From 305dacf77952e6e62405f916654f38423c78ab2f Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Wed, 3 Jun 2020 15:59:31 -0700 Subject: padata: remove exit routine Patch series "padata: parallelize deferred page init", v3. Deferred struct page init is a bottleneck in kernel boot--the biggest for us and probably others. Optimizing it maximizes availability for large-memory systems and allows spinning up short-lived VMs as needed without having to leave them running. It also benefits bare metal machines hosting VMs that are sensitive to downtime. In projects such as VMM Fast Restart[1], where guest state is preserved across kexec reboot, it helps prevent application and network timeouts in the guests. So, multithread deferred init to take full advantage of system memory bandwidth. Extend padata, a framework that handles many parallel singlethreaded jobs, to handle multithreaded jobs as well by adding support for splitting up the work evenly, specifying a minimum amount of work that's appropriate for one helper thread to do, load balancing between helpers, and coordinating them. More documentation in patches 4 and 8. This series is the first step in a project to address other memory proportional bottlenecks in the kernel such as pmem struct page init, vfio page pinning, hugetlb fallocate, and munmap. Deferred page init doesn't require concurrency limits, resource control, or priority adjustments like these other users will because it happens during boot when the system is otherwise idle and waiting for page init to finish. This has been run on a variety of x86 systems and speeds up kernel boot by 4% to 49%, saving up to 1.6 out of 4 seconds. Patch 6 has more numbers. This patch (of 8): padata_driver_exit() is unnecessary because padata isn't built as a module and doesn't exit. padata's init routine will soon allocate memory, so getting rid of the exit function now avoids pointless code to free it. Signed-off-by: Daniel Jordan Signed-off-by: Andrew Morton Tested-by: Josh Triplett Cc: Alexander Duyck Cc: Alex Williamson Cc: Dan Williams Cc: Dave Hansen Cc: David Hildenbrand Cc: Herbert Xu Cc: Jason Gunthorpe Cc: Jonathan Corbet Cc: Kirill Tkhai Cc: Michal Hocko Cc: Pavel Machek Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Randy Dunlap Cc: Robert Elliott Cc: Shile Zhang Cc: Steffen Klassert Cc: Steven Sistare Cc: Tejun Heo Cc: Zi Yan Link: http://lkml.kernel.org/r/20200527173608.2885243-1-daniel.m.jordan@oracle.com Link: http://lkml.kernel.org/r/20200527173608.2885243-2-daniel.m.jordan@oracle.com Signed-off-by: Linus Torvalds --- kernel/padata.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'kernel') diff --git a/kernel/padata.c b/kernel/padata.c index aae789896616..b4c7e3e38a05 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -1074,10 +1074,4 @@ static __init int padata_driver_init(void) } module_init(padata_driver_init); -static __exit void padata_driver_exit(void) -{ - cpuhp_remove_multi_state(CPUHP_PADATA_DEAD); - cpuhp_remove_multi_state(hp_online); -} -module_exit(padata_driver_exit); #endif -- cgit v1.2.3-59-g8ed1b From f1b192b117cd418bacf42a9583d7a01855a18fe5 Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Wed, 3 Jun 2020 15:59:35 -0700 Subject: padata: initialize earlier padata will soon initialize the system's struct pages in parallel, so it needs to be ready by page_alloc_init_late(). The error return from padata_driver_init() triggers an initcall warning, so add a warning to padata_init() to avoid silent failure. Signed-off-by: Daniel Jordan Signed-off-by: Andrew Morton Tested-by: Josh Triplett Cc: Alexander Duyck Cc: Alex Williamson Cc: Dan Williams Cc: Dave Hansen Cc: David Hildenbrand Cc: Herbert Xu Cc: Jason Gunthorpe Cc: Jonathan Corbet Cc: Kirill Tkhai Cc: Michal Hocko Cc: Pavel Machek Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Randy Dunlap Cc: Robert Elliott Cc: Shile Zhang Cc: Steffen Klassert Cc: Steven Sistare Cc: Tejun Heo Cc: Zi Yan Link: http://lkml.kernel.org/r/20200527173608.2885243-3-daniel.m.jordan@oracle.com Signed-off-by: Linus Torvalds --- include/linux/padata.h | 6 ++++++ init/main.c | 2 ++ kernel/padata.c | 17 ++++++++--------- 3 files changed, 16 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/include/linux/padata.h b/include/linux/padata.h index 693cae9bfe66..d50bd1a7756f 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -166,6 +166,12 @@ struct padata_instance { #define PADATA_INVALID 4 }; +#ifdef CONFIG_PADATA +extern void __init padata_init(void); +#else +static inline void __init padata_init(void) {} +#endif + extern struct padata_instance *padata_alloc_possible(const char *name); extern void padata_free(struct padata_instance *pinst); extern struct padata_shell *padata_alloc_shell(struct padata_instance *pinst); diff --git a/init/main.c b/init/main.c index 03371976d387..df32f67214d2 100644 --- a/init/main.c +++ b/init/main.c @@ -63,6 +63,7 @@ #include #include #include +#include #include #include #include @@ -1482,6 +1483,7 @@ static noinline void __init kernel_init_freeable(void) smp_init(); sched_init_smp(); + padata_init(); page_alloc_init_late(); /* Initialize page ext after all struct pages are initialized. */ page_ext_init(); diff --git a/kernel/padata.c b/kernel/padata.c index b4c7e3e38a05..0c5f4f78f2c2 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -31,7 +31,6 @@ #include #include #include -#include #define MAX_OBJ_NUM 1000 @@ -1052,26 +1051,26 @@ void padata_free_shell(struct padata_shell *ps) } EXPORT_SYMBOL(padata_free_shell); -#ifdef CONFIG_HOTPLUG_CPU - -static __init int padata_driver_init(void) +void __init padata_init(void) { +#ifdef CONFIG_HOTPLUG_CPU int ret; ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "padata:online", padata_cpu_online, NULL); if (ret < 0) - return ret; + goto err; hp_online = ret; ret = cpuhp_setup_state_multi(CPUHP_PADATA_DEAD, "padata:dead", NULL, padata_cpu_dead); if (ret < 0) { cpuhp_remove_multi_state(hp_online); - return ret; + goto err; } - return 0; -} -module_init(padata_driver_init); + return; +err: + pr_warn("padata: initialization failed\n"); #endif +} -- cgit v1.2.3-59-g8ed1b From 4611ce22468895acd61fee9ac1da810d60617d9a Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Wed, 3 Jun 2020 15:59:39 -0700 Subject: padata: allocate work structures for parallel jobs from a pool padata allocates per-CPU, per-instance work structs for parallel jobs. A do_parallel call assigns a job to a sequence number and hashes the number to a CPU, where the job will eventually run using the corresponding work. This approach fit with how padata used to bind a job to each CPU round-robin, makes less sense after commit bfde23ce200e6 ("padata: unbind parallel jobs from specific CPUs") because a work isn't bound to a particular CPU anymore, and isn't needed at all for multithreaded jobs because they don't have sequence numbers. Replace the per-CPU works with a preallocated pool, which allows sharing them between existing padata users and the upcoming multithreaded user. The pool will also facilitate setting NUMA-aware concurrency limits with later users. The pool is sized according to the number of possible CPUs. With this limit, MAX_OBJ_NUM no longer makes sense, so remove it. If the global pool is exhausted, a parallel job is run in the current task instead to throttle a system trying to do too much in parallel. Signed-off-by: Daniel Jordan Signed-off-by: Andrew Morton Tested-by: Josh Triplett Cc: Alexander Duyck Cc: Alex Williamson Cc: Dan Williams Cc: Dave Hansen Cc: David Hildenbrand Cc: Herbert Xu Cc: Jason Gunthorpe Cc: Jonathan Corbet Cc: Kirill Tkhai Cc: Michal Hocko Cc: Pavel Machek Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Randy Dunlap Cc: Robert Elliott Cc: Shile Zhang Cc: Steffen Klassert Cc: Steven Sistare Cc: Tejun Heo Cc: Zi Yan Link: http://lkml.kernel.org/r/20200527173608.2885243-4-daniel.m.jordan@oracle.com Signed-off-by: Linus Torvalds --- include/linux/padata.h | 8 +--- kernel/padata.c | 118 ++++++++++++++++++++++++++++++++----------------- 2 files changed, 78 insertions(+), 48 deletions(-) (limited to 'kernel') diff --git a/include/linux/padata.h b/include/linux/padata.h index d50bd1a7756f..b4da88f8588c 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -24,7 +24,6 @@ * @list: List entry, to attach to the padata lists. * @pd: Pointer to the internal control structure. * @cb_cpu: Callback cpu for serializatioon. - * @cpu: Cpu for parallelization. * @seq_nr: Sequence number of the parallelized data object. * @info: Used to pass information from the parallel to the serial function. * @parallel: Parallel execution function. @@ -34,7 +33,6 @@ struct padata_priv { struct list_head list; struct parallel_data *pd; int cb_cpu; - int cpu; unsigned int seq_nr; int info; void (*parallel)(struct padata_priv *padata); @@ -68,15 +66,11 @@ struct padata_serial_queue { /** * struct padata_parallel_queue - The percpu padata parallel queue * - * @parallel: List to wait for parallelization. * @reorder: List to wait for reordering after parallel processing. - * @work: work struct for parallelization. * @num_obj: Number of objects that are processed by this cpu. */ struct padata_parallel_queue { - struct padata_list parallel; struct padata_list reorder; - struct work_struct work; atomic_t num_obj; }; @@ -111,7 +105,7 @@ struct parallel_data { struct padata_parallel_queue __percpu *pqueue; struct padata_serial_queue __percpu *squeue; atomic_t refcnt; - atomic_t seq_nr; + unsigned int seq_nr; unsigned int processed; int cpu; struct padata_cpumask cpumask; diff --git a/kernel/padata.c b/kernel/padata.c index 0c5f4f78f2c2..d779a73d4d92 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -32,7 +32,15 @@ #include #include -#define MAX_OBJ_NUM 1000 +struct padata_work { + struct work_struct pw_work; + struct list_head pw_list; /* padata_free_works linkage */ + void *pw_data; +}; + +static DEFINE_SPINLOCK(padata_works_lock); +static struct padata_work *padata_works; +static LIST_HEAD(padata_free_works); static void padata_free_pd(struct parallel_data *pd); @@ -58,30 +66,44 @@ static int padata_cpu_hash(struct parallel_data *pd, unsigned int seq_nr) return padata_index_to_cpu(pd, cpu_index); } -static void padata_parallel_worker(struct work_struct *parallel_work) +static struct padata_work *padata_work_alloc(void) { - struct padata_parallel_queue *pqueue; - LIST_HEAD(local_list); + struct padata_work *pw; - local_bh_disable(); - pqueue = container_of(parallel_work, - struct padata_parallel_queue, work); + lockdep_assert_held(&padata_works_lock); - spin_lock(&pqueue->parallel.lock); - list_replace_init(&pqueue->parallel.list, &local_list); - spin_unlock(&pqueue->parallel.lock); + if (list_empty(&padata_free_works)) + return NULL; /* No more work items allowed to be queued. */ - while (!list_empty(&local_list)) { - struct padata_priv *padata; + pw = list_first_entry(&padata_free_works, struct padata_work, pw_list); + list_del(&pw->pw_list); + return pw; +} - padata = list_entry(local_list.next, - struct padata_priv, list); +static void padata_work_init(struct padata_work *pw, work_func_t work_fn, + void *data) +{ + INIT_WORK(&pw->pw_work, work_fn); + pw->pw_data = data; +} - list_del_init(&padata->list); +static void padata_work_free(struct padata_work *pw) +{ + lockdep_assert_held(&padata_works_lock); + list_add(&pw->pw_list, &padata_free_works); +} - padata->parallel(padata); - } +static void padata_parallel_worker(struct work_struct *parallel_work) +{ + struct padata_work *pw = container_of(parallel_work, struct padata_work, + pw_work); + struct padata_priv *padata = pw->pw_data; + local_bh_disable(); + padata->parallel(padata); + spin_lock(&padata_works_lock); + padata_work_free(pw); + spin_unlock(&padata_works_lock); local_bh_enable(); } @@ -105,9 +127,9 @@ int padata_do_parallel(struct padata_shell *ps, struct padata_priv *padata, int *cb_cpu) { struct padata_instance *pinst = ps->pinst; - int i, cpu, cpu_index, target_cpu, err; - struct padata_parallel_queue *queue; + int i, cpu, cpu_index, err; struct parallel_data *pd; + struct padata_work *pw; rcu_read_lock_bh(); @@ -135,25 +157,25 @@ int padata_do_parallel(struct padata_shell *ps, if ((pinst->flags & PADATA_RESET)) goto out; - if (atomic_read(&pd->refcnt) >= MAX_OBJ_NUM) - goto out; - - err = 0; atomic_inc(&pd->refcnt); padata->pd = pd; padata->cb_cpu = *cb_cpu; - padata->seq_nr = atomic_inc_return(&pd->seq_nr); - target_cpu = padata_cpu_hash(pd, padata->seq_nr); - padata->cpu = target_cpu; - queue = per_cpu_ptr(pd->pqueue, target_cpu); - - spin_lock(&queue->parallel.lock); - list_add_tail(&padata->list, &queue->parallel.list); - spin_unlock(&queue->parallel.lock); + rcu_read_unlock_bh(); - queue_work(pinst->parallel_wq, &queue->work); + spin_lock(&padata_works_lock); + padata->seq_nr = ++pd->seq_nr; + pw = padata_work_alloc(); + spin_unlock(&padata_works_lock); + if (pw) { + padata_work_init(pw, padata_parallel_worker, padata); + queue_work(pinst->parallel_wq, &pw->pw_work); + } else { + /* Maximum works limit exceeded, run in the current task. */ + padata->parallel(padata); + } + return 0; out: rcu_read_unlock_bh(); @@ -324,8 +346,9 @@ static void padata_serial_worker(struct work_struct *serial_work) void padata_do_serial(struct padata_priv *padata) { struct parallel_data *pd = padata->pd; + int hashed_cpu = padata_cpu_hash(pd, padata->seq_nr); struct padata_parallel_queue *pqueue = per_cpu_ptr(pd->pqueue, - padata->cpu); + hashed_cpu); struct padata_priv *cur; spin_lock(&pqueue->reorder.lock); @@ -416,8 +439,6 @@ static void padata_init_pqueues(struct parallel_data *pd) pqueue = per_cpu_ptr(pd->pqueue, cpu); __padata_list_init(&pqueue->reorder); - __padata_list_init(&pqueue->parallel); - INIT_WORK(&pqueue->work, padata_parallel_worker); atomic_set(&pqueue->num_obj, 0); } } @@ -451,7 +472,7 @@ 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); + pd->seq_nr = -1; atomic_set(&pd->refcnt, 1); spin_lock_init(&pd->lock); pd->cpu = cpumask_first(pd->cpumask.pcpu); @@ -1053,6 +1074,7 @@ EXPORT_SYMBOL(padata_free_shell); void __init padata_init(void) { + unsigned int i, possible_cpus; #ifdef CONFIG_HOTPLUG_CPU int ret; @@ -1064,13 +1086,27 @@ void __init padata_init(void) ret = cpuhp_setup_state_multi(CPUHP_PADATA_DEAD, "padata:dead", NULL, padata_cpu_dead); - if (ret < 0) { - cpuhp_remove_multi_state(hp_online); - goto err; - } + if (ret < 0) + goto remove_online_state; +#endif + + possible_cpus = num_possible_cpus(); + padata_works = kmalloc_array(possible_cpus, sizeof(struct padata_work), + GFP_KERNEL); + if (!padata_works) + goto remove_dead_state; + + for (i = 0; i < possible_cpus; ++i) + list_add(&padata_works[i].pw_list, &padata_free_works); return; + +remove_dead_state: +#ifdef CONFIG_HOTPLUG_CPU + cpuhp_remove_multi_state(CPUHP_PADATA_DEAD); +remove_online_state: + cpuhp_remove_multi_state(hp_online); err: - pr_warn("padata: initialization failed\n"); #endif + pr_warn("padata: initialization failed\n"); } -- cgit v1.2.3-59-g8ed1b From 004ed42638f4428e70ead59d170f3d17ff761a0f Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Wed, 3 Jun 2020 15:59:43 -0700 Subject: padata: add basic support for multithreaded jobs Sometimes the kernel doesn't take full advantage of system memory bandwidth, leading to a single CPU spending excessive time in initialization paths where the data scales with memory size. Multithreading naturally addresses this problem. Extend padata, a framework that handles many parallel yet singlethreaded jobs, to also handle multithreaded jobs by adding support for splitting up the work evenly, specifying a minimum amount of work that's appropriate for one helper thread to do, load balancing between helpers, and coordinating them. This is inspired by work from Pavel Tatashin and Steve Sistare. Signed-off-by: Daniel Jordan Signed-off-by: Andrew Morton Tested-by: Josh Triplett Cc: Alexander Duyck Cc: Alex Williamson Cc: Dan Williams Cc: Dave Hansen Cc: David Hildenbrand Cc: Herbert Xu Cc: Jason Gunthorpe Cc: Jonathan Corbet Cc: Kirill Tkhai Cc: Michal Hocko Cc: Pavel Machek Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Randy Dunlap Cc: Robert Elliott Cc: Shile Zhang Cc: Steffen Klassert Cc: Steven Sistare Cc: Tejun Heo Cc: Zi Yan Link: http://lkml.kernel.org/r/20200527173608.2885243-5-daniel.m.jordan@oracle.com Signed-off-by: Linus Torvalds --- include/linux/padata.h | 29 ++++++++++ kernel/padata.c | 152 ++++++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 178 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/include/linux/padata.h b/include/linux/padata.h index b4da88f8588c..7302efff5e65 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -4,6 +4,9 @@ * * Copyright (C) 2008, 2009 secunet Security Networks AG * Copyright (C) 2008, 2009 Steffen Klassert + * + * Copyright (c) 2020 Oracle and/or its affiliates. + * Author: Daniel Jordan */ #ifndef PADATA_H @@ -130,6 +133,31 @@ struct padata_shell { struct list_head list; }; +/** + * struct padata_mt_job - represents one multithreaded job + * + * @thread_fn: Called for each chunk of work that a padata thread does. + * @fn_arg: The thread function argument. + * @start: The start of the job (units are job-specific). + * @size: size of this node's work (units are job-specific). + * @align: Ranges passed to the thread function fall on this boundary, with the + * possible exceptions of the beginning and end of the job. + * @min_chunk: The minimum chunk size in job-specific units. This allows + * the client to communicate the minimum amount of work that's + * appropriate for one worker thread to do at once. + * @max_threads: Max threads to use for the job, actual number may be less + * depending on task size and minimum chunk size. + */ +struct padata_mt_job { + void (*thread_fn)(unsigned long start, unsigned long end, void *arg); + void *fn_arg; + unsigned long start; + unsigned long size; + unsigned long align; + unsigned long min_chunk; + int max_threads; +}; + /** * struct padata_instance - The overall control structure. * @@ -173,6 +201,7 @@ 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 void __init padata_do_multithreaded(struct padata_mt_job *job); extern int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type, cpumask_var_t cpumask); extern int padata_start(struct padata_instance *pinst); diff --git a/kernel/padata.c b/kernel/padata.c index d779a73d4d92..29fc5d87a4cd 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -7,6 +7,9 @@ * Copyright (C) 2008, 2009 secunet Security Networks AG * Copyright (C) 2008, 2009 Steffen Klassert * + * Copyright (c) 2020 Oracle and/or its affiliates. + * Author: Daniel Jordan + * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, * version 2, as published by the Free Software Foundation. @@ -21,6 +24,7 @@ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. */ +#include #include #include #include @@ -32,6 +36,8 @@ #include #include +#define PADATA_WORK_ONSTACK 1 /* Work's memory is on stack */ + struct padata_work { struct work_struct pw_work; struct list_head pw_list; /* padata_free_works linkage */ @@ -42,7 +48,17 @@ static DEFINE_SPINLOCK(padata_works_lock); static struct padata_work *padata_works; static LIST_HEAD(padata_free_works); +struct padata_mt_job_state { + spinlock_t lock; + struct completion completion; + struct padata_mt_job *job; + int nworks; + int nworks_fini; + unsigned long chunk_size; +}; + static void padata_free_pd(struct parallel_data *pd); +static void __init padata_mt_helper(struct work_struct *work); static int padata_index_to_cpu(struct parallel_data *pd, int cpu_index) { @@ -81,18 +97,56 @@ static struct padata_work *padata_work_alloc(void) } static void padata_work_init(struct padata_work *pw, work_func_t work_fn, - void *data) + void *data, int flags) { - INIT_WORK(&pw->pw_work, work_fn); + if (flags & PADATA_WORK_ONSTACK) + INIT_WORK_ONSTACK(&pw->pw_work, work_fn); + else + INIT_WORK(&pw->pw_work, work_fn); pw->pw_data = data; } +static int __init padata_work_alloc_mt(int nworks, void *data, + struct list_head *head) +{ + int i; + + spin_lock(&padata_works_lock); + /* Start at 1 because the current task participates in the job. */ + for (i = 1; i < nworks; ++i) { + struct padata_work *pw = padata_work_alloc(); + + if (!pw) + break; + padata_work_init(pw, padata_mt_helper, data, 0); + list_add(&pw->pw_list, head); + } + spin_unlock(&padata_works_lock); + + return i; +} + static void padata_work_free(struct padata_work *pw) { lockdep_assert_held(&padata_works_lock); list_add(&pw->pw_list, &padata_free_works); } +static void __init padata_works_free(struct list_head *works) +{ + struct padata_work *cur, *next; + + if (list_empty(works)) + return; + + spin_lock(&padata_works_lock); + list_for_each_entry_safe(cur, next, works, pw_list) { + list_del(&cur->pw_list); + padata_work_free(cur); + } + spin_unlock(&padata_works_lock); +} + static void padata_parallel_worker(struct work_struct *parallel_work) { struct padata_work *pw = container_of(parallel_work, struct padata_work, @@ -168,7 +222,7 @@ int padata_do_parallel(struct padata_shell *ps, pw = padata_work_alloc(); spin_unlock(&padata_works_lock); if (pw) { - padata_work_init(pw, padata_parallel_worker, padata); + padata_work_init(pw, padata_parallel_worker, padata, 0); queue_work(pinst->parallel_wq, &pw->pw_work); } else { /* Maximum works limit exceeded, run in the current task. */ @@ -409,6 +463,98 @@ out: return err; } +static void __init padata_mt_helper(struct work_struct *w) +{ + struct padata_work *pw = container_of(w, struct padata_work, pw_work); + struct padata_mt_job_state *ps = pw->pw_data; + struct padata_mt_job *job = ps->job; + bool done; + + spin_lock(&ps->lock); + + while (job->size > 0) { + unsigned long start, size, end; + + start = job->start; + /* So end is chunk size aligned if enough work remains. */ + size = roundup(start + 1, ps->chunk_size) - start; + size = min(size, job->size); + end = start + size; + + job->start = end; + job->size -= size; + + spin_unlock(&ps->lock); + job->thread_fn(start, end, job->fn_arg); + spin_lock(&ps->lock); + } + + ++ps->nworks_fini; + done = (ps->nworks_fini == ps->nworks); + spin_unlock(&ps->lock); + + if (done) + complete(&ps->completion); +} + +/** + * padata_do_multithreaded - run a multithreaded job + * @job: Description of the job. + * + * See the definition of struct padata_mt_job for more details. + */ +void __init padata_do_multithreaded(struct padata_mt_job *job) +{ + /* In case threads finish at different times. */ + static const unsigned long load_balance_factor = 4; + struct padata_work my_work, *pw; + struct padata_mt_job_state ps; + LIST_HEAD(works); + int nworks; + + if (job->size == 0) + return; + + /* Ensure at least one thread when size < min_chunk. */ + nworks = max(job->size / job->min_chunk, 1ul); + nworks = min(nworks, job->max_threads); + + if (nworks == 1) { + /* Single thread, no coordination needed, cut to the chase. */ + job->thread_fn(job->start, job->start + job->size, job->fn_arg); + return; + } + + spin_lock_init(&ps.lock); + init_completion(&ps.completion); + ps.job = job; + ps.nworks = padata_work_alloc_mt(nworks, &ps, &works); + ps.nworks_fini = 0; + + /* + * Chunk size is the amount of work a helper does per call to the + * thread function. Load balance large jobs between threads by + * increasing the number of chunks, guarantee at least the minimum + * chunk size from the caller, and honor the caller's alignment. + */ + ps.chunk_size = job->size / (ps.nworks * load_balance_factor); + ps.chunk_size = max(ps.chunk_size, job->min_chunk); + ps.chunk_size = roundup(ps.chunk_size, job->align); + + list_for_each_entry(pw, &works, pw_list) + queue_work(system_unbound_wq, &pw->pw_work); + + /* Use the current thread, which saves starting a workqueue worker. */ + padata_work_init(&my_work, padata_mt_helper, &ps, PADATA_WORK_ONSTACK); + padata_mt_helper(&my_work.pw_work); + + /* Wait for all the helpers to finish. */ + wait_for_completion(&ps.completion); + + destroy_work_on_stack(&my_work.pw_work); + padata_works_free(&works); +} + static void __padata_list_init(struct padata_list *pd_list) { INIT_LIST_HEAD(&pd_list->list); -- cgit v1.2.3-59-g8ed1b From 3fba69a56e16e8dcf182fe6ca77735dd65a898aa Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:01:31 -0700 Subject: mm: memcontrol: drop @compound parameter from memcg charging API The memcg charging API carries a boolean @compound parameter that tells whether the page we're dealing with is a hugepage. mem_cgroup_commit_charge() has another boolean @lrucare that indicates whether the page needs LRU locking or not while charging. The majority of callsites know those parameters at compile time, which results in a lot of naked "false, false" argument lists. This makes for cryptic code and is a breeding ground for subtle mistakes. Thankfully, the huge page state can be inferred from the page itself and doesn't need to be passed along. This is safe because charging completes before the page is published and somebody may split it. Simplify the callsites by removing @compound, and let memcg infer the state by using hpage_nr_pages() unconditionally. That function does PageTransHuge() to identify huge pages, which also helpfully asserts that nobody passes in tail pages by accident. The following patches will introduce a new charging API, best not to carry over unnecessary weight. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Alex Shi Reviewed-by: Joonsoo Kim Reviewed-by: Shakeel Butt Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-4-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 22 ++++++++-------------- kernel/events/uprobes.c | 6 +++--- mm/filemap.c | 6 +++--- mm/huge_memory.c | 8 ++++---- mm/khugepaged.c | 20 ++++++++++---------- mm/memcontrol.c | 38 +++++++++++++++----------------------- mm/memory.c | 32 +++++++++++++++----------------- mm/migrate.c | 6 +++--- mm/shmem.c | 22 +++++++++------------- mm/swapfile.c | 9 ++++----- mm/userfaultfd.c | 6 +++--- 11 files changed, 77 insertions(+), 98 deletions(-) (limited to 'kernel') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index bfe9533bb67e..fc400002c7be 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -359,15 +359,12 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, struct mem_cgroup *memcg); int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp, - bool compound); + gfp_t gfp_mask, struct mem_cgroup **memcgp); int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp, - bool compound); + gfp_t gfp_mask, struct mem_cgroup **memcgp); void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare, bool compound); -void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg, - bool compound); + bool lrucare); +void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg); void mem_cgroup_uncharge(struct page *page); void mem_cgroup_uncharge_list(struct list_head *page_list); @@ -849,8 +846,7 @@ static inline enum mem_cgroup_protection mem_cgroup_protected( static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, - struct mem_cgroup **memcgp, - bool compound) + struct mem_cgroup **memcgp) { *memcgp = NULL; return 0; @@ -859,8 +855,7 @@ static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, static inline int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, - struct mem_cgroup **memcgp, - bool compound) + struct mem_cgroup **memcgp) { *memcgp = NULL; return 0; @@ -868,13 +863,12 @@ static inline int mem_cgroup_try_charge_delay(struct page *page, static inline void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare, bool compound) + bool lrucare) { } static inline void mem_cgroup_cancel_charge(struct page *page, - struct mem_cgroup *memcg, - bool compound) + struct mem_cgroup *memcg) { } diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index ece7e13f6e4a..40e7488ce467 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -169,7 +169,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, if (new_page) { err = mem_cgroup_try_charge(new_page, vma->vm_mm, GFP_KERNEL, - &memcg, false); + &memcg); if (err) return err; } @@ -181,7 +181,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, err = -EAGAIN; if (!page_vma_mapped_walk(&pvmw)) { if (new_page) - mem_cgroup_cancel_charge(new_page, memcg, false); + mem_cgroup_cancel_charge(new_page, memcg); goto unlock; } VM_BUG_ON_PAGE(addr != pvmw.address, old_page); @@ -189,7 +189,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, if (new_page) { get_page(new_page); page_add_new_anon_rmap(new_page, vma, addr, false); - mem_cgroup_commit_charge(new_page, memcg, false, false); + mem_cgroup_commit_charge(new_page, memcg, false); lru_cache_add_active_or_unevictable(new_page, vma); } else /* no new page, just dec_mm_counter for old_page */ diff --git a/mm/filemap.c b/mm/filemap.c index 9af4af660ef1..f268cfffbc6e 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -842,7 +842,7 @@ static int __add_to_page_cache_locked(struct page *page, if (!huge) { error = mem_cgroup_try_charge(page, current->mm, - gfp_mask, &memcg, false); + gfp_mask, &memcg); if (error) return error; } @@ -878,14 +878,14 @@ unlock: goto error; if (!huge) - mem_cgroup_commit_charge(page, memcg, false, false); + mem_cgroup_commit_charge(page, memcg, false); trace_mm_filemap_add_to_page_cache(page); return 0; error: page->mapping = NULL; /* Leave page->index set: truncation relies upon it */ if (!huge) - mem_cgroup_cancel_charge(page, memcg, false); + mem_cgroup_cancel_charge(page, memcg); put_page(page); return xas_error(&xas); } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 693c0ff2256c..672e34932b53 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -594,7 +594,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, VM_BUG_ON_PAGE(!PageCompound(page), page); - if (mem_cgroup_try_charge_delay(page, vma->vm_mm, gfp, &memcg, true)) { + if (mem_cgroup_try_charge_delay(page, vma->vm_mm, gfp, &memcg)) { put_page(page); count_vm_event(THP_FAULT_FALLBACK); count_vm_event(THP_FAULT_FALLBACK_CHARGE); @@ -630,7 +630,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, vm_fault_t ret2; spin_unlock(vmf->ptl); - mem_cgroup_cancel_charge(page, memcg, true); + mem_cgroup_cancel_charge(page, memcg); put_page(page); pte_free(vma->vm_mm, pgtable); ret2 = handle_userfault(vmf, VM_UFFD_MISSING); @@ -641,7 +641,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, entry = mk_huge_pmd(page, vma->vm_page_prot); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); page_add_new_anon_rmap(page, vma, haddr, true); - mem_cgroup_commit_charge(page, memcg, false, true); + mem_cgroup_commit_charge(page, memcg, false); lru_cache_add_active_or_unevictable(page, vma); pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable); set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); @@ -658,7 +658,7 @@ unlock_release: release: if (pgtable) pte_free(vma->vm_mm, pgtable); - mem_cgroup_cancel_charge(page, memcg, true); + mem_cgroup_cancel_charge(page, memcg); put_page(page); return ret; diff --git a/mm/khugepaged.c b/mm/khugepaged.c index e7897a7dfbec..0a29b51494fd 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1060,7 +1060,7 @@ static void collapse_huge_page(struct mm_struct *mm, goto out_nolock; } - if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) { + if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out_nolock; } @@ -1068,7 +1068,7 @@ static void collapse_huge_page(struct mm_struct *mm, down_read(&mm->mmap_sem); result = hugepage_vma_revalidate(mm, address, &vma); if (result) { - mem_cgroup_cancel_charge(new_page, memcg, true); + mem_cgroup_cancel_charge(new_page, memcg); up_read(&mm->mmap_sem); goto out_nolock; } @@ -1076,7 +1076,7 @@ static void collapse_huge_page(struct mm_struct *mm, pmd = mm_find_pmd(mm, address); if (!pmd) { result = SCAN_PMD_NULL; - mem_cgroup_cancel_charge(new_page, memcg, true); + mem_cgroup_cancel_charge(new_page, memcg); up_read(&mm->mmap_sem); goto out_nolock; } @@ -1088,7 +1088,7 @@ static void collapse_huge_page(struct mm_struct *mm, */ if (unmapped && !__collapse_huge_page_swapin(mm, vma, address, pmd, referenced)) { - mem_cgroup_cancel_charge(new_page, memcg, true); + mem_cgroup_cancel_charge(new_page, memcg); up_read(&mm->mmap_sem); goto out_nolock; } @@ -1176,7 +1176,7 @@ static void collapse_huge_page(struct mm_struct *mm, spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); page_add_new_anon_rmap(new_page, vma, address, true); - mem_cgroup_commit_charge(new_page, memcg, false, true); + mem_cgroup_commit_charge(new_page, memcg, false); count_memcg_events(memcg, THP_COLLAPSE_ALLOC, 1); lru_cache_add_active_or_unevictable(new_page, vma); pgtable_trans_huge_deposit(mm, pmd, pgtable); @@ -1194,7 +1194,7 @@ out_nolock: trace_mm_collapse_huge_page(mm, isolated, result); return; out: - mem_cgroup_cancel_charge(new_page, memcg, true); + mem_cgroup_cancel_charge(new_page, memcg); goto out_up_write; } @@ -1637,7 +1637,7 @@ static void collapse_file(struct mm_struct *mm, goto out; } - if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) { + if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out; } @@ -1650,7 +1650,7 @@ static void collapse_file(struct mm_struct *mm, break; xas_unlock_irq(&xas); if (!xas_nomem(&xas, GFP_KERNEL)) { - mem_cgroup_cancel_charge(new_page, memcg, true); + mem_cgroup_cancel_charge(new_page, memcg); result = SCAN_FAIL; goto out; } @@ -1887,7 +1887,7 @@ xa_unlocked: SetPageUptodate(new_page); page_ref_add(new_page, HPAGE_PMD_NR - 1); - mem_cgroup_commit_charge(new_page, memcg, false, true); + mem_cgroup_commit_charge(new_page, memcg, false); if (is_shmem) { set_page_dirty(new_page); @@ -1942,7 +1942,7 @@ xa_unlocked: VM_BUG_ON(nr_none); xas_unlock_irq(&xas); - mem_cgroup_cancel_charge(new_page, memcg, true); + mem_cgroup_cancel_charge(new_page, memcg); new_page->mapping = NULL; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 8f95896c5aa1..340c580f8363 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -834,7 +834,7 @@ static unsigned long memcg_events_local(struct mem_cgroup *memcg, int event) static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, struct page *page, - bool compound, int nr_pages) + int nr_pages) { /* * Here, RSS means 'mapped anon' and anon's SwapCache. Shmem/tmpfs is @@ -848,7 +848,7 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, __mod_memcg_state(memcg, NR_SHMEM, nr_pages); } - if (compound) { + if (abs(nr_pages) > 1) { VM_BUG_ON_PAGE(!PageTransHuge(page), page); __mod_memcg_state(memcg, MEMCG_RSS_HUGE, nr_pages); } @@ -5501,9 +5501,9 @@ static int mem_cgroup_move_account(struct page *page, ret = 0; local_irq_disable(); - mem_cgroup_charge_statistics(to, page, compound, nr_pages); + mem_cgroup_charge_statistics(to, page, nr_pages); memcg_check_events(to, page); - mem_cgroup_charge_statistics(from, page, compound, -nr_pages); + mem_cgroup_charge_statistics(from, page, -nr_pages); memcg_check_events(from, page); local_irq_enable(); out_unlock: @@ -6494,7 +6494,6 @@ out: * @mm: mm context of the victim * @gfp_mask: reclaim mode * @memcgp: charged memcg return - * @compound: charge the page as compound or small page * * Try to charge @page to the memcg that @mm belongs to, reclaiming * pages according to @gfp_mask if necessary. @@ -6507,11 +6506,10 @@ out: * with mem_cgroup_cancel_charge() in case page instantiation fails. */ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp, - bool compound) + gfp_t gfp_mask, struct mem_cgroup **memcgp) { + unsigned int nr_pages = hpage_nr_pages(page); struct mem_cgroup *memcg = NULL; - unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1; int ret = 0; if (mem_cgroup_disabled()) @@ -6553,13 +6551,12 @@ out: } int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp, - bool compound) + gfp_t gfp_mask, struct mem_cgroup **memcgp) { struct mem_cgroup *memcg; int ret; - ret = mem_cgroup_try_charge(page, mm, gfp_mask, memcgp, compound); + ret = mem_cgroup_try_charge(page, mm, gfp_mask, memcgp); memcg = *memcgp; mem_cgroup_throttle_swaprate(memcg, page_to_nid(page), gfp_mask); return ret; @@ -6570,7 +6567,6 @@ int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, * @page: page to charge * @memcg: memcg to charge the page to * @lrucare: page might be on LRU already - * @compound: charge the page as compound or small page * * Finalize a charge transaction started by mem_cgroup_try_charge(), * after page->mapping has been set up. This must happen atomically @@ -6583,9 +6579,9 @@ int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, * Use mem_cgroup_cancel_charge() to cancel the transaction instead. */ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare, bool compound) + bool lrucare) { - unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1; + unsigned int nr_pages = hpage_nr_pages(page); VM_BUG_ON_PAGE(!page->mapping, page); VM_BUG_ON_PAGE(PageLRU(page) && !lrucare, page); @@ -6603,7 +6599,7 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, commit_charge(page, memcg, lrucare); local_irq_disable(); - mem_cgroup_charge_statistics(memcg, page, compound, nr_pages); + mem_cgroup_charge_statistics(memcg, page, nr_pages); memcg_check_events(memcg, page); local_irq_enable(); @@ -6622,14 +6618,12 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, * mem_cgroup_cancel_charge - cancel a page charge * @page: page to charge * @memcg: memcg to charge the page to - * @compound: charge the page as compound or small page * * Cancel a charge transaction started by mem_cgroup_try_charge(). */ -void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg, - bool compound) +void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg) { - unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1; + unsigned int nr_pages = hpage_nr_pages(page); if (mem_cgroup_disabled()) return; @@ -6844,8 +6838,7 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) commit_charge(newpage, memcg, false); local_irq_save(flags); - mem_cgroup_charge_statistics(memcg, newpage, PageTransHuge(newpage), - nr_pages); + mem_cgroup_charge_statistics(memcg, newpage, nr_pages); memcg_check_events(memcg, newpage); local_irq_restore(flags); } @@ -7075,8 +7068,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) * only synchronisation we have for updating the per-CPU variables. */ VM_BUG_ON(!irqs_disabled()); - mem_cgroup_charge_statistics(memcg, page, PageTransHuge(page), - -nr_entries); + mem_cgroup_charge_statistics(memcg, page, -nr_entries); memcg_check_events(memcg, page); if (!mem_cgroup_is_root(memcg)) diff --git a/mm/memory.c b/mm/memory.c index 21438278afca..6b8c5900e9a4 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2676,7 +2676,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) } } - if (mem_cgroup_try_charge_delay(new_page, mm, GFP_KERNEL, &memcg, false)) + if (mem_cgroup_try_charge_delay(new_page, mm, GFP_KERNEL, &memcg)) goto oom_free_new; __SetPageUptodate(new_page); @@ -2711,7 +2711,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) */ ptep_clear_flush_notify(vma, vmf->address, vmf->pte); page_add_new_anon_rmap(new_page, vma, vmf->address, false); - mem_cgroup_commit_charge(new_page, memcg, false, false); + mem_cgroup_commit_charge(new_page, memcg, false); lru_cache_add_active_or_unevictable(new_page, vma); /* * We call the notify macro here because, when using secondary @@ -2750,7 +2750,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) new_page = old_page; page_copied = 1; } else { - mem_cgroup_cancel_charge(new_page, memcg, false); + mem_cgroup_cancel_charge(new_page, memcg); } if (new_page) @@ -3193,8 +3193,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) goto out_page; } - if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, - &memcg, false)) { + if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, &memcg)) { ret = VM_FAULT_OOM; goto out_page; } @@ -3245,11 +3244,11 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) /* ksm created a completely new copy */ if (unlikely(page != swapcache && swapcache)) { page_add_new_anon_rmap(page, vma, vmf->address, false); - mem_cgroup_commit_charge(page, memcg, false, false); + mem_cgroup_commit_charge(page, memcg, false); lru_cache_add_active_or_unevictable(page, vma); } else { do_page_add_anon_rmap(page, vma, vmf->address, exclusive); - mem_cgroup_commit_charge(page, memcg, true, false); + mem_cgroup_commit_charge(page, memcg, true); activate_page(page); } @@ -3285,7 +3284,7 @@ unlock: out: return ret; out_nomap: - mem_cgroup_cancel_charge(page, memcg, false); + mem_cgroup_cancel_charge(page, memcg); pte_unmap_unlock(vmf->pte, vmf->ptl); out_page: unlock_page(page); @@ -3359,8 +3358,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) if (!page) goto oom; - if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, &memcg, - false)) + if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, &memcg)) goto oom_free_page; /* @@ -3386,14 +3384,14 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); - mem_cgroup_cancel_charge(page, memcg, false); + mem_cgroup_cancel_charge(page, memcg); put_page(page); return handle_userfault(vmf, VM_UFFD_MISSING); } inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, vmf->address, false); - mem_cgroup_commit_charge(page, memcg, false, false); + mem_cgroup_commit_charge(page, memcg, false); lru_cache_add_active_or_unevictable(page, vma); setpte: set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); @@ -3404,7 +3402,7 @@ unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; release: - mem_cgroup_cancel_charge(page, memcg, false); + mem_cgroup_cancel_charge(page, memcg); put_page(page); goto unlock; oom_free_page: @@ -3655,7 +3653,7 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, if (write && !(vma->vm_flags & VM_SHARED)) { inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, vmf->address, false); - mem_cgroup_commit_charge(page, memcg, false, false); + mem_cgroup_commit_charge(page, memcg, false); lru_cache_add_active_or_unevictable(page, vma); } else { inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page)); @@ -3864,8 +3862,8 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf) if (!vmf->cow_page) return VM_FAULT_OOM; - if (mem_cgroup_try_charge_delay(vmf->cow_page, vma->vm_mm, GFP_KERNEL, - &vmf->memcg, false)) { + if (mem_cgroup_try_charge_delay(vmf->cow_page, vma->vm_mm, + GFP_KERNEL, &vmf->memcg)) { put_page(vmf->cow_page); return VM_FAULT_OOM; } @@ -3886,7 +3884,7 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf) goto uncharge_out; return ret; uncharge_out: - mem_cgroup_cancel_charge(vmf->cow_page, vmf->memcg, false); + mem_cgroup_cancel_charge(vmf->cow_page, vmf->memcg); put_page(vmf->cow_page); return ret; } diff --git a/mm/migrate.c b/mm/migrate.c index 846af96b84a5..93c732213d12 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2780,7 +2780,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, if (unlikely(anon_vma_prepare(vma))) goto abort; - if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, &memcg, false)) + if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, &memcg)) goto abort; /* @@ -2826,7 +2826,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, inc_mm_counter(mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, addr, false); - mem_cgroup_commit_charge(page, memcg, false, false); + mem_cgroup_commit_charge(page, memcg, false); if (!is_zone_device_page(page)) lru_cache_add_active_or_unevictable(page, vma); get_page(page); @@ -2848,7 +2848,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, unlock_abort: pte_unmap_unlock(ptep, ptl); - mem_cgroup_cancel_charge(page, memcg, false); + mem_cgroup_cancel_charge(page, memcg); abort: *src &= ~MIGRATE_PFN_MIGRATE; } diff --git a/mm/shmem.c b/mm/shmem.c index bd8840082c94..d505b6cce4ab 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1664,8 +1664,7 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index, goto failed; } - error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg, - false); + error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg); if (!error) { error = shmem_add_to_page_cache(page, mapping, index, swp_to_radix_entry(swap), gfp); @@ -1680,14 +1679,14 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index, * the rest. */ if (error) { - mem_cgroup_cancel_charge(page, memcg, false); + mem_cgroup_cancel_charge(page, memcg); delete_from_swap_cache(page); } } if (error) goto failed; - mem_cgroup_commit_charge(page, memcg, true, false); + mem_cgroup_commit_charge(page, memcg, true); spin_lock_irq(&info->lock); info->swapped--; @@ -1859,8 +1858,7 @@ alloc_nohuge: if (sgp == SGP_WRITE) __SetPageReferenced(page); - error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg, - PageTransHuge(page)); + error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg); if (error) { if (PageTransHuge(page)) { count_vm_event(THP_FILE_FALLBACK); @@ -1871,12 +1869,10 @@ alloc_nohuge: error = shmem_add_to_page_cache(page, mapping, hindex, NULL, gfp & GFP_RECLAIM_MASK); if (error) { - mem_cgroup_cancel_charge(page, memcg, - PageTransHuge(page)); + mem_cgroup_cancel_charge(page, memcg); goto unacct; } - mem_cgroup_commit_charge(page, memcg, false, - PageTransHuge(page)); + mem_cgroup_commit_charge(page, memcg, false); lru_cache_add_anon(page); spin_lock_irq(&info->lock); @@ -2364,7 +2360,7 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, if (unlikely(offset >= max_off)) goto out_release; - ret = mem_cgroup_try_charge_delay(page, dst_mm, gfp, &memcg, false); + ret = mem_cgroup_try_charge_delay(page, dst_mm, gfp, &memcg); if (ret) goto out_release; @@ -2373,7 +2369,7 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, if (ret) goto out_release_uncharge; - mem_cgroup_commit_charge(page, memcg, false, false); + mem_cgroup_commit_charge(page, memcg, false); _dst_pte = mk_pte(page, dst_vma->vm_page_prot); if (dst_vma->vm_flags & VM_WRITE) @@ -2424,7 +2420,7 @@ out_release_uncharge_unlock: ClearPageDirty(page); delete_from_page_cache(page); out_release_uncharge: - mem_cgroup_cancel_charge(page, memcg, false); + mem_cgroup_cancel_charge(page, memcg); out_release: unlock_page(page); put_page(page); diff --git a/mm/swapfile.c b/mm/swapfile.c index 63ac67208453..40a80617cb03 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1902,15 +1902,14 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, if (unlikely(!page)) return -ENOMEM; - if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, - &memcg, false)) { + if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, &memcg)) { ret = -ENOMEM; goto out_nolock; } pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (unlikely(!pte_same_as_swp(*pte, swp_entry_to_pte(entry)))) { - mem_cgroup_cancel_charge(page, memcg, false); + mem_cgroup_cancel_charge(page, memcg); ret = 0; goto out; } @@ -1922,10 +1921,10 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, pte_mkold(mk_pte(page, vma->vm_page_prot))); if (page == swapcache) { page_add_anon_rmap(page, vma, addr, false); - mem_cgroup_commit_charge(page, memcg, true, false); + mem_cgroup_commit_charge(page, memcg, true); } else { /* ksm created a completely new copy */ page_add_new_anon_rmap(page, vma, addr, false); - mem_cgroup_commit_charge(page, memcg, false, false); + mem_cgroup_commit_charge(page, memcg, false); lru_cache_add_active_or_unevictable(page, vma); } swap_free(entry); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 512576e171ce..bb57d0a3fca7 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -97,7 +97,7 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, __SetPageUptodate(page); ret = -ENOMEM; - if (mem_cgroup_try_charge(page, dst_mm, GFP_KERNEL, &memcg, false)) + if (mem_cgroup_try_charge(page, dst_mm, GFP_KERNEL, &memcg)) goto out_release; _dst_pte = pte_mkdirty(mk_pte(page, dst_vma->vm_page_prot)); @@ -124,7 +124,7 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, inc_mm_counter(dst_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, dst_vma, dst_addr, false); - mem_cgroup_commit_charge(page, memcg, false, false); + mem_cgroup_commit_charge(page, memcg, false); lru_cache_add_active_or_unevictable(page, dst_vma); set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); @@ -138,7 +138,7 @@ out: return ret; out_release_uncharge_unlock: pte_unmap_unlock(dst_pte, ptl); - mem_cgroup_cancel_charge(page, memcg, false); + mem_cgroup_cancel_charge(page, memcg); out_release: put_page(page); goto out; -- cgit v1.2.3-59-g8ed1b From be5d0a74c62d8da43f9526a5b08cdd18e2bbc37a Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:01:57 -0700 Subject: mm: memcontrol: switch to native NR_ANON_MAPPED counter Memcg maintains a private MEMCG_RSS counter. This divergence from the generic VM accounting means unnecessary code overhead, and creates a dependency for memcg that page->mapping is set up at the time of charging, so that page types can be told apart. Convert the generic accounting sites to mod_lruvec_page_state and friends to maintain the per-cgroup vmstat counter of NR_ANON_MAPPED. We use lock_page_memcg() to stabilize page->mem_cgroup during rmap changes, the same way we do for NR_FILE_MAPPED. With the previous patch removing MEMCG_CACHE and the private NR_SHMEM counter, this patch finally eliminates the need to have page->mapping set up at charge time. However, we need to have page->mem_cgroup set up by the time rmap runs and does the accounting, so switch the commit and the rmap callbacks around. v2: fix temporary accounting bug by switching rmap<->commit (Joonsoo) Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Cc: Alex Shi Cc: Hugh Dickins Cc: Joonsoo Kim Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-11-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 3 +-- kernel/events/uprobes.c | 2 +- mm/huge_memory.c | 2 +- mm/khugepaged.c | 2 +- mm/memcontrol.c | 27 +++++++++----------------- mm/memory.c | 10 +++++----- mm/migrate.c | 2 +- mm/rmap.c | 47 ++++++++++++++++++++++++++++------------------ mm/swapfile.c | 4 ++-- mm/userfaultfd.c | 2 +- 10 files changed, 51 insertions(+), 50 deletions(-) (limited to 'kernel') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index f6ea68ceed2c..acacc3018957 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -29,8 +29,7 @@ struct kmem_cache; /* Cgroup-specific page state, on top of universal node page state */ enum memcg_stat_item { - MEMCG_RSS = NR_VM_NODE_STAT_ITEMS, - MEMCG_RSS_HUGE, + MEMCG_RSS_HUGE = NR_VM_NODE_STAT_ITEMS, MEMCG_SWAP, MEMCG_SOCK, /* XXX: why are these zone and not node counters? */ diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 40e7488ce467..89ef81b65bcb 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -188,8 +188,8 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, if (new_page) { get_page(new_page); - page_add_new_anon_rmap(new_page, vma, addr, false); mem_cgroup_commit_charge(new_page, memcg, false); + page_add_new_anon_rmap(new_page, vma, addr, false); lru_cache_add_active_or_unevictable(new_page, vma); } else /* no new page, just dec_mm_counter for old_page */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 672e34932b53..2caf2494db66 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -640,8 +640,8 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, entry = mk_huge_pmd(page, vma->vm_page_prot); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); - page_add_new_anon_rmap(page, vma, haddr, true); mem_cgroup_commit_charge(page, memcg, false); + page_add_new_anon_rmap(page, vma, haddr, true); lru_cache_add_active_or_unevictable(page, vma); pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable); set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index ddbdc1e3a694..34eff4dfae80 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1175,8 +1175,8 @@ static void collapse_huge_page(struct mm_struct *mm, spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); - page_add_new_anon_rmap(new_page, vma, address, true); mem_cgroup_commit_charge(new_page, memcg, false); + page_add_new_anon_rmap(new_page, vma, address, true); count_memcg_events(memcg, THP_COLLAPSE_ALLOC, 1); lru_cache_add_active_or_unevictable(new_page, vma); pgtable_trans_huge_deposit(mm, pmd, pgtable); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ab3497ba0e35..b80125303c02 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -836,13 +836,6 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, struct page *page, int nr_pages) { - /* - * Here, RSS means 'mapped anon' and anon's SwapCache. Shmem/tmpfs is - * counted as CACHE even if it's on ANON LRU. - */ - if (PageAnon(page)) - __mod_memcg_state(memcg, MEMCG_RSS, nr_pages); - if (abs(nr_pages) > 1) { VM_BUG_ON_PAGE(!PageTransHuge(page), page); __mod_memcg_state(memcg, MEMCG_RSS_HUGE, nr_pages); @@ -1384,7 +1377,7 @@ static char *memory_stat_format(struct mem_cgroup *memcg) */ seq_buf_printf(&s, "anon %llu\n", - (u64)memcg_page_state(memcg, MEMCG_RSS) * + (u64)memcg_page_state(memcg, NR_ANON_MAPPED) * PAGE_SIZE); seq_buf_printf(&s, "file %llu\n", (u64)memcg_page_state(memcg, NR_FILE_PAGES) * @@ -3353,7 +3346,7 @@ static unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) if (mem_cgroup_is_root(memcg)) { val = memcg_page_state(memcg, NR_FILE_PAGES) + - memcg_page_state(memcg, MEMCG_RSS); + memcg_page_state(memcg, NR_ANON_MAPPED); if (swap) val += memcg_page_state(memcg, MEMCG_SWAP); } else { @@ -3824,7 +3817,7 @@ static int memcg_numa_stat_show(struct seq_file *m, void *v) static const unsigned int memcg1_stats[] = { NR_FILE_PAGES, - MEMCG_RSS, + NR_ANON_MAPPED, MEMCG_RSS_HUGE, NR_SHMEM, NR_FILE_MAPPED, @@ -5455,7 +5448,12 @@ static int mem_cgroup_move_account(struct page *page, lock_page_memcg(page); - if (!PageAnon(page)) { + if (PageAnon(page)) { + if (page_mapped(page)) { + __mod_lruvec_state(from_vec, NR_ANON_MAPPED, -nr_pages); + __mod_lruvec_state(to_vec, NR_ANON_MAPPED, nr_pages); + } + } else { __mod_lruvec_state(from_vec, NR_FILE_PAGES, -nr_pages); __mod_lruvec_state(to_vec, NR_FILE_PAGES, nr_pages); @@ -6589,7 +6587,6 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, { unsigned int nr_pages = hpage_nr_pages(page); - VM_BUG_ON_PAGE(!page->mapping, page); VM_BUG_ON_PAGE(PageLRU(page) && !lrucare, page); if (mem_cgroup_disabled()) @@ -6662,8 +6659,6 @@ int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, struct mem_cgroup *memcg; int ret; - VM_BUG_ON_PAGE(!page->mapping, page); - ret = mem_cgroup_try_charge(page, mm, gfp_mask, &memcg); if (ret) return ret; @@ -6675,7 +6670,6 @@ struct uncharge_gather { struct mem_cgroup *memcg; unsigned long nr_pages; unsigned long pgpgout; - unsigned long nr_anon; unsigned long nr_kmem; unsigned long nr_huge; struct page *dummy_page; @@ -6700,7 +6694,6 @@ static void uncharge_batch(const struct uncharge_gather *ug) } local_irq_save(flags); - __mod_memcg_state(ug->memcg, MEMCG_RSS, -ug->nr_anon); __mod_memcg_state(ug->memcg, MEMCG_RSS_HUGE, -ug->nr_huge); __count_memcg_events(ug->memcg, PGPGOUT, ug->pgpgout); __this_cpu_add(ug->memcg->vmstats_percpu->nr_page_events, ug->nr_pages); @@ -6740,8 +6733,6 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug) if (!PageKmemcg(page)) { if (PageTransHuge(page)) ug->nr_huge += nr_pages; - if (PageAnon(page)) - ug->nr_anon += nr_pages; ug->pgpgout++; } else { ug->nr_kmem += nr_pages; diff --git a/mm/memory.c b/mm/memory.c index 6b8c5900e9a4..543e41b1d57a 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2710,8 +2710,8 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) * thread doing COW. */ ptep_clear_flush_notify(vma, vmf->address, vmf->pte); - page_add_new_anon_rmap(new_page, vma, vmf->address, false); mem_cgroup_commit_charge(new_page, memcg, false); + page_add_new_anon_rmap(new_page, vma, vmf->address, false); lru_cache_add_active_or_unevictable(new_page, vma); /* * We call the notify macro here because, when using secondary @@ -3243,12 +3243,12 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) /* ksm created a completely new copy */ if (unlikely(page != swapcache && swapcache)) { - page_add_new_anon_rmap(page, vma, vmf->address, false); mem_cgroup_commit_charge(page, memcg, false); + page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_active_or_unevictable(page, vma); } else { - do_page_add_anon_rmap(page, vma, vmf->address, exclusive); mem_cgroup_commit_charge(page, memcg, true); + do_page_add_anon_rmap(page, vma, vmf->address, exclusive); activate_page(page); } @@ -3390,8 +3390,8 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) } inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, vmf->address, false); mem_cgroup_commit_charge(page, memcg, false); + page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_active_or_unevictable(page, vma); setpte: set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); @@ -3652,8 +3652,8 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, /* copy-on-write page */ if (write && !(vma->vm_flags & VM_SHARED)) { inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, vmf->address, false); mem_cgroup_commit_charge(page, memcg, false); + page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_active_or_unevictable(page, vma); } else { inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page)); diff --git a/mm/migrate.c b/mm/migrate.c index 0d1f796df75f..e72ed681634f 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2832,8 +2832,8 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, goto unlock_abort; inc_mm_counter(mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, addr, false); mem_cgroup_commit_charge(page, memcg, false); + page_add_new_anon_rmap(page, vma, addr, false); if (!is_zone_device_page(page)) lru_cache_add_active_or_unevictable(page, vma); get_page(page); diff --git a/mm/rmap.c b/mm/rmap.c index f79a206b271a..150513d31efa 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1114,6 +1114,11 @@ void do_page_add_anon_rmap(struct page *page, bool compound = flags & RMAP_COMPOUND; bool first; + if (unlikely(PageKsm(page))) + lock_page_memcg(page); + else + VM_BUG_ON_PAGE(!PageLocked(page), page); + if (compound) { atomic_t *mapcount; VM_BUG_ON_PAGE(!PageLocked(page), page); @@ -1134,12 +1139,13 @@ void do_page_add_anon_rmap(struct page *page, */ if (compound) __inc_node_page_state(page, NR_ANON_THPS); - __mod_node_page_state(page_pgdat(page), NR_ANON_MAPPED, nr); + __mod_lruvec_page_state(page, NR_ANON_MAPPED, nr); } - if (unlikely(PageKsm(page))) - return; - VM_BUG_ON_PAGE(!PageLocked(page), page); + if (unlikely(PageKsm(page))) { + unlock_page_memcg(page); + return; + } /* address might be in next vma when migration races vma_adjust */ if (first) @@ -1181,7 +1187,7 @@ void page_add_new_anon_rmap(struct page *page, /* increment count (starts at -1) */ atomic_set(&page->_mapcount, 0); } - __mod_node_page_state(page_pgdat(page), NR_ANON_MAPPED, nr); + __mod_lruvec_page_state(page, NR_ANON_MAPPED, nr); __page_set_anon_rmap(page, vma, address, 1); } @@ -1230,13 +1236,12 @@ static void page_remove_file_rmap(struct page *page, bool compound) int i, nr = 1; VM_BUG_ON_PAGE(compound && !PageHead(page), page); - lock_page_memcg(page); /* Hugepages are not counted in NR_FILE_MAPPED for now. */ if (unlikely(PageHuge(page))) { /* hugetlb pages are always mapped with pmds */ atomic_dec(compound_mapcount_ptr(page)); - goto out; + return; } /* page still mapped by someone else? */ @@ -1246,14 +1251,14 @@ static void page_remove_file_rmap(struct page *page, bool compound) nr++; } if (!atomic_add_negative(-1, compound_mapcount_ptr(page))) - goto out; + return; if (PageSwapBacked(page)) __dec_node_page_state(page, NR_SHMEM_PMDMAPPED); else __dec_node_page_state(page, NR_FILE_PMDMAPPED); } else { if (!atomic_add_negative(-1, &page->_mapcount)) - goto out; + return; } /* @@ -1265,8 +1270,6 @@ static void page_remove_file_rmap(struct page *page, bool compound) if (unlikely(PageMlocked(page))) clear_page_mlock(page); -out: - unlock_page_memcg(page); } static void page_remove_anon_compound_rmap(struct page *page) @@ -1310,7 +1313,7 @@ static void page_remove_anon_compound_rmap(struct page *page) clear_page_mlock(page); if (nr) - __mod_node_page_state(page_pgdat(page), NR_ANON_MAPPED, -nr); + __mod_lruvec_page_state(page, NR_ANON_MAPPED, -nr); } /** @@ -1322,22 +1325,28 @@ static void page_remove_anon_compound_rmap(struct page *page) */ void page_remove_rmap(struct page *page, bool compound) { - if (!PageAnon(page)) - return page_remove_file_rmap(page, compound); + lock_page_memcg(page); - if (compound) - return page_remove_anon_compound_rmap(page); + if (!PageAnon(page)) { + page_remove_file_rmap(page, compound); + goto out; + } + + if (compound) { + page_remove_anon_compound_rmap(page); + goto out; + } /* page still mapped by someone else? */ if (!atomic_add_negative(-1, &page->_mapcount)) - return; + goto out; /* * We use the irq-unsafe __{inc|mod}_zone_page_stat because * these counters are not modified in interrupt context, and * pte lock(a spinlock) is held, which implies preemption disabled. */ - __dec_node_page_state(page, NR_ANON_MAPPED); + __dec_lruvec_page_state(page, NR_ANON_MAPPED); if (unlikely(PageMlocked(page))) clear_page_mlock(page); @@ -1354,6 +1363,8 @@ void page_remove_rmap(struct page *page, bool compound) * Leaving it set also helps swapoff to reinstate ptes * faster for those pages still in swapcache. */ +out: + unlock_page_memcg(page); } /* diff --git a/mm/swapfile.c b/mm/swapfile.c index 1829fc4b3ca2..01f6538bad2d 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1920,11 +1920,11 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, set_pte_at(vma->vm_mm, addr, pte, pte_mkold(mk_pte(page, vma->vm_page_prot))); if (page == swapcache) { - page_add_anon_rmap(page, vma, addr, false); mem_cgroup_commit_charge(page, memcg, true); + page_add_anon_rmap(page, vma, addr, false); } else { /* ksm created a completely new copy */ - page_add_new_anon_rmap(page, vma, addr, false); mem_cgroup_commit_charge(page, memcg, false); + page_add_new_anon_rmap(page, vma, addr, false); lru_cache_add_active_or_unevictable(page, vma); } swap_free(entry); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index bb57d0a3fca7..3dea268d2850 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -123,8 +123,8 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, goto out_release_uncharge_unlock; inc_mm_counter(dst_mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, dst_vma, dst_addr, false); mem_cgroup_commit_charge(page, memcg, false); + page_add_new_anon_rmap(page, dst_vma, dst_addr, false); lru_cache_add_active_or_unevictable(page, dst_vma); set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); -- cgit v1.2.3-59-g8ed1b From 9d82c69438d0dff8809061edbcce43a5a4bcf09f Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:04 -0700 Subject: mm: memcontrol: convert anon and file-thp to new mem_cgroup_charge() API With the page->mapping requirement gone from memcg, we can charge anon and file-thp pages in one single step, right after they're allocated. This removes two out of three API calls - especially the tricky commit step that needed to happen at just the right time between when the page is "set up" and when it's "published" - somewhat vague and fluid concepts that varied by page type. All we need is a freshly allocated page and a memcg context to charge. v2: prevent double charges on pre-allocated hugepages in khugepaged [hannes@cmpxchg.org: Fix crash - *hpage could be ERR_PTR instead of NULL] Link: http://lkml.kernel.org/r/20200512215813.GA487759@cmpxchg.org Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Joonsoo Kim Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Cc: Qian Cai Link: http://lkml.kernel.org/r/20200508183105.225460-13-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 +--- kernel/events/uprobes.c | 11 +++-------- mm/filemap.c | 2 +- mm/huge_memory.c | 9 +++------ mm/khugepaged.c | 35 ++++++++++------------------------- mm/memory.c | 36 ++++++++++-------------------------- mm/migrate.c | 5 +---- mm/swapfile.c | 6 +----- mm/userfaultfd.c | 5 +---- 9 files changed, 31 insertions(+), 82 deletions(-) (limited to 'kernel') diff --git a/include/linux/mm.h b/include/linux/mm.h index ff73187c3fd4..4ef044fa09fa 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -501,7 +501,6 @@ struct vm_fault { pte_t orig_pte; /* Value of PTE at the time of fault */ struct page *cow_page; /* Page handler may use for COW fault */ - struct mem_cgroup *memcg; /* Cgroup cow_page belongs to */ struct page *page; /* ->fault handlers should return a * page here, unless VM_FAULT_NOPAGE * is set (which is also implied by @@ -946,8 +945,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) return pte; } -vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, - struct page *page); +vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page); vm_fault_t finish_fault(struct vm_fault *vmf); vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf); #endif diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 89ef81b65bcb..4253c153e985 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -162,14 +162,13 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, }; int err; struct mmu_notifier_range range; - struct mem_cgroup *memcg; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, addr, addr + PAGE_SIZE); if (new_page) { - err = mem_cgroup_try_charge(new_page, vma->vm_mm, GFP_KERNEL, - &memcg); + err = mem_cgroup_charge(new_page, vma->vm_mm, GFP_KERNEL, + false); if (err) return err; } @@ -179,16 +178,12 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, mmu_notifier_invalidate_range_start(&range); err = -EAGAIN; - if (!page_vma_mapped_walk(&pvmw)) { - if (new_page) - mem_cgroup_cancel_charge(new_page, memcg); + if (!page_vma_mapped_walk(&pvmw)) goto unlock; - } VM_BUG_ON_PAGE(addr != pvmw.address, old_page); if (new_page) { get_page(new_page); - mem_cgroup_commit_charge(new_page, memcg, false); page_add_new_anon_rmap(new_page, vma, addr, false); lru_cache_add_active_or_unevictable(new_page, vma); } else diff --git a/mm/filemap.c b/mm/filemap.c index a6565890cdf0..f08b0ca34e31 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2633,7 +2633,7 @@ void filemap_map_pages(struct vm_fault *vmf, if (vmf->pte) vmf->pte += xas.xa_index - last_pgoff; last_pgoff = xas.xa_index; - if (alloc_set_pte(vmf, NULL, page)) + if (alloc_set_pte(vmf, page)) goto unlock; unlock_page(page); goto next; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 1fe980dafe03..e9201a88157e 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -587,19 +587,19 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page, gfp_t gfp) { struct vm_area_struct *vma = vmf->vma; - struct mem_cgroup *memcg; pgtable_t pgtable; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; vm_fault_t ret = 0; VM_BUG_ON_PAGE(!PageCompound(page), page); - if (mem_cgroup_try_charge_delay(page, vma->vm_mm, gfp, &memcg)) { + if (mem_cgroup_charge(page, vma->vm_mm, gfp, false)) { put_page(page); count_vm_event(THP_FAULT_FALLBACK); count_vm_event(THP_FAULT_FALLBACK_CHARGE); return VM_FAULT_FALLBACK; } + cgroup_throttle_swaprate(page, gfp); pgtable = pte_alloc_one(vma->vm_mm); if (unlikely(!pgtable)) { @@ -630,7 +630,6 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, vm_fault_t ret2; spin_unlock(vmf->ptl); - mem_cgroup_cancel_charge(page, memcg); put_page(page); pte_free(vma->vm_mm, pgtable); ret2 = handle_userfault(vmf, VM_UFFD_MISSING); @@ -640,7 +639,6 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, entry = mk_huge_pmd(page, vma->vm_page_prot); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); - mem_cgroup_commit_charge(page, memcg, false); page_add_new_anon_rmap(page, vma, haddr, true); lru_cache_add_active_or_unevictable(page, vma); pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable); @@ -649,7 +647,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, mm_inc_nr_ptes(vma->vm_mm); spin_unlock(vmf->ptl); count_vm_event(THP_FAULT_ALLOC); - count_memcg_events(memcg, THP_FAULT_ALLOC, 1); + count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC); } return 0; @@ -658,7 +656,6 @@ unlock_release: release: if (pgtable) pte_free(vma->vm_mm, pgtable); - mem_cgroup_cancel_charge(page, memcg); put_page(page); return ret; diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 34eff4dfae80..32c85b81837a 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1037,7 +1037,6 @@ static void collapse_huge_page(struct mm_struct *mm, struct page *new_page; spinlock_t *pmd_ptl, *pte_ptl; int isolated = 0, result = 0; - struct mem_cgroup *memcg; struct vm_area_struct *vma; struct mmu_notifier_range range; gfp_t gfp; @@ -1060,15 +1059,15 @@ static void collapse_huge_page(struct mm_struct *mm, goto out_nolock; } - if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg))) { + if (unlikely(mem_cgroup_charge(new_page, mm, gfp, false))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out_nolock; } + count_memcg_page_event(new_page, THP_COLLAPSE_ALLOC); down_read(&mm->mmap_sem); result = hugepage_vma_revalidate(mm, address, &vma); if (result) { - mem_cgroup_cancel_charge(new_page, memcg); up_read(&mm->mmap_sem); goto out_nolock; } @@ -1076,7 +1075,6 @@ static void collapse_huge_page(struct mm_struct *mm, pmd = mm_find_pmd(mm, address); if (!pmd) { result = SCAN_PMD_NULL; - mem_cgroup_cancel_charge(new_page, memcg); up_read(&mm->mmap_sem); goto out_nolock; } @@ -1088,7 +1086,6 @@ static void collapse_huge_page(struct mm_struct *mm, */ if (unmapped && !__collapse_huge_page_swapin(mm, vma, address, pmd, referenced)) { - mem_cgroup_cancel_charge(new_page, memcg); up_read(&mm->mmap_sem); goto out_nolock; } @@ -1175,9 +1172,7 @@ static void collapse_huge_page(struct mm_struct *mm, spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); - mem_cgroup_commit_charge(new_page, memcg, false); page_add_new_anon_rmap(new_page, vma, address, true); - count_memcg_events(memcg, THP_COLLAPSE_ALLOC, 1); lru_cache_add_active_or_unevictable(new_page, vma); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, address, pmd, _pmd); @@ -1191,10 +1186,11 @@ static void collapse_huge_page(struct mm_struct *mm, out_up_write: up_write(&mm->mmap_sem); out_nolock: + if (!IS_ERR_OR_NULL(*hpage)) + mem_cgroup_uncharge(*hpage); trace_mm_collapse_huge_page(mm, isolated, result); return; out: - mem_cgroup_cancel_charge(new_page, memcg); goto out_up_write; } @@ -1618,7 +1614,6 @@ static void collapse_file(struct mm_struct *mm, struct address_space *mapping = file->f_mapping; gfp_t gfp; struct page *new_page; - struct mem_cgroup *memcg; pgoff_t index, end = start + HPAGE_PMD_NR; LIST_HEAD(pagelist); XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER); @@ -1637,10 +1632,11 @@ static void collapse_file(struct mm_struct *mm, goto out; } - if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg))) { + if (unlikely(mem_cgroup_charge(new_page, mm, gfp, false))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out; } + count_memcg_page_event(new_page, THP_COLLAPSE_ALLOC); /* This will be less messy when we use multi-index entries */ do { @@ -1650,7 +1646,6 @@ static void collapse_file(struct mm_struct *mm, break; xas_unlock_irq(&xas); if (!xas_nomem(&xas, GFP_KERNEL)) { - mem_cgroup_cancel_charge(new_page, memcg); result = SCAN_FAIL; goto out; } @@ -1844,18 +1839,9 @@ out_unlock: } if (nr_none) { - struct lruvec *lruvec; - /* - * XXX: We have started try_charge and pinned the - * memcg, but the page isn't committed yet so we - * cannot use mod_lruvec_page_state(). This hackery - * will be cleaned up when remove the page->mapping - * dependency from memcg and fully charge above. - */ - lruvec = mem_cgroup_lruvec(memcg, page_pgdat(new_page)); - __mod_lruvec_state(lruvec, NR_FILE_PAGES, nr_none); + __mod_lruvec_page_state(new_page, NR_FILE_PAGES, nr_none); if (is_shmem) - __mod_lruvec_state(lruvec, NR_SHMEM, nr_none); + __mod_lruvec_page_state(new_page, NR_SHMEM, nr_none); } xa_locked: @@ -1893,7 +1879,6 @@ xa_unlocked: SetPageUptodate(new_page); page_ref_add(new_page, HPAGE_PMD_NR - 1); - mem_cgroup_commit_charge(new_page, memcg, false); if (is_shmem) { set_page_dirty(new_page); @@ -1901,7 +1886,6 @@ xa_unlocked: } else { lru_cache_add_file(new_page); } - count_memcg_events(memcg, THP_COLLAPSE_ALLOC, 1); /* * Remove pte page tables, so we can re-fault the page as huge. @@ -1948,13 +1932,14 @@ xa_unlocked: VM_BUG_ON(nr_none); xas_unlock_irq(&xas); - mem_cgroup_cancel_charge(new_page, memcg); new_page->mapping = NULL; } unlock_page(new_page); out: VM_BUG_ON(!list_empty(&pagelist)); + if (!IS_ERR_OR_NULL(*hpage)) + mem_cgroup_uncharge(*hpage); /* TODO: tracepoints */ } diff --git a/mm/memory.c b/mm/memory.c index 543e41b1d57a..27e225bef5d0 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2645,7 +2645,6 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) struct page *new_page = NULL; pte_t entry; int page_copied = 0; - struct mem_cgroup *memcg; struct mmu_notifier_range range; if (unlikely(anon_vma_prepare(vma))) @@ -2676,8 +2675,9 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) } } - if (mem_cgroup_try_charge_delay(new_page, mm, GFP_KERNEL, &memcg)) + if (mem_cgroup_charge(new_page, mm, GFP_KERNEL, false)) goto oom_free_new; + cgroup_throttle_swaprate(new_page, GFP_KERNEL); __SetPageUptodate(new_page); @@ -2710,7 +2710,6 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) * thread doing COW. */ ptep_clear_flush_notify(vma, vmf->address, vmf->pte); - mem_cgroup_commit_charge(new_page, memcg, false); page_add_new_anon_rmap(new_page, vma, vmf->address, false); lru_cache_add_active_or_unevictable(new_page, vma); /* @@ -2749,8 +2748,6 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) /* Free the old page.. */ new_page = old_page; page_copied = 1; - } else { - mem_cgroup_cancel_charge(new_page, memcg); } if (new_page) @@ -3088,7 +3085,6 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page = NULL, *swapcache; - struct mem_cgroup *memcg; swp_entry_t entry; pte_t pte; int locked; @@ -3193,10 +3189,11 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) goto out_page; } - if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, &memcg)) { + if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL, true)) { ret = VM_FAULT_OOM; goto out_page; } + cgroup_throttle_swaprate(page, GFP_KERNEL); /* * Back out if somebody else already faulted in this pte. @@ -3243,11 +3240,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) /* ksm created a completely new copy */ if (unlikely(page != swapcache && swapcache)) { - mem_cgroup_commit_charge(page, memcg, false); page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_active_or_unevictable(page, vma); } else { - mem_cgroup_commit_charge(page, memcg, true); do_page_add_anon_rmap(page, vma, vmf->address, exclusive); activate_page(page); } @@ -3284,7 +3279,6 @@ unlock: out: return ret; out_nomap: - mem_cgroup_cancel_charge(page, memcg); pte_unmap_unlock(vmf->pte, vmf->ptl); out_page: unlock_page(page); @@ -3305,7 +3299,6 @@ out_release: static vm_fault_t do_anonymous_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; - struct mem_cgroup *memcg; struct page *page; vm_fault_t ret = 0; pte_t entry; @@ -3358,8 +3351,9 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) if (!page) goto oom; - if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, &memcg)) + if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL, false)) goto oom_free_page; + cgroup_throttle_swaprate(page, GFP_KERNEL); /* * The memory barrier inside __SetPageUptodate makes sure that @@ -3384,13 +3378,11 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); - mem_cgroup_cancel_charge(page, memcg); put_page(page); return handle_userfault(vmf, VM_UFFD_MISSING); } inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); - mem_cgroup_commit_charge(page, memcg, false); page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_active_or_unevictable(page, vma); setpte: @@ -3402,7 +3394,6 @@ unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; release: - mem_cgroup_cancel_charge(page, memcg); put_page(page); goto unlock; oom_free_page: @@ -3607,7 +3598,6 @@ static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) * mapping. If needed, the fucntion allocates page table or use pre-allocated. * * @vmf: fault environment - * @memcg: memcg to charge page (only for private mappings) * @page: page to map * * Caller must take care of unlocking vmf->ptl, if vmf->pte is non-NULL on @@ -3618,8 +3608,7 @@ static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) * * Return: %0 on success, %VM_FAULT_ code in case of error. */ -vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, - struct page *page) +vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page) { struct vm_area_struct *vma = vmf->vma; bool write = vmf->flags & FAULT_FLAG_WRITE; @@ -3627,9 +3616,6 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, vm_fault_t ret; if (pmd_none(*vmf->pmd) && PageTransCompound(page)) { - /* THP on COW? */ - VM_BUG_ON_PAGE(memcg, page); - ret = do_set_pmd(vmf, page); if (ret != VM_FAULT_FALLBACK) return ret; @@ -3652,7 +3638,6 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, /* copy-on-write page */ if (write && !(vma->vm_flags & VM_SHARED)) { inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); - mem_cgroup_commit_charge(page, memcg, false); page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_active_or_unevictable(page, vma); } else { @@ -3702,7 +3687,7 @@ vm_fault_t finish_fault(struct vm_fault *vmf) if (!(vmf->vma->vm_flags & VM_SHARED)) ret = check_stable_address_space(vmf->vma->vm_mm); if (!ret) - ret = alloc_set_pte(vmf, vmf->memcg, page); + ret = alloc_set_pte(vmf, page); if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; @@ -3862,11 +3847,11 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf) if (!vmf->cow_page) return VM_FAULT_OOM; - if (mem_cgroup_try_charge_delay(vmf->cow_page, vma->vm_mm, - GFP_KERNEL, &vmf->memcg)) { + if (mem_cgroup_charge(vmf->cow_page, vma->vm_mm, GFP_KERNEL, false)) { put_page(vmf->cow_page); return VM_FAULT_OOM; } + cgroup_throttle_swaprate(vmf->cow_page, GFP_KERNEL); ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) @@ -3884,7 +3869,6 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf) goto uncharge_out; return ret; uncharge_out: - mem_cgroup_cancel_charge(vmf->cow_page, vmf->memcg); put_page(vmf->cow_page); return ret; } diff --git a/mm/migrate.c b/mm/migrate.c index e72ed681634f..44cee40221ec 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2740,7 +2740,6 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, { struct vm_area_struct *vma = migrate->vma; struct mm_struct *mm = vma->vm_mm; - struct mem_cgroup *memcg; bool flush = false; spinlock_t *ptl; pte_t entry; @@ -2787,7 +2786,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, if (unlikely(anon_vma_prepare(vma))) goto abort; - if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, &memcg)) + if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL, false)) goto abort; /* @@ -2832,7 +2831,6 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, goto unlock_abort; inc_mm_counter(mm, MM_ANONPAGES); - mem_cgroup_commit_charge(page, memcg, false); page_add_new_anon_rmap(page, vma, addr, false); if (!is_zone_device_page(page)) lru_cache_add_active_or_unevictable(page, vma); @@ -2855,7 +2853,6 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, unlock_abort: pte_unmap_unlock(ptep, ptl); - mem_cgroup_cancel_charge(page, memcg); abort: *src &= ~MIGRATE_PFN_MIGRATE; } diff --git a/mm/swapfile.c b/mm/swapfile.c index 01f6538bad2d..720e9a924c01 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1892,7 +1892,6 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, swp_entry_t entry, struct page *page) { struct page *swapcache; - struct mem_cgroup *memcg; spinlock_t *ptl; pte_t *pte; int ret = 1; @@ -1902,14 +1901,13 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, if (unlikely(!page)) return -ENOMEM; - if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, &memcg)) { + if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL, true)) { ret = -ENOMEM; goto out_nolock; } pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (unlikely(!pte_same_as_swp(*pte, swp_entry_to_pte(entry)))) { - mem_cgroup_cancel_charge(page, memcg); ret = 0; goto out; } @@ -1920,10 +1918,8 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, set_pte_at(vma->vm_mm, addr, pte, pte_mkold(mk_pte(page, vma->vm_page_prot))); if (page == swapcache) { - mem_cgroup_commit_charge(page, memcg, true); page_add_anon_rmap(page, vma, addr, false); } else { /* ksm created a completely new copy */ - mem_cgroup_commit_charge(page, memcg, false); page_add_new_anon_rmap(page, vma, addr, false); lru_cache_add_active_or_unevictable(page, vma); } diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 3dea268d2850..2745489415cc 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -56,7 +56,6 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, struct page **pagep, bool wp_copy) { - struct mem_cgroup *memcg; pte_t _dst_pte, *dst_pte; spinlock_t *ptl; void *page_kaddr; @@ -97,7 +96,7 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, __SetPageUptodate(page); ret = -ENOMEM; - if (mem_cgroup_try_charge(page, dst_mm, GFP_KERNEL, &memcg)) + if (mem_cgroup_charge(page, dst_mm, GFP_KERNEL, false)) goto out_release; _dst_pte = pte_mkdirty(mk_pte(page, dst_vma->vm_page_prot)); @@ -123,7 +122,6 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, goto out_release_uncharge_unlock; inc_mm_counter(dst_mm, MM_ANONPAGES); - mem_cgroup_commit_charge(page, memcg, false); page_add_new_anon_rmap(page, dst_vma, dst_addr, false); lru_cache_add_active_or_unevictable(page, dst_vma); @@ -138,7 +136,6 @@ out: return ret; out_release_uncharge_unlock: pte_unmap_unlock(dst_pte, ptl); - mem_cgroup_cancel_charge(page, memcg); out_release: put_page(page); goto out; -- cgit v1.2.3-59-g8ed1b From d9eb1ea2bf8734afd8ec7d995270437a7242f82b Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:24 -0700 Subject: mm: memcontrol: delete unused lrucare handling Swapin faults were the last event to charge pages after they had already been put on the LRU list. Now that we charge directly on swapin, the lrucare portion of the charge code is unused. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Joonsoo Kim Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Balbir Singh Cc: Shakeel Butt Link: http://lkml.kernel.org/r/20200508183105.225460-19-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 5 ++-- kernel/events/uprobes.c | 3 +-- mm/filemap.c | 2 +- mm/huge_memory.c | 2 +- mm/khugepaged.c | 4 ++-- mm/memcontrol.c | 57 ++++------------------------------------------ mm/memory.c | 8 +++---- mm/migrate.c | 2 +- mm/shmem.c | 2 +- mm/swap_state.c | 2 +- mm/userfaultfd.c | 2 +- 11 files changed, 19 insertions(+), 70 deletions(-) (limited to 'kernel') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 96257f995caa..d5bf3b5bfe6d 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -355,8 +355,7 @@ static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg, enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, struct mem_cgroup *memcg); -int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, - bool lrucare); +int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask); void mem_cgroup_uncharge(struct page *page); void mem_cgroup_uncharge_list(struct list_head *page_list); @@ -839,7 +838,7 @@ static inline enum mem_cgroup_protection mem_cgroup_protected( } static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, bool lrucare) + gfp_t gfp_mask) { return 0; } diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 4253c153e985..eddc8db96027 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -167,8 +167,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, addr + PAGE_SIZE); if (new_page) { - err = mem_cgroup_charge(new_page, vma->vm_mm, GFP_KERNEL, - false); + err = mem_cgroup_charge(new_page, vma->vm_mm, GFP_KERNEL); if (err) return err; } diff --git a/mm/filemap.c b/mm/filemap.c index f08b0ca34e31..455990621989 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -845,7 +845,7 @@ static int __add_to_page_cache_locked(struct page *page, page->index = offset; if (!huge) { - error = mem_cgroup_charge(page, current->mm, gfp_mask, false); + error = mem_cgroup_charge(page, current->mm, gfp_mask); if (error) goto error; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index e9201a88157e..6df182a18d2c 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -593,7 +593,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, VM_BUG_ON_PAGE(!PageCompound(page), page); - if (mem_cgroup_charge(page, vma->vm_mm, gfp, false)) { + if (mem_cgroup_charge(page, vma->vm_mm, gfp)) { put_page(page); count_vm_event(THP_FAULT_FALLBACK); count_vm_event(THP_FAULT_FALLBACK_CHARGE); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 32c85b81837a..f29038c485e0 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1059,7 +1059,7 @@ static void collapse_huge_page(struct mm_struct *mm, goto out_nolock; } - if (unlikely(mem_cgroup_charge(new_page, mm, gfp, false))) { + if (unlikely(mem_cgroup_charge(new_page, mm, gfp))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out_nolock; } @@ -1632,7 +1632,7 @@ static void collapse_file(struct mm_struct *mm, goto out; } - if (unlikely(mem_cgroup_charge(new_page, mm, gfp, false))) { + if (unlikely(mem_cgroup_charge(new_page, mm, gfp))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 425a265dc2a0..316a84025090 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2655,51 +2655,9 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) } #endif -static void lock_page_lru(struct page *page, int *isolated) +static void commit_charge(struct page *page, struct mem_cgroup *memcg) { - pg_data_t *pgdat = page_pgdat(page); - - spin_lock_irq(&pgdat->lru_lock); - if (PageLRU(page)) { - struct lruvec *lruvec; - - lruvec = mem_cgroup_page_lruvec(page, pgdat); - ClearPageLRU(page); - del_page_from_lru_list(page, lruvec, page_lru(page)); - *isolated = 1; - } else - *isolated = 0; -} - -static void unlock_page_lru(struct page *page, int isolated) -{ - pg_data_t *pgdat = page_pgdat(page); - - if (isolated) { - struct lruvec *lruvec; - - lruvec = mem_cgroup_page_lruvec(page, pgdat); - VM_BUG_ON_PAGE(PageLRU(page), page); - SetPageLRU(page); - add_page_to_lru_list(page, lruvec, page_lru(page)); - } - spin_unlock_irq(&pgdat->lru_lock); -} - -static void commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare) -{ - int isolated; - VM_BUG_ON_PAGE(page->mem_cgroup, page); - - /* - * In some cases, SwapCache and FUSE(splice_buf->radixtree), the page - * may already be on some other mem_cgroup's LRU. Take care of it. - */ - if (lrucare) - lock_page_lru(page, &isolated); - /* * Nobody should be changing or seriously looking at * page->mem_cgroup at this point: @@ -2715,9 +2673,6 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg, * have the page locked */ page->mem_cgroup = memcg; - - if (lrucare) - unlock_page_lru(page, isolated); } #ifdef CONFIG_MEMCG_KMEM @@ -6503,22 +6458,18 @@ out: * @page: page to charge * @mm: mm context of the victim * @gfp_mask: reclaim mode - * @lrucare: page might be on the LRU already * * Try to charge @page to the memcg that @mm belongs to, reclaiming * pages according to @gfp_mask if necessary. * * Returns 0 on success. Otherwise, an error code is returned. */ -int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, - bool lrucare) +int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) { unsigned int nr_pages = hpage_nr_pages(page); struct mem_cgroup *memcg = NULL; int ret = 0; - VM_BUG_ON_PAGE(PageLRU(page) && !lrucare, page); - if (mem_cgroup_disabled()) goto out; @@ -6552,7 +6503,7 @@ int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, if (ret) goto out_put; - commit_charge(page, memcg, lrucare); + commit_charge(page, memcg); local_irq_disable(); mem_cgroup_charge_statistics(memcg, page, nr_pages); @@ -6753,7 +6704,7 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) page_counter_charge(&memcg->memsw, nr_pages); css_get_many(&memcg->css, nr_pages); - commit_charge(newpage, memcg, false); + commit_charge(newpage, memcg); local_irq_save(flags); mem_cgroup_charge_statistics(memcg, newpage, nr_pages); diff --git a/mm/memory.c b/mm/memory.c index 9c886e4207a2..d50d8b498af5 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2675,7 +2675,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) } } - if (mem_cgroup_charge(new_page, mm, GFP_KERNEL, false)) + if (mem_cgroup_charge(new_page, mm, GFP_KERNEL)) goto oom_free_new; cgroup_throttle_swaprate(new_page, GFP_KERNEL); @@ -3134,7 +3134,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) /* Tell memcg to use swap ownership records */ SetPageSwapCache(page); err = mem_cgroup_charge(page, vma->vm_mm, - GFP_KERNEL, false); + GFP_KERNEL); ClearPageSwapCache(page); if (err) goto out_page; @@ -3358,7 +3358,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) if (!page) goto oom; - if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL, false)) + if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL)) goto oom_free_page; cgroup_throttle_swaprate(page, GFP_KERNEL); @@ -3854,7 +3854,7 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf) if (!vmf->cow_page) return VM_FAULT_OOM; - if (mem_cgroup_charge(vmf->cow_page, vma->vm_mm, GFP_KERNEL, false)) { + if (mem_cgroup_charge(vmf->cow_page, vma->vm_mm, GFP_KERNEL)) { put_page(vmf->cow_page); return VM_FAULT_OOM; } diff --git a/mm/migrate.c b/mm/migrate.c index 44cee40221ec..7bfd0962149e 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2786,7 +2786,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, if (unlikely(anon_vma_prepare(vma))) goto abort; - if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL, false)) + if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL)) goto abort; /* diff --git a/mm/shmem.c b/mm/shmem.c index b79116185046..e83de27ce8f4 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -624,7 +624,7 @@ static int shmem_add_to_page_cache(struct page *page, page->index = index; if (!PageSwapCache(page)) { - error = mem_cgroup_charge(page, charge_mm, gfp, false); + error = mem_cgroup_charge(page, charge_mm, gfp); if (error) { if (PageTransHuge(page)) { count_vm_event(THP_FILE_FALLBACK); diff --git a/mm/swap_state.c b/mm/swap_state.c index f841257a3014..ab0462819a5b 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -435,7 +435,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, goto fail_unlock; } - if (mem_cgroup_charge(page, NULL, gfp_mask, false)) { + if (mem_cgroup_charge(page, NULL, gfp_mask)) { delete_from_swap_cache(page); goto fail_unlock; } diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 2745489415cc..7f5194046b01 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -96,7 +96,7 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, __SetPageUptodate(page); ret = -ENOMEM; - if (mem_cgroup_charge(page, dst_mm, GFP_KERNEL, false)) + if (mem_cgroup_charge(page, dst_mm, GFP_KERNEL)) goto out_release; _dst_pte = pte_mkdirty(mk_pte(page, dst_vma->vm_page_prot)); -- cgit v1.2.3-59-g8ed1b From c843966c556d7370bb32e7319a6d164cb8c70ae2 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:37 -0700 Subject: mm: allow swappiness that prefers reclaiming anon over the file workingset With the advent of fast random IO devices (SSDs, PMEM) and in-memory swap devices such as zswap, it's possible for swap to be much faster than filesystems, and for swapping to be preferable over thrashing filesystem caches. Allow setting swappiness - which defines the rough relative IO cost of cache misses between page cache and swap-backed pages - to reflect such situations by making the swap-preferred range configurable. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Link: http://lkml.kernel.org/r/20200520232525.798933-4-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- Documentation/admin-guide/sysctl/vm.rst | 23 ++++++++++++++++++----- kernel/sysctl.c | 3 ++- mm/vmscan.c | 2 +- 3 files changed, 21 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst index 0329a4d3fa9e..d46d5b7013c6 100644 --- a/Documentation/admin-guide/sysctl/vm.rst +++ b/Documentation/admin-guide/sysctl/vm.rst @@ -831,14 +831,27 @@ tooling to work, you can do:: swappiness ========== -This control is used to define how aggressive the kernel will swap -memory pages. Higher values will increase aggressiveness, lower values -decrease the amount of swap. A value of 0 instructs the kernel not to -initiate swap until the amount of free and file-backed pages is less -than the high water mark in a zone. +This control is used to define the rough relative IO cost of swapping +and filesystem paging, as a value between 0 and 200. At 100, the VM +assumes equal IO cost and will thus apply memory pressure to the page +cache and swap-backed pages equally; lower values signify more +expensive swap IO, higher values indicates cheaper. + +Keep in mind that filesystem IO patterns under memory pressure tend to +be more efficient than swap's random IO. An optimal value will require +experimentation and will also be workload-dependent. The default value is 60. +For in-memory swap, like zram or zswap, as well as hybrid setups that +have swap on faster devices than the filesystem, values beyond 100 can +be considered. For example, if the random IO against the swap device +is on average 2x faster than IO from the filesystem, swappiness should +be 133 (x + 2x = 200, 2x = 133.33). + +At 0, the kernel will not initiate swap until the amount of free and +file-backed pages is less than the high watermark in a zone. + unprivileged_userfaultfd ======================== diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 8a176d8727a3..7f15d292e44c 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -131,6 +131,7 @@ static unsigned long zero_ul; static unsigned long one_ul = 1; static unsigned long long_max = LONG_MAX; static int one_hundred = 100; +static int two_hundred = 200; static int one_thousand = 1000; #ifdef CONFIG_PRINTK static int ten_thousand = 10000; @@ -1391,7 +1392,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = &one_hundred, + .extra2 = &two_hundred, }, #ifdef CONFIG_HUGETLB_PAGE { diff --git a/mm/vmscan.c b/mm/vmscan.c index 1fa2417f7c2a..c711efc42cfc 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -161,7 +161,7 @@ struct scan_control { #endif /* - * From 0 .. 100. Higher means more swappy. + * From 0 .. 200. Higher means more swappy. */ int vm_swappiness = 60; /* -- cgit v1.2.3-59-g8ed1b