From b4edb8d2d4647a71a246d91fe34ff25c2c5f3481 Mon Sep 17 00:00:00 2001 From: "wuqiang.matt" Date: Tue, 17 Oct 2023 21:56:50 +0800 Subject: lib: objpool added: ring-array based lockless MPMC objpool is a scalable implementation of high performance queue for object allocation and reclamation, such as kretprobe instances. With leveraging percpu ring-array to mitigate hot spots of memory contention, it delivers near-linear scalability for high parallel scenarios. The objpool is best suited for the following cases: 1) Memory allocation or reclamation are prohibited or too expensive 2) Consumers are of different priorities, such as irqs and threads Limitations: 1) Maximum objects (capacity) is fixed after objpool creation 2) All pre-allocated objects are managed in percpu ring array, which consumes more memory than linked lists Link: https://lore.kernel.org/all/20231017135654.82270-2-wuqiang.matt@bytedance.com/ Signed-off-by: wuqiang.matt Acked-by: Masami Hiramatsu (Google) Signed-off-by: Masami Hiramatsu (Google) --- include/linux/objpool.h | 181 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 181 insertions(+) create mode 100644 include/linux/objpool.h (limited to 'include') diff --git a/include/linux/objpool.h b/include/linux/objpool.h new file mode 100644 index 000000000000..15aff4a17f0c --- /dev/null +++ b/include/linux/objpool.h @@ -0,0 +1,181 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _LINUX_OBJPOOL_H +#define _LINUX_OBJPOOL_H + +#include +#include + +/* + * objpool: ring-array based lockless MPMC queue + * + * Copyright: wuqiang.matt@bytedance.com,mhiramat@kernel.org + * + * objpool is a scalable implementation of high performance queue for + * object allocation and reclamation, such as kretprobe instances. + * + * With leveraging percpu ring-array to mitigate hot spots of memory + * contention, it delivers near-linear scalability for high parallel + * scenarios. The objpool is best suited for the following cases: + * 1) Memory allocation or reclamation are prohibited or too expensive + * 2) Consumers are of different priorities, such as irqs and threads + * + * Limitations: + * 1) Maximum objects (capacity) is fixed after objpool creation + * 2) All pre-allocated objects are managed in percpu ring array, + * which consumes more memory than linked lists + */ + +/** + * struct objpool_slot - percpu ring array of objpool + * @head: head sequence of the local ring array (to retrieve at) + * @tail: tail sequence of the local ring array (to append at) + * @last: the last sequence number marked as ready for retrieve + * @mask: bits mask for modulo capacity to compute array indexes + * @entries: object entries on this slot + * + * Represents a cpu-local array-based ring buffer, its size is specialized + * during initialization of object pool. The percpu objpool node is to be + * allocated from local memory for NUMA system, and to be kept compact in + * continuous memory: CPU assigned number of objects are stored just after + * the body of objpool_node. + * + * Real size of the ring array is far too smaller than the value range of + * head and tail, typed as uint32_t: [0, 2^32), so only lower bits (mask) + * of head and tail are used as the actual position in the ring array. In + * general the ring array is acting like a small sliding window, which is + * always moving forward in the loop of [0, 2^32). + */ +struct objpool_slot { + uint32_t head; + uint32_t tail; + uint32_t last; + uint32_t mask; + void *entries[]; +} __packed; + +struct objpool_head; + +/* + * caller-specified callback for object initial setup, it's only called + * once for each object (just after the memory allocation of the object) + */ +typedef int (*objpool_init_obj_cb)(void *obj, void *context); + +/* caller-specified cleanup callback for objpool destruction */ +typedef int (*objpool_fini_cb)(struct objpool_head *head, void *context); + +/** + * struct objpool_head - object pooling metadata + * @obj_size: object size, aligned to sizeof(void *) + * @nr_objs: total objs (to be pre-allocated with objpool) + * @nr_cpus: local copy of nr_cpu_ids + * @capacity: max objs can be managed by one objpool_slot + * @gfp: gfp flags for kmalloc & vmalloc + * @ref: refcount of objpool + * @flags: flags for objpool management + * @cpu_slots: pointer to the array of objpool_slot + * @release: resource cleanup callback + * @context: caller-provided context + */ +struct objpool_head { + int obj_size; + int nr_objs; + int nr_cpus; + int capacity; + gfp_t gfp; + refcount_t ref; + unsigned long flags; + struct objpool_slot **cpu_slots; + objpool_fini_cb release; + void *context; +}; + +#define OBJPOOL_NR_OBJECT_MAX (1UL << 24) /* maximum numbers of total objects */ +#define OBJPOOL_OBJECT_SIZE_MAX (1UL << 16) /* maximum size of an object */ + +/** + * objpool_init() - initialize objpool and pre-allocated objects + * @pool: the object pool to be initialized, declared by caller + * @nr_objs: total objects to be pre-allocated by this object pool + * @object_size: size of an object (should be > 0) + * @gfp: flags for memory allocation (via kmalloc or vmalloc) + * @context: user context for object initialization callback + * @objinit: object initialization callback for extra setup + * @release: cleanup callback for extra cleanup task + * + * return value: 0 for success, otherwise error code + * + * All pre-allocated objects are to be zeroed after memory allocation. + * Caller could do extra initialization in objinit callback. objinit() + * will be called just after slot allocation and called only once for + * each object. After that the objpool won't touch any content of the + * objects. It's caller's duty to perform reinitialization after each + * pop (object allocation) or do clearance before each push (object + * reclamation). + */ +int objpool_init(struct objpool_head *pool, int nr_objs, int object_size, + gfp_t gfp, void *context, objpool_init_obj_cb objinit, + objpool_fini_cb release); + +/** + * objpool_pop() - allocate an object from objpool + * @pool: object pool + * + * return value: object ptr or NULL if failed + */ +void *objpool_pop(struct objpool_head *pool); + +/** + * objpool_push() - reclaim the object and return back to objpool + * @obj: object ptr to be pushed to objpool + * @pool: object pool + * + * return: 0 or error code (it fails only when user tries to push + * the same object multiple times or wrong "objects" into objpool) + */ +int objpool_push(void *obj, struct objpool_head *pool); + +/** + * objpool_drop() - discard the object and deref objpool + * @obj: object ptr to be discarded + * @pool: object pool + * + * return: 0 if objpool was released; -EAGAIN if there are still + * outstanding objects + * + * objpool_drop is normally for the release of outstanding objects + * after objpool cleanup (objpool_fini). Thinking of this example: + * kretprobe is unregistered and objpool_fini() is called to release + * all remained objects, but there are still objects being used by + * unfinished kretprobes (like blockable function: sys_accept). So + * only when the last outstanding object is dropped could the whole + * objpool be released along with the call of objpool_drop() + */ +int objpool_drop(void *obj, struct objpool_head *pool); + +/** + * objpool_free() - release objpool forcely (all objects to be freed) + * @pool: object pool to be released + */ +void objpool_free(struct objpool_head *pool); + +/** + * objpool_fini() - deref object pool (also releasing unused objects) + * @pool: object pool to be dereferenced + * + * objpool_fini() will try to release all remained free objects and + * then drop an extra reference of the objpool. If all objects are + * already returned to objpool (so called synchronous use cases), + * the objpool itself will be freed together. But if there are still + * outstanding objects (so called asynchronous use cases, such like + * blockable kretprobe), the objpool won't be released until all + * the outstanding objects are dropped, but the caller must assure + * there are no concurrent objpool_push() on the fly. Normally RCU + * is being required to make sure all ongoing objpool_push() must + * be finished before calling objpool_fini(), so does test_objpool, + * kretprobe or rethook + */ +void objpool_fini(struct objpool_head *pool); + +#endif /* _LINUX_OBJPOOL_H */ -- cgit v1.2.3 From 4bbd9345565933823f38a419df65661f12adbe5e Mon Sep 17 00:00:00 2001 From: "wuqiang.matt" Date: Tue, 17 Oct 2023 21:56:52 +0800 Subject: kprobes: kretprobe scalability improvement kretprobe is using freelist to manage return-instances, but freelist, as LIFO queue based on singly linked list, scales badly and reduces the overall throughput of kretprobed routines, especially for high contention scenarios. Here's a typical throughput test of sys_prctl (counts in 10 seconds, measured with perf stat -a -I 10000 -e syscalls:sys_enter_prctl): OS: Debian 10 X86_64, Linux 6.5rc7 with freelist HW: XEON 8336C x 2, 64 cores/128 threads, DDR4 3200MT/s 1T 2T 4T 8T 16T 24T 24150045 29317964 15446741 12494489 18287272 17708768 32T 48T 64T 72T 96T 128T 16200682 13737658 11645677 11269858 10470118 9931051 This patch introduces objpool to replace freelist. objpool is a high performance queue, which can bring near-linear scalability to kretprobed routines. Tests of kretprobe throughput show the biggest ratio as 159x of original freelist. Here's the result: 1T 2T 4T 8T 16T native: 41186213 82336866 164250978 328662645 658810299 freelist: 24150045 29317964 15446741 12494489 18287272 objpool: 23926730 48010314 96125218 191782984 385091769 32T 48T 64T 96T 128T native: 1330338351 1969957941 2512291791 2615754135 2671040914 freelist: 16200682 13737658 11645677 10470118 9931051 objpool: 764481096 1147149781 1456220214 1502109662 1579015050 Testings on 96-core ARM64 output similarly, but with the biggest ratio up to 448x: OS: Debian 10 AARCH64, Linux 6.5rc7 HW: Kunpeng-920 96 cores/2 sockets/4 NUMA nodes, DDR4 2933 MT/s 1T 2T 4T 8T 16T native: . 30066096 63569843 126194076 257447289 505800181 freelist: 16152090 11064397 11124068 7215768 5663013 objpool: 13997541 28032100 55726624 110099926 221498787 24T 32T 48T 64T 96T native: 763305277 1015925192 1521075123 2033009392 3021013752 freelist: 5015810 4602893 3766792 3382478 2945292 objpool: 328192025 439439564 668534502 887401381 1319972072 Link: https://lore.kernel.org/all/20231017135654.82270-4-wuqiang.matt@bytedance.com/ Signed-off-by: wuqiang.matt Acked-by: Masami Hiramatsu (Google) Signed-off-by: Masami Hiramatsu (Google) --- include/linux/kprobes.h | 11 ++---- include/linux/rethook.h | 16 +++------ kernel/kprobes.c | 91 +++++++++++++++++++++---------------------------- kernel/trace/fprobe.c | 28 ++++++--------- kernel/trace/rethook.c | 90 ++++++++++++++++++++++-------------------------- 5 files changed, 96 insertions(+), 140 deletions(-) (limited to 'include') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 85a64cb95d75..365eb092e9c4 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -26,8 +26,7 @@ #include #include #include -#include -#include +#include #include #include @@ -141,7 +140,7 @@ static inline bool kprobe_ftrace(struct kprobe *p) */ struct kretprobe_holder { struct kretprobe *rp; - refcount_t ref; + struct objpool_head pool; }; struct kretprobe { @@ -154,7 +153,6 @@ struct kretprobe { #ifdef CONFIG_KRETPROBE_ON_RETHOOK struct rethook *rh; #else - struct freelist_head freelist; struct kretprobe_holder *rph; #endif }; @@ -165,10 +163,7 @@ struct kretprobe_instance { #ifdef CONFIG_KRETPROBE_ON_RETHOOK struct rethook_node node; #else - union { - struct freelist_node freelist; - struct rcu_head rcu; - }; + struct rcu_head rcu; struct llist_node llist; struct kretprobe_holder *rph; kprobe_opcode_t *ret_addr; diff --git a/include/linux/rethook.h b/include/linux/rethook.h index 26b6f3c81a76..ce69b2b7bc35 100644 --- a/include/linux/rethook.h +++ b/include/linux/rethook.h @@ -6,11 +6,10 @@ #define _LINUX_RETHOOK_H #include -#include +#include #include #include #include -#include struct rethook_node; @@ -30,14 +29,12 @@ typedef void (*rethook_handler_t) (struct rethook_node *, void *, unsigned long, struct rethook { void *data; rethook_handler_t handler; - struct freelist_head pool; - refcount_t ref; + struct objpool_head pool; struct rcu_head rcu; }; /** * struct rethook_node - The rethook shadow-stack entry node. - * @freelist: The freelist, linked to struct rethook::pool. * @rcu: The rcu_head for deferred freeing. * @llist: The llist, linked to a struct task_struct::rethooks. * @rethook: The pointer to the struct rethook. @@ -48,20 +45,16 @@ struct rethook { * on each entry of the shadow stack. */ struct rethook_node { - union { - struct freelist_node freelist; - struct rcu_head rcu; - }; + struct rcu_head rcu; struct llist_node llist; struct rethook *rethook; unsigned long ret_addr; unsigned long frame; }; -struct rethook *rethook_alloc(void *data, rethook_handler_t handler); +struct rethook *rethook_alloc(void *data, rethook_handler_t handler, int size, int num); void rethook_stop(struct rethook *rh); void rethook_free(struct rethook *rh); -void rethook_add_node(struct rethook *rh, struct rethook_node *node); struct rethook_node *rethook_try_get(struct rethook *rh); void rethook_recycle(struct rethook_node *node); void rethook_hook(struct rethook_node *node, struct pt_regs *regs, bool mcount); @@ -98,4 +91,3 @@ void rethook_flush_task(struct task_struct *tk); #endif #endif - diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 0c6185aefaef..075a632e6c7c 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1877,13 +1877,27 @@ static struct notifier_block kprobe_exceptions_nb = { #ifdef CONFIG_KRETPROBES #if !defined(CONFIG_KRETPROBE_ON_RETHOOK) + +/* callbacks for objpool of kretprobe instances */ +static int kretprobe_init_inst(void *nod, void *context) +{ + struct kretprobe_instance *ri = nod; + + ri->rph = context; + return 0; +} +static int kretprobe_fini_pool(struct objpool_head *head, void *context) +{ + kfree(context); + return 0; +} + static void free_rp_inst_rcu(struct rcu_head *head) { struct kretprobe_instance *ri = container_of(head, struct kretprobe_instance, rcu); + struct kretprobe_holder *rph = ri->rph; - if (refcount_dec_and_test(&ri->rph->ref)) - kfree(ri->rph); - kfree(ri); + objpool_drop(ri, &rph->pool); } NOKPROBE_SYMBOL(free_rp_inst_rcu); @@ -1892,7 +1906,7 @@ static void recycle_rp_inst(struct kretprobe_instance *ri) struct kretprobe *rp = get_kretprobe(ri); if (likely(rp)) - freelist_add(&ri->freelist, &rp->freelist); + objpool_push(ri, &rp->rph->pool); else call_rcu(&ri->rcu, free_rp_inst_rcu); } @@ -1929,23 +1943,12 @@ NOKPROBE_SYMBOL(kprobe_flush_task); static inline void free_rp_inst(struct kretprobe *rp) { - struct kretprobe_instance *ri; - struct freelist_node *node; - int count = 0; - - node = rp->freelist.head; - while (node) { - ri = container_of(node, struct kretprobe_instance, freelist); - node = node->next; - - kfree(ri); - count++; - } + struct kretprobe_holder *rph = rp->rph; - if (refcount_sub_and_test(count, &rp->rph->ref)) { - kfree(rp->rph); - rp->rph = NULL; - } + if (!rph) + return; + rp->rph = NULL; + objpool_fini(&rph->pool); } /* This assumes the 'tsk' is the current task or the is not running. */ @@ -2087,19 +2090,17 @@ NOKPROBE_SYMBOL(__kretprobe_trampoline_handler) static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs) { struct kretprobe *rp = container_of(p, struct kretprobe, kp); + struct kretprobe_holder *rph = rp->rph; struct kretprobe_instance *ri; - struct freelist_node *fn; - fn = freelist_try_get(&rp->freelist); - if (!fn) { + ri = objpool_pop(&rph->pool); + if (!ri) { rp->nmissed++; return 0; } - ri = container_of(fn, struct kretprobe_instance, freelist); - if (rp->entry_handler && rp->entry_handler(ri, regs)) { - freelist_add(&ri->freelist, &rp->freelist); + objpool_push(ri, &rph->pool); return 0; } @@ -2193,7 +2194,6 @@ int kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long o int register_kretprobe(struct kretprobe *rp) { int ret; - struct kretprobe_instance *inst; int i; void *addr; @@ -2227,19 +2227,12 @@ int register_kretprobe(struct kretprobe *rp) rp->maxactive = max_t(unsigned int, 10, 2*num_possible_cpus()); #ifdef CONFIG_KRETPROBE_ON_RETHOOK - rp->rh = rethook_alloc((void *)rp, kretprobe_rethook_handler); - if (!rp->rh) - return -ENOMEM; + rp->rh = rethook_alloc((void *)rp, kretprobe_rethook_handler, + sizeof(struct kretprobe_instance) + + rp->data_size, rp->maxactive); + if (IS_ERR(rp->rh)) + return PTR_ERR(rp->rh); - for (i = 0; i < rp->maxactive; i++) { - inst = kzalloc(struct_size(inst, data, rp->data_size), GFP_KERNEL); - if (inst == NULL) { - rethook_free(rp->rh); - rp->rh = NULL; - return -ENOMEM; - } - rethook_add_node(rp->rh, &inst->node); - } rp->nmissed = 0; /* Establish function entry probe point */ ret = register_kprobe(&rp->kp); @@ -2248,24 +2241,18 @@ int register_kretprobe(struct kretprobe *rp) rp->rh = NULL; } #else /* !CONFIG_KRETPROBE_ON_RETHOOK */ - rp->freelist.head = NULL; rp->rph = kzalloc(sizeof(struct kretprobe_holder), GFP_KERNEL); if (!rp->rph) return -ENOMEM; - rp->rph->rp = rp; - for (i = 0; i < rp->maxactive; i++) { - inst = kzalloc(struct_size(inst, data, rp->data_size), GFP_KERNEL); - if (inst == NULL) { - refcount_set(&rp->rph->ref, i); - free_rp_inst(rp); - return -ENOMEM; - } - inst->rph = rp->rph; - freelist_add(&inst->freelist, &rp->freelist); + if (objpool_init(&rp->rph->pool, rp->maxactive, rp->data_size + + sizeof(struct kretprobe_instance), GFP_KERNEL, + rp->rph, kretprobe_init_inst, kretprobe_fini_pool)) { + kfree(rp->rph); + rp->rph = NULL; + return -ENOMEM; } - refcount_set(&rp->rph->ref, i); - + rp->rph->rp = rp; rp->nmissed = 0; /* Establish function entry probe point */ ret = register_kprobe(&rp->kp); diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 3b21f4063258..6890f4fd17fc 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -187,7 +187,7 @@ static void fprobe_init(struct fprobe *fp) static int fprobe_init_rethook(struct fprobe *fp, int num) { - int i, size; + int size; if (num < 0) return -EINVAL; @@ -205,26 +205,18 @@ static int fprobe_init_rethook(struct fprobe *fp, int num) if (size < 0) return -E2BIG; - fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler); - if (!fp->rethook) - return -ENOMEM; - for (i = 0; i < size; i++) { - struct fprobe_rethook_node *node; - - node = kzalloc(sizeof(*node) + fp->entry_data_size, GFP_KERNEL); - if (!node) { - rethook_free(fp->rethook); - fp->rethook = NULL; - return -ENOMEM; - } - rethook_add_node(fp->rethook, &node->node); - } + /* Initialize rethook */ + fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler, + sizeof(struct fprobe_rethook_node), size); + if (IS_ERR(fp->rethook)) + return PTR_ERR(fp->rethook); + return 0; } static void fprobe_fail_cleanup(struct fprobe *fp) { - if (fp->rethook) { + if (!IS_ERR_OR_NULL(fp->rethook)) { /* Don't need to cleanup rethook->handler because this is not used. */ rethook_free(fp->rethook); fp->rethook = NULL; @@ -379,14 +371,14 @@ int unregister_fprobe(struct fprobe *fp) if (!fprobe_is_registered(fp)) return -EINVAL; - if (fp->rethook) + if (!IS_ERR_OR_NULL(fp->rethook)) rethook_stop(fp->rethook); ret = unregister_ftrace_function(&fp->ops); if (ret < 0) return ret; - if (fp->rethook) + if (!IS_ERR_OR_NULL(fp->rethook)) rethook_free(fp->rethook); ftrace_free_filter(&fp->ops); diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c index 5eb9b598f4e9..13c8e6773892 100644 --- a/kernel/trace/rethook.c +++ b/kernel/trace/rethook.c @@ -9,6 +9,7 @@ #include #include #include +#include /* Return hook list (shadow stack by list) */ @@ -36,21 +37,7 @@ void rethook_flush_task(struct task_struct *tk) static void rethook_free_rcu(struct rcu_head *head) { struct rethook *rh = container_of(head, struct rethook, rcu); - struct rethook_node *rhn; - struct freelist_node *node; - int count = 1; - - node = rh->pool.head; - while (node) { - rhn = container_of(node, struct rethook_node, freelist); - node = node->next; - kfree(rhn); - count++; - } - - /* The rh->ref is the number of pooled node + 1 */ - if (refcount_sub_and_test(count, &rh->ref)) - kfree(rh); + objpool_fini(&rh->pool); } /** @@ -83,54 +70,62 @@ void rethook_free(struct rethook *rh) call_rcu(&rh->rcu, rethook_free_rcu); } +static int rethook_init_node(void *nod, void *context) +{ + struct rethook_node *node = nod; + + node->rethook = context; + return 0; +} + +static int rethook_fini_pool(struct objpool_head *head, void *context) +{ + kfree(context); + return 0; +} + /** * rethook_alloc() - Allocate struct rethook. * @data: a data to pass the @handler when hooking the return. - * @handler: the return hook callback function. + * @handler: the return hook callback function, must NOT be NULL + * @size: node size: rethook node and additional data + * @num: number of rethook nodes to be preallocated * * Allocate and initialize a new rethook with @data and @handler. - * Return NULL if memory allocation fails or @handler is NULL. + * Return pointer of new rethook, or error codes for failures. + * * Note that @handler == NULL means this rethook is going to be freed. */ -struct rethook *rethook_alloc(void *data, rethook_handler_t handler) +struct rethook *rethook_alloc(void *data, rethook_handler_t handler, + int size, int num) { - struct rethook *rh = kzalloc(sizeof(struct rethook), GFP_KERNEL); + struct rethook *rh; - if (!rh || !handler) { - kfree(rh); - return NULL; - } + if (!handler || num <= 0 || size < sizeof(struct rethook_node)) + return ERR_PTR(-EINVAL); + + rh = kzalloc(sizeof(struct rethook), GFP_KERNEL); + if (!rh) + return ERR_PTR(-ENOMEM); rh->data = data; rh->handler = handler; - rh->pool.head = NULL; - refcount_set(&rh->ref, 1); + /* initialize the objpool for rethook nodes */ + if (objpool_init(&rh->pool, num, size, GFP_KERNEL, rh, + rethook_init_node, rethook_fini_pool)) { + kfree(rh); + return ERR_PTR(-ENOMEM); + } return rh; } -/** - * rethook_add_node() - Add a new node to the rethook. - * @rh: the struct rethook. - * @node: the struct rethook_node to be added. - * - * Add @node to @rh. User must allocate @node (as a part of user's - * data structure.) The @node fields are initialized in this function. - */ -void rethook_add_node(struct rethook *rh, struct rethook_node *node) -{ - node->rethook = rh; - freelist_add(&node->freelist, &rh->pool); - refcount_inc(&rh->ref); -} - static void free_rethook_node_rcu(struct rcu_head *head) { struct rethook_node *node = container_of(head, struct rethook_node, rcu); + struct rethook *rh = node->rethook; - if (refcount_dec_and_test(&node->rethook->ref)) - kfree(node->rethook); - kfree(node); + objpool_drop(node, &rh->pool); } /** @@ -145,7 +140,7 @@ void rethook_recycle(struct rethook_node *node) lockdep_assert_preemption_disabled(); if (likely(READ_ONCE(node->rethook->handler))) - freelist_add(&node->freelist, &node->rethook->pool); + objpool_push(node, &node->rethook->pool); else call_rcu(&node->rcu, free_rethook_node_rcu); } @@ -161,7 +156,6 @@ NOKPROBE_SYMBOL(rethook_recycle); struct rethook_node *rethook_try_get(struct rethook *rh) { rethook_handler_t handler = READ_ONCE(rh->handler); - struct freelist_node *fn; lockdep_assert_preemption_disabled(); @@ -178,11 +172,7 @@ struct rethook_node *rethook_try_get(struct rethook *rh) if (unlikely(!rcu_is_watching())) return NULL; - fn = freelist_try_get(&rh->pool); - if (!fn) - return NULL; - - return container_of(fn, struct rethook_node, freelist); + return (struct rethook_node *)objpool_pop(&rh->pool); } NOKPROBE_SYMBOL(rethook_try_get); -- cgit v1.2.3 From f46e8939de80bf029787111bf488ee86355b111c Mon Sep 17 00:00:00 2001 From: "wuqiang.matt" Date: Tue, 17 Oct 2023 21:56:53 +0800 Subject: kprobes: freelist.h removed This patch will remove freelist.h from kernel source tree, since the only use cases (kretprobe and rethook) are converted to objpool. Link: https://lore.kernel.org/all/20231017135654.82270-5-wuqiang.matt@bytedance.com/ Signed-off-by: wuqiang.matt Acked-by: Masami Hiramatsu (Google) Signed-off-by: Masami Hiramatsu (Google) --- include/linux/freelist.h | 129 ----------------------------------------------- 1 file changed, 129 deletions(-) delete mode 100644 include/linux/freelist.h (limited to 'include') diff --git a/include/linux/freelist.h b/include/linux/freelist.h deleted file mode 100644 index fc1842b96469..000000000000 --- a/include/linux/freelist.h +++ /dev/null @@ -1,129 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause */ -#ifndef FREELIST_H -#define FREELIST_H - -#include - -/* - * Copyright: cameron@moodycamel.com - * - * A simple CAS-based lock-free free list. Not the fastest thing in the world - * under heavy contention, but simple and correct (assuming nodes are never - * freed until after the free list is destroyed), and fairly speedy under low - * contention. - * - * Adapted from: https://moodycamel.com/blog/2014/solving-the-aba-problem-for-lock-free-free-lists - */ - -struct freelist_node { - atomic_t refs; - struct freelist_node *next; -}; - -struct freelist_head { - struct freelist_node *head; -}; - -#define REFS_ON_FREELIST 0x80000000 -#define REFS_MASK 0x7FFFFFFF - -static inline void __freelist_add(struct freelist_node *node, struct freelist_head *list) -{ - /* - * Since the refcount is zero, and nobody can increase it once it's - * zero (except us, and we run only one copy of this method per node at - * a time, i.e. the single thread case), then we know we can safely - * change the next pointer of the node; however, once the refcount is - * back above zero, then other threads could increase it (happens under - * heavy contention, when the refcount goes to zero in between a load - * and a refcount increment of a node in try_get, then back up to - * something non-zero, then the refcount increment is done by the other - * thread) -- so if the CAS to add the node to the actual list fails, - * decrese the refcount and leave the add operation to the next thread - * who puts the refcount back to zero (which could be us, hence the - * loop). - */ - struct freelist_node *head = READ_ONCE(list->head); - - for (;;) { - WRITE_ONCE(node->next, head); - atomic_set_release(&node->refs, 1); - - if (!try_cmpxchg_release(&list->head, &head, node)) { - /* - * Hmm, the add failed, but we can only try again when - * the refcount goes back to zero. - */ - if (atomic_fetch_add_release(REFS_ON_FREELIST - 1, &node->refs) == 1) - continue; - } - return; - } -} - -static inline void freelist_add(struct freelist_node *node, struct freelist_head *list) -{ - /* - * We know that the should-be-on-freelist bit is 0 at this point, so - * it's safe to set it using a fetch_add. - */ - if (!atomic_fetch_add_release(REFS_ON_FREELIST, &node->refs)) { - /* - * Oh look! We were the last ones referencing this node, and we - * know we want to add it to the free list, so let's do it! - */ - __freelist_add(node, list); - } -} - -static inline struct freelist_node *freelist_try_get(struct freelist_head *list) -{ - struct freelist_node *prev, *next, *head = smp_load_acquire(&list->head); - unsigned int refs; - - while (head) { - prev = head; - refs = atomic_read(&head->refs); - if ((refs & REFS_MASK) == 0 || - !atomic_try_cmpxchg_acquire(&head->refs, &refs, refs+1)) { - head = smp_load_acquire(&list->head); - continue; - } - - /* - * Good, reference count has been incremented (it wasn't at - * zero), which means we can read the next and not worry about - * it changing between now and the time we do the CAS. - */ - next = READ_ONCE(head->next); - if (try_cmpxchg_acquire(&list->head, &head, next)) { - /* - * Yay, got the node. This means it was on the list, - * which means should-be-on-freelist must be false no - * matter the refcount (because nobody else knows it's - * been taken off yet, it can't have been put back on). - */ - WARN_ON_ONCE(atomic_read(&head->refs) & REFS_ON_FREELIST); - - /* - * Decrease refcount twice, once for our ref, and once - * for the list's ref. - */ - atomic_fetch_add(-2, &head->refs); - - return head; - } - - /* - * OK, the head must have changed on us, but we still need to decrement - * the refcount we increased. - */ - refs = atomic_fetch_add(-1, &prev->refs); - if (refs == REFS_ON_FREELIST + 1) - __freelist_add(prev, list); - } - - return NULL; -} - -#endif /* FREELIST_H */ -- cgit v1.2.3