diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 320480a8db4f..bc0a3c941b35 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 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/syscalls.h b/include/linux/syscalls.h index 33a0ee3bcb2e..6648c07c4381 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -72,6 +72,8 @@ struct open_how; struct mount_attr; struct landlock_ruleset_attr; enum landlock_rule_type; +struct cachestat_range; +struct cachestat; #include #include @@ -1058,6 +1060,9 @@ 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, + struct cachestat_range __user *cstat_range, + 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..cd639fae9086 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 +__SYSCALL(__NR_cachestat, 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..a246e11988d5 100644 --- a/include/uapi/linux/mman.h +++ b/include/uapi/linux/mman.h @@ -4,6 +4,7 @@ #include #include +#include #define MREMAP_MAYMOVE 1 #define MREMAP_FIXED 2 @@ -41,4 +42,17 @@ #define MAP_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB #define MAP_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB +struct cachestat_range { + __u64 off; + __u64 len; +}; + +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 32c24950c4ce..f7f65af4ee12 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1771,6 +1771,16 @@ 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 b4c9bd368b7e..2d3d70c64dfd 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -58,6 +59,8 @@ #include +#include "swap.h" + /* * Shared mappings implemented 30.11.1994. It's not fully working yet, * though. @@ -4119,3 +4122,171 @@ bool filemap_release_folio(struct folio *folio, gfp_t gfp) return try_to_free_buffers(folio); } EXPORT_SYMBOL(filemap_release_folio); + +#ifdef CONFIG_CACHESTAT_SYSCALL +/** + * 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. + */ +static 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; + + if (xa_is_value(folio)) { + /* page is evicted */ + void *shadow = (void *)folio; + bool workingset; /* not used */ + int order = xa_get_order(xas.xa, xas.xa_index); + + nr_pages = 1 << order; + folio_first_index = round_down(xas.xa_index, 1 << order); + folio_last_index = folio_first_index + nr_pages - 1; + + /* Folios might straddle the range boundaries, only count covered pages */ + 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; + + 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; + } + + 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 pages */ + 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; + + /* 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(); +} + +/* + * The cachestat(2) 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). + * + * Currently, hugetlbfs is not supported. + * + * 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 or cstat_range points to an illegal address + * -EINVAL - invalid flags + * -EBADF - invalid file descriptor + * -EOPNOTSUPP - file descriptor is of a hugetlbfs file + */ +SYSCALL_DEFINE4(cachestat, unsigned int, fd, + struct cachestat_range __user *, cstat_range, + struct cachestat __user *, cstat, unsigned int, flags) +{ + struct fd f = fdget(fd); + struct address_space *mapping; + struct cachestat_range csr; + struct cachestat cs; + pgoff_t first_index, last_index; + + if (!f.file) + return -EBADF; + + if (copy_from_user(&csr, cstat_range, + sizeof(struct cachestat_range))) { + fdput(f); + return -EFAULT; + } + + /* hugetlbfs is not supported */ + if (is_file_hugepages(f.file)) { + fdput(f); + return -EOPNOTSUPP; + } + + if (flags != 0) { + fdput(f); + return -EINVAL; + } + + first_index = csr.off >> PAGE_SHIFT; + last_index = + csr.len == 0 ? ULONG_MAX : (csr.off + csr.len - 1) >> PAGE_SHIFT; + 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; +} +#endif /* CONFIG_CACHESTAT_SYSCALL */