From bd5fc253e847006af47f0e079543aaefbd7c7429 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Sun, 31 Jul 2022 10:48:17 -0700 Subject: lib: add allocation tagging support for memory allocation profiling Introduce CONFIG_MEM_ALLOC_PROFILING which provides definitions to easily instrument memory allocators. It registers an "alloc_tags" codetag type with /proc/allocinfo interface to output allocation tag information when the feature is enabled. CONFIG_MEM_ALLOC_PROFILING_DEBUG is provided for debugging the memory allocation profiling instrumentation. Memory allocation profiling can be enabled or disabled at runtime using /proc/sys/vm/mem_profiling sysctl when CONFIG_MEM_ALLOC_PROFILING_DEBUG=n. CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT enables memory allocation profiling by default. Signed-off-by: Suren Baghdasaryan Co-developed-by: Kent Overstreet Signed-off-by: Kent Overstreet --- lib/alloc_tag.c | 149 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 149 insertions(+) create mode 100644 lib/alloc_tag.c (limited to 'lib/alloc_tag.c') diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c new file mode 100644 index 000000000000..f09c8a422bc2 --- /dev/null +++ b/lib/alloc_tag.c @@ -0,0 +1,149 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include +#include +#include +#include +#include +#include +#include + +static struct codetag_type *alloc_tag_cttype; + +DEFINE_STATIC_KEY_MAYBE(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT, + mem_alloc_profiling_key); + +static void *allocinfo_start(struct seq_file *m, loff_t *pos) +{ + struct codetag_iterator *iter; + struct codetag *ct; + loff_t node = *pos; + + iter = kzalloc(sizeof(*iter), GFP_KERNEL); + m->private = iter; + if (!iter) + return NULL; + + codetag_lock_module_list(alloc_tag_cttype, true); + *iter = codetag_get_ct_iter(alloc_tag_cttype); + while ((ct = codetag_next_ct(iter)) != NULL && node) + node--; + + return ct ? iter : NULL; +} + +static void *allocinfo_next(struct seq_file *m, void *arg, loff_t *pos) +{ + struct codetag_iterator *iter = (struct codetag_iterator *)arg; + struct codetag *ct = codetag_next_ct(iter); + + (*pos)++; + if (!ct) + return NULL; + + return iter; +} + +static void allocinfo_stop(struct seq_file *m, void *arg) +{ + struct codetag_iterator *iter = (struct codetag_iterator *)m->private; + + if (iter) { + codetag_lock_module_list(alloc_tag_cttype, false); + kfree(iter); + } +} + +static void alloc_tag_to_text(struct seq_buf *out, struct codetag *ct) +{ + struct alloc_tag *tag = ct_to_alloc_tag(ct); + struct alloc_tag_counters counter = alloc_tag_read(tag); + s64 bytes = counter.bytes; + + seq_buf_printf(out, "%12lli %8llu ", bytes, counter.calls); + codetag_to_text(out, ct); + seq_buf_putc(out, ' '); + seq_buf_putc(out, '\n'); +} + +static int allocinfo_show(struct seq_file *m, void *arg) +{ + struct codetag_iterator *iter = (struct codetag_iterator *)arg; + char *bufp; + size_t n = seq_get_buf(m, &bufp); + struct seq_buf buf; + + seq_buf_init(&buf, bufp, n); + alloc_tag_to_text(&buf, iter->ct); + seq_commit(m, seq_buf_used(&buf)); + return 0; +} + +static const struct seq_operations allocinfo_seq_op = { + .start = allocinfo_start, + .next = allocinfo_next, + .stop = allocinfo_stop, + .show = allocinfo_show, +}; + +static void __init procfs_init(void) +{ + proc_create_seq("allocinfo", 0444, NULL, &allocinfo_seq_op); +} + +static bool alloc_tag_module_unload(struct codetag_type *cttype, + struct codetag_module *cmod) +{ + struct codetag_iterator iter = codetag_get_ct_iter(cttype); + struct alloc_tag_counters counter; + bool module_unused = true; + struct alloc_tag *tag; + struct codetag *ct; + + for (ct = codetag_next_ct(&iter); ct; ct = codetag_next_ct(&iter)) { + if (iter.cmod != cmod) + continue; + + tag = ct_to_alloc_tag(ct); + counter = alloc_tag_read(tag); + + if (WARN(counter.bytes, + "%s:%u module %s func:%s has %llu allocated at module unload", + ct->filename, ct->lineno, ct->modname, ct->function, counter.bytes)) + module_unused = false; + } + + return module_unused; +} + +static struct ctl_table memory_allocation_profiling_sysctls[] = { + { + .procname = "mem_profiling", + .data = &mem_alloc_profiling_key, +#ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG + .mode = 0444, +#else + .mode = 0644, +#endif + .proc_handler = proc_do_static_key, + }, + { } +}; + +static int __init alloc_tag_init(void) +{ + const struct codetag_type_desc desc = { + .section = "alloc_tags", + .tag_size = sizeof(struct alloc_tag), + .module_unload = alloc_tag_module_unload, + }; + + alloc_tag_cttype = codetag_register_type(&desc); + if (IS_ERR_OR_NULL(alloc_tag_cttype)) + return PTR_ERR(alloc_tag_cttype); + + register_sysctl_init("vm", memory_allocation_profiling_sysctls); + procfs_init(); + + return 0; +} +module_init(alloc_tag_init); -- cgit v1.2.3 From da4de03e7871e57af3e448f9d7197eb5404d62e9 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Sun, 31 Jul 2022 11:23:24 -0700 Subject: lib: introduce support for page allocation tagging Introduce helper functions to easily instrument page allocators by storing a pointer to the allocation tag associated with the code that allocated the page in a page_ext field. Signed-off-by: Suren Baghdasaryan Co-developed-by: Kent Overstreet Signed-off-by: Kent Overstreet Reviewed-by: Vlastimil Babka --- include/linux/page_ext.h | 1 - include/linux/pgalloc_tag.h | 78 +++++++++++++++++++++++++++++++++++++++++++++ lib/Kconfig.debug | 1 + lib/alloc_tag.c | 17 ++++++++++ mm/mm_init.c | 1 + mm/page_alloc.c | 4 +++ mm/page_ext.c | 4 +++ 7 files changed, 105 insertions(+), 1 deletion(-) create mode 100644 include/linux/pgalloc_tag.h (limited to 'lib/alloc_tag.c') diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index be98564191e6..07e0656898f9 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -4,7 +4,6 @@ #include #include -#include struct pglist_data; diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h new file mode 100644 index 000000000000..66bd021eb46e --- /dev/null +++ b/include/linux/pgalloc_tag.h @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * page allocation tagging + */ +#ifndef _LINUX_PGALLOC_TAG_H +#define _LINUX_PGALLOC_TAG_H + +#include + +#ifdef CONFIG_MEM_ALLOC_PROFILING + +#include + +extern struct page_ext_operations page_alloc_tagging_ops; +extern struct page_ext *page_ext_get(struct page *page); +extern void page_ext_put(struct page_ext *page_ext); + +static inline union codetag_ref *codetag_ref_from_page_ext(struct page_ext *page_ext) +{ + return (void *)page_ext + page_alloc_tagging_ops.offset; +} + +static inline struct page_ext *page_ext_from_codetag_ref(union codetag_ref *ref) +{ + return (void *)ref - page_alloc_tagging_ops.offset; +} + +/* Should be called only if mem_alloc_profiling_enabled() */ +static inline union codetag_ref *get_page_tag_ref(struct page *page) +{ + if (page) { + struct page_ext *page_ext = page_ext_get(page); + + if (page_ext) + return codetag_ref_from_page_ext(page_ext); + } + return NULL; +} + +static inline void put_page_tag_ref(union codetag_ref *ref) +{ + page_ext_put(page_ext_from_codetag_ref(ref)); +} + +static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, + unsigned int nr) +{ + if (mem_alloc_profiling_enabled()) { + union codetag_ref *ref = get_page_tag_ref(page); + + if (ref) { + alloc_tag_add(ref, task->alloc_tag, PAGE_SIZE * nr); + put_page_tag_ref(ref); + } + } +} + +static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) +{ + if (mem_alloc_profiling_enabled()) { + union codetag_ref *ref = get_page_tag_ref(page); + + if (ref) { + alloc_tag_sub(ref, PAGE_SIZE * nr); + put_page_tag_ref(ref); + } + } +} + +#else /* CONFIG_MEM_ALLOC_PROFILING */ + +static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, + unsigned int nr) {} +static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) {} + +#endif /* CONFIG_MEM_ALLOC_PROFILING */ + +#endif /* _LINUX_PGALLOC_TAG_H */ diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index d9a6477afdb1..ca2c466056d5 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -978,6 +978,7 @@ config MEM_ALLOC_PROFILING depends on PROC_FS depends on !DEBUG_FORCE_WEAK_PER_CPU select CODE_TAGGING + select PAGE_EXTENSION help Track allocation source code and record total allocation size initiated at that code location. The mechanism can be used to track diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index f09c8a422bc2..cb5adec4b2e2 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -3,6 +3,7 @@ #include #include #include +#include #include #include #include @@ -115,6 +116,22 @@ static bool alloc_tag_module_unload(struct codetag_type *cttype, return module_unused; } +static __init bool need_page_alloc_tagging(void) +{ + return true; +} + +static __init void init_page_alloc_tagging(void) +{ +} + +struct page_ext_operations page_alloc_tagging_ops = { + .size = sizeof(union codetag_ref), + .need = need_page_alloc_tagging, + .init = init_page_alloc_tagging, +}; +EXPORT_SYMBOL(page_alloc_tagging_ops); + static struct ctl_table memory_allocation_profiling_sysctls[] = { { .procname = "mem_profiling", diff --git a/mm/mm_init.c b/mm/mm_init.c index 549e76af8f82..2fd9bf044a79 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 14d39f34d336..e986f485deff 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -54,6 +54,7 @@ #include #include #include +#include #include #include "internal.h" #include "shuffle.h" @@ -1101,6 +1102,7 @@ __always_inline bool free_pages_prepare(struct page *page, /* Do not let hwpoison pages hit pcplists/buddy */ reset_page_owner(page, order); page_table_check_free(page, order); + pgalloc_tag_sub(page, 1 << order); return false; } @@ -1140,6 +1142,7 @@ __always_inline bool free_pages_prepare(struct page *page, page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; reset_page_owner(page, order); page_table_check_free(page, order); + pgalloc_tag_sub(page, 1 << order); if (!PageHighMem(page)) { debug_check_no_locks_freed(page_address(page), @@ -1533,6 +1536,7 @@ inline void post_alloc_hook(struct page *page, unsigned int order, set_page_owner(page, order, gfp_flags); page_table_check_alloc(page, order); + pgalloc_tag_add(page, current, 1 << order); } static void prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags, diff --git a/mm/page_ext.c b/mm/page_ext.c index 4548fcc66d74..3c58fe8a24df 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -10,6 +10,7 @@ #include #include #include +#include /* * struct page extension @@ -82,6 +83,9 @@ static struct page_ext_operations *page_ext_ops[] __initdata = { #if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) &page_idle_ops, #endif +#ifdef CONFIG_MEM_ALLOC_PROFILING + &page_alloc_tagging_ops, +#endif #ifdef CONFIG_PAGE_TABLE_CHECK &page_table_check_ops, #endif -- cgit v1.2.3 From 752efe69b2fcae5f76963200cc2ae57140535767 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Sun, 25 Feb 2024 00:22:13 +0000 Subject: lib: introduce early boot parameter to avoid page_ext memory overhead The highest memory overhead from memory allocation profiling comes from page_ext objects. This overhead exists even if the feature is disabled but compiled-in. To avoid it, introduce an early boot parameter that prevents page_ext object creation. The new boot parameter is a tri-state with possible values of 0|1|never. When it is set to "never" the memory allocation profiling support is disabled, and overhead is minimized (currently no page_ext objects are allocated, in the future more overhead might be eliminated). As a result we also lose ability to enable memory allocation profiling at runtime (because there is no space to store alloctag references). Runtime sysctrl becomes read-only if the early boot parameter was set to "never". Note that the default value of this boot parameter depends on the CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT configuration. When CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT=n the boot parameter is set to "never", therefore eliminating any overhead. CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT=y results in boot parameter being set to 1 (enabled). This allows distributions to avoid any overhead by setting CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT=n config and with no changes to the kernel command line. We reuse sysctl.vm.mem_profiling boot parameter name in order to avoid introducing yet another control. This change turns it into a tri-state early boot parameter. Signed-off-by: Suren Baghdasaryan Reviewed-by: Vlastimil Babka --- lib/alloc_tag.c | 41 ++++++++++++++++++++++++++++++++++++++++- 1 file changed, 40 insertions(+), 1 deletion(-) (limited to 'lib/alloc_tag.c') diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index cb5adec4b2e2..617c2fbb6673 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -116,9 +116,46 @@ static bool alloc_tag_module_unload(struct codetag_type *cttype, return module_unused; } +#ifdef CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT +static bool mem_profiling_support __meminitdata = true; +#else +static bool mem_profiling_support __meminitdata; +#endif + +static int __init setup_early_mem_profiling(char *str) +{ + bool enable; + + if (!str || !str[0]) + return -EINVAL; + + if (!strncmp(str, "never", 5)) { + enable = false; + mem_profiling_support = false; + } else { + int res; + + res = kstrtobool(str, &enable); + if (res) + return res; + + mem_profiling_support = true; + } + + if (enable != static_key_enabled(&mem_alloc_profiling_key)) { + if (enable) + static_branch_enable(&mem_alloc_profiling_key); + else + static_branch_disable(&mem_alloc_profiling_key); + } + + return 0; +} +early_param("sysctl.vm.mem_profiling", setup_early_mem_profiling); + static __init bool need_page_alloc_tagging(void) { - return true; + return mem_profiling_support; } static __init void init_page_alloc_tagging(void) @@ -158,6 +195,8 @@ static int __init alloc_tag_init(void) if (IS_ERR_OR_NULL(alloc_tag_cttype)) return PTR_ERR(alloc_tag_cttype); + if (!mem_profiling_support) + memory_allocation_profiling_sysctls[0].mode = 0444; register_sysctl_init("vm", memory_allocation_profiling_sysctls); procfs_init(); -- cgit v1.2.3 From 2886d227436a7aea812f2b498a939cb9aa4841ab Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 10 Apr 2023 20:17:52 +0000 Subject: lib: add memory allocations report in show_mem() Include allocations in show_mem reports. Signed-off-by: Kent Overstreet Signed-off-by: Suren Baghdasaryan Reviewed-by: Vlastimil Babka --- include/linux/alloc_tag.h | 7 +++++++ include/linux/codetag.h | 1 + lib/alloc_tag.c | 38 ++++++++++++++++++++++++++++++++++++++ lib/codetag.c | 5 +++++ mm/show_mem.c | 26 ++++++++++++++++++++++++++ 5 files changed, 77 insertions(+) (limited to 'lib/alloc_tag.c') diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h index cf69e037f645..aefe3c81a1e3 100644 --- a/include/linux/alloc_tag.h +++ b/include/linux/alloc_tag.h @@ -30,6 +30,13 @@ struct alloc_tag { #ifdef CONFIG_MEM_ALLOC_PROFILING +struct codetag_bytes { + struct codetag *ct; + s64 bytes; +}; + +size_t alloc_tag_top_users(struct codetag_bytes *tags, size_t count, bool can_sleep); + static inline struct alloc_tag *ct_to_alloc_tag(struct codetag *ct) { return container_of(ct, struct alloc_tag, ct); diff --git a/include/linux/codetag.h b/include/linux/codetag.h index bfd0ba5c4185..c2a579ccd455 100644 --- a/include/linux/codetag.h +++ b/include/linux/codetag.h @@ -61,6 +61,7 @@ struct codetag_iterator { } void codetag_lock_module_list(struct codetag_type *cttype, bool lock); +bool codetag_trylock_module_list(struct codetag_type *cttype); struct codetag_iterator codetag_get_ct_iter(struct codetag_type *cttype); struct codetag *codetag_next_ct(struct codetag_iterator *iter); diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index 617c2fbb6673..e24830c44783 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -86,6 +86,44 @@ static const struct seq_operations allocinfo_seq_op = { .show = allocinfo_show, }; +size_t alloc_tag_top_users(struct codetag_bytes *tags, size_t count, bool can_sleep) +{ + struct codetag_iterator iter; + struct codetag *ct; + struct codetag_bytes n; + unsigned int i, nr = 0; + + if (can_sleep) + codetag_lock_module_list(alloc_tag_cttype, true); + else if (!codetag_trylock_module_list(alloc_tag_cttype)) + return 0; + + iter = codetag_get_ct_iter(alloc_tag_cttype); + while ((ct = codetag_next_ct(&iter))) { + struct alloc_tag_counters counter = alloc_tag_read(ct_to_alloc_tag(ct)); + + n.ct = ct; + n.bytes = counter.bytes; + + for (i = 0; i < nr; i++) + if (n.bytes > tags[i].bytes) + break; + + if (i < count) { + nr -= nr == count; + memmove(&tags[i + 1], + &tags[i], + sizeof(tags[0]) * (nr - i)); + nr++; + tags[i] = n; + } + } + + codetag_lock_module_list(alloc_tag_cttype, false); + + return nr; +} + static void __init procfs_init(void) { proc_create_seq("allocinfo", 0444, NULL, &allocinfo_seq_op); diff --git a/lib/codetag.c b/lib/codetag.c index 408062f722ce..5ace625f2328 100644 --- a/lib/codetag.c +++ b/lib/codetag.c @@ -36,6 +36,11 @@ void codetag_lock_module_list(struct codetag_type *cttype, bool lock) up_read(&cttype->mod_lock); } +bool codetag_trylock_module_list(struct codetag_type *cttype) +{ + return down_read_trylock(&cttype->mod_lock) != 0; +} + struct codetag_iterator codetag_get_ct_iter(struct codetag_type *cttype) { struct codetag_iterator iter = { diff --git a/mm/show_mem.c b/mm/show_mem.c index 8dcfafbd283c..bdb439551eef 100644 --- a/mm/show_mem.c +++ b/mm/show_mem.c @@ -423,4 +423,30 @@ void __show_mem(unsigned int filter, nodemask_t *nodemask, int max_zone_idx) #ifdef CONFIG_MEMORY_FAILURE printk("%lu pages hwpoisoned\n", atomic_long_read(&num_poisoned_pages)); #endif +#ifdef CONFIG_MEM_ALLOC_PROFILING + { + struct codetag_bytes tags[10]; + size_t i, nr; + + nr = alloc_tag_top_users(tags, ARRAY_SIZE(tags), false); + if (nr) { + pr_notice("Memory allocations:\n"); + for (i = 0; i < nr; i++) { + struct codetag *ct = tags[i].ct; + struct alloc_tag *tag = ct_to_alloc_tag(ct); + struct alloc_tag_counters counter = alloc_tag_read(tag); + + /* Same as alloc_tag_to_text() but w/o intermediate buffer */ + if (ct->modname) + pr_notice("%12lli %8llu %s:%u [%s] func:%s\n", + counter.bytes, counter.calls, ct->filename, + ct->lineno, ct->modname, ct->function); + else + pr_notice("%12lli %8llu %s:%u func:%s\n", + counter.bytes, counter.calls, ct->filename, + ct->lineno, ct->function); + } + } + } +#endif } -- cgit v1.2.3