cdf13927ac50d0 Mon Sep 17 00:00:00 2001 From: Denis CIOCCA Date: Wed, 19 Jun 2013 09:28:00 +0100 Subject: iio: Added ST-sensors platform data to select the DRDY interrupt pin This patch add support to redirect the DRDY interrupt on INT1 or INT2 on accelerometer and pressure sensors. Signed-off-by: Denis Ciocca Signed-off-by: Jonathan Cameron --- include/linux/iio/common/st_sensors.h | 14 +++++++++++--- include/linux/platform_data/st_sensors_pdata.h | 24 ++++++++++++++++++++++++ 2 files changed, 35 insertions(+), 3 deletions(-) create mode 100644 include/linux/platform_data/st_sensors_pdata.h (limited to 'include/linux') diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index 72b26940730d..e51f65480ea5 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -17,6 +17,8 @@ #include #include +#include + #define ST_SENSORS_TX_MAX_LENGTH 2 #define ST_SENSORS_RX_MAX_LENGTH 6 @@ -118,14 +120,16 @@ struct st_sensor_bdu { /** * struct st_sensor_data_ready_irq - ST sensor device data-ready interrupt * @addr: address of the register. - * @mask: mask to write the on/off value. + * @mask_int1: mask to enable/disable IRQ on INT1 pin. + * @mask_int2: mask to enable/disable IRQ on INT2 pin. * struct ig1 - represents the Interrupt Generator 1 of sensors. * @en_addr: address of the enable ig1 register. * @en_mask: mask to write the on/off value for enable. */ struct st_sensor_data_ready_irq { u8 addr; - u8 mask; + u8 mask_int1; + u8 mask_int2; struct { u8 en_addr; u8 en_mask; @@ -201,6 +205,7 @@ struct st_sensors { * @buffer_data: Data used by buffer part. * @odr: Output data rate of the sensor [Hz]. * num_data_channels: Number of data channels used in buffer. + * @drdy_int_pin: Redirect DRDY on pin 1 (1) or pin 2 (2). * @get_irq_data_ready: Function to get the IRQ used for data ready signal. * @tf: Transfer function structure used by I/O operations. * @tb: Transfer buffers and mutex used by I/O operations. @@ -219,6 +224,8 @@ struct st_sensor_data { unsigned int odr; unsigned int num_data_channels; + u8 drdy_int_pin; + unsigned int (*get_irq_data_ready) (struct iio_dev *indio_dev); const struct st_sensor_transfer_function *tf; @@ -249,7 +256,8 @@ static inline void st_sensors_deallocate_trigger(struct iio_dev *indio_dev) } #endif -int st_sensors_init_sensor(struct iio_dev *indio_dev); +int st_sensors_init_sensor(struct iio_dev *indio_dev, + struct st_sensors_platform_data *pdata); int st_sensors_set_enable(struct iio_dev *indio_dev, bool enable); diff --git a/include/linux/platform_data/st_sensors_pdata.h b/include/linux/platform_data/st_sensors_pdata.h new file mode 100644 index 000000000000..753839187ba0 --- /dev/null +++ b/include/linux/platform_data/st_sensors_pdata.h @@ -0,0 +1,24 @@ +/* + * STMicroelectronics sensors platform-data driver + * + * Copyright 2013 STMicroelectronics Inc. + * + * Denis Ciocca + * + * Licensed under the GPL-2. + */ + +#ifndef ST_SENSORS_PDATA_H +#define ST_SENSORS_PDATA_H + +/** + * struct st_sensors_platform_data - Platform data for the ST sensors + * @drdy_int_pin: Redirect DRDY on pin 1 (1) or pin 2 (2). + * Available only for accelerometer and pressure sensors. + * Accelerometer DRDY on LSM330 available only on pin 1 (see datasheet). + */ +struct st_sensors_platform_data { + u8 drdy_int_pin; +}; + +#endif /* ST_SENSORS_PDATA_H */ -- cgit v1.2.3 From 60b188f0d679656a1a2603d3bc1fa005373f4b9c Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Tue, 16 Jul 2013 16:08:00 +0100 Subject: iio: Remove IIO_DEV_ATTR_RESET macro There are no users of this macro left and we have come to the conclusion that it is not a good idea to expose the raw chip reset to userspace so the macro is very unlikely to be used in new drivers. Signed-off-by: Lars-Peter Clausen Signed-off-by: Jonathan Cameron --- include/linux/iio/sysfs.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/sysfs.h b/include/linux/iio/sysfs.h index b7a934b9431b..2958c960003a 100644 --- a/include/linux/iio/sysfs.h +++ b/include/linux/iio/sysfs.h @@ -73,11 +73,6 @@ struct iio_const_attr { .dev_attr = __ATTR(_name, S_IRUGO, iio_read_const_attr, NULL)} /* Generic attributes of onetype or another */ -/** - * IIO_DEV_ATTR_RESET: resets the device - **/ -#define IIO_DEV_ATTR_RESET(_store) \ - IIO_DEVICE_ATTR(reset, S_IWUSR, NULL, _store, 0) /** * IIO_DEV_ATTR_SAMP_FREQ - sets any internal clock frequency -- cgit v1.2.3 From 9dabaf5eddbafa21aded7c063cb38d2e8936c237 Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Thu, 18 Jul 2013 11:19:00 +0100 Subject: iio: core: implement devm_iio_device_alloc/devm_iio_device_free Add a resource managed devm_iio_device_alloc()/devm_iio_device_free() to automatically clean up any allocations made by IIO drivers, thus leading to simplified IIO drivers code. In addition, this will allow IIO drivers to use other devm_*() API (like devm_request_irq) and don't care about the race between iio_device_free() and the release of resources by Device core during driver removing. Signed-off-by: Grygorii Strashko Signed-off-by: Oleksandr Kravchenko Tested-by: Oleksandr Kravchenko Reviewed-by: Lars-Peter Clausen Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 3d35b7023591..61d220f89aca 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -531,6 +531,31 @@ static inline struct iio_dev *iio_priv_to_dev(void *priv) **/ void iio_device_free(struct iio_dev *indio_dev); +/** + * devm_iio_device_alloc - Resource-managed iio_device_alloc() + * @dev: Device to allocate iio_dev for + * @sizeof_priv: Space to allocate for private structure. + * + * Managed iio_device_alloc. iio_dev allocated with this function is + * automatically freed on driver detach. + * + * If an iio_dev allocated with this function needs to be freed separately, + * devm_iio_device_free() must be used. + * + * RETURNS: + * Pointer to allocated iio_dev on success, NULL on failure. + */ +struct iio_dev *devm_iio_device_alloc(struct device *dev, int sizeof_priv); + +/** + * devm_iio_device_free - Resource-managed iio_device_free() + * @dev: Device this iio_dev belongs to + * @indio_dev: the iio_dev associated with the device + * + * Free indio_dev allocated with devm_iio_device_alloc(). + */ +void devm_iio_device_free(struct device *dev, struct iio_dev *iio_dev); + /** * iio_buffer_enabled() - helper function to test if the buffer is enabled * @indio_dev: IIO device structure for device -- cgit v1.2.3 From 9bc541028b2b93962e0bebce62ce6e295aab2086 Mon Sep 17 00:00:00 2001 From: Peter Meerwald Date: Mon, 29 Jul 2013 22:35:00 +0100 Subject: iio: Fix documentation of devm_iio_device_free() Signed-off-by: Peter Meerwald Cc: Grygorii Strashko Cc: Oleksandr Kravchenko Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 61d220f89aca..09ebe0a4d8e6 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -552,9 +552,9 @@ struct iio_dev *devm_iio_device_alloc(struct device *dev, int sizeof_priv); * @dev: Device this iio_dev belongs to * @indio_dev: the iio_dev associated with the device * - * Free indio_dev allocated with devm_iio_device_alloc(). + * Free iio_dev allocated with devm_iio_device_alloc(). */ -void devm_iio_device_free(struct device *dev, struct iio_dev *iio_dev); +void devm_iio_device_free(struct device *dev, struct iio_dev *indio_dev); /** * iio_buffer_enabled() - helper function to test if the buffer is enabled -- cgit v1.2.3 From 6eee5b3b493824731ed34ade0299241f91f04096 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Tue, 11 Jun 2013 20:48:02 +0900 Subject: extcon: Add an API to get extcon device from dt node Added an API of_extcon_get_extcon_dev() to be used by drivers to get extcon device in the case of dt boot (this can be used instead of extcon_get_extcon_dev()). Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Chanwoo Choi Signed-off-by: Myungjoo Ham --- include/linux/extcon/of_extcon.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) create mode 100644 include/linux/extcon/of_extcon.h (limited to 'include/linux') diff --git a/include/linux/extcon/of_extcon.h b/include/linux/extcon/of_extcon.h new file mode 100644 index 000000000000..0ebfeff1b55d --- /dev/null +++ b/include/linux/extcon/of_extcon.h @@ -0,0 +1,31 @@ +/* + * OF helpers for External connector (extcon) framework + * + * Copyright (C) 2013 Texas Instruments, Inc. + * Kishon Vijay Abraham I + * + * Copyright (C) 2013 Samsung Electronics + * Chanwoo Choi + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef __LINUX_OF_EXTCON_H +#define __LINUX_OF_EXTCON_H + +#include + +#if IS_ENABLED(CONFIG_OF_EXTCON) +extern struct extcon_dev + *of_extcon_get_extcon_dev(struct device *dev, int index); +#else +static inline struct extcon_dev + *of_extcon_get_extcon_dev(struct device *dev, int index) +{ + return ERR_PTR(-ENOSYS); +} +#endif /* CONFIG_OF_EXTCON */ +#endif /* __LINUX_OF_EXTCON_H */ -- cgit v1.2.3 From 8061ad7239f3f97b477984660e95134ca684578c Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Mon, 8 Jul 2013 09:54:43 +0900 Subject: usb: dwc3: use extcon fwrk to receive connect/disconnect Modified dwc3-omap to receive connect and disconnect notification using extcon framework. Also did the necessary cleanups required after adapting to extcon framework. Signed-off-by: Kishon Vijay Abraham I Acked-by: Felipe Balbi Signed-off-by: Chanwoo Choi --- include/linux/usb/dwc3-omap.h | 30 ------------------------------ 1 file changed, 30 deletions(-) delete mode 100644 include/linux/usb/dwc3-omap.h (limited to 'include/linux') diff --git a/include/linux/usb/dwc3-omap.h b/include/linux/usb/dwc3-omap.h deleted file mode 100644 index 5615f4d82724..000000000000 --- a/include/linux/usb/dwc3-omap.h +++ /dev/null @@ -1,30 +0,0 @@ -/* - * Copyright (C) 2013 by Texas Instruments - * - * The Inventra Controller Driver for Linux is free software; you - * can redistribute it and/or modify it under the terms of the GNU - * General Public License version 2 as published by the Free Software - * Foundation. - */ - -#ifndef __DWC3_OMAP_H__ -#define __DWC3_OMAP_H__ - -enum omap_dwc3_vbus_id_status { - OMAP_DWC3_UNKNOWN = 0, - OMAP_DWC3_ID_GROUND, - OMAP_DWC3_ID_FLOAT, - OMAP_DWC3_VBUS_VALID, - OMAP_DWC3_VBUS_OFF, -}; - -#if (defined(CONFIG_USB_DWC3) || defined(CONFIG_USB_DWC3_MODULE)) -extern int dwc3_omap_mailbox(enum omap_dwc3_vbus_id_status status); -#else -static inline int dwc3_omap_mailbox(enum omap_dwc3_vbus_id_status status) -{ - return -ENODEV; -} -#endif - -#endif /* __DWC3_OMAP_H__ */ -- cgit v1.2.3 From 43e3f38892a6a521ff5901cdb97cf6985101badd Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Tue, 9 Jul 2013 18:34:21 +0530 Subject: extcon: palmas: remove unused member from palams_usb structure Remove unused member vbus_enable and set_vbus_work from palmas_usb as these members are not used in drivers. Signed-off-by: Laxman Dewangan Acked-by: Graeme Gregory Signed-off-by: Chanwoo Choi Signed-off-by: Myungjoo Ham --- include/linux/mfd/palmas.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index 1a8dd7afe084..03c22ca55446 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -371,16 +371,11 @@ struct palmas_usb { struct extcon_dev edev; - /* used to set vbus, in atomic path */ - struct work_struct set_vbus_work; - int id_otg_irq; int id_irq; int vbus_otg_irq; int vbus_irq; - int vbus_enable; - enum palmas_usb_state linkstat; }; -- cgit v1.2.3 From 7281e05aabee7484624d448da208932690ed62b3 Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Wed, 10 Jul 2013 14:59:06 +0530 Subject: extcon: palmas: Option to disable ID/VBUS detection based on platform Based on system design, platform needs to detect the VBUS or ID or both. Provide option to select this through platform data to disable part of cable detection through palmas-usb. Signed-off-by: Laxman Dewangan Acked-by: Graeme Gregory Signed-off-by: Chanwoo Choi Signed-off-by: Myungjoo Ham --- include/linux/mfd/palmas.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index 03c22ca55446..cfc678ceb570 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -377,6 +377,9 @@ struct palmas_usb { int vbus_irq; enum palmas_usb_state linkstat; + int wakeup; + bool enable_vbus_detection; + bool enable_id_detection; }; #define comparator_to_palmas(x) container_of((x), struct palmas_usb, comparator) -- cgit v1.2.3 From 7d46daba8dd5df1aa45724518a041ef7163d3ad5 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Mon, 5 Aug 2013 16:05:32 +0300 Subject: mlx5: remove health handler plugin Remove this code, per Dave Miller's request, since it is not being used anywhere in the kernel. Signed-off-by: Eli Cohen Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 2aa258b0ced1..611e65e76b00 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -731,9 +731,6 @@ void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev); int mlx5_db_alloc(struct mlx5_core_dev *dev, struct mlx5_db *db); void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db); -typedef void (*health_handler_t)(struct pci_dev *pdev, struct health_buffer __iomem *buf, int size); -int mlx5_register_health_report_handler(health_handler_t handler); -void mlx5_unregister_health_report_handler(void); const char *mlx5_command_str(int command); int mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev); void mlx5_cmdif_debugfs_cleanup(struct mlx5_core_dev *dev); -- cgit v1.2.3 From 49ccc142f9cbc33fdda18e8fa90c1c5b4a79c0ad Mon Sep 17 00:00:00 2001 From: Mateusz Krawczuk Date: Tue, 6 Aug 2013 18:34:40 +0200 Subject: regmap: Add missing header for !CONFIG_REGMAP stubs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit regmap.h requires linux/err.h if CONFIG_REGMAP is not defined. Without it I get error. CC drivers/media/platform/exynos4-is/fimc-reg.o In file included from drivers/media/platform/exynos4-is/fimc-reg.c:14:0: include/linux/regmap.h: In function ‘regmap_write’: include/linux/regmap.h:525:10: error: ‘EINVAL’ undeclared (first use in this function) include/linux/regmap.h:525:10: note: each undeclared identifier is reported only once for each function it appears in Signed-off-by: Mateusz Krawczuk Signed-off-by: Kyungmin Park Signed-off-by: Mark Brown Cc: stable@kernel.org --- include/linux/regmap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 75981d0b57dc..580a5320cc96 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -15,6 +15,7 @@ #include #include +#include struct module; struct device; -- cgit v1.2.3 From b6c035d04e80b4244a143e34e51c84cf2181bd94 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 5 Aug 2013 15:02:48 -0700 Subject: x86, asmlinkage: Make dump_stack visible dump_stack is used from assembler code, so make it visible. Signed-off-by: Andi Kleen Link: http://lkml.kernel.org/r/1375740170-7446-15-git-send-email-andi@firstfloor.org Signed-off-by: H. Peter Anvin --- include/linux/printk.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index 22c7052e9372..e6131a782481 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -200,7 +200,7 @@ static inline void show_regs_print_info(const char *log_lvl) } #endif -extern void dump_stack(void) __cold; +extern asmlinkage void dump_stack(void) __cold; #ifndef pr_fmt #define pr_fmt(fmt) fmt -- cgit v1.2.3 From 36f8250e4d478429a393c20910dcd02772bd0839 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Wed, 7 Aug 2013 08:56:10 +0800 Subject: regulator: fan53555: Prevent multiple include of fan53555.h Add define for __FAN53555_H__ to prevent multiple include of the header file. Signed-off-by: Axel Lin Signed-off-by: Mark Brown --- include/linux/regulator/fan53555.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/regulator/fan53555.h b/include/linux/regulator/fan53555.h index 5c45c85d52ca..f13880e84d85 100644 --- a/include/linux/regulator/fan53555.h +++ b/include/linux/regulator/fan53555.h @@ -11,6 +11,7 @@ */ #ifndef __FAN53555_H__ +#define __FAN53555_H__ /* VSEL ID */ enum { -- cgit v1.2.3 From 786615bc1ce84150ded80daea6bd9f6297f48e73 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 5 Aug 2013 16:04:47 -0400 Subject: SUNRPC: If the rpcbind channel is disconnected, fail the call to unregister If rpcbind causes our connection to the AF_LOCAL socket to close after we've registered a service, then we want to be careful about reconnecting since the mount namespace may have changed. By simply refusing to reconnect the AF_LOCAL socket in the case of unregister, we avoid the need to somehow save the mount namespace. While this may lead to some services not unregistering properly, it should be safe. Signed-off-by: Trond Myklebust Cc: Nix Cc: Jeff Layton Cc: stable@vger.kernel.org # 3.9.x --- include/linux/sunrpc/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 6d870353674a..1821445708d6 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -121,6 +121,7 @@ struct rpc_task_setup { #define RPC_TASK_SOFTCONN 0x0400 /* Fail if can't connect */ #define RPC_TASK_SENT 0x0800 /* message was sent */ #define RPC_TASK_TIMEOUT 0x1000 /* fail with ETIMEDOUT on timeout */ +#define RPC_TASK_NOCONNECT 0x2000 /* return ENOTCONN if not connected */ #define RPC_IS_ASYNC(t) ((t)->tk_flags & RPC_TASK_ASYNC) #define RPC_IS_SWAPPER(t) ((t)->tk_flags & RPC_TASK_SWAPPER) -- cgit v1.2.3 From 5ff0a268037d344f86df690ccb994d8bc015d2d9 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 6 Aug 2013 22:53:03 +0530 Subject: cpufreq: Clean up header files included in the core This patch addresses the following issues in the header files in the cpufreq core: - Include headers in ascending order, so that we don't add same many times by mistake. - must be included after , so that they override whatever they need to. - Remove unnecessary includes. - Don't include files already included by cpufreq.h or cpufreq_governor.h. [rjw: Changelog] Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index e1fd215e16c9..97627bbbca82 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -11,16 +11,11 @@ #ifndef _LINUX_CPUFREQ_H #define _LINUX_CPUFREQ_H -#include -#include -#include -#include +#include +#include #include +#include #include -#include -#include -#include -#include #define CPUFREQ_NAME_LEN 16 /* Print length for names. Extra 1 space for accomodating '\n' in prints */ -- cgit v1.2.3 From 74aca95da74836a6807118f6590d8df8232c74a9 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 6 Aug 2013 22:53:04 +0530 Subject: cpufreq: Re-arrange declarations in cpufreq.h They are pretty much mixed up. Although generic headers are present, definitions/declarations are present outside of them too ... This patch just moves stuff up and down to make it look better and consistent. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 373 +++++++++++++++++++++++------------------------- 1 file changed, 177 insertions(+), 196 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 97627bbbca82..0d3b0266bc98 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -17,60 +17,30 @@ #include #include -#define CPUFREQ_NAME_LEN 16 -/* Print length for names. Extra 1 space for accomodating '\n' in prints */ -#define CPUFREQ_NAME_PLEN (CPUFREQ_NAME_LEN + 1) - /********************************************************************* - * CPUFREQ NOTIFIER INTERFACE * + * CPUFREQ INTERFACE * *********************************************************************/ - -#define CPUFREQ_TRANSITION_NOTIFIER (0) -#define CPUFREQ_POLICY_NOTIFIER (1) - -#ifdef CONFIG_CPU_FREQ -int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list); -int cpufreq_unregister_notifier(struct notifier_block *nb, unsigned int list); -extern void disable_cpufreq(void); -#else /* CONFIG_CPU_FREQ */ -static inline int cpufreq_register_notifier(struct notifier_block *nb, - unsigned int list) -{ - return 0; -} -static inline int cpufreq_unregister_notifier(struct notifier_block *nb, - unsigned int list) -{ - return 0; -} -static inline void disable_cpufreq(void) { } -#endif /* CONFIG_CPU_FREQ */ - -/* if (cpufreq_driver->target) exists, the ->governor decides what frequency - * within the limits is used. If (cpufreq_driver->setpolicy> exists, these - * two generic policies are available: - */ - -#define CPUFREQ_POLICY_POWERSAVE (1) -#define CPUFREQ_POLICY_PERFORMANCE (2) - -/* Frequency values here are CPU kHz so that hardware which doesn't run - * with some frequencies can complain without having to guess what per - * cent / per mille means. +/* + * Frequency values here are CPU kHz + * * Maximum transition latency is in nanoseconds - if it's unknown, * CPUFREQ_ETERNAL shall be used. */ +#define CPUFREQ_ETERNAL (-1) +#define CPUFREQ_NAME_LEN 16 +/* Print length for names. Extra 1 space for accomodating '\n' in prints */ +#define CPUFREQ_NAME_PLEN (CPUFREQ_NAME_LEN + 1) + struct cpufreq_governor; -/* /sys/devices/system/cpu/cpufreq: entry point for global variables */ -extern struct kobject *cpufreq_global_kobject; -int cpufreq_get_global_kobject(void); -void cpufreq_put_global_kobject(void); -int cpufreq_sysfs_create_file(const struct attribute *attr); -void cpufreq_sysfs_remove_file(const struct attribute *attr); +struct cpufreq_freqs { + unsigned int cpu; /* cpu nr */ + unsigned int old; + unsigned int new; + u8 flags; /* flags of cpufreq_driver, see below. */ +}; -#define CPUFREQ_ETERNAL (-1) struct cpufreq_cpuinfo { unsigned int max_freq; unsigned int min_freq; @@ -117,111 +87,95 @@ struct cpufreq_policy { int transition_ongoing; /* Tracks transition status */ }; -#define CPUFREQ_ADJUST (0) -#define CPUFREQ_INCOMPATIBLE (1) -#define CPUFREQ_NOTIFY (2) -#define CPUFREQ_START (3) -#define CPUFREQ_UPDATE_POLICY_CPU (4) - /* Only for ACPI */ #define CPUFREQ_SHARED_TYPE_NONE (0) /* None */ #define CPUFREQ_SHARED_TYPE_HW (1) /* HW does needed coordination */ #define CPUFREQ_SHARED_TYPE_ALL (2) /* All dependent CPUs should set freq */ #define CPUFREQ_SHARED_TYPE_ANY (3) /* Freq can be set from any dependent CPU*/ +struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu); +void cpufreq_cpu_put(struct cpufreq_policy *data); + static inline bool policy_is_shared(struct cpufreq_policy *policy) { return cpumask_weight(policy->cpus) > 1; } -/******************** cpufreq transition notifiers *******************/ - -#define CPUFREQ_PRECHANGE (0) -#define CPUFREQ_POSTCHANGE (1) -#define CPUFREQ_RESUMECHANGE (8) -#define CPUFREQ_SUSPENDCHANGE (9) +/* /sys/devices/system/cpu/cpufreq: entry point for global variables */ +extern struct kobject *cpufreq_global_kobject; +int cpufreq_get_global_kobject(void); +void cpufreq_put_global_kobject(void); +int cpufreq_sysfs_create_file(const struct attribute *attr); +void cpufreq_sysfs_remove_file(const struct attribute *attr); -struct cpufreq_freqs { - unsigned int cpu; /* cpu nr */ - unsigned int old; - unsigned int new; - u8 flags; /* flags of cpufreq_driver, see below. */ -}; +#ifdef CONFIG_CPU_FREQ +unsigned int cpufreq_get(unsigned int cpu); +unsigned int cpufreq_quick_get(unsigned int cpu); +unsigned int cpufreq_quick_get_max(unsigned int cpu); +void disable_cpufreq(void); -/** - * cpufreq_scale - "old * mult / div" calculation for large values (32-bit-arch - * safe) - * @old: old value - * @div: divisor - * @mult: multiplier - * - * - * new = old * mult / div - */ -static inline unsigned long cpufreq_scale(unsigned long old, u_int div, - u_int mult) +u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy); +int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu); +int cpufreq_update_policy(unsigned int cpu); +bool have_governor_per_policy(void); +struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy); +#else +static inline unsigned int cpufreq_get(unsigned int cpu) { -#if BITS_PER_LONG == 32 - - u64 result = ((u64) old) * ((u64) mult); - do_div(result, div); - return (unsigned long) result; - -#elif BITS_PER_LONG == 64 - - unsigned long result = old * ((u64) mult); - result /= div; - return result; - + return 0; +} +static inline unsigned int cpufreq_quick_get(unsigned int cpu) +{ + return 0; +} +static inline unsigned int cpufreq_quick_get_max(unsigned int cpu) +{ + return 0; +} +static inline void disable_cpufreq(void) { } #endif -}; /********************************************************************* - * CPUFREQ GOVERNORS * + * CPUFREQ DRIVER INTERFACE * *********************************************************************/ -#define CPUFREQ_GOV_START 1 -#define CPUFREQ_GOV_STOP 2 -#define CPUFREQ_GOV_LIMITS 3 -#define CPUFREQ_GOV_POLICY_INIT 4 -#define CPUFREQ_GOV_POLICY_EXIT 5 +#define CPUFREQ_RELATION_L 0 /* lowest frequency at or above target */ +#define CPUFREQ_RELATION_H 1 /* highest frequency below or at target */ -struct cpufreq_governor { - char name[CPUFREQ_NAME_LEN]; - int initialized; - int (*governor) (struct cpufreq_policy *policy, - unsigned int event); - ssize_t (*show_setspeed) (struct cpufreq_policy *policy, - char *buf); - int (*store_setspeed) (struct cpufreq_policy *policy, - unsigned int freq); - unsigned int max_transition_latency; /* HW must be able to switch to - next freq faster than this value in nano secs or we - will fallback to performance governor */ - struct list_head governor_list; - struct module *owner; +struct freq_attr { + struct attribute attr; + ssize_t (*show)(struct cpufreq_policy *, char *); + ssize_t (*store)(struct cpufreq_policy *, const char *, size_t count); }; -/* - * Pass a target to the cpufreq driver. - */ -extern int cpufreq_driver_target(struct cpufreq_policy *policy, - unsigned int target_freq, - unsigned int relation); -extern int __cpufreq_driver_target(struct cpufreq_policy *policy, - unsigned int target_freq, - unsigned int relation); -int cpufreq_register_governor(struct cpufreq_governor *governor); -void cpufreq_unregister_governor(struct cpufreq_governor *governor); +#define cpufreq_freq_attr_ro(_name) \ +static struct freq_attr _name = \ +__ATTR(_name, 0444, show_##_name, NULL) -/********************************************************************* - * CPUFREQ DRIVER INTERFACE * - *********************************************************************/ +#define cpufreq_freq_attr_ro_perm(_name, _perm) \ +static struct freq_attr _name = \ +__ATTR(_name, _perm, show_##_name, NULL) -#define CPUFREQ_RELATION_L 0 /* lowest frequency at or above target */ -#define CPUFREQ_RELATION_H 1 /* highest frequency below or at target */ +#define cpufreq_freq_attr_rw(_name) \ +static struct freq_attr _name = \ +__ATTR(_name, 0644, show_##_name, store_##_name) + +struct global_attr { + struct attribute attr; + ssize_t (*show)(struct kobject *kobj, + struct attribute *attr, char *buf); + ssize_t (*store)(struct kobject *a, struct attribute *b, + const char *c, size_t count); +}; + +#define define_one_global_ro(_name) \ +static struct global_attr _name = \ +__ATTR(_name, 0444, show_##_name, NULL) + +#define define_one_global_rw(_name) \ +static struct global_attr _name = \ +__ATTR(_name, 0644, show_##_name, store_##_name) -struct freq_attr; struct cpufreq_driver { struct module *owner; @@ -258,7 +212,6 @@ struct cpufreq_driver { }; /* flags */ - #define CPUFREQ_STICKY 0x01 /* the driver isn't removed even if * all ->init() calls failed */ #define CPUFREQ_CONST_LOOPS 0x02 /* loops_per_jiffy or other kernel @@ -270,8 +223,7 @@ struct cpufreq_driver { int cpufreq_register_driver(struct cpufreq_driver *driver_data); int cpufreq_unregister_driver(struct cpufreq_driver *driver_data); -void cpufreq_notify_transition(struct cpufreq_policy *policy, - struct cpufreq_freqs *freqs, unsigned int state); +const char *cpufreq_get_current_driver(void); static inline void cpufreq_verify_within_limits(struct cpufreq_policy *policy, unsigned int min, unsigned int max) @@ -289,86 +241,117 @@ static inline void cpufreq_verify_within_limits(struct cpufreq_policy *policy, return; } -struct freq_attr { - struct attribute attr; - ssize_t (*show)(struct cpufreq_policy *, char *); - ssize_t (*store)(struct cpufreq_policy *, const char *, size_t count); -}; - -#define cpufreq_freq_attr_ro(_name) \ -static struct freq_attr _name = \ -__ATTR(_name, 0444, show_##_name, NULL) - -#define cpufreq_freq_attr_ro_perm(_name, _perm) \ -static struct freq_attr _name = \ -__ATTR(_name, _perm, show_##_name, NULL) - -#define cpufreq_freq_attr_rw(_name) \ -static struct freq_attr _name = \ -__ATTR(_name, 0644, show_##_name, store_##_name) +/********************************************************************* + * CPUFREQ NOTIFIER INTERFACE * + *********************************************************************/ -struct global_attr { - struct attribute attr; - ssize_t (*show)(struct kobject *kobj, - struct attribute *attr, char *buf); - ssize_t (*store)(struct kobject *a, struct attribute *b, - const char *c, size_t count); -}; +#define CPUFREQ_TRANSITION_NOTIFIER (0) +#define CPUFREQ_POLICY_NOTIFIER (1) -#define define_one_global_ro(_name) \ -static struct global_attr _name = \ -__ATTR(_name, 0444, show_##_name, NULL) +/* Transition notifiers */ +#define CPUFREQ_PRECHANGE (0) +#define CPUFREQ_POSTCHANGE (1) +#define CPUFREQ_RESUMECHANGE (8) +#define CPUFREQ_SUSPENDCHANGE (9) -#define define_one_global_rw(_name) \ -static struct global_attr _name = \ -__ATTR(_name, 0644, show_##_name, store_##_name) +/* Policy Notifiers */ +#define CPUFREQ_ADJUST (0) +#define CPUFREQ_INCOMPATIBLE (1) +#define CPUFREQ_NOTIFY (2) +#define CPUFREQ_START (3) +#define CPUFREQ_UPDATE_POLICY_CPU (4) -struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu); -void cpufreq_cpu_put(struct cpufreq_policy *data); -const char *cpufreq_get_current_driver(void); +#ifdef CONFIG_CPU_FREQ +int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list); +int cpufreq_unregister_notifier(struct notifier_block *nb, unsigned int list); -/********************************************************************* - * CPUFREQ 2.6. INTERFACE * - *********************************************************************/ -u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy); -int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu); -int cpufreq_update_policy(unsigned int cpu); -bool have_governor_per_policy(void); -struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy); +void cpufreq_notify_transition(struct cpufreq_policy *policy, + struct cpufreq_freqs *freqs, unsigned int state); -#ifdef CONFIG_CPU_FREQ -/* - * query the current CPU frequency (in kHz). If zero, cpufreq couldn't detect it - */ -unsigned int cpufreq_get(unsigned int cpu); -#else -static inline unsigned int cpufreq_get(unsigned int cpu) +#else /* CONFIG_CPU_FREQ */ +static inline int cpufreq_register_notifier(struct notifier_block *nb, + unsigned int list) { return 0; } -#endif - -/* - * query the last known CPU freq (in kHz). If zero, cpufreq couldn't detect it - */ -#ifdef CONFIG_CPU_FREQ -unsigned int cpufreq_quick_get(unsigned int cpu); -unsigned int cpufreq_quick_get_max(unsigned int cpu); -#else -static inline unsigned int cpufreq_quick_get(unsigned int cpu) +static inline int cpufreq_unregister_notifier(struct notifier_block *nb, + unsigned int list) { return 0; } -static inline unsigned int cpufreq_quick_get_max(unsigned int cpu) +#endif /* !CONFIG_CPU_FREQ */ + +/** + * cpufreq_scale - "old * mult / div" calculation for large values (32-bit-arch + * safe) + * @old: old value + * @div: divisor + * @mult: multiplier + * + * + * new = old * mult / div + */ +static inline unsigned long cpufreq_scale(unsigned long old, u_int div, + u_int mult) { - return 0; -} +#if BITS_PER_LONG == 32 + u64 result = ((u64) old) * ((u64) mult); + do_div(result, div); + return (unsigned long) result; + +#elif BITS_PER_LONG == 64 + unsigned long result = old * ((u64) mult); + result /= div; + return result; #endif +} /********************************************************************* - * CPUFREQ DEFAULT GOVERNOR * + * CPUFREQ GOVERNORS * *********************************************************************/ +/* + * If (cpufreq_driver->target) exists, the ->governor decides what frequency + * within the limits is used. If (cpufreq_driver->setpolicy> exists, these + * two generic policies are available: + */ +#define CPUFREQ_POLICY_POWERSAVE (1) +#define CPUFREQ_POLICY_PERFORMANCE (2) + +/* Governor Events */ +#define CPUFREQ_GOV_START 1 +#define CPUFREQ_GOV_STOP 2 +#define CPUFREQ_GOV_LIMITS 3 +#define CPUFREQ_GOV_POLICY_INIT 4 +#define CPUFREQ_GOV_POLICY_EXIT 5 + +struct cpufreq_governor { + char name[CPUFREQ_NAME_LEN]; + int initialized; + int (*governor) (struct cpufreq_policy *policy, + unsigned int event); + ssize_t (*show_setspeed) (struct cpufreq_policy *policy, + char *buf); + int (*store_setspeed) (struct cpufreq_policy *policy, + unsigned int freq); + unsigned int max_transition_latency; /* HW must be able to switch to + next freq faster than this value in nano secs or we + will fallback to performance governor */ + struct list_head governor_list; + struct module *owner; +}; + +/* Pass a target to the cpufreq driver */ +int cpufreq_driver_target(struct cpufreq_policy *policy, + unsigned int target_freq, + unsigned int relation); +int __cpufreq_driver_target(struct cpufreq_policy *policy, + unsigned int target_freq, + unsigned int relation); +int cpufreq_register_governor(struct cpufreq_governor *governor); +void cpufreq_unregister_governor(struct cpufreq_governor *governor); + +/* CPUFREQ DEFAULT GOVERNOR */ /* * Performance governor is fallback governor if any other gov failed to auto * load due latency restrictions @@ -417,18 +400,16 @@ int cpufreq_frequency_table_target(struct cpufreq_policy *policy, unsigned int relation, unsigned int *index); -/* the following 3 funtions are for cpufreq core use only */ +void cpufreq_frequency_table_update_policy_cpu(struct cpufreq_policy *policy); +ssize_t cpufreq_show_cpus(const struct cpumask *mask, char *buf); + +/* the following funtion is for cpufreq core use only */ struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu); /* the following are really really optional */ extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs; - void cpufreq_frequency_table_get_attr(struct cpufreq_frequency_table *table, unsigned int cpu); -void cpufreq_frequency_table_update_policy_cpu(struct cpufreq_policy *policy); - void cpufreq_frequency_table_put_attr(unsigned int cpu); -ssize_t cpufreq_show_cpus(const struct cpumask *mask, char *buf); - #endif /* _LINUX_CPUFREQ_H */ -- cgit v1.2.3 From 3a3e9e06d0c11b8efa95933a88c9e67209fa4330 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 6 Aug 2013 22:53:05 +0530 Subject: cpufreq: Give consistent names to cpufreq_policy objects They are called policy, cur_policy, new_policy, data, etc. Just call them policy wherever possible. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 0d3b0266bc98..29208923c9d3 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -94,7 +94,7 @@ struct cpufreq_policy { #define CPUFREQ_SHARED_TYPE_ANY (3) /* Freq can be set from any dependent CPU*/ struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu); -void cpufreq_cpu_put(struct cpufreq_policy *data); +void cpufreq_cpu_put(struct cpufreq_policy *policy); static inline bool policy_is_shared(struct cpufreq_policy *policy) { -- cgit v1.2.3 From 8742f229b635bf1c1c84a3dfe5e47c814c20b5c8 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 8 Aug 2013 18:55:32 +0200 Subject: userns: limit the maximum depth of user_namespace->parent chain Ensure that user_namespace->parent chain can't grow too much. Currently we use the hardroded 32 as limit. Reported-by: Andy Lutomirski Signed-off-by: Oleg Nesterov Signed-off-by: Linus Torvalds --- include/linux/user_namespace.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index b6b215f13b45..14105c26a836 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -23,6 +23,7 @@ struct user_namespace { struct uid_gid_map projid_map; atomic_t count; struct user_namespace *parent; + int level; kuid_t owner; kgid_t group; unsigned int proc_inum; -- cgit v1.2.3 From 8af01f56a03e9cbd91a55d688fce1315021efba8 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:22 -0400 Subject: cgroup: s/cgroup_subsys_state/cgroup_css/ s/task_subsys_state/task_css/ The names of the two struct cgroup_subsys_state accessors - cgroup_subsys_state() and task_subsys_state() - are somewhat awkward. The former clashes with the type name and the latter doesn't even indicate it's somehow related to cgroup. We're about to revamp large portion of cgroup API, so, let's rename them so that they're less awkward. Most per-controller usages of the accessors are localized in accessor wrappers and given the amount of scheduled changes, this isn't gonna add any noticeable headache. Rename cgroup_subsys_state() to cgroup_css() and task_subsys_state() to task_css(). This patch is pure rename. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 31 +++++++++++++++++++------------ 1 file changed, 19 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 44dd422d7e9b..552c5feef733 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -647,8 +647,15 @@ struct cgroup_subsys { #undef IS_SUBSYS_ENABLED #undef SUBSYS -static inline struct cgroup_subsys_state *cgroup_subsys_state( - struct cgroup *cgrp, int subsys_id) +/** + * cgroup_css - obtain a cgroup's css for the specified subsystem + * @cgrp: the cgroup of interest + * @subsys_id: the subsystem of interest + * + * Return @cgrp's css (cgroup_subsys_state) associated with @subsys_id. + */ +static inline struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp, + int subsys_id) { return cgrp->subsys[subsys_id]; } @@ -678,7 +685,7 @@ extern struct mutex cgroup_mutex; #endif /** - * task_subsys_state_check - obtain css for (task, subsys) w/ extra access conds + * task_css_check - obtain css for (task, subsys) w/ extra access conds * @task: the target task * @subsys_id: the target subsystem ID * @__c: extra condition expression to be passed to rcu_dereference_check() @@ -686,7 +693,7 @@ extern struct mutex cgroup_mutex; * Return the cgroup_subsys_state for the (@task, @subsys_id) pair. The * synchronization rules are the same as task_css_set_check(). */ -#define task_subsys_state_check(task, subsys_id, __c) \ +#define task_css_check(task, subsys_id, __c) \ task_css_set_check((task), (__c))->subsys[(subsys_id)] /** @@ -701,22 +708,22 @@ static inline struct css_set *task_css_set(struct task_struct *task) } /** - * task_subsys_state - obtain css for (task, subsys) + * task_css - obtain css for (task, subsys) * @task: the target task * @subsys_id: the target subsystem ID * - * See task_subsys_state_check(). + * See task_css_check(). */ -static inline struct cgroup_subsys_state * -task_subsys_state(struct task_struct *task, int subsys_id) +static inline struct cgroup_subsys_state *task_css(struct task_struct *task, + int subsys_id) { - return task_subsys_state_check(task, subsys_id, false); + return task_css_check(task, subsys_id, false); } -static inline struct cgroup* task_cgroup(struct task_struct *task, - int subsys_id) +static inline struct cgroup *task_cgroup(struct task_struct *task, + int subsys_id) { - return task_subsys_state(task, subsys_id)->cgroup; + return task_css(task, subsys_id)->cgroup; } /** -- cgit v1.2.3 From 72c97e54e0f043d33b246d7460ae0a36c4b8c643 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:22 -0400 Subject: cgroup: add subsystem pointer to cgroup_subsys_state Currently, given a cgroup_subsys_state, there's no way to find out which subsystem the css is for, which we'll need to convert the cgroup controller API to primarily use @css instead of @cgroup. This patch adds cgroup_subsys_state->ss which points to the subsystem the @css belongs to. While at it, remove the comment about accessing @css->cgroup to determine the hierarchy. cgroup core will provide API to traverse hierarchy of css'es and we don't want subsystems to directly walk cgroup hierarchies anymore. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 552c5feef733..821678aae4db 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -66,13 +66,12 @@ enum cgroup_subsys_id { /* Per-subsystem/per-cgroup state maintained by the system. */ struct cgroup_subsys_state { - /* - * The cgroup that this subsystem is attached to. Useful - * for subsystems that want to know about the cgroup - * hierarchy structure - */ + /* the cgroup that this css is attached to */ struct cgroup *cgroup; + /* the cgroup subsystem that this css is attached to */ + struct cgroup_subsys *ss; + /* reference count - access via css_[try]get() and css_put() */ struct percpu_ref refcnt; -- cgit v1.2.3 From 6387698699afd72d6304566fb6ccf84bffe07c56 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:23 -0400 Subject: cgroup: add css_parent() Currently, controllers have to explicitly follow the cgroup hierarchy to find the parent of a given css. cgroup is moving towards using cgroup_subsys_state as the main controller interface construct, so let's provide a way to climb the hierarchy using just csses. This patch implements css_parent() which, given a css, returns its parent. The function is guarnateed to valid non-NULL parent css as long as the target css is not at the top of the hierarchy. freezer, cpuset, cpu, cpuacct, hugetlb, memory, net_cls and devices are converted to use css_parent() instead of accessing cgroup->parent directly. * __parent_ca() is dropped from cpuacct and its usage is replaced with parent_ca(). The only difference between the two was NULL test on cgroup->parent which is now embedded in css_parent() making the distinction moot. Note that eventually a css->parent field will be added to css and the NULL check in css_parent() will go away. This patch shouldn't cause any behavior differences. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 821678aae4db..18112a3bb12b 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -646,6 +646,21 @@ struct cgroup_subsys { #undef IS_SUBSYS_ENABLED #undef SUBSYS +/** + * css_parent - find the parent css + * @css: the target cgroup_subsys_state + * + * Return the parent css of @css. This function is guaranteed to return + * non-NULL parent as long as @css isn't the root. + */ +static inline +struct cgroup_subsys_state *css_parent(struct cgroup_subsys_state *css) +{ + struct cgroup *parent_cgrp = css->cgroup->parent; + + return parent_cgrp ? parent_cgrp->subsys[css->ss->subsys_id] : NULL; +} + /** * cgroup_css - obtain a cgroup's css for the specified subsystem * @cgrp: the cgroup of interest -- cgit v1.2.3 From eb95419b023abacb415e2a18fea899023ce7624d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:23 -0400 Subject: cgroup: pass around cgroup_subsys_state instead of cgroup in subsystem methods cgroup is currently in the process of transitioning to using struct cgroup_subsys_state * as the primary handle instead of struct cgroup * in subsystem implementations for the following reasons. * With unified hierarchy, subsystems will be dynamically bound and unbound from cgroups and thus css's (cgroup_subsys_state) may be created and destroyed dynamically over the lifetime of a cgroup, which is different from the current state where all css's are allocated and destroyed together with the associated cgroup. This in turn means that cgroup_css() should be synchronized and may return NULL, making it more cumbersome to use. * Differing levels of per-subsystem granularity in the unified hierarchy means that the task and descendant iterators should behave differently depending on the specific subsystem the iteration is being performed for. * In majority of the cases, subsystems only care about its part in the cgroup hierarchy - ie. the hierarchy of css's. Subsystem methods often obtain the matching css pointer from the cgroup and don't bother with the cgroup pointer itself. Passing around css fits much better. This patch converts all cgroup_subsys methods to take @css instead of @cgroup. The conversions are mostly straight-forward. A few noteworthy changes are * ->css_alloc() now takes css of the parent cgroup rather than the pointer to the new cgroup as the css for the new cgroup doesn't exist yet. Knowing the parent css is enough for all the existing subsystems. * In kernel/cgroup.c::offline_css(), unnecessary open coded css dereference is replaced with local variable access. This patch shouldn't cause any behavior differences. v2: Unnecessary explicit cgrp->subsys[] deref in css_online() replaced with local variable @css as suggested by Li Zefan. Rebased on top of new for-3.12 which includes for-3.11-fixes so that ->css_free() invocation added by da0a12caff ("cgroup: fix a leak when percpu_ref_init() fails") is converted too. Suggested by Li Zefan. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Michal Hocko Acked-by: Vivek Goyal Acked-by: Aristeu Rozanski Acked-by: Daniel Wagner Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Johannes Weiner Cc: Balbir Singh Cc: Matt Helsley Cc: Jens Axboe Cc: Steven Rostedt --- include/linux/cgroup.h | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 18112a3bb12b..9c2b9dd9121d 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -579,18 +579,22 @@ int cgroup_taskset_size(struct cgroup_taskset *tset); */ struct cgroup_subsys { - struct cgroup_subsys_state *(*css_alloc)(struct cgroup *cgrp); - int (*css_online)(struct cgroup *cgrp); - void (*css_offline)(struct cgroup *cgrp); - void (*css_free)(struct cgroup *cgrp); - - int (*can_attach)(struct cgroup *cgrp, struct cgroup_taskset *tset); - void (*cancel_attach)(struct cgroup *cgrp, struct cgroup_taskset *tset); - void (*attach)(struct cgroup *cgrp, struct cgroup_taskset *tset); + struct cgroup_subsys_state *(*css_alloc)(struct cgroup_subsys_state *parent_css); + int (*css_online)(struct cgroup_subsys_state *css); + void (*css_offline)(struct cgroup_subsys_state *css); + void (*css_free)(struct cgroup_subsys_state *css); + + int (*can_attach)(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset); + void (*cancel_attach)(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset); + void (*attach)(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset); void (*fork)(struct task_struct *task); - void (*exit)(struct cgroup *cgrp, struct cgroup *old_cgrp, + void (*exit)(struct cgroup_subsys_state *css, + struct cgroup_subsys_state *old_css, struct task_struct *task); - void (*bind)(struct cgroup *root); + void (*bind)(struct cgroup_subsys_state *root_css); int subsys_id; int disabled; -- cgit v1.2.3 From 2bb566cb68dfafad328af666ebadf0e49accd6ca Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:23 -0400 Subject: cgroup: add subsys backlink pointer to cftype cgroup is transitioning to using css (cgroup_subsys_state) instead of cgroup as the primary subsystem handle. The cgroupfs file interface will be converted to use css's which requires finding out the subsystem from cftype so that the matching css can be determined from the cgroup. This patch adds cftype->ss which points to the subsystem the file belongs to. The field is initialized while a cftype is being registered. This makes it unnecessary to explicitly specify the subsystem for other cftype handling functions. @ss argument dropped from various cftype handling functions. This patch shouldn't introduce any behavior differences. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Vivek Goyal Cc: Jens Axboe --- include/linux/cgroup.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 9c2b9dd9121d..5db8138a0482 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -429,6 +429,12 @@ struct cftype { /* CFTYPE_* flags */ unsigned int flags; + /* + * The subsys this file belongs to. Initialized automatically + * during registration. NULL for cgroup core files. + */ + struct cgroup_subsys *ss; + int (*open)(struct inode *inode, struct file *file); ssize_t (*read)(struct cgroup *cgrp, struct cftype *cft, struct file *file, @@ -542,7 +548,7 @@ static inline const char *cgroup_name(const struct cgroup *cgrp) } int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); -int cgroup_rm_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); +int cgroup_rm_cftypes(struct cftype *cfts); bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor); -- cgit v1.2.3 From 67f4c36f83455b253445b2cb28ac9a2c4f85d99a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:24 -0400 Subject: cgroup: add cgroup->dummy_css cgroup subsystem API is being converted to use css (cgroup_subsys_state) as the main handle, which makes things a bit awkward for subsystem agnostic core features - the "cgroup.*" interface files and various iterations - a bit awkward as they don't have a css to use. This patch adds cgroup->dummy_css which has NULL ->ss and whose only role is pointing back to the cgroup. This will be used to support subsystem agnostic features on the coming css based API. css_parent() is updated to handle dummy_css's. Note that css will soon grow its own ->parent field and css_parent() will be made trivial. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 5db8138a0482..b0d5f53ae5e1 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -225,6 +225,9 @@ struct cgroup { struct list_head pidlists; struct mutex pidlist_mutex; + /* dummy css with NULL ->ss, points back to this cgroup */ + struct cgroup_subsys_state dummy_css; + /* For css percpu_ref killing and RCU-protected deletion */ struct rcu_head rcu_head; struct work_struct destroy_work; @@ -668,7 +671,13 @@ struct cgroup_subsys_state *css_parent(struct cgroup_subsys_state *css) { struct cgroup *parent_cgrp = css->cgroup->parent; - return parent_cgrp ? parent_cgrp->subsys[css->ss->subsys_id] : NULL; + if (!parent_cgrp) + return NULL; + + if (css->ss) + return parent_cgrp->subsys[css->ss->subsys_id]; + else + return &parent_cgrp->dummy_css; } /** -- cgit v1.2.3 From 182446d087906de40e514573a92a97b203695f71 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:24 -0400 Subject: cgroup: pass around cgroup_subsys_state instead of cgroup in file methods cgroup is currently in the process of transitioning to using struct cgroup_subsys_state * as the primary handle instead of struct cgroup. Please see the previous commit which converts the subsystem methods for rationale. This patch converts all cftype file operations to take @css instead of @cgroup. cftypes for the cgroup core files don't have their subsytem pointer set. These will automatically use the dummy_css added by the previous patch and can be converted the same way. Most subsystem conversions are straight forwards but there are some interesting ones. * freezer: update_if_frozen() is also converted to take @css instead of @cgroup for consistency. This will make the code look simpler too once iterators are converted to use css. * memory/vmpressure: mem_cgroup_from_css() needs to be exported to vmpressure while mem_cgroup_from_cont() can be made static. Updated accordingly. * cpu: cgroup_tg() doesn't have any user left. Removed. * cpuacct: cgroup_ca() doesn't have any user left. Removed. * hugetlb: hugetlb_cgroup_form_cgroup() doesn't have any user left. Removed. * net_cls: cgrp_cls_state() doesn't have any user left. Removed. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Michal Hocko Acked-by: Vivek Goyal Acked-by: Aristeu Rozanski Acked-by: Daniel Wagner Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Johannes Weiner Cc: Balbir Singh Cc: Matt Helsley Cc: Jens Axboe Cc: Steven Rostedt --- include/linux/cgroup.h | 24 +++++++++++++----------- include/linux/memcontrol.h | 2 +- 2 files changed, 14 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b0d5f53ae5e1..0b91436c68ef 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -439,34 +439,34 @@ struct cftype { struct cgroup_subsys *ss; int (*open)(struct inode *inode, struct file *file); - ssize_t (*read)(struct cgroup *cgrp, struct cftype *cft, + ssize_t (*read)(struct cgroup_subsys_state *css, struct cftype *cft, struct file *file, char __user *buf, size_t nbytes, loff_t *ppos); /* * read_u64() is a shortcut for the common case of returning a * single integer. Use it in place of read() */ - u64 (*read_u64)(struct cgroup *cgrp, struct cftype *cft); + u64 (*read_u64)(struct cgroup_subsys_state *css, struct cftype *cft); /* * read_s64() is a signed version of read_u64() */ - s64 (*read_s64)(struct cgroup *cgrp, struct cftype *cft); + s64 (*read_s64)(struct cgroup_subsys_state *css, struct cftype *cft); /* * read_map() is used for defining a map of key/value * pairs. It should call cb->fill(cb, key, value) for each * entry. The key/value pairs (and their ordering) should not * change between reboots. */ - int (*read_map)(struct cgroup *cgrp, struct cftype *cft, + int (*read_map)(struct cgroup_subsys_state *css, struct cftype *cft, struct cgroup_map_cb *cb); /* * read_seq_string() is used for outputting a simple sequence * using seqfile. */ - int (*read_seq_string)(struct cgroup *cgrp, struct cftype *cft, - struct seq_file *m); + int (*read_seq_string)(struct cgroup_subsys_state *css, + struct cftype *cft, struct seq_file *m); - ssize_t (*write)(struct cgroup *cgrp, struct cftype *cft, + ssize_t (*write)(struct cgroup_subsys_state *css, struct cftype *cft, struct file *file, const char __user *buf, size_t nbytes, loff_t *ppos); @@ -475,18 +475,20 @@ struct cftype { * a single integer (as parsed by simple_strtoull) from * userspace. Use in place of write(); return 0 or error. */ - int (*write_u64)(struct cgroup *cgrp, struct cftype *cft, u64 val); + int (*write_u64)(struct cgroup_subsys_state *css, struct cftype *cft, + u64 val); /* * write_s64() is a signed version of write_u64() */ - int (*write_s64)(struct cgroup *cgrp, struct cftype *cft, s64 val); + int (*write_s64)(struct cgroup_subsys_state *css, struct cftype *cft, + s64 val); /* * write_string() is passed a nul-terminated kernelspace * buffer of maximum length determined by max_write_len. * Returns 0 or -ve error code. */ - int (*write_string)(struct cgroup *cgrp, struct cftype *cft, + int (*write_string)(struct cgroup_subsys_state *css, struct cftype *cft, const char *buffer); /* * trigger() callback can be used to get some kick from the @@ -494,7 +496,7 @@ struct cftype { * at all. The private field can be used to determine the * kick type for multiplexing. */ - int (*trigger)(struct cgroup *cgrp, unsigned int event); + int (*trigger)(struct cgroup_subsys_state *css, unsigned int event); int (*release)(struct inode *inode, struct file *file); diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 7b4d9d79570b..6c416092e324 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -85,7 +85,7 @@ extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); extern struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm); extern struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg); -extern struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont); +extern struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css); static inline bool mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *memcg) -- cgit v1.2.3 From 3b287a505ef4024634beb12a93773254909d5dae Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:24 -0400 Subject: cgroup: convert cgroup_next_sibling() to cgroup_next_child() cgroup is transitioning to using css (cgroup_subsys_state) as the main subsys interface handle instead of cgroup and the iterators will be updated to use css too. The iterators need to walk the cgroup hierarchy and return the css's matching the origin css, which is a bit cumbersome to open code. This patch converts cgroup_next_sibling() to cgroup_next_child() so that it can handle all steps of direct child iteration. This will be used to update iterators to take @css instead of @cgrp. In addition to the new iteration init handling, cgroup_next_child() is restructured so that the different branches share the end of iteration condition check. This patch doesn't change any behavior. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 0b91436c68ef..5f9ba5881717 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -779,7 +779,7 @@ static inline struct cgroup *cgroup_from_id(struct cgroup_subsys *ss, int id) return idr_find(&ss->root->cgroup_idr, id); } -struct cgroup *cgroup_next_sibling(struct cgroup *pos); +struct cgroup *cgroup_next_child(struct cgroup *pos, struct cgroup *cgrp); /** * cgroup_for_each_child - iterate through children of a cgroup @@ -802,7 +802,7 @@ struct cgroup *cgroup_next_sibling(struct cgroup *pos); #define cgroup_for_each_child(pos, cgrp) \ for ((pos) = list_first_or_null_rcu(&(cgrp)->children, \ struct cgroup, sibling); \ - (pos); (pos) = cgroup_next_sibling((pos))) + (pos); (pos) = cgroup_next_child((pos), (cgrp))) struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos, struct cgroup *cgroup); -- cgit v1.2.3 From f48e3924dca268c677c4e338e5d91ad9e6fe6b9e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:24 -0400 Subject: cgroup: always use cgroup_next_child() to walk the children list There are several places where the children list is accessed directly. This patch converts those places to use cgroup_next_child(). This will help updating the hierarchy iterators to use @css instead of @cgrp. While cgroup_next_child() can be heavy in pathological cases - e.g. a lot of dead children, this shouldn't cause any noticeable behavior differences. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 5f9ba5881717..c288bce428f8 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -800,9 +800,8 @@ struct cgroup *cgroup_next_child(struct cgroup *pos, struct cgroup *cgrp); * the start of the next iteration by, for example, bumping the css refcnt. */ #define cgroup_for_each_child(pos, cgrp) \ - for ((pos) = list_first_or_null_rcu(&(cgrp)->children, \ - struct cgroup, sibling); \ - (pos); (pos) = cgroup_next_child((pos), (cgrp))) + for ((pos) = cgroup_next_child(NULL, (cgrp)); (pos); \ + (pos) = cgroup_next_child((pos), (cgrp))) struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos, struct cgroup *cgroup); -- cgit v1.2.3 From 492eb21b98f88e411a8bb43d6edcd7d7022add10 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:25 -0400 Subject: cgroup: make hierarchy iterators deal with cgroup_subsys_state instead of cgroup cgroup is currently in the process of transitioning to using css (cgroup_subsys_state) as the primary handle instead of cgroup in subsystem API. For hierarchy iterators, this is beneficial because * In most cases, css is the only thing subsystems care about anyway. * On the planned unified hierarchy, iterations for different subsystems will need to skip over different subtrees of the hierarchy depending on which subsystems are enabled on each cgroup. Passing around css makes it unnecessary to explicitly specify the subsystem in question as css is intersection between cgroup and subsystem * For the planned unified hierarchy, css's would need to be created and destroyed dynamically independent from cgroup hierarchy. Having cgroup core manage css iteration makes enforcing deref rules a lot easier. Most subsystem conversions are straight-forward. Noteworthy changes are * blkio: cgroup_to_blkcg() is no longer used. Removed. * freezer: cgroup_freezer() is no longer used. Removed. * devices: cgroup_to_devcgroup() is no longer used. Removed. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Michal Hocko Acked-by: Vivek Goyal Acked-by: Aristeu Rozanski Cc: Johannes Weiner Cc: Balbir Singh Cc: Matt Helsley Cc: Jens Axboe --- include/linux/cgroup.h | 88 ++++++++++++++++++++++++++------------------------ 1 file changed, 46 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index c288bce428f8..4bc22f4a1abb 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -779,68 +779,72 @@ static inline struct cgroup *cgroup_from_id(struct cgroup_subsys *ss, int id) return idr_find(&ss->root->cgroup_idr, id); } -struct cgroup *cgroup_next_child(struct cgroup *pos, struct cgroup *cgrp); +struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, + struct cgroup_subsys_state *parent); /** - * cgroup_for_each_child - iterate through children of a cgroup - * @pos: the cgroup * to use as the loop cursor - * @cgrp: cgroup whose children to walk + * css_for_each_child - iterate through children of a css + * @pos: the css * to use as the loop cursor + * @parent: css whose children to walk * - * Walk @cgrp's children. Must be called under rcu_read_lock(). A child - * cgroup which hasn't finished ->css_online() or already has finished + * Walk @parent's children. Must be called under rcu_read_lock(). A child + * css which hasn't finished ->css_online() or already has finished * ->css_offline() may show up during traversal and it's each subsystem's * responsibility to verify that each @pos is alive. * * If a subsystem synchronizes against the parent in its ->css_online() and - * before starting iterating, a cgroup which finished ->css_online() is + * before starting iterating, a css which finished ->css_online() is * guaranteed to be visible in the future iterations. * * It is allowed to temporarily drop RCU read lock during iteration. The * caller is responsible for ensuring that @pos remains accessible until * the start of the next iteration by, for example, bumping the css refcnt. */ -#define cgroup_for_each_child(pos, cgrp) \ - for ((pos) = cgroup_next_child(NULL, (cgrp)); (pos); \ - (pos) = cgroup_next_child((pos), (cgrp))) +#define css_for_each_child(pos, parent) \ + for ((pos) = css_next_child(NULL, (parent)); (pos); \ + (pos) = css_next_child((pos), (parent))) -struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos, - struct cgroup *cgroup); -struct cgroup *cgroup_rightmost_descendant(struct cgroup *pos); +struct cgroup_subsys_state * +css_next_descendant_pre(struct cgroup_subsys_state *pos, + struct cgroup_subsys_state *css); + +struct cgroup_subsys_state * +css_rightmost_descendant(struct cgroup_subsys_state *pos); /** - * cgroup_for_each_descendant_pre - pre-order walk of a cgroup's descendants - * @pos: the cgroup * to use as the loop cursor - * @cgroup: cgroup whose descendants to walk + * css_for_each_descendant_pre - pre-order walk of a css's descendants + * @pos: the css * to use as the loop cursor + * @root: css whose descendants to walk * - * Walk @cgroup's descendants. Must be called under rcu_read_lock(). A - * descendant cgroup which hasn't finished ->css_online() or already has + * Walk @root's descendants. Must be called under rcu_read_lock(). A + * descendant css which hasn't finished ->css_online() or already has * finished ->css_offline() may show up during traversal and it's each * subsystem's responsibility to verify that each @pos is alive. * * If a subsystem synchronizes against the parent in its ->css_online() and * before starting iterating, and synchronizes against @pos on each - * iteration, any descendant cgroup which finished ->css_online() is + * iteration, any descendant css which finished ->css_online() is * guaranteed to be visible in the future iterations. * * In other words, the following guarantees that a descendant can't escape * state updates of its ancestors. * - * my_online(@cgrp) + * my_online(@css) * { - * Lock @cgrp->parent and @cgrp; - * Inherit state from @cgrp->parent; + * Lock @css's parent and @css; + * Inherit state from the parent; * Unlock both. * } * - * my_update_state(@cgrp) + * my_update_state(@css) * { - * Lock @cgrp; - * Update @cgrp's state; - * Unlock @cgrp; + * Lock @css; + * Update @css's state; + * Unlock @css; * - * cgroup_for_each_descendant_pre(@pos, @cgrp) { + * css_for_each_descendant_pre(@pos, @css) { * Lock @pos; - * Verify @pos is alive and inherit state from @pos->parent; + * Verify @pos is alive and inherit state from @pos's parent; * Unlock @pos; * } * } @@ -851,8 +855,7 @@ struct cgroup *cgroup_rightmost_descendant(struct cgroup *pos); * visible by walking order and, as long as inheriting operations to the * same @pos are atomic to each other, multiple updates racing each other * still result in the correct state. It's guaranateed that at least one - * inheritance happens for any cgroup after the latest update to its - * parent. + * inheritance happens for any css after the latest update to its parent. * * If checking parent's state requires locking the parent, each inheriting * iteration should lock and unlock both @pos->parent and @pos. @@ -865,25 +868,26 @@ struct cgroup *cgroup_rightmost_descendant(struct cgroup *pos); * caller is responsible for ensuring that @pos remains accessible until * the start of the next iteration by, for example, bumping the css refcnt. */ -#define cgroup_for_each_descendant_pre(pos, cgroup) \ - for (pos = cgroup_next_descendant_pre(NULL, (cgroup)); (pos); \ - pos = cgroup_next_descendant_pre((pos), (cgroup))) +#define css_for_each_descendant_pre(pos, css) \ + for ((pos) = css_next_descendant_pre(NULL, (css)); (pos); \ + (pos) = css_next_descendant_pre((pos), (css))) -struct cgroup *cgroup_next_descendant_post(struct cgroup *pos, - struct cgroup *cgroup); +struct cgroup_subsys_state * +css_next_descendant_post(struct cgroup_subsys_state *pos, + struct cgroup_subsys_state *css); /** - * cgroup_for_each_descendant_post - post-order walk of a cgroup's descendants - * @pos: the cgroup * to use as the loop cursor - * @cgroup: cgroup whose descendants to walk + * css_for_each_descendant_post - post-order walk of a css's descendants + * @pos: the css * to use as the loop cursor + * @css: css whose descendants to walk * - * Similar to cgroup_for_each_descendant_pre() but performs post-order + * Similar to css_for_each_descendant_pre() but performs post-order * traversal instead. Note that the walk visibility guarantee described in * pre-order walk doesn't apply the same to post-order walks. */ -#define cgroup_for_each_descendant_post(pos, cgroup) \ - for (pos = cgroup_next_descendant_post(NULL, (cgroup)); (pos); \ - pos = cgroup_next_descendant_post((pos), (cgroup))) +#define css_for_each_descendant_post(pos, css) \ + for ((pos) = css_next_descendant_post(NULL, (css)); (pos); \ + (pos) = css_next_descendant_post((pos), (css))) /* A cgroup_iter should be treated as an opaque object */ struct cgroup_iter { -- cgit v1.2.3 From 0942eeeef68f9493c1bcb1a52baf612b73fcf9fb Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:26 -0400 Subject: cgroup: rename cgroup_iter to cgroup_task_iter cgroup now has multiple iterators and it's quite confusing to have something which walks over tasks of a single cgroup named cgroup_iter. Let's rename it to cgroup_task_iter. While at it, reformat / update comments and replace the overview comment above the interface function decls with proper function comments. Such overview can be useful but function comments should be more than enough here. This is pure rename and doesn't introduce any functional changes. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Michal Hocko Cc: Matt Helsley Cc: Johannes Weiner Cc: Balbir Singh --- include/linux/cgroup.h | 31 ++++++++----------------------- 1 file changed, 8 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 4bc22f4a1abb..ea439794bd9b 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -889,31 +889,16 @@ css_next_descendant_post(struct cgroup_subsys_state *pos, for ((pos) = css_next_descendant_post(NULL, (css)); (pos); \ (pos) = css_next_descendant_post((pos), (css))) -/* A cgroup_iter should be treated as an opaque object */ -struct cgroup_iter { - struct list_head *cset_link; - struct list_head *task; +/* A cgroup_task_iter should be treated as an opaque object */ +struct cgroup_task_iter { + struct list_head *cset_link; + struct list_head *task; }; -/* - * To iterate across the tasks in a cgroup: - * - * 1) call cgroup_iter_start to initialize an iterator - * - * 2) call cgroup_iter_next() to retrieve member tasks until it - * returns NULL or until you want to end the iteration - * - * 3) call cgroup_iter_end() to destroy the iterator. - * - * Or, call cgroup_scan_tasks() to iterate through every task in a - * cgroup - cgroup_scan_tasks() holds the css_set_lock when calling - * the test_task() callback, but not while calling the process_task() - * callback. - */ -void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it); -struct task_struct *cgroup_iter_next(struct cgroup *cgrp, - struct cgroup_iter *it); -void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it); +void cgroup_task_iter_start(struct cgroup *cgrp, struct cgroup_task_iter *it); +struct task_struct *cgroup_task_iter_next(struct cgroup *cgrp, + struct cgroup_task_iter *it); +void cgroup_task_iter_end(struct cgroup *cgrp, struct cgroup_task_iter *it); int cgroup_scan_tasks(struct cgroup_scanner *scan); int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); -- cgit v1.2.3 From c59cd3d840b1b0a8f996cbbd9132128dcaabbeb9 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:26 -0400 Subject: cgroup: make cgroup_task_iter remember the cgroup being iterated Currently all cgroup_task_iter functions require @cgrp to be passed in, which is superflous and increases chance of usage error. Make cgroup_task_iter remember the cgroup being iterated and drop @cgrp argument from next and end functions. This patch doesn't introduce any behavior differences. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Michal Hocko Cc: Matt Helsley Cc: Johannes Weiner Cc: Balbir Singh --- include/linux/cgroup.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index ea439794bd9b..0287fccd0f54 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -891,14 +891,14 @@ css_next_descendant_post(struct cgroup_subsys_state *pos, /* A cgroup_task_iter should be treated as an opaque object */ struct cgroup_task_iter { + struct cgroup *origin_cgrp; struct list_head *cset_link; struct list_head *task; }; void cgroup_task_iter_start(struct cgroup *cgrp, struct cgroup_task_iter *it); -struct task_struct *cgroup_task_iter_next(struct cgroup *cgrp, - struct cgroup_task_iter *it); -void cgroup_task_iter_end(struct cgroup *cgrp, struct cgroup_task_iter *it); +struct task_struct *cgroup_task_iter_next(struct cgroup_task_iter *it); +void cgroup_task_iter_end(struct cgroup_task_iter *it); int cgroup_scan_tasks(struct cgroup_scanner *scan); int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); -- cgit v1.2.3 From e535837b1dae17b5a2d76ea1bc22ac1a79354624 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:26 -0400 Subject: cgroup: remove struct cgroup_scanner cgroup_scan_tasks() takes a pointer to struct cgroup_scanner as its sole argument and the only function of that struct is packing the arguments of the function call which are consisted of five fields. It's not too unusual to pack parameters into a struct when the number of arguments gets excessive or the whole set needs to be passed around a lot, but neither holds here making it just weird. Drop struct cgroup_scanner and pass the params directly to cgroup_scan_tasks(). Note that struct cpuset_change_nodemask_arg was added to cpuset.c to pass both ->cs and ->newmems pointer to cpuset_change_nodemask() using single data pointer. This doesn't make any functional differences. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 0287fccd0f54..8472ed576b64 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -528,15 +528,6 @@ struct cftype_set { struct cftype *cfts; }; -struct cgroup_scanner { - struct cgroup *cgrp; - int (*test_task)(struct task_struct *p, struct cgroup_scanner *scan); - void (*process_task)(struct task_struct *p, - struct cgroup_scanner *scan); - struct ptr_heap *heap; - void *data; -}; - /* * See the comment above CGRP_ROOT_SANE_BEHAVIOR for details. This * function can be called as long as @cgrp is accessible. @@ -899,7 +890,12 @@ struct cgroup_task_iter { void cgroup_task_iter_start(struct cgroup *cgrp, struct cgroup_task_iter *it); struct task_struct *cgroup_task_iter_next(struct cgroup_task_iter *it); void cgroup_task_iter_end(struct cgroup_task_iter *it); -int cgroup_scan_tasks(struct cgroup_scanner *scan); + +int cgroup_scan_tasks(struct cgroup *cgrp, + bool (*test)(struct task_struct *, void *), + void (*process)(struct task_struct *, void *), + void *data, struct ptr_heap *heap); + int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); -- cgit v1.2.3 From 72ec7029937f0518eff21b8762743c31591684f5 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:26 -0400 Subject: cgroup: make task iterators deal with cgroup_subsys_state instead of cgroup cgroup is in the process of converting to css (cgroup_subsys_state) from cgroup as the principal subsystem interface handle. This is mostly to prepare for the unified hierarchy support where css's will be created and destroyed dynamically but also helps cleaning up subsystem implementations as css is usually what they are interested in anyway. This patch converts task iterators to deal with css instead of cgroup. Note that under unified hierarchy, different sets of tasks will be considered belonging to a given cgroup depending on the subsystem in question and making the iterators deal with css instead cgroup provides them with enough information about the iteration. While at it, fix several function comment formats in cpuset.c. This patch doesn't introduce any behavior differences. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Balbir Singh Cc: Matt Helsley --- include/linux/cgroup.h | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 8472ed576b64..cd105fce089c 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -880,21 +880,22 @@ css_next_descendant_post(struct cgroup_subsys_state *pos, for ((pos) = css_next_descendant_post(NULL, (css)); (pos); \ (pos) = css_next_descendant_post((pos), (css))) -/* A cgroup_task_iter should be treated as an opaque object */ -struct cgroup_task_iter { - struct cgroup *origin_cgrp; +/* A css_task_iter should be treated as an opaque object */ +struct css_task_iter { + struct cgroup_subsys_state *origin_css; struct list_head *cset_link; struct list_head *task; }; -void cgroup_task_iter_start(struct cgroup *cgrp, struct cgroup_task_iter *it); -struct task_struct *cgroup_task_iter_next(struct cgroup_task_iter *it); -void cgroup_task_iter_end(struct cgroup_task_iter *it); +void css_task_iter_start(struct cgroup_subsys_state *css, + struct css_task_iter *it); +struct task_struct *css_task_iter_next(struct css_task_iter *it); +void css_task_iter_end(struct css_task_iter *it); -int cgroup_scan_tasks(struct cgroup *cgrp, - bool (*test)(struct task_struct *, void *), - void (*process)(struct task_struct *, void *), - void *data, struct ptr_heap *heap); +int css_scan_tasks(struct cgroup_subsys_state *css, + bool (*test)(struct task_struct *, void *), + void (*process)(struct task_struct *, void *), + void *data, struct ptr_heap *heap); int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); -- cgit v1.2.3 From 81eeaf0411204f52af8ef78ff107cfca2fcfec1d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:26 -0400 Subject: cgroup: make cftype->[un]register_event() deal with cgroup_subsys_state instead of cgroup cgroup is in the process of converting to css (cgroup_subsys_state) from cgroup as the principal subsystem interface handle. This is mostly to prepare for the unified hierarchy support where css's will be created and destroyed dynamically but also helps cleaning up subsystem implementations as css is usually what they are interested in anyway. cftype->[un]register_event() is among the remaining couple interfaces which still use struct cgroup. Convert it to cgroup_subsys_state. The conversion is mostly mechanical and removes the last users of mem_cgroup_from_cont() and cg_to_vmpressure(), which are removed. v2: indentation update as suggested by Li Zefan. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Balbir Singh --- include/linux/cgroup.h | 10 ++++++---- include/linux/vmpressure.h | 6 ++++-- 2 files changed, 10 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index cd105fce089c..b065d24486e6 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -506,16 +506,18 @@ struct cftype { * you want to provide this functionality. Use eventfd_signal() * on eventfd to send notification to userspace. */ - int (*register_event)(struct cgroup *cgrp, struct cftype *cft, - struct eventfd_ctx *eventfd, const char *args); + int (*register_event)(struct cgroup_subsys_state *css, + struct cftype *cft, struct eventfd_ctx *eventfd, + const char *args); /* * unregister_event() callback will be called when userspace * closes the eventfd or on cgroup removing. * This callback must be implemented, if you want provide * notification functionality. */ - void (*unregister_event)(struct cgroup *cgrp, struct cftype *cft, - struct eventfd_ctx *eventfd); + void (*unregister_event)(struct cgroup_subsys_state *css, + struct cftype *cft, + struct eventfd_ctx *eventfd); }; /* diff --git a/include/linux/vmpressure.h b/include/linux/vmpressure.h index 76be077340ea..b239482bd39d 100644 --- a/include/linux/vmpressure.h +++ b/include/linux/vmpressure.h @@ -33,10 +33,12 @@ extern void vmpressure_init(struct vmpressure *vmpr); extern struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg); extern struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr); extern struct vmpressure *css_to_vmpressure(struct cgroup_subsys_state *css); -extern int vmpressure_register_event(struct cgroup *cg, struct cftype *cft, +extern int vmpressure_register_event(struct cgroup_subsys_state *css, + struct cftype *cft, struct eventfd_ctx *eventfd, const char *args); -extern void vmpressure_unregister_event(struct cgroup *cg, struct cftype *cft, +extern void vmpressure_unregister_event(struct cgroup_subsys_state *css, + struct cftype *cft, struct eventfd_ctx *eventfd); #else static inline void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, -- cgit v1.2.3 From d99c8727e7bbc01b70e2c57e6127bfab26b868fd Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:27 -0400 Subject: cgroup: make cgroup_taskset deal with cgroup_subsys_state instead of cgroup cgroup is in the process of converting to css (cgroup_subsys_state) from cgroup as the principal subsystem interface handle. This is mostly to prepare for the unified hierarchy support where css's will be created and destroyed dynamically but also helps cleaning up subsystem implementations as css is usually what they are interested in anyway. cgroup_taskset which is used by the subsystem attach methods is the last cgroup subsystem API which isn't using css as the handle. Update cgroup_taskset_cur_cgroup() to cgroup_taskset_cur_css() and cgroup_taskset_for_each() to take @skip_css instead of @skip_cgrp. The conversions are pretty mechanical. One exception is cpuset::cgroup_cs(), which lost its last user and got removed. This patch shouldn't introduce any functional changes. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Daniel Wagner Cc: Ingo Molnar Cc: Matt Helsley Cc: Steven Rostedt --- include/linux/cgroup.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b065d24486e6..d9a970568be9 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -562,20 +562,22 @@ int cgroup_task_count(const struct cgroup *cgrp); struct cgroup_taskset; struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset); struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset); -struct cgroup *cgroup_taskset_cur_cgroup(struct cgroup_taskset *tset); +struct cgroup_subsys_state *cgroup_taskset_cur_css(struct cgroup_taskset *tset, + int subsys_id); int cgroup_taskset_size(struct cgroup_taskset *tset); /** * cgroup_taskset_for_each - iterate cgroup_taskset * @task: the loop cursor - * @skip_cgrp: skip if task's cgroup matches this, %NULL to iterate through all + * @skip_css: skip if task's css matches this, %NULL to iterate through all * @tset: taskset to iterate */ -#define cgroup_taskset_for_each(task, skip_cgrp, tset) \ +#define cgroup_taskset_for_each(task, skip_css, tset) \ for ((task) = cgroup_taskset_first((tset)); (task); \ (task) = cgroup_taskset_next((tset))) \ - if (!(skip_cgrp) || \ - cgroup_taskset_cur_cgroup((tset)) != (skip_cgrp)) + if (!(skip_css) || \ + cgroup_taskset_cur_css((tset), \ + (skip_css)->ss->subsys_id) != (skip_css)) /* * Control Group subsystem type. -- cgit v1.2.3 From 95109b627ba6a043c181fa5fa45d1c754dd44fbc Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:27 -0400 Subject: cgroup: unexport cgroup_css() cgroup_css() no longer has any user left outside cgroup.c proper and we don't want subsystems to grow new usages of the function. cgroup core should always provide the css to use to the subsystems, which will make dynamic creation and destruction of css's across the lifetime of a cgroup much more manageable than exposing the cgroup directly to subsystems and let them dereference css's from it. Make cgroup_css() a static function in cgroup.c. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index d9a970568be9..c40e508d54e9 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -677,19 +677,6 @@ struct cgroup_subsys_state *css_parent(struct cgroup_subsys_state *css) return &parent_cgrp->dummy_css; } -/** - * cgroup_css - obtain a cgroup's css for the specified subsystem - * @cgrp: the cgroup of interest - * @subsys_id: the subsystem of interest - * - * Return @cgrp's css (cgroup_subsys_state) associated with @subsys_id. - */ -static inline struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp, - int subsys_id) -{ - return cgrp->subsys[subsys_id]; -} - /** * task_css_set_check - obtain a task's css_set with extra access conditions * @task: the task to obtain css_set for -- cgit v1.2.3 From bd8815a6d802fc16a7a106e170593aa05dc17e72 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:27 -0400 Subject: cgroup: make css_for_each_descendant() and friends include the origin css in the iteration Previously, all css descendant iterators didn't include the origin (root of subtree) css in the iteration. The reasons were maintaining consistency with css_for_each_child() and that at the time of introduction more use cases needed skipping the origin anyway; however, given that css_is_descendant() considers self to be a descendant, omitting the origin css has become more confusing and looking at the accumulated use cases rather clearly indicates that including origin would result in simpler code overall. While this is a change which can easily lead to subtle bugs, cgroup API including the iterators has recently gone through major restructuring and no out-of-tree changes will be applicable without adjustments making this a relatively acceptable opportunity for this type of change. The conversions are mostly straight-forward. If the iteration block had explicit origin handling before or after, it's moved inside the iteration. If not, if (pos == origin) continue; is added. Some conversions add extra reference get/put around origin handling by consolidating origin handling and the rest. While the extra ref operations aren't strictly necessary, this shouldn't cause any noticeable difference. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Vivek Goyal Acked-by: Aristeu Rozanski Acked-by: Michal Hocko Cc: Jens Axboe Cc: Matt Helsley Cc: Johannes Weiner Cc: Balbir Singh --- include/linux/cgroup.h | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index c40e508d54e9..8ec5b0f38292 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -798,7 +798,8 @@ css_rightmost_descendant(struct cgroup_subsys_state *pos); * @pos: the css * to use as the loop cursor * @root: css whose descendants to walk * - * Walk @root's descendants. Must be called under rcu_read_lock(). A + * Walk @root's descendants. @root is included in the iteration and the + * first node to be visited. Must be called under rcu_read_lock(). A * descendant css which hasn't finished ->css_online() or already has * finished ->css_offline() may show up during traversal and it's each * subsystem's responsibility to verify that each @pos is alive. @@ -820,13 +821,12 @@ css_rightmost_descendant(struct cgroup_subsys_state *pos); * * my_update_state(@css) * { - * Lock @css; - * Update @css's state; - * Unlock @css; - * * css_for_each_descendant_pre(@pos, @css) { * Lock @pos; - * Verify @pos is alive and inherit state from @pos's parent; + * if (@pos == @css) + * Update @css's state; + * else + * Verify @pos is alive and inherit state from its parent; * Unlock @pos; * } * } @@ -864,8 +864,9 @@ css_next_descendant_post(struct cgroup_subsys_state *pos, * @css: css whose descendants to walk * * Similar to css_for_each_descendant_pre() but performs post-order - * traversal instead. Note that the walk visibility guarantee described in - * pre-order walk doesn't apply the same to post-order walks. + * traversal instead. @root is included in the iteration and the last + * node to be visited. Note that the walk visibility guarantee described + * in pre-order walk doesn't apply the same to post-order walks. */ #define css_for_each_descendant_post(pos, css) \ for ((pos) = css_next_descendant_post(NULL, (css)); (pos); \ -- cgit v1.2.3 From 3fa4d7344be0afebd80382ffeea6b1787cccf971 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 26 Jul 2013 12:16:42 +0200 Subject: usb: phy: rename nop_usb_xceiv => usb_phy_gen_xceiv The "nop" driver isn't a do-nothing-stub but supports a couple functions like clock on/off or is able to use a voltage regulator. This patch simply renames the driver to "generic" since it is easy possible to extend it by a simple function istead of writing a complete driver. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Felipe Balbi --- include/linux/usb/nop-usb-xceiv.h | 29 ----------------------------- include/linux/usb/usb_phy_gen_xceiv.h | 29 +++++++++++++++++++++++++++++ 2 files changed, 29 insertions(+), 29 deletions(-) delete mode 100644 include/linux/usb/nop-usb-xceiv.h create mode 100644 include/linux/usb/usb_phy_gen_xceiv.h (limited to 'include/linux') diff --git a/include/linux/usb/nop-usb-xceiv.h b/include/linux/usb/nop-usb-xceiv.h deleted file mode 100644 index 148d35171aac..000000000000 --- a/include/linux/usb/nop-usb-xceiv.h +++ /dev/null @@ -1,29 +0,0 @@ -#ifndef __LINUX_USB_NOP_XCEIV_H -#define __LINUX_USB_NOP_XCEIV_H - -#include - -struct nop_usb_xceiv_platform_data { - enum usb_phy_type type; - unsigned long clk_rate; - - /* if set fails with -EPROBE_DEFER if can't get regulator */ - unsigned int needs_vcc:1; - unsigned int needs_reset:1; -}; - -#if defined(CONFIG_NOP_USB_XCEIV) || (defined(CONFIG_NOP_USB_XCEIV_MODULE) && defined(MODULE)) -/* sometimes transceivers are accessed only through e.g. ULPI */ -extern void usb_nop_xceiv_register(void); -extern void usb_nop_xceiv_unregister(void); -#else -static inline void usb_nop_xceiv_register(void) -{ -} - -static inline void usb_nop_xceiv_unregister(void) -{ -} -#endif - -#endif /* __LINUX_USB_NOP_XCEIV_H */ diff --git a/include/linux/usb/usb_phy_gen_xceiv.h b/include/linux/usb/usb_phy_gen_xceiv.h new file mode 100644 index 000000000000..f9a7e7bc925b --- /dev/null +++ b/include/linux/usb/usb_phy_gen_xceiv.h @@ -0,0 +1,29 @@ +#ifndef __LINUX_USB_NOP_XCEIV_H +#define __LINUX_USB_NOP_XCEIV_H + +#include + +struct usb_phy_gen_xceiv_platform_data { + enum usb_phy_type type; + unsigned long clk_rate; + + /* if set fails with -EPROBE_DEFER if can't get regulator */ + unsigned int needs_vcc:1; + unsigned int needs_reset:1; +}; + +#if IS_ENABLED(CONFIG_NOP_USB_XCEIV) +/* sometimes transceivers are accessed only through e.g. ULPI */ +extern void usb_nop_xceiv_register(void); +extern void usb_nop_xceiv_unregister(void); +#else +static inline void usb_nop_xceiv_register(void) +{ +} + +static inline void usb_nop_xceiv_unregister(void) +{ +} +#endif + +#endif /* __LINUX_USB_NOP_XCEIV_H */ -- cgit v1.2.3 From 86f8973c1053cb03e1b1b45989a4e144e05b1735 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Thu, 8 Aug 2013 16:09:50 +0200 Subject: spi: new controller driver for efm32 SoCs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Uwe Kleine-König Signed-off-by: Mark Brown --- include/linux/platform_data/efm32-spi.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) create mode 100644 include/linux/platform_data/efm32-spi.h (limited to 'include/linux') diff --git a/include/linux/platform_data/efm32-spi.h b/include/linux/platform_data/efm32-spi.h new file mode 100644 index 000000000000..31b19ca1d73a --- /dev/null +++ b/include/linux/platform_data/efm32-spi.h @@ -0,0 +1,14 @@ +#ifndef __LINUX_PLATFORM_DATA_EFM32_SPI_H__ +#define __LINUX_PLATFORM_DATA_EFM32_SPI_H__ + +#include + +/** + * struct efm32_spi_pdata + * @location: pinmux location for the I/O pins (to be written to the ROUTE + * register) + */ +struct efm32_spi_pdata { + u8 location; +}; +#endif /* ifndef __LINUX_PLATFORM_DATA_EFM32_SPI_H__ */ -- cgit v1.2.3 From 64e8674fbe6bc848333a9b7e19f8cc019dde9eab Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Thu, 8 Aug 2013 14:09:24 -0600 Subject: PCI: Add pci_reset_bridge_secondary_bus() Move the secondary bus reset code from pci_parent_bus_reset() into its own function. Export it as we'll later be calling it from hotplug controllers and elsewhere. Signed-off-by: Alex Williamson 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 0fd1f1582fa1..35c1bc4909f3 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -924,6 +924,7 @@ int pcie_set_mps(struct pci_dev *dev, int mps); int __pci_reset_function(struct pci_dev *dev); int __pci_reset_function_locked(struct pci_dev *dev); int pci_reset_function(struct pci_dev *dev); +void pci_reset_bridge_secondary_bus(struct pci_dev *dev); void pci_update_resource(struct pci_dev *dev, int resno); int __must_check pci_assign_resource(struct pci_dev *dev, int i); int __must_check pci_reassign_resource(struct pci_dev *dev, int i, resource_size_t add_size, resource_size_t align); -- cgit v1.2.3 From c88a1f8b96e7384627b918dfabbfc0c615a4a914 Mon Sep 17 00:00:00 2001 From: Lukasz Majewski Date: Tue, 6 Aug 2013 22:53:08 +0530 Subject: cpufreq: Store cpufreq policies in a list Policies available in the cpufreq framework are now linked together. They are accessible via cpufreq_policy_list defined in the cpufreq core. [rjw: Fix from Yinghai Lu folded in] Signed-off-by: Lukasz Majewski Signed-off-by: Myungjoo Ham Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 29208923c9d3..431a05d4b4c9 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -82,6 +82,7 @@ struct cpufreq_policy { struct cpufreq_real_policy user_policy; + struct list_head policy_list; struct kobject kobj; struct completion kobj_unregister; int transition_ongoing; /* Tracks transition status */ -- cgit v1.2.3 From adc97d6a735dbb1e94cb4f1bf0b55f258b349941 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 6 Aug 2013 22:53:12 +0530 Subject: cpufreq: Drop the owner field from struct cpufreq_driver We don't need to set .owner = THIS_MODULE any more in cpufreq drivers as this field isn't used any more by the cpufreq core. This patch removes it and updates all dependent drivers accordingly. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 431a05d4b4c9..d568f3975eeb 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -179,7 +179,6 @@ __ATTR(_name, 0644, show_##_name, store_##_name) struct cpufreq_driver { - struct module *owner; char name[CPUFREQ_NAME_LEN]; u8 flags; /* -- cgit v1.2.3 From 77409d9bcc0ee3fc309a3d6fd18553f6ec5a9aa6 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Mon, 12 Aug 2013 14:21:14 +0530 Subject: regulator: palmas: model SMPS10 as two regulators SMPS10 has two outputs OUT1 and OUT2 and have one input IN1. SMPS10-OUT2 is connected to SMPS10-IN1 and can be configured either in BOOST mode or BYPASS mode. regulator_enable of SMPS10-OUT2 configures it in BOOST mode. For BYPASS mode regulator_allow_bypass() API can be used. SMPS10-OUT1 is connected to SMPS10-OUT2 and can be enabled using regulator_enable(). [ axel.lin@ingics.com : Simplify regulator_desc setting for SMPS10_[OUT1|OUT2] Signed-off-by: J Keerthy Signed-off-by: Laxman Dewangan Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Axel Lin Signed-off-by: Mark Brown --- include/linux/mfd/palmas.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index 1a8dd7afe084..c06d78af3342 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -160,7 +160,8 @@ enum palmas_regulators { PALMAS_REG_SMPS7, PALMAS_REG_SMPS8, PALMAS_REG_SMPS9, - PALMAS_REG_SMPS10, + PALMAS_REG_SMPS10_OUT2, + PALMAS_REG_SMPS10_OUT1, /* LDO regulators */ PALMAS_REG_LDO1, PALMAS_REG_LDO2, @@ -355,9 +356,9 @@ struct palmas_pmic { int smps123; int smps457; - int range[PALMAS_REG_SMPS10]; - unsigned int ramp_delay[PALMAS_REG_SMPS10]; - unsigned int current_reg_mode[PALMAS_REG_SMPS10]; + int range[PALMAS_REG_SMPS10_OUT1]; + unsigned int ramp_delay[PALMAS_REG_SMPS10_OUT1]; + unsigned int current_reg_mode[PALMAS_REG_SMPS10_OUT1]; }; struct palmas_resource { -- cgit v1.2.3 From 5c19e95216b93b0d29c6a4887e69a980edc6fc81 Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Mon, 5 Aug 2013 14:40:44 +0200 Subject: OF: Add helper for matching against linux,stdout-path devicetrees may have a linux,stdout-path property in the chosen node describing the console device. This adds a helper function to match a device against this property so a driver can call add_preferred_console for a matching device. Signed-off-by: Sascha Hauer Acked-by: Rob Herring Signed-off-by: Greg Kroah-Hartman --- include/linux/of.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 1fd08ca23106..429e16801858 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -343,6 +343,8 @@ const char *of_prop_next_string(struct property *prop, const char *cur); s; \ s = of_prop_next_string(prop, s)) +int of_device_is_stdout_path(struct device_node *dn); + #else /* CONFIG_OF */ static inline const char* of_node_full_name(struct device_node *np) @@ -505,6 +507,11 @@ static inline int of_machine_is_compatible(const char *compat) return 0; } +static inline int of_device_is_stdout_path(struct device_node *dn) +{ + return 0; +} + #define of_match_ptr(_ptr) NULL #define of_match_node(_matches, _node) NULL #define of_property_for_each_u32(np, propname, prop, p, u) \ -- cgit v1.2.3 From 3e635202ce40e4d7ff3fafc18db70c5d28cc6622 Mon Sep 17 00:00:00 2001 From: Tuomas Tynkkynen Date: Mon, 12 Aug 2013 16:06:51 +0300 Subject: usb: phy: tegra: Tegra30 support The Tegra30 USB PHY is a bit different than the Tegra20 PHY: - The EHCI controller supports the HOSTPC register extension, and some of the fields that the PHY needs to modify (PHCD and PTS) have moved to the new HOSTPC register. - Some of the UTMI PLL configuration registers have moved from the USB register space to the Clock-And-Reset controller space. In Tegra30 the clock driver is responsible for configuring the UTMI PLL. - The USBMODE register must be explicitly written to enter host mode. - Certain PHY parameters need to be programmed for optimal signal quality. Support for this will be added in the next patch. The new tegra_phy_soc_config structure is added to describe the differences between the SoCs. Signed-off-by: Tuomas Tynkkynen Tested-by: Stephen Warren Reviewed-by: Stephen Warren Signed-off-by: Felipe Balbi --- include/linux/usb/tegra_usb_phy.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index d3db274610a1..d3a63c354db9 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -18,6 +18,24 @@ #include #include +/* + * utmi_pll_config_in_car_module: true if the UTMI PLL configuration registers + * should be set up by clk-tegra, false if by the PHY code + * has_hostpc: true if the USB controller has the HOSTPC extension, which + * changes the location of the PHCD and PTS fields + * requires_usbmode_setup: true if the USBMODE register needs to be set to + * enter host mode + * requires_extra_tuning_parameters: true if xcvr_hsslew, hssquelch_level + * and hsdiscon_level should be set for adequate signal quality + */ + +struct tegra_phy_soc_config { + bool utmi_pll_config_in_car_module; + bool has_hostpc; + bool requires_usbmode_setup; + bool requires_extra_tuning_parameters; +}; + struct tegra_utmip_config { u8 hssync_start_delay; u8 elastic_limit; @@ -47,6 +65,7 @@ struct tegra_usb_phy { struct regulator *vbus; enum usb_dr_mode mode; void *config; + const struct tegra_phy_soc_config *soc_config; struct usb_phy *ulpi; struct usb_phy u_phy; bool is_legacy_phy; -- cgit v1.2.3 From e497a24d8e18af510879b2ae059ee20a4a58eae8 Mon Sep 17 00:00:00 2001 From: Tuomas Tynkkynen Date: Mon, 12 Aug 2013 16:06:53 +0300 Subject: usb: phy: tegra: Program new PHY parameters The Tegra30 TRM recommends configuration of certain PHY parameters for optimal quality. Program the following registers based on device tree parameters: - UTMIP_XCVR_HSSLEW: HS slew rate control. - UTMIP_HSSQUELCH_LEVEL: HS squelch detector level - UTMIP_HSDISCON_LEVEL: HS disconnect detector level. These registers exist in Tegra20, but programming them hasn't been necessary, so these parameters won't be set on Tegra20 to keep the device trees backward compatible. Additionally, the UTMIP_XCVR_SETUP parameter can be set from fuses instead of a software-programmed value, as the optimal value can vary between invidual boards. The boolean property nvidia,xcvr-setup-use-fuses can be used to enable this behaviour. Signed-off-by: Tuomas Tynkkynen Tested-by: Stephen Warren Reviewed-by: Stephen Warren Signed-off-by: Felipe Balbi --- include/linux/usb/tegra_usb_phy.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index d3a63c354db9..1de16c324ec8 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -41,9 +41,13 @@ struct tegra_utmip_config { u8 elastic_limit; u8 idle_wait_delay; u8 term_range_adj; + bool xcvr_setup_use_fuses; u8 xcvr_setup; u8 xcvr_lsfslew; u8 xcvr_lsrslew; + u8 xcvr_hsslew; + u8 hssquelch_level; + u8 hsdiscon_level; }; enum tegra_usb_phy_port_speed { -- cgit v1.2.3 From 94dfd7edfd5c9b605caf7b562de7a813d216e011 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Wed, 3 Jul 2013 22:53:07 +0800 Subject: USB: HCD: support giveback of URB in tasklet context This patch implements the mechanism of giveback of URB in tasklet context, so that hardware interrupt handling time for usb host controller can be saved much, and HCD interrupt handling can be simplified. Motivations: 1), on some arch(such as ARM), DMA mapping/unmapping is a bit time-consuming, for example: when accessing usb mass storage via EHCI on pandaboard, the common length of transfer buffer is 120KB, the time consumed on DMA unmapping may reach hundreds of microseconds; even on A15 based box, the time is still about scores of microseconds 2), on some arch, reading DMA coherent memoery is very time-consuming, the most common example is usb video class driver[1] 3), driver's complete() callback may do much things which is driver specific, so the time is consumed unnecessarily in hardware irq context. 4), running driver's complete() callback in hardware irq context causes that host controller driver has to release its lock in interrupt handler, so reacquiring the lock after return may busy wait a while and increase interrupt handling time. More seriously, releasing the HCD lock makes HCD becoming quite complicated to deal with introduced races. So the patch proposes to run giveback of URB in tasklet context, then time consumed in HCD irq handling doesn't depend on drivers' complete and DMA mapping/unmapping any more, also we can simplify HCD since the HCD lock isn't needed to be released during irq handling. The patch should be reasonable and doable: 1), for drivers, they don't care if the complete() is called in hard irq context or softirq context 2), the biggest change is the situation in which usb_submit_urb() is called in complete() callback, so the introduced tasklet schedule delay might be a con, but it shouldn't be a big deal: - control/bulk asynchronous transfer isn't sensitive to schedule delay - the patch schedules giveback of periodic URBs using tasklet_hi_schedule, so the introduced delay should be very small - for ISOC transfer, generally, drivers submit several URBs concurrently to avoid interrupt delay, so it is OK with the little schedule delay. - for interrupt transfer, generally, drivers only submit one URB at the same time, but interrupt transfer is often used in event report, polling, ... situations, and a little delay should be OK. Considered that HCDs may optimize on submitting URB in complete(), the patch may cause the optimization not working, so introduces one flag to mark if the HCD supports to run giveback URB in tasklet context. When all HCDs are ready, the flag can be removed. [1], http://marc.info/?t=136438111600010&r=1&w=2 Cc: Oliver Neukum Acked-by: Alan Stern Signed-off-by: Ming Lei Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 1e88377e22f4..a9c7d44bd2ed 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -22,6 +22,7 @@ #ifdef __KERNEL__ #include +#include #define MAX_TOPO_LEVEL 6 @@ -67,6 +68,13 @@ /*-------------------------------------------------------------------------*/ +struct giveback_urb_bh { + bool running; + spinlock_t lock; + struct list_head head; + struct tasklet_struct bh; +}; + struct usb_hcd { /* @@ -139,6 +147,9 @@ struct usb_hcd { resource_size_t rsrc_len; /* memory/io resource length */ unsigned power_budget; /* in mA, 0 = no limit */ + struct giveback_urb_bh high_prio_bh; + struct giveback_urb_bh low_prio_bh; + /* bandwidth_mutex should be taken before adding or removing * any new bus bandwidth constraints: * 1. Before adding a configuration for a new device. @@ -221,6 +232,7 @@ struct hc_driver { #define HCD_USB25 0x0030 /* Wireless USB 1.0 (USB 2.5)*/ #define HCD_USB3 0x0040 /* USB 3.0 */ #define HCD_MASK 0x0070 +#define HCD_BH 0x0100 /* URB complete in BH context */ /* called to init HCD and root hub */ int (*reset) (struct usb_hcd *hcd); @@ -361,6 +373,11 @@ struct hc_driver { int (*find_raw_port_number)(struct usb_hcd *, int); }; +static inline int hcd_giveback_urb_in_bh(struct usb_hcd *hcd) +{ + return hcd->driver->flags & HCD_BH; +} + extern int usb_hcd_link_urb_to_ep(struct usb_hcd *hcd, struct urb *urb); extern int usb_hcd_check_unlink_urb(struct usb_hcd *hcd, struct urb *urb, int status); -- cgit v1.2.3 From bcc48f1a7a0d40ae2e5a26aff72c2b674fd8b596 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 8 Aug 2013 21:48:22 +0800 Subject: USB: introduce usb_device_no_sg_constraint() helper Some host controllers(such as xHCI) can support building packet from discontinuous buffers, so introduce one flag and helper for this kind of host controllers, then the feature can help some applications(such as usbnet) by supporting arbitrary length of sg buffers. Acked-by: Alan Stern Signed-off-by: Ming Lei Reviewed-by: Eric Dumazet Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index acb1b0aa77d8..001629cd1a97 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -337,6 +337,7 @@ struct usb_bus { * the ep queue on a short transfer * with the URB_SHORT_NOT_OK flag set. */ + unsigned no_sg_constraint:1; /* no sg constraint */ unsigned sg_tablesize; /* 0 or largest number of sg list entries */ int devnum_next; /* Next open device number in @@ -684,6 +685,11 @@ static inline bool usb_device_supports_ltm(struct usb_device *udev) return udev->bos->ss_cap->bmAttributes & USB_LTM_SUPPORT; } +static inline bool usb_device_no_sg_constraint(struct usb_device *udev) +{ + return udev && udev->bus && udev->bus->no_sg_constraint; +} + /*-------------------------------------------------------------------------*/ @@ -1253,7 +1259,7 @@ typedef void (*usb_complete_t)(struct urb *); * transfer_buffer. * @sg: scatter gather buffer list, the buffer size of each element in * the list (except the last) must be divisible by the endpoint's - * max packet size + * max packet size if no_sg_constraint isn't set in 'struct usb_bus' * @num_mapped_sgs: (internal) number of mapped sg entries * @num_sgs: number of entries in the sg list * @transfer_buffer_length: How big is transfer_buffer. The transfer may -- cgit v1.2.3 From 638c5115a794981441246fa8fa5d95c1875af5ba Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 8 Aug 2013 21:48:24 +0800 Subject: USBNET: support DMA SG This patch introduces support of DMA SG if the USB host controller which usbnet device is attached to is capable of building packet from discontinuous buffers. The patch supports passing the skb fragment buffers to usb stack directly via urb->sg. Cc: Ben Hutchings Cc: Grant Grundler Cc: Freddy Xin Cc: Alan Stern Acked-by: Oliver Neukum Signed-off-by: Ming Lei Reviewed-by: Eric Dumazet Acked-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/usbnet.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index f18d64129f99..2b47e6364e36 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -34,6 +34,7 @@ struct usbnet { struct mutex phy_mutex; unsigned char suspend_count; unsigned char pkt_cnt, pkt_err; + unsigned can_dma_sg:1; /* i/o info: pipes etc */ unsigned in, out; -- cgit v1.2.3 From 3775a209d38aa3a0c7ed89a7d0f529e0230f280e Mon Sep 17 00:00:00 2001 From: Casey Leedom Date: Tue, 6 Aug 2013 15:48:36 +0530 Subject: PCI: Add pci_wait_for_pending_transaction() New routine to avoid duplication of code to wait for pending PCI transactions to complete. Signed-off-by: Casey Leedom Signed-off-by: Vipul Pandya 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 0fd1f1582fa1..e6470016c718 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -914,6 +914,7 @@ bool pci_check_and_unmask_intx(struct pci_dev *dev); void pci_msi_off(struct pci_dev *dev); int pci_set_dma_max_seg_size(struct pci_dev *dev, unsigned int size); int pci_set_dma_seg_boundary(struct pci_dev *dev, unsigned long mask); +int pci_wait_for_pending_transaction(struct pci_dev *dev); int pcix_get_max_mmrbc(struct pci_dev *dev); int pcix_get_mmrbc(struct pci_dev *dev); int pcix_set_mmrbc(struct pci_dev *dev, int mmrbc); -- cgit v1.2.3 From fa6fdb33b486a8afc5439c504da8d581e142c77d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 8 Aug 2013 15:22:55 -0700 Subject: driver core: bus_type: add dev_groups attribute groups are much more flexible than just a list of attributes, due to their support for visibility of the attributes, and binary attributes. Add dev_groups to struct bus_type which should be used instead of dev_attrs. dev_attrs will be removed from the structure soon. Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 22b546a58591..3aec4a68b1d4 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -66,6 +66,7 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *); * @bus_attrs: Default attributes of the bus. * @dev_attrs: Default attributes of the devices on the bus. * @drv_attrs: Default attributes of the device drivers on the bus. + * @dev_groups: Default attributes of the devices on the bus. * @match: Called, perhaps multiple times, whenever a new device or driver * is added for this bus. It should return a nonzero value if the * given device can be handled by the given driver. @@ -104,8 +105,9 @@ struct bus_type { const char *dev_name; struct device *dev_root; struct bus_attribute *bus_attrs; - struct device_attribute *dev_attrs; + struct device_attribute *dev_attrs; /* use dev_groups instead */ struct driver_attribute *drv_attrs; + const struct attribute_group **dev_groups; int (*match)(struct device *dev, struct device_driver *drv); int (*uevent)(struct device *dev, struct kobj_uevent_env *env); -- cgit v1.2.3 From ed0617b5c0bcd7fd04053568aa0cc19a977a1f26 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 8 Aug 2013 15:22:56 -0700 Subject: driver core: bus_type: add drv_groups attribute groups are much more flexible than just a list of attributes, due to their support for visibility of the attributes, and binary attributes. Add drv_groups to struct bus_type which should be used instead of drv_attrs. drv_attrs will be removed from the structure soon. Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 3aec4a68b1d4..94d987f128bb 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -67,6 +67,7 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *); * @dev_attrs: Default attributes of the devices on the bus. * @drv_attrs: Default attributes of the device drivers on the bus. * @dev_groups: Default attributes of the devices on the bus. + * @drv_groups: Default attributes of the device drivers on the bus. * @match: Called, perhaps multiple times, whenever a new device or driver * is added for this bus. It should return a nonzero value if the * given device can be handled by the given driver. @@ -106,8 +107,9 @@ struct bus_type { struct device *dev_root; struct bus_attribute *bus_attrs; struct device_attribute *dev_attrs; /* use dev_groups instead */ - struct driver_attribute *drv_attrs; + struct driver_attribute *drv_attrs; /* use drv_groups instead */ const struct attribute_group **dev_groups; + const struct attribute_group **drv_groups; int (*match)(struct device *dev, struct device_driver *drv); int (*uevent)(struct device *dev, struct kobj_uevent_env *env); -- cgit v1.2.3 From 12478ba077adf8b53be6101b80dd8a65e4df9ea6 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 8 Aug 2013 15:22:57 -0700 Subject: driver core: bus_type: add bus_groups attribute groups are much more flexible than just a list of attributes, due to their support for visibility of the attributes, and binary attributes. Add bus_groups to struct bus_type which should be used instead of bus_attrs. bus_attrs will be removed from the structure soon. Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 94d987f128bb..26e23b22ed0a 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -66,6 +66,7 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *); * @bus_attrs: Default attributes of the bus. * @dev_attrs: Default attributes of the devices on the bus. * @drv_attrs: Default attributes of the device drivers on the bus. + * @bus_groups: Default attributes of the bus. * @dev_groups: Default attributes of the devices on the bus. * @drv_groups: Default attributes of the device drivers on the bus. * @match: Called, perhaps multiple times, whenever a new device or driver @@ -105,9 +106,10 @@ struct bus_type { const char *name; const char *dev_name; struct device *dev_root; - struct bus_attribute *bus_attrs; + struct bus_attribute *bus_attrs; /* use bus_groups instead */ struct device_attribute *dev_attrs; /* use dev_groups instead */ struct driver_attribute *drv_attrs; /* use drv_groups instead */ + const struct attribute_group **bus_groups; const struct attribute_group **dev_groups; const struct attribute_group **drv_groups; -- cgit v1.2.3 From 2d854e5738cded368a0759f85b1197f5c044513d Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 12 Jul 2013 19:02:30 +0200 Subject: context_tracing: Fix guest accounting with native vtime 1) If context tracking is enabled with native vtime accounting (which combo is useless except for dev testing), we call vtime_guest_enter() and vtime_guest_exit() on host <-> guest switches. But those are stubs in this configurations. As a result, cputime is not correctly flushed on kvm context switches. 2) If context tracking runs but is disabled on some CPUs, those CPUs end up calling __guest_enter/__guest_exit which in turn call vtime_account_system(). We don't want to call this because we run in tick based accounting for these CPUs. Refactor the guest_enter/guest_exit code such that all combinations finally work. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/context_tracking.h | 52 +++++++++++++++++----------------------- 1 file changed, 22 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index fc09d7b0dacf..5984f2556d13 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -20,25 +20,6 @@ struct context_tracking { } state; }; -static inline void __guest_enter(void) -{ - /* - * This is running in ioctl context so we can avoid - * the call to vtime_account() with its unnecessary idle check. - */ - vtime_account_system(current); - current->flags |= PF_VCPU; -} - -static inline void __guest_exit(void) -{ - /* - * This is running in ioctl context so we can avoid - * the call to vtime_account() with its unnecessary idle check. - */ - vtime_account_system(current); - current->flags &= ~PF_VCPU; -} #ifdef CONFIG_CONTEXT_TRACKING DECLARE_PER_CPU(struct context_tracking, context_tracking); @@ -56,9 +37,6 @@ static inline bool context_tracking_active(void) extern void user_enter(void); extern void user_exit(void); -extern void guest_enter(void); -extern void guest_exit(void); - static inline enum ctx_state exception_enter(void) { enum ctx_state prev_ctx; @@ -81,21 +59,35 @@ extern void context_tracking_task_switch(struct task_struct *prev, static inline bool context_tracking_in_user(void) { return false; } static inline void user_enter(void) { } static inline void user_exit(void) { } +static inline enum ctx_state exception_enter(void) { return 0; } +static inline void exception_exit(enum ctx_state prev_ctx) { } +static inline void context_tracking_task_switch(struct task_struct *prev, + struct task_struct *next) { } +#endif /* !CONFIG_CONTEXT_TRACKING */ +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +extern void guest_enter(void); +extern void guest_exit(void); +#else static inline void guest_enter(void) { - __guest_enter(); + /* + * This is running in ioctl context so we can avoid + * the call to vtime_account() with its unnecessary idle check. + */ + vtime_account_system(current); + current->flags |= PF_VCPU; } static inline void guest_exit(void) { - __guest_exit(); + /* + * This is running in ioctl context so we can avoid + * the call to vtime_account() with its unnecessary idle check. + */ + vtime_account_system(current); + current->flags &= ~PF_VCPU; } - -static inline enum ctx_state exception_enter(void) { return 0; } -static inline void exception_exit(enum ctx_state prev_ctx) { } -static inline void context_tracking_task_switch(struct task_struct *prev, - struct task_struct *next) { } -#endif /* !CONFIG_CONTEXT_TRACKING */ +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ #endif -- cgit v1.2.3 From 5b206d48e58204e84d249c4eb18651a1ff7a1274 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 12 Jul 2013 19:05:14 +0200 Subject: vtime: Update a few comments Update a stale comment from the old vtime era and document some locking that might be non obvious. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/context_tracking.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 5984f2556d13..d883ff0dd8fc 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -72,8 +72,9 @@ extern void guest_exit(void); static inline void guest_enter(void) { /* - * This is running in ioctl context so we can avoid - * the call to vtime_account() with its unnecessary idle check. + * This is running in ioctl context so its safe + * to assume that it's the stime pending cputime + * to flush. */ vtime_account_system(current); current->flags |= PF_VCPU; @@ -81,10 +82,7 @@ static inline void guest_enter(void) static inline void guest_exit(void) { - /* - * This is running in ioctl context so we can avoid - * the call to vtime_account() with its unnecessary idle check. - */ + /* Flush the guest cputime we spent on the guest */ vtime_account_system(current); current->flags &= ~PF_VCPU; } -- cgit v1.2.3 From 2e70933866ace52091a3c11a5c104c063ab0c445 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 10 Jul 2013 00:55:25 +0200 Subject: nohz: Only enable context tracking on full dynticks CPUs The context tracking subsystem has the ability to selectively enable the tracking on any defined subset of CPU. This means that we can define a CPU range that doesn't run the context tracking and another range that does. Now what we want in practice is to enable the tracking on full dynticks CPUs only. In order to perform this, we just need to pass our full dynticks CPU range selection from the full dynticks subsystem to the context tracking. This way we can spare the overhead of RCU user extended quiescent state and vtime maintainance on the CPUs that are outside the full dynticks range. Just keep in mind the raw context tracking itself is still necessary everywhere. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/context_tracking.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index d883ff0dd8fc..1ae37c708c63 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -34,6 +34,8 @@ static inline bool context_tracking_active(void) return __this_cpu_read(context_tracking.active); } +extern void context_tracking_cpu_set(int cpu); + extern void user_enter(void); extern void user_exit(void); -- cgit v1.2.3 From b9d10be7a8e88fdcb12540387c219cdde87b0795 Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Mon, 12 Aug 2013 09:45:53 -0600 Subject: ACPI / processor: Acquire writer lock to update CPU maps CPU system maps are protected with reader/writer locks. The reader lock, get_online_cpus(), assures that the maps are not updated while holding the lock. The writer lock, cpu_hotplug_begin(), is used to udpate the cpu maps along with cpu_maps_update_begin(). However, the ACPI processor handler updates the cpu maps without holding the the writer lock. acpi_map_lsapic() is called from acpi_processor_hotadd_init() to update cpu_possible_mask and cpu_present_mask. acpi_unmap_lsapic() is called from acpi_processor_remove() to update cpu_possible_mask. Currently, they are either unprotected or protected with the reader lock, which is not correct. For example, the get_online_cpus() below is supposed to assure that cpu_possible_mask is not changed while the code is iterating with for_each_possible_cpu(). get_online_cpus(); for_each_possible_cpu(cpu) { : } put_online_cpus(); However, this lock has no protection with CPU hotplug since the ACPI processor handler does not use the writer lock when it updates cpu_possible_mask. The reader lock does not serialize within the readers. This patch protects them with the writer lock with cpu_hotplug_begin() along with cpu_maps_update_begin(), which must be held before calling cpu_hotplug_begin(). It also protects arch_register_cpu() / arch_unregister_cpu(), which creates / deletes a sysfs cpu device interface. For this purpose it changes cpu_hotplug_begin() and cpu_hotplug_done() to global and exports them in cpu.h. Signed-off-by: Toshi Kani Signed-off-by: Rafael J. Wysocki --- include/linux/cpu.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index ab0eade73039..956c0a16566f 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -172,6 +172,8 @@ extern struct bus_type cpu_subsys; #ifdef CONFIG_HOTPLUG_CPU /* Stop CPUs going up and down. */ +extern void cpu_hotplug_begin(void); +extern void cpu_hotplug_done(void); extern void get_online_cpus(void); extern void put_online_cpus(void); extern void cpu_hotplug_disable(void); @@ -197,6 +199,8 @@ static inline void cpu_hotplug_driver_unlock(void) #else /* CONFIG_HOTPLUG_CPU */ +static inline void cpu_hotplug_begin(void) {} +static inline void cpu_hotplug_done(void) {} #define get_online_cpus() do { } while (0) #define put_online_cpus() do { } while (0) #define cpu_hotplug_disable() do { } while (0) -- cgit v1.2.3 From 35ef10da65d43211f4cd7e7822cbb3becdfc0ae1 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 13 Aug 2013 11:01:54 -0400 Subject: cgroup: rename cgroup_subsys_state->dput_work and its callback function css (cgroup_subsys_state) will become RCU protected and there will be two stages which require punting to work item during release. To prepare for using the work item for multiple times, rename css->dput_work to css->destroy_work and css_dput_fn() to css_free_work_fn() and move work item initialization from css init to right before the actual usage. This reorganization doesn't introduce any behavior change. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 8ec5b0f38292..12d66fee26f8 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -80,7 +80,7 @@ struct cgroup_subsys_state { struct css_id __rcu *id; /* Used to put @cgroup->dentry on the last css_put() */ - struct work_struct dput_work; + struct work_struct destroy_work; }; /* bits in struct cgroup_subsys_state flags field */ -- cgit v1.2.3 From 0ae78e0bf10ac38ab53548e18383afc9997eca22 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 13 Aug 2013 11:01:54 -0400 Subject: cgroup: add cgroup_subsys_state->parent With the planned unified hierarchy, css's (cgroup_subsys_state) will be RCU protected and allowed to be attached and detached dynamically over the course of a cgroup's lifetime. This means that css's will stay accessible after being detached from its cgroup - the matching pointer in cgroup->subsys[] cleared - for ref draining and RCU grace period. cgroup core still wants to guarantee that the parent css is never destroyed before its children and css_parent() always returns the parent regardless of the state of the child css as long as it's accessible. This patch makes css's hold onto their parents and adds css->parent so that the parent css is never detroyed before its children and can be determined without consulting the cgroups. cgroup->dummy_css is also updated to point to the parent dummy_css; however, it doesn't need to worry about object lifetime as the parent cgroup is already pinned by the child. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 12d66fee26f8..8a5dc91fbaad 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -75,6 +75,9 @@ struct cgroup_subsys_state { /* reference count - access via css_[try]get() and css_put() */ struct percpu_ref refcnt; + /* the parent css */ + struct cgroup_subsys_state *parent; + unsigned long flags; /* ID for this css, if possible */ struct css_id __rcu *id; @@ -666,15 +669,7 @@ struct cgroup_subsys { static inline struct cgroup_subsys_state *css_parent(struct cgroup_subsys_state *css) { - struct cgroup *parent_cgrp = css->cgroup->parent; - - if (!parent_cgrp) - return NULL; - - if (css->ss) - return parent_cgrp->subsys[css->ss->subsys_id]; - else - return &parent_cgrp->dummy_css; + return css->parent; } /** -- cgit v1.2.3 From 73e80ed8007fc48a6deeb295ba37159fad274bd2 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 13 Aug 2013 11:01:55 -0400 Subject: cgroup: add __rcu modifier to cgroup->subsys[] For the planned unified hierarchy, each css (cgroup_subsys_state) will be RCU protected so that it can be created and destroyed individually while allowing RCU accesses. Previous changes ensured that all cgroup->subsys[] accesses use the cgroup_css() accessor. This patch adds __rcu modifier to cgroup->subsys[], add matching RCU dereference in cgroup_css() and convert all assignments to either rcu_assign_pointer() or RCU_INIT_POINTER(). This change prepares for the actual RCUfication of css's and doesn't introduce any visible behavior change. The conversion is verified with sparse and all accesses are properly RCU annotated. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 8a5dc91fbaad..eb200b5794e7 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -204,7 +204,7 @@ struct cgroup { struct cgroup_name __rcu *name; /* Private pointers for each registered subsystem */ - struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; + struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT]; struct cgroupfs_root *root; -- cgit v1.2.3 From e0acd0a68ec7dbf6b7a81a87a867ebd7ac9b76c4 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 12 Aug 2013 18:14:00 +0200 Subject: sched: fix the theoretical signal_wake_up() vs schedule() race This is only theoretical, but after try_to_wake_up(p) was changed to check p->state under p->pi_lock the code like __set_current_state(TASK_INTERRUPTIBLE); schedule(); can miss a signal. This is the special case of wait-for-condition, it relies on try_to_wake_up/schedule interaction and thus it does not need mb() between __set_current_state() and if(signal_pending). However, this __set_current_state() can move into the critical section protected by rq->lock, now that try_to_wake_up() takes another lock we need to ensure that it can't be reordered with "if (signal_pending(current))" check inside that section. The patch is actually one-liner, it simply adds smp_wmb() before spin_lock_irq(rq->lock). This is what try_to_wake_up() already does by the same reason. We turn this wmb() into the new helper, smp_mb__before_spinlock(), for better documentation and to allow the architectures to change the default implementation. While at it, kill smp_mb__after_lock(), it has no callers. Perhaps we can also add smp_mb__before/after_spinunlock() for prepare_to_wait(). Signed-off-by: Oleg Nesterov Acked-by: Peter Zijlstra Signed-off-by: Linus Torvalds --- include/linux/spinlock.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 7d537ced949a..75f34949d9ab 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -117,9 +117,17 @@ do { \ #endif /*arch_spin_is_contended*/ #endif -/* The lock does not imply full memory barrier. */ -#ifndef ARCH_HAS_SMP_MB_AFTER_LOCK -static inline void smp_mb__after_lock(void) { smp_mb(); } +/* + * Despite its name it doesn't necessarily has to be a full barrier. + * It should only guarantee that a STORE before the critical section + * can not be reordered with a LOAD inside this section. + * spin_lock() is the one-way barrier, this LOAD can not escape out + * of the region. So the default implementation simply ensures that + * a STORE can not move into the critical section, smp_wmb() should + * serialize it with another STORE done by spin_lock(). + */ +#ifndef smp_mb__before_spinlock +#define smp_mb__before_spinlock() smp_wmb() #endif /** -- cgit v1.2.3 From f20104de55a212a9742d8df1807f1f29dc95b748 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 13 Aug 2013 20:22:50 -0400 Subject: cgroup: replace cgroup->css_kill_cnt with ->nr_css Currently, css (cgroup_subsys_state) lifetime is tied to that of the associated cgroup. With the planned unified hierarchy, css's will be dynamically created and destroyed within the lifetime of a cgroup. To enable such usages, css's will be individually RCU protected instead of being tied to the cgroup. cgroup->css_kill_cnt is used during cgroup destruction to wait for css reference count disable; however, this model doesn't work once css's lifetimes are managed separately from cgroup's. This patch replaces it with cgroup->nr_css which is an cgroup_mutex protected integer counting the number of attached css's. The count is incremented from online_css() and decremented after refcnt kill is confirmed. If the count reaches zero and the cgroup is marked dead, the second stage of cgroup destruction is kicked off. If a cgroup doesn't have any css attached at the time of rmdir, cgroup_destroy_locked() now invokes the second stage directly as no css kill confirmation would happen. cgroup_offline_fn() - the second step of cgroup destruction - is renamed to cgroup_destroy_css_killed() and now expects to be called with cgroup_mutex held. While this patch changes how css destruction is punted to work items, it shouldn't change any visible behavior. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index eb200b5794e7..80dca872f4d4 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -171,6 +171,9 @@ struct cgroup { */ int id; + /* the number of attached css's */ + int nr_css; + /* * We link our 'sibling' struct into our parent's 'children'. * Our children link their 'sibling' into our 'children'. @@ -234,7 +237,6 @@ struct cgroup { /* For css percpu_ref killing and RCU-protected deletion */ struct rcu_head rcu_head; struct work_struct destroy_work; - atomic_t css_kill_cnt; /* List of events which userspace want to receive */ struct list_head event_list; -- cgit v1.2.3 From 09a503ea3a816b285b0b402b7f785eaec0c7a7e1 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 13 Aug 2013 20:22:50 -0400 Subject: cgroup: decouple cgroup_subsys_state destruction from cgroup destruction Currently, css (cgroup_subsys_state) lifetime is tied to that of the associated cgroup. css's are created when the associated cgroup is created and destroyed when it gets destroyed. Also, individual css's aren't RCU protected but the whole cgroup is. With the planned unified hierarchy, css's will need to be dynamically created and destroyed within the lifetime of a cgroup. To enable such usages, this patch decouples css destruction from cgroup destruction - offline_css() invocation and the final css_put() are moved from cgroup_destroy_css_killed() to css_killed_work_fn(). Now each css is individually offlined and put as its reference count is killed instead of waiting for all css's attached to the cgroup to finish refcnt killing and then proceeding to offlining and putting them together. While this changes the order of destruction operations, the changes shouldn't be noticeable to cgroup subsystems or userland. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 80dca872f4d4..71e77e7cdb6f 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -82,7 +82,7 @@ struct cgroup_subsys_state { /* ID for this css, if possible */ struct css_id __rcu *id; - /* Used to put @cgroup->dentry on the last css_put() */ + /* percpu_ref killing and putting dentry on the last css_put() */ struct work_struct destroy_work; }; -- cgit v1.2.3 From 0c21ead136a900c36f1ab74fd7d09a306dc31324 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 13 Aug 2013 20:22:51 -0400 Subject: cgroup: RCU protect each cgroup_subsys_state release With the planned unified hierarchy, individual css's will be created and destroyed dynamically across the lifetime of a cgroup. To enable such usages, css destruction is being decoupled from cgroup destruction. Most of the destruction path has been decoupled but the actual free of css still depends on cgroup free path. When all css refs are drained, css_release() kicks off css_free_work_fn() which puts the cgroup. When the cgroup refcnt reaches zero, cgroup_diput() is invoked which in turn schedules RCU free of the cgroup. After a grace period, all css's are freed along with the cgroup itself. This patch moves the RCU grace period and css freeing from cgroup release path to css release path. css_release(), instead of kicking off css_free_work_fn() directly, schedules RCU callback css_free_rcu_fn() which in turn kicks off css_free_work_fn() after a RCU grace period. css_free_work_fn() is updated to free the css directly. The five-way punting - percpu ref kill confirmation, a work item, percpu ref release, RCU grace period, and again a work item - is quite hairy but the work items are there only to provide process context and the actual sequence is kill confirm -> release -> RCU free, which isn't simple but not too crazy. This removes cgroup_css() usage after offline_css() allowing clearing cgroup->subsys[] from offline_css(), which makes it consistent with online_css() and brings it closer to proper lifetime management for individual css's. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 71e77e7cdb6f..c24bd0b9f93a 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -82,7 +82,8 @@ struct cgroup_subsys_state { /* ID for this css, if possible */ struct css_id __rcu *id; - /* percpu_ref killing and putting dentry on the last css_put() */ + /* percpu_ref killing and RCU release */ + struct rcu_head rcu_head; struct work_struct destroy_work; }; -- cgit v1.2.3 From 179ef71cbc085252e3fe6b8159263a7ed1d88ea4 Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Tue, 13 Aug 2013 16:00:49 -0700 Subject: mm: save soft-dirty bits on swapped pages Andy Lutomirski reported that if a page with _PAGE_SOFT_DIRTY bit set get swapped out, the bit is getting lost and no longer available when pte read back. To resolve this we introduce _PTE_SWP_SOFT_DIRTY bit which is saved in pte entry for the page being swapped out. When such page is to be read back from a swap cache we check for bit presence and if it's there we clear it and restore the former _PAGE_SOFT_DIRTY bit back. One of the problem was to find a place in pte entry where we can save the _PTE_SWP_SOFT_DIRTY bit while page is in swap. The _PAGE_PSE was chosen for that, it doesn't intersect with swap entry format stored in pte. Reported-by: Andy Lutomirski Signed-off-by: Cyrill Gorcunov Acked-by: Pavel Emelyanov Cc: Matt Mackall Cc: Xiao Guangrong Cc: Marcelo Tosatti Cc: KOSAKI Motohiro Cc: Stephen Rothwell Cc: Peter Zijlstra Cc: "Aneesh Kumar K.V" Reviewed-by: Minchan Kim Reviewed-by: Wanpeng Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swapops.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index c5fd30d2a415..8d4fa82bfb91 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -67,6 +67,8 @@ static inline swp_entry_t pte_to_swp_entry(pte_t pte) swp_entry_t arch_entry; BUG_ON(pte_file(pte)); + if (pte_swp_soft_dirty(pte)) + pte = pte_swp_clear_soft_dirty(pte); arch_entry = __pte_to_swp_entry(pte); return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry)); } -- cgit v1.2.3 From dfa9771a7c4784bafd0673bc7abcee3813088b77 Mon Sep 17 00:00:00 2001 From: Michal Simek Date: Tue, 13 Aug 2013 16:00:53 -0700 Subject: microblaze: fix clone syscall Fix inadvertent breakage in the clone syscall ABI for Microblaze that was introduced in commit f3268edbe6fe ("microblaze: switch to generic fork/vfork/clone"). The Microblaze syscall ABI for clone takes the parent tid address in the 4th argument; the third argument slot is used for the stack size. The incorrectly-used CLONE_BACKWARDS type assigned parent tid to the 3rd slot. This commit restores the original ABI so that existing userspace libc code will work correctly. All kernel versions from v3.8-rc1 were affected. Signed-off-by: Michal Simek Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/syscalls.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 4147d700a293..84662ecc7b51 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -802,9 +802,14 @@ asmlinkage long sys_vfork(void); asmlinkage long sys_clone(unsigned long, unsigned long, int __user *, int, int __user *); #else +#ifdef CONFIG_CLONE_BACKWARDS3 +asmlinkage long sys_clone(unsigned long, unsigned long, int, int __user *, + int __user *, int); +#else asmlinkage long sys_clone(unsigned long, unsigned long, int __user *, int __user *, int); #endif +#endif asmlinkage long sys_execve(const char __user *filename, const char __user *const __user *argv, -- cgit v1.2.3 From df54d6fa54275ce59660453e29d1228c2b45a826 Mon Sep 17 00:00:00 2001 From: Radu Caragea Date: Tue, 13 Aug 2013 16:00:59 -0700 Subject: x86 get_unmapped_area(): use proper mmap base for bottom-up direction When the stack is set to unlimited, the bottomup direction is used for mmap-ings but the mmap_base is not used and thus effectively renders ASLR for mmapings along with PIE useless. Cc: Michel Lespinasse Cc: Oleg Nesterov Reviewed-by: Rik van Riel Acked-by: Ingo Molnar Cc: Adrian Sendroiu Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index d722490da030..923dd6ea4a0e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -314,6 +314,7 @@ struct nsproxy; struct user_namespace; #ifdef CONFIG_MMU +extern unsigned long mmap_legacy_base(void); extern void arch_pick_mmap_layout(struct mm_struct *mm); extern unsigned long arch_get_unmapped_area(struct file *, unsigned long, unsigned long, -- cgit v1.2.3 From 65f382fd0c8fa483713c0971de9f1dfb4cf1ad9c Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 11 Jul 2013 19:12:32 +0200 Subject: context_tracking: Ground setup for static key use Prepare for using a static key in the context tracking subsystem. This will help optimizing the off case on its many users: * user_enter, user_exit, exception_enter, exception_exit, guest_enter, guest_exit, vtime_*() Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/context_tracking.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 1ae37c708c63..c138c24bad1a 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -4,6 +4,7 @@ #include #include #include +#include #include struct context_tracking { @@ -22,6 +23,7 @@ struct context_tracking { #ifdef CONFIG_CONTEXT_TRACKING +extern struct static_key context_tracking_enabled; DECLARE_PER_CPU(struct context_tracking, context_tracking); static inline bool context_tracking_in_user(void) @@ -67,6 +69,14 @@ static inline void context_tracking_task_switch(struct task_struct *prev, struct task_struct *next) { } #endif /* !CONFIG_CONTEXT_TRACKING */ + +#ifdef CONFIG_CONTEXT_TRACKING_FORCE +extern void context_tracking_init(void); +#else +static inline void context_tracking_init(void) { } +#endif /* CONFIG_CONTEXT_TRACKING_FORCE */ + + #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN extern void guest_enter(void); extern void guest_exit(void); -- cgit v1.2.3 From ad65782fba507d91a0a98f519b59e79cac1b474c Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 10 Jul 2013 02:44:35 +0200 Subject: context_tracking: Optimize main APIs off case with static key Optimize user and exception entry/exit APIs with static keys. This minimize the overhead for those who enable CONFIG_NO_HZ_FULL without always using it. Having no range passed to nohz_full= should result in the probes to be nopped (at least we hope so...). If this proves not be enough in the long term, we'll need to bring an exception slow path by re-routing the exception handlers. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/context_tracking.h | 27 ++++++++++++++++++++++----- 1 file changed, 22 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index c138c24bad1a..38ab60b3f3a6 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -38,23 +38,40 @@ static inline bool context_tracking_active(void) extern void context_tracking_cpu_set(int cpu); -extern void user_enter(void); -extern void user_exit(void); +extern void context_tracking_user_enter(void); +extern void context_tracking_user_exit(void); + +static inline void user_enter(void) +{ + if (static_key_false(&context_tracking_enabled)) + context_tracking_user_enter(); + +} +static inline void user_exit(void) +{ + if (static_key_false(&context_tracking_enabled)) + context_tracking_user_exit(); +} static inline enum ctx_state exception_enter(void) { enum ctx_state prev_ctx; + if (!static_key_false(&context_tracking_enabled)) + return 0; + prev_ctx = this_cpu_read(context_tracking.state); - user_exit(); + context_tracking_user_exit(); return prev_ctx; } static inline void exception_exit(enum ctx_state prev_ctx) { - if (prev_ctx == IN_USER) - user_enter(); + if (static_key_false(&context_tracking_enabled)) { + if (prev_ctx == IN_USER) + context_tracking_user_enter(); + } } extern void context_tracking_task_switch(struct task_struct *prev, -- cgit v1.2.3 From 48d6a816a8bf36e2a197c322697323003bdc1cfe Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 10 Jul 2013 02:44:35 +0200 Subject: context_tracking: Optimize guest APIs off case with static key Optimize guest entry/exit APIs with static keys. This minimize the overhead for those who enable CONFIG_NO_HZ_FULL without always using it. Having no range passed to nohz_full= should result in the probes overhead to be minimized. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/context_tracking.h | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 38ab60b3f3a6..8854eadb2142 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -95,8 +95,23 @@ static inline void context_tracking_init(void) { } #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -extern void guest_enter(void); -extern void guest_exit(void); +static inline void guest_enter(void) +{ + if (static_key_false(&context_tracking_enabled) && + vtime_accounting_enabled()) + vtime_guest_enter(current); + else + current->flags |= PF_VCPU; +} + +static inline void guest_exit(void) +{ + if (static_key_false(&context_tracking_enabled) && + vtime_accounting_enabled()) + vtime_guest_exit(current); + else + current->flags &= ~PF_VCPU; +} #else static inline void guest_enter(void) { -- cgit v1.2.3 From 73d424f9af7b571276e6284617cb59726d47bf12 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 11 Jul 2013 19:42:13 +0200 Subject: context_tracking: Optimize context switch off case with static keys No need for syscall slowpath if no CPU is full dynticks, rather nop this in this case. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/context_tracking.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 8854eadb2142..e070ea5dadac 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -40,6 +40,8 @@ extern void context_tracking_cpu_set(int cpu); extern void context_tracking_user_enter(void); extern void context_tracking_user_exit(void); +extern void __context_tracking_task_switch(struct task_struct *prev, + struct task_struct *next); static inline void user_enter(void) { @@ -74,8 +76,12 @@ static inline void exception_exit(enum ctx_state prev_ctx) } } -extern void context_tracking_task_switch(struct task_struct *prev, - struct task_struct *next); +static inline void context_tracking_task_switch(struct task_struct *prev, + struct task_struct *next) +{ + if (static_key_false(&context_tracking_enabled)) + __context_tracking_task_switch(prev, next); +} #else static inline bool context_tracking_in_user(void) { return false; } static inline void user_enter(void) { } @@ -112,6 +118,7 @@ static inline void guest_exit(void) else current->flags &= ~PF_VCPU; } + #else static inline void guest_enter(void) { -- cgit v1.2.3 From e7358b3bc0d7fcec0e7a724477f06db2b0c68e21 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 12 Jul 2013 02:15:49 +0200 Subject: context_tracking: Split low level state headers We plan to use the context tracking static key on inline vtime APIs. For this we need to include the context tracking headers from those of vtime. However vtime headers need to stay low level because they are included in hardirq.h that mostly contains standalone definitions. But context_tracking.h includes sched.h for a few task_struct references, therefore it wouldn't be sensible to include it from vtime.h To solve this, lets split the context tracking headers and move out the pure state definitions that only require a few low level headers. We can safely include that small part in vtime.h later. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/context_tracking.h | 31 +-------------------------- include/linux/context_tracking_state.h | 39 ++++++++++++++++++++++++++++++++++ 2 files changed, 40 insertions(+), 30 deletions(-) create mode 100644 include/linux/context_tracking_state.h (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index e070ea5dadac..82ec4870e064 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -2,40 +2,12 @@ #define _LINUX_CONTEXT_TRACKING_H #include -#include #include -#include +#include #include -struct context_tracking { - /* - * When active is false, probes are unset in order - * to minimize overhead: TIF flags are cleared - * and calls to user_enter/exit are ignored. This - * may be further optimized using static keys. - */ - bool active; - enum ctx_state { - IN_KERNEL = 0, - IN_USER, - } state; -}; - #ifdef CONFIG_CONTEXT_TRACKING -extern struct static_key context_tracking_enabled; -DECLARE_PER_CPU(struct context_tracking, context_tracking); - -static inline bool context_tracking_in_user(void) -{ - return __this_cpu_read(context_tracking.state) == IN_USER; -} - -static inline bool context_tracking_active(void) -{ - return __this_cpu_read(context_tracking.active); -} - extern void context_tracking_cpu_set(int cpu); extern void context_tracking_user_enter(void); @@ -83,7 +55,6 @@ static inline void context_tracking_task_switch(struct task_struct *prev, __context_tracking_task_switch(prev, next); } #else -static inline bool context_tracking_in_user(void) { return false; } static inline void user_enter(void) { } static inline void user_exit(void) { } static inline enum ctx_state exception_enter(void) { return 0; } diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h new file mode 100644 index 000000000000..0f1979d0674f --- /dev/null +++ b/include/linux/context_tracking_state.h @@ -0,0 +1,39 @@ +#ifndef _LINUX_CONTEXT_TRACKING_STATE_H +#define _LINUX_CONTEXT_TRACKING_STATE_H + +#include +#include + +struct context_tracking { + /* + * When active is false, probes are unset in order + * to minimize overhead: TIF flags are cleared + * and calls to user_enter/exit are ignored. This + * may be further optimized using static keys. + */ + bool active; + enum ctx_state { + IN_KERNEL = 0, + IN_USER, + } state; +}; + +#ifdef CONFIG_CONTEXT_TRACKING +extern struct static_key context_tracking_enabled; +DECLARE_PER_CPU(struct context_tracking, context_tracking); + +static inline bool context_tracking_in_user(void) +{ + return __this_cpu_read(context_tracking.state) == IN_USER; +} + +static inline bool context_tracking_active(void) +{ + return __this_cpu_read(context_tracking.active); +} +#else +static inline bool context_tracking_in_user(void) { return false; } +static inline bool context_tracking_active(void) { return false; } +#endif /* CONFIG_CONTEXT_TRACKING */ + +#endif -- cgit v1.2.3 From 2d4b84739f0acf61f37267b4e80c5bd85fb90a7e Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 29 Jul 2013 20:29:43 +0200 Subject: hardirq: Split preempt count mask definitions In order to use static keys with vtime APIs, we'll need to add static keys headers to vtime.h hardirq.h then becomes a problem because it needs vtime.h for irqtime accounting in irq_enter/irq_exit, but it's often included just to get the irq mask definitions in the task preempt_count field and the APIs that come along: in_interrupt(), in_hardirq(), etc... Some very low level arch headers sometimes need these masks and APIs such as arch/m68k/include/asm/irqflags.h for example. But they don't want to include hardirq.h if vtime.h, jump_label.h and even workqueue.h come along. Including such bloated high level header from arch headers can quickly result in circular headers dependency that crash the build. So let's split hardirq.h in two parts: * preempt_mask.h that gathers all the preempt_count definitions and the APIs associated. This one is considered low level and can be safely included anywhere. * hardirq.h that includes the previous one. It defines the irq entry/exit APIs. To avoid future circular headers dependencies, the preempt_mask.h inclusion can replace hardirq.h on files that don't implement irq low level handlers but just need the atomic/context check APIs. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/hardirq.h | 117 +---------------------------------------- include/linux/preempt_mask.h | 122 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 123 insertions(+), 116 deletions(-) create mode 100644 include/linux/preempt_mask.h (limited to 'include/linux') diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 05bcc0903766..ccfe17c5c8da 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -1,126 +1,11 @@ #ifndef LINUX_HARDIRQ_H #define LINUX_HARDIRQ_H -#include +#include #include #include #include -#include -/* - * We put the hardirq and softirq counter into the preemption - * counter. The bitmask has the following meaning: - * - * - bits 0-7 are the preemption count (max preemption depth: 256) - * - bits 8-15 are the softirq count (max # of softirqs: 256) - * - * The hardirq count can in theory reach the same as NR_IRQS. - * In reality, the number of nested IRQS is limited to the stack - * size as well. For archs with over 1000 IRQS it is not practical - * to expect that they will all nest. We give a max of 10 bits for - * hardirq nesting. An arch may choose to give less than 10 bits. - * m68k expects it to be 8. - * - * - bits 16-25 are the hardirq count (max # of nested hardirqs: 1024) - * - bit 26 is the NMI_MASK - * - bit 27 is the PREEMPT_ACTIVE flag - * - * PREEMPT_MASK: 0x000000ff - * SOFTIRQ_MASK: 0x0000ff00 - * HARDIRQ_MASK: 0x03ff0000 - * NMI_MASK: 0x04000000 - */ -#define PREEMPT_BITS 8 -#define SOFTIRQ_BITS 8 -#define NMI_BITS 1 - -#define MAX_HARDIRQ_BITS 10 - -#ifndef HARDIRQ_BITS -# define HARDIRQ_BITS MAX_HARDIRQ_BITS -#endif - -#if HARDIRQ_BITS > MAX_HARDIRQ_BITS -#error HARDIRQ_BITS too high! -#endif - -#define PREEMPT_SHIFT 0 -#define SOFTIRQ_SHIFT (PREEMPT_SHIFT + PREEMPT_BITS) -#define HARDIRQ_SHIFT (SOFTIRQ_SHIFT + SOFTIRQ_BITS) -#define NMI_SHIFT (HARDIRQ_SHIFT + HARDIRQ_BITS) - -#define __IRQ_MASK(x) ((1UL << (x))-1) - -#define PREEMPT_MASK (__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT) -#define SOFTIRQ_MASK (__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT) -#define HARDIRQ_MASK (__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT) -#define NMI_MASK (__IRQ_MASK(NMI_BITS) << NMI_SHIFT) - -#define PREEMPT_OFFSET (1UL << PREEMPT_SHIFT) -#define SOFTIRQ_OFFSET (1UL << SOFTIRQ_SHIFT) -#define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT) -#define NMI_OFFSET (1UL << NMI_SHIFT) - -#define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) - -#ifndef PREEMPT_ACTIVE -#define PREEMPT_ACTIVE_BITS 1 -#define PREEMPT_ACTIVE_SHIFT (NMI_SHIFT + NMI_BITS) -#define PREEMPT_ACTIVE (__IRQ_MASK(PREEMPT_ACTIVE_BITS) << PREEMPT_ACTIVE_SHIFT) -#endif - -#if PREEMPT_ACTIVE < (1 << (NMI_SHIFT + NMI_BITS)) -#error PREEMPT_ACTIVE is too low! -#endif - -#define hardirq_count() (preempt_count() & HARDIRQ_MASK) -#define softirq_count() (preempt_count() & SOFTIRQ_MASK) -#define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \ - | NMI_MASK)) - -/* - * Are we doing bottom half or hardware interrupt processing? - * Are we in a softirq context? Interrupt context? - * in_softirq - Are we currently processing softirq or have bh disabled? - * in_serving_softirq - Are we currently processing softirq? - */ -#define in_irq() (hardirq_count()) -#define in_softirq() (softirq_count()) -#define in_interrupt() (irq_count()) -#define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) - -/* - * Are we in NMI context? - */ -#define in_nmi() (preempt_count() & NMI_MASK) - -#if defined(CONFIG_PREEMPT_COUNT) -# define PREEMPT_CHECK_OFFSET 1 -#else -# define PREEMPT_CHECK_OFFSET 0 -#endif - -/* - * Are we running in atomic context? WARNING: this macro cannot - * always detect atomic context; in particular, it cannot know about - * held spinlocks in non-preemptible kernels. Thus it should not be - * used in the general case to determine whether sleeping is possible. - * Do not use in_atomic() in driver code. - */ -#define in_atomic() ((preempt_count() & ~PREEMPT_ACTIVE) != 0) - -/* - * Check whether we were atomic before we did preempt_disable(): - * (used by the scheduler, *after* releasing the kernel lock) - */ -#define in_atomic_preempt_off() \ - ((preempt_count() & ~PREEMPT_ACTIVE) != PREEMPT_CHECK_OFFSET) - -#ifdef CONFIG_PREEMPT_COUNT -# define preemptible() (preempt_count() == 0 && !irqs_disabled()) -#else -# define preemptible() 0 -#endif #if defined(CONFIG_SMP) || defined(CONFIG_GENERIC_HARDIRQS) extern void synchronize_irq(unsigned int irq); diff --git a/include/linux/preempt_mask.h b/include/linux/preempt_mask.h new file mode 100644 index 000000000000..931bc616219f --- /dev/null +++ b/include/linux/preempt_mask.h @@ -0,0 +1,122 @@ +#ifndef LINUX_PREEMPT_MASK_H +#define LINUX_PREEMPT_MASK_H + +#include +#include + +/* + * We put the hardirq and softirq counter into the preemption + * counter. The bitmask has the following meaning: + * + * - bits 0-7 are the preemption count (max preemption depth: 256) + * - bits 8-15 are the softirq count (max # of softirqs: 256) + * + * The hardirq count can in theory reach the same as NR_IRQS. + * In reality, the number of nested IRQS is limited to the stack + * size as well. For archs with over 1000 IRQS it is not practical + * to expect that they will all nest. We give a max of 10 bits for + * hardirq nesting. An arch may choose to give less than 10 bits. + * m68k expects it to be 8. + * + * - bits 16-25 are the hardirq count (max # of nested hardirqs: 1024) + * - bit 26 is the NMI_MASK + * - bit 27 is the PREEMPT_ACTIVE flag + * + * PREEMPT_MASK: 0x000000ff + * SOFTIRQ_MASK: 0x0000ff00 + * HARDIRQ_MASK: 0x03ff0000 + * NMI_MASK: 0x04000000 + */ +#define PREEMPT_BITS 8 +#define SOFTIRQ_BITS 8 +#define NMI_BITS 1 + +#define MAX_HARDIRQ_BITS 10 + +#ifndef HARDIRQ_BITS +# define HARDIRQ_BITS MAX_HARDIRQ_BITS +#endif + +#if HARDIRQ_BITS > MAX_HARDIRQ_BITS +#error HARDIRQ_BITS too high! +#endif + +#define PREEMPT_SHIFT 0 +#define SOFTIRQ_SHIFT (PREEMPT_SHIFT + PREEMPT_BITS) +#define HARDIRQ_SHIFT (SOFTIRQ_SHIFT + SOFTIRQ_BITS) +#define NMI_SHIFT (HARDIRQ_SHIFT + HARDIRQ_BITS) + +#define __IRQ_MASK(x) ((1UL << (x))-1) + +#define PREEMPT_MASK (__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT) +#define SOFTIRQ_MASK (__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT) +#define HARDIRQ_MASK (__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT) +#define NMI_MASK (__IRQ_MASK(NMI_BITS) << NMI_SHIFT) + +#define PREEMPT_OFFSET (1UL << PREEMPT_SHIFT) +#define SOFTIRQ_OFFSET (1UL << SOFTIRQ_SHIFT) +#define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT) +#define NMI_OFFSET (1UL << NMI_SHIFT) + +#define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) + +#ifndef PREEMPT_ACTIVE +#define PREEMPT_ACTIVE_BITS 1 +#define PREEMPT_ACTIVE_SHIFT (NMI_SHIFT + NMI_BITS) +#define PREEMPT_ACTIVE (__IRQ_MASK(PREEMPT_ACTIVE_BITS) << PREEMPT_ACTIVE_SHIFT) +#endif + +#if PREEMPT_ACTIVE < (1 << (NMI_SHIFT + NMI_BITS)) +#error PREEMPT_ACTIVE is too low! +#endif + +#define hardirq_count() (preempt_count() & HARDIRQ_MASK) +#define softirq_count() (preempt_count() & SOFTIRQ_MASK) +#define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \ + | NMI_MASK)) + +/* + * Are we doing bottom half or hardware interrupt processing? + * Are we in a softirq context? Interrupt context? + * in_softirq - Are we currently processing softirq or have bh disabled? + * in_serving_softirq - Are we currently processing softirq? + */ +#define in_irq() (hardirq_count()) +#define in_softirq() (softirq_count()) +#define in_interrupt() (irq_count()) +#define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) + +/* + * Are we in NMI context? + */ +#define in_nmi() (preempt_count() & NMI_MASK) + +#if defined(CONFIG_PREEMPT_COUNT) +# define PREEMPT_CHECK_OFFSET 1 +#else +# define PREEMPT_CHECK_OFFSET 0 +#endif + +/* + * Are we running in atomic context? WARNING: this macro cannot + * always detect atomic context; in particular, it cannot know about + * held spinlocks in non-preemptible kernels. Thus it should not be + * used in the general case to determine whether sleeping is possible. + * Do not use in_atomic() in driver code. + */ +#define in_atomic() ((preempt_count() & ~PREEMPT_ACTIVE) != 0) + +/* + * Check whether we were atomic before we did preempt_disable(): + * (used by the scheduler, *after* releasing the kernel lock) + */ +#define in_atomic_preempt_off() \ + ((preempt_count() & ~PREEMPT_ACTIVE) != PREEMPT_CHECK_OFFSET) + +#ifdef CONFIG_PREEMPT_COUNT +# define preemptible() (preempt_count() == 0 && !irqs_disabled()) +#else +# define preemptible() 0 +#endif + +#endif /* LINUX_PREEMPT_MASK_H */ -- cgit v1.2.3 From a5725ac23bf4ff79656ac2c317c323e261327fb3 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 16 Jul 2013 18:50:52 +0200 Subject: vtime: Describe overriden functions in dedicated arch headers If the arch overrides some generic vtime APIs, let it describe these on a dedicated and standalone header. This way it becomes convenient to include it in vtime generic headers without irrelevant stuff in such a low level header. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman Cc: Martin Schwidefsky Cc: Heiko Carstens --- include/linux/vtime.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vtime.h b/include/linux/vtime.h index b1dd2db80076..2ad073915e8c 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -1,6 +1,10 @@ #ifndef _LINUX_KERNEL_VTIME_H #define _LINUX_KERNEL_VTIME_H +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE +#include +#endif + struct task_struct; #ifdef CONFIG_VIRT_CPU_ACCOUNTING -- cgit v1.2.3 From b04934061330a4a449cfce703c97d887c3e11cd7 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 12 Jul 2013 03:10:15 +0200 Subject: vtime: Optimize full dynticks accounting off case with static keys If no CPU is in the full dynticks range, we can avoid the full dynticks cputime accounting through generic vtime along with its overhead and use the traditional tick based accounting instead. Let's do this and nope the off case with static keys. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/context_tracking.h | 6 ++-- include/linux/vtime.h | 70 ++++++++++++++++++++++++++++++++++------ 2 files changed, 63 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 82ec4870e064..158158704c30 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -74,8 +74,7 @@ static inline void context_tracking_init(void) { } #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN static inline void guest_enter(void) { - if (static_key_false(&context_tracking_enabled) && - vtime_accounting_enabled()) + if (vtime_accounting_enabled()) vtime_guest_enter(current); else current->flags |= PF_VCPU; @@ -83,8 +82,7 @@ static inline void guest_enter(void) static inline void guest_exit(void) { - if (static_key_false(&context_tracking_enabled) && - vtime_accounting_enabled()) + if (vtime_accounting_enabled()) vtime_guest_exit(current); else current->flags &= ~PF_VCPU; diff --git a/include/linux/vtime.h b/include/linux/vtime.h index 2ad073915e8c..f5b72b364bda 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -1,22 +1,68 @@ #ifndef _LINUX_KERNEL_VTIME_H #define _LINUX_KERNEL_VTIME_H +#include #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE #include #endif + struct task_struct; +/* + * vtime_accounting_enabled() definitions/declarations + */ +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE +static inline bool vtime_accounting_enabled(void) { return true; } +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ + +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +static inline bool vtime_accounting_enabled(void) +{ + if (static_key_false(&context_tracking_enabled)) { + if (context_tracking_active()) + return true; + } + + return false; +} +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ + +#ifndef CONFIG_VIRT_CPU_ACCOUNTING +static inline bool vtime_accounting_enabled(void) { return false; } +#endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ + + +/* + * Common vtime APIs + */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING + +#ifdef __ARCH_HAS_VTIME_TASK_SWITCH extern void vtime_task_switch(struct task_struct *prev); +#else +extern void vtime_common_task_switch(struct task_struct *prev); +static inline void vtime_task_switch(struct task_struct *prev) +{ + if (vtime_accounting_enabled()) + vtime_common_task_switch(prev); +} +#endif /* __ARCH_HAS_VTIME_TASK_SWITCH */ + extern void vtime_account_system(struct task_struct *tsk); extern void vtime_account_idle(struct task_struct *tsk); extern void vtime_account_user(struct task_struct *tsk); -extern void vtime_account_irq_enter(struct task_struct *tsk); -#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE -static inline bool vtime_accounting_enabled(void) { return true; } -#endif +#ifdef __ARCH_HAS_VTIME_ACCOUNT +extern void vtime_account_irq_enter(struct task_struct *tsk); +#else +extern void vtime_common_account_irq_enter(struct task_struct *tsk); +static inline void vtime_account_irq_enter(struct task_struct *tsk) +{ + if (vtime_accounting_enabled()) + vtime_common_account_irq_enter(tsk); +} +#endif /* __ARCH_HAS_VTIME_ACCOUNT */ #else /* !CONFIG_VIRT_CPU_ACCOUNTING */ @@ -24,14 +70,20 @@ static inline void vtime_task_switch(struct task_struct *prev) { } static inline void vtime_account_system(struct task_struct *tsk) { } static inline void vtime_account_user(struct task_struct *tsk) { } static inline void vtime_account_irq_enter(struct task_struct *tsk) { } -static inline bool vtime_accounting_enabled(void) { return false; } -#endif +#endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN extern void arch_vtime_task_switch(struct task_struct *tsk); -extern void vtime_account_irq_exit(struct task_struct *tsk); -extern bool vtime_accounting_enabled(void); +extern void vtime_gen_account_irq_exit(struct task_struct *tsk); + +static inline void vtime_account_irq_exit(struct task_struct *tsk) +{ + if (vtime_accounting_enabled()) + vtime_gen_account_irq_exit(tsk); +} + extern void vtime_user_enter(struct task_struct *tsk); + static inline void vtime_user_exit(struct task_struct *tsk) { vtime_account_user(tsk); @@ -39,7 +91,7 @@ static inline void vtime_user_exit(struct task_struct *tsk) extern void vtime_guest_enter(struct task_struct *tsk); extern void vtime_guest_exit(struct task_struct *tsk); extern void vtime_init_idle(struct task_struct *tsk, int cpu); -#else +#else /* !CONFIG_VIRT_CPU_ACCOUNTING_GEN */ static inline void vtime_account_irq_exit(struct task_struct *tsk) { /* On hard|softirq exit we always account to hard|softirq cputime */ -- cgit v1.2.3 From 460775df4680b4593d8449bc171008578625a850 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 24 Jul 2013 23:52:27 +0200 Subject: nohz: Optimize full dynticks state checks with static keys These APIs are frequenctly accessed and priority is given to optimize the full dynticks off-case in order to let distros enable this feature without suffering from significant performance regressions. Let's inline these APIs and optimize them with static keys. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/tick.h | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tick.h b/include/linux/tick.h index 9180f4b85e6d..c60b079e1b37 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -10,6 +10,8 @@ #include #include #include +#include +#include #ifdef CONFIG_GENERIC_CLOCKEVENTS @@ -158,15 +160,34 @@ static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; } # endif /* !CONFIG_NO_HZ_COMMON */ #ifdef CONFIG_NO_HZ_FULL +extern bool tick_nohz_full_running; +extern cpumask_var_t tick_nohz_full_mask; + +static inline bool tick_nohz_full_enabled(void) +{ + if (!static_key_false(&context_tracking_enabled)) + return false; + + return tick_nohz_full_running; +} + +static inline bool tick_nohz_full_cpu(int cpu) +{ + if (!tick_nohz_full_enabled()) + return false; + + return cpumask_test_cpu(cpu, tick_nohz_full_mask); +} + extern void tick_nohz_init(void); -extern int tick_nohz_full_cpu(int cpu); extern void tick_nohz_full_check(void); extern void tick_nohz_full_kick(void); extern void tick_nohz_full_kick_all(void); extern void tick_nohz_task_switch(struct task_struct *tsk); #else static inline void tick_nohz_init(void) { } -static inline int tick_nohz_full_cpu(int cpu) { return 0; } +static inline bool tick_nohz_full_enabled(void) { return false; } +static inline bool tick_nohz_full_cpu(int cpu) { return false; } static inline void tick_nohz_full_check(void) { } static inline void tick_nohz_full_kick(void) { } static inline void tick_nohz_full_kick_all(void) { } -- cgit v1.2.3 From d13508f9440e46dccac6a2dd48d51a73b2207482 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 24 Jul 2013 23:52:27 +0200 Subject: nohz: Optimize full dynticks's sched hooks with static keys Scheduler IPIs and task context switches are serious fast path. Let's try to hide as much as we can the impact of full dynticks APIs' off case that are called on these sites through the use of static keys. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/tick.h | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tick.h b/include/linux/tick.h index c60b079e1b37..a7ef1d6fceb6 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -180,20 +180,32 @@ static inline bool tick_nohz_full_cpu(int cpu) } extern void tick_nohz_init(void); -extern void tick_nohz_full_check(void); +extern void __tick_nohz_full_check(void); extern void tick_nohz_full_kick(void); extern void tick_nohz_full_kick_all(void); -extern void tick_nohz_task_switch(struct task_struct *tsk); +extern void __tick_nohz_task_switch(struct task_struct *tsk); #else static inline void tick_nohz_init(void) { } static inline bool tick_nohz_full_enabled(void) { return false; } static inline bool tick_nohz_full_cpu(int cpu) { return false; } -static inline void tick_nohz_full_check(void) { } +static inline void __tick_nohz_full_check(void) { } static inline void tick_nohz_full_kick(void) { } static inline void tick_nohz_full_kick_all(void) { } -static inline void tick_nohz_task_switch(struct task_struct *tsk) { } +static inline void __tick_nohz_task_switch(struct task_struct *tsk) { } #endif +static inline void tick_nohz_full_check(void) +{ + if (tick_nohz_full_enabled()) + __tick_nohz_full_check(); +} + +static inline void tick_nohz_task_switch(struct task_struct *tsk) +{ + if (tick_nohz_full_enabled()) + __tick_nohz_task_switch(tsk); +} + # ifdef CONFIG_CPU_IDLE_GOV_MENU extern void menu_hrtimer_cancel(void); -- cgit v1.2.3 From 1542d9c35d8166c54e0616574954a0f48449f331 Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Wed, 14 Aug 2013 12:44:03 +0300 Subject: usb: chipidea: move vbus regulator operation to core The vbus regulator is a common element for USB vbus operation, So, move it from glue layer to core. Tested-by: Marek Vasut Signed-off-by: Michael Grzeschik Signed-off-by: Peter Chen Signed-off-by: Alexander Shishkin Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/chipidea.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h index 25629948c842..ce4e1aa071b3 100644 --- a/include/linux/usb/chipidea.h +++ b/include/linux/usb/chipidea.h @@ -24,6 +24,7 @@ struct ci_hdrc_platform_data { #define CI_HDRC_CONTROLLER_RESET_EVENT 0 #define CI_HDRC_CONTROLLER_STOPPED_EVENT 1 void (*notify_event) (struct ci_hdrc *ci, unsigned event); + struct regulator *reg_vbus; }; /* Default offset of capability registers */ -- cgit v1.2.3 From 577b232fc9caba1b6f7a3bb9901c00b10e0ca1ba Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Wed, 14 Aug 2013 12:44:08 +0300 Subject: usb: chipidea: add flag CI_HDRC_DUAL_ROLE_NOT_OTG Since we need otgsc to know vbus's status at some chipidea controllers even it is peripheral-only mode. Besides, some SoCs (eg, AR9331 SoC) don't have otgsc register even the DCCPARAMS_DC and DCCPARAMS_HC are both 1 at CAP_DCCPARAMS. We inroduce flag CI_HDRC_DUAL_ROLE_NOT_OTG to indicate if the controller is dual role, but not supports OTG. If this flag is not set, we follow the rule that if DCCPARAMS_DC and DCCPARAMS_HC are both 1 at CAP_DCCPARAMS, then this controller is otg capable. Signed-off-by: Peter Chen Signed-off-by: Alexander Shishkin Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/chipidea.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h index ce4e1aa071b3..10a607ce9090 100644 --- a/include/linux/usb/chipidea.h +++ b/include/linux/usb/chipidea.h @@ -20,6 +20,11 @@ struct ci_hdrc_platform_data { #define CI_HDRC_REQUIRE_TRANSCEIVER BIT(1) #define CI_HDRC_PULLUP_ON_VBUS BIT(2) #define CI_HDRC_DISABLE_STREAMING BIT(3) + /* + * Only set it when DCCPARAMS.DC==1 and DCCPARAMS.HC==1, + * but otg is not supported (no register otgsc). + */ +#define CI_HDRC_DUAL_ROLE_NOT_OTG BIT(4) enum usb_dr_mode dr_mode; #define CI_HDRC_CONTROLLER_RESET_EVENT 0 #define CI_HDRC_CONTROLLER_STOPPED_EVENT 1 -- cgit v1.2.3 From d268e9bc23f5df4a2f4167da246d277c2a468d3d Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Wed, 14 Aug 2013 12:44:14 +0300 Subject: usb: chipidea: retire flag CI_HDRC_PULLUP_ON_VBUS Currently, the controller only runs when the ci->vbus_active is true. So the flag CI_HDRC_PULLUP_ON_VBUS is useless no longer. If the user doesn't have otgsc, he/she needs to change ci_handle_vbus_change to update ci->vbus_active. Signed-off-by: Peter Chen Signed-off-by: Alexander Shishkin Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/chipidea.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h index 10a607ce9090..7d399671a566 100644 --- a/include/linux/usb/chipidea.h +++ b/include/linux/usb/chipidea.h @@ -18,7 +18,6 @@ struct ci_hdrc_platform_data { unsigned long flags; #define CI_HDRC_REGS_SHARED BIT(0) #define CI_HDRC_REQUIRE_TRANSCEIVER BIT(1) -#define CI_HDRC_PULLUP_ON_VBUS BIT(2) #define CI_HDRC_DISABLE_STREAMING BIT(3) /* * Only set it when DCCPARAMS.DC==1 and DCCPARAMS.HC==1, -- cgit v1.2.3 From 5c32b35b004f5ef70dcf62bbc42b8bed1e50b471 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Thu, 8 Aug 2013 14:09:31 -0600 Subject: PCI: Add hotplug_slot_ops.reset_slot() This optional callback allows hotplug controllers to perform slot specific resets. These may be necessary in cases where a normal secondary bus reset can interact with controller logic and expose spurious hotplugs. Signed-off-by: Alex Williamson Signed-off-by: Bjorn Helgaas --- include/linux/pci_hotplug.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index 8db71dcd6337..bd32109e607e 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -63,6 +63,9 @@ enum pcie_link_width { * @get_adapter_status: Called to get see if an adapter is present in the slot or not. * If this field is NULL, the value passed in the struct hotplug_slot_info * will be used when this value is requested by a user. + * @reset_slot: Optional interface to allow override of a bus reset for the + * slot for cases where a secondary bus reset can result in spurious + * hotplug events or where a slot can be reset independent of the bus. * * The table of function pointers that is passed to the hotplug pci core by a * hotplug pci driver. These functions are called by the hotplug pci core when @@ -80,6 +83,7 @@ struct hotplug_slot_ops { int (*get_attention_status) (struct hotplug_slot *slot, u8 *value); int (*get_latch_status) (struct hotplug_slot *slot, u8 *value); int (*get_adapter_status) (struct hotplug_slot *slot, u8 *value); + int (*reset_slot) (struct hotplug_slot *slot, int probe); }; /** -- cgit v1.2.3 From 090a3c5322e900f468b3205b76d0837003ad57b2 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Thu, 8 Aug 2013 14:09:55 -0600 Subject: PCI: Add pci_reset_slot() and pci_reset_bus() Sometimes pci_reset_function() is not sufficient. We have cases where devices do not support any kind of reset, but there might be multiple functions on the bus preventing pci_reset_function() from doing a secondary bus reset. We also have cases where a device will advertise that it supports a PM reset, but really does nothing on D3hot->D0 (graphics cards are notorious for this). These devices often also have more than one function, so even blacklisting PM reset for them wouldn't allow a secondary bus reset through pci_reset_function(). If a driver supports multiple devices it should have the ability to induce a bus reset when it needs to. This patch provides that ability through pci_reset_slot() and pci_reset_bus(). It's the caller's responsibility when using these interfaces to understand that all of the devices in or below the slot (or on or below the bus) will be reset and therefore should be under control of the caller. PCI state of all the affected devices is saved and restored around these resets, but internal state of all of the affected devices is reset (which should be the intention). Signed-off-by: Alex Williamson Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 35c1bc4909f3..1a8fd3464daf 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -924,6 +924,8 @@ int pcie_set_mps(struct pci_dev *dev, int mps); int __pci_reset_function(struct pci_dev *dev); int __pci_reset_function_locked(struct pci_dev *dev); int pci_reset_function(struct pci_dev *dev); +int pci_reset_slot(struct pci_slot *slot); +int pci_reset_bus(struct pci_bus *bus); void pci_reset_bridge_secondary_bus(struct pci_dev *dev); void pci_update_resource(struct pci_dev *dev, int resno); int __must_check pci_assign_resource(struct pci_dev *dev, int i); -- cgit v1.2.3 From 3f0fa9a808f98fa10a18ba2a73f13d65fda990fb Mon Sep 17 00:00:00 2001 From: Kevin Hilman Date: Wed, 14 Aug 2013 16:05:02 -0700 Subject: regmap: Add another missing header for !CONFIG_REGMAP stubs The use of WARN_ON() needs the definitions from bug.h, without it you can get: include/linux/regmap.h: In function 'regmap_write': include/linux/regmap.h:525:2: error: implicit declaration of function 'WARN_ONCE' [-Werror=implicit-function-declaration] Signed-off-by: Kevin Hilman Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- include/linux/regmap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 580a5320cc96..6d91fcb4c5cb 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -16,6 +16,7 @@ #include #include #include +#include struct module; struct device; -- cgit v1.2.3 From 9a3d2b9beefd5b07c1d8f70ded01b88f203ee304 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Wed, 14 Aug 2013 14:06:05 -0600 Subject: PCI: Add pci_probe_reset_slot() and pci_probe_reset_bus() Users of pci_reset_bus() and pci_reset_slot() need a way to probe whether the bus or slot supports reset. Add trivial helper functions and export them as vfio-pci will make use of these. Signed-off-by: Alex Williamson Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 1a8fd3464daf..daf40cd851df 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -924,7 +924,9 @@ int pcie_set_mps(struct pci_dev *dev, int mps); int __pci_reset_function(struct pci_dev *dev); int __pci_reset_function_locked(struct pci_dev *dev); int pci_reset_function(struct pci_dev *dev); +int pci_probe_reset_slot(struct pci_slot *slot); int pci_reset_slot(struct pci_slot *slot); +int pci_probe_reset_bus(struct pci_bus *bus); int pci_reset_bus(struct pci_bus *bus); void pci_reset_bridge_secondary_bus(struct pci_dev *dev); void pci_update_resource(struct pci_dev *dev, int resno); -- cgit v1.2.3 From 0a324f3189ed9c78b1aaf48d88e93cb18643c655 Mon Sep 17 00:00:00 2001 From: Moshe Lazer Date: Wed, 14 Aug 2013 17:46:48 +0300 Subject: net/mlx5_core: Support MANAGE_PAGES and QUERY_PAGES firmware command changes In the previous QUERY_PAGES command version we used one command to get the required amount of boot, init and post init pages. The new version uses the op_mod field to specify whether the query is for the required amount of boot, init or post init pages. In addition the output field size for the required amount of pages increased from 16 to 32 bits. In MANAGE_PAGES command the input_num_entries and output_num_entries fields sizes changed from 16 to 32 bits and the PAS tables offset changed to 0x10. In the pages request event the num_pages field also changed to 32 bits. In the HCA-capabilities-layout the size and location of max_qp_mcg field has been changed to support 24 bits. This patch isn't compatible with firmware versions < 5; however, it turns out that the first GA firmware we will publish will not support previous versions so this should be OK. Signed-off-by: Moshe Lazer Signed-off-by: Eli Cohen Signed-off-by: David S. Miller --- include/linux/mlx5/device.h | 22 ++++++++++------------ include/linux/mlx5/driver.h | 4 ++-- 2 files changed, 12 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 737685e9e852..68029b30c3dc 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -309,21 +309,20 @@ struct mlx5_hca_cap { __be16 max_desc_sz_rq; u8 rsvd21[2]; __be16 max_desc_sz_sq_dc; - u8 rsvd22[4]; - __be16 max_qp_mcg; - u8 rsvd23; + __be32 max_qp_mcg; + u8 rsvd22[3]; u8 log_max_mcg; - u8 rsvd24; + u8 rsvd23; u8 log_max_pd; - u8 rsvd25; + u8 rsvd24; u8 log_max_xrcd; - u8 rsvd26[42]; + u8 rsvd25[42]; __be16 log_uar_page_sz; - u8 rsvd27[28]; + u8 rsvd26[28]; u8 log_msx_atomic_size_qp; - u8 rsvd28[2]; + u8 rsvd27[2]; u8 log_msx_atomic_size_dc; - u8 rsvd29[76]; + u8 rsvd28[76]; }; @@ -472,9 +471,8 @@ struct mlx5_eqe_cmd { struct mlx5_eqe_page_req { u8 rsvd0[2]; __be16 func_id; - u8 rsvd1[2]; - __be16 num_pages; - __be32 rsvd2[5]; + __be32 num_pages; + __be32 rsvd1[5]; }; union ev_data { diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 611e65e76b00..8888381fc150 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -358,7 +358,7 @@ struct mlx5_caps { u32 reserved_lkey; u8 local_ca_ack_delay; u8 log_max_mcg; - u16 max_qp_mcg; + u32 max_qp_mcg; int min_page_sz; }; @@ -691,7 +691,7 @@ void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev); int mlx5_pagealloc_start(struct mlx5_core_dev *dev); void mlx5_pagealloc_stop(struct mlx5_core_dev *dev); void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id, - s16 npages); + s32 npages); int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot); int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev); void mlx5_register_debugfs(void); -- cgit v1.2.3 From 98d4f93c79b002f85480320fe63fefaa31d58b6c Mon Sep 17 00:00:00 2001 From: Jens Frederich Date: Thu, 15 Aug 2013 21:34:55 +0200 Subject: Staging: olpc_dcon: replace some magic numbers This patch replace some magic numbers. I believe it makes the driver more readable. The magic number 0x26 is the XO system embedded controller (EC) command 'DCON power enable/disable'. Number 0x41, and 0x42 are special memory controller settings register. The 0x41 initialize bit sequence 0x101 means: enable memory power down function and special SDRAM clock delay for synchronize SDRAM output and clock signal. The 0x42 initialize squence 0x101 is wrong. According to the specification Bit 8 is reserved, thus not in use. I removed it. Signed-off-by: Jens Frederich Signed-off-by: Greg Kroah-Hartman --- include/linux/olpc-ec.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/olpc-ec.h b/include/linux/olpc-ec.h index 5bb6e760aa61..2925df3ce78a 100644 --- a/include/linux/olpc-ec.h +++ b/include/linux/olpc-ec.h @@ -6,6 +6,7 @@ #define EC_WRITE_SCI_MASK 0x1b #define EC_WAKE_UP_WLAN 0x24 #define EC_WLAN_LEAVE_RESET 0x25 +#define EC_DCON_POWER_MODE 0x26 #define EC_READ_EB_MODE 0x2a #define EC_SET_SCI_INHIBIT 0x32 #define EC_SET_SCI_INHIBIT_RELEASE 0x34 -- cgit v1.2.3 From 6d33f7bb8c3863e54f8bdede0a2bf97a3585ac20 Mon Sep 17 00:00:00 2001 From: Thomas Pugliese Date: Thu, 15 Aug 2013 12:21:30 -0500 Subject: USB: WUSBCORE: clear RPIPE stall for control endpoints When the HWA encounters a STALL on a control endpoint, it should clear the RPIPE_STALL feature on the RPIPE before processing the next transfer request. Otherwise, all transfer requests on that endpoint after the first STALL will fail because the RPIPE is still in the halted state. This also removes the unneccessary call to spin_lock_irqsave for a nested lock that was present in the first patch. Signed-off-by: Thomas Pugliese Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/wusb-wa.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/wusb-wa.h b/include/linux/usb/wusb-wa.h index 6be985b2a434..4ff744e2b678 100644 --- a/include/linux/usb/wusb-wa.h +++ b/include/linux/usb/wusb-wa.h @@ -66,6 +66,7 @@ enum { WA_ENABLE = 0x01, WA_RESET = 0x02, RPIPE_PAUSE = 0x1, + RPIPE_STALL = 0x2, }; /* Responses from Get Status request ([WUSB] section 8.3.1.6) */ -- cgit v1.2.3 From d536321df392ee0db6a5e92d98f0303020315f40 Mon Sep 17 00:00:00 2001 From: Jacek Anaszewski Date: Fri, 16 Aug 2013 14:11:00 +0100 Subject: iio: trigger: implement devm_iio_trigger_alloc/devm_iio_triger_free Add a resource managed devm_iio_trigger_alloc()/devm_iio_triger_free() to automatically clean up triggers allocated by IIO drivers, thus leading to simplified IIO drivers code. Signed-off-by: Jacek Anaszewski Signed-off-by: Kyunmin Park Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 09ebe0a4d8e6..2103cc32a5fb 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -556,6 +556,35 @@ struct iio_dev *devm_iio_device_alloc(struct device *dev, int sizeof_priv); */ void devm_iio_device_free(struct device *dev, struct iio_dev *indio_dev); +/** + * devm_iio_trigger_alloc - Resource-managed iio_trigger_alloc() + * @dev: Device to allocate iio_trigger for + * @fmt: trigger name format. If it includes format + * specifiers, the additional arguments following + * format are formatted and inserted in the resulting + * string replacing their respective specifiers. + * + * Managed iio_trigger_alloc. iio_trigger allocated with this function is + * automatically freed on driver detach. + * + * If an iio_trigger allocated with this function needs to be freed separately, + * devm_iio_trigger_free() must be used. + * + * RETURNS: + * Pointer to allocated iio_trigger on success, NULL on failure. + */ +struct iio_trigger *devm_iio_trigger_alloc(struct device *dev, + const char *fmt, ...); + +/** + * devm_iio_trigger_free - Resource-managed iio_trigger_free() + * @dev: Device this iio_dev belongs to + * @iio_trig: the iio_trigger associated with the device + * + * Free iio_trigger allocated with devm_iio_trigger_alloc(). + */ +void devm_iio_trigger_free(struct device *dev, struct iio_trigger *iio_trig); + /** * iio_buffer_enabled() - helper function to test if the buffer is enabled * @indio_dev: IIO device structure for device -- cgit v1.2.3 From b778ae25366e6f3891fe51306f56a3bca211975d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 23 Apr 2013 12:51:11 -0700 Subject: debugobjects: Make debug_object_activate() return status In order to better respond to things like duplicate invocations of call_rcu(), RCU needs to see the status of a call to debug_object_activate(). This would allow RCU to leak the callback in order to avoid adding freelist-reuse mischief to the duplicate invoations. This commit therefore makes debug_object_activate() return status, zero for success and -EINVAL for failure. Signed-off-by: Paul E. McKenney Cc: Mathieu Desnoyers Cc: Sedat Dilek Cc: Davidlohr Bueso Cc: Rik van Riel Cc: Thomas Gleixner Cc: Linus Torvalds Tested-by: Sedat Dilek Reviewed-by: Josh Triplett --- include/linux/debugobjects.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/debugobjects.h b/include/linux/debugobjects.h index 0e5f5785d9f2..98ffcbd4888e 100644 --- a/include/linux/debugobjects.h +++ b/include/linux/debugobjects.h @@ -63,7 +63,7 @@ struct debug_obj_descr { extern void debug_object_init (void *addr, struct debug_obj_descr *descr); extern void debug_object_init_on_stack(void *addr, struct debug_obj_descr *descr); -extern void debug_object_activate (void *addr, struct debug_obj_descr *descr); +extern int debug_object_activate (void *addr, struct debug_obj_descr *descr); extern void debug_object_deactivate(void *addr, struct debug_obj_descr *descr); extern void debug_object_destroy (void *addr, struct debug_obj_descr *descr); extern void debug_object_free (void *addr, struct debug_obj_descr *descr); @@ -85,8 +85,8 @@ static inline void debug_object_init (void *addr, struct debug_obj_descr *descr) { } static inline void debug_object_init_on_stack(void *addr, struct debug_obj_descr *descr) { } -static inline void -debug_object_activate (void *addr, struct debug_obj_descr *descr) { } +static inline int +debug_object_activate (void *addr, struct debug_obj_descr *descr) { return 0; } static inline void debug_object_deactivate(void *addr, struct debug_obj_descr *descr) { } static inline void -- cgit v1.2.3 From c34ac00caefbe49d40058ae7200bd58725cebb45 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 28 Jun 2013 10:34:48 -0700 Subject: rculist: list_first_or_null_rcu() should use list_entry_rcu() list_first_or_null() should test whether the list is empty and return pointer to the first entry if not in a RCU safe manner. It's broken in several ways. * It compares __kernel @__ptr with __rcu @__next triggering the following sparse warning. net/core/dev.c:4331:17: error: incompatible types in comparison expression (different address spaces) * It doesn't perform rcu_dereference*() and computes the entry address using container_of() directly from the __rcu pointer which is inconsitent with other rculist interface. As a result, all three in-kernel users - net/core/dev.c, macvlan, cgroup - are buggy. They dereference the pointer w/o going through read barrier. * While ->next dereference passes through list_next_rcu(), the compiler is still free to fetch ->next more than once and thus nullify the "__ptr != __next" condition check. Fix it by making list_first_or_null_rcu() dereference ->next directly using ACCESS_ONCE() and then use list_entry_rcu() on it like other rculist accessors. v2: Paul pointed out that the compiler may fetch the pointer more than once nullifying the condition check. ACCESS_ONCE() added on ->next dereference. v3: Restored () around macro param which was accidentally removed. Spotted by Paul. Signed-off-by: Tejun Heo Reported-by: Fengguang Wu Cc: Dipankar Sarma Cc: "Paul E. McKenney" Cc: "David S. Miller" Cc: Li Zefan Cc: Patrick McHardy Cc: stable@vger.kernel.org Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- include/linux/rculist.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index f4b1001a4676..4106721c4e5e 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -267,8 +267,9 @@ static inline void list_splice_init_rcu(struct list_head *list, */ #define list_first_or_null_rcu(ptr, type, member) \ ({struct list_head *__ptr = (ptr); \ - struct list_head __rcu *__next = list_next_rcu(__ptr); \ - likely(__ptr != __next) ? container_of(__next, type, member) : NULL; \ + struct list_head *__next = ACCESS_ONCE(__ptr->next); \ + likely(__ptr != __next) ? \ + list_entry_rcu(__next, type, member) : NULL; \ }) /** -- cgit v1.2.3 From feed66ed26a53e700ca02ce1744fed7d0c647292 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 9 May 2013 08:55:54 -0700 Subject: rcu: Eliminate unused APIs intended for adaptive ticks The rcu_user_enter_after_irq() and rcu_user_exit_after_irq() functions were intended for use by adaptive ticks, but changes in implementation have rendered them unnecessary. This commit therefore removes them. Reported-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- include/linux/rcupdate.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 0c38abbe6e35..30bea9c25735 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -229,13 +229,9 @@ extern void rcu_irq_exit(void); #ifdef CONFIG_RCU_USER_QS extern void rcu_user_enter(void); extern void rcu_user_exit(void); -extern void rcu_user_enter_after_irq(void); -extern void rcu_user_exit_after_irq(void); #else static inline void rcu_user_enter(void) { } static inline void rcu_user_exit(void) { } -static inline void rcu_user_enter_after_irq(void) { } -static inline void rcu_user_exit_after_irq(void) { } static inline void rcu_user_hooks_switch(struct task_struct *prev, struct task_struct *next) { } #endif /* CONFIG_RCU_USER_QS */ -- cgit v1.2.3 From 1cb650b91ba582f6737457b7d22e368585596d2c Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Mon, 19 Aug 2013 10:05:24 +0800 Subject: cgroup: change cgroup_from_id() to css_from_id() Now we want cgroup core to always provide the css to use to the subsystems, so change this API to css_from_id(). Uninline css_from_id(), because it's getting bigger and cgroup_css() has been unexported. While at it, remove the #ifdef, and shuffle the order of the args. Signed-off-by: Li Zefan Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 20 ++------------------ 1 file changed, 2 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index c24bd0b9f93a..b685955d4b29 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -741,27 +741,11 @@ static inline struct cgroup *task_cgroup(struct task_struct *task, return task_css(task, subsys_id)->cgroup; } -/** - * cgroup_from_id - lookup cgroup by id - * @ss: cgroup subsys to be looked into - * @id: the cgroup id - * - * Returns the cgroup if there's valid one with @id, otherwise returns NULL. - * Should be called under rcu_read_lock(). - */ -static inline struct cgroup *cgroup_from_id(struct cgroup_subsys *ss, int id) -{ -#ifdef CONFIG_PROVE_RCU - rcu_lockdep_assert(rcu_read_lock_held() || - lockdep_is_held(&cgroup_mutex), - "cgroup_from_id() needs proper protection"); -#endif - return idr_find(&ss->root->cgroup_idr, id); -} - struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *parent); +struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss); + /** * css_for_each_child - iterate through children of a css * @pos: the css * to use as the loop cursor -- cgit v1.2.3 From b3b515bbd689ba3937cac2dd3fc55057f8c50329 Mon Sep 17 00:00:00 2001 From: Aruna Balakrishnaiah Date: Fri, 16 Aug 2013 13:52:47 -0700 Subject: pstore: Add new argument 'compressed' in pstore write callback Addition of new argument 'compressed' in the write call back will help the backend to know if the data passed from pstore is compressed or not (In case where compression fails.). If compressed, the backend can add a tag indicating the data is compressed while writing to persistent store. Signed-off-by: Aruna Balakrishnaiah Reviewed-by: Kees Cook Signed-off-by: Tony Luck --- include/linux/pstore.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pstore.h b/include/linux/pstore.h index 4aa80ba830a2..abfca4f59422 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -58,11 +58,11 @@ struct pstore_info { struct pstore_info *psi); int (*write)(enum pstore_type_id type, enum kmsg_dump_reason reason, u64 *id, - unsigned int part, int count, size_t hsize, + unsigned int part, int count, bool compressed, size_t size, struct pstore_info *psi); int (*write_buf)(enum pstore_type_id type, enum kmsg_dump_reason reason, u64 *id, - unsigned int part, const char *buf, size_t hsize, + unsigned int part, const char *buf, bool compressed, size_t size, struct pstore_info *psi); int (*erase)(enum pstore_type_id type, u64 id, int count, struct timespec time, -- cgit v1.2.3 From 9a4e1398208d147a9240731a1f8cfe7d8cc4c553 Mon Sep 17 00:00:00 2001 From: Aruna Balakrishnaiah Date: Fri, 16 Aug 2013 13:53:19 -0700 Subject: pstore: Introduce new argument 'compressed' in the read callback Backends will set the flag 'compressed' after reading the log from persistent store to indicate the data being returned to pstore is compressed or not. Signed-off-by: Aruna Balakrishnaiah Reviewed-by: Kees Cook Signed-off-by: Tony Luck --- include/linux/pstore.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pstore.h b/include/linux/pstore.h index abfca4f59422..abd437d0a8a7 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -55,7 +55,7 @@ struct pstore_info { int (*close)(struct pstore_info *psi); ssize_t (*read)(u64 *id, enum pstore_type_id *type, int *count, struct timespec *time, char **buf, - struct pstore_info *psi); + bool *compressed, struct pstore_info *psi); int (*write)(enum pstore_type_id type, enum kmsg_dump_reason reason, u64 *id, unsigned int part, int count, bool compressed, -- cgit v1.2.3 From bd0eae4e1cd5c4ff7c2a9ebcb3e78ea4631251ef Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 24 Jul 2013 15:05:19 -0700 Subject: PPS: convert class code to use dev_groups The dev_attrs field of struct class is going away soon, dev_groups should be used instead. This converts the pps class code to use the correct field. Cc: Rodolfo Giometti Signed-off-by: Greg Kroah-Hartman --- include/linux/pps_kernel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pps_kernel.h b/include/linux/pps_kernel.h index 7db3eb93a079..1d2cd21242e8 100644 --- a/include/linux/pps_kernel.h +++ b/include/linux/pps_kernel.h @@ -80,7 +80,7 @@ struct pps_device { * Global variables */ -extern struct device_attribute pps_attrs[]; +extern const struct attribute_group *pps_groups[]; /* * Internal functions. -- cgit v1.2.3 From f46078cfcd77fa5165bf849f5e568a7ac5fa569c Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Fri, 16 Aug 2013 13:30:07 +0200 Subject: ipv6: drop packets with multiple fragmentation headers It is not allowed for an ipv6 packet to contain multiple fragmentation headers. So discard packets which were already reassembled by fragmentation logic and send back a parameter problem icmp. The updates for RFC 6980 will come in later, I have to do a bit more research here. Cc: YOSHIFUJI Hideaki Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 850e95bc766c..b8b7dc755752 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -101,6 +101,7 @@ struct inet6_skb_parm { #define IP6SKB_FORWARDED 2 #define IP6SKB_REROUTED 4 #define IP6SKB_ROUTERALERT 8 +#define IP6SKB_FRAGMENTED 16 }; #define IP6CB(skb) ((struct inet6_skb_parm*)((skb)->cb)) -- cgit v1.2.3 From 5a581b367b5df0531265311fc681c2abd377e5e6 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 27 Jul 2013 03:53:54 -0700 Subject: jiffies: Avoid undefined behavior from signed overflow According to the C standard 3.4.3p3, overflow of a signed integer results in undefined behavior. This commit therefore changes the definitions of time_after(), time_after_eq(), time_after64(), and time_after_eq64() to avoid this undefined behavior. The trick is that the subtraction is done using unsigned arithmetic, which according to 6.2.5p9 cannot overflow because it is defined as modulo arithmetic. This has the added (though admittedly quite small) benefit of shortening four lines of code by four characters each. Note that the C standard considers the cast from unsigned to signed to be implementation-defined, see 6.3.1.3p3. However, on a two's-complement system, an implementation that defines anything other than a reinterpretation of the bits is free to come to me, and I will be happy to act as a witness for its being committed to an insane asylum. (Although I have nothing against saturating arithmetic or signals in some cases, these things really should not be the default when compiling an operating-system kernel.) Signed-off-by: Paul E. McKenney Cc: John Stultz Cc: "David S. Miller" Cc: Arnd Bergmann Cc: Ingo Molnar Cc: Linus Torvalds Cc: Eric Dumazet Cc: Kevin Easton [ paulmck: Included time_after64() and time_after_eq64(), as suggested by Eric Dumazet, also fixed commit message.] Reviewed-by: Josh Triplett --- include/linux/jiffies.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 97ba4e78a37e..d235e88cfd7c 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -101,13 +101,13 @@ static inline u64 get_jiffies_64(void) #define time_after(a,b) \ (typecheck(unsigned long, a) && \ typecheck(unsigned long, b) && \ - ((long)(b) - (long)(a) < 0)) + ((long)((b) - (a)) < 0)) #define time_before(a,b) time_after(b,a) #define time_after_eq(a,b) \ (typecheck(unsigned long, a) && \ typecheck(unsigned long, b) && \ - ((long)(a) - (long)(b) >= 0)) + ((long)((a) - (b)) >= 0)) #define time_before_eq(a,b) time_after_eq(b,a) /* @@ -130,13 +130,13 @@ static inline u64 get_jiffies_64(void) #define time_after64(a,b) \ (typecheck(__u64, a) && \ typecheck(__u64, b) && \ - ((__s64)(b) - (__s64)(a) < 0)) + ((__s64)((b) - (a)) < 0)) #define time_before64(a,b) time_after64(b,a) #define time_after_eq64(a,b) \ (typecheck(__u64, a) && \ typecheck(__u64, b) && \ - ((__s64)(a) - (__s64)(b) >= 0)) + ((__s64)((a) - (b)) >= 0)) #define time_before_eq64(a,b) time_after_eq64(b,a) #define time_in_range64(a, b, c) \ -- cgit v1.2.3 From 6853152689d47b4a1eb9f38a25a18f3f8b7a60de Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 20 Aug 2013 16:48:54 -0700 Subject: sysfs.h: fix __BIN_ATTR_RW() __BIN_ATTR_RW() wasn't passing in the _size field. As it would break the build if this macro was ever used, it's obvious no one had ever tried to use it before. Fix it so that it can be used. Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 9e8a9b555ad6..0f04958623d7 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -153,7 +153,7 @@ struct bin_attribute { #define __BIN_ATTR_RW(_name, _size) __BIN_ATTR(_name, \ (S_IWUSR | S_IRUGO), _name##_read, \ - _name##_write) + _name##_write, _size) #define __BIN_ATTR_NULL __ATTR_NULL -- cgit v1.2.3 From 183912d352a242a276a7877852f107459a13aff9 Mon Sep 17 00:00:00 2001 From: Sudeep KarkadaNagesha Date: Thu, 15 Aug 2013 14:01:40 +0100 Subject: of: move of_get_cpu_node implementation to DT core library This patch moves the generalized implementation of of_get_cpu_node from PowerPC to DT core library, thereby adding support for retrieving cpu node for a given logical cpu index on any architecture. The CPU subsystem can now use this function to assign of_node in the cpu device while registering CPUs. It is recommended to use these helper function only in pre-SMP/early initialisation stages to retrieve CPU device node pointers in logical ordering. Once the cpu devices are registered, it can be retrieved easily from cpu device of_node which avoids unnecessary parsing and matching. Cc: Benjamin Herrenschmidt Cc: Grant Likely Acked-by: Rob Herring Signed-off-by: Sudeep KarkadaNagesha --- include/linux/cpu.h | 1 + include/linux/of.h | 7 +++++++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index ab0eade73039..3dfed2b9ae2e 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -28,6 +28,7 @@ struct cpu { extern int register_cpu(struct cpu *cpu, int num); extern struct device *get_cpu_device(unsigned cpu); extern bool cpu_is_hotpluggable(unsigned cpu); +extern bool arch_match_cpu_phys_id(int cpu, u64 phys_id); extern int cpu_add_dev_attr(struct device_attribute *attr); extern void cpu_remove_dev_attr(struct device_attribute *attr); diff --git a/include/linux/of.h b/include/linux/of.h index 1fd08ca23106..c0bb2f188048 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -266,6 +266,7 @@ extern int of_device_is_available(const struct device_node *device); extern const void *of_get_property(const struct device_node *node, const char *name, int *lenp); +extern struct device_node *of_get_cpu_node(int cpu, unsigned int *thread); #define for_each_property_of_node(dn, pp) \ for (pp = dn->properties; pp != NULL; pp = pp->next) @@ -459,6 +460,12 @@ static inline const void *of_get_property(const struct device_node *node, return NULL; } +static inline struct device_node *of_get_cpu_node(int cpu, + unsigned int *thread) +{ + return NULL; +} + static inline int of_property_read_u64(const struct device_node *np, const char *propname, u64 *out_value) { -- cgit v1.2.3 From bd00860e960e52658cebfd65eeb4748ed6ff039f Mon Sep 17 00:00:00 2001 From: Sudeep KarkadaNagesha Date: Thu, 18 Jul 2013 11:22:04 +0100 Subject: of/device: add helper to get cpu device node from logical cpu index Multiple drivers need to get the cpu device node from the cpu logical index and then access the of_node. This patch adds helper function to fetch the device node directly. Acked-by: Rob Herring Signed-off-by: Sudeep KarkadaNagesha --- include/linux/of_device.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_device.h b/include/linux/of_device.h index 9d27475feec1..82ce324fdce7 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -1,6 +1,7 @@ #ifndef _LINUX_OF_DEVICE_H #define _LINUX_OF_DEVICE_H +#include #include #include /* temporary until merge */ @@ -43,6 +44,15 @@ static inline void of_device_node_put(struct device *dev) of_node_put(dev->of_node); } +static inline struct device_node *of_cpu_device_node_get(int cpu) +{ + struct device *cpu_dev; + cpu_dev = get_cpu_device(cpu); + if (!cpu_dev) + return NULL; + return of_node_get(cpu_dev->of_node); +} + #else /* CONFIG_OF */ static inline int of_driver_match_device(struct device *dev, @@ -67,6 +77,11 @@ static inline const struct of_device_id *of_match_device( { return NULL; } + +static inline struct device_node *of_cpu_device_node_get(int cpu) +{ + return NULL; +} #endif /* CONFIG_OF */ #endif /* _LINUX_OF_DEVICE_H */ -- cgit v1.2.3 From 37a7bd6255b415afe197489b5cd1f9568a7ae058 Mon Sep 17 00:00:00 2001 From: Seth Jennings Date: Tue, 20 Aug 2013 12:13:01 -0500 Subject: drivers: base: reduce add_memory_section() for boot-time only Now that add_memory_section() is only called from boot time, reduce the logic and remove the enum. Signed-off-by: Seth Jennings Signed-off-by: Greg Kroah-Hartman --- include/linux/memory.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index 85c31a8e2904..4c89fb0c8f4c 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -125,7 +125,6 @@ extern struct memory_block *find_memory_block_hinted(struct mem_section *, struct memory_block *); extern struct memory_block *find_memory_block(struct mem_section *); #define CONFIG_MEM_BLOCK_SIZE (PAGES_PER_SECTION< Date: Tue, 20 Aug 2013 16:05:05 -0500 Subject: drivers: base: use standard device online/offline for state change There are two ways to set the online/offline state for a memory block: echo 0|1 > online and echo online|online_kernel|online_movable|offline > state. The state attribute can online a memory block with extra data, the "online type", where the online attribute uses a default online type of ONLINE_KEEP, same as echo online > state. Currently there is a state_mutex that provides consistency between the memory block state and the underlying memory. The problem is that this code does a lot of things that the common device layer can do for us, such as the serialization of the online/offline handlers using the device lock, setting the dev->offline field, and calling kobject_uevent(). This patch refactors the online/offline code to allow the common device_[online|offline] functions to be used. The result is a simpler and more common code path for the two state setting mechanisms. It also removes the state_mutex from the struct memory_block as the memory block device lock provides the state consistency. No functional change is intended by this patch. Signed-off-by: Seth Jennings Signed-off-by: Greg Kroah-Hartman --- include/linux/memory.h | 13 +++---------- 1 file changed, 3 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index 4c89fb0c8f4c..9a6bbf76452d 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -25,16 +25,9 @@ struct memory_block { unsigned long start_section_nr; unsigned long end_section_nr; - unsigned long state; - int section_count; - - /* - * This serializes all state change requests. It isn't - * held during creation because the control files are - * created long after the critical areas during - * initialization. - */ - struct mutex state_mutex; + unsigned long state; /* serialized by the dev->lock */ + int section_count; /* serialized by mem_sysfs_mutex */ + int online_type; /* for passing data to online routine */ int phys_device; /* to which fru does this belong? */ void *hw; /* optional pointer to fw/hw data */ int (*phys_callback)(struct memory_block *); -- cgit v1.2.3 From 3e9b2bae8369661070622d05570cbcdfa01770e6 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 21 Aug 2013 13:47:50 -0700 Subject: sysfs: add sysfs_create/remove_groups() These functions are being open-coded in 3 different places in the driver core, and other driver subsystems will want to start doing this as well, so move it to the sysfs core to keep it all in one place, where we know it is written properly. Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 0f04958623d7..4dbb9d31daa8 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -215,10 +215,14 @@ void sysfs_delete_link(struct kobject *dir, struct kobject *targ, int __must_check sysfs_create_group(struct kobject *kobj, const struct attribute_group *grp); +int __must_check sysfs_create_groups(struct kobject *kobj, + const struct attribute_group **groups); int sysfs_update_group(struct kobject *kobj, const struct attribute_group *grp); void sysfs_remove_group(struct kobject *kobj, const struct attribute_group *grp); +void sysfs_remove_groups(struct kobject *kobj, + const struct attribute_group **groups); int sysfs_add_file_to_group(struct kobject *kobj, const struct attribute *attr, const char *group); void sysfs_remove_file_from_group(struct kobject *kobj, -- cgit v1.2.3 From 5da5c9c899dc456d6eb43aae3e8d4e853b7f5306 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 21 Aug 2013 17:47:05 -0700 Subject: sysfs: fix up minor coding style issues in sysfs.h As long as we are cleaning up sysfs coding style issues, don't forget the main sysfs.h file, so fix up the space issues there as well. Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 4dbb9d31daa8..a864b8d918ee 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -51,9 +51,9 @@ do { \ static struct lock_class_key __key; \ \ (attr)->key = &__key; \ -} while(0) +} while (0) #else -#define sysfs_attr_init(attr) do {} while(0) +#define sysfs_attr_init(attr) do {} while (0) #endif struct attribute_group { @@ -69,7 +69,7 @@ struct attribute_group { * for examples.. */ -#define __ATTR(_name,_mode,_show,_store) { \ +#define __ATTR(_name, _mode, _show, _store) { \ .attr = {.name = __stringify(_name), .mode = _mode }, \ .show = _show, \ .store = _store, \ @@ -119,7 +119,7 @@ struct bin_attribute { void *private; ssize_t (*read)(struct file *, struct kobject *, struct bin_attribute *, char *, loff_t, size_t); - ssize_t (*write)(struct file *,struct kobject *, struct bin_attribute *, + ssize_t (*write)(struct file *, struct kobject *, struct bin_attribute *, char *, loff_t, size_t); int (*mmap)(struct file *, struct kobject *, struct bin_attribute *attr, struct vm_area_struct *vma); @@ -168,8 +168,8 @@ struct bin_attribute bin_attr_##_name = __BIN_ATTR_RO(_name, _size) struct bin_attribute bin_attr_##_name = __BIN_ATTR_RW(_name, _size) struct sysfs_ops { - ssize_t (*show)(struct kobject *, struct attribute *,char *); - ssize_t (*store)(struct kobject *,struct attribute *,const char *, size_t); + ssize_t (*show)(struct kobject *, struct attribute *, char *); + ssize_t (*store)(struct kobject *, struct attribute *, const char *, size_t); const void *(*namespace)(struct kobject *, const struct attribute *); }; -- cgit v1.2.3 From f477b7fb13df2b843997559ff34e87d054ba6538 Mon Sep 17 00:00:00 2001 From: wangyuhang Date: Sun, 11 Aug 2013 18:15:17 +0800 Subject: spi: DUAL and QUAD support fix the previous patch some mistake below: 1. DT in slave node, use "spi-tx-nbits = <1/2/4>" in place of using "spi-tx-dual, spi-tx-quad" directly, same to rx. So correct the previous way to get the property in @of_register_spi_devices(). 2. Change the value of transfer bit macro(SPI_NBITS_SINGLE, SPI_NBITS_DUAL SPI_NBITS_QUAD) to 0x01, 0x02 and 0x04 to match the actual wires. 3. Add the following check (1)keep the tx_nbits and rx_nbits in spi_transfer is not beyond the single, dual and quad. (2)keep tx_nbits and rx_nbits are contained by @spi_device->mode example: if @spi_device->mode = DUAL, then tx/rx_nbits can not be set to QUAD(SPI_NBITS_QUAD) (3)if "@spi_device->mode & SPI_3WIRE", then tx/rx_nbits should be in single(SPI_NBITS_SINGLE) Signed-off-by: wangyuhang Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index cdf668156154..ccd7840c4507 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -74,7 +74,7 @@ struct spi_device { struct spi_master *master; u32 max_speed_hz; u8 chip_select; - u8 mode; + u16 mode; #define SPI_CPHA 0x01 /* clock phase */ #define SPI_CPOL 0x02 /* clock polarity */ #define SPI_MODE_0 (0|0) /* (original MicroWire) */ @@ -87,6 +87,10 @@ struct spi_device { #define SPI_LOOP 0x20 /* loopback mode */ #define SPI_NO_CS 0x40 /* 1 dev/bus, no chipselect */ #define SPI_READY 0x80 /* slave pulls low to pause */ +#define SPI_TX_DUAL 0x100 /* transmit with 2 wires */ +#define SPI_TX_QUAD 0x200 /* transmit with 4 wires */ +#define SPI_RX_DUAL 0x400 /* receive with 2 wires */ +#define SPI_RX_QUAD 0x800 /* receive with 4 wires */ u8 bits_per_word; int irq; void *controller_state; @@ -454,6 +458,10 @@ extern struct spi_master *spi_busnum_to_master(u16 busnum); * @rx_buf: data to be read (dma-safe memory), or NULL * @tx_dma: DMA address of tx_buf, if @spi_message.is_dma_mapped * @rx_dma: DMA address of rx_buf, if @spi_message.is_dma_mapped + * @tx_nbits: number of bits used for writting. If 0 the default + * (SPI_NBITS_SINGLE) is used. + * @rx_nbits: number of bits used for reading. If 0 the default + * (SPI_NBITS_SINGLE) is used. * @len: size of rx and tx buffers (in bytes) * @speed_hz: Select a speed other than the device default for this * transfer. If 0 the default (from @spi_device) is used. @@ -508,6 +516,11 @@ extern struct spi_master *spi_busnum_to_master(u16 busnum); * by the results of previous messages and where the whole transaction * ends when the chipselect goes intactive. * + * When SPI can transfer in 1x,2x or 4x. It can get this tranfer information + * from device through @tx_nbits and @rx_nbits. In Bi-direction, these + * two should both be set. User can set transfer mode with SPI_NBITS_SINGLE(1x) + * SPI_NBITS_DUAL(2x) and SPI_NBITS_QUAD(4x) to support these three transfer. + * * The code that submits an spi_message (and its spi_transfers) * to the lower layers is responsible for managing its memory. * Zero-initialize every field you don't set up explicitly, to @@ -528,6 +541,11 @@ struct spi_transfer { dma_addr_t rx_dma; unsigned cs_change:1; + u8 tx_nbits; + u8 rx_nbits; +#define SPI_NBITS_SINGLE 0x01 /* 1bit transfer */ +#define SPI_NBITS_DUAL 0x02 /* 2bits transfer */ +#define SPI_NBITS_QUAD 0x04 /* 4bits transfer */ u8 bits_per_word; u16 delay_usecs; u32 speed_hz; @@ -875,7 +893,7 @@ struct spi_board_info { /* mode becomes spi_device.mode, and is essential for chips * where the default of SPI_CS_HIGH = 0 is wrong. */ - u8 mode; + u16 mode; /* ... may need additional spi_device chip config data here. * avoid stuff protocol drivers can set; but include stuff -- cgit v1.2.3 From d79ff142624e1be080ad8d09101f7004d79c36e1 Mon Sep 17 00:00:00 2001 From: Martin Peschke Date: Thu, 22 Aug 2013 17:45:36 +0200 Subject: [SCSI] zfcp: fix lock imbalance by reworking request queue locking This patch adds wait_event_interruptible_lock_irq_timeout(), which is a straight-forward descendant of wait_event_interruptible_timeout() and wait_event_interruptible_lock_irq(). The zfcp driver used to call wait_event_interruptible_timeout() in combination with some intricate and error-prone locking. Using wait_event_interruptible_lock_irq_timeout() as a replacement nicely cleans up that locking. This rework removes a situation that resulted in a locking imbalance in zfcp_qdio_sbal_get(): BUG: workqueue leaked lock or atomic: events/1/0xffffff00/10 last function: zfcp_fc_wka_port_offline+0x0/0xa0 [zfcp] It was introduced by commit c2af7545aaff3495d9bf9a7608c52f0af86fb194 "[SCSI] zfcp: Do not wait for SBALs on stopped queue", which had a new code path related to ZFCP_STATUS_ADAPTER_QDIOUP that took an early exit without a required lock being held. The problem occured when a special, non-SCSI I/O request was being submitted in process context, when the adapter's queues had been torn down. In this case the bug surfaced when the Fibre Channel port connection for a well-known address was closed during a concurrent adapter shut-down procedure, which is a rare constellation. This patch also fixes these warnings from the sparse tool (make C=1): drivers/s390/scsi/zfcp_qdio.c:224:12: warning: context imbalance in 'zfcp_qdio_sbal_check' - wrong count at exit drivers/s390/scsi/zfcp_qdio.c:244:5: warning: context imbalance in 'zfcp_qdio_sbal_get' - unexpected unlock Last but not least, we get rid of that crappy lock-unlock-lock sequence at the beginning of the critical section. It is okay to call zfcp_erp_adapter_reopen() with req_q_lock held. Reported-by: Mikulas Patocka Reported-by: Heiko Carstens Signed-off-by: Martin Peschke Cc: stable@vger.kernel.org #2.6.35+ Signed-off-by: Steffen Maier Signed-off-by: James Bottomley --- include/linux/wait.h | 57 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 57 insertions(+) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index f487a4750b7f..a67fc1635592 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -811,6 +811,63 @@ do { \ __ret; \ }) +#define __wait_event_interruptible_lock_irq_timeout(wq, condition, \ + lock, ret) \ +do { \ + DEFINE_WAIT(__wait); \ + \ + for (;;) { \ + prepare_to_wait(&wq, &__wait, TASK_INTERRUPTIBLE); \ + if (condition) \ + break; \ + if (signal_pending(current)) { \ + ret = -ERESTARTSYS; \ + break; \ + } \ + spin_unlock_irq(&lock); \ + ret = schedule_timeout(ret); \ + spin_lock_irq(&lock); \ + if (!ret) \ + break; \ + } \ + finish_wait(&wq, &__wait); \ +} while (0) + +/** + * wait_event_interruptible_lock_irq_timeout - sleep until a condition gets true or a timeout elapses. + * The condition is checked under the lock. This is expected + * to be called with the lock taken. + * @wq: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * @lock: a locked spinlock_t, which will be released before schedule() + * and reacquired afterwards. + * @timeout: timeout, in jiffies + * + * The process is put to sleep (TASK_INTERRUPTIBLE) until the + * @condition evaluates to true or signal is received. The @condition is + * checked each time the waitqueue @wq is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + * + * This is supposed to be called while holding the lock. The lock is + * dropped before going to sleep and is reacquired afterwards. + * + * The function returns 0 if the @timeout elapsed, -ERESTARTSYS if it + * was interrupted by a signal, and the remaining jiffies otherwise + * if the condition evaluated to true before the timeout elapsed. + */ +#define wait_event_interruptible_lock_irq_timeout(wq, condition, lock, \ + timeout) \ +({ \ + int __ret = timeout; \ + \ + if (!(condition)) \ + __wait_event_interruptible_lock_irq_timeout( \ + wq, condition, lock, __ret); \ + __ret; \ +}) + /* * These are the old interfaces to sleep waiting for an event. -- cgit v1.2.3 From a58674ff8383f5b8f6a77f03c48f6a47840b9325 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 22 Aug 2013 11:24:44 +0800 Subject: PCI: Simplify pcie_bus_configure_settings() interface Based on a patch by Jon Mason (see URL below). All users of pcie_bus_configure_settings() pass arguments of the form "bus, bus->self->pcie_mpss". The "mpss" argument is redundant since we can easily look it up internally. In addition, all callers check "bus->self" for NULL, which we can also do internally. This patch simplifies the interface and the callers. No functional change. Reference: http://lkml.kernel.org/r/1317048850-30728-2-git-send-email-mason@myri.com Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 0fd1f1582fa1..57062b7a20ba 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -675,7 +675,7 @@ struct pci_driver { /* these external functions are only available when PCI support is enabled */ #ifdef CONFIG_PCI -void pcie_bus_configure_settings(struct pci_bus *bus, u8 smpss); +void pcie_bus_configure_settings(struct pci_bus *bus); enum pcie_bus_config_types { PCIE_BUS_TUNE_OFF, -- cgit v1.2.3 From 5ea80f76a56605a190a7ea16846c82aa63dbd0aa Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 22 Aug 2013 09:13:06 -0700 Subject: Revert "x86 get_unmapped_area(): use proper mmap base for bottom-up direction" This reverts commit df54d6fa54275ce59660453e29d1228c2b45a826. The commit isn't necessarily wrong, but because it recalculates the random mmap_base every time, it seems to confuse user memory allocators that expect contiguous mmap allocations even when the mmap address isn't specified. In particular, the MATLAB Java runtime seems to be unhappy. See https://bugzilla.kernel.org/show_bug.cgi?id=60774 So we'll want to apply the random offset only once, and Radu has a patch for that. Revert this older commit in order to apply the other one. Reported-by: Jeff Shorey Cc: Radu Caragea Cc: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index e9995eb5985c..078066daffd4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -314,7 +314,6 @@ struct nsproxy; struct user_namespace; #ifdef CONFIG_MMU -extern unsigned long mmap_legacy_base(void); extern void arch_pick_mmap_layout(struct mm_struct *mm); extern unsigned long arch_get_unmapped_area(struct file *, unsigned long, unsigned long, -- cgit v1.2.3 From 41aacc1eea645c99edbe8fbcf78a97dc9b862adc Mon Sep 17 00:00:00 2001 From: Radu Caragea Date: Wed, 21 Aug 2013 20:55:59 +0300 Subject: x86 get_unmapped_area: Access mmap_legacy_base through mm_struct member This is the updated version of df54d6fa5427 ("x86 get_unmapped_area(): use proper mmap base for bottom-up direction") that only randomizes the mmap base address once. Signed-off-by: Radu Caragea Reported-and-tested-by: Jeff Shorey Cc: Andrew Morton Cc: Michel Lespinasse Cc: Oleg Nesterov Cc: Rik van Riel Cc: Ingo Molnar Cc: Adrian Sendroiu Cc: Greg KH Cc: Kamal Mostafa Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index fb425aa16c01..faf4b7c1ad12 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -332,6 +332,7 @@ struct mm_struct { unsigned long pgoff, unsigned long flags); #endif unsigned long mmap_base; /* base of mmap area */ + unsigned long mmap_legacy_base; /* base of mmap area in bottom-up allocations */ unsigned long task_size; /* size of task vm space */ unsigned long highest_vm_end; /* highest vma end address */ pgd_t * pgd; -- cgit v1.2.3 From 3e1026b3fa2f61d33ce6a9e42a22398cc4ab8e58 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 22 Aug 2013 10:25:34 -0700 Subject: sysfs.h: remove attr_name() macro Gotta love a macro that doesn't reduce the typing you have to do. Also, only the driver core, and one network driver uses this. The driver core functions will be going away soon, and I'll convert the network driver soon to not need this as well, so delete it for now before anyone else gets some bright ideas and wants to use it. Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index a864b8d918ee..b5a9d9b26bd4 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -108,8 +108,6 @@ static const struct attribute_group _name##_group = { \ }; \ __ATTRIBUTE_GROUPS(_name) -#define attr_name(_attr) (_attr).attr.name - struct file; struct vm_area_struct; -- cgit v1.2.3 From 699c1985587aad3432c5ae19801efb4186db8b7a Mon Sep 17 00:00:00 2001 From: Sebastian Ott Date: Tue, 20 Aug 2013 16:41:02 +0200 Subject: PCI: Add pcibios_pm_ops for optional arch-specific hibernate functionality Platforms may want to provide architecture-specific functionality when a PCI device is doing a hibernate transition. Add a weak symbol pcibios_pm_ops that architectures can override to do so. [bhelgaas: fold in return value checks from v2 patch] Signed-off-by: Sebastian Ott Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 0fd1f1582fa1..89ed12379f2f 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1648,6 +1648,10 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, int pcibios_add_device(struct pci_dev *dev); void pcibios_release_device(struct pci_dev *dev); +#ifdef CONFIG_HIBERNATE_CALLBACKS +extern struct dev_pm_ops pcibios_pm_ops; +#endif + #ifdef CONFIG_PCI_MMCONFIG void __init pci_mmcfg_early_init(void); void __init pci_mmcfg_late_init(void); -- cgit v1.2.3 From 4a5a8aa6c966eafc106543bd955ae388230420e5 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Wed, 21 Aug 2013 21:09:47 -0700 Subject: ipv4: expose IPV4_DEVCONF IP sends device configuration (see inet_fill_link_af) as an array in the netlink information, but the indices in that array are not exposed to userspace through any current santized header file. It was available back in 2.6.32 (in /usr/include/linux/sysctl.h) but was broken by: commit 02291680ffba92e5b5865bc0c5e7d1f3056b80ec Author: Eric W. Biederman Date: Sun Feb 14 03:25:51 2010 +0000 net ipv4: Decouple ipv4 interface parameters from binary sysctl numbers Eric was solving the sysctl problem but then the indices were re-exposed by a later addition of devconf support for IPV4 commit 9f0f7272ac9506f4c8c05cc597b7e376b0b9f3e4 Author: Thomas Graf Date: Tue Nov 16 04:32:48 2010 +0000 ipv4: AF_INET link address family Putting them in /usr/include/linux/ip.h seemed the logical match for the DEVCONF_ definitions for IPV6 in /usr/include/linux/ip6.h Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 34 +--------------------------------- 1 file changed, 1 insertion(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index b99cd23f3474..79640e015a86 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -5,45 +5,13 @@ #include #include +#include #include #include #include #include #include -enum -{ - IPV4_DEVCONF_FORWARDING=1, - IPV4_DEVCONF_MC_FORWARDING, - IPV4_DEVCONF_PROXY_ARP, - IPV4_DEVCONF_ACCEPT_REDIRECTS, - IPV4_DEVCONF_SECURE_REDIRECTS, - IPV4_DEVCONF_SEND_REDIRECTS, - IPV4_DEVCONF_SHARED_MEDIA, - IPV4_DEVCONF_RP_FILTER, - IPV4_DEVCONF_ACCEPT_SOURCE_ROUTE, - IPV4_DEVCONF_BOOTP_RELAY, - IPV4_DEVCONF_LOG_MARTIANS, - IPV4_DEVCONF_TAG, - IPV4_DEVCONF_ARPFILTER, - IPV4_DEVCONF_MEDIUM_ID, - IPV4_DEVCONF_NOXFRM, - IPV4_DEVCONF_NOPOLICY, - IPV4_DEVCONF_FORCE_IGMP_VERSION, - IPV4_DEVCONF_ARP_ANNOUNCE, - IPV4_DEVCONF_ARP_IGNORE, - IPV4_DEVCONF_PROMOTE_SECONDARIES, - IPV4_DEVCONF_ARP_ACCEPT, - IPV4_DEVCONF_ARP_NOTIFY, - IPV4_DEVCONF_ACCEPT_LOCAL, - IPV4_DEVCONF_SRC_VMARK, - IPV4_DEVCONF_PROXY_ARP_PVLAN, - IPV4_DEVCONF_ROUTE_LOCALNET, - __IPV4_DEVCONF_MAX -}; - -#define IPV4_DEVCONF_MAX (__IPV4_DEVCONF_MAX - 1) - struct ipv4_devconf { void *sysctl; int data[IPV4_DEVCONF_MAX]; -- cgit v1.2.3 From f1bc1e4c44b1b78fe34431936c60759b5aad5e3f Mon Sep 17 00:00:00 2001 From: Aaron Lu Date: Fri, 23 Aug 2013 10:17:54 +0800 Subject: ata: acpi: rework the ata acpi bind support Binding ACPI handle to SCSI device has several drawbacks, namely: 1 During ATA device initialization time, ACPI handle will be needed while SCSI devices are not created yet. So each time ACPI handle is needed, instead of retrieving the handle by ACPI_HANDLE macro, a namespace scan is performed to find the handle for the corresponding ATA device. This is inefficient, and also expose a restriction on calling path not holding any lock. 2 The binding to SCSI device tree makes code complex, while at the same time doesn't bring us any benefit. All ACPI handlings are still done in ATA module, not in SCSI. Rework the ATA ACPI binding code to bind ACPI handle to ATA transport devices(ATA port and ATA device). The binding needs to be done only once, since the ATA transport devices do not go away with hotplug. And due to this, the flush_work call in hotplug handler for ATA bay is no longer needed. Tested on an Intel test platform for binding and runtime power off for ODD(ZPODD) and hard disk; on an ASUS S400C for binding and normal boot and S3, where its SATA port node has _SDD and _GTF control methods when configured as an AHCI controller and its PATA device node has _GTF control method when configured as an IDE controller. SATA PMP binding and ATA hotplug is not tested. Signed-off-by: Aaron Lu Tested-by: Dirk Griesbach Signed-off-by: Tejun Heo --- include/linux/libata.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 283d66bc603c..3198617905e1 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1244,8 +1244,6 @@ int ata_acpi_stm(struct ata_port *ap, const struct ata_acpi_gtm *stm); int ata_acpi_gtm(struct ata_port *ap, struct ata_acpi_gtm *stm); unsigned long ata_acpi_gtm_xfermask(struct ata_device *dev, const struct ata_acpi_gtm *gtm); -acpi_handle ata_ap_acpi_handle(struct ata_port *ap); -acpi_handle ata_dev_acpi_handle(struct ata_device *dev); int ata_acpi_cbl_80wire(struct ata_port *ap, const struct ata_acpi_gtm *gtm); #else static inline const struct ata_acpi_gtm *ata_acpi_init_gtm(struct ata_port *ap) -- cgit v1.2.3 From abec1a806e0c3cf168999667d5fb6218398ef12a Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Fri, 23 Aug 2013 19:01:58 +0000 Subject: percpu: Make __verify_pcu_ptr handle per cpu pointers to arrays __verify_pcpu_ptr() will cause a compilation failure if the type of the pointer is a pointer to a fixed array of objects. Adding zero to the pointer converts the type of pointer to that pointing to a single object of the array. Signed-off-by: Christoph Lameter Signed-off-by: Tejun Heo --- include/linux/percpu-defs.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index 27ef6b190ea6..57e890abe1f0 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -22,9 +22,12 @@ * Macro which verifies @ptr is a percpu pointer without evaluating * @ptr. This is to be used in percpu accessors to verify that the * input parameter is a percpu pointer. + * + * + 0 is required in order to convert the pointer type from a + * potential array type to a pointer to a single item of the array. */ #define __verify_pcpu_ptr(ptr) do { \ - const void __percpu *__vpp_verify = (typeof(ptr))NULL; \ + const void __percpu *__vpp_verify = (typeof((ptr) + 0))NULL; \ (void)__vpp_verify; \ } while (0) -- cgit v1.2.3 From a65fcce75a75c0d41b938f86d09d42b6f1733309 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 23 Aug 2013 15:02:01 -0700 Subject: sysfs: create __ATTR_WO() This creates the macro __ATTR_WO() for write-only attributes, instead of having to "open define" them. Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index b5a9d9b26bd4..69c1ff003628 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -80,6 +80,11 @@ struct attribute_group { .show = _name##_show, \ } +#define __ATTR_WO(_name) { \ + .attr = { .name = __stringify(_name), .mode = S_IWUSR }, \ + .store = _name##_store, \ +} + #define __ATTR_RW(_name) __ATTR(_name, (S_IWUSR | S_IRUGO), \ _name##_show, _name##_store) -- cgit v1.2.3 From 1130c55c757660ac83bd2de220f08580c56b6855 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 23 Aug 2013 15:02:56 -0700 Subject: driver core: create write-only attribute macros for devices and drivers This creates the macros DRIVER_ATTR_WO() and DEVICE_ATTR_WO() for write-only attributes for drivers and devices. Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 26e23b22ed0a..0ed94b5f67fc 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -277,6 +277,8 @@ struct driver_attribute { struct driver_attribute driver_attr_##_name = __ATTR_RW(_name) #define DRIVER_ATTR_RO(_name) \ struct driver_attribute driver_attr_##_name = __ATTR_RO(_name) +#define DRIVER_ATTR_WO(_name) \ + struct driver_attribute driver_attr_##_name = __ATTR_WO(_name) extern int __must_check driver_create_file(struct device_driver *driver, const struct driver_attribute *attr); @@ -534,6 +536,8 @@ ssize_t device_store_bool(struct device *dev, struct device_attribute *attr, struct device_attribute dev_attr_##_name = __ATTR_RW(_name) #define DEVICE_ATTR_RO(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RO(_name) +#define DEVICE_ATTR_WO(_name) \ + struct device_attribute dev_attr_##_name = __ATTR_WO(_name) #define DEVICE_ULONG_ATTR(_name, _mode, _var) \ struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, _mode, device_show_ulong, device_store_ulong), &(_var) } -- cgit v1.2.3 From 118b23022512eb2f41ce42db70dc0568d00be4ba Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 24 Aug 2013 12:08:17 -0400 Subject: cope with potentially long ->d_dname() output for shmem/hugetlb dynamic_dname() is both too much and too little for those - the output may be well in excess of 64 bytes dynamic_dname() assumes to be enough (thanks to ashmem feeding really long names to shmem_file_setup()) and vsnprintf() is an overkill for those guys. Signed-off-by: Al Viro --- include/linux/dcache.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index b90337c9d468..4a12532da8c4 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -336,6 +336,7 @@ extern int d_validate(struct dentry *, struct dentry *); * helper function for dentry_operations.d_dname() members */ extern char *dynamic_dname(struct dentry *, char *, int, const char *, ...); +extern char *simple_dname(struct dentry *, char *, int); extern char *__d_path(const struct path *, const struct path *, char *, int); extern char *d_absolute_path(const struct path *, char *, int); -- cgit v1.2.3 From 8be5ad9acb7c11b9d717bcdbe3d6de0dab081a39 Mon Sep 17 00:00:00 2001 From: Marc Carino Date: Sat, 24 Aug 2013 23:22:48 -0700 Subject: libata: Populate host-to-device FIS "auxiliary" field SATA 3.1 added an "auxiliary" field to the host-to-device FIS. Populate the host-to-device FIS with the new field via the taskfile struct. Signed-off-by: Marc Carino Signed-off-by: Tejun Heo --- include/linux/libata.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 3198617905e1..9b6ba196179f 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -555,6 +555,10 @@ struct ata_taskfile { u8 device; u8 command; /* IO operation */ + + u32 auxiliary; /* auxiliary field */ + /* from SATA 3.1 and */ + /* ATA-8 ACS-3 */ }; #ifdef CONFIG_ATA_SFF -- cgit v1.2.3 From 40fb59e75ad197a1c4ca2fbccef85432d8d103f8 Mon Sep 17 00:00:00 2001 From: Marc Carino Date: Sat, 24 Aug 2013 23:22:49 -0700 Subject: libata: Add H2D FIS "auxiliary" port flag Add a new port flag, ATA_FLAG_FPDMA_AUX, used to indicate support for transmission of the H2D FIS 'auxiliary' field. Signed-off-by: Marc Carino Signed-off-by: Tejun Heo --- include/linux/libata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 9b6ba196179f..578f98c3ff57 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -223,6 +223,7 @@ enum { ATA_FLAG_ACPI_SATA = (1 << 17), /* need native SATA ACPI layout */ ATA_FLAG_AN = (1 << 18), /* controller supports AN */ ATA_FLAG_PMP = (1 << 19), /* controller supports PMP */ + ATA_FLAG_FPDMA_AUX = (1 << 20), /* controller supports H2DFIS aux field */ ATA_FLAG_EM = (1 << 21), /* driver supports enclosure * management */ ATA_FLAG_SW_ACTIVITY = (1 << 22), /* driver supports sw activity -- cgit v1.2.3 From ed36911c747c18525691c0aa0fbe6b918c8eac19 Mon Sep 17 00:00:00 2001 From: Marc Carino Date: Sat, 24 Aug 2013 23:22:50 -0700 Subject: libata: Add support for SEND/RECEIVE FPDMA QUEUED Add support for the following ATA opcodes, which are present in SATA 3.1 and T13 ATA ACS-3: SEND FPDMA QUEUED RECEIVE FPDMA QUEUED Signed-off-by: Marc Carino Signed-off-by: Tejun Heo --- include/linux/ata.h | 21 +++++++++++++++++++++ include/linux/libata.h | 4 ++++ 2 files changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index f63fb1afc5cc..bf4c69ca76df 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -239,6 +239,8 @@ enum { ATA_CMD_WRITE_QUEUED_FUA_EXT = 0x3E, ATA_CMD_FPDMA_READ = 0x60, ATA_CMD_FPDMA_WRITE = 0x61, + ATA_CMD_FPDMA_SEND = 0x64, + ATA_CMD_FPDMA_RECV = 0x65, ATA_CMD_PIO_READ = 0x20, ATA_CMD_PIO_READ_EXT = 0x24, ATA_CMD_PIO_WRITE = 0x30, @@ -293,8 +295,13 @@ enum { /* marked obsolete in the ATA/ATAPI-7 spec */ ATA_CMD_RESTORE = 0x10, + /* Subcmds for ATA_CMD_FPDMA_SEND */ + ATA_SUBCMD_FPDMA_SEND_DSM = 0x00, + ATA_SUBCMD_FPDMA_SEND_WR_LOG_DMA_EXT = 0x02, + /* READ_LOG_EXT pages */ ATA_LOG_SATA_NCQ = 0x10, + ATA_LOG_NCQ_SEND_RECV = 0x13, ATA_LOG_SATA_ID_DEV_DATA = 0x30, ATA_LOG_SATA_SETTINGS = 0x08, ATA_LOG_DEVSLP_OFFSET = 0x30, @@ -305,6 +312,15 @@ enum { ATA_LOG_DEVSLP_VALID = 0x07, ATA_LOG_DEVSLP_VALID_MASK = 0x80, + /* NCQ send and receive log */ + ATA_LOG_NCQ_SEND_RECV_SUBCMDS_OFFSET = 0x00, + ATA_LOG_NCQ_SEND_RECV_SUBCMDS_DSM = (1 << 0), + ATA_LOG_NCQ_SEND_RECV_DSM_OFFSET = 0x04, + ATA_LOG_NCQ_SEND_RECV_DSM_TRIM = (1 << 0), + ATA_LOG_NCQ_SEND_RECV_RD_LOG_OFFSET = 0x08, + ATA_LOG_NCQ_SEND_RECV_WR_LOG_OFFSET = 0x0C, + ATA_LOG_NCQ_SEND_RECV_SIZE = 0x10, + /* READ/WRITE LONG (obsolete) */ ATA_CMD_READ_LONG = 0x22, ATA_CMD_READ_LONG_ONCE = 0x23, @@ -772,6 +788,11 @@ static inline int ata_id_rotation_rate(const u16 *id) return val; } +static inline bool ata_id_has_ncq_send_and_recv(const u16 *id) +{ + return id[ATA_ID_SATA_CAPABILITY_2] & BIT(6); +} + static inline bool ata_id_has_trim(const u16 *id) { if (ata_id_major_version(id) >= 7 && diff --git a/include/linux/libata.h b/include/linux/libata.h index 578f98c3ff57..a988c2d7d0e8 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -172,6 +172,7 @@ enum { ATA_DFLAG_DUBIOUS_XFER = (1 << 16), /* data transfer not verified */ ATA_DFLAG_NO_UNLOAD = (1 << 17), /* device doesn't support unload */ ATA_DFLAG_UNLOCK_HPA = (1 << 18), /* unlock HPA */ + ATA_DFLAG_NCQ_SEND_RECV = (1 << 19), /* device supports NCQ SEND and RECV */ ATA_DFLAG_INIT_MASK = (1 << 24) - 1, ATA_DFLAG_DETACH = (1 << 24), @@ -704,6 +705,9 @@ struct ata_device { /* DEVSLP Timing Variables from Identify Device Data Log */ u8 devslp_timing[ATA_LOG_DEVSLP_SIZE]; + /* NCQ send and receive log subcommand support */ + u8 ncq_send_recv_cmds[ATA_LOG_NCQ_SEND_RECV_SIZE]; + /* error history */ int spdn_cnt; /* ering is CLEAR_END, read comment above CLEAR_END */ -- cgit v1.2.3 From 87fb6c31b9ef9ccab9a822b01fc3911f026a29bb Mon Sep 17 00:00:00 2001 From: Marc Carino Date: Sat, 24 Aug 2013 23:22:51 -0700 Subject: libata: Add support for queued DSM TRIM Some new SSDs support the queued version of the DSM TRIM command. Let the driver use the new command if supported. Signed-off-by: Marc Carino Signed-off-by: Tejun Heo --- include/linux/libata.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index a988c2d7d0e8..0e23c26485f4 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1606,6 +1606,13 @@ static inline int ata_ncq_enabled(struct ata_device *dev) ATA_DFLAG_NCQ)) == ATA_DFLAG_NCQ; } +static inline bool ata_fpdma_dsm_supported(struct ata_device *dev) +{ + return (dev->flags & ATA_DFLAG_NCQ_SEND_RECV) && + (dev->ncq_send_recv_cmds[ATA_LOG_NCQ_SEND_RECV_DSM_OFFSET] & + ATA_LOG_NCQ_SEND_RECV_DSM_TRIM); +} + static inline void ata_qc_set_polling(struct ata_queued_cmd *qc) { qc->tf.ctl |= ATA_NIEN; -- cgit v1.2.3 From 35cf083619da5677f83e9a8eae813f0b413d7082 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 26 Aug 2013 18:40:56 -0400 Subject: cgroup: rename cgroup_css_from_dir() to css_from_dir() and update its syntax cgroup_css_from_dir() will grow another user. In preparation, make the following changes. * All css functions are prefixed with just "css_", rename it to css_from_dir(). * Take dentry * instead of file * as dentry is what ultimately identifies a cgroup and file may not always be available. Note that the function now checkes whether @dentry->d_inode is NULL as the caller now may specify a negative dentry. * Make it take cgroup_subsys * instead of integer subsys_id. This simplifies the function and allows specifying no subsystem for cgroup->dummy_css. * Make return section a bit less verbose. This patch doesn't introduce any behavior changes. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Kirill A. Shutemov Cc: Steven Rostedt Cc: Frederic Weisbecker Cc: Ingo Molnar --- include/linux/cgroup.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b685955d4b29..21ba29869eb8 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -903,7 +903,8 @@ bool css_is_ancestor(struct cgroup_subsys_state *cg, /* Get id and depth of css */ unsigned short css_id(struct cgroup_subsys_state *css); -struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id); +struct cgroup_subsys_state *css_from_dir(struct dentry *dentry, + struct cgroup_subsys *ss); #else /* !CONFIG_CGROUPS */ -- cgit v1.2.3 From 9fa4db334c7d9570aec7a5121e84fae99aae1d04 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 26 Aug 2013 18:40:56 -0400 Subject: cgroup: implement CFTYPE_NO_PREFIX When cgroup files are created, cgroup core automatically prepends the name of the subsystem as prefix. This patch adds CFTYPE_NO_ which disables the automatic prefix. This is to work around historical baggages and shouldn't be used for new files. This will be used to move "cgroup.event_control" from cgroup core to memcg. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Kirill A. Shutemov Cc: Glauber Costa --- include/linux/cgroup.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 21ba29869eb8..3561d305b1e0 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -411,6 +411,7 @@ enum { CFTYPE_ONLY_ON_ROOT = (1 << 0), /* only create on root cgrp */ CFTYPE_NOT_ON_ROOT = (1 << 1), /* don't create on root cgrp */ CFTYPE_INSANE = (1 << 2), /* don't create if sane_behavior */ + CFTYPE_NO_PREFIX = (1 << 3), /* (DON'T USE FOR NEW FILES) no subsys prefix */ }; #define MAX_CFTYPE_NAME 64 -- cgit v1.2.3 From c2b1df2eb42978073ec27c99cc199d20ae48b849 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Thu, 22 Aug 2013 11:39:16 -0700 Subject: Rename nsproxy.pid_ns to nsproxy.pid_ns_for_children nsproxy.pid_ns is *not* the task's pid namespace. The name should clarify that. This makes it more obvious that setns on a pid namespace is weird -- it won't change the pid namespace shown in procfs. Signed-off-by: Andy Lutomirski Reviewed-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/linux/nsproxy.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index 10e5947491c7..b4ec59d159ac 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -14,6 +14,10 @@ struct fs_struct; * A structure to contain pointers to all per-process * namespaces - fs (mount), uts, network, sysvipc, etc. * + * The pid namespace is an exception -- it's accessed using + * task_active_pid_ns. The pid namespace here is the + * namespace that children will use. + * * 'count' is the number of tasks holding a reference. * The count for each namespace, then, will be the number * of nsproxies pointing to it, not the number of tasks. @@ -27,7 +31,7 @@ struct nsproxy { struct uts_namespace *uts_ns; struct ipc_namespace *ipc_ns; struct mnt_namespace *mnt_ns; - struct pid_namespace *pid_ns; + struct pid_namespace *pid_ns_for_children; struct net *net_ns; }; extern struct nsproxy init_nsproxy; -- cgit v1.2.3 From f799878000c5a9a1e6a311dfd4faa50601dcb1f8 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 27 Aug 2013 17:24:49 -0700 Subject: sysfs: add sysfs_create/remove_groups for when SYSFS is not enabled We need these functions for when CONFIG_SYSFS=n. Reported-by: Fengguang Wu Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 69c1ff003628..e647a1aa0723 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -350,6 +350,11 @@ static inline int sysfs_create_group(struct kobject *kobj, return 0; } +static inline int sysfs_create_groups(struct kobject *kobj, + const struct attribute_group **groups) +{ +} + static inline int sysfs_update_group(struct kobject *kobj, const struct attribute_group *grp) { @@ -361,6 +366,11 @@ static inline void sysfs_remove_group(struct kobject *kobj, { } +static inline void sysfs_remove_groups(struct kobject *kobj, + const struct attribute_group **groups) +{ +} + static inline int sysfs_add_file_to_group(struct kobject *kobj, const struct attribute *attr, const char *group) { -- cgit v1.2.3 From 3159269ef484954985cbbf1ff89976f090a18b24 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 26 Aug 2013 09:58:30 +0200 Subject: debugfs: provide debugfs_create_x64() when disabled commit 15b0beaa332b3923cc ("Add x64 support to debugfs") added debugfs_create_x64(), but forgot to provide it when debugfs is disabled, causing problems when code tries to use it even then. Provide the appropriate static inline. Cc: Huang Ying Signed-off-by: Johannes Berg Signed-off-by: Greg Kroah-Hartman --- include/linux/debugfs.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index d68b4ea7343c..263489d0788d 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -192,6 +192,13 @@ static inline struct dentry *debugfs_create_x32(const char *name, umode_t mode, return ERR_PTR(-ENODEV); } +static inline struct dentry *debugfs_create_x64(const char *name, umode_t mode, + struct dentry *parent, + u64 *value) +{ + return ERR_PTR(-ENODEV); +} + static inline struct dentry *debugfs_create_size_t(const char *name, umode_t mode, struct dentry *parent, size_t *value) -- cgit v1.2.3 From 574979c617eb9593f8dfbb804da3f0e00f8bf28e Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 28 Aug 2013 09:51:41 -0700 Subject: sysfs: sysfs_create_groups returns a value. When I included the "empty" function for sysfs_create_groups() when CONFIG_SYSFS=n, I forgot to return a value for it, so things blew up the build. This patch fixes that, stupid me. Reported-by: kbuild test robot Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index e647a1aa0723..11baec7c9b26 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -353,6 +353,7 @@ static inline int sysfs_create_group(struct kobject *kobj, static inline int sysfs_create_groups(struct kobject *kobj, const struct attribute_group **groups) { + return 0; } static inline int sysfs_update_group(struct kobject *kobj, -- cgit v1.2.3 From 8ef2d6511f7eba89ef5fe41cc83008ae63368aa2 Mon Sep 17 00:00:00 2001 From: Dmitry Kasatkin Date: Tue, 27 Aug 2013 17:47:34 +0300 Subject: dev-core: fix build break when DEBUG is enabled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When DEBUG is defined, dev_dbg_ratelimited uses dynamic debug data structures even when CONFIG_DYNAMIC_DEBUG is not defined. It leads to build break. For example, when I try to use dev_dbg_ratelimited in USB code and CONFIG_USB_DEBUG is enabled, but CONFIG_DYNAMIC_DEBUG is not, I get: CC [M] drivers/usb/host/xhci-ring.o drivers/usb/host/xhci-ring.c: In function ‘xhci_queue_intr_tx’: drivers/usb/host/xhci-ring.c:3059:3: error: implicit declaration of function ‘DEFINE_DYNAMIC_DEBUG_METADATA’ [-Werror=implicit-function-declaration] drivers/usb/host/xhci-ring.c:3059:3: error: ‘descriptor’ undeclared (first use in this function) drivers/usb/host/xhci-ring.c:3059:3: note: each undeclared identifier is reported only once for each function it appears in drivers/usb/host/xhci-ring.c:3059:3: error: implicit declaration of function ‘__dynamic_pr_debug’ [-Werror=implicit-function-declaration] drivers/usb/host/xhci-ring.c: In function ‘xhci_queue_isoc_tx_prepare’: drivers/usb/host/xhci-ring.c:3847:3: error: ‘descriptor’ undeclared (first use in this function) cc1: some warnings being treated as errors make[2]: *** [drivers/usb/host/xhci-ring.o] Error 1 make[1]: *** [drivers/usb/host] Error 2 make: *** [drivers/usb/] Error 2 This patch separates definition for CONFIG_DYNAMIC_DEBUG and DEBUG cases. [Note, Sarah moved the comment above the macro to avoid checkpatch warnings.] Signed-off-by: Dmitry Kasatkin Signed-off-by: Sarah Sharp Acked-by: Greg Kroah-Hartman --- include/linux/device.h | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 22b546a58591..7d960d581e9c 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1099,7 +1099,8 @@ do { \ dev_level_ratelimited(dev_notice, dev, fmt, ##__VA_ARGS__) #define dev_info_ratelimited(dev, fmt, ...) \ dev_level_ratelimited(dev_info, dev, fmt, ##__VA_ARGS__) -#if defined(CONFIG_DYNAMIC_DEBUG) || defined(DEBUG) +#if defined(CONFIG_DYNAMIC_DEBUG) +/* descriptor check is first to prevent flooding with "callbacks suppressed" */ #define dev_dbg_ratelimited(dev, fmt, ...) \ do { \ static DEFINE_RATELIMIT_STATE(_rs, \ @@ -1108,8 +1109,17 @@ do { \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT) && \ __ratelimit(&_rs)) \ - __dynamic_pr_debug(&descriptor, pr_fmt(fmt), \ - ##__VA_ARGS__); \ + __dynamic_dev_dbg(&descriptor, dev, fmt, \ + ##__VA_ARGS__); \ +} while (0) +#elif defined(DEBUG) +#define dev_dbg_ratelimited(dev, fmt, ...) \ +do { \ + static DEFINE_RATELIMIT_STATE(_rs, \ + DEFAULT_RATELIMIT_INTERVAL, \ + DEFAULT_RATELIMIT_BURST); \ + if (__ratelimit(&_rs)) \ + dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__); \ } while (0) #else #define dev_dbg_ratelimited(dev, fmt, ...) \ -- cgit v1.2.3 From 0f8f2aaaab0b0f9c13635cb02e7d19bdaa9aa1bb Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 28 Aug 2013 18:13:26 -0700 Subject: Add new lockref infrastructure reference implementation This introduces a new "lockref" structure that supports the concept of lockless updates of reference counts that still honor an attached spinlock. NOTE! This reference implementation is not the optimized lockless version, rather it is the fallback implementation using standard spinlocks. The actual optimized versions will be merged into 3.12, but I wanted to get the infrastructure in place and document the new interfaces. [ Also note that this particular commit is drastically cut-down minimal version of the original patch by Waiman. In order to properly credit the original author I'm marking Waiman as the author here, but in the end this patch bears little resemblance to the patch by Waiman. So blame any errors on me editing things down to the point where I can introduce the infrastructure before the merge window for 3.12 actually opens. - Linus ] Signed-off-by: Waiman Long Signed-off-by: Linus Torvalds --- include/linux/lockref.h | 71 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 71 insertions(+) create mode 100644 include/linux/lockref.h (limited to 'include/linux') diff --git a/include/linux/lockref.h b/include/linux/lockref.h new file mode 100644 index 000000000000..01233e01627a --- /dev/null +++ b/include/linux/lockref.h @@ -0,0 +1,71 @@ +#ifndef __LINUX_LOCKREF_H +#define __LINUX_LOCKREF_H + +/* + * Locked reference counts. + * + * These are different from just plain atomic refcounts in that they + * are atomic with respect to the spinlock that goes with them. In + * particular, there can be implementations that don't actually get + * the spinlock for the common decrement/increment operations, but they + * still have to check that the operation is done semantically as if + * the spinlock had been taken (using a cmpxchg operation that covers + * both the lock and the count word, or using memory transactions, for + * example). + */ + +#include + +struct lockref { + spinlock_t lock; + unsigned int count; +}; + +/** + * lockref_get - Increments reference count unconditionally + * @lockcnt: pointer to lockref structure + * + * This operation is only valid if you already hold a reference + * to the object, so you know the count cannot be zero. + */ +static inline void lockref_get(struct lockref *lockref) +{ + spin_lock(&lockref->lock); + lockref->count++; + spin_unlock(&lockref->lock); +} + +/** + * lockref_get_not_zero - Increments count unless the count is 0 + * @lockcnt: pointer to lockref structure + * Return: 1 if count updated successfully or 0 if count is 0 + */ +static inline int lockref_get_not_zero(struct lockref *lockref) +{ + int retval = 0; + + spin_lock(&lockref->lock); + if (lockref->count) { + lockref->count++; + retval = 1; + } + spin_unlock(&lockref->lock); + return retval; +} + +/** + * lockref_put_or_lock - decrements count unless count <= 1 before decrement + * @lockcnt: pointer to lockref structure + * Return: 1 if count updated successfully or 0 if count <= 1 and lock taken + */ +static inline int lockref_put_or_lock(struct lockref *lockref) +{ + spin_lock(&lockref->lock); + if (lockref->count <= 1) + return 0; + lockref->count--; + spin_unlock(&lockref->lock); + return 1; +} + +#endif /* __LINUX_LOCKREF_H */ -- cgit v1.2.3 From 98474236f72e5a8b89c14cd7c74f0bb77a4b1a99 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 28 Aug 2013 18:24:59 -0700 Subject: vfs: make the dentry cache use the lockref infrastructure This just replaces the dentry count/lock combination with the lockref structure that contains both a count and a spinlock, and does the mechanical conversion to use the lockref infrastructure. There are no semantic changes here, it's purely syntactic. The reference lockref implementation uses the spinlock exactly the same way that the old dcache code did, and the bulk of this patch is just expanding the internal "d_count" use in the dcache code to use "d_lockref.count" instead. This is purely preparation for the real change to make the reference count updates be lockless during the 3.12 merge window. [ As with the previous commit, this is a rewritten version of a concept originally from Waiman, so credit goes to him, blame for any errors goes to me. Waiman's patch had some semantic differences for taking advantage of the lockless update in dget_parent(), while this patch is intentionally a pure search-and-replace change with no semantic changes. - Linus ] Signed-off-by: Waiman Long Signed-off-by: Linus Torvalds --- include/linux/dcache.h | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 4a12532da8c4..efdc94434c30 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -9,6 +9,7 @@ #include #include #include +#include struct nameidata; struct path; @@ -100,6 +101,8 @@ extern unsigned int full_name_hash(const unsigned char *, unsigned int); # endif #endif +#define d_lock d_lockref.lock + struct dentry { /* RCU lookup touched fields */ unsigned int d_flags; /* protected by d_lock */ @@ -112,8 +115,7 @@ struct dentry { unsigned char d_iname[DNAME_INLINE_LEN]; /* small names */ /* Ref lookup also touches following */ - unsigned int d_count; /* protected by d_lock */ - spinlock_t d_lock; /* per dentry lock */ + struct lockref d_lockref; /* per-dentry lock and refcount */ const struct dentry_operations *d_op; struct super_block *d_sb; /* The root of the dentry tree */ unsigned long d_time; /* used by d_revalidate */ @@ -318,7 +320,7 @@ static inline int __d_rcu_to_refcount(struct dentry *dentry, unsigned seq) assert_spin_locked(&dentry->d_lock); if (!read_seqcount_retry(&dentry->d_seq, seq)) { ret = 1; - dentry->d_count++; + dentry->d_lockref.count++; } return ret; @@ -326,7 +328,7 @@ static inline int __d_rcu_to_refcount(struct dentry *dentry, unsigned seq) static inline unsigned d_count(const struct dentry *dentry) { - return dentry->d_count; + return dentry->d_lockref.count; } /* validate "insecure" dentry pointer */ @@ -357,17 +359,14 @@ extern char *dentry_path(struct dentry *, char *, int); static inline struct dentry *dget_dlock(struct dentry *dentry) { if (dentry) - dentry->d_count++; + dentry->d_lockref.count++; return dentry; } static inline struct dentry *dget(struct dentry *dentry) { - if (dentry) { - spin_lock(&dentry->d_lock); - dget_dlock(dentry); - spin_unlock(&dentry->d_lock); - } + if (dentry) + lockref_get(&dentry->d_lockref); return dentry; } -- cgit v1.2.3 From 9efdd27678ef5e22c27c230a08a211b702768f3a Mon Sep 17 00:00:00 2001 From: Matthias Kaehlcke Date: Sun, 25 Aug 2013 17:54:13 +0200 Subject: regulator: Add devm_regulator_get_exclusive() Add a resource managed regulator_get_exclusive() Signed-off-by: Matthias Kaehlcke Signed-off-by: Mark Brown --- include/linux/regulator/consumer.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index e2bac6db4abc..91aca11198d8 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -137,6 +137,8 @@ struct regulator *__must_check devm_regulator_get(struct device *dev, const char *id); struct regulator *__must_check regulator_get_exclusive(struct device *dev, const char *id); +struct regulator *__must_check devm_regulator_get_exclusive(struct device *dev, + const char *id); struct regulator *__must_check regulator_get_optional(struct device *dev, const char *id); struct regulator *__must_check devm_regulator_get_optional(struct device *dev, -- cgit v1.2.3 From 5e33bc4165f3edd558d9633002465a95230effc1 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 28 Aug 2013 21:41:01 +0200 Subject: driver core / ACPI: Avoid device hot remove locking issues device_hotplug_lock is held around the acpi_bus_trim() call in acpi_scan_hot_remove() which generally removes devices (it removes ACPI device objects at least, but it may also remove "physical" device objects through .detach() callbacks of ACPI scan handlers). Thus, potentially, device sysfs attributes are removed under that lock and to remove those attributes it is necessary to hold the s_active references of their directory entries for writing. On the other hand, the execution of a .show() or .store() callback from a sysfs attribute is carried out with that attribute's s_active reference held for reading. Consequently, if any device sysfs attribute that may be removed from within acpi_scan_hot_remove() through acpi_bus_trim() has a .store() or .show() callback which acquires device_hotplug_lock, the execution of that callback may deadlock with the removal of the attribute. [Unfortunately, the "online" device attribute of CPUs and memory blocks is one of them.] To avoid such deadlocks, make all of the sysfs attribute callbacks that need to lock device hotplug, for example store_online(), use a special function, lock_device_hotplug_sysfs(), to lock device hotplug and return the result of that function immediately if it is not zero. This will cause the s_active reference of the directory entry in question to be released and the syscall to be restarted if device_hotplug_lock cannot be acquired. [show_online() actually doesn't need to lock device hotplug, but it is useful to serialize it with respect to device_offline() and device_online() for the same device (in case user space attempts to run them concurrently) which can be done with the help of device_lock().] Reported-by: Yasuaki Ishimatsu Reported-and-tested-by: Gu Zheng Suggested-by: Tejun Heo Signed-off-by: Rafael J. Wysocki Acked-by: Greg Kroah-Hartman Acked-by: Toshi Kani --- include/linux/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 22b546a58591..545a04285120 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -895,6 +895,7 @@ static inline bool device_supports_offline(struct device *dev) extern void lock_device_hotplug(void); extern void unlock_device_hotplug(void); +extern int lock_device_hotplug_sysfs(void); extern int device_offline(struct device *dev); extern int device_online(struct device *dev); /* -- cgit v1.2.3 From 9120c0bea999cc26c3493486828d34138a7ac901 Mon Sep 17 00:00:00 2001 From: Josh Wu Date: Tue, 27 Aug 2013 12:28:00 +0100 Subject: iio: at91: Use different prescal, startup mask in MR for different IP For at91 boards, there are different IPs for adc. Different IPs has different STARTUP & PRESCAL mask in ADC_MR. Signed-off-by: Josh Wu Acked-by: Maxime Ripard Signed-off-by: Jonathan Cameron --- include/linux/platform_data/at91_adc.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/at91_adc.h b/include/linux/platform_data/at91_adc.h index e15745b4f3a5..b3ca1e94e0c8 100644 --- a/include/linux/platform_data/at91_adc.h +++ b/include/linux/platform_data/at91_adc.h @@ -14,12 +14,16 @@ (Interruptions registers mostly) * @status_register: Offset of the Interrupt Status Register * @trigger_register: Offset of the Trigger setup register + * @mr_prescal_mask: Mask of the PRESCAL field in the adc MR register + * @mr_startup_mask: Mask of the STARTUP field in the adc MR register */ struct at91_adc_reg_desc { u8 channel_base; u32 drdy_mask; u8 status_register; u8 trigger_register; + u32 mr_prescal_mask; + u32 mr_startup_mask; }; /** -- cgit v1.2.3 From 6290d60656e9f4f5a0071bafa798370ab35978a0 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Fri, 30 Aug 2013 18:06:06 +0800 Subject: regulator: tps65217: Convert to use linear ranges Below is the equation in original code: tps65217_uv1_ranges: 0 ... 24: uV = vsel * 25000 + 900000; 25 ... 52: uV = (vsel - 24) * 50000 + 1500000; = (vsel - 25) * 50000 + 1550000; 53 ... 55: uV = (vsel - 52) * 100000 + 2900000; = (vsel - 53) * 100000 + 3000000; 56 ... 62: uV = 3300000; tps65217_uv2_ranges: 0 ... 8: uV = vsel * 50000 + 1500000; 9 ... 13: uV = (vsel - 8) * 100000 + 1900000; = (vsel - 9) * 100000 + 2000000; 14 ... 31: uV = (vsel - 13) * 50000 + 2400000; = (vsel - 14) * 50000 + 2450000; The voltage tables are composed of linear ranges. This patch converts this driver to use multiple linear ranges APIs. In original code, voltage range for DCDC1 is 900000 ~ 1800000 and voltage range for DCDC3 is 900000 ~ 1500000. This patch separates the range 25~52 in tps65217_uv1_ranges table to two linear ranges: 25~30 and 31~52. This change makes it possible to reuse the same linear_ranges table for DCDCx. Signed-off-by: Axel Lin Signed-off-by: Mark Brown --- include/linux/mfd/tps65217.h | 19 ------------------- 1 file changed, 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tps65217.h b/include/linux/mfd/tps65217.h index 29eab2bd3dfa..a5a7f0130e96 100644 --- a/include/linux/mfd/tps65217.h +++ b/include/linux/mfd/tps65217.h @@ -243,24 +243,6 @@ struct tps65217_board { struct tps65217_bl_pdata *bl_pdata; }; -/** - * struct tps_info - packages regulator constraints - * @name: Voltage regulator name - * @min_uV: minimum micro volts - * @max_uV: minimum micro volts - * @vsel_to_uv: Function pointer to get voltage from selector - * @uv_to_vsel: Function pointer to get selector from voltage - * - * This data is used to check the regualtor voltage limits while setting. - */ -struct tps_info { - const char *name; - int min_uV; - int max_uV; - int (*vsel_to_uv)(unsigned int vsel); - int (*uv_to_vsel)(int uV, unsigned int *vsel); -}; - /** * struct tps65217 - tps65217 sub-driver chip access routines * @@ -273,7 +255,6 @@ struct tps65217 { unsigned int id; struct regulator_desc desc[TPS65217_NUM_REGULATOR]; struct regulator_dev *rdev[TPS65217_NUM_REGULATOR]; - struct tps_info *info[TPS65217_NUM_REGULATOR]; struct regmap *regmap; }; -- cgit v1.2.3 From 9d8924297cd9c256c23c02abae40202563452453 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Fri, 30 Aug 2013 10:46:00 -0400 Subject: USB: fix build error when CONFIG_PM_SLEEP isn't enabled This patch fixes a build error that occurs when CONFIG_PM is enabled and CONFIG_PM_SLEEP isn't: >> drivers/usb/host/ohci-pci.c:294:10: error: 'usb_hcd_pci_pm_ops' undeclared here (not in a function) .pm = &usb_hcd_pci_pm_ops Since the usb_hcd_pci_pm_ops structure is defined and used when CONFIG_PM is enabled, its declaration should not be protected by CONFIG_PM_SLEEP. Signed-off-by: Alan Stern Reported-by: kbuild test robot CC: Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index a9c7d44bd2ed..75efc45eaa2f 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -428,7 +428,7 @@ extern int usb_hcd_pci_probe(struct pci_dev *dev, extern void usb_hcd_pci_remove(struct pci_dev *dev); extern void usb_hcd_pci_shutdown(struct pci_dev *dev); -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_PM extern const struct dev_pm_ops usb_hcd_pci_pm_ops; #endif #endif /* CONFIG_PCI */ -- cgit v1.2.3 From 0edd1b1784cbdad55aca2c1293be018f53c0ab1d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 21 Jun 2013 16:37:22 -0700 Subject: nohz_full: Add full-system-idle state machine This commit adds the state machine that takes the per-CPU idle data as input and produces a full-system-idle indication as output. This state machine is driven out of RCU's quiescent-state-forcing mechanism, which invokes rcu_sysidle_check_cpu() to collect per-CPU idle state and then rcu_sysidle_report() to drive the state machine. The full-system-idle state is sampled using rcu_sys_is_idle(), which also drives the state machine if RCU is idle (and does so by forcing RCU to become non-idle). This function returns true if all but the timekeeping CPU (tick_do_timer_cpu) are idle and have been idle long enough to avoid memory contention on the full_sysidle_state state variable. The rcu_sysidle_force_exit() may be called externally to reset the state machine back into non-idle state. For large systems the state machine is driven out of RCU's force-quiescent-state logic, which provides good scalability at the price of millisecond-scale latencies on the transition to full-system-idle state. This is not so good for battery-powered systems, which are usually small enough that they don't need to care about scalability, but which do care deeply about energy efficiency. Small systems therefore drive the state machine directly out of the idle-entry code. The number of CPUs in a "small" system is defined by a new NO_HZ_FULL_SYSIDLE_SMALL Kconfig parameter, which defaults to 8. Note that this is a build-time definition. Signed-off-by: Paul E. McKenney Cc: Frederic Weisbecker Cc: Steven Rostedt Cc: Lai Jiangshan [ paulmck: Use true and false for boolean constants per Lai Jiangshan. ] Reviewed-by: Josh Triplett [ paulmck: Simplify logic and provide better comments for memory barriers, based on review comments and questions by Lai Jiangshan. ] --- include/linux/rcupdate.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 30bea9c25735..f1f1bc39346b 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -1011,4 +1011,22 @@ static inline bool rcu_is_nocb_cpu(int cpu) { return false; } #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ +/* Only for use by adaptive-ticks code. */ +#ifdef CONFIG_NO_HZ_FULL_SYSIDLE +extern bool rcu_sys_is_idle(void); +extern void rcu_sysidle_force_exit(void); +#else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ + +static inline bool rcu_sys_is_idle(void) +{ + return false; +} + +static inline void rcu_sysidle_force_exit(void) +{ +} + +#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ + + #endif /* __LINUX_RCUPDATE_H */ -- cgit v1.2.3 From 274481de6cb69abdb49403ff32abb63c23743413 Mon Sep 17 00:00:00 2001 From: Vince Weaver Date: Fri, 23 Aug 2013 15:51:03 -0400 Subject: perf: Export struct perf_branch_entry to userspace If PERF_SAMPLE_BRANCH_STACK is enabled then samples are returned with the format { u64 from, to, flags } but the flags layout is not specified. This field has the type struct perf_branch_entry; move this definition into include/uapi/linux/perf_event.h so users can access these fields. This is similar to the existing inclusion of perf_mem_data_src in the include/uapi/linux/perf_event.h file. Signed-off-by: Vince Weaver Acked-by: Stephane Eranian Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/alpine.DEB.2.10.1308231544420.1889@vincent-weaver-1.um.maine.edu Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 24 ------------------------ 1 file changed, 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index c43f6eabad5b..4019d82c3d03 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -63,30 +63,6 @@ struct perf_raw_record { void *data; }; -/* - * single taken branch record layout: - * - * from: source instruction (may not always be a branch insn) - * to: branch target - * mispred: branch target was mispredicted - * predicted: branch target was predicted - * - * support for mispred, predicted is optional. In case it - * is not supported mispred = predicted = 0. - * - * in_tx: running in a hardware transaction - * abort: aborting a hardware transaction - */ -struct perf_branch_entry { - __u64 from; - __u64 to; - __u64 mispred:1, /* target mispredicted */ - predicted:1,/* target predicted */ - in_tx:1, /* in transaction */ - abort:1, /* transaction abort */ - reserved:60; -}; - /* * branch stack layout: * nr: number of taken branches stored in entries[] -- cgit v1.2.3 From b3abd80250c13414bc258b53e57242feb159af91 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 2 Sep 2013 11:14:19 -0700 Subject: lockref: add 'lockref_get_or_lock() helper This behaves like "lockref_get_not_zero()", but instead of doing nothing if the count was zero, it returns with the lock held. This allows callers to revalidate the lockref-protected data structure if required even if the count was zero to begin with, and possibly increment the count if it passes muster. In particular, the dentry code wants this when it wants to turn an RCU-protected dentry into a stable refcounted one: if the dentry count it zero, but the sequence number still validates the dentry, we can take a reference to it. Signed-off-by: Linus Torvalds --- include/linux/lockref.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lockref.h b/include/linux/lockref.h index 01233e01627a..0ea026092d1d 100644 --- a/include/linux/lockref.h +++ b/include/linux/lockref.h @@ -53,6 +53,22 @@ static inline int lockref_get_not_zero(struct lockref *lockref) return retval; } +/** + * lockref_get_or_lock - Increments count unless the count is 0 + * @lockcnt: pointer to lockref structure + * Return: 1 if count updated successfully or 0 if count was zero + * and we got the lock instead. + */ +static inline int lockref_get_or_lock(struct lockref *lockref) +{ + spin_lock(&lockref->lock); + if (!lockref->count) + return 0; + lockref->count++; + spin_unlock(&lockref->lock); + return 1; +} + /** * lockref_put_or_lock - decrements count unless count <= 1 before decrement * @lockcnt: pointer to lockref structure -- cgit v1.2.3 From 15570086b590a69d59183b08a7770e316cca20a7 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 2 Sep 2013 11:38:06 -0700 Subject: vfs: reimplement d_rcu_to_refcount() using lockref_get_or_lock() This moves __d_rcu_to_refcount() from into fs/namei.c and re-implements it using the lockref infrastructure instead. It also adds a lot of comments about what is actually going on, because turning a dentry that was looked up using RCU into a long-lived reference counted entry is one of the more subtle parts of the rcu walk. We also used to be _particularly_ subtle in unlazy_walk() where we re-validate both the dentry and its parent using the same sequence count. We used to do it by nesting the locks and then verifying the sequence count just once. That was silly, because nested locking is expensive, but the sequence count check is not. So this just re-validates the dentry and the parent separately, avoiding the nested locking, and making the lockref lookup possible. Acked-by: Waiman Long Signed-off-by: Linus Torvalds --- include/linux/dcache.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index efdc94434c30..9169b91ea2d2 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -304,28 +304,6 @@ extern struct dentry *__d_lookup(const struct dentry *, const struct qstr *); extern struct dentry *__d_lookup_rcu(const struct dentry *parent, const struct qstr *name, unsigned *seq); -/** - * __d_rcu_to_refcount - take a refcount on dentry if sequence check is ok - * @dentry: dentry to take a ref on - * @seq: seqcount to verify against - * Returns: 0 on failure, else 1. - * - * __d_rcu_to_refcount operates on a dentry,seq pair that was returned - * by __d_lookup_rcu, to get a reference on an rcu-walk dentry. - */ -static inline int __d_rcu_to_refcount(struct dentry *dentry, unsigned seq) -{ - int ret = 0; - - assert_spin_locked(&dentry->d_lock); - if (!read_seqcount_retry(&dentry->d_seq, seq)) { - ret = 1; - dentry->d_lockref.count++; - } - - return ret; -} - static inline unsigned d_count(const struct dentry *dentry) { return dentry->d_lockref.count; -- cgit v1.2.3 From 2f4f12e571c4e2f50f3818a3c2544929145f75dd Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 2 Sep 2013 11:58:20 -0700 Subject: lockref: uninline lockref helper functions They aren't very good to inline, since they already call external functions (the spinlock code), and we're going to create rather more complicated versions of them that can do the reference count updates locklessly. Signed-off-by: Linus Torvalds --- include/linux/lockref.h | 66 +++---------------------------------------------- 1 file changed, 4 insertions(+), 62 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockref.h b/include/linux/lockref.h index 0ea026092d1d..4c0af31c8d47 100644 --- a/include/linux/lockref.h +++ b/include/linux/lockref.h @@ -21,67 +21,9 @@ struct lockref { unsigned int count; }; -/** - * lockref_get - Increments reference count unconditionally - * @lockcnt: pointer to lockref structure - * - * This operation is only valid if you already hold a reference - * to the object, so you know the count cannot be zero. - */ -static inline void lockref_get(struct lockref *lockref) -{ - spin_lock(&lockref->lock); - lockref->count++; - spin_unlock(&lockref->lock); -} - -/** - * lockref_get_not_zero - Increments count unless the count is 0 - * @lockcnt: pointer to lockref structure - * Return: 1 if count updated successfully or 0 if count is 0 - */ -static inline int lockref_get_not_zero(struct lockref *lockref) -{ - int retval = 0; - - spin_lock(&lockref->lock); - if (lockref->count) { - lockref->count++; - retval = 1; - } - spin_unlock(&lockref->lock); - return retval; -} - -/** - * lockref_get_or_lock - Increments count unless the count is 0 - * @lockcnt: pointer to lockref structure - * Return: 1 if count updated successfully or 0 if count was zero - * and we got the lock instead. - */ -static inline int lockref_get_or_lock(struct lockref *lockref) -{ - spin_lock(&lockref->lock); - if (!lockref->count) - return 0; - lockref->count++; - spin_unlock(&lockref->lock); - return 1; -} - -/** - * lockref_put_or_lock - decrements count unless count <= 1 before decrement - * @lockcnt: pointer to lockref structure - * Return: 1 if count updated successfully or 0 if count <= 1 and lock taken - */ -static inline int lockref_put_or_lock(struct lockref *lockref) -{ - spin_lock(&lockref->lock); - if (lockref->count <= 1) - return 0; - lockref->count--; - spin_unlock(&lockref->lock); - return 1; -} +extern void lockref_get(struct lockref *); +extern int lockref_get_not_zero(struct lockref *); +extern int lockref_get_or_lock(struct lockref *); +extern int lockref_put_or_lock(struct lockref *); #endif /* __LINUX_LOCKREF_H */ -- cgit v1.2.3 From bc08b449ee14ace4d869adaa1bb35a44ce68d775 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 2 Sep 2013 12:12:15 -0700 Subject: lockref: implement lockless reference count updates using cmpxchg() Instead of taking the spinlock, the lockless versions atomically check that the lock is not taken, and do the reference count update using a cmpxchg() loop. This is semantically identical to doing the reference count update protected by the lock, but avoids the "wait for lock" contention that you get when accesses to the reference count are contended. Note that a "lockref" is absolutely _not_ equivalent to an atomic_t. Even when the lockref reference counts are updated atomically with cmpxchg, the fact that they also verify the state of the spinlock means that the lockless updates can never happen while somebody else holds the spinlock. So while "lockref_put_or_lock()" looks a lot like just another name for "atomic_dec_and_lock()", and both optimize to lockless updates, they are fundamentally different: the decrement done by atomic_dec_and_lock() is truly independent of any lock (as long as it doesn't decrement to zero), so a locked region can still see the count change. The lockref structure, in contrast, really is a *locked* reference count. If you hold the spinlock, the reference count will be stable and you can modify the reference count without using atomics, because even the lockless updates will see and respect the state of the lock. In order to enable the cmpxchg lockless code, the architecture needs to do three things: (1) Make sure that the "arch_spinlock_t" and an "unsigned int" can fit in an aligned u64, and have a "cmpxchg()" implementation that works on such a u64 data type. (2) define a helper function to test for a spinlock being unlocked ("arch_spin_value_unlocked()") (3) select the "ARCH_USE_CMPXCHG_LOCKREF" config variable in its Kconfig file. This enables it for x86-64 (but not 32-bit, we'd need to make sure cmpxchg() turns into the proper cmpxchg8b in order to enable it for 32-bit mode). Signed-off-by: Linus Torvalds --- include/linux/lockref.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockref.h b/include/linux/lockref.h index 4c0af31c8d47..ca07b5028b01 100644 --- a/include/linux/lockref.h +++ b/include/linux/lockref.h @@ -17,8 +17,15 @@ #include struct lockref { - spinlock_t lock; - unsigned int count; + union { +#ifdef CONFIG_CMPXCHG_LOCKREF + aligned_u64 lock_count; +#endif + struct { + spinlock_t lock; + unsigned int count; + }; + }; }; extern void lockref_get(struct lockref *); -- cgit v1.2.3