From bbefa1dd6a6d53537c11624752219e39959d04fb Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 26 Nov 2019 15:58:45 +0800 Subject: crypto: pcrypt - Avoid deadlock by using per-instance padata queues If the pcrypt template is used multiple times in an algorithm, then a deadlock occurs because all pcrypt instances share the same padata_instance, which completes requests in the order submitted. That is, the inner pcrypt request waits for the outer pcrypt request while the outer request is already waiting for the inner. This patch fixes this by allocating a set of queues for each pcrypt instance instead of using two global queues. In order to maintain the existing user-space interface, the pinst structure remains global so any sysfs modifications will apply to every pcrypt instance. Note that when an update occurs we have to allocate memory for every pcrypt instance. Should one of the allocations fail we will abort the update without rolling back changes already made. The new per-instance data structure is called padata_shell and is essentially a wrapper around parallel_data. Reproducer: #include #include #include int main() { struct sockaddr_alg addr = { .salg_type = "aead", .salg_name = "pcrypt(pcrypt(rfc4106-gcm-aesni))" }; int algfd, reqfd; char buf[32] = { 0 }; algfd = socket(AF_ALG, SOCK_SEQPACKET, 0); bind(algfd, (void *)&addr, sizeof(addr)); setsockopt(algfd, SOL_ALG, ALG_SET_KEY, buf, 20); reqfd = accept(algfd, 0, 0); write(reqfd, buf, 32); read(reqfd, buf, 16); } Reported-by: syzbot+56c7151cad94eec37c521f0e47d2eee53f9361c4@syzkaller.appspotmail.com Fixes: 5068c7a883d1 ("crypto: pcrypt - Add pcrypt crypto parallelization wrapper") Signed-off-by: Herbert Xu Tested-by: Eric Biggers Signed-off-by: Herbert Xu --- include/linux/padata.h | 34 +++++++++++++++++++++++++++++----- 1 file changed, 29 insertions(+), 5 deletions(-) (limited to 'include/linux/padata.h') diff --git a/include/linux/padata.h b/include/linux/padata.h index 23717eeaad23..cccab7a59787 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -9,6 +9,7 @@ #ifndef PADATA_H #define PADATA_H +#include #include #include #include @@ -98,7 +99,7 @@ struct padata_cpumask { * struct parallel_data - Internal control structure, covers everything * that depends on the cpumask in use. * - * @pinst: padata instance. + * @sh: padata_shell object. * @pqueue: percpu padata queues used for parallelization. * @squeue: percpu padata queues used for serialuzation. * @reorder_objects: Number of objects waiting in the reorder queues. @@ -111,7 +112,7 @@ struct padata_cpumask { * @lock: Reorder lock. */ struct parallel_data { - struct padata_instance *pinst; + struct padata_shell *ps; struct padata_parallel_queue __percpu *pqueue; struct padata_serial_queue __percpu *squeue; atomic_t reorder_objects; @@ -124,14 +125,33 @@ struct parallel_data { spinlock_t lock ____cacheline_aligned; }; +/** + * struct padata_shell - Wrapper around struct parallel_data, its + * purpose is to allow the underlying control structure to be replaced + * on the fly using RCU. + * + * @pinst: padat instance. + * @pd: Actual parallel_data structure which may be substituted on the fly. + * @opd: Pointer to old pd to be freed by padata_replace. + * @list: List entry in padata_instance list. + */ +struct padata_shell { + struct padata_instance *pinst; + struct parallel_data __rcu *pd; + struct parallel_data *opd; + struct list_head list; +}; + /** * struct padata_instance - The overall control structure. * * @cpu_notifier: cpu hotplug notifier. * @parallel_wq: The workqueue used for parallel work. * @serial_wq: The workqueue used for serial work. - * @pd: The internal control structure. + * @pslist: List of padata_shell objects attached to this instance. * @cpumask: User supplied cpumasks for parallel and serial works. + * @rcpumask: Actual cpumasks based on user cpumask and cpu_online_mask. + * @omask: Temporary storage used to compute the notification mask. * @cpumask_change_notifier: Notifiers chain for user-defined notify * callbacks that will be called when either @pcpu or @cbcpu * or both cpumasks change. @@ -143,8 +163,10 @@ struct padata_instance { struct hlist_node node; struct workqueue_struct *parallel_wq; struct workqueue_struct *serial_wq; - struct parallel_data *pd; + struct list_head pslist; struct padata_cpumask cpumask; + struct padata_cpumask rcpumask; + cpumask_var_t omask; struct blocking_notifier_head cpumask_change_notifier; struct kobject kobj; struct mutex lock; @@ -156,7 +178,9 @@ struct padata_instance { extern struct padata_instance *padata_alloc_possible(const char *name); extern void padata_free(struct padata_instance *pinst); -extern int padata_do_parallel(struct padata_instance *pinst, +extern struct padata_shell *padata_alloc_shell(struct padata_instance *pinst); +extern void padata_free_shell(struct padata_shell *ps); +extern int padata_do_parallel(struct padata_shell *ps, struct padata_priv *padata, int *cb_cpu); extern void padata_do_serial(struct padata_priv *padata); extern int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type, -- cgit v1.2.3 From 91a71d612128f84f725022d7b7c5d5a741f6fdc7 Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Tue, 3 Dec 2019 14:31:12 -0500 Subject: padata: remove cpumask change notifier Since commit 63d3578892dc ("crypto: pcrypt - remove padata cpumask notifier") this feature is unused, so get rid of it. Signed-off-by: Daniel Jordan Cc: Eric Biggers Cc: Herbert Xu Cc: Jonathan Corbet Cc: Steffen Klassert Cc: linux-crypto@vger.kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Herbert Xu --- Documentation/padata.txt | 24 ---------------------- crypto/pcrypt.c | 1 - include/linux/padata.h | 11 ---------- kernel/padata.c | 52 +----------------------------------------------- 4 files changed, 1 insertion(+), 87 deletions(-) (limited to 'include/linux/padata.h') diff --git a/Documentation/padata.txt b/Documentation/padata.txt index b37ba1eaace3..b45df9c6547b 100644 --- a/Documentation/padata.txt +++ b/Documentation/padata.txt @@ -75,30 +75,6 @@ To simply add or remove one CPU from a certain cpumask the functions padata_add_cpu/padata_remove_cpu are used. cpu specifies the CPU to add or remove and mask is one of PADATA_CPU_SERIAL, PADATA_CPU_PARALLEL. -If a user is interested in padata cpumask changes, he can register to -the padata cpumask change notifier:: - - int padata_register_cpumask_notifier(struct padata_instance *pinst, - struct notifier_block *nblock); - -To unregister from that notifier:: - - int padata_unregister_cpumask_notifier(struct padata_instance *pinst, - struct notifier_block *nblock); - -The padata cpumask change notifier notifies about changes of the usable -cpumasks, i.e. the subset of active CPUs in the user supplied cpumask. - -Padata calls the notifier chain with:: - - blocking_notifier_call_chain(&pinst->cpumask_change_notifier, - notification_mask, - &pd_new->cpumask); - -Here cpumask_change_notifier is registered notifier, notification_mask -is one of PADATA_CPU_SERIAL, PADATA_CPU_PARALLEL and cpumask is a pointer -to a struct padata_cpumask that contains the new cpumask information. - Actually submitting work to the padata instance requires the creation of a padata_priv structure:: diff --git a/crypto/pcrypt.c b/crypto/pcrypt.c index a4f3b3f342c8..d6696e217128 100644 --- a/crypto/pcrypt.c +++ b/crypto/pcrypt.c @@ -13,7 +13,6 @@ #include #include #include -#include #include #include #include diff --git a/include/linux/padata.h b/include/linux/padata.h index cccab7a59787..178d5cc6b494 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -13,7 +13,6 @@ #include #include #include -#include #include #define PADATA_CPU_SERIAL 0x01 @@ -151,10 +150,6 @@ struct padata_shell { * @pslist: List of padata_shell objects attached to this instance. * @cpumask: User supplied cpumasks for parallel and serial works. * @rcpumask: Actual cpumasks based on user cpumask and cpu_online_mask. - * @omask: Temporary storage used to compute the notification mask. - * @cpumask_change_notifier: Notifiers chain for user-defined notify - * callbacks that will be called when either @pcpu or @cbcpu - * or both cpumasks change. * @kobj: padata instance kernel object. * @lock: padata instance lock. * @flags: padata flags. @@ -166,8 +161,6 @@ struct padata_instance { struct list_head pslist; struct padata_cpumask cpumask; struct padata_cpumask rcpumask; - cpumask_var_t omask; - struct blocking_notifier_head cpumask_change_notifier; struct kobject kobj; struct mutex lock; u8 flags; @@ -187,8 +180,4 @@ extern int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type, cpumask_var_t cpumask); extern int padata_start(struct padata_instance *pinst); extern void padata_stop(struct padata_instance *pinst); -extern int padata_register_cpumask_notifier(struct padata_instance *pinst, - struct notifier_block *nblock); -extern int padata_unregister_cpumask_notifier(struct padata_instance *pinst, - struct notifier_block *nblock); #endif diff --git a/kernel/padata.c b/kernel/padata.c index f5964f015139..bc594c00b26e 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -514,23 +514,16 @@ static int padata_replace_one(struct padata_shell *ps) static int padata_replace(struct padata_instance *pinst) { - int notification_mask = 0; struct padata_shell *ps; int err; pinst->flags |= PADATA_RESET; - cpumask_copy(pinst->omask, pinst->rcpumask.pcpu); cpumask_and(pinst->rcpumask.pcpu, pinst->cpumask.pcpu, cpu_online_mask); - if (!cpumask_equal(pinst->omask, pinst->rcpumask.pcpu)) - notification_mask |= PADATA_CPU_PARALLEL; - cpumask_copy(pinst->omask, pinst->rcpumask.cbcpu); cpumask_and(pinst->rcpumask.cbcpu, pinst->cpumask.cbcpu, cpu_online_mask); - if (!cpumask_equal(pinst->omask, pinst->rcpumask.cbcpu)) - notification_mask |= PADATA_CPU_SERIAL; list_for_each_entry(ps, &pinst->pslist, list) { err = padata_replace_one(ps); @@ -544,48 +537,11 @@ static int padata_replace(struct padata_instance *pinst) if (atomic_dec_and_test(&ps->opd->refcnt)) padata_free_pd(ps->opd); - if (notification_mask) - blocking_notifier_call_chain(&pinst->cpumask_change_notifier, - notification_mask, - &pinst->cpumask); - pinst->flags &= ~PADATA_RESET; return err; } -/** - * padata_register_cpumask_notifier - Registers a notifier that will be called - * if either pcpu or cbcpu or both cpumasks change. - * - * @pinst: A poineter to padata instance - * @nblock: A pointer to notifier block. - */ -int padata_register_cpumask_notifier(struct padata_instance *pinst, - struct notifier_block *nblock) -{ - return blocking_notifier_chain_register(&pinst->cpumask_change_notifier, - nblock); -} -EXPORT_SYMBOL(padata_register_cpumask_notifier); - -/** - * padata_unregister_cpumask_notifier - Unregisters cpumask notifier - * registered earlier using padata_register_cpumask_notifier - * - * @pinst: A pointer to data instance. - * @nlock: A pointer to notifier block. - */ -int padata_unregister_cpumask_notifier(struct padata_instance *pinst, - struct notifier_block *nblock) -{ - return blocking_notifier_chain_unregister( - &pinst->cpumask_change_notifier, - nblock); -} -EXPORT_SYMBOL(padata_unregister_cpumask_notifier); - - /* If cpumask contains no active cpu, we mark the instance as invalid. */ static bool padata_validate_cpumask(struct padata_instance *pinst, const struct cpumask *cpumask) @@ -785,7 +741,6 @@ static void __padata_free(struct padata_instance *pinst) WARN_ON(!list_empty(&pinst->pslist)); padata_stop(pinst); - free_cpumask_var(pinst->omask); free_cpumask_var(pinst->rcpumask.cbcpu); free_cpumask_var(pinst->rcpumask.pcpu); free_cpumask_var(pinst->cpumask.pcpu); @@ -965,8 +920,6 @@ static struct padata_instance *padata_alloc(const char *name, goto err_free_masks; if (!alloc_cpumask_var(&pinst->rcpumask.cbcpu, GFP_KERNEL)) goto err_free_rcpumask_pcpu; - if (!alloc_cpumask_var(&pinst->omask, GFP_KERNEL)) - goto err_free_rcpumask_cbcpu; INIT_LIST_HEAD(&pinst->pslist); @@ -976,11 +929,10 @@ static struct padata_instance *padata_alloc(const char *name, cpumask_and(pinst->rcpumask.cbcpu, cbcpumask, cpu_online_mask); if (padata_setup_cpumasks(pinst)) - goto err_free_omask; + goto err_free_rcpumask_cbcpu; pinst->flags = 0; - BLOCKING_INIT_NOTIFIER_HEAD(&pinst->cpumask_change_notifier); kobject_init(&pinst->kobj, &padata_attr_type); mutex_init(&pinst->lock); @@ -994,8 +946,6 @@ static struct padata_instance *padata_alloc(const char *name, return pinst; -err_free_omask: - free_cpumask_var(pinst->omask); err_free_rcpumask_cbcpu: free_cpumask_var(pinst->rcpumask.cbcpu); err_free_rcpumask_pcpu: -- cgit v1.2.3 From 3facced7aeed131c1002b724e488d68ebe59c56f Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Tue, 3 Dec 2019 14:31:13 -0500 Subject: padata: remove reorder_objects reorder_objects is unused since the rework of padata's flushing, so remove it. Signed-off-by: Daniel Jordan Cc: Eric Biggers Cc: Herbert Xu Cc: Steffen Klassert Cc: linux-crypto@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Herbert Xu --- include/linux/padata.h | 2 -- kernel/padata.c | 3 --- 2 files changed, 5 deletions(-) (limited to 'include/linux/padata.h') diff --git a/include/linux/padata.h b/include/linux/padata.h index 178d5cc6b494..faa2e36832f8 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -101,7 +101,6 @@ struct padata_cpumask { * @sh: padata_shell object. * @pqueue: percpu padata queues used for parallelization. * @squeue: percpu padata queues used for serialuzation. - * @reorder_objects: Number of objects waiting in the reorder queues. * @refcnt: Number of objects holding a reference on this parallel_data. * @max_seq_nr: Maximal used sequence number. * @processed: Number of already processed objects. @@ -114,7 +113,6 @@ struct parallel_data { struct padata_shell *ps; struct padata_parallel_queue __percpu *pqueue; struct padata_serial_queue __percpu *squeue; - atomic_t reorder_objects; atomic_t refcnt; atomic_t seq_nr; unsigned int processed; diff --git a/kernel/padata.c b/kernel/padata.c index bc594c00b26e..db950d287b3d 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -202,7 +202,6 @@ static struct padata_priv *padata_find_next(struct parallel_data *pd, if (remove_object) { list_del_init(&padata->list); - atomic_dec(&pd->reorder_objects); ++pd->processed; pd->cpu = cpumask_next_wrap(cpu, pd->cpumask.pcpu, -1, false); } @@ -336,7 +335,6 @@ void padata_do_serial(struct padata_priv *padata) if (cur->seq_nr < padata->seq_nr) break; list_add(&padata->list, &cur->list); - atomic_inc(&pd->reorder_objects); spin_unlock(&pqueue->reorder.lock); /* @@ -455,7 +453,6 @@ static struct parallel_data *padata_alloc_pd(struct padata_shell *ps) padata_init_pqueues(pd); padata_init_squeues(pd); atomic_set(&pd->seq_nr, -1); - atomic_set(&pd->reorder_objects, 0); atomic_set(&pd->refcnt, 1); spin_lock_init(&pd->lock); pd->cpu = cpumask_first(pd->cpumask.pcpu); -- cgit v1.2.3 From bfcdcef8c8e3469f4d6c082a1da27a6ef77e5715 Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Tue, 3 Dec 2019 14:31:14 -0500 Subject: padata: update documentation Remove references to unused functions, standardize language, update to reflect new functionality, migrate to rst format, and fix all kernel-doc warnings. Fixes: 815613da6a67 ("kernel/padata.c: removed unused code") Signed-off-by: Daniel Jordan Cc: Eric Biggers Cc: Herbert Xu Cc: Jonathan Corbet Cc: Steffen Klassert Cc: linux-crypto@vger.kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Daniel Jordan Signed-off-by: Herbert Xu --- Documentation/core-api/index.rst | 1 + Documentation/core-api/padata.rst | 169 ++++++++++++++++++++++++++++++++++++++ Documentation/padata.txt | 139 ------------------------------- include/linux/padata.h | 15 ++-- kernel/padata.c | 35 +++++--- 5 files changed, 198 insertions(+), 161 deletions(-) create mode 100644 Documentation/core-api/padata.rst delete mode 100644 Documentation/padata.txt (limited to 'include/linux/padata.h') diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst index ab0eae1c153a..ab0b9ec85506 100644 --- a/Documentation/core-api/index.rst +++ b/Documentation/core-api/index.rst @@ -39,6 +39,7 @@ Core utilities ../RCU/index gcc-plugins symbol-namespaces + padata Interfaces for kernel debugging diff --git a/Documentation/core-api/padata.rst b/Documentation/core-api/padata.rst new file mode 100644 index 000000000000..9a24c111781d --- /dev/null +++ b/Documentation/core-api/padata.rst @@ -0,0 +1,169 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======================================= +The padata parallel execution mechanism +======================================= + +:Date: December 2019 + +Padata is a mechanism by which the kernel can farm jobs out to be done in +parallel on multiple CPUs while retaining their ordering. It was developed for +use with the IPsec code, which needs to be able to perform encryption and +decryption on large numbers of packets without reordering those packets. The +crypto developers made a point of writing padata in a sufficiently general +fashion that it could be put to other uses as well. + +Usage +===== + +Initializing +------------ + +The first step in using padata is to set up a padata_instance structure for +overall control of how jobs are to be run:: + + #include + + struct padata_instance *padata_alloc_possible(const char *name); + +'name' simply identifies the instance. + +There are functions for enabling and disabling the instance:: + + int padata_start(struct padata_instance *pinst); + void padata_stop(struct padata_instance *pinst); + +These functions are setting or clearing the "PADATA_INIT" flag; if that flag is +not set, other functions will refuse to work. padata_start() returns zero on +success (flag set) or -EINVAL if the padata cpumask contains no active CPU +(flag not set). padata_stop() clears the flag and blocks until the padata +instance is unused. + +Finally, complete padata initialization by allocating a padata_shell:: + + struct padata_shell *padata_alloc_shell(struct padata_instance *pinst); + +A padata_shell is used to submit a job to padata and allows a series of such +jobs to be serialized independently. A padata_instance may have one or more +padata_shells associated with it, each allowing a separate series of jobs. + +Modifying cpumasks +------------------ + +The CPUs used to run jobs can be changed in two ways, programatically with +padata_set_cpumask() or via sysfs. The former is defined:: + + int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type, + cpumask_var_t cpumask); + +Here cpumask_type is one of PADATA_CPU_PARALLEL or PADATA_CPU_SERIAL, where a +parallel cpumask describes which processors will be used to execute jobs +submitted to this instance in parallel and a serial cpumask defines which +processors are allowed to be used as the serialization callback processor. +cpumask specifies the new cpumask to use. + +There may be sysfs files for an instance's cpumasks. For example, pcrypt's +live in /sys/kernel/pcrypt/. Within an instance's directory +there are two files, parallel_cpumask and serial_cpumask, and either cpumask +may be changed by echoing a bitmask into the file, for example:: + + echo f > /sys/kernel/pcrypt/pencrypt/parallel_cpumask + +Reading one of these files shows the user-supplied cpumask, which may be +different from the 'usable' cpumask. + +Padata maintains two pairs of cpumasks internally, the user-supplied cpumasks +and the 'usable' cpumasks. (Each pair consists of a parallel and a serial +cpumask.) The user-supplied cpumasks default to all possible CPUs on instance +allocation and may be changed as above. The usable cpumasks are always a +subset of the user-supplied cpumasks and contain only the online CPUs in the +user-supplied masks; these are the cpumasks padata actually uses. So it is +legal to supply a cpumask to padata that contains offline CPUs. Once an +offline CPU in the user-supplied cpumask comes online, padata is going to use +it. + +Changing the CPU masks are expensive operations, so it should not be done with +great frequency. + +Running A Job +------------- + +Actually submitting work to the padata instance requires the creation of a +padata_priv structure, which represents one job:: + + struct padata_priv { + /* Other stuff here... */ + void (*parallel)(struct padata_priv *padata); + void (*serial)(struct padata_priv *padata); + }; + +This structure will almost certainly be embedded within some larger +structure specific to the work to be done. Most of its fields are private to +padata, but the structure should be zeroed at initialisation time, and the +parallel() and serial() functions should be provided. Those functions will +be called in the process of getting the work done as we will see +momentarily. + +The submission of the job is done with:: + + int padata_do_parallel(struct padata_shell *ps, + struct padata_priv *padata, int *cb_cpu); + +The ps and padata structures must be set up as described above; cb_cpu +points to the preferred CPU to be used for the final callback when the job is +done; it must be in the current instance's CPU mask (if not the cb_cpu pointer +is updated to point to the CPU actually chosen). The return value from +padata_do_parallel() is zero on success, indicating that the job is in +progress. -EBUSY means that somebody, somewhere else is messing with the +instance's CPU mask, while -EINVAL is a complaint about cb_cpu not being in the +serial cpumask, no online CPUs in the parallel or serial cpumasks, or a stopped +instance. + +Each job submitted to padata_do_parallel() will, in turn, be passed to +exactly one call to the above-mentioned parallel() function, on one CPU, so +true parallelism is achieved by submitting multiple jobs. parallel() runs with +software interrupts disabled and thus cannot sleep. The parallel() +function gets the padata_priv structure pointer as its lone parameter; +information about the actual work to be done is probably obtained by using +container_of() to find the enclosing structure. + +Note that parallel() has no return value; the padata subsystem assumes that +parallel() will take responsibility for the job from this point. The job +need not be completed during this call, but, if parallel() leaves work +outstanding, it should be prepared to be called again with a new job before +the previous one completes. + +Serializing Jobs +---------------- + +When a job does complete, parallel() (or whatever function actually finishes +the work) should inform padata of the fact with a call to:: + + void padata_do_serial(struct padata_priv *padata); + +At some point in the future, padata_do_serial() will trigger a call to the +serial() function in the padata_priv structure. That call will happen on +the CPU requested in the initial call to padata_do_parallel(); it, too, is +run with local software interrupts disabled. +Note that this call may be deferred for a while since the padata code takes +pains to ensure that jobs are completed in the order in which they were +submitted. + +Destroying +---------- + +Cleaning up a padata instance predictably involves calling the three free +functions that correspond to the allocation in reverse:: + + void padata_free_shell(struct padata_shell *ps); + void padata_stop(struct padata_instance *pinst); + void padata_free(struct padata_instance *pinst); + +It is the user's responsibility to ensure all outstanding jobs are complete +before any of the above are called. + +Interface +========= + +.. kernel-doc:: include/linux/padata.h +.. kernel-doc:: kernel/padata.c diff --git a/Documentation/padata.txt b/Documentation/padata.txt deleted file mode 100644 index b45df9c6547b..000000000000 --- a/Documentation/padata.txt +++ /dev/null @@ -1,139 +0,0 @@ -======================================= -The padata parallel execution mechanism -======================================= - -:Last updated: for 2.6.36 - -Padata is a mechanism by which the kernel can farm work out to be done in -parallel on multiple CPUs while retaining the ordering of tasks. It was -developed for use with the IPsec code, which needs to be able to perform -encryption and decryption on large numbers of packets without reordering -those packets. The crypto developers made a point of writing padata in a -sufficiently general fashion that it could be put to other uses as well. - -The first step in using padata is to set up a padata_instance structure for -overall control of how tasks are to be run:: - - #include - - struct padata_instance *padata_alloc(const char *name, - const struct cpumask *pcpumask, - const struct cpumask *cbcpumask); - -'name' simply identifies the instance. - -The pcpumask describes which processors will be used to execute work -submitted to this instance in parallel. The cbcpumask defines which -processors are allowed to be used as the serialization callback processor. -The workqueue wq is where the work will actually be done; it should be -a multithreaded queue, naturally. - -To allocate a padata instance with the cpu_possible_mask for both -cpumasks this helper function can be used:: - - struct padata_instance *padata_alloc_possible(struct workqueue_struct *wq); - -Note: Padata maintains two kinds of cpumasks internally. The user supplied -cpumasks, submitted by padata_alloc/padata_alloc_possible and the 'usable' -cpumasks. The usable cpumasks are always a subset of active CPUs in the -user supplied cpumasks; these are the cpumasks padata actually uses. So -it is legal to supply a cpumask to padata that contains offline CPUs. -Once an offline CPU in the user supplied cpumask comes online, padata -is going to use it. - -There are functions for enabling and disabling the instance:: - - int padata_start(struct padata_instance *pinst); - void padata_stop(struct padata_instance *pinst); - -These functions are setting or clearing the "PADATA_INIT" flag; -if that flag is not set, other functions will refuse to work. -padata_start returns zero on success (flag set) or -EINVAL if the -padata cpumask contains no active CPU (flag not set). -padata_stop clears the flag and blocks until the padata instance -is unused. - -The list of CPUs to be used can be adjusted with these functions:: - - int padata_set_cpumasks(struct padata_instance *pinst, - cpumask_var_t pcpumask, - cpumask_var_t cbcpumask); - int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type, - cpumask_var_t cpumask); - int padata_add_cpu(struct padata_instance *pinst, int cpu, int mask); - int padata_remove_cpu(struct padata_instance *pinst, int cpu, int mask); - -Changing the CPU masks are expensive operations, though, so it should not be -done with great frequency. - -It's possible to change both cpumasks of a padata instance with -padata_set_cpumasks by specifying the cpumasks for parallel execution (pcpumask) -and for the serial callback function (cbcpumask). padata_set_cpumask is used to -change just one of the cpumasks. Here cpumask_type is one of PADATA_CPU_SERIAL, -PADATA_CPU_PARALLEL and cpumask specifies the new cpumask to use. -To simply add or remove one CPU from a certain cpumask the functions -padata_add_cpu/padata_remove_cpu are used. cpu specifies the CPU to add or -remove and mask is one of PADATA_CPU_SERIAL, PADATA_CPU_PARALLEL. - -Actually submitting work to the padata instance requires the creation of a -padata_priv structure:: - - struct padata_priv { - /* Other stuff here... */ - void (*parallel)(struct padata_priv *padata); - void (*serial)(struct padata_priv *padata); - }; - -This structure will almost certainly be embedded within some larger -structure specific to the work to be done. Most of its fields are private to -padata, but the structure should be zeroed at initialisation time, and the -parallel() and serial() functions should be provided. Those functions will -be called in the process of getting the work done as we will see -momentarily. - -The submission of work is done with:: - - int padata_do_parallel(struct padata_instance *pinst, - struct padata_priv *padata, int cb_cpu); - -The pinst and padata structures must be set up as described above; cb_cpu -specifies which CPU will be used for the final callback when the work is -done; it must be in the current instance's CPU mask. The return value from -padata_do_parallel() is zero on success, indicating that the work is in -progress. -EBUSY means that somebody, somewhere else is messing with the -instance's CPU mask, while -EINVAL is a complaint about cb_cpu not being -in that CPU mask or about a not running instance. - -Each task submitted to padata_do_parallel() will, in turn, be passed to -exactly one call to the above-mentioned parallel() function, on one CPU, so -true parallelism is achieved by submitting multiple tasks. parallel() runs with -software interrupts disabled and thus cannot sleep. The parallel() -function gets the padata_priv structure pointer as its lone parameter; -information about the actual work to be done is probably obtained by using -container_of() to find the enclosing structure. - -Note that parallel() has no return value; the padata subsystem assumes that -parallel() will take responsibility for the task from this point. The work -need not be completed during this call, but, if parallel() leaves work -outstanding, it should be prepared to be called again with a new job before -the previous one completes. When a task does complete, parallel() (or -whatever function actually finishes the job) should inform padata of the -fact with a call to:: - - void padata_do_serial(struct padata_priv *padata); - -At some point in the future, padata_do_serial() will trigger a call to the -serial() function in the padata_priv structure. That call will happen on -the CPU requested in the initial call to padata_do_parallel(); it, too, is -run with local software interrupts disabled. -Note that this call may be deferred for a while since the padata code takes -pains to ensure that tasks are completed in the order in which they were -submitted. - -The one remaining function in the padata API should be called to clean up -when a padata instance is no longer needed:: - - void padata_free(struct padata_instance *pinst); - -This function will busy-wait while any remaining tasks are completed, so it -might be best not to call it while there is work outstanding. diff --git a/include/linux/padata.h b/include/linux/padata.h index faa2e36832f8..a0d8b41850b2 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -19,7 +19,7 @@ #define PADATA_CPU_PARALLEL 0x02 /** - * struct padata_priv - Embedded to the users data structure. + * struct padata_priv - Represents one job * * @list: List entry, to attach to the padata lists. * @pd: Pointer to the internal control structure. @@ -42,7 +42,7 @@ struct padata_priv { }; /** - * struct padata_list + * struct padata_list - one per work type per CPU * * @list: List head. * @lock: List lock. @@ -70,9 +70,6 @@ struct padata_serial_queue { * * @parallel: List to wait for parallelization. * @reorder: List to wait for reordering after parallel processing. - * @serial: List to wait for serialization after reordering. - * @pwork: work struct for parallelization. - * @swork: work struct for serialization. * @work: work struct for parallelization. * @num_obj: Number of objects that are processed by this cpu. */ @@ -98,11 +95,11 @@ struct padata_cpumask { * struct parallel_data - Internal control structure, covers everything * that depends on the cpumask in use. * - * @sh: padata_shell object. + * @ps: padata_shell object. * @pqueue: percpu padata queues used for parallelization. * @squeue: percpu padata queues used for serialuzation. * @refcnt: Number of objects holding a reference on this parallel_data. - * @max_seq_nr: Maximal used sequence number. + * @seq_nr: Sequence number of the parallelized data object. * @processed: Number of already processed objects. * @cpu: Next CPU to be processed. * @cpumask: The cpumasks in use for parallel and serial workers. @@ -119,7 +116,7 @@ struct parallel_data { int cpu; struct padata_cpumask cpumask; struct work_struct reorder_work; - spinlock_t lock ____cacheline_aligned; + spinlock_t ____cacheline_aligned lock; }; /** @@ -142,7 +139,7 @@ struct padata_shell { /** * struct padata_instance - The overall control structure. * - * @cpu_notifier: cpu hotplug notifier. + * @node: Used by CPU hotplug. * @parallel_wq: The workqueue used for parallel work. * @serial_wq: The workqueue used for serial work. * @pslist: List of padata_shell objects attached to this instance. diff --git a/kernel/padata.c b/kernel/padata.c index db950d287b3d..72777c10bb9c 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -2,7 +2,7 @@ /* * padata.c - generic interface to process data streams in parallel * - * See Documentation/padata.txt for an api documentation. + * See Documentation/core-api/padata.rst for more information. * * Copyright (C) 2008, 2009 secunet Security Networks AG * Copyright (C) 2008, 2009 Steffen Klassert @@ -99,6 +99,8 @@ static void padata_parallel_worker(struct work_struct *parallel_work) * The parallelization callback function will run with BHs off. * Note: Every object which is parallelized by padata_do_parallel * must be seen by padata_do_serial. + * + * Return: 0 on success or else negative error code. */ int padata_do_parallel(struct padata_shell *ps, struct padata_priv *padata, int *cb_cpu) @@ -163,14 +165,12 @@ EXPORT_SYMBOL(padata_do_parallel); /* * padata_find_next - Find the next object that needs serialization. * - * Return values are: - * - * A pointer to the control struct of the next object that needs - * serialization, if present in one of the percpu reorder queues. - * - * NULL, if the next object that needs serialization will - * be parallel processed by another cpu and is not yet present in - * the cpu's reorder queue. + * Return: + * * A pointer to the control struct of the next object that needs + * serialization, if present in one of the percpu reorder queues. + * * NULL, if the next object that needs serialization will + * be parallel processed by another cpu and is not yet present in + * the cpu's reorder queue. */ static struct padata_priv *padata_find_next(struct parallel_data *pd, bool remove_object) @@ -582,13 +582,14 @@ out_replace: } /** - * padata_set_cpumask: Sets specified by @cpumask_type cpumask to the value - * equivalent to @cpumask. - * + * padata_set_cpumask - Sets specified by @cpumask_type cpumask to the value + * equivalent to @cpumask. * @pinst: padata instance * @cpumask_type: PADATA_CPU_SERIAL or PADATA_CPU_PARALLEL corresponding * to parallel and serial cpumasks respectively. * @cpumask: the cpumask to use + * + * Return: 0 on success or negative error code */ int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type, cpumask_var_t cpumask) @@ -626,6 +627,8 @@ EXPORT_SYMBOL(padata_set_cpumask); * padata_start - start the parallel processing * * @pinst: padata instance to start + * + * Return: 0 on success or negative error code */ int padata_start(struct padata_instance *pinst) { @@ -880,6 +883,8 @@ static struct kobj_type padata_attr_type = { * @name: used to identify the instance * @pcpumask: cpumask that will be used for padata parallelization * @cbcpumask: cpumask that will be used for padata serialization + * + * Return: new instance on success, NULL on error */ static struct padata_instance *padata_alloc(const char *name, const struct cpumask *pcpumask, @@ -967,6 +972,8 @@ err: * parallel workers. * * @name: used to identify the instance + * + * Return: new instance on success, NULL on error */ struct padata_instance *padata_alloc_possible(const char *name) { @@ -977,7 +984,7 @@ EXPORT_SYMBOL(padata_alloc_possible); /** * padata_free - free a padata instance * - * @padata_inst: padata instance to free + * @pinst: padata instance to free */ void padata_free(struct padata_instance *pinst) { @@ -989,6 +996,8 @@ EXPORT_SYMBOL(padata_free); * padata_alloc_shell - Allocate and initialize padata shell. * * @pinst: Parent padata_instance object. + * + * Return: new shell on success, NULL on error */ struct padata_shell *padata_alloc_shell(struct padata_instance *pinst) { -- cgit v1.2.3