From 4e4438b86527e8bf1f49503a30d487e401e64f9c Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Wed, 1 Sep 2010 08:55:24 -0600 Subject: gpiolib: Add 'struct gpio_chip' forward declaration for !GPIOLIB case With CONFIG_GPIOLIB=n, the 'struct gpio_chip' is not declared, so the following pops up on PowerPC: cc1: warnings being treated as errors In file included from arch/powerpc/platforms/52xx/mpc52xx_common.c:19: include/linux/of_gpio.h:74: warning: 'struct gpio_chip' declared inside parameter list include/linux/of_gpio.h:74: warning: its scope is only this definition or declaration, which is probably not what you want include/linux/of_gpio.h:75: warning: 'struct gpio_chip' declared inside parameter list make[2]: *** [arch/powerpc/platforms/52xx/mpc52xx_common.o] Error 1 This patch fixes the issue by providing the proper forward declaration. Signed-off-by: Anton Vorontsov Signed-off-by: Grant Likely --- include/linux/gpio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/gpio.h b/include/linux/gpio.h index 03f616b78cfa..e41f7dd1ae67 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -13,6 +13,7 @@ #include struct device; +struct gpio_chip; /* * Some platforms don't support the GPIO programming interface. -- cgit v1.2.3-71-gd317 From e3e55ff5854655d8723ad8b307f02515aecc3df5 Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Tue, 7 Sep 2010 15:52:06 +0800 Subject: spi/dw_spi: clean the cs_control code commit 052dc7c45i "spi/dw_spi: conditional transfer mode change" introduced cs_control code, which has a bug by using bit offset for spi mode to set transfer mode in control register. Also it forces devices who don't need cs_control to re-configure the control registers for each spi transfer. This patch will fix them Signed-off-by: Feng Tang Signed-off-by: Grant Likely --- drivers/spi/dw_spi.c | 17 +++++------------ include/linux/spi/dw_spi.h | 2 ++ 2 files changed, 7 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/spi/dw_spi.c b/drivers/spi/dw_spi.c index 11fbbf6fb07b..56247853c298 100644 --- a/drivers/spi/dw_spi.c +++ b/drivers/spi/dw_spi.c @@ -181,10 +181,6 @@ static void flush(struct dw_spi *dws) wait_till_not_busy(dws); } -static void null_cs_control(u32 command) -{ -} - static int null_writer(struct dw_spi *dws) { u8 n_bytes = dws->n_bytes; @@ -322,7 +318,7 @@ static void giveback(struct dw_spi *dws) struct spi_transfer, transfer_list); - if (!last_transfer->cs_change) + if (!last_transfer->cs_change && dws->cs_control) dws->cs_control(MRST_SPI_DEASSERT); msg->state = NULL; @@ -549,13 +545,13 @@ static void pump_transfers(unsigned long data) */ if (dws->cs_control) { if (dws->rx && dws->tx) - chip->tmode = 0x00; + chip->tmode = SPI_TMOD_TR; else if (dws->rx) - chip->tmode = 0x02; + chip->tmode = SPI_TMOD_RO; else - chip->tmode = 0x01; + chip->tmode = SPI_TMOD_TO; - cr0 &= ~(0x3 << SPI_MODE_OFFSET); + cr0 &= ~SPI_TMOD_MASK; cr0 |= (chip->tmode << SPI_TMOD_OFFSET); } @@ -704,9 +700,6 @@ static int dw_spi_setup(struct spi_device *spi) chip = kzalloc(sizeof(struct chip_data), GFP_KERNEL); if (!chip) return -ENOMEM; - - chip->cs_control = null_cs_control; - chip->enable_dma = 0; } /* diff --git a/include/linux/spi/dw_spi.h b/include/linux/spi/dw_spi.h index cc813f95a2f2..c91302f3a257 100644 --- a/include/linux/spi/dw_spi.h +++ b/include/linux/spi/dw_spi.h @@ -14,7 +14,9 @@ #define SPI_MODE_OFFSET 6 #define SPI_SCPH_OFFSET 6 #define SPI_SCOL_OFFSET 7 + #define SPI_TMOD_OFFSET 8 +#define SPI_TMOD_MASK (0x3 << SPI_TMOD_OFFSET) #define SPI_TMOD_TR 0x0 /* xmit & recv */ #define SPI_TMOD_TO 0x1 /* xmit only */ #define SPI_TMOD_RO 0x2 /* recv only */ -- cgit v1.2.3-71-gd317 From d530148ae8bffe1b33f50d1776d185a6e85dc774 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Fri, 20 Aug 2010 16:49:43 +0800 Subject: dquot: do full inode dirty in allocating space Alex Shi found a regression when doing ffsb test. The test has several threads, and each thread creates a small file, write to it and then delete it. ffsb reports about 20% regression and Alex bisected it to 43d2932d88e4. The test will call __mark_inode_dirty 3 times. without this commit, we only take inode_lock one time, while with it, we take the lock 3 times with flags ( I_DIRTY_SYNC,I_DIRTY_PAGES,I_DIRTY). Perf shows the lock contention increased too much. Below proposed patch fixes it. fs is allocating blocks, which usually means file writes and the inode will be dirtied soon. We fully dirty the inode to reduce some inode_lock contention in several calls of __mark_inode_dirty. Jan Kara: Added comment. Signed-off-by: Shaohua Li Signed-off-by: Alex Shi Signed-off-by: Jan Kara --- include/linux/quotaops.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index d50ba858cfe0..d1a9193960f1 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -274,8 +274,14 @@ static inline int dquot_alloc_space(struct inode *inode, qsize_t nr) int ret; ret = dquot_alloc_space_nodirty(inode, nr); - if (!ret) - mark_inode_dirty_sync(inode); + if (!ret) { + /* + * Mark inode fully dirty. Since we are allocating blocks, inode + * would become fully dirty soon anyway and it reportedly + * reduces inode_lock contention. + */ + mark_inode_dirty(inode); + } return ret; } -- cgit v1.2.3-71-gd317 From 006abe887c5e637d059c44310de6c92f36aded3b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 12 Sep 2010 19:55:25 -0400 Subject: SUNRPC: Fix a race in rpc_info_open There is a race between rpc_info_open and rpc_release_client() in that nothing stops a process from opening the file after the clnt->cl_kref goes to zero. Fix this by using atomic_inc_unless_zero()... Reported-by: J. Bruce Fields Signed-off-by: Trond Myklebust Cc: stable@kernel.org --- include/linux/sunrpc/clnt.h | 2 +- net/sunrpc/clnt.c | 26 ++++++++++++-------------- net/sunrpc/rpc_pipe.c | 14 ++++++++------ 3 files changed, 21 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 569dc722a600..85f38a63f098 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -30,7 +30,7 @@ struct rpc_inode; * The high-level client handle */ struct rpc_clnt { - struct kref cl_kref; /* Number of references */ + atomic_t cl_count; /* Number of references */ struct list_head cl_clients; /* Global list of clients */ struct list_head cl_tasks; /* List of tasks */ spinlock_t cl_lock; /* spinlock */ diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 657aac630fc9..3a8f53e7ba07 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -226,7 +226,7 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, stru goto out_no_principal; } - kref_init(&clnt->cl_kref); + atomic_set(&clnt->cl_count, 1); err = rpc_setup_pipedir(clnt, program->pipe_dir_name); if (err < 0) @@ -390,14 +390,14 @@ rpc_clone_client(struct rpc_clnt *clnt) if (new->cl_principal == NULL) goto out_no_principal; } - kref_init(&new->cl_kref); + atomic_set(&new->cl_count, 1); err = rpc_setup_pipedir(new, clnt->cl_program->pipe_dir_name); if (err != 0) goto out_no_path; if (new->cl_auth) atomic_inc(&new->cl_auth->au_count); xprt_get(clnt->cl_xprt); - kref_get(&clnt->cl_kref); + atomic_inc(&clnt->cl_count); rpc_register_client(new); rpciod_up(); return new; @@ -465,10 +465,8 @@ EXPORT_SYMBOL_GPL(rpc_shutdown_client); * Free an RPC client */ static void -rpc_free_client(struct kref *kref) +rpc_free_client(struct rpc_clnt *clnt) { - struct rpc_clnt *clnt = container_of(kref, struct rpc_clnt, cl_kref); - dprintk("RPC: destroying %s client for %s\n", clnt->cl_protname, clnt->cl_server); if (!IS_ERR(clnt->cl_path.dentry)) { @@ -495,12 +493,10 @@ out_free: * Free an RPC client */ static void -rpc_free_auth(struct kref *kref) +rpc_free_auth(struct rpc_clnt *clnt) { - struct rpc_clnt *clnt = container_of(kref, struct rpc_clnt, cl_kref); - if (clnt->cl_auth == NULL) { - rpc_free_client(kref); + rpc_free_client(clnt); return; } @@ -509,10 +505,11 @@ rpc_free_auth(struct kref *kref) * release remaining GSS contexts. This mechanism ensures * that it can do so safely. */ - kref_init(kref); + atomic_inc(&clnt->cl_count); rpcauth_release(clnt->cl_auth); clnt->cl_auth = NULL; - kref_put(kref, rpc_free_client); + if (atomic_dec_and_test(&clnt->cl_count)) + rpc_free_client(clnt); } /* @@ -525,7 +522,8 @@ rpc_release_client(struct rpc_clnt *clnt) if (list_empty(&clnt->cl_tasks)) wake_up(&destroy_wait); - kref_put(&clnt->cl_kref, rpc_free_auth); + if (atomic_dec_and_test(&clnt->cl_count)) + rpc_free_auth(clnt); } /** @@ -588,7 +586,7 @@ void rpc_task_set_client(struct rpc_task *task, struct rpc_clnt *clnt) if (clnt != NULL) { rpc_task_release_client(task); task->tk_client = clnt; - kref_get(&clnt->cl_kref); + atomic_inc(&clnt->cl_count); if (clnt->cl_softrtry) task->tk_flags |= RPC_TASK_SOFT; /* Add to the client's list of all tasks */ diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 41a762f82630..8c8eef2b8f26 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -371,21 +371,23 @@ rpc_show_info(struct seq_file *m, void *v) static int rpc_info_open(struct inode *inode, struct file *file) { - struct rpc_clnt *clnt; + struct rpc_clnt *clnt = NULL; int ret = single_open(file, rpc_show_info, NULL); if (!ret) { struct seq_file *m = file->private_data; - mutex_lock(&inode->i_mutex); - clnt = RPC_I(inode)->private; - if (clnt) { - kref_get(&clnt->cl_kref); + + spin_lock(&file->f_path.dentry->d_lock); + if (!d_unhashed(file->f_path.dentry)) + clnt = RPC_I(inode)->private; + if (clnt != NULL && atomic_inc_not_zero(&clnt->cl_count)) { + spin_unlock(&file->f_path.dentry->d_lock); m->private = clnt; } else { + spin_unlock(&file->f_path.dentry->d_lock); single_release(inode, file); ret = -EINVAL; } - mutex_unlock(&inode->i_mutex); } return ret; } -- cgit v1.2.3-71-gd317 From c54fce6eff197d9c57c97afbf6c9722ce434fc8f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 10 Sep 2010 16:51:36 +0200 Subject: workqueue: add documentation Update copyright notice and add Documentation/workqueue.txt. Randy Dunlap, Dave Chinner: misc fixes. Signed-off-by: Tejun Heo Reviewed-By: Florian Mickler Cc: Ingo Molnar Cc: Christoph Lameter Cc: Randy Dunlap Cc: Dave Chinner --- Documentation/workqueue.txt | 380 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/workqueue.h | 4 + kernel/workqueue.c | 27 ++-- 3 files changed, 401 insertions(+), 10 deletions(-) create mode 100644 Documentation/workqueue.txt (limited to 'include/linux') diff --git a/Documentation/workqueue.txt b/Documentation/workqueue.txt new file mode 100644 index 000000000000..e4498a2872c3 --- /dev/null +++ b/Documentation/workqueue.txt @@ -0,0 +1,380 @@ + +Concurrency Managed Workqueue (cmwq) + +September, 2010 Tejun Heo + Florian Mickler + +CONTENTS + +1. Introduction +2. Why cmwq? +3. The Design +4. Application Programming Interface (API) +5. Example Execution Scenarios +6. Guidelines + + +1. Introduction + +There are many cases where an asynchronous process execution context +is needed and the workqueue (wq) API is the most commonly used +mechanism for such cases. + +When such an asynchronous execution context is needed, a work item +describing which function to execute is put on a queue. An +independent thread serves as the asynchronous execution context. The +queue is called workqueue and the thread is called worker. + +While there are work items on the workqueue the worker executes the +functions associated with the work items one after the other. When +there is no work item left on the workqueue the worker becomes idle. +When a new work item gets queued, the worker begins executing again. + + +2. Why cmwq? + +In the original wq implementation, a multi threaded (MT) wq had one +worker thread per CPU and a single threaded (ST) wq had one worker +thread system-wide. A single MT wq needed to keep around the same +number of workers as the number of CPUs. The kernel grew a lot of MT +wq users over the years and with the number of CPU cores continuously +rising, some systems saturated the default 32k PID space just booting +up. + +Although MT wq wasted a lot of resource, the level of concurrency +provided was unsatisfactory. The limitation was common to both ST and +MT wq albeit less severe on MT. Each wq maintained its own separate +worker pool. A MT wq could provide only one execution context per CPU +while a ST wq one for the whole system. Work items had to compete for +those very limited execution contexts leading to various problems +including proneness to deadlocks around the single execution context. + +The tension between the provided level of concurrency and resource +usage also forced its users to make unnecessary tradeoffs like libata +choosing to use ST wq for polling PIOs and accepting an unnecessary +limitation that no two polling PIOs can progress at the same time. As +MT wq don't provide much better concurrency, users which require +higher level of concurrency, like async or fscache, had to implement +their own thread pool. + +Concurrency Managed Workqueue (cmwq) is a reimplementation of wq with +focus on the following goals. + +* Maintain compatibility with the original workqueue API. + +* Use per-CPU unified worker pools shared by all wq to provide + flexible level of concurrency on demand without wasting a lot of + resource. + +* Automatically regulate worker pool and level of concurrency so that + the API users don't need to worry about such details. + + +3. The Design + +In order to ease the asynchronous execution of functions a new +abstraction, the work item, is introduced. + +A work item is a simple struct that holds a pointer to the function +that is to be executed asynchronously. Whenever a driver or subsystem +wants a function to be executed asynchronously it has to set up a work +item pointing to that function and queue that work item on a +workqueue. + +Special purpose threads, called worker threads, execute the functions +off of the queue, one after the other. If no work is queued, the +worker threads become idle. These worker threads are managed in so +called thread-pools. + +The cmwq design differentiates between the user-facing workqueues that +subsystems and drivers queue work items on and the backend mechanism +which manages thread-pool and processes the queued work items. + +The backend is called gcwq. There is one gcwq for each possible CPU +and one gcwq to serve work items queued on unbound workqueues. + +Subsystems and drivers can create and queue work items through special +workqueue API functions as they see fit. They can influence some +aspects of the way the work items are executed by setting flags on the +workqueue they are putting the work item on. These flags include +things like CPU locality, reentrancy, concurrency limits and more. To +get a detailed overview refer to the API description of +alloc_workqueue() below. + +When a work item is queued to a workqueue, the target gcwq is +determined according to the queue parameters and workqueue attributes +and appended on the shared worklist of the gcwq. For example, unless +specifically overridden, a work item of a bound workqueue will be +queued on the worklist of exactly that gcwq that is associated to the +CPU the issuer is running on. + +For any worker pool implementation, managing the concurrency level +(how many execution contexts are active) is an important issue. cmwq +tries to keep the concurrency at a minimal but sufficient level. +Minimal to save resources and sufficient in that the system is used at +its full capacity. + +Each gcwq bound to an actual CPU implements concurrency management by +hooking into the scheduler. The gcwq is notified whenever an active +worker wakes up or sleeps and keeps track of the number of the +currently runnable workers. Generally, work items are not expected to +hog a CPU and consume many cycles. That means maintaining just enough +concurrency to prevent work processing from stalling should be +optimal. As long as there are one or more runnable workers on the +CPU, the gcwq doesn't start execution of a new work, but, when the +last running worker goes to sleep, it immediately schedules a new +worker so that the CPU doesn't sit idle while there are pending work +items. This allows using a minimal number of workers without losing +execution bandwidth. + +Keeping idle workers around doesn't cost other than the memory space +for kthreads, so cmwq holds onto idle ones for a while before killing +them. + +For an unbound wq, the above concurrency management doesn't apply and +the gcwq for the pseudo unbound CPU tries to start executing all work +items as soon as possible. The responsibility of regulating +concurrency level is on the users. There is also a flag to mark a +bound wq to ignore the concurrency management. Please refer to the +API section for details. + +Forward progress guarantee relies on that workers can be created when +more execution contexts are necessary, which in turn is guaranteed +through the use of rescue workers. All work items which might be used +on code paths that handle memory reclaim are required to be queued on +wq's that have a rescue-worker reserved for execution under memory +pressure. Else it is possible that the thread-pool deadlocks waiting +for execution contexts to free up. + + +4. Application Programming Interface (API) + +alloc_workqueue() allocates a wq. The original create_*workqueue() +functions are deprecated and scheduled for removal. alloc_workqueue() +takes three arguments - @name, @flags and @max_active. @name is the +name of the wq and also used as the name of the rescuer thread if +there is one. + +A wq no longer manages execution resources but serves as a domain for +forward progress guarantee, flush and work item attributes. @flags +and @max_active control how work items are assigned execution +resources, scheduled and executed. + +@flags: + + WQ_NON_REENTRANT + + By default, a wq guarantees non-reentrance only on the same + CPU. A work item may not be executed concurrently on the same + CPU by multiple workers but is allowed to be executed + concurrently on multiple CPUs. This flag makes sure + non-reentrance is enforced across all CPUs. Work items queued + to a non-reentrant wq are guaranteed to be executed by at most + one worker system-wide at any given time. + + WQ_UNBOUND + + Work items queued to an unbound wq are served by a special + gcwq which hosts workers which are not bound to any specific + CPU. This makes the wq behave as a simple execution context + provider without concurrency management. The unbound gcwq + tries to start execution of work items as soon as possible. + Unbound wq sacrifices locality but is useful for the following + cases. + + * Wide fluctuation in the concurrency level requirement is + expected and using bound wq may end up creating large number + of mostly unused workers across different CPUs as the issuer + hops through different CPUs. + + * Long running CPU intensive workloads which can be better + managed by the system scheduler. + + WQ_FREEZEABLE + + A freezeable wq participates in the freeze phase of the system + suspend operations. Work items on the wq are drained and no + new work item starts execution until thawed. + + WQ_RESCUER + + All wq which might be used in the memory reclaim paths _MUST_ + have this flag set. This reserves one worker exclusively for + the execution of this wq under memory pressure. + + WQ_HIGHPRI + + Work items of a highpri wq are queued at the head of the + worklist of the target gcwq and start execution regardless of + the current concurrency level. In other words, highpri work + items will always start execution as soon as execution + resource is available. + + Ordering among highpri work items is preserved - a highpri + work item queued after another highpri work item will start + execution after the earlier highpri work item starts. + + Although highpri work items are not held back by other + runnable work items, they still contribute to the concurrency + level. Highpri work items in runnable state will prevent + non-highpri work items from starting execution. + + This flag is meaningless for unbound wq. + + WQ_CPU_INTENSIVE + + Work items of a CPU intensive wq do not contribute to the + concurrency level. In other words, runnable CPU intensive + work items will not prevent other work items from starting + execution. This is useful for bound work items which are + expected to hog CPU cycles so that their execution is + regulated by the system scheduler. + + Although CPU intensive work items don't contribute to the + concurrency level, start of their executions is still + regulated by the concurrency management and runnable + non-CPU-intensive work items can delay execution of CPU + intensive work items. + + This flag is meaningless for unbound wq. + + WQ_HIGHPRI | WQ_CPU_INTENSIVE + + This combination makes the wq avoid interaction with + concurrency management completely and behave as a simple + per-CPU execution context provider. Work items queued on a + highpri CPU-intensive wq start execution as soon as resources + are available and don't affect execution of other work items. + +@max_active: + +@max_active determines the maximum number of execution contexts per +CPU which can be assigned to the work items of a wq. For example, +with @max_active of 16, at most 16 work items of the wq can be +executing at the same time per CPU. + +Currently, for a bound wq, the maximum limit for @max_active is 512 +and the default value used when 0 is specified is 256. For an unbound +wq, the limit is higher of 512 and 4 * num_possible_cpus(). These +values are chosen sufficiently high such that they are not the +limiting factor while providing protection in runaway cases. + +The number of active work items of a wq is usually regulated by the +users of the wq, more specifically, by how many work items the users +may queue at the same time. Unless there is a specific need for +throttling the number of active work items, specifying '0' is +recommended. + +Some users depend on the strict execution ordering of ST wq. The +combination of @max_active of 1 and WQ_UNBOUND is used to achieve this +behavior. Work items on such wq are always queued to the unbound gcwq +and only one work item can be active at any given time thus achieving +the same ordering property as ST wq. + + +5. Example Execution Scenarios + +The following example execution scenarios try to illustrate how cmwq +behave under different configurations. + + Work items w0, w1, w2 are queued to a bound wq q0 on the same CPU. + w0 burns CPU for 5ms then sleeps for 10ms then burns CPU for 5ms + again before finishing. w1 and w2 burn CPU for 5ms then sleep for + 10ms. + +Ignoring all other tasks, works and processing overhead, and assuming +simple FIFO scheduling, the following is one highly simplified version +of possible sequences of events with the original wq. + + TIME IN MSECS EVENT + 0 w0 starts and burns CPU + 5 w0 sleeps + 15 w0 wakes up and burns CPU + 20 w0 finishes + 20 w1 starts and burns CPU + 25 w1 sleeps + 35 w1 wakes up and finishes + 35 w2 starts and burns CPU + 40 w2 sleeps + 50 w2 wakes up and finishes + +And with cmwq with @max_active >= 3, + + TIME IN MSECS EVENT + 0 w0 starts and burns CPU + 5 w0 sleeps + 5 w1 starts and burns CPU + 10 w1 sleeps + 10 w2 starts and burns CPU + 15 w2 sleeps + 15 w0 wakes up and burns CPU + 20 w0 finishes + 20 w1 wakes up and finishes + 25 w2 wakes up and finishes + +If @max_active == 2, + + TIME IN MSECS EVENT + 0 w0 starts and burns CPU + 5 w0 sleeps + 5 w1 starts and burns CPU + 10 w1 sleeps + 15 w0 wakes up and burns CPU + 20 w0 finishes + 20 w1 wakes up and finishes + 20 w2 starts and burns CPU + 25 w2 sleeps + 35 w2 wakes up and finishes + +Now, let's assume w1 and w2 are queued to a different wq q1 which has +WQ_HIGHPRI set, + + TIME IN MSECS EVENT + 0 w1 and w2 start and burn CPU + 5 w1 sleeps + 10 w2 sleeps + 10 w0 starts and burns CPU + 15 w0 sleeps + 15 w1 wakes up and finishes + 20 w2 wakes up and finishes + 25 w0 wakes up and burns CPU + 30 w0 finishes + +If q1 has WQ_CPU_INTENSIVE set, + + TIME IN MSECS EVENT + 0 w0 starts and burns CPU + 5 w0 sleeps + 5 w1 and w2 start and burn CPU + 10 w1 sleeps + 15 w2 sleeps + 15 w0 wakes up and burns CPU + 20 w0 finishes + 20 w1 wakes up and finishes + 25 w2 wakes up and finishes + + +6. Guidelines + +* Do not forget to use WQ_RESCUER if a wq may process work items which + are used during memory reclaim. Each wq with WQ_RESCUER set has one + rescuer thread reserved for it. If there is dependency among + multiple work items used during memory reclaim, they should be + queued to separate wq each with WQ_RESCUER. + +* Unless strict ordering is required, there is no need to use ST wq. + +* Unless there is a specific need, using 0 for @max_active is + recommended. In most use cases, concurrency level usually stays + well under the default limit. + +* A wq serves as a domain for forward progress guarantee (WQ_RESCUER), + flush and work item attributes. Work items which are not involved + in memory reclaim and don't need to be flushed as a part of a group + of work items, and don't require any special attribute, can use one + of the system wq. There is no difference in execution + characteristics between using a dedicated wq and a system wq. + +* Unless work items are expected to consume a huge amount of CPU + cycles, using a bound wq is usually beneficial due to the increased + level of locality in wq operations and work item execution. diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index f11100f96482..25e02c941bac 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -235,6 +235,10 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } #define work_clear_pending(work) \ clear_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) +/* + * Workqueue flags and constants. For details, please refer to + * Documentation/workqueue.txt. + */ enum { WQ_NON_REENTRANT = 1 << 0, /* guarantee non-reentrance */ WQ_UNBOUND = 1 << 1, /* not bound to any cpu */ diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 727f24e563ae..f77afd939229 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1,19 +1,26 @@ /* - * linux/kernel/workqueue.c + * kernel/workqueue.c - generic async execution with shared worker pool * - * Generic mechanism for defining kernel helper threads for running - * arbitrary tasks in process context. + * Copyright (C) 2002 Ingo Molnar * - * Started by Ingo Molnar, Copyright (C) 2002 + * Derived from the taskqueue/keventd code by: + * David Woodhouse + * Andrew Morton + * Kai Petzke + * Theodore Ts'o * - * Derived from the taskqueue/keventd code by: + * Made to use alloc_percpu by Christoph Lameter. * - * David Woodhouse - * Andrew Morton - * Kai Petzke - * Theodore Ts'o + * Copyright (C) 2010 SUSE Linux Products GmbH + * Copyright (C) 2010 Tejun Heo * - * Made to use alloc_percpu by Christoph Lameter. + * This is the generic async execution mechanism. Work items as are + * executed in process context. The worker pool is shared and + * automatically managed. There is one worker pool for each CPU and + * one extra for works which are better served by workers which are + * not bound to any specific CPU. + * + * Please read Documentation/workqueue.txt for details. */ #include -- cgit v1.2.3-71-gd317 From c41d68a513c71e35a14f66d71782d27a79a81ea6 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Tue, 7 Sep 2010 16:16:18 -0700 Subject: compat: Make compat_alloc_user_space() incorporate the access_ok() compat_alloc_user_space() expects the caller to independently call access_ok() to verify the returned area. A missing call could introduce problems on some architectures. This patch incorporates the access_ok() check into compat_alloc_user_space() and also adds a sanity check on the length. The existing compat_alloc_user_space() implementations are renamed arch_compat_alloc_user_space() and are used as part of the implementation of the new global function. This patch assumes NULL will cause __get_user()/__put_user() to either fail or access userspace on all architectures. This should be followed by checking the return value of compat_access_user_space() for NULL in the callers, at which time the access_ok() in the callers can also be removed. Reported-by: Ben Hawkes Signed-off-by: H. Peter Anvin Acked-by: Benjamin Herrenschmidt Acked-by: Chris Metcalf Acked-by: David S. Miller Acked-by: Ingo Molnar Acked-by: Thomas Gleixner Acked-by: Tony Luck Cc: Andrew Morton Cc: Arnd Bergmann Cc: Fenghua Yu Cc: H. Peter Anvin Cc: Heiko Carstens Cc: Helge Deller Cc: James Bottomley Cc: Kyle McMartin Cc: Martin Schwidefsky Cc: Paul Mackerras Cc: Ralf Baechle Cc: --- arch/ia64/include/asm/compat.h | 2 +- arch/mips/include/asm/compat.h | 2 +- arch/parisc/include/asm/compat.h | 2 +- arch/powerpc/include/asm/compat.h | 2 +- arch/s390/include/asm/compat.h | 2 +- arch/sparc/include/asm/compat.h | 2 +- arch/tile/include/asm/compat.h | 2 +- arch/x86/include/asm/compat.h | 2 +- include/linux/compat.h | 3 +++ kernel/compat.c | 21 +++++++++++++++++++++ 10 files changed, 32 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/arch/ia64/include/asm/compat.h b/arch/ia64/include/asm/compat.h index f90edc85b509..9301a2821615 100644 --- a/arch/ia64/include/asm/compat.h +++ b/arch/ia64/include/asm/compat.h @@ -199,7 +199,7 @@ ptr_to_compat(void __user *uptr) } static __inline__ void __user * -compat_alloc_user_space (long len) +arch_compat_alloc_user_space (long len) { struct pt_regs *regs = task_pt_regs(current); return (void __user *) (((regs->r12 & 0xffffffff) & -16) - len); diff --git a/arch/mips/include/asm/compat.h b/arch/mips/include/asm/compat.h index 613f6912dfc1..dbc51065df5b 100644 --- a/arch/mips/include/asm/compat.h +++ b/arch/mips/include/asm/compat.h @@ -145,7 +145,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr) return (u32)(unsigned long)uptr; } -static inline void __user *compat_alloc_user_space(long len) +static inline void __user *arch_compat_alloc_user_space(long len) { struct pt_regs *regs = (struct pt_regs *) ((unsigned long) current_thread_info() + THREAD_SIZE - 32) - 1; diff --git a/arch/parisc/include/asm/compat.h b/arch/parisc/include/asm/compat.h index 02b77baa5da6..efa0b60c63fe 100644 --- a/arch/parisc/include/asm/compat.h +++ b/arch/parisc/include/asm/compat.h @@ -147,7 +147,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr) return (u32)(unsigned long)uptr; } -static __inline__ void __user *compat_alloc_user_space(long len) +static __inline__ void __user *arch_compat_alloc_user_space(long len) { struct pt_regs *regs = ¤t->thread.regs; return (void __user *)regs->gr[30]; diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h index 396d21a80058..a11d4eac4f97 100644 --- a/arch/powerpc/include/asm/compat.h +++ b/arch/powerpc/include/asm/compat.h @@ -134,7 +134,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr) return (u32)(unsigned long)uptr; } -static inline void __user *compat_alloc_user_space(long len) +static inline void __user *arch_compat_alloc_user_space(long len) { struct pt_regs *regs = current->thread.regs; unsigned long usp = regs->gpr[1]; diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h index 104f2007f097..a875c2f542e1 100644 --- a/arch/s390/include/asm/compat.h +++ b/arch/s390/include/asm/compat.h @@ -181,7 +181,7 @@ static inline int is_compat_task(void) #endif -static inline void __user *compat_alloc_user_space(long len) +static inline void __user *arch_compat_alloc_user_space(long len) { unsigned long stack; diff --git a/arch/sparc/include/asm/compat.h b/arch/sparc/include/asm/compat.h index 5016f76ea98a..6f57325bb883 100644 --- a/arch/sparc/include/asm/compat.h +++ b/arch/sparc/include/asm/compat.h @@ -167,7 +167,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr) return (u32)(unsigned long)uptr; } -static inline void __user *compat_alloc_user_space(long len) +static inline void __user *arch_compat_alloc_user_space(long len) { struct pt_regs *regs = current_thread_info()->kregs; unsigned long usp = regs->u_regs[UREG_I6]; diff --git a/arch/tile/include/asm/compat.h b/arch/tile/include/asm/compat.h index 5a34da6cdd79..345d81ce44bb 100644 --- a/arch/tile/include/asm/compat.h +++ b/arch/tile/include/asm/compat.h @@ -195,7 +195,7 @@ static inline unsigned long ptr_to_compat_reg(void __user *uptr) return (long)(int)(long __force)uptr; } -static inline void __user *compat_alloc_user_space(long len) +static inline void __user *arch_compat_alloc_user_space(long len) { struct pt_regs *regs = task_pt_regs(current); return (void __user *)regs->sp - len; diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index 306160e58b48..1d9cd27c2920 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -205,7 +205,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr) return (u32)(unsigned long)uptr; } -static inline void __user *compat_alloc_user_space(long len) +static inline void __user *arch_compat_alloc_user_space(long len) { struct pt_regs *regs = task_pt_regs(current); return (void __user *)regs->sp - len; diff --git a/include/linux/compat.h b/include/linux/compat.h index 9ddc8780e8db..5778b559d59c 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -360,5 +360,8 @@ extern ssize_t compat_rw_copy_check_uvector(int type, const struct compat_iovec __user *uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_pointer, struct iovec **ret_pointer); + +extern void __user *compat_alloc_user_space(unsigned long len); + #endif /* CONFIG_COMPAT */ #endif /* _LINUX_COMPAT_H */ diff --git a/kernel/compat.c b/kernel/compat.c index e167efce8423..c9e2ec0b34a8 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -1126,3 +1126,24 @@ compat_sys_sysinfo(struct compat_sysinfo __user *info) return 0; } + +/* + * Allocate user-space memory for the duration of a single system call, + * in order to marshall parameters inside a compat thunk. + */ +void __user *compat_alloc_user_space(unsigned long len) +{ + void __user *ptr; + + /* If len would occupy more than half of the entire compat space... */ + if (unlikely(len > (((compat_uptr_t)~0) >> 1))) + return NULL; + + ptr = arch_compat_alloc_user_space(len); + + if (unlikely(!access_ok(VERIFY_WRITE, ptr, len))) + return NULL; + + return ptr; +} +EXPORT_SYMBOL_GPL(compat_alloc_user_space); -- cgit v1.2.3-71-gd317 From f0f9deae9e7c421fa0c1c627beb8e174325e1ba7 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Fri, 17 Sep 2010 16:55:03 -0700 Subject: netpoll: Disable IRQ around RCU dereference in netpoll_rx We cannot use rcu_dereference_bh safely in netpoll_rx as we may be called with IRQs disabled. We could however simply disable IRQs as that too causes BH to be disabled and is safe in either case. Thanks to John Linville for discovering this bug and providing a patch. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/netpoll.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 791d5109f34c..50d8009be86c 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -63,20 +63,20 @@ static inline bool netpoll_rx(struct sk_buff *skb) unsigned long flags; bool ret = false; - rcu_read_lock_bh(); + local_irq_save(flags); npinfo = rcu_dereference_bh(skb->dev->npinfo); if (!npinfo || (list_empty(&npinfo->rx_np) && !npinfo->rx_flags)) goto out; - spin_lock_irqsave(&npinfo->rx_lock, flags); + spin_lock(&npinfo->rx_lock); /* check rx_flags again with the lock held */ if (npinfo->rx_flags && __netpoll_rx(skb)) ret = true; - spin_unlock_irqrestore(&npinfo->rx_lock, flags); + spin_unlock(&npinfo->rx_lock); out: - rcu_read_unlock_bh(); + local_irq_restore(flags); return ret; } -- cgit v1.2.3-71-gd317