Tracing fixes: - Fix a deadloop in reading trace_pipe that was caused by a mismatch between ring_buffer_empty() returning false which then asked to read the data, but the read code uses rb_num_of_entries() that returned zero, and causing an infinite "retry".
- Fix a warning caused by not using all pages allocated to store ftrace functions, where this can happen if the linker inserts a bunch of "NULL" entries, causing the accounting of how many pages needed to be off.
Zheng Yejian (2): ring-buffer: Fix deadloop issue on reading trace_pipe ftrace: Fix possible warning on checking all pages used in ftrace_process_locs()
kernel/trace/ftrace.c | 41 +++++++++++++++++++++++++++----------- kernel/trace/ring_buffer.c | 24 +++++++++++++--------- 2 files changed, 44 insertions(+), 21 deletions(-)
mainline inclusion from mainline-v6.5-rc2 commit 7e42907f3a7b4ce3a2d1757f6d78336984daf8f5 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7KXY9 CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
---------------------------
Soft lockup occurs when reading file 'trace_pipe':
watchdog: BUG: soft lockup - CPU#6 stuck for 22s! [cat:4488] [...] RIP: 0010:ring_buffer_empty_cpu+0xed/0x170 RSP: 0018:ffff88810dd6fc48 EFLAGS: 00000246 RAX: 0000000000000000 RBX: 0000000000000246 RCX: ffffffff93d1aaeb RDX: ffff88810a280040 RSI: 0000000000000008 RDI: ffff88811164b218 RBP: ffff88811164b218 R08: 0000000000000000 R09: ffff88815156600f R10: ffffed102a2acc01 R11: 0000000000000001 R12: 0000000051651901 R13: 0000000000000000 R14: ffff888115e49500 R15: 0000000000000000 [...] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f8d853c2000 CR3: 000000010dcd8000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: __find_next_entry+0x1a8/0x4b0 ? peek_next_entry+0x250/0x250 ? down_write+0xa5/0x120 ? down_write_killable+0x130/0x130 trace_find_next_entry_inc+0x3b/0x1d0 tracing_read_pipe+0x423/0xae0 ? tracing_splice_read_pipe+0xcb0/0xcb0 vfs_read+0x16b/0x490 ksys_read+0x105/0x210 ? __ia32_sys_pwrite64+0x200/0x200 ? switch_fpu_return+0x108/0x220 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x61/0xc6
Through the vmcore, I found it's because in tracing_read_pipe(), ring_buffer_empty_cpu() found some buffer is not empty but then it cannot read anything due to "rb_num_of_entries() == 0" always true, Then it infinitely loop the procedure due to user buffer not been filled, see following code path:
tracing_read_pipe() { ... ... waitagain: tracing_wait_pipe() // 1. find non-empty buffer here trace_find_next_entry_inc() // 2. loop here try to find an entry __find_next_entry() ring_buffer_empty_cpu(); // 3. find non-empty buffer peek_next_entry() // 4. but peek always return NULL ring_buffer_peek() rb_buffer_peek() rb_get_reader_page() // 5. because rb_num_of_entries() == 0 always true here // then return NULL // 6. user buffer not been filled so goto 'waitgain' // and eventually leads to an deadloop in kernel!!! }
By some analyzing, I found that when resetting ringbuffer, the 'entries' of its pages are not all cleared (see rb_reset_cpu()). Then when reducing the ringbuffer, and if some reduced pages exist dirty 'entries' data, they will be added into 'cpu_buffer->overrun' (see rb_remove_pages()), which cause wrong 'overrun' count and eventually cause the deadloop issue.
To fix it, we need to clear every pages in rb_reset_cpu().
Link: https://lore.kernel.org/linux-trace-kernel/20230708225144.3785600-1-zhengyej...
Cc: stable@vger.kernel.org Fixes: a5fb833172eca ("ring-buffer: Fix uninitialized read_stamp") Signed-off-by: Zheng Yejian zhengyejian1@huawei.com Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org --- kernel/trace/ring_buffer.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-)
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 3f098e32a7df..176777060349 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -4407,28 +4407,34 @@ unsigned long ring_buffer_size(struct ring_buffer *buffer, int cpu) } EXPORT_SYMBOL_GPL(ring_buffer_size);
+static void rb_clear_buffer_page(struct buffer_page *page) +{ + local_set(&page->write, 0); + local_set(&page->entries, 0); + rb_init_page(page->page); + page->read = 0; +} + static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) { + struct buffer_page *page; + rb_head_page_deactivate(cpu_buffer);
cpu_buffer->head_page = list_entry(cpu_buffer->pages, struct buffer_page, list); - local_set(&cpu_buffer->head_page->write, 0); - local_set(&cpu_buffer->head_page->entries, 0); - local_set(&cpu_buffer->head_page->page->commit, 0); - - cpu_buffer->head_page->read = 0; + rb_clear_buffer_page(cpu_buffer->head_page); + list_for_each_entry(page, cpu_buffer->pages, list) { + rb_clear_buffer_page(page); + }
cpu_buffer->tail_page = cpu_buffer->head_page; cpu_buffer->commit_page = cpu_buffer->head_page;
INIT_LIST_HEAD(&cpu_buffer->reader_page->list); INIT_LIST_HEAD(&cpu_buffer->new_pages); - local_set(&cpu_buffer->reader_page->write, 0); - local_set(&cpu_buffer->reader_page->entries, 0); - local_set(&cpu_buffer->reader_page->page->commit, 0); - cpu_buffer->reader_page->read = 0; + rb_clear_buffer_page(cpu_buffer->reader_page);
local_set(&cpu_buffer->entries_bytes, 0); local_set(&cpu_buffer->overrun, 0);
mainline inclusion from mainline-v6.5-rc2 commit 26efd79c4624294e553aeaa3439c646729bad084 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7KYPM CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
--------------------------------
As comments in ftrace_process_locs(), there may be NULL pointers in mcount_loc section:
Some architecture linkers will pad between the different mcount_loc sections of different object files to satisfy alignments. Skip any NULL pointers.
After commit 20e5227e9f55 ("ftrace: allow NULL pointers in mcount_loc"), NULL pointers will be accounted when allocating ftrace pages but skipped before adding into ftrace pages, this may result in some pages not being used. Then after commit 706c81f87f84 ("ftrace: Remove extra helper functions"), warning may occur at: WARN_ON(pg->next);
To fix it, only warn for case that no pointers skipped but pages not used up, then free those unused pages after releasing ftrace_lock.
Link: https://lore.kernel.org/linux-trace-kernel/20230712060452.3175675-1-zhengyej...
Cc: stable@vger.kernel.org Fixes: 706c81f87f84 ("ftrace: Remove extra helper functions") Suggested-by: Steven Rostedt rostedt@goodmis.org Signed-off-by: Zheng Yejian zhengyejian1@huawei.com Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org --- kernel/trace/ftrace.c | 41 +++++++++++++++++++++++++++++------------ 1 file changed, 29 insertions(+), 12 deletions(-)
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index e6aa32a27149..3ea4c9fa8b57 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3048,12 +3048,25 @@ static int ftrace_allocate_records(struct ftrace_page *pg, int count) return cnt; }
+static void ftrace_free_pages(struct ftrace_page *pages) +{ + struct ftrace_page *pg = pages; + int order; + + while (pg) { + order = get_count_order(pg->size / ENTRIES_PER_PAGE); + free_pages((unsigned long)pg->records, order); + pages = pg->next; + kfree(pg); + pg = pages; + } +} + static struct ftrace_page * ftrace_allocate_pages(unsigned long num_to_init) { struct ftrace_page *start_pg; struct ftrace_page *pg; - int order; int cnt;
if (!num_to_init) @@ -3087,14 +3100,7 @@ ftrace_allocate_pages(unsigned long num_to_init) return start_pg;
free_pages: - pg = start_pg; - while (pg) { - order = get_count_order(pg->size / ENTRIES_PER_PAGE); - free_pages((unsigned long)pg->records, order); - start_pg = pg->next; - kfree(pg); - pg = start_pg; - } + ftrace_free_pages(start_pg); pr_info("ftrace: FAILED to allocate memory for functions\n"); return NULL; } @@ -5575,9 +5581,11 @@ static int ftrace_process_locs(struct module *mod, unsigned long *start, unsigned long *end) { + struct ftrace_page *pg_unuse = NULL; struct ftrace_page *start_pg; struct ftrace_page *pg; struct dyn_ftrace *rec; + unsigned long skipped = 0; unsigned long count; unsigned long *p; unsigned long addr; @@ -5630,8 +5638,10 @@ static int ftrace_process_locs(struct module *mod, * object files to satisfy alignments. * Skip any NULL pointers. */ - if (!addr) + if (!addr) { + skipped++; continue; + }
if (pg->index == pg->size) { /* We should have allocated enough */ @@ -5644,8 +5654,10 @@ static int ftrace_process_locs(struct module *mod, rec->ip = addr; }
- /* We should have used all pages */ - WARN_ON(pg->next); + if (pg->next) { + pg_unuse = pg->next; + pg->next = NULL; + }
/* Assign the last page to ftrace_pages */ ftrace_pages = pg; @@ -5667,6 +5679,11 @@ static int ftrace_process_locs(struct module *mod, out: mutex_unlock(&ftrace_lock);
+ /* We should have used all pages unless we skipped some */ + if (pg_unuse) { + WARN_ON(!skipped); + ftrace_free_pages(pg_unuse); + } return ret; }
反馈： 您发送到kernel@openeuler.org的补丁/补丁集，已成功转换为PR！ PR链接地址： https://gitee.com/openeuler/kernel/pulls/1451 邮件列表地址：https://mailweb.openeuler.org/hyperkitty/list/kernel@openeuler.org/message/S...
FeedBack: The patch(es) which you have sent to kernel@openeuler.org mailing list has been converted to a pull request successfully! Pull request link: https://gitee.com/openeuler/kernel/pulls/1451 Mailing list address: https://mailweb.openeuler.org/hyperkitty/list/kernel@openeuler.org/message/S...
-
patchwork bot -
Zheng Yejian