[v9,2/3] cachestat: implement cachestat syscall

Message ID	20230203190413.2559707-3-nphamcs@gmail.com (mailing list archive)
State	New
Headers	show Return-Path: <owner-linux-mm@kvack.org> From: Nhat Pham <nphamcs@gmail.com> To: akpm@linux-foundation.org Cc: hannes@cmpxchg.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org, bfoster@redhat.com, willy@infradead.org, linux-api@vger.kernel.org, kernel-team@meta.com Subject: [PATCH v9 2/3] cachestat: implement cachestat syscall Date: Fri, 3 Feb 2023 11:04:12 -0800 Message-Id: <20230203190413.2559707-3-nphamcs@gmail.com> In-Reply-To: <20230203190413.2559707-1-nphamcs@gmail.com> References: <20230203190413.2559707-1-nphamcs@gmail.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Sender: owner-linux-mm@kvack.org Precedence: bulk
Series	cachestat: a new syscall for page cache state of files \| expand [v9,0/3] cachestat: a new syscall for page cache state of files [v9,1/3] workingset: refactor LRU refault to expose refault recency check [v9,2/3] cachestat: implement cachestat syscall [v9,3/3] selftests: Add selftests for cachestat

diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 320480a8db4f..01d1cc009250 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -455,3 +455,4 @@ 448 i386 process_mrelease sys_process_mrelease 449 i386 futex_waitv sys_futex_waitv 450 i386 set_mempolicy_home_node sys_set_mempolicy_home_node +451 i386 cachestat sys_cachestat compat_sys_cachestat diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index c84d12608cd2..227538b0ce80 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -372,6 +372,7 @@ 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common cachestat sys_cachestat # # Due to a historical design error, certain syscalls are numbered differently diff --git a/include/linux/compat.h b/include/linux/compat.h index 594357881b0b..353d3ce657a7 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -816,7 +816,9 @@ asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg, unsigned int flags); -/* mm/filemap.c: No generic prototype for readahead */ +/* mm/filemap.c */ +asmlinkage long compat_sys_cachestat(int fd, compat_arg_u64(off), + size_t len, struct cachestat __user *cstat, unsigned int flags); /* security/keys/keyctl.c */ asmlinkage long compat_sys_keyctl(u32 option, diff --git a/include/linux/fs.h b/include/linux/fs.h index e654435f1651..83300f1491e7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -75,6 +75,7 @@ struct fs_context; struct fs_parameter_spec; struct fileattr; struct iomap_ops; +struct cachestat; extern void __init inode_init(void); extern void __init inode_init_early(void); @@ -830,6 +831,8 @@ void filemap_invalidate_lock_two(struct address_space *mapping1, struct address_space *mapping2); void filemap_invalidate_unlock_two(struct address_space *mapping1, struct address_space *mapping2); +void filemap_cachestat(struct address_space *mapping, pgoff_t first_index, + pgoff_t last_index, struct cachestat *cs); /* diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a34b0f9a9972..f92f25d96286 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -72,6 +72,7 @@ struct open_how; struct mount_attr; struct landlock_ruleset_attr; enum landlock_rule_type; +struct cachestat; #include <linux/types.h> #include <linux/aio_abi.h> @@ -1056,6 +1057,9 @@ asmlinkage long sys_memfd_secret(unsigned int flags); asmlinkage long sys_set_mempolicy_home_node(unsigned long start, unsigned long len, unsigned long home_node, unsigned long flags); +asmlinkage long sys_cachestat(unsigned int fd, unsigned long off_low, + unsigned long off_high, size_t len, struct cachestat __user *cstat, + unsigned int flags); /* * Architecture-specific system calls diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 45fa180cc56a..dc5fcfee7f09 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -886,8 +886,11 @@ __SYSCALL(__NR_futex_waitv, sys_futex_waitv) #define __NR_set_mempolicy_home_node 450 __SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node) +#define __NR_cachestat 451 +__SC_COMP(__NR_cachestat, sys_cachestat, compat_sys_cachestat) + #undef __NR_syscalls -#define __NR_syscalls 451 +#define __NR_syscalls 452 /* * 32 bit systems traditionally used different diff --git a/include/uapi/linux/mman.h b/include/uapi/linux/mman.h index f55bc680b5b0..fe03ed0b7587 100644 --- a/include/uapi/linux/mman.h +++ b/include/uapi/linux/mman.h @@ -4,6 +4,7 @@ #include <asm/mman.h> #include <asm-generic/hugetlb_encode.h> +#include <linux/types.h> #define MREMAP_MAYMOVE 1 #define MREMAP_FIXED 2 @@ -41,4 +42,12 @@ #define MAP_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB #define MAP_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB +struct cachestat { + __u64 nr_cache; + __u64 nr_dirty; + __u64 nr_writeback; + __u64 nr_evicted; + __u64 nr_recently_evicted; +}; + #endif /* _UAPI_LINUX_MMAN_H */ diff --git a/init/Kconfig b/init/Kconfig index 694f7c160c9c..da96ac29af1d 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1798,6 +1798,16 @@ config RSEQ If unsure, say Y. +config CACHESTAT_SYSCALL + bool "Enable cachestat() system call" if EXPERT + default y + help + Enable the cachestat system call, which queries the page cache + statistics of a file (number of cached pages, dirty pages, + pages marked for writeback, (recently) evicted pages). + + If unsure say Y here. + config DEBUG_RSEQ default n bool "Enabled debugging of rseq() system call" if EXPERT diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 860b2dcf3ac4..04bfb1e4d377 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -299,6 +299,7 @@ COND_SYSCALL(set_mempolicy); COND_SYSCALL(migrate_pages); COND_SYSCALL(move_pages); COND_SYSCALL(set_mempolicy_home_node); +COND_SYSCALL(cachestat); COND_SYSCALL(perf_event_open); COND_SYSCALL(accept4); diff --git a/mm/filemap.c b/mm/filemap.c index 08341616ae7a..87a391976408 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -22,6 +22,7 @@ #include <linux/mm.h> #include <linux/swap.h> #include <linux/swapops.h> +#include <linux/syscalls.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/file.h> @@ -55,6 +56,9 @@ #include <linux/buffer_head.h> /* for try_to_free_buffers */ #include <asm/mman.h> +#include <uapi/linux/mman.h> + +#include "swap.h" /* * Shared mappings implemented 30.11.1994. It's not fully working yet, @@ -3949,3 +3953,156 @@ bool filemap_release_folio(struct folio *folio, gfp_t gfp) return try_to_free_buffers(folio); } EXPORT_SYMBOL(filemap_release_folio); + +/** + * filemap_cachestat() - compute the page cache statistics of a mapping + * @mapping: The mapping to compute the statistics for. + * @first_index: The starting page cache index. + * @last_index: The final page index (inclusive). + * @cs: the cachestat struct to write the result to. + * + * This will query the page cache statistics of a mapping in the + * page range of [first_index, last_index] (inclusive). The statistics + * queried include: number of dirty pages, number of pages marked for + * writeback, and the number of (recently) evicted pages. + */ +void filemap_cachestat(struct address_space *mapping, pgoff_t first_index, + pgoff_t last_index, struct cachestat *cs) +{ + XA_STATE(xas, &mapping->i_pages, first_index); + struct folio *folio; + + rcu_read_lock(); + xas_for_each(&xas, folio, last_index) { + unsigned long nr_pages; + pgoff_t folio_first_index, folio_last_index; + + if (xas_retry(&xas, folio)) + continue; + + nr_pages = folio_nr_pages(folio); + folio_first_index = folio_pgoff(folio); + folio_last_index = folio_first_index + nr_pages - 1; + + /* Folios might straddle the range boundaries, only count covered subpages */ + if (folio_first_index < first_index) + nr_pages -= first_index - folio_first_index; + + if (folio_last_index > last_index) + nr_pages -= folio_last_index - last_index; + + if (xa_is_value(folio)) { + /* page is evicted */ + void *shadow = (void *)folio; + bool workingset; /* not used */ + + cs->nr_evicted += nr_pages; + +#ifdef CONFIG_SWAP /* implies CONFIG_MMU */ + if (shmem_mapping(mapping)) { + /* shmem file - in swap cache */ + swp_entry_t swp = radix_to_swp_entry(folio); + + shadow = get_shadow_from_swap_cache(swp); + } +#endif + if (workingset_test_recent(shadow, true, &workingset)) + cs->nr_recently_evicted += nr_pages; + + goto resched; + } + + /* page is in cache */ + cs->nr_cache += nr_pages; + + if (folio_test_dirty(folio)) + cs->nr_dirty += nr_pages; + + if (folio_test_writeback(folio)) + cs->nr_writeback += nr_pages; + +resched: + if (need_resched()) { + xas_pause(&xas); + cond_resched_rcu(); + } + } + rcu_read_unlock(); +} +EXPORT_SYMBOL(filemap_cachestat); + +#ifdef CONFIG_CACHESTAT_SYSCALL +long ksys_cachestat(unsigned int fd, loff_t off, size_t len, + struct cachestat __user *cstat, unsigned int flags) +{ + struct fd f = fdget(fd); + struct address_space *mapping; + struct cachestat cs; + pgoff_t first_index = off >> PAGE_SHIFT; + pgoff_t last_index = + len == 0 ? ULONG_MAX : (off + len - 1) >> PAGE_SHIFT; + + if (!f.file) + return -EBADF; + + if (off < 0 || flags != 0) { + fdput(f); + return -EINVAL; + } + + memset(&cs, 0, sizeof(struct cachestat)); + mapping = f.file->f_mapping; + filemap_cachestat(mapping, first_index, last_index, &cs); + fdput(f); + + if (copy_to_user(cstat, &cs, sizeof(struct cachestat))) + return -EFAULT; + + return 0; +} + +/* + * The cachestat(5) system call. + * + * cachestat() returns the page cache statistics of a file in the + * bytes range specified by `off` and `len`: number of cached pages, + * number of dirty pages, number of pages marked for writeback, + * number of evicted pages, and number of recently evicted pages. + * + * An evicted page is a page that is previously in the page cache + * but has been evicted since. A page is recently evicted if its last + * eviction was recent enough that its reentry to the cache would + * indicate that it is actively being used by the system, and that + * there is memory pressure on the system. + * + * `off` and `len` must be non-negative integers. If `len` > 0, + * the queried range is [`off`, `off` + `len`]. If `len` == 0, + * we will query in the range from `off` to the end of the file. + * + * The `flags` argument is unused for now, but is included for future + * extensibility. User should pass 0 (i.e no flag specified). + * + * Because the status of a page can change after cachestat() checks it + * but before it returns to the application, the returned values may + * contain stale information. + * + * return values: + * zero - success + * -EFAULT - cstat points to an illegal address + * -EINVAL - invalid arguments + * -EBADF - invalid file descriptor + */ +SYSCALL_DEFINE5(cachestat, unsigned int, fd, loff_t, off, size_t, len, + struct cachestat __user *, cstat, unsigned int, flags) +{ + return ksys_cachestat(fd, off, len, cstat, flags); +} + +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE6(cachestat, unsigned int, fd, compat_arg_u64_dual(off), + size_t, len, struct cachestat __user *, cstat, unsigned int, flags) +{ + return ksys_cachestat(fd, compat_arg_u64_glue(off), len, cstat, flags); +} +#endif +#endif /* CONFIG_CACHESTAT_SYSCALL */

[v9,2/3] cachestat: implement cachestat syscall

Commit Message

Comments

Patch