diff options
Diffstat (limited to 'tools/vm/page-types.c')
| -rw-r--r-- | tools/vm/page-types.c | 231 |
1 files changed, 201 insertions, 30 deletions
diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c index 71c9c2511ee..c4d6d2e20e0 100644 --- a/tools/vm/page-types.c +++ b/tools/vm/page-types.c @@ -19,7 +19,8 @@ * Authors: Wu Fengguang <fengguang.wu@intel.com> */ -#define _LARGEFILE64_SOURCE +#define _FILE_OFFSET_BITS 64 +#define _GNU_SOURCE #include <stdio.h> #include <stdlib.h> #include <unistd.h> @@ -29,14 +30,19 @@ #include <getopt.h> #include <limits.h> #include <assert.h> +#include <ftw.h> +#include <time.h> +#include <setjmp.h> +#include <signal.h> #include <sys/types.h> #include <sys/errno.h> #include <sys/fcntl.h> #include <sys/mount.h> #include <sys/statfs.h> +#include <sys/mman.h> #include "../../include/uapi/linux/magic.h" #include "../../include/uapi/linux/kernel-page-flags.h" -#include <lk/debugfs.h> +#include <api/fs/debugfs.h> #ifndef MAX_PATH # define MAX_PATH 256 @@ -59,12 +65,14 @@ #define PM_PSHIFT_BITS 6 #define PM_PSHIFT_OFFSET (PM_STATUS_OFFSET - PM_PSHIFT_BITS) #define PM_PSHIFT_MASK (((1LL << PM_PSHIFT_BITS) - 1) << PM_PSHIFT_OFFSET) -#define PM_PSHIFT(x) (((u64) (x) << PM_PSHIFT_OFFSET) & PM_PSHIFT_MASK) +#define __PM_PSHIFT(x) (((uint64_t) (x) << PM_PSHIFT_OFFSET) & PM_PSHIFT_MASK) #define PM_PFRAME_MASK ((1LL << PM_PSHIFT_OFFSET) - 1) #define PM_PFRAME(x) ((x) & PM_PFRAME_MASK) +#define __PM_SOFT_DIRTY (1LL) #define PM_PRESENT PM_STATUS(4LL) #define PM_SWAP PM_STATUS(2LL) +#define PM_SOFT_DIRTY __PM_PSHIFT(__PM_SOFT_DIRTY) /* @@ -83,6 +91,7 @@ #define KPF_OWNER_PRIVATE 37 #define KPF_ARCH 38 #define KPF_UNCACHED 39 +#define KPF_SOFTDIRTY 40 /* [48-] take some arbitrary free slots for expanding overloaded flags * not part of kernel API @@ -132,6 +141,7 @@ static const char * const page_flag_names[] = { [KPF_OWNER_PRIVATE] = "O:owner_private", [KPF_ARCH] = "h:arch", [KPF_UNCACHED] = "c:uncached", + [KPF_SOFTDIRTY] = "f:softdirty", [KPF_READAHEAD] = "I:readahead", [KPF_SLOB_FREE] = "P:slob_free", @@ -154,6 +164,7 @@ static int opt_raw; /* for kernel developers */ static int opt_list; /* list pages (in ranges) */ static int opt_no_summary; /* don't show summary */ static pid_t opt_pid; /* process to walk */ +const char * opt_file; #define MAX_ADDR_RANGES 1024 static int nr_addr_ranges; @@ -249,12 +260,7 @@ static unsigned long do_u64_read(int fd, char *name, if (index > ULONG_MAX / 8) fatal("index overflow: %lu\n", index); - if (lseek(fd, index * 8, SEEK_SET) < 0) { - perror(name); - exit(EXIT_FAILURE); - } - - bytes = read(fd, buf, count * 8); + bytes = pread(fd, buf, count * 8, (off_t)index * 8); if (bytes < 0) { perror(name); exit(EXIT_FAILURE); @@ -339,8 +345,8 @@ static char *page_flag_longname(uint64_t flags) * page list and summary */ -static void show_page_range(unsigned long voffset, - unsigned long offset, uint64_t flags) +static void show_page_range(unsigned long voffset, unsigned long offset, + unsigned long size, uint64_t flags) { static uint64_t flags0; static unsigned long voff; @@ -348,14 +354,16 @@ static void show_page_range(unsigned long voffset, static unsigned long count; if (flags == flags0 && offset == index + count && - (!opt_pid || voffset == voff + count)) { - count++; + size && voffset == voff + count) { + count += size; return; } if (count) { if (opt_pid) printf("%lx\t", voff); + if (opt_file) + printf("%lu\t", voff); printf("%lx\t%lx\t%s\n", index, count, page_flag_name(flags0)); } @@ -363,7 +371,12 @@ static void show_page_range(unsigned long voffset, flags0 = flags; index = offset; voff = voffset; - count = 1; + count = size; +} + +static void flush_page_range(void) +{ + show_page_range(0, 0, 0, 0); } static void show_page(unsigned long voffset, @@ -371,6 +384,8 @@ static void show_page(unsigned long voffset, { if (opt_pid) printf("%lx\t", voffset); + if (opt_file) + printf("%lu\t", voffset); printf("%lx\t%s\n", offset, page_flag_name(flags)); } @@ -417,7 +432,7 @@ static int bit_mask_ok(uint64_t flags) return 1; } -static uint64_t expand_overloaded_flags(uint64_t flags) +static uint64_t expand_overloaded_flags(uint64_t flags, uint64_t pme) { /* SLOB/SLUB overload several page flags */ if (flags & BIT(SLAB)) { @@ -433,6 +448,9 @@ static uint64_t expand_overloaded_flags(uint64_t flags) if ((flags & (BIT(RECLAIM) | BIT(WRITEBACK))) == BIT(RECLAIM)) flags ^= BIT(RECLAIM) | BIT(READAHEAD); + if (pme & PM_SOFT_DIRTY) + flags |= BIT(SOFTDIRTY); + return flags; } @@ -448,11 +466,11 @@ static uint64_t well_known_flags(uint64_t flags) return flags; } -static uint64_t kpageflags_flags(uint64_t flags) +static uint64_t kpageflags_flags(uint64_t flags, uint64_t pme) { - flags = expand_overloaded_flags(flags); - - if (!opt_raw) + if (opt_raw) + flags = expand_overloaded_flags(flags, pme); + else flags = well_known_flags(flags); return flags; @@ -545,9 +563,9 @@ static size_t hash_slot(uint64_t flags) } static void add_page(unsigned long voffset, - unsigned long offset, uint64_t flags) + unsigned long offset, uint64_t flags, uint64_t pme) { - flags = kpageflags_flags(flags); + flags = kpageflags_flags(flags, pme); if (!bit_mask_ok(flags)) return; @@ -558,7 +576,7 @@ static void add_page(unsigned long voffset, unpoison_page(offset); if (opt_list == 1) - show_page_range(voffset, offset, flags); + show_page_range(voffset, offset, 1, flags); else if (opt_list == 2) show_page(voffset, offset, flags); @@ -569,7 +587,8 @@ static void add_page(unsigned long voffset, #define KPAGEFLAGS_BATCH (64 << 10) /* 64k pages */ static void walk_pfn(unsigned long voffset, unsigned long index, - unsigned long count) + unsigned long count, + uint64_t pme) { uint64_t buf[KPAGEFLAGS_BATCH]; unsigned long batch; @@ -583,7 +602,7 @@ static void walk_pfn(unsigned long voffset, break; for (i = 0; i < pages; i++) - add_page(voffset + i, index + i, buf[i]); + add_page(voffset + i, index + i, buf[i], pme); index += pages; count -= pages; @@ -608,7 +627,7 @@ static void walk_vma(unsigned long index, unsigned long count) for (i = 0; i < pages; i++) { pfn = pagemap_pfn(buf[i]); if (pfn) - walk_pfn(index + i, pfn, 1); + walk_pfn(index + i, pfn, 1, buf[i]); } index += pages; @@ -659,7 +678,7 @@ static void walk_addr_ranges(void) for (i = 0; i < nr_addr_ranges; i++) if (!opt_pid) - walk_pfn(0, opt_offset[i], opt_size[i]); + walk_pfn(opt_offset[i], opt_offset[i], opt_size[i], 0); else walk_task(opt_offset[i], opt_size[i]); @@ -691,9 +710,7 @@ static void usage(void) " -a|--addr addr-spec Walk a range of pages\n" " -b|--bits bits-spec Walk pages with specified bits\n" " -p|--pid pid Walk process address space\n" -#if 0 /* planned features */ " -f|--file filename Walk file address space\n" -#endif " -l|--list Show page details in ranges\n" " -L|--list-each Show page details one by one\n" " -N|--no-summary Don't show summary info\n" @@ -791,8 +808,157 @@ static void parse_pid(const char *str) fclose(file); } +static void show_file(const char *name, const struct stat *st) +{ + unsigned long long size = st->st_size; + char atime[64], mtime[64]; + long now = time(NULL); + + printf("%s\tInode: %u\tSize: %llu (%llu pages)\n", + name, (unsigned)st->st_ino, + size, (size + page_size - 1) / page_size); + + strftime(atime, sizeof(atime), "%c", localtime(&st->st_atime)); + strftime(mtime, sizeof(mtime), "%c", localtime(&st->st_mtime)); + + printf("Modify: %s (%ld seconds ago)\nAccess: %s (%ld seconds ago)\n", + mtime, now - st->st_mtime, + atime, now - st->st_atime); +} + +static sigjmp_buf sigbus_jmp; + +static void * volatile sigbus_addr; + +static void sigbus_handler(int sig, siginfo_t *info, void *ucontex) +{ + (void)sig; + (void)ucontex; + sigbus_addr = info ? info->si_addr : NULL; + siglongjmp(sigbus_jmp, 1); +} + +static struct sigaction sigbus_action = { + .sa_sigaction = sigbus_handler, + .sa_flags = SA_SIGINFO, +}; + +static void walk_file(const char *name, const struct stat *st) +{ + uint8_t vec[PAGEMAP_BATCH]; + uint64_t buf[PAGEMAP_BATCH], flags; + unsigned long nr_pages, pfn, i; + off_t off, end = st->st_size; + int fd; + ssize_t len; + void *ptr; + int first = 1; + + fd = checked_open(name, O_RDONLY|O_NOATIME|O_NOFOLLOW); + + for (off = 0; off < end; off += len) { + nr_pages = (end - off + page_size - 1) / page_size; + if (nr_pages > PAGEMAP_BATCH) + nr_pages = PAGEMAP_BATCH; + len = nr_pages * page_size; + + ptr = mmap(NULL, len, PROT_READ, MAP_SHARED, fd, off); + if (ptr == MAP_FAILED) + fatal("mmap failed: %s", name); + + /* determine cached pages */ + if (mincore(ptr, len, vec)) + fatal("mincore failed: %s", name); + + /* turn off readahead */ + if (madvise(ptr, len, MADV_RANDOM)) + fatal("madvice failed: %s", name); + + if (sigsetjmp(sigbus_jmp, 1)) { + end = off + sigbus_addr ? sigbus_addr - ptr : 0; + fprintf(stderr, "got sigbus at offset %lld: %s\n", + (long long)end, name); + goto got_sigbus; + } + + /* populate ptes */ + for (i = 0; i < nr_pages ; i++) { + if (vec[i] & 1) + (void)*(volatile int *)(ptr + i * page_size); + } +got_sigbus: + + /* turn off harvesting reference bits */ + if (madvise(ptr, len, MADV_SEQUENTIAL)) + fatal("madvice failed: %s", name); + + if (pagemap_read(buf, (unsigned long)ptr / page_size, + nr_pages) != nr_pages) + fatal("cannot read pagemap"); + + munmap(ptr, len); + + for (i = 0; i < nr_pages; i++) { + pfn = pagemap_pfn(buf[i]); + if (!pfn) + continue; + if (!kpageflags_read(&flags, pfn, 1)) + continue; + if (first && opt_list) { + first = 0; + flush_page_range(); + show_file(name, st); + } + add_page(off / page_size + i, pfn, flags, buf[i]); + } + } + + close(fd); +} + +int walk_tree(const char *name, const struct stat *st, int type, struct FTW *f) +{ + (void)f; + switch (type) { + case FTW_F: + if (S_ISREG(st->st_mode)) + walk_file(name, st); + break; + case FTW_DNR: + fprintf(stderr, "cannot read dir: %s\n", name); + break; + } + return 0; +} + +static void walk_page_cache(void) +{ + struct stat st; + + kpageflags_fd = checked_open(PROC_KPAGEFLAGS, O_RDONLY); + pagemap_fd = checked_open("/proc/self/pagemap", O_RDONLY); + sigaction(SIGBUS, &sigbus_action, NULL); + + if (stat(opt_file, &st)) + fatal("stat failed: %s\n", opt_file); + + if (S_ISREG(st.st_mode)) { + walk_file(opt_file, &st); + } else if (S_ISDIR(st.st_mode)) { + /* do not follow symlinks and mountpoints */ + if (nftw(opt_file, walk_tree, 64, FTW_MOUNT | FTW_PHYS) < 0) + fatal("nftw failed: %s\n", opt_file); + } else + fatal("unhandled file type: %s\n", opt_file); + + close(kpageflags_fd); + close(pagemap_fd); + signal(SIGBUS, SIG_DFL); +} + static void parse_file(const char *name) { + opt_file = name; } static void parse_addr_range(const char *optarg) @@ -983,15 +1149,20 @@ int main(int argc, char *argv[]) if (opt_list && opt_pid) printf("voffset\t"); + if (opt_list && opt_file) + printf("foffset\t"); if (opt_list == 1) printf("offset\tlen\tflags\n"); if (opt_list == 2) printf("offset\tflags\n"); - walk_addr_ranges(); + if (opt_file) + walk_page_cache(); + else + walk_addr_ranges(); if (opt_list == 1) - show_page_range(0, 0, 0); /* drain the buffer */ + flush_page_range(); if (opt_no_summary) return 0; |