From 12bc915ee149ac31d17c513edc7303660d024239 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 1 Mar 2013 17:34:49 +0100 Subject: [PATCH] perf: Fix vmalloc ring buffer free function If we allocate perf ring buffer with the size of single page, we will get memory corruption when releasing it. It's caused by rb_free_work function (CONFIG_PERF_USE_VMALLOC option). For single page sized ring buffer the page_order is -1 (because nr_pages is 0). This needs to be recognized in the rb_free_work function to release proper amount of pages. Introducing page_nr function (CONFIG_PERF_USE_VMALLOC only) that returns number of allocated pages. Using it in rb_free_work and perf_mmap_to_page functions. Also setting rb->nr_pages to 0 in case we have only user page allocated, which will fail perf_output_begin function and prevents sample storage. Reported-by: Jan Stancek Signed-off-by: Jiri Olsa Cc: Corey Ashford Cc: Frederic Weisbecker Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: "David S. Miller" Cc: Linus Torvalds Cc: Thomas Gleixner Cc: Andrew Morton Link: http://lkml.kernel.org/r/1362155689-13719-1-git-send-email-jolsa@redhat.com Signed-off-by: Ingo Molnar --- kernel/events/ring_buffer.c | 40 ++++++++++++++++++++++++++++++------- 1 file changed, 33 insertions(+), 7 deletions(-) diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 23cb34ff3973..a8021513cb39 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -154,7 +154,8 @@ int perf_output_begin(struct perf_output_handle *handle, if (head - local_read(&rb->wakeup) > rb->watermark) local_add(rb->watermark, &rb->wakeup); - handle->page = offset >> (PAGE_SHIFT + page_order(rb)); + /* page is allways 0 for CONFIG_PERF_USE_VMALLOC option */ + handle->page = offset >> PAGE_SHIFT; handle->page &= rb->nr_pages - 1; handle->size = offset & ((PAGE_SIZE << page_order(rb)) - 1); handle->addr = rb->data_pages[handle->page]; @@ -312,11 +313,21 @@ void rb_free(struct ring_buffer *rb) } #else +/* + * Returns the total number of pages allocated + * by ring buffer including the user page. + */ +static int page_nr(struct ring_buffer *rb) +{ + return page_order(rb) == -1 ? + 1 : /* no data, just user page */ + 1 + (1 << page_order(rb)); /* user page + data pages */ +} struct page * perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff) { - if (pgoff > (1UL << page_order(rb))) + if (pgoff > page_nr(rb)) return NULL; return vmalloc_to_page((void *)rb->user_page + pgoff * PAGE_SIZE); @@ -336,10 +347,10 @@ static void rb_free_work(struct work_struct *work) int i, nr; rb = container_of(work, struct ring_buffer, work); - nr = 1 << page_order(rb); + nr = page_nr(rb); base = rb->user_page; - for (i = 0; i < nr + 1; i++) + for (i = 0; i < nr; i++) perf_mmap_unmark_page(base + (i * PAGE_SIZE)); vfree(base); @@ -371,9 +382,24 @@ struct ring_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags) goto fail_all_buf; rb->user_page = all_buf; - rb->data_pages[0] = all_buf + PAGE_SIZE; - rb->page_order = ilog2(nr_pages); - rb->nr_pages = 1; + + /* + * For special case nr_pages == 0 we have + * only the user page mmaped plus: + * + * rb->data_pages[0] = NULL + * rb->nr_pages = 0 + * rb->page_order = -1 + * + * The perf_output_begin function is guarded + * by (rb->nr_pages > 0) condition, so no + * output code touches above setup if we + * have only user page allocated. + */ + + rb->data_pages[0] = nr_pages ? all_buf + PAGE_SIZE : NULL; + rb->nr_pages = nr_pages ? 1 : 0; + rb->page_order = ilog2(nr_pages); ring_buffer_init(rb, watermark, flags); -- 2.39.5