From 2c67568903d6ae1b8cfa343c649029180239418e Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 8 Aug 2014 13:02:36 +0200 Subject: spi: Add missing kerneldoc bits These are all arguments or fields that got added without updating the kerneldoc comments. Signed-off-by: Thierry Reding Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index e713543336f1..46d188a9947c 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -253,6 +253,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * the device whose settings are being modified. * @transfer: adds a message to the controller's transfer queue. * @cleanup: frees controller-specific state + * @can_dma: determine whether this master supports DMA * @queued: whether this master is providing an internal message queue * @kworker: thread struct for message pump * @kworker_task: pointer to task for message pump kworker thread @@ -262,6 +263,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * @cur_msg: the currently in-flight message * @cur_msg_prepared: spi_prepare_message was called for the currently * in-flight message + * @cur_msg_mapped: message has been mapped for DMA * @xfer_completion: used by core transfer_one_message() * @busy: message pump is busy * @running: message pump is running @@ -299,6 +301,10 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * @cs_gpios: Array of GPIOs to use as chip select lines; one per CS * number. Any individual value may be -ENOENT for CS lines that * are not GPIOs (driven by the SPI controller itself). + * @dma_tx: DMA transmit channel + * @dma_rx: DMA receive channel + * @dummy_rx: dummy receive buffer for full-duplex devices + * @dummy_tx: dummy transmit buffer for full-duplex devices * * Each SPI master controller can communicate with one or more @spi_device * children. These make a small bus, sharing MOSI, MISO and SCK signals @@ -632,6 +638,7 @@ struct spi_transfer { * addresses for each transfer buffer * @complete: called to report transaction completions * @context: the argument to complete() when it's called + * @frame_length: the total number of bytes in the message * @actual_length: the total number of bytes that were transferred in all * successful segments * @status: zero for success, else negative errno -- cgit v1.2.3 From 8a58d1f1f373238cb0d6d7f8d3dd723aa164b8ac Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 15 Aug 2014 12:38:41 -0600 Subject: blk-mq: get rid of unused BLK_MQ_F_SHOULD_SORT flag We used to use this for determining whether to sort the dispatch list, but it's unused now. Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index eb726b9c5762..a1e31f274fcd 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -127,10 +127,9 @@ enum { BLK_MQ_RQ_QUEUE_ERROR = 2, /* end IO with error */ BLK_MQ_F_SHOULD_MERGE = 1 << 0, - BLK_MQ_F_SHOULD_SORT = 1 << 1, - BLK_MQ_F_TAG_SHARED = 1 << 2, - BLK_MQ_F_SG_MERGE = 1 << 3, - BLK_MQ_F_SYSFS_UP = 1 << 4, + BLK_MQ_F_TAG_SHARED = 1 << 1, + BLK_MQ_F_SG_MERGE = 1 << 2, + BLK_MQ_F_SYSFS_UP = 1 << 3, BLK_MQ_S_STOPPED = 0, BLK_MQ_S_TAG_ACTIVE = 1, -- cgit v1.2.3 From 16466f4284154311f163a58b77379eb186274f87 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 14 Aug 2014 16:52:51 -0700 Subject: net: phy: bcm7xxx: remove 28nm wildcard entry A wildcard entry with the 32-bits OUI 0x600d8400 was added as part of the BCM7xxx internal PHY driver, but that entry might match other PHYs that are not covered by this driver, so let's just remove it. Fixes: b560a58c45c6 ("net: phy: add Broadcom BCM7xxx internal PHY driver") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/bcm7xxx.c | 14 -------------- include/linux/brcmphy.h | 1 - 2 files changed, 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c index 526b94cea569..2b40548c85d5 100644 --- a/drivers/net/phy/bcm7xxx.c +++ b/drivers/net/phy/bcm7xxx.c @@ -286,19 +286,6 @@ static struct phy_driver bcm7xxx_driver[] = { .suspend = bcm7xxx_suspend, .resume = bcm7xxx_28nm_config_init, .driver = { .owner = THIS_MODULE }, -}, { - .name = "Broadcom BCM7XXX 28nm", - .phy_id = PHY_ID_BCM7XXX_28, - .phy_id_mask = PHY_BCM_OUI_MASK, - .features = PHY_GBIT_FEATURES | - SUPPORTED_Pause | SUPPORTED_Asym_Pause, - .flags = PHY_IS_INTERNAL, - .config_init = bcm7xxx_28nm_config_init, - .config_aneg = genphy_config_aneg, - .read_status = genphy_read_status, - .suspend = bcm7xxx_suspend, - .resume = bcm7xxx_28nm_config_init, - .driver = { .owner = THIS_MODULE }, }, { .phy_id = PHY_BCM_OUI_4, .phy_id_mask = 0xffff0000, @@ -331,7 +318,6 @@ static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = { { PHY_ID_BCM7366, 0xfffffff0, }, { PHY_ID_BCM7439, 0xfffffff0, }, { PHY_ID_BCM7445, 0xfffffff0, }, - { PHY_ID_BCM7XXX_28, 0xfffffc00 }, { PHY_BCM_OUI_4, 0xffff0000 }, { PHY_BCM_OUI_5, 0xffffff00 }, { } diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 6f76277baf39..61219b9b3445 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -16,7 +16,6 @@ #define PHY_ID_BCM7366 0x600d8490 #define PHY_ID_BCM7439 0x600d8480 #define PHY_ID_BCM7445 0x600d8510 -#define PHY_ID_BCM7XXX_28 0x600d8400 #define PHY_BCM_OUI_MASK 0xfffffc00 #define PHY_BCM_OUI_1 0x00206000 -- cgit v1.2.3 From 366047515c6eab2ff886bc28d1c2b0ad041d040a Mon Sep 17 00:00:00 2001 From: Lan Tianyu Date: Fri, 15 Aug 2014 13:38:59 +0800 Subject: i2c: rework kernel config I2C_ACPI Commit da3c6647(I2C/ACPI: Clean up I2C ACPI code and Add CONFIG_I2C_ACPI config) adds a new kernel config I2C_ACPI and make I2C core built in when the config is selected. This is wrong because distributions etc generally compile I2C as a module and the commit broken that. This patch is to rename I2C_ACPI to ACPI_I2C_OPREGION. New config only controls ACPI I2C operation region code and depends on I2C=y. Signed-off-by: Lan Tianyu Reviewed-by: Mika Westerberg [wsa: removed unrelated change for Kconfig] Signed-off-by: Wolfram Sang --- drivers/i2c/Kconfig | 15 ++++++--------- drivers/i2c/Makefile | 2 +- drivers/i2c/i2c-acpi.c | 2 ++ include/linux/i2c.h | 12 ++++++++---- 4 files changed, 17 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/i2c/Kconfig b/drivers/i2c/Kconfig index 3e3b680dc007..b51a402752c4 100644 --- a/drivers/i2c/Kconfig +++ b/drivers/i2c/Kconfig @@ -23,17 +23,14 @@ config I2C This I2C support can also be built as a module. If so, the module will be called i2c-core. -config I2C_ACPI - bool "I2C ACPI support" - select I2C - depends on ACPI +config ACPI_I2C_OPREGION + bool "ACPI I2C Operation region support" + depends on I2C=y && ACPI default y help - Say Y here if you want to enable ACPI I2C support. This includes support - for automatic enumeration of I2C slave devices and support for ACPI I2C - Operation Regions. Operation Regions allow firmware (BIOS) code to - access I2C slave devices, such as smart batteries through an I2C host - controller driver. + Say Y here if you want to enable ACPI I2C operation region support. + Operation Regions allow firmware (BIOS) code to access I2C slave devices, + such as smart batteries through an I2C host controller driver. if I2C diff --git a/drivers/i2c/Makefile b/drivers/i2c/Makefile index a1f590cbb435..e0228b228256 100644 --- a/drivers/i2c/Makefile +++ b/drivers/i2c/Makefile @@ -3,7 +3,7 @@ # i2ccore-y := i2c-core.o -i2ccore-$(CONFIG_I2C_ACPI) += i2c-acpi.o +i2ccore-$(CONFIG_ACPI) += i2c-acpi.o obj-$(CONFIG_I2C_BOARDINFO) += i2c-boardinfo.o obj-$(CONFIG_I2C) += i2ccore.o diff --git a/drivers/i2c/i2c-acpi.c b/drivers/i2c/i2c-acpi.c index e8b61967334b..0dbc18c15c43 100644 --- a/drivers/i2c/i2c-acpi.c +++ b/drivers/i2c/i2c-acpi.c @@ -126,6 +126,7 @@ void acpi_i2c_register_devices(struct i2c_adapter *adap) dev_warn(&adap->dev, "failed to enumerate I2C slaves\n"); } +#ifdef CONFIG_ACPI_I2C_OPREGION static int acpi_gsb_i2c_read_bytes(struct i2c_client *client, u8 cmd, u8 *data, u8 data_len) { @@ -360,3 +361,4 @@ void acpi_i2c_remove_space_handler(struct i2c_adapter *adapter) acpi_bus_detach_private_data(handle); } +#endif diff --git a/include/linux/i2c.h b/include/linux/i2c.h index ea507665896c..a95efeb53a8b 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -577,16 +577,20 @@ static inline struct i2c_adapter *of_find_i2c_adapter_by_node(struct device_node } #endif /* CONFIG_OF */ -#ifdef CONFIG_I2C_ACPI -int acpi_i2c_install_space_handler(struct i2c_adapter *adapter); -void acpi_i2c_remove_space_handler(struct i2c_adapter *adapter); +#ifdef CONFIG_ACPI void acpi_i2c_register_devices(struct i2c_adapter *adap); #else static inline void acpi_i2c_register_devices(struct i2c_adapter *adap) { } +#endif /* CONFIG_ACPI */ + +#ifdef CONFIG_ACPI_I2C_OPREGION +int acpi_i2c_install_space_handler(struct i2c_adapter *adapter); +void acpi_i2c_remove_space_handler(struct i2c_adapter *adapter); +#else static inline void acpi_i2c_remove_space_handler(struct i2c_adapter *adapter) { } static inline int acpi_i2c_install_space_handler(struct i2c_adapter *adapter) { return 0; } -#endif +#endif /* CONFIG_ACPI_I2C_OPREGION */ #endif /* _LINUX_I2C_H */ -- cgit v1.2.3 From 58b84f6a97f7f8811e0636836734809ff52cad43 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 19 Aug 2014 12:00:53 -0500 Subject: gpio: move GPIOD flags outside #ifdef The GPIOD flags are defined inside the #ifdef CONFIG_GPIOLIB switch, making the gpiolib stubs fail if these flags are used by a consumer. This is not correct: the stubs should compile fine without GPIOLIB. Reported-by: Ulf Hansson Reviewed-by: Alexandre Courbot Signed-off-by: Linus Walleij --- include/linux/gpio/consumer.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index b7ce0c64c6f3..c7e17de732f3 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -16,8 +16,6 @@ struct device; */ struct gpio_desc; -#ifdef CONFIG_GPIOLIB - #define GPIOD_FLAGS_BIT_DIR_SET BIT(0) #define GPIOD_FLAGS_BIT_DIR_OUT BIT(1) #define GPIOD_FLAGS_BIT_DIR_VAL BIT(2) @@ -34,6 +32,8 @@ enum gpiod_flags { GPIOD_FLAGS_BIT_DIR_VAL, }; +#ifdef CONFIG_GPIOLIB + /* Acquire and dispose GPIOs */ struct gpio_desc *__must_check __gpiod_get(struct device *dev, const char *con_id, -- cgit v1.2.3 From 33b7f99cf003ca6c1d31c42b50e1100ad71aaec0 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Fri, 15 Aug 2014 17:23:02 -0400 Subject: ftrace: Allow ftrace_ops to use the hashes from other ops Currently the top level debug file system function tracer shares its ftrace_ops with the function graph tracer. This was thought to be fine because the tracers are not used together, as one can only enable function or function_graph tracer in the current_tracer file. But that assumption proved to be incorrect. The function profiler can use the function graph tracer when function tracing is enabled. Since all function graph users uses the function tracing ftrace_ops this causes a conflict and when a user enables both function profiling as well as the function tracer it will crash ftrace and disable it. The quick solution so far is to move them as separate ftrace_ops like it was earlier. The problem though is to synchronize the functions that are traced because both function and function_graph tracer are limited by the selections made in the set_ftrace_filter and set_ftrace_notrace files. To handle this, a new structure is made called ftrace_ops_hash. This structure will now hold the filter_hash and notrace_hash, and the ftrace_ops will point to this structure. That will allow two ftrace_ops to share the same hashes. Since most ftrace_ops do not share the hashes, and to keep allocation simple, the ftrace_ops structure will include both a pointer to the ftrace_ops_hash called func_hash, as well as the structure itself, called local_hash. When the ops are registered, the func_hash pointer will be initialized to point to the local_hash within the ftrace_ops structure. Some of the ftrace internal ftrace_ops will be initialized statically. This will allow for the function and function_graph tracer to have separate ops but still share the same hash tables that determine what functions they trace. Cc: stable@vger.kernel.org # 3.16 (apply after 3.17-rc4 is out) Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 14 +++++-- kernel/trace/ftrace.c | 100 +++++++++++++++++++++++++------------------------ 2 files changed, 63 insertions(+), 51 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 6bb5e3f2a3b4..f0b0edbf55a9 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -102,6 +102,15 @@ enum { FTRACE_OPS_FL_DELETED = 1 << 8, }; +#ifdef CONFIG_DYNAMIC_FTRACE +/* The hash used to know what functions callbacks trace */ +struct ftrace_ops_hash { + struct ftrace_hash *notrace_hash; + struct ftrace_hash *filter_hash; + struct mutex regex_lock; +}; +#endif + /* * Note, ftrace_ops can be referenced outside of RCU protection. * (Although, for perf, the control ops prevent that). If ftrace_ops is @@ -121,10 +130,9 @@ struct ftrace_ops { int __percpu *disabled; #ifdef CONFIG_DYNAMIC_FTRACE int nr_trampolines; - struct ftrace_hash *notrace_hash; - struct ftrace_hash *filter_hash; + struct ftrace_ops_hash local_hash; + struct ftrace_ops_hash *func_hash; struct ftrace_hash *tramp_hash; - struct mutex regex_lock; unsigned long trampoline; #endif }; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 1654b12c891a..c92757adba79 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -65,15 +65,17 @@ #define FL_GLOBAL_CONTROL_MASK (FTRACE_OPS_FL_CONTROL) #ifdef CONFIG_DYNAMIC_FTRACE -#define INIT_REGEX_LOCK(opsname) \ - .regex_lock = __MUTEX_INITIALIZER(opsname.regex_lock), +#define INIT_OPS_HASH(opsname) \ + .func_hash = &opsname.local_hash, \ + .local_hash.regex_lock = __MUTEX_INITIALIZER(opsname.local_hash.regex_lock), #else -#define INIT_REGEX_LOCK(opsname) +#define INIT_OPS_HASH(opsname) #endif static struct ftrace_ops ftrace_list_end __read_mostly = { .func = ftrace_stub, .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_STUB, + INIT_OPS_HASH(ftrace_list_end) }; /* ftrace_enabled is a method to turn ftrace on or off */ @@ -140,7 +142,8 @@ static inline void ftrace_ops_init(struct ftrace_ops *ops) { #ifdef CONFIG_DYNAMIC_FTRACE if (!(ops->flags & FTRACE_OPS_FL_INITIALIZED)) { - mutex_init(&ops->regex_lock); + mutex_init(&ops->local_hash.regex_lock); + ops->func_hash = &ops->local_hash; ops->flags |= FTRACE_OPS_FL_INITIALIZED; } #endif @@ -899,7 +902,7 @@ static void unregister_ftrace_profiler(void) static struct ftrace_ops ftrace_profile_ops __read_mostly = { .func = function_profile_call, .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_INITIALIZED, - INIT_REGEX_LOCK(ftrace_profile_ops) + INIT_OPS_HASH(ftrace_profile_ops) }; static int register_ftrace_profiler(void) @@ -1081,11 +1084,12 @@ static const struct ftrace_hash empty_hash = { #define EMPTY_HASH ((struct ftrace_hash *)&empty_hash) static struct ftrace_ops global_ops = { - .func = ftrace_stub, - .notrace_hash = EMPTY_HASH, - .filter_hash = EMPTY_HASH, - .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_INITIALIZED, - INIT_REGEX_LOCK(global_ops) + .func = ftrace_stub, + .local_hash.notrace_hash = EMPTY_HASH, + .local_hash.filter_hash = EMPTY_HASH, + INIT_OPS_HASH(global_ops) + .flags = FTRACE_OPS_FL_RECURSION_SAFE | + FTRACE_OPS_FL_INITIALIZED, }; struct ftrace_page { @@ -1226,8 +1230,8 @@ static void free_ftrace_hash_rcu(struct ftrace_hash *hash) void ftrace_free_filter(struct ftrace_ops *ops) { ftrace_ops_init(ops); - free_ftrace_hash(ops->filter_hash); - free_ftrace_hash(ops->notrace_hash); + free_ftrace_hash(ops->func_hash->filter_hash); + free_ftrace_hash(ops->func_hash->notrace_hash); } static struct ftrace_hash *alloc_ftrace_hash(int size_bits) @@ -1382,8 +1386,8 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs) return 0; #endif - filter_hash = rcu_dereference_raw_notrace(ops->filter_hash); - notrace_hash = rcu_dereference_raw_notrace(ops->notrace_hash); + filter_hash = rcu_dereference_raw_notrace(ops->func_hash->filter_hash); + notrace_hash = rcu_dereference_raw_notrace(ops->func_hash->notrace_hash); if ((ftrace_hash_empty(filter_hash) || ftrace_lookup_ip(filter_hash, ip)) && @@ -1554,14 +1558,14 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, * gets inversed. */ if (filter_hash) { - hash = ops->filter_hash; - other_hash = ops->notrace_hash; + hash = ops->func_hash->filter_hash; + other_hash = ops->func_hash->notrace_hash; if (ftrace_hash_empty(hash)) all = 1; } else { inc = !inc; - hash = ops->notrace_hash; - other_hash = ops->filter_hash; + hash = ops->func_hash->notrace_hash; + other_hash = ops->func_hash->filter_hash; /* * If the notrace hash has no items, * then there's nothing to do. @@ -2436,8 +2440,8 @@ static inline int ops_traces_mod(struct ftrace_ops *ops) * Filter_hash being empty will default to trace module. * But notrace hash requires a test of individual module functions. */ - return ftrace_hash_empty(ops->filter_hash) && - ftrace_hash_empty(ops->notrace_hash); + return ftrace_hash_empty(ops->func_hash->filter_hash) && + ftrace_hash_empty(ops->func_hash->notrace_hash); } /* @@ -2459,12 +2463,12 @@ ops_references_rec(struct ftrace_ops *ops, struct dyn_ftrace *rec) return 0; /* The function must be in the filter */ - if (!ftrace_hash_empty(ops->filter_hash) && - !ftrace_lookup_ip(ops->filter_hash, rec->ip)) + if (!ftrace_hash_empty(ops->func_hash->filter_hash) && + !ftrace_lookup_ip(ops->func_hash->filter_hash, rec->ip)) return 0; /* If in notrace hash, we ignore it too */ - if (ftrace_lookup_ip(ops->notrace_hash, rec->ip)) + if (ftrace_lookup_ip(ops->func_hash->notrace_hash, rec->ip)) return 0; return 1; @@ -2785,10 +2789,10 @@ t_next(struct seq_file *m, void *v, loff_t *pos) } else { rec = &iter->pg->records[iter->idx++]; if (((iter->flags & FTRACE_ITER_FILTER) && - !(ftrace_lookup_ip(ops->filter_hash, rec->ip))) || + !(ftrace_lookup_ip(ops->func_hash->filter_hash, rec->ip))) || ((iter->flags & FTRACE_ITER_NOTRACE) && - !ftrace_lookup_ip(ops->notrace_hash, rec->ip)) || + !ftrace_lookup_ip(ops->func_hash->notrace_hash, rec->ip)) || ((iter->flags & FTRACE_ITER_ENABLED) && !(rec->flags & FTRACE_FL_ENABLED))) { @@ -2837,9 +2841,9 @@ static void *t_start(struct seq_file *m, loff_t *pos) * functions are enabled. */ if ((iter->flags & FTRACE_ITER_FILTER && - ftrace_hash_empty(ops->filter_hash)) || + ftrace_hash_empty(ops->func_hash->filter_hash)) || (iter->flags & FTRACE_ITER_NOTRACE && - ftrace_hash_empty(ops->notrace_hash))) { + ftrace_hash_empty(ops->func_hash->notrace_hash))) { if (*pos > 0) return t_hash_start(m, pos); iter->flags |= FTRACE_ITER_PRINTALL; @@ -3001,12 +3005,12 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag, iter->ops = ops; iter->flags = flag; - mutex_lock(&ops->regex_lock); + mutex_lock(&ops->func_hash->regex_lock); if (flag & FTRACE_ITER_NOTRACE) - hash = ops->notrace_hash; + hash = ops->func_hash->notrace_hash; else - hash = ops->filter_hash; + hash = ops->func_hash->filter_hash; if (file->f_mode & FMODE_WRITE) { const int size_bits = FTRACE_HASH_DEFAULT_BITS; @@ -3041,7 +3045,7 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag, file->private_data = iter; out_unlock: - mutex_unlock(&ops->regex_lock); + mutex_unlock(&ops->func_hash->regex_lock); return ret; } @@ -3279,7 +3283,7 @@ static struct ftrace_ops trace_probe_ops __read_mostly = { .func = function_trace_probe_call, .flags = FTRACE_OPS_FL_INITIALIZED, - INIT_REGEX_LOCK(trace_probe_ops) + INIT_OPS_HASH(trace_probe_ops) }; static int ftrace_probe_registered; @@ -3342,7 +3346,7 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, void *data) { struct ftrace_func_probe *entry; - struct ftrace_hash **orig_hash = &trace_probe_ops.filter_hash; + struct ftrace_hash **orig_hash = &trace_probe_ops.func_hash->filter_hash; struct ftrace_hash *hash; struct ftrace_page *pg; struct dyn_ftrace *rec; @@ -3359,7 +3363,7 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, if (WARN_ON(not)) return -EINVAL; - mutex_lock(&trace_probe_ops.regex_lock); + mutex_lock(&trace_probe_ops.func_hash->regex_lock); hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash); if (!hash) { @@ -3428,7 +3432,7 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, out_unlock: mutex_unlock(&ftrace_lock); out: - mutex_unlock(&trace_probe_ops.regex_lock); + mutex_unlock(&trace_probe_ops.func_hash->regex_lock); free_ftrace_hash(hash); return count; @@ -3446,7 +3450,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, struct ftrace_func_entry *rec_entry; struct ftrace_func_probe *entry; struct ftrace_func_probe *p; - struct ftrace_hash **orig_hash = &trace_probe_ops.filter_hash; + struct ftrace_hash **orig_hash = &trace_probe_ops.func_hash->filter_hash; struct list_head free_list; struct ftrace_hash *hash; struct hlist_node *tmp; @@ -3468,7 +3472,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, return; } - mutex_lock(&trace_probe_ops.regex_lock); + mutex_lock(&trace_probe_ops.func_hash->regex_lock); hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash); if (!hash) @@ -3521,7 +3525,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, mutex_unlock(&ftrace_lock); out_unlock: - mutex_unlock(&trace_probe_ops.regex_lock); + mutex_unlock(&trace_probe_ops.func_hash->regex_lock); free_ftrace_hash(hash); } @@ -3717,12 +3721,12 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, if (unlikely(ftrace_disabled)) return -ENODEV; - mutex_lock(&ops->regex_lock); + mutex_lock(&ops->func_hash->regex_lock); if (enable) - orig_hash = &ops->filter_hash; + orig_hash = &ops->func_hash->filter_hash; else - orig_hash = &ops->notrace_hash; + orig_hash = &ops->func_hash->notrace_hash; if (reset) hash = alloc_ftrace_hash(FTRACE_HASH_DEFAULT_BITS); @@ -3752,7 +3756,7 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, mutex_unlock(&ftrace_lock); out_regex_unlock: - mutex_unlock(&ops->regex_lock); + mutex_unlock(&ops->func_hash->regex_lock); free_ftrace_hash(hash); return ret; @@ -3975,15 +3979,15 @@ int ftrace_regex_release(struct inode *inode, struct file *file) trace_parser_put(parser); - mutex_lock(&iter->ops->regex_lock); + mutex_lock(&iter->ops->func_hash->regex_lock); if (file->f_mode & FMODE_WRITE) { filter_hash = !!(iter->flags & FTRACE_ITER_FILTER); if (filter_hash) - orig_hash = &iter->ops->filter_hash; + orig_hash = &iter->ops->func_hash->filter_hash; else - orig_hash = &iter->ops->notrace_hash; + orig_hash = &iter->ops->func_hash->notrace_hash; mutex_lock(&ftrace_lock); ret = ftrace_hash_move(iter->ops, filter_hash, @@ -3994,7 +3998,7 @@ int ftrace_regex_release(struct inode *inode, struct file *file) mutex_unlock(&ftrace_lock); } - mutex_unlock(&iter->ops->regex_lock); + mutex_unlock(&iter->ops->func_hash->regex_lock); free_ftrace_hash(iter->hash); kfree(iter); @@ -4611,7 +4615,7 @@ void __init ftrace_init(void) static struct ftrace_ops global_ops = { .func = ftrace_stub, .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_INITIALIZED, - INIT_REGEX_LOCK(global_ops) + INIT_OPS_HASH(global_ops) }; static int __init ftrace_nodyn_init(void) @@ -4713,7 +4717,7 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip, static struct ftrace_ops control_ops = { .func = ftrace_ops_control_func, .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_INITIALIZED, - INIT_REGEX_LOCK(control_ops) + INIT_OPS_HASH(control_ops) }; static inline void -- cgit v1.2.3 From 7c3af975257383ece54b83c0505d3e0656cb7daf Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Fri, 8 Aug 2014 11:00:57 -0400 Subject: nfs: don't sleep with inode lock in lock_and_join_requests This handles the 'nonblock=false' case in nfs_lock_and_join_requests. If the group is already locked and blocking is allowed, drop the inode lock and wait for the group lock to be cleared before trying it all again. This should fix warnings found in peterz's tree (sched/wait branch), where might_sleep() checks are added to wait.[ch]. Reported-by: Fengguang Wu Signed-off-by: Weston Andros Adamson Reviewed-by: Peng Tao Signed-off-by: Trond Myklebust --- fs/nfs/pagelist.c | 17 +++++++++++++++++ fs/nfs/write.c | 12 +++++++++++- include/linux/nfs_page.h | 1 + 3 files changed, 29 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 30c9626f96b0..4ec67f8d70aa 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -167,6 +167,23 @@ nfs_page_group_lock(struct nfs_page *req, bool nonblock) return -EAGAIN; } +/* + * nfs_page_group_lock_wait - wait for the lock to clear, but don't grab it + * @req - a request in the group + * + * This is a blocking call to wait for the group lock to be cleared. + */ +void +nfs_page_group_lock_wait(struct nfs_page *req) +{ + struct nfs_page *head = req->wb_head; + + WARN_ON_ONCE(head != head->wb_head); + + wait_on_bit(&head->wb_flags, PG_HEADLOCK, + TASK_UNINTERRUPTIBLE); +} + /* * nfs_page_group_unlock - unlock the head of the page group * @req - request in group that is to be unlocked diff --git a/fs/nfs/write.c b/fs/nfs/write.c index e056f617adf2..175d5d073ccf 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -478,13 +478,23 @@ try_again: return NULL; } - /* lock each request in the page group */ + /* holding inode lock, so always make a non-blocking call to try the + * page group lock */ ret = nfs_page_group_lock(head, true); if (ret < 0) { spin_unlock(&inode->i_lock); + + if (!nonblock && ret == -EAGAIN) { + nfs_page_group_lock_wait(head); + nfs_release_request(head); + goto try_again; + } + nfs_release_request(head); return ERR_PTR(ret); } + + /* lock each request in the page group */ subreq = head; do { /* diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 6ad2bbcad405..6c3e06ee2fb7 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -123,6 +123,7 @@ extern int nfs_wait_on_request(struct nfs_page *); extern void nfs_unlock_request(struct nfs_page *req); extern void nfs_unlock_and_release_request(struct nfs_page *); extern int nfs_page_group_lock(struct nfs_page *, bool); +extern void nfs_page_group_lock_wait(struct nfs_page *); extern void nfs_page_group_unlock(struct nfs_page *); extern bool nfs_page_group_sync_on_bit(struct nfs_page *, unsigned int); -- cgit v1.2.3 From 7d5929c1f34304ca5a970cfde8044053e56aa8c9 Mon Sep 17 00:00:00 2001 From: Roger Quadros Date: Mon, 25 Aug 2014 16:15:32 -0700 Subject: mtd: nand: omap: Revert to using software ECC by default For v3.12 and prior, 1-bit Hamming code ECC via software was the default choice. Commit c66d039197e4 in v3.13 changed the behaviour to use 1-bit Hamming code via Hardware using a different ECC layout i.e. (ROM code layout) than what is used by software ECC. This ECC layout change causes NAND filesystems created in v3.12 and prior to be unusable in v3.13 and later. So revert back to using software ECC by default if an ECC scheme is not explicitely specified. This defect can be observed on the following boards during legacy boot -omap3beagle -omap3touchbook -overo -am3517crane -devkit8000 -ldp -3430sdp Signed-off-by: Roger Quadros Tested-by: Grazvydas Ignotas Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/board-flash.c | 2 +- arch/arm/mach-omap2/gpmc-nand.c | 3 ++- drivers/mtd/nand/omap2.c | 14 +++++++++++--- include/linux/platform_data/mtd-nand-omap2.h | 13 +++++++++++-- 4 files changed, 25 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mach-omap2/board-flash.c b/arch/arm/mach-omap2/board-flash.c index e87f2a83d6bf..2d245c2e641c 100644 --- a/arch/arm/mach-omap2/board-flash.c +++ b/arch/arm/mach-omap2/board-flash.c @@ -142,7 +142,7 @@ __init board_nand_init(struct mtd_partition *nand_parts, u8 nr_parts, u8 cs, board_nand_data.nr_parts = nr_parts; board_nand_data.devsize = nand_type; - board_nand_data.ecc_opt = OMAP_ECC_HAM1_CODE_HW; + board_nand_data.ecc_opt = OMAP_ECC_HAM1_CODE_SW; gpmc_nand_init(&board_nand_data, gpmc_t); } #endif /* CONFIG_MTD_NAND_OMAP2 || CONFIG_MTD_NAND_OMAP2_MODULE */ diff --git a/arch/arm/mach-omap2/gpmc-nand.c b/arch/arm/mach-omap2/gpmc-nand.c index 8897ad7035fd..cb7764314f17 100644 --- a/arch/arm/mach-omap2/gpmc-nand.c +++ b/arch/arm/mach-omap2/gpmc-nand.c @@ -49,7 +49,8 @@ static bool gpmc_hwecc_bch_capable(enum omap_ecc ecc_opt) return 0; /* legacy platforms support only HAM1 (1-bit Hamming) ECC scheme */ - if (ecc_opt == OMAP_ECC_HAM1_CODE_HW) + if (ecc_opt == OMAP_ECC_HAM1_CODE_HW || + ecc_opt == OMAP_ECC_HAM1_CODE_SW) return 1; else return 0; diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c index f0ed92e210a1..4dd617897eee 100644 --- a/drivers/mtd/nand/omap2.c +++ b/drivers/mtd/nand/omap2.c @@ -1794,9 +1794,12 @@ static int omap_nand_probe(struct platform_device *pdev) } /* populate MTD interface based on ECC scheme */ - nand_chip->ecc.layout = &omap_oobinfo; ecclayout = &omap_oobinfo; switch (info->ecc_opt) { + case OMAP_ECC_HAM1_CODE_SW: + nand_chip->ecc.mode = NAND_ECC_SOFT; + break; + case OMAP_ECC_HAM1_CODE_HW: pr_info("nand: using OMAP_ECC_HAM1_CODE_HW\n"); nand_chip->ecc.mode = NAND_ECC_HW; @@ -1848,7 +1851,7 @@ static int omap_nand_probe(struct platform_device *pdev) nand_chip->ecc.priv = nand_bch_init(mtd, nand_chip->ecc.size, nand_chip->ecc.bytes, - &nand_chip->ecc.layout); + &ecclayout); if (!nand_chip->ecc.priv) { pr_err("nand: error: unable to use s/w BCH library\n"); err = -EINVAL; @@ -1923,7 +1926,7 @@ static int omap_nand_probe(struct platform_device *pdev) nand_chip->ecc.priv = nand_bch_init(mtd, nand_chip->ecc.size, nand_chip->ecc.bytes, - &nand_chip->ecc.layout); + &ecclayout); if (!nand_chip->ecc.priv) { pr_err("nand: error: unable to use s/w BCH library\n"); err = -EINVAL; @@ -2012,6 +2015,9 @@ static int omap_nand_probe(struct platform_device *pdev) goto return_error; } + if (info->ecc_opt == OMAP_ECC_HAM1_CODE_SW) + goto scan_tail; + /* all OOB bytes from oobfree->offset till end off OOB are free */ ecclayout->oobfree->length = mtd->oobsize - ecclayout->oobfree->offset; /* check if NAND device's OOB is enough to store ECC signatures */ @@ -2021,7 +2027,9 @@ static int omap_nand_probe(struct platform_device *pdev) err = -EINVAL; goto return_error; } + nand_chip->ecc.layout = ecclayout; +scan_tail: /* second phase scan */ if (nand_scan_tail(mtd)) { err = -ENXIO; diff --git a/include/linux/platform_data/mtd-nand-omap2.h b/include/linux/platform_data/mtd-nand-omap2.h index 660c029d694f..16ec262dfcc8 100644 --- a/include/linux/platform_data/mtd-nand-omap2.h +++ b/include/linux/platform_data/mtd-nand-omap2.h @@ -21,8 +21,17 @@ enum nand_io { }; enum omap_ecc { - /* 1-bit ECC calculation by GPMC, Error detection by Software */ - OMAP_ECC_HAM1_CODE_HW = 0, + /* + * 1-bit ECC: calculation and correction by SW + * ECC stored at end of spare area + */ + OMAP_ECC_HAM1_CODE_SW = 0, + + /* + * 1-bit ECC: calculation by GPMC, Error detection by Software + * ECC layout compatible with ROM code layout + */ + OMAP_ECC_HAM1_CODE_HW, /* 4-bit ECC calculation by GPMC, Error detection by Software */ OMAP_ECC_BCH4_CODE_HW_DETECTION_SW, /* 4-bit ECC calculation by GPMC, Error detection by ELM */ -- cgit v1.2.3 From 1f58d9465c568eb47cab939bbc4f30ae51863295 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 8 Aug 2014 13:06:30 +0200 Subject: dma-buf/fence: Fix one more kerneldoc warning The seqno_fence_init() function's cond argument isn't described in the kerneldoc comment. Fix that to silence a warning when building DocBook documentation. Signed-off-by: Thierry Reding Signed-off-by: Sumit Semwal --- include/linux/seqno-fence.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/seqno-fence.h b/include/linux/seqno-fence.h index 3d6003de4b0d..a1ba6a5ccdd6 100644 --- a/include/linux/seqno-fence.h +++ b/include/linux/seqno-fence.h @@ -62,6 +62,7 @@ to_seqno_fence(struct fence *fence) * @context: the execution context this fence is a part of * @seqno_ofs: the offset within @sync_buf * @seqno: the sequence # to signal on + * @cond: fence wait condition * @ops: the fence_ops for operations on this seqno fence * * This function initializes a struct seqno_fence with passed parameters, -- cgit v1.2.3 From db9ee220361de03ee86388f9ea5e529eaad5323c Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 27 Aug 2014 18:40:07 -0400 Subject: jbd2: fix descriptor block size handling errors with journal_csum It turns out that there are some serious problems with the on-disk format of journal checksum v2. The foremost is that the function to calculate descriptor tag size returns sizes that are too big. This causes alignment issues on some architectures and is compounded by the fact that some parts of jbd2 use the structure size (incorrectly) to determine the presence of a 64bit journal instead of checking the feature flags. Therefore, introduce journal checksum v3, which enlarges the descriptor block tag format to allow for full 32-bit checksums of journal blocks, fix the journal tag function to return the correct sizes, and fix the jbd2 recovery code to use feature flags to determine 64bitness. Add a few function helpers so we don't have to open-code quite so many pieces. Switching to a 16-byte block size was found to increase journal size overhead by a maximum of 0.1%, to convert a 32-bit journal with no checksumming to a 32-bit journal with checksum v3 enabled. Signed-off-by: Darrick J. Wong Reported-by: TR Reardon Signed-off-by: Theodore Ts'o Cc: stable@vger.kernel.org --- fs/ext4/super.c | 5 +++-- fs/jbd2/commit.c | 21 +++++++++++--------- fs/jbd2/journal.c | 56 ++++++++++++++++++++++++++++++++++------------------ fs/jbd2/recovery.c | 26 +++++++++++++----------- fs/jbd2/revoke.c | 6 +++--- include/linux/jbd2.h | 30 +++++++++++++++++++++++----- 6 files changed, 95 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 32b43ad154b9..0b28b36e7915 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3181,9 +3181,9 @@ static int set_journal_csum_feature_set(struct super_block *sb) if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) { - /* journal checksum v2 */ + /* journal checksum v3 */ compat = 0; - incompat = JBD2_FEATURE_INCOMPAT_CSUM_V2; + incompat = JBD2_FEATURE_INCOMPAT_CSUM_V3; } else { /* journal checksum v1 */ compat = JBD2_FEATURE_COMPAT_CHECKSUM; @@ -3205,6 +3205,7 @@ static int set_journal_csum_feature_set(struct super_block *sb) jbd2_journal_clear_features(sbi->s_journal, JBD2_FEATURE_COMPAT_CHECKSUM, 0, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | + JBD2_FEATURE_INCOMPAT_CSUM_V3 | JBD2_FEATURE_INCOMPAT_CSUM_V2); } diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 6fac74349856..b73e0215baa7 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -97,7 +97,7 @@ static void jbd2_commit_block_csum_set(journal_t *j, struct buffer_head *bh) struct commit_header *h; __u32 csum; - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return; h = (struct commit_header *)(bh->b_data); @@ -313,11 +313,11 @@ static __u32 jbd2_checksum_data(__u32 crc32_sum, struct buffer_head *bh) return checksum; } -static void write_tag_block(int tag_bytes, journal_block_tag_t *tag, +static void write_tag_block(journal_t *j, journal_block_tag_t *tag, unsigned long long block) { tag->t_blocknr = cpu_to_be32(block & (u32)~0); - if (tag_bytes > JBD2_TAG_SIZE32) + if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_64BIT)) tag->t_blocknr_high = cpu_to_be32((block >> 31) >> 1); } @@ -327,7 +327,7 @@ static void jbd2_descr_block_csum_set(journal_t *j, struct jbd2_journal_block_tail *tail; __u32 csum; - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return; tail = (struct jbd2_journal_block_tail *)(bh->b_data + j->j_blocksize - @@ -340,12 +340,13 @@ static void jbd2_descr_block_csum_set(journal_t *j, static void jbd2_block_tag_csum_set(journal_t *j, journal_block_tag_t *tag, struct buffer_head *bh, __u32 sequence) { + journal_block_tag3_t *tag3 = (journal_block_tag3_t *)tag; struct page *page = bh->b_page; __u8 *addr; __u32 csum32; __be32 seq; - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return; seq = cpu_to_be32(sequence); @@ -355,8 +356,10 @@ static void jbd2_block_tag_csum_set(journal_t *j, journal_block_tag_t *tag, bh->b_size); kunmap_atomic(addr); - /* We only have space to store the lower 16 bits of the crc32c. */ - tag->t_checksum = cpu_to_be16(csum32); + if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V3)) + tag3->t_checksum = cpu_to_be32(csum32); + else + tag->t_checksum = cpu_to_be16(csum32); } /* * jbd2_journal_commit_transaction @@ -396,7 +399,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) LIST_HEAD(io_bufs); LIST_HEAD(log_bufs); - if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (jbd2_journal_has_csum_v2or3(journal)) csum_size = sizeof(struct jbd2_journal_block_tail); /* @@ -690,7 +693,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) tag_flag |= JBD2_FLAG_SAME_UUID; tag = (journal_block_tag_t *) tagp; - write_tag_block(tag_bytes, tag, jh2bh(jh)->b_blocknr); + write_tag_block(journal, tag, jh2bh(jh)->b_blocknr); tag->t_flags = cpu_to_be16(tag_flag); jbd2_block_tag_csum_set(journal, tag, wbuf[bufs], commit_transaction->t_tid); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 67b8e303946c..19d74d86d99c 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -124,7 +124,7 @@ EXPORT_SYMBOL(__jbd2_debug); /* Checksumming functions */ static int jbd2_verify_csum_type(journal_t *j, journal_superblock_t *sb) { - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return 1; return sb->s_checksum_type == JBD2_CRC32C_CHKSUM; @@ -145,7 +145,7 @@ static __be32 jbd2_superblock_csum(journal_t *j, journal_superblock_t *sb) static int jbd2_superblock_csum_verify(journal_t *j, journal_superblock_t *sb) { - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return 1; return sb->s_checksum == jbd2_superblock_csum(j, sb); @@ -153,7 +153,7 @@ static int jbd2_superblock_csum_verify(journal_t *j, journal_superblock_t *sb) static void jbd2_superblock_csum_set(journal_t *j, journal_superblock_t *sb) { - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return; sb->s_checksum = jbd2_superblock_csum(j, sb); @@ -1522,21 +1522,29 @@ static int journal_get_superblock(journal_t *journal) goto out; } - if (JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM) && - JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) { + if (jbd2_journal_has_csum_v2or3(journal) && + JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM)) { /* Can't have checksum v1 and v2 on at the same time! */ printk(KERN_ERR "JBD2: Can't enable checksumming v1 and v2 " "at the same time!\n"); goto out; } + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2) && + JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3)) { + /* Can't have checksum v2 and v3 at the same time! */ + printk(KERN_ERR "JBD2: Can't enable checksumming v2 and v3 " + "at the same time!\n"); + goto out; + } + if (!jbd2_verify_csum_type(journal, sb)) { printk(KERN_ERR "JBD2: Unknown checksum type\n"); goto out; } /* Load the checksum driver */ - if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) { + if (jbd2_journal_has_csum_v2or3(journal)) { journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); if (IS_ERR(journal->j_chksum_driver)) { printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n"); @@ -1553,7 +1561,7 @@ static int journal_get_superblock(journal_t *journal) } /* Precompute checksum seed for all metadata */ - if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (jbd2_journal_has_csum_v2or3(journal)) journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid, sizeof(sb->s_uuid)); @@ -1813,8 +1821,14 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat, if (!jbd2_journal_check_available_features(journal, compat, ro, incompat)) return 0; - /* Asking for checksumming v2 and v1? Only give them v2. */ - if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V2 && + /* If enabling v2 checksums, turn on v3 instead */ + if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V2) { + incompat &= ~JBD2_FEATURE_INCOMPAT_CSUM_V2; + incompat |= JBD2_FEATURE_INCOMPAT_CSUM_V3; + } + + /* Asking for checksumming v3 and v1? Only give them v3. */ + if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V3 && compat & JBD2_FEATURE_COMPAT_CHECKSUM) compat &= ~JBD2_FEATURE_COMPAT_CHECKSUM; @@ -1823,8 +1837,8 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat, sb = journal->j_superblock; - /* If enabling v2 checksums, update superblock */ - if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V2)) { + /* If enabling v3 checksums, update superblock */ + if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) { sb->s_checksum_type = JBD2_CRC32C_CHKSUM; sb->s_feature_compat &= ~cpu_to_be32(JBD2_FEATURE_COMPAT_CHECKSUM); @@ -1842,8 +1856,7 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat, } /* Precompute checksum seed for all metadata */ - if (JBD2_HAS_INCOMPAT_FEATURE(journal, - JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (jbd2_journal_has_csum_v2or3(journal)) journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid, sizeof(sb->s_uuid)); @@ -1852,7 +1865,8 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat, /* If enabling v1 checksums, downgrade superblock */ if (COMPAT_FEATURE_ON(JBD2_FEATURE_COMPAT_CHECKSUM)) sb->s_feature_incompat &= - ~cpu_to_be32(JBD2_FEATURE_INCOMPAT_CSUM_V2); + ~cpu_to_be32(JBD2_FEATURE_INCOMPAT_CSUM_V2 | + JBD2_FEATURE_INCOMPAT_CSUM_V3); sb->s_feature_compat |= cpu_to_be32(compat); sb->s_feature_ro_compat |= cpu_to_be32(ro); @@ -2165,16 +2179,20 @@ int jbd2_journal_blocks_per_page(struct inode *inode) */ size_t journal_tag_bytes(journal_t *journal) { - journal_block_tag_t tag; - size_t x = 0; + size_t sz; + + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3)) + return sizeof(journal_block_tag3_t); + + sz = sizeof(journal_block_tag_t); if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) - x += sizeof(tag.t_checksum); + sz += sizeof(__u16); if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) - return x + JBD2_TAG_SIZE64; + return sz; else - return x + JBD2_TAG_SIZE32; + return sz - sizeof(__u32); } /* diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index 00e9703d7dc6..9b329b55ffe3 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -181,7 +181,7 @@ static int jbd2_descr_block_csum_verify(journal_t *j, __be32 provided; __u32 calculated; - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return 1; tail = (struct jbd2_journal_block_tail *)(buf + j->j_blocksize - @@ -205,7 +205,7 @@ static int count_tags(journal_t *journal, struct buffer_head *bh) int nr = 0, size = journal->j_blocksize; int tag_bytes = journal_tag_bytes(journal); - if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (jbd2_journal_has_csum_v2or3(journal)) size -= sizeof(struct jbd2_journal_block_tail); tagp = &bh->b_data[sizeof(journal_header_t)]; @@ -338,10 +338,11 @@ int jbd2_journal_skip_recovery(journal_t *journal) return err; } -static inline unsigned long long read_tag_block(int tag_bytes, journal_block_tag_t *tag) +static inline unsigned long long read_tag_block(journal_t *journal, + journal_block_tag_t *tag) { unsigned long long block = be32_to_cpu(tag->t_blocknr); - if (tag_bytes > JBD2_TAG_SIZE32) + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) block |= (u64)be32_to_cpu(tag->t_blocknr_high) << 32; return block; } @@ -384,7 +385,7 @@ static int jbd2_commit_block_csum_verify(journal_t *j, void *buf) __be32 provided; __u32 calculated; - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return 1; h = buf; @@ -399,17 +400,21 @@ static int jbd2_commit_block_csum_verify(journal_t *j, void *buf) static int jbd2_block_tag_csum_verify(journal_t *j, journal_block_tag_t *tag, void *buf, __u32 sequence) { + journal_block_tag3_t *tag3 = (journal_block_tag3_t *)tag; __u32 csum32; __be32 seq; - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return 1; seq = cpu_to_be32(sequence); csum32 = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&seq, sizeof(seq)); csum32 = jbd2_chksum(j, csum32, buf, j->j_blocksize); - return tag->t_checksum == cpu_to_be16(csum32); + if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V3)) + return tag3->t_checksum == cpu_to_be32(csum32); + else + return tag->t_checksum == cpu_to_be16(csum32); } static int do_one_pass(journal_t *journal, @@ -513,8 +518,7 @@ static int do_one_pass(journal_t *journal, switch(blocktype) { case JBD2_DESCRIPTOR_BLOCK: /* Verify checksum first */ - if (JBD2_HAS_INCOMPAT_FEATURE(journal, - JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (jbd2_journal_has_csum_v2or3(journal)) descr_csum_size = sizeof(struct jbd2_journal_block_tail); if (descr_csum_size > 0 && @@ -575,7 +579,7 @@ static int do_one_pass(journal_t *journal, unsigned long long blocknr; J_ASSERT(obh != NULL); - blocknr = read_tag_block(tag_bytes, + blocknr = read_tag_block(journal, tag); /* If the block has been @@ -814,7 +818,7 @@ static int jbd2_revoke_block_csum_verify(journal_t *j, __be32 provided; __u32 calculated; - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return 1; tail = (struct jbd2_journal_revoke_tail *)(buf + j->j_blocksize - diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c index 198c9c10276d..d5e95a175c92 100644 --- a/fs/jbd2/revoke.c +++ b/fs/jbd2/revoke.c @@ -91,8 +91,8 @@ #include #include #include -#endif #include +#endif static struct kmem_cache *jbd2_revoke_record_cache; static struct kmem_cache *jbd2_revoke_table_cache; @@ -597,7 +597,7 @@ static void write_one_revoke_record(journal_t *journal, offset = *offsetp; /* Do we need to leave space at the end for a checksum? */ - if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (jbd2_journal_has_csum_v2or3(journal)) csum_size = sizeof(struct jbd2_journal_revoke_tail); /* Make sure we have a descriptor with space left for the record */ @@ -644,7 +644,7 @@ static void jbd2_revoke_csum_set(journal_t *j, struct buffer_head *bh) struct jbd2_journal_revoke_tail *tail; __u32 csum; - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return; tail = (struct jbd2_journal_revoke_tail *)(bh->b_data + j->j_blocksize - diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index d5b50a19463c..0dae71e9971c 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -159,7 +159,11 @@ typedef struct journal_header_s * journal_block_tag (in the descriptor). The other h_chksum* fields are * not used. * - * Checksum v1 and v2 are mutually exclusive features. + * If FEATURE_INCOMPAT_CSUM_V3 is set, the descriptor block uses + * journal_block_tag3_t to store a full 32-bit checksum. Everything else + * is the same as v2. + * + * Checksum v1, v2, and v3 are mutually exclusive features. */ struct commit_header { __be32 h_magic; @@ -179,6 +183,14 @@ struct commit_header { * raw struct shouldn't be used for pointer math or sizeof() - use * journal_tag_bytes(journal) instead to compute this. */ +typedef struct journal_block_tag3_s +{ + __be32 t_blocknr; /* The on-disk block number */ + __be32 t_flags; /* See below */ + __be32 t_blocknr_high; /* most-significant high 32bits. */ + __be32 t_checksum; /* crc32c(uuid+seq+block) */ +} journal_block_tag3_t; + typedef struct journal_block_tag_s { __be32 t_blocknr; /* The on-disk block number */ @@ -187,9 +199,6 @@ typedef struct journal_block_tag_s __be32 t_blocknr_high; /* most-significant high 32bits. */ } journal_block_tag_t; -#define JBD2_TAG_SIZE32 (offsetof(journal_block_tag_t, t_blocknr_high)) -#define JBD2_TAG_SIZE64 (sizeof(journal_block_tag_t)) - /* Tail of descriptor block, for checksumming */ struct jbd2_journal_block_tail { __be32 t_checksum; /* crc32c(uuid+descr_block) */ @@ -284,6 +293,7 @@ typedef struct journal_superblock_s #define JBD2_FEATURE_INCOMPAT_64BIT 0x00000002 #define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT 0x00000004 #define JBD2_FEATURE_INCOMPAT_CSUM_V2 0x00000008 +#define JBD2_FEATURE_INCOMPAT_CSUM_V3 0x00000010 /* Features known to this kernel version: */ #define JBD2_KNOWN_COMPAT_FEATURES JBD2_FEATURE_COMPAT_CHECKSUM @@ -291,7 +301,8 @@ typedef struct journal_superblock_s #define JBD2_KNOWN_INCOMPAT_FEATURES (JBD2_FEATURE_INCOMPAT_REVOKE | \ JBD2_FEATURE_INCOMPAT_64BIT | \ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | \ - JBD2_FEATURE_INCOMPAT_CSUM_V2) + JBD2_FEATURE_INCOMPAT_CSUM_V2 | \ + JBD2_FEATURE_INCOMPAT_CSUM_V3) #ifdef __KERNEL__ @@ -1296,6 +1307,15 @@ static inline int tid_geq(tid_t x, tid_t y) extern int jbd2_journal_blocks_per_page(struct inode *inode); extern size_t journal_tag_bytes(journal_t *journal); +static inline int jbd2_journal_has_csum_v2or3(journal_t *journal) +{ + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2) || + JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3)) + return 1; + + return 0; +} + /* * We reserve t_outstanding_credits >> JBD2_CONTROL_BLOCKS_SHIFT for * transaction control blocks. -- cgit v1.2.3