The patch titled Subject: debugging: meep track of page owners has been added to the -mm tree. Its filename is debugging-keep-track-of-page-owners.patch Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/SubmitChecklist when testing your code *** The -mm tree is included into linux-next and is updated there every 3-4 working days ------------------------------------------------------ From: Alexander Nyberg <alexn@xxxxxxxxx> Subject: debugging: meep track of page owners akpm: Alex's ancient page-owner tracking code, resurrected yet again. Someone(tm) should mainline this. Please see Ingo's thoughts at https://lkml.org/lkml/2009/4/1/137. PAGE_OWNER tracks free pages by setting page->order to -1. However, it is set during __free_pages() which is not the only free path as __pagevec_free() and free_compound_page() do not go through __free_pages(). This leads to a situation where free pages are visible in page_owner which is confusing and might be interpreted as a memory leak. This patch sets page->owner when PageBuddy is set. It also prints a warning to the kernel log if a free page is found that does not appear free to PAGE_OWNER. This should be considered a fix to page-owner-tracking-leak-detector.patch. This only applies to -mm as PAGE_OWNER is not in mainline. [mel@xxxxxxxxx: print out PAGE_OWNER statistics in relation to fragmentation avoidance] [mel.ul.ie: allow PAGE_OWNER to be set on any architecture] Signed-off-by: Mel Gorman <mel@xxxxxxxxx> Acked-by: Andy Whitcroft <apw@xxxxxxxxxxxx> Signed-off-by: Mel Gorman <mel@xxxxxxxxx> Cc: Christoph Lameter <cl@xxxxxxxxxxxxxxxxxxxx> Cc: Ingo Molnar <mingo@xxxxxxx> Cc: Laura Abbott <lauraa@xxxxxxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- Documentation/page_owner.c | 141 ++++++++++++++++++++++++++++ include/linux/mm_types.h | 5 + lib/Kconfig.debug | 11 ++ mm/Makefile | 1 mm/page_alloc.c | 76 +++++++++++++++ mm/pageowner.c | 174 +++++++++++++++++++++++++++++++++++ mm/vmstat.c | 93 ++++++++++++++++++ 7 files changed, 501 insertions(+) diff -puN /dev/null Documentation/page_owner.c --- /dev/null +++ a/Documentation/page_owner.c @@ -0,0 +1,141 @@ +/* + * User-space helper to sort the output of /sys/kernel/debug/page_owner + * + * Example use: + * cat /sys/kernel/debug/page_owner > page_owner_full.txt + * grep -v ^PFN page_owner_full.txt > page_owner.txt + * ./sort page_owner.txt sorted_page_owner.txt +*/ + +#include <stdio.h> +#include <stdlib.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <unistd.h> +#include <string.h> + +struct block_list { + char *txt; + int len; + int num; +}; + + +static struct block_list *list; +static int list_size; +static int max_size; + +struct block_list *block_head; + +int read_block(char *buf, FILE *fin) +{ + int ret = 0; + int hit = 0; + char *curr = buf; + + for (;;) { + *curr = getc(fin); + if (*curr == EOF) return -1; + + ret++; + if (*curr == '\n' && hit == 1) + return ret - 1; + else if (*curr == '\n') + hit = 1; + else + hit = 0; + curr++; + } +} + +static int compare_txt(struct block_list *l1, struct block_list *l2) +{ + return strcmp(l1->txt, l2->txt); +} + +static int compare_num(struct block_list *l1, struct block_list *l2) +{ + return l2->num - l1->num; +} + +static void add_list(char *buf, int len) +{ + if (list_size != 0 && + len == list[list_size-1].len && + memcmp(buf, list[list_size-1].txt, len) == 0) { + list[list_size-1].num++; + return; + } + if (list_size == max_size) { + printf("max_size too small??\n"); + exit(1); + } + list[list_size].txt = malloc(len+1); + list[list_size].len = len; + list[list_size].num = 1; + memcpy(list[list_size].txt, buf, len); + list[list_size].txt[len] = 0; + list_size++; + if (list_size % 1000 == 0) { + printf("loaded %d\r", list_size); + fflush(stdout); + } +} + +int main(int argc, char **argv) +{ + FILE *fin, *fout; + char buf[1024]; + int ret, i, count; + struct block_list *list2; + struct stat st; + + fin = fopen(argv[1], "r"); + fout = fopen(argv[2], "w"); + if (!fin || !fout) { + printf("Usage: ./program <input> <output>\n"); + perror("open: "); + exit(2); + } + + fstat(fileno(fin), &st); + max_size = st.st_size / 100; /* hack ... */ + + list = malloc(max_size * sizeof(*list)); + + for(;;) { + ret = read_block(buf, fin); + if (ret < 0) + break; + + buf[ret] = '\0'; + add_list(buf, ret); + } + + printf("loaded %d\n", list_size); + + printf("sorting ....\n"); + + qsort(list, list_size, sizeof(list[0]), compare_txt); + + list2 = malloc(sizeof(*list) * list_size); + + printf("culling\n"); + + for (i=count=0;i<list_size;i++) { + if (count == 0 || + strcmp(list2[count-1].txt, list[i].txt) != 0) { + list2[count++] = list[i]; + } else { + list2[count-1].num += list[i].num; + } + } + + qsort(list2, count, sizeof(list[0]), compare_num); + + for (i=0;i<count;i++) { + fprintf(fout, "%d times:\n%s\n", list2[i].num, list2[i].txt); + } + return 0; +} diff -puN include/linux/mm_types.h~debugging-keep-track-of-page-owners include/linux/mm_types.h --- a/include/linux/mm_types.h~debugging-keep-track-of-page-owners +++ a/include/linux/mm_types.h @@ -177,6 +177,11 @@ struct page { #ifdef LAST_CPU_NOT_IN_PAGE_FLAGS int _last_cpu; #endif +#ifdef CONFIG_PAGE_OWNER + int order; + unsigned int gfp_mask; + unsigned long trace[8]; +#endif } /* * The struct page can be forced to be double word aligned so that atomic ops diff -puN lib/Kconfig.debug~debugging-keep-track-of-page-owners lib/Kconfig.debug --- a/lib/Kconfig.debug~debugging-keep-track-of-page-owners +++ a/lib/Kconfig.debug @@ -99,6 +99,17 @@ config UNUSED_SYMBOLS you really need it, and what the merge plan to the mainline kernel for your module is. +config PAGE_OWNER + bool "Track page owner" + depends on DEBUG_KERNEL + select DEBUG_FS + help + This keeps track of what call chain is the owner of a page, may + help to find bare alloc_page(s) leaks. Eats a fair amount of memory. + See Documentation/page_owner.c for user-space helper. + + If unsure, say N. + config DEBUG_FS bool "Debug Filesystem" help diff -puN mm/Makefile~debugging-keep-track-of-page-owners mm/Makefile --- a/mm/Makefile~debugging-keep-track-of-page-owners +++ a/mm/Makefile @@ -59,3 +59,4 @@ obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak-test.o obj-$(CONFIG_CLEANCACHE) += cleancache.o obj-$(CONFIG_MEMORY_ISOLATION) += page_isolation.o +obj-$(CONFIG_PAGE_OWNER) += pageowner.o diff -puN mm/page_alloc.c~debugging-keep-track-of-page-owners mm/page_alloc.c --- a/mm/page_alloc.c~debugging-keep-track-of-page-owners +++ a/mm/page_alloc.c @@ -439,6 +439,9 @@ static inline void set_page_order(struct { set_page_private(page, order); __SetPageBuddy(page); +#ifdef CONFIG_PAGE_OWNER + page->order = -1; +#endif } static inline void rmv_page_order(struct page *page) @@ -2264,6 +2267,63 @@ __perform_reclaim(gfp_t gfp_mask, unsign return progress; } +#ifdef CONFIG_PAGE_OWNER +static inline int valid_stack_ptr(struct thread_info *tinfo, void *p) +{ + return p > (void *)tinfo && + p < (void *)tinfo + THREAD_SIZE - 3; +} + +static inline void __stack_trace(struct page *page, unsigned long *stack, + unsigned long bp) +{ + int i = 0; + unsigned long addr; + struct thread_info *tinfo = (struct thread_info *) + ((unsigned long)stack & (~(THREAD_SIZE - 1))); + + memset(page->trace, 0, sizeof(long) * 8); + +#ifdef CONFIG_FRAME_POINTER + if (bp) { + while (valid_stack_ptr(tinfo, (void *)bp)) { + addr = *(unsigned long *)(bp + sizeof(long)); + page->trace[i] = addr; + if (++i >= 8) + break; + bp = *(unsigned long *)bp; + } + return; + } +#endif /* CONFIG_FRAME_POINTER */ + while (valid_stack_ptr(tinfo, stack)) { + addr = *stack++; + if (__kernel_text_address(addr)) { + page->trace[i] = addr; + if (++i >= 8) + break; + } + } +} + +static void set_page_owner(struct page *page, unsigned int order, + unsigned int gfp_mask) +{ + unsigned long address; + unsigned long bp = 0; +#ifdef CONFIG_X86_64 + asm ("movq %%rbp, %0" : "=r" (bp) : ); +#endif +#ifdef CONFIG_X86_32 + asm ("movl %%ebp, %0" : "=r" (bp) : ); +#endif + page->order = (int) order; + page->gfp_mask = gfp_mask; + __stack_trace(page, &address, bp); +} +#endif /* CONFIG_PAGE_OWNER */ + + /* The really slow allocator path where we enter direct reclaim */ static inline struct page * __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, @@ -2299,6 +2359,10 @@ retry: goto retry; } +#ifdef CONFIG_PAGE_OWNER + if (page) + set_page_owner(page, order, gfp_mask); +#endif return page; } @@ -2608,6 +2672,10 @@ nopage: warn_alloc_failed(gfp_mask, order, NULL); return page; got_pg: +#ifdef CONFIG_PAGE_OWNER + if (page) + set_page_owner(page, order, gfp_mask); +#endif if (kmemcheck_enabled) kmemcheck_pagealloc_alloc(page, order, gfp_mask); @@ -2690,6 +2758,11 @@ out: memcg_kmem_commit_charge(page, memcg, order); +#ifdef CONFIG_PAGE_OWNER + if (page) + set_page_owner(page, order, gfp_mask); +#endif + return page; } EXPORT_SYMBOL(__alloc_pages_nodemask); @@ -3962,6 +4035,9 @@ void __meminit memmap_init_zone(unsigned if (!is_highmem_idx(zone)) set_page_address(page, __va(pfn << PAGE_SHIFT)); #endif +#ifdef CONFIG_PAGE_OWNER + page->order = -1; +#endif } } diff -puN /dev/null mm/pageowner.c --- /dev/null +++ a/mm/pageowner.c @@ -0,0 +1,174 @@ +#include <linux/debugfs.h> +#include <linux/mm.h> +#include <linux/hugetlb.h> +#include <linux/huge_mm.h> +#include <linux/mount.h> +#include <linux/seq_file.h> +#include <linux/highmem.h> +#include <linux/ptrace.h> +#include <linux/slab.h> +#include <linux/pagemap.h> +#include <linux/mempolicy.h> +#include <linux/rmap.h> +#include <linux/swap.h> +#include <linux/swapops.h> + +#include <asm/elf.h> +#include <asm/uaccess.h> +#include <asm/tlbflush.h> +#include "internal.h" + +#include <linux/bootmem.h> +#include <linux/kallsyms.h> + +static ssize_t +read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos) +{ + unsigned long pfn; + struct page *page; + char *kbuf, *modname; + const char *symname; + int ret = 0; + char namebuf[128]; + unsigned long offset = 0, symsize; + int i; + ssize_t num_written = 0; + int blocktype = 0, pagetype = 0; + + page = NULL; + pfn = min_low_pfn + *ppos; + + /* Find a valid PFN or the start of a MAX_ORDER_NR_PAGES area */ + while (!pfn_valid(pfn) && (pfn & (MAX_ORDER_NR_PAGES - 1)) != 0) + pfn++; + + //printk("pfn: %ld max_pfn: %ld\n", pfn, max_pfn); + /* Find an allocated page */ + for (; pfn < max_pfn; pfn++) { + /* + * If the new page is in a new MAX_ORDER_NR_PAGES area, + * validate the area as existing, skip it if not + */ + if ((pfn & (MAX_ORDER_NR_PAGES - 1)) == 0 && !pfn_valid(pfn)) { + pfn += MAX_ORDER_NR_PAGES - 1; + continue; + } + + /* Check for holes within a MAX_ORDER area */ + if (!pfn_valid_within(pfn)) + continue; + + page = pfn_to_page(pfn); + + /* Catch situations where free pages have a bad ->order */ + if (page->order >= 0 && PageBuddy(page)) + printk(KERN_WARNING + "PageOwner info inaccurate for PFN %lu\n", + pfn); + + /* Stop search if page is allocated and has trace info */ + if (page->order >= 0 && page->trace[0]) { + //intk("stopped search at pfn: %ld\n", pfn); + break; + } + } + + if (!pfn_valid(pfn)) + return 0; + /* + * If memory does not end at a SECTION_SIZE boundary, then + * we might have a pfn_valid() above max_pfn + */ + if (pfn >= max_pfn) + return 0; + + /* Record the next PFN to read in the file offset */ + *ppos = (pfn - min_low_pfn) + 1; + + kbuf = kmalloc(count, GFP_KERNEL); + if (!kbuf) + return -ENOMEM; + + //printk("page: %p\n", page); + ret = snprintf(kbuf, count, "Page allocated via order %d, mask 0x%x\n", + page->order, page->gfp_mask); + if (ret >= count) { + ret = -ENOMEM; + goto out; + } + + /* Print information relevant to grouping pages by mobility */ + blocktype = get_pageblock_migratetype(page); + pagetype = allocflags_to_migratetype(page->gfp_mask); + ret += snprintf(kbuf+ret, count-ret, + "PFN %lu Block %lu type %d %s " + "Flags %s%s%s%s%s%s%s%s%s%s%s%s\n", + pfn, + pfn >> pageblock_order, + blocktype, + blocktype != pagetype ? "Fallback" : " ", + PageLocked(page) ? "K" : " ", + PageError(page) ? "E" : " ", + PageReferenced(page) ? "R" : " ", + PageUptodate(page) ? "U" : " ", + PageDirty(page) ? "D" : " ", + PageLRU(page) ? "L" : " ", + PageActive(page) ? "A" : " ", + PageSlab(page) ? "S" : " ", + PageWriteback(page) ? "W" : " ", + PageCompound(page) ? "C" : " ", + PageSwapCache(page) ? "B" : " ", + PageMappedToDisk(page) ? "M" : " "); + if (ret >= count) { + ret = -ENOMEM; + goto out; + } + + num_written = ret; + + for (i = 0; i < 8; i++) { + if (!page->trace[i]) + break; + symname = kallsyms_lookup(page->trace[i], &symsize, &offset, + &modname, namebuf); + ret = snprintf(kbuf + num_written, count - num_written, + "[0x%lx] %s+%lu\n", + page->trace[i], namebuf, offset); + if (ret >= count - num_written) { + ret = -ENOMEM; + goto out; + } + num_written += ret; + } + + ret = snprintf(kbuf + num_written, count - num_written, "\n"); + if (ret >= count - num_written) { + ret = -ENOMEM; + goto out; + } + + num_written += ret; + ret = num_written; + + if (copy_to_user(buf, kbuf, ret)) + ret = -EFAULT; +out: + kfree(kbuf); + return ret; +} + +static struct file_operations proc_page_owner_operations = { + .read = read_page_owner, +}; + +static int __init pageowner_init(void) +{ + struct dentry *dentry; + + dentry = debugfs_create_file("page_owner", S_IRUSR, NULL, + NULL, &proc_page_owner_operations); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + return 0; +} +module_init(pageowner_init) diff -puN mm/vmstat.c~debugging-keep-track-of-page-owners mm/vmstat.c --- a/mm/vmstat.c~debugging-keep-track-of-page-owners +++ a/mm/vmstat.c @@ -19,6 +19,7 @@ #include <linux/math64.h> #include <linux/writeback.h> #include <linux/compaction.h> +#include "internal.h" #ifdef CONFIG_VM_EVENT_COUNTERS DEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}}; @@ -930,6 +931,97 @@ static int pagetypeinfo_showblockcount(s return 0; } +#ifdef CONFIG_PAGE_OWNER +static void pagetypeinfo_showmixedcount_print(struct seq_file *m, + pg_data_t *pgdat, + struct zone *zone) +{ + int mtype, pagetype; + unsigned long pfn; + unsigned long start_pfn = zone->zone_start_pfn; + unsigned long end_pfn = start_pfn + zone->spanned_pages; + unsigned long count[MIGRATE_TYPES] = { 0, }; + + /* Align PFNs to pageblock_nr_pages boundary */ + pfn = start_pfn & ~(pageblock_nr_pages-1); + + /* + * Walk the zone in pageblock_nr_pages steps. If a page block spans + * a zone boundary, it will be double counted between zones. This does + * not matter as the mixed block count will still be correct + */ + for (; pfn < end_pfn; pfn += pageblock_nr_pages) { + struct page *page; + unsigned long offset = 0; + + /* Do not read before the zone start, use a valid page */ + if (pfn < start_pfn) + offset = start_pfn - pfn; + + if (!pfn_valid(pfn + offset)) + continue; + + page = pfn_to_page(pfn + offset); + mtype = get_pageblock_migratetype(page); + + /* Check the block for bad migrate types */ + for (; offset < pageblock_nr_pages; offset++) { + /* Do not past the end of the zone */ + if (pfn + offset >= end_pfn) + break; + + if (!pfn_valid_within(pfn + offset)) + continue; + + page = pfn_to_page(pfn + offset); + + /* Skip free pages */ + if (PageBuddy(page)) { + offset += (1UL << page_order(page)) - 1UL; + continue; + } + if (page->order < 0) + continue; + + pagetype = allocflags_to_migratetype(page->gfp_mask); + if (pagetype != mtype) { + count[mtype]++; + break; + } + + /* Move to end of this allocation */ + offset += (1 << page->order) - 1; + } + } + + /* Print counts */ + seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name); + for (mtype = 0; mtype < MIGRATE_TYPES; mtype++) + seq_printf(m, "%12lu ", count[mtype]); + seq_putc(m, '\n'); +} +#endif /* CONFIG_PAGE_OWNER */ + +/* + * Print out the number of pageblocks for each migratetype that contain pages + * of other types. This gives an indication of how well fallbacks are being + * contained by rmqueue_fallback(). It requires information from PAGE_OWNER + * to determine what is going on + */ +static void pagetypeinfo_showmixedcount(struct seq_file *m, pg_data_t *pgdat) +{ +#ifdef CONFIG_PAGE_OWNER + int mtype; + + seq_printf(m, "\n%-23s", "Number of mixed blocks "); + for (mtype = 0; mtype < MIGRATE_TYPES; mtype++) + seq_printf(m, "%12s ", migratetype_names[mtype]); + seq_putc(m, '\n'); + + walk_zones_in_node(m, pgdat, pagetypeinfo_showmixedcount_print); +#endif /* CONFIG_PAGE_OWNER */ +} + /* * This prints out statistics in relation to grouping pages by mobility. * It is expensive to collect so do not constantly read the file. @@ -947,6 +1039,7 @@ static int pagetypeinfo_show(struct seq_ seq_putc(m, '\n'); pagetypeinfo_showfree(m, pgdat); pagetypeinfo_showblockcount(m, pgdat); + pagetypeinfo_showmixedcount(m, pgdat); return 0; } _ Patches currently in -mm which might be from alexn@xxxxxxxxx are debugging-keep-track-of-page-owners.patch -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html