October 2023 - Linux-stable-mirror

FAILED: patch "[PATCH] btrfs: don't clear uptodate on write errors" failed to apply to 6.5-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.5-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.5.y git checkout FETCH_HEAD git cherry-pick -x b595d25996329427b2c09d4b90395a165fb3ef8e # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100400-garbage-caboose-c859@gregkh' --subject-prefix 'PATCH 6.5.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From b595d25996329427b2c09d4b90395a165fb3ef8e Mon Sep 17 00:00:00 2001 From: Josef Bacik <josef(a)toxicpanda.com> Date: Fri, 8 Sep 2023 15:31:39 -0400 Subject: [PATCH] btrfs: don't clear uptodate on write errors We have been consistently seeing hangs with generic/648 in our subpage GitHub CI setup. This is a classic deadlock, we are calling btrfs_read_folio() on a folio, which requires holding the folio lock on the folio, and then finding a ordered extent that overlaps that range and calling btrfs_start_ordered_extent(), which then tries to write out the dirty page, which requires taking the folio lock and then we deadlock. The hang happens because we're writing to range [1271750656, 1271767040), page index [77621, 77622], and page 77621 is !Uptodate. It is also Dirty, so we call btrfs_read_folio() for 77621 and which does btrfs_lock_and_flush_ordered_range() for that range, and we find an ordered extent which is [1271644160, 1271746560), page index [77615, 77621]. The page indexes overlap, but the actual bytes don't overlap. We're holding the page lock for 77621, then call btrfs_lock_and_flush_ordered_range() which tries to flush the dirty page, and tries to lock 77621 again and then we deadlock. The byte ranges do not overlap, but with subpage support if we clear uptodate on any portion of the page we mark the entire thing as not uptodate. We have been clearing page uptodate on write errors, but no other file system does this, and is in fact incorrect. This doesn't hurt us in the !subpage case because we can't end up with overlapped ranges that don't also overlap on the page. Fix this by not clearing uptodate when we have a write error. The only thing we should be doing in this case is setting the mapping error and carrying on. This makes it so we would no longer call btrfs_read_folio() on the page as it's uptodate and eliminates the deadlock. With this patch we're now able to make it through a full fstests run on our subpage blocksize VMs. Note for stable backports: this probably goes beyond 6.1 but the code has been cleaned up and clearing the uptodate bit must be verified on each version independently. CC: stable(a)vger.kernel.org # 6.1+ Reviewed-by: Qu Wenruo <wqu(a)suse.com> Signed-off-by: Josef Bacik <josef(a)toxicpanda.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index ac3fca5a5e41..6954ae763b86 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -484,10 +484,8 @@ static void end_bio_extent_writepage(struct btrfs_bio *bbio) bvec->bv_offset, bvec->bv_len); btrfs_finish_ordered_extent(bbio->ordered, page, start, len, !error); - if (error) { - btrfs_page_clear_uptodate(fs_info, page, start, len); + if (error) mapping_set_error(page->mapping, error); - } btrfs_page_clear_writeback(fs_info, page, start, len); } @@ -1456,8 +1454,6 @@ static int __extent_writepage(struct page *page, struct btrfs_bio_ctrl *bio_ctrl if (ret) { btrfs_mark_ordered_io_finished(BTRFS_I(inode), page, page_start, PAGE_SIZE, !ret); - btrfs_page_clear_uptodate(btrfs_sb(inode->i_sb), page, - page_start, PAGE_SIZE); mapping_set_error(page->mapping, ret); } unlock_page(page); @@ -1624,8 +1620,6 @@ static void extent_buffer_write_end_io(struct btrfs_bio *bbio) struct page *page = bvec->bv_page; u32 len = bvec->bv_len; - if (!uptodate) - btrfs_page_clear_uptodate(fs_info, page, start, len); btrfs_page_clear_writeback(fs_info, page, start, len); bio_offset += len; } @@ -2201,7 +2195,6 @@ void extent_write_locked_range(struct inode *inode, struct page *locked_page, if (ret) { btrfs_mark_ordered_io_finished(BTRFS_I(inode), page, cur, cur_len, !ret); - btrfs_page_clear_uptodate(fs_info, page, cur, cur_len); mapping_set_error(page->mapping, ret); } btrfs_page_unlock_writer(fs_info, page, cur, cur_len); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index e211e88c6545..616fdcf40467 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1085,9 +1085,6 @@ static void submit_uncompressed_range(struct btrfs_inode *inode, btrfs_mark_ordered_io_finished(inode, locked_page, page_start, PAGE_SIZE, !ret); - btrfs_page_clear_uptodate(inode->root->fs_info, - locked_page, page_start, - PAGE_SIZE); mapping_set_error(locked_page->mapping, ret); unlock_page(locked_page); } @@ -2791,7 +2788,6 @@ static void btrfs_writepage_fixup_worker(struct btrfs_work *work) mapping_set_error(page->mapping, ret); btrfs_mark_ordered_io_finished(inode, page, page_start, PAGE_SIZE, !ret); - btrfs_page_clear_uptodate(fs_info, page, page_start, PAGE_SIZE); clear_page_dirty_for_io(page); } btrfs_page_clear_checked(fs_info, page, page_start, PAGE_SIZE);

2 years, 1 month

1
0
0 0

FAILED: patch "[PATCH] ring-buffer: Fix bytes info in per_cpu buffer stats" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.14.y git checkout FETCH_HEAD git cherry-pick -x 45d99ea451d0c30bfd4864f0fe485d7dac014902 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100440-armory-unbalance-bd33@gregkh' --subject-prefix 'PATCH 4.14.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 45d99ea451d0c30bfd4864f0fe485d7dac014902 Mon Sep 17 00:00:00 2001 From: Zheng Yejian <zhengyejian1(a)huawei.com> Date: Thu, 21 Sep 2023 20:54:25 +0800 Subject: [PATCH] ring-buffer: Fix bytes info in per_cpu buffer stats The 'bytes' info in file 'per_cpu/cpu<X>/stats' means the number of bytes in cpu buffer that have not been consumed. However, currently after consuming data by reading file 'trace_pipe', the 'bytes' info was not changed as expected. # cat per_cpu/cpu0/stats entries: 0 overrun: 0 commit overrun: 0 bytes: 568 <--- 'bytes' is problematical !!! oldest event ts: 8651.371479 now ts: 8653.912224 dropped events: 0 read events: 8 The root cause is incorrect stat on cpu_buffer->read_bytes. To fix it: 1. When stat 'read_bytes', account consumed event in rb_advance_reader(); 2. When stat 'entries_bytes', exclude the discarded padding event which is smaller than minimum size because it is invisible to reader. Then use rb_page_commit() instead of BUF_PAGE_SIZE at where accounting for page-based read/remove/overrun. Also correct the comments of ring_buffer_bytes_cpu() in this patch. Link: https://lore.kernel.org/linux-trace-kernel/20230921125425.1708423-1-zhengye… Cc: stable(a)vger.kernel.org Fixes: c64e148a3be3 ("trace: Add ring buffer stats to measure rate of events") Signed-off-by: Zheng Yejian <zhengyejian1(a)huawei.com> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index a1651edc48d5..28daf0ce95c5 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -354,6 +354,11 @@ static void rb_init_page(struct buffer_data_page *bpage) local_set(&bpage->commit, 0); } +static __always_inline unsigned int rb_page_commit(struct buffer_page *bpage) +{ + return local_read(&bpage->page->commit); +} + static void free_buffer_page(struct buffer_page *bpage) { free_page((unsigned long)bpage->page); @@ -2003,7 +2008,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages) * Increment overrun to account for the lost events. */ local_add(page_entries, &cpu_buffer->overrun); - local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); + local_sub(rb_page_commit(to_remove_page), &cpu_buffer->entries_bytes); local_inc(&cpu_buffer->pages_lost); } @@ -2367,11 +2372,6 @@ rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->reader_page->read); } -static __always_inline unsigned rb_page_commit(struct buffer_page *bpage) -{ - return local_read(&bpage->page->commit); -} - static struct ring_buffer_event * rb_iter_head_event(struct ring_buffer_iter *iter) { @@ -2517,7 +2517,7 @@ rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer, * the counters. */ local_add(entries, &cpu_buffer->overrun); - local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); + local_sub(rb_page_commit(next_page), &cpu_buffer->entries_bytes); local_inc(&cpu_buffer->pages_lost); /* @@ -2660,9 +2660,6 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, event = __rb_page_index(tail_page, tail); - /* account for padding bytes */ - local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes); - /* * Save the original length to the meta data. * This will be used by the reader to add lost event @@ -2676,7 +2673,8 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, * write counter enough to allow another writer to slip * in on this page. * We put in a discarded commit instead, to make sure - * that this space is not used again. + * that this space is not used again, and this space will + * not be accounted into 'entries_bytes'. * * If we are less than the minimum size, we don't need to * worry about it. @@ -2701,6 +2699,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, /* time delta must be non zero */ event->time_delta = 1; + /* account for padding bytes */ + local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes); + /* Make sure the padding is visible before the tail_page->write update */ smp_wmb(); @@ -4215,7 +4216,7 @@ u64 ring_buffer_oldest_event_ts(struct trace_buffer *buffer, int cpu) EXPORT_SYMBOL_GPL(ring_buffer_oldest_event_ts); /** - * ring_buffer_bytes_cpu - get the number of bytes consumed in a cpu buffer + * ring_buffer_bytes_cpu - get the number of bytes unconsumed in a cpu buffer * @buffer: The ring buffer * @cpu: The per CPU buffer to read from. */ @@ -4723,6 +4724,7 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer) length = rb_event_length(event); cpu_buffer->reader_page->read += length; + cpu_buffer->read_bytes += length; } static void rb_advance_iter(struct ring_buffer_iter *iter) @@ -5816,7 +5818,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer, } else { /* update the entry counter */ cpu_buffer->read += rb_page_entries(reader); - cpu_buffer->read_bytes += BUF_PAGE_SIZE; + cpu_buffer->read_bytes += rb_page_commit(reader); /* swap the pages */ rb_init_page(bpage);

2 years, 1 month

1
0
0 0

FAILED: patch "[PATCH] ring-buffer: Fix bytes info in per_cpu buffer stats" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y git checkout FETCH_HEAD git cherry-pick -x 45d99ea451d0c30bfd4864f0fe485d7dac014902 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100438-palpable-marina-68c8@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 45d99ea451d0c30bfd4864f0fe485d7dac014902 Mon Sep 17 00:00:00 2001 From: Zheng Yejian <zhengyejian1(a)huawei.com> Date: Thu, 21 Sep 2023 20:54:25 +0800 Subject: [PATCH] ring-buffer: Fix bytes info in per_cpu buffer stats The 'bytes' info in file 'per_cpu/cpu<X>/stats' means the number of bytes in cpu buffer that have not been consumed. However, currently after consuming data by reading file 'trace_pipe', the 'bytes' info was not changed as expected. # cat per_cpu/cpu0/stats entries: 0 overrun: 0 commit overrun: 0 bytes: 568 <--- 'bytes' is problematical !!! oldest event ts: 8651.371479 now ts: 8653.912224 dropped events: 0 read events: 8 The root cause is incorrect stat on cpu_buffer->read_bytes. To fix it: 1. When stat 'read_bytes', account consumed event in rb_advance_reader(); 2. When stat 'entries_bytes', exclude the discarded padding event which is smaller than minimum size because it is invisible to reader. Then use rb_page_commit() instead of BUF_PAGE_SIZE at where accounting for page-based read/remove/overrun. Also correct the comments of ring_buffer_bytes_cpu() in this patch. Link: https://lore.kernel.org/linux-trace-kernel/20230921125425.1708423-1-zhengye… Cc: stable(a)vger.kernel.org Fixes: c64e148a3be3 ("trace: Add ring buffer stats to measure rate of events") Signed-off-by: Zheng Yejian <zhengyejian1(a)huawei.com> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index a1651edc48d5..28daf0ce95c5 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -354,6 +354,11 @@ static void rb_init_page(struct buffer_data_page *bpage) local_set(&bpage->commit, 0); } +static __always_inline unsigned int rb_page_commit(struct buffer_page *bpage) +{ + return local_read(&bpage->page->commit); +} + static void free_buffer_page(struct buffer_page *bpage) { free_page((unsigned long)bpage->page); @@ -2003,7 +2008,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages) * Increment overrun to account for the lost events. */ local_add(page_entries, &cpu_buffer->overrun); - local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); + local_sub(rb_page_commit(to_remove_page), &cpu_buffer->entries_bytes); local_inc(&cpu_buffer->pages_lost); } @@ -2367,11 +2372,6 @@ rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->reader_page->read); } -static __always_inline unsigned rb_page_commit(struct buffer_page *bpage) -{ - return local_read(&bpage->page->commit); -} - static struct ring_buffer_event * rb_iter_head_event(struct ring_buffer_iter *iter) { @@ -2517,7 +2517,7 @@ rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer, * the counters. */ local_add(entries, &cpu_buffer->overrun); - local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); + local_sub(rb_page_commit(next_page), &cpu_buffer->entries_bytes); local_inc(&cpu_buffer->pages_lost); /* @@ -2660,9 +2660,6 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, event = __rb_page_index(tail_page, tail); - /* account for padding bytes */ - local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes); - /* * Save the original length to the meta data. * This will be used by the reader to add lost event @@ -2676,7 +2673,8 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, * write counter enough to allow another writer to slip * in on this page. * We put in a discarded commit instead, to make sure - * that this space is not used again. + * that this space is not used again, and this space will + * not be accounted into 'entries_bytes'. * * If we are less than the minimum size, we don't need to * worry about it. @@ -2701,6 +2699,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, /* time delta must be non zero */ event->time_delta = 1; + /* account for padding bytes */ + local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes); + /* Make sure the padding is visible before the tail_page->write update */ smp_wmb(); @@ -4215,7 +4216,7 @@ u64 ring_buffer_oldest_event_ts(struct trace_buffer *buffer, int cpu) EXPORT_SYMBOL_GPL(ring_buffer_oldest_event_ts); /** - * ring_buffer_bytes_cpu - get the number of bytes consumed in a cpu buffer + * ring_buffer_bytes_cpu - get the number of bytes unconsumed in a cpu buffer * @buffer: The ring buffer * @cpu: The per CPU buffer to read from. */ @@ -4723,6 +4724,7 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer) length = rb_event_length(event); cpu_buffer->reader_page->read += length; + cpu_buffer->read_bytes += length; } static void rb_advance_iter(struct ring_buffer_iter *iter) @@ -5816,7 +5818,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer, } else { /* update the entry counter */ cpu_buffer->read += rb_page_entries(reader); - cpu_buffer->read_bytes += BUF_PAGE_SIZE; + cpu_buffer->read_bytes += rb_page_commit(reader); /* swap the pages */ rb_init_page(bpage);

2 years, 1 month

1
0
0 0

FAILED: patch "[PATCH] ring-buffer: Fix bytes info in per_cpu buffer stats" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x 45d99ea451d0c30bfd4864f0fe485d7dac014902 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100437-backyard-cartwheel-4b2f@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 45d99ea451d0c30bfd4864f0fe485d7dac014902 Mon Sep 17 00:00:00 2001 From: Zheng Yejian <zhengyejian1(a)huawei.com> Date: Thu, 21 Sep 2023 20:54:25 +0800 Subject: [PATCH] ring-buffer: Fix bytes info in per_cpu buffer stats The 'bytes' info in file 'per_cpu/cpu<X>/stats' means the number of bytes in cpu buffer that have not been consumed. However, currently after consuming data by reading file 'trace_pipe', the 'bytes' info was not changed as expected. # cat per_cpu/cpu0/stats entries: 0 overrun: 0 commit overrun: 0 bytes: 568 <--- 'bytes' is problematical !!! oldest event ts: 8651.371479 now ts: 8653.912224 dropped events: 0 read events: 8 The root cause is incorrect stat on cpu_buffer->read_bytes. To fix it: 1. When stat 'read_bytes', account consumed event in rb_advance_reader(); 2. When stat 'entries_bytes', exclude the discarded padding event which is smaller than minimum size because it is invisible to reader. Then use rb_page_commit() instead of BUF_PAGE_SIZE at where accounting for page-based read/remove/overrun. Also correct the comments of ring_buffer_bytes_cpu() in this patch. Link: https://lore.kernel.org/linux-trace-kernel/20230921125425.1708423-1-zhengye… Cc: stable(a)vger.kernel.org Fixes: c64e148a3be3 ("trace: Add ring buffer stats to measure rate of events") Signed-off-by: Zheng Yejian <zhengyejian1(a)huawei.com> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index a1651edc48d5..28daf0ce95c5 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -354,6 +354,11 @@ static void rb_init_page(struct buffer_data_page *bpage) local_set(&bpage->commit, 0); } +static __always_inline unsigned int rb_page_commit(struct buffer_page *bpage) +{ + return local_read(&bpage->page->commit); +} + static void free_buffer_page(struct buffer_page *bpage) { free_page((unsigned long)bpage->page); @@ -2003,7 +2008,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages) * Increment overrun to account for the lost events. */ local_add(page_entries, &cpu_buffer->overrun); - local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); + local_sub(rb_page_commit(to_remove_page), &cpu_buffer->entries_bytes); local_inc(&cpu_buffer->pages_lost); } @@ -2367,11 +2372,6 @@ rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->reader_page->read); } -static __always_inline unsigned rb_page_commit(struct buffer_page *bpage) -{ - return local_read(&bpage->page->commit); -} - static struct ring_buffer_event * rb_iter_head_event(struct ring_buffer_iter *iter) { @@ -2517,7 +2517,7 @@ rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer, * the counters. */ local_add(entries, &cpu_buffer->overrun); - local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); + local_sub(rb_page_commit(next_page), &cpu_buffer->entries_bytes); local_inc(&cpu_buffer->pages_lost); /* @@ -2660,9 +2660,6 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, event = __rb_page_index(tail_page, tail); - /* account for padding bytes */ - local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes); - /* * Save the original length to the meta data. * This will be used by the reader to add lost event @@ -2676,7 +2673,8 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, * write counter enough to allow another writer to slip * in on this page. * We put in a discarded commit instead, to make sure - * that this space is not used again. + * that this space is not used again, and this space will + * not be accounted into 'entries_bytes'. * * If we are less than the minimum size, we don't need to * worry about it. @@ -2701,6 +2699,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, /* time delta must be non zero */ event->time_delta = 1; + /* account for padding bytes */ + local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes); + /* Make sure the padding is visible before the tail_page->write update */ smp_wmb(); @@ -4215,7 +4216,7 @@ u64 ring_buffer_oldest_event_ts(struct trace_buffer *buffer, int cpu) EXPORT_SYMBOL_GPL(ring_buffer_oldest_event_ts); /** - * ring_buffer_bytes_cpu - get the number of bytes consumed in a cpu buffer + * ring_buffer_bytes_cpu - get the number of bytes unconsumed in a cpu buffer * @buffer: The ring buffer * @cpu: The per CPU buffer to read from. */ @@ -4723,6 +4724,7 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer) length = rb_event_length(event); cpu_buffer->reader_page->read += length; + cpu_buffer->read_bytes += length; } static void rb_advance_iter(struct ring_buffer_iter *iter) @@ -5816,7 +5818,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer, } else { /* update the entry counter */ cpu_buffer->read += rb_page_entries(reader); - cpu_buffer->read_bytes += BUF_PAGE_SIZE; + cpu_buffer->read_bytes += rb_page_commit(reader); /* swap the pages */ rb_init_page(bpage);

2 years, 1 month

1
0
0 0

FAILED: patch "[PATCH] ring-buffer: Fix bytes info in per_cpu buffer stats" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x 45d99ea451d0c30bfd4864f0fe485d7dac014902 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100436-ergonomic-enviably-bf14@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 45d99ea451d0c30bfd4864f0fe485d7dac014902 Mon Sep 17 00:00:00 2001 From: Zheng Yejian <zhengyejian1(a)huawei.com> Date: Thu, 21 Sep 2023 20:54:25 +0800 Subject: [PATCH] ring-buffer: Fix bytes info in per_cpu buffer stats The 'bytes' info in file 'per_cpu/cpu<X>/stats' means the number of bytes in cpu buffer that have not been consumed. However, currently after consuming data by reading file 'trace_pipe', the 'bytes' info was not changed as expected. # cat per_cpu/cpu0/stats entries: 0 overrun: 0 commit overrun: 0 bytes: 568 <--- 'bytes' is problematical !!! oldest event ts: 8651.371479 now ts: 8653.912224 dropped events: 0 read events: 8 The root cause is incorrect stat on cpu_buffer->read_bytes. To fix it: 1. When stat 'read_bytes', account consumed event in rb_advance_reader(); 2. When stat 'entries_bytes', exclude the discarded padding event which is smaller than minimum size because it is invisible to reader. Then use rb_page_commit() instead of BUF_PAGE_SIZE at where accounting for page-based read/remove/overrun. Also correct the comments of ring_buffer_bytes_cpu() in this patch. Link: https://lore.kernel.org/linux-trace-kernel/20230921125425.1708423-1-zhengye… Cc: stable(a)vger.kernel.org Fixes: c64e148a3be3 ("trace: Add ring buffer stats to measure rate of events") Signed-off-by: Zheng Yejian <zhengyejian1(a)huawei.com> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index a1651edc48d5..28daf0ce95c5 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -354,6 +354,11 @@ static void rb_init_page(struct buffer_data_page *bpage) local_set(&bpage->commit, 0); } +static __always_inline unsigned int rb_page_commit(struct buffer_page *bpage) +{ + return local_read(&bpage->page->commit); +} + static void free_buffer_page(struct buffer_page *bpage) { free_page((unsigned long)bpage->page); @@ -2003,7 +2008,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages) * Increment overrun to account for the lost events. */ local_add(page_entries, &cpu_buffer->overrun); - local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); + local_sub(rb_page_commit(to_remove_page), &cpu_buffer->entries_bytes); local_inc(&cpu_buffer->pages_lost); } @@ -2367,11 +2372,6 @@ rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->reader_page->read); } -static __always_inline unsigned rb_page_commit(struct buffer_page *bpage) -{ - return local_read(&bpage->page->commit); -} - static struct ring_buffer_event * rb_iter_head_event(struct ring_buffer_iter *iter) { @@ -2517,7 +2517,7 @@ rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer, * the counters. */ local_add(entries, &cpu_buffer->overrun); - local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); + local_sub(rb_page_commit(next_page), &cpu_buffer->entries_bytes); local_inc(&cpu_buffer->pages_lost); /* @@ -2660,9 +2660,6 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, event = __rb_page_index(tail_page, tail); - /* account for padding bytes */ - local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes); - /* * Save the original length to the meta data. * This will be used by the reader to add lost event @@ -2676,7 +2673,8 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, * write counter enough to allow another writer to slip * in on this page. * We put in a discarded commit instead, to make sure - * that this space is not used again. + * that this space is not used again, and this space will + * not be accounted into 'entries_bytes'. * * If we are less than the minimum size, we don't need to * worry about it. @@ -2701,6 +2699,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, /* time delta must be non zero */ event->time_delta = 1; + /* account for padding bytes */ + local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes); + /* Make sure the padding is visible before the tail_page->write update */ smp_wmb(); @@ -4215,7 +4216,7 @@ u64 ring_buffer_oldest_event_ts(struct trace_buffer *buffer, int cpu) EXPORT_SYMBOL_GPL(ring_buffer_oldest_event_ts); /** - * ring_buffer_bytes_cpu - get the number of bytes consumed in a cpu buffer + * ring_buffer_bytes_cpu - get the number of bytes unconsumed in a cpu buffer * @buffer: The ring buffer * @cpu: The per CPU buffer to read from. */ @@ -4723,6 +4724,7 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer) length = rb_event_length(event); cpu_buffer->reader_page->read += length; + cpu_buffer->read_bytes += length; } static void rb_advance_iter(struct ring_buffer_iter *iter) @@ -5816,7 +5818,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer, } else { /* update the entry counter */ cpu_buffer->read += rb_page_entries(reader); - cpu_buffer->read_bytes += BUF_PAGE_SIZE; + cpu_buffer->read_bytes += rb_page_commit(reader); /* swap the pages */ rb_init_page(bpage);

2 years, 1 month

1
0
0 0

FAILED: patch "[PATCH] ring-buffer: Fix bytes info in per_cpu buffer stats" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x 45d99ea451d0c30bfd4864f0fe485d7dac014902 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100434-majestic-daisy-4a02@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 45d99ea451d0c30bfd4864f0fe485d7dac014902 Mon Sep 17 00:00:00 2001 From: Zheng Yejian <zhengyejian1(a)huawei.com> Date: Thu, 21 Sep 2023 20:54:25 +0800 Subject: [PATCH] ring-buffer: Fix bytes info in per_cpu buffer stats The 'bytes' info in file 'per_cpu/cpu<X>/stats' means the number of bytes in cpu buffer that have not been consumed. However, currently after consuming data by reading file 'trace_pipe', the 'bytes' info was not changed as expected. # cat per_cpu/cpu0/stats entries: 0 overrun: 0 commit overrun: 0 bytes: 568 <--- 'bytes' is problematical !!! oldest event ts: 8651.371479 now ts: 8653.912224 dropped events: 0 read events: 8 The root cause is incorrect stat on cpu_buffer->read_bytes. To fix it: 1. When stat 'read_bytes', account consumed event in rb_advance_reader(); 2. When stat 'entries_bytes', exclude the discarded padding event which is smaller than minimum size because it is invisible to reader. Then use rb_page_commit() instead of BUF_PAGE_SIZE at where accounting for page-based read/remove/overrun. Also correct the comments of ring_buffer_bytes_cpu() in this patch. Link: https://lore.kernel.org/linux-trace-kernel/20230921125425.1708423-1-zhengye… Cc: stable(a)vger.kernel.org Fixes: c64e148a3be3 ("trace: Add ring buffer stats to measure rate of events") Signed-off-by: Zheng Yejian <zhengyejian1(a)huawei.com> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index a1651edc48d5..28daf0ce95c5 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -354,6 +354,11 @@ static void rb_init_page(struct buffer_data_page *bpage) local_set(&bpage->commit, 0); } +static __always_inline unsigned int rb_page_commit(struct buffer_page *bpage) +{ + return local_read(&bpage->page->commit); +} + static void free_buffer_page(struct buffer_page *bpage) { free_page((unsigned long)bpage->page); @@ -2003,7 +2008,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages) * Increment overrun to account for the lost events. */ local_add(page_entries, &cpu_buffer->overrun); - local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); + local_sub(rb_page_commit(to_remove_page), &cpu_buffer->entries_bytes); local_inc(&cpu_buffer->pages_lost); } @@ -2367,11 +2372,6 @@ rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->reader_page->read); } -static __always_inline unsigned rb_page_commit(struct buffer_page *bpage) -{ - return local_read(&bpage->page->commit); -} - static struct ring_buffer_event * rb_iter_head_event(struct ring_buffer_iter *iter) { @@ -2517,7 +2517,7 @@ rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer, * the counters. */ local_add(entries, &cpu_buffer->overrun); - local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); + local_sub(rb_page_commit(next_page), &cpu_buffer->entries_bytes); local_inc(&cpu_buffer->pages_lost); /* @@ -2660,9 +2660,6 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, event = __rb_page_index(tail_page, tail); - /* account for padding bytes */ - local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes); - /* * Save the original length to the meta data. * This will be used by the reader to add lost event @@ -2676,7 +2673,8 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, * write counter enough to allow another writer to slip * in on this page. * We put in a discarded commit instead, to make sure - * that this space is not used again. + * that this space is not used again, and this space will + * not be accounted into 'entries_bytes'. * * If we are less than the minimum size, we don't need to * worry about it. @@ -2701,6 +2699,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, /* time delta must be non zero */ event->time_delta = 1; + /* account for padding bytes */ + local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes); + /* Make sure the padding is visible before the tail_page->write update */ smp_wmb(); @@ -4215,7 +4216,7 @@ u64 ring_buffer_oldest_event_ts(struct trace_buffer *buffer, int cpu) EXPORT_SYMBOL_GPL(ring_buffer_oldest_event_ts); /** - * ring_buffer_bytes_cpu - get the number of bytes consumed in a cpu buffer + * ring_buffer_bytes_cpu - get the number of bytes unconsumed in a cpu buffer * @buffer: The ring buffer * @cpu: The per CPU buffer to read from. */ @@ -4723,6 +4724,7 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer) length = rb_event_length(event); cpu_buffer->reader_page->read += length; + cpu_buffer->read_bytes += length; } static void rb_advance_iter(struct ring_buffer_iter *iter) @@ -5816,7 +5818,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer, } else { /* update the entry counter */ cpu_buffer->read += rb_page_entries(reader); - cpu_buffer->read_bytes += BUF_PAGE_SIZE; + cpu_buffer->read_bytes += rb_page_commit(reader); /* swap the pages */ rb_init_page(bpage);

2 years, 1 month

1
0
0 0

FAILED: patch "[PATCH] ring-buffer: Fix bytes info in per_cpu buffer stats" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 45d99ea451d0c30bfd4864f0fe485d7dac014902 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100433-pumice-despise-a596@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 45d99ea451d0c30bfd4864f0fe485d7dac014902 Mon Sep 17 00:00:00 2001 From: Zheng Yejian <zhengyejian1(a)huawei.com> Date: Thu, 21 Sep 2023 20:54:25 +0800 Subject: [PATCH] ring-buffer: Fix bytes info in per_cpu buffer stats The 'bytes' info in file 'per_cpu/cpu<X>/stats' means the number of bytes in cpu buffer that have not been consumed. However, currently after consuming data by reading file 'trace_pipe', the 'bytes' info was not changed as expected. # cat per_cpu/cpu0/stats entries: 0 overrun: 0 commit overrun: 0 bytes: 568 <--- 'bytes' is problematical !!! oldest event ts: 8651.371479 now ts: 8653.912224 dropped events: 0 read events: 8 The root cause is incorrect stat on cpu_buffer->read_bytes. To fix it: 1. When stat 'read_bytes', account consumed event in rb_advance_reader(); 2. When stat 'entries_bytes', exclude the discarded padding event which is smaller than minimum size because it is invisible to reader. Then use rb_page_commit() instead of BUF_PAGE_SIZE at where accounting for page-based read/remove/overrun. Also correct the comments of ring_buffer_bytes_cpu() in this patch. Link: https://lore.kernel.org/linux-trace-kernel/20230921125425.1708423-1-zhengye… Cc: stable(a)vger.kernel.org Fixes: c64e148a3be3 ("trace: Add ring buffer stats to measure rate of events") Signed-off-by: Zheng Yejian <zhengyejian1(a)huawei.com> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index a1651edc48d5..28daf0ce95c5 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -354,6 +354,11 @@ static void rb_init_page(struct buffer_data_page *bpage) local_set(&bpage->commit, 0); } +static __always_inline unsigned int rb_page_commit(struct buffer_page *bpage) +{ + return local_read(&bpage->page->commit); +} + static void free_buffer_page(struct buffer_page *bpage) { free_page((unsigned long)bpage->page); @@ -2003,7 +2008,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages) * Increment overrun to account for the lost events. */ local_add(page_entries, &cpu_buffer->overrun); - local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); + local_sub(rb_page_commit(to_remove_page), &cpu_buffer->entries_bytes); local_inc(&cpu_buffer->pages_lost); } @@ -2367,11 +2372,6 @@ rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->reader_page->read); } -static __always_inline unsigned rb_page_commit(struct buffer_page *bpage) -{ - return local_read(&bpage->page->commit); -} - static struct ring_buffer_event * rb_iter_head_event(struct ring_buffer_iter *iter) { @@ -2517,7 +2517,7 @@ rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer, * the counters. */ local_add(entries, &cpu_buffer->overrun); - local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); + local_sub(rb_page_commit(next_page), &cpu_buffer->entries_bytes); local_inc(&cpu_buffer->pages_lost); /* @@ -2660,9 +2660,6 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, event = __rb_page_index(tail_page, tail); - /* account for padding bytes */ - local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes); - /* * Save the original length to the meta data. * This will be used by the reader to add lost event @@ -2676,7 +2673,8 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, * write counter enough to allow another writer to slip * in on this page. * We put in a discarded commit instead, to make sure - * that this space is not used again. + * that this space is not used again, and this space will + * not be accounted into 'entries_bytes'. * * If we are less than the minimum size, we don't need to * worry about it. @@ -2701,6 +2699,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, /* time delta must be non zero */ event->time_delta = 1; + /* account for padding bytes */ + local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes); + /* Make sure the padding is visible before the tail_page->write update */ smp_wmb(); @@ -4215,7 +4216,7 @@ u64 ring_buffer_oldest_event_ts(struct trace_buffer *buffer, int cpu) EXPORT_SYMBOL_GPL(ring_buffer_oldest_event_ts); /** - * ring_buffer_bytes_cpu - get the number of bytes consumed in a cpu buffer + * ring_buffer_bytes_cpu - get the number of bytes unconsumed in a cpu buffer * @buffer: The ring buffer * @cpu: The per CPU buffer to read from. */ @@ -4723,6 +4724,7 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer) length = rb_event_length(event); cpu_buffer->reader_page->read += length; + cpu_buffer->read_bytes += length; } static void rb_advance_iter(struct ring_buffer_iter *iter) @@ -5816,7 +5818,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer, } else { /* update the entry counter */ cpu_buffer->read += rb_page_entries(reader); - cpu_buffer->read_bytes += BUF_PAGE_SIZE; + cpu_buffer->read_bytes += rb_page_commit(reader); /* swap the pages */ rb_init_page(bpage);

2 years, 1 month

1
0
0 0

FAILED: patch "[PATCH] mm: mempolicy: keep VMA walk if both MPOL_MF_STRICT and" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.14.y git checkout FETCH_HEAD git cherry-pick -x 24526268f4e38c9ec0c4a30de4f37ad2a2a84e47 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100431-ascertain-evade-5e53@gregkh' --subject-prefix 'PATCH 4.14.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 24526268f4e38c9ec0c4a30de4f37ad2a2a84e47 Mon Sep 17 00:00:00 2001 From: Yang Shi <yang(a)os.amperecomputing.com> Date: Wed, 20 Sep 2023 15:32:42 -0700 Subject: [PATCH] mm: mempolicy: keep VMA walk if both MPOL_MF_STRICT and MPOL_MF_MOVE are specified When calling mbind() with MPOL_MF_{MOVE|MOVEALL} | MPOL_MF_STRICT, kernel should attempt to migrate all existing pages, and return -EIO if there is misplaced or unmovable page. Then commit 6f4576e3687b ("mempolicy: apply page table walker on queue_pages_range()") messed up the return value and didn't break VMA scan early ianymore when MPOL_MF_STRICT alone. The return value problem was fixed by commit a7f40cfe3b7a ("mm: mempolicy: make mbind() return -EIO when MPOL_MF_STRICT is specified"), but it broke the VMA walk early if unmovable page is met, it may cause some pages are not migrated as expected. The code should conceptually do: if (MPOL_MF_MOVE|MOVEALL) scan all vmas try to migrate the existing pages return success else if (MPOL_MF_MOVE* | MPOL_MF_STRICT) scan all vmas try to migrate the existing pages return -EIO if unmovable or migration failed else /* MPOL_MF_STRICT alone */ break early if meets unmovable and don't call mbind_range() at all else /* none of those flags */ check the ranges in test_walk, EFAULT without mbind_range() if discontig. Fixed the behavior. Link: https://lkml.kernel.org/r/20230920223242.3425775-1-yang@os.amperecomputing.… Fixes: a7f40cfe3b7a ("mm: mempolicy: make mbind() return -EIO when MPOL_MF_STRICT is specified") Signed-off-by: Yang Shi <yang(a)os.amperecomputing.com> Cc: Hugh Dickins <hughd(a)google.com> Cc: Suren Baghdasaryan <surenb(a)google.com> Cc: Matthew Wilcox <willy(a)infradead.org> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: Rafael Aquini <aquini(a)redhat.com> Cc: Kirill A. Shutemov <kirill(a)shutemov.name> Cc: David Rientjes <rientjes(a)google.com> Cc: <stable(a)vger.kernel.org> [4.9+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 42b5567e3773..f1b00d6ac7ee 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -426,6 +426,7 @@ struct queue_pages { unsigned long start; unsigned long end; struct vm_area_struct *first; + bool has_unmovable; }; /* @@ -446,9 +447,8 @@ static inline bool queue_folio_required(struct folio *folio, /* * queue_folios_pmd() has three possible return values: * 0 - folios are placed on the right node or queued successfully, or - * special page is met, i.e. huge zero page. - * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were - * specified. + * special page is met, i.e. zero page, or unmovable page is found + * but continue walking (indicated by queue_pages.has_unmovable). * -EIO - is migration entry or only MPOL_MF_STRICT was specified and an * existing folio was already on a node that does not follow the * policy. @@ -479,7 +479,7 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { if (!vma_migratable(walk->vma) || migrate_folio_add(folio, qp->pagelist, flags)) { - ret = 1; + qp->has_unmovable = true; goto unlock; } } else @@ -495,9 +495,8 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, * * queue_folios_pte_range() has three possible return values: * 0 - folios are placed on the right node or queued successfully, or - * special page is met, i.e. zero page. - * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were - * specified. + * special page is met, i.e. zero page, or unmovable page is found + * but continue walking (indicated by queue_pages.has_unmovable). * -EIO - only MPOL_MF_STRICT was specified and an existing folio was already * on a node that does not follow the policy. */ @@ -508,7 +507,6 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, struct folio *folio; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; - bool has_unmovable = false; pte_t *pte, *mapped_pte; pte_t ptent; spinlock_t *ptl; @@ -538,11 +536,12 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, if (!queue_folio_required(folio, qp)) continue; if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { - /* MPOL_MF_STRICT must be specified if we get here */ - if (!vma_migratable(vma)) { - has_unmovable = true; - break; - } + /* + * MPOL_MF_STRICT must be specified if we get here. + * Continue walking vmas due to MPOL_MF_MOVE* flags. + */ + if (!vma_migratable(vma)) + qp->has_unmovable = true; /* * Do not abort immediately since there may be @@ -550,16 +549,13 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, * need migrate other LRU pages. */ if (migrate_folio_add(folio, qp->pagelist, flags)) - has_unmovable = true; + qp->has_unmovable = true; } else break; } pte_unmap_unlock(mapped_pte, ptl); cond_resched(); - if (has_unmovable) - return 1; - return addr != end ? -EIO : 0; } @@ -599,7 +595,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, * Detecting misplaced folio but allow migrating folios which * have been queued. */ - ret = 1; + qp->has_unmovable = true; goto unlock; } @@ -620,7 +616,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, * Failed to isolate folio but allow migrating pages * which have been queued. */ - ret = 1; + qp->has_unmovable = true; } unlock: spin_unlock(ptl); @@ -756,12 +752,15 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, .start = start, .end = end, .first = NULL, + .has_unmovable = false, }; const struct mm_walk_ops *ops = lock_vma ? &queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops; err = walk_page_range(mm, start, end, ops, &qp); + if (qp.has_unmovable) + err = 1; if (!qp.first) /* whole range in hole */ err = -EFAULT; @@ -1358,7 +1357,7 @@ static long do_mbind(unsigned long start, unsigned long len, putback_movable_pages(&pagelist); } - if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT))) + if (((ret > 0) || nr_failed) && (flags & MPOL_MF_STRICT)) err = -EIO; } else { up_out:

2 years, 1 month

1
0
0 0

FAILED: patch "[PATCH] mm: mempolicy: keep VMA walk if both MPOL_MF_STRICT and" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y git checkout FETCH_HEAD git cherry-pick -x 24526268f4e38c9ec0c4a30de4f37ad2a2a84e47 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100429-unwatched-blaspheme-2d9d@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 24526268f4e38c9ec0c4a30de4f37ad2a2a84e47 Mon Sep 17 00:00:00 2001 From: Yang Shi <yang(a)os.amperecomputing.com> Date: Wed, 20 Sep 2023 15:32:42 -0700 Subject: [PATCH] mm: mempolicy: keep VMA walk if both MPOL_MF_STRICT and MPOL_MF_MOVE are specified When calling mbind() with MPOL_MF_{MOVE|MOVEALL} | MPOL_MF_STRICT, kernel should attempt to migrate all existing pages, and return -EIO if there is misplaced or unmovable page. Then commit 6f4576e3687b ("mempolicy: apply page table walker on queue_pages_range()") messed up the return value and didn't break VMA scan early ianymore when MPOL_MF_STRICT alone. The return value problem was fixed by commit a7f40cfe3b7a ("mm: mempolicy: make mbind() return -EIO when MPOL_MF_STRICT is specified"), but it broke the VMA walk early if unmovable page is met, it may cause some pages are not migrated as expected. The code should conceptually do: if (MPOL_MF_MOVE|MOVEALL) scan all vmas try to migrate the existing pages return success else if (MPOL_MF_MOVE* | MPOL_MF_STRICT) scan all vmas try to migrate the existing pages return -EIO if unmovable or migration failed else /* MPOL_MF_STRICT alone */ break early if meets unmovable and don't call mbind_range() at all else /* none of those flags */ check the ranges in test_walk, EFAULT without mbind_range() if discontig. Fixed the behavior. Link: https://lkml.kernel.org/r/20230920223242.3425775-1-yang@os.amperecomputing.… Fixes: a7f40cfe3b7a ("mm: mempolicy: make mbind() return -EIO when MPOL_MF_STRICT is specified") Signed-off-by: Yang Shi <yang(a)os.amperecomputing.com> Cc: Hugh Dickins <hughd(a)google.com> Cc: Suren Baghdasaryan <surenb(a)google.com> Cc: Matthew Wilcox <willy(a)infradead.org> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: Rafael Aquini <aquini(a)redhat.com> Cc: Kirill A. Shutemov <kirill(a)shutemov.name> Cc: David Rientjes <rientjes(a)google.com> Cc: <stable(a)vger.kernel.org> [4.9+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 42b5567e3773..f1b00d6ac7ee 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -426,6 +426,7 @@ struct queue_pages { unsigned long start; unsigned long end; struct vm_area_struct *first; + bool has_unmovable; }; /* @@ -446,9 +447,8 @@ static inline bool queue_folio_required(struct folio *folio, /* * queue_folios_pmd() has three possible return values: * 0 - folios are placed on the right node or queued successfully, or - * special page is met, i.e. huge zero page. - * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were - * specified. + * special page is met, i.e. zero page, or unmovable page is found + * but continue walking (indicated by queue_pages.has_unmovable). * -EIO - is migration entry or only MPOL_MF_STRICT was specified and an * existing folio was already on a node that does not follow the * policy. @@ -479,7 +479,7 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { if (!vma_migratable(walk->vma) || migrate_folio_add(folio, qp->pagelist, flags)) { - ret = 1; + qp->has_unmovable = true; goto unlock; } } else @@ -495,9 +495,8 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, * * queue_folios_pte_range() has three possible return values: * 0 - folios are placed on the right node or queued successfully, or - * special page is met, i.e. zero page. - * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were - * specified. + * special page is met, i.e. zero page, or unmovable page is found + * but continue walking (indicated by queue_pages.has_unmovable). * -EIO - only MPOL_MF_STRICT was specified and an existing folio was already * on a node that does not follow the policy. */ @@ -508,7 +507,6 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, struct folio *folio; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; - bool has_unmovable = false; pte_t *pte, *mapped_pte; pte_t ptent; spinlock_t *ptl; @@ -538,11 +536,12 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, if (!queue_folio_required(folio, qp)) continue; if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { - /* MPOL_MF_STRICT must be specified if we get here */ - if (!vma_migratable(vma)) { - has_unmovable = true; - break; - } + /* + * MPOL_MF_STRICT must be specified if we get here. + * Continue walking vmas due to MPOL_MF_MOVE* flags. + */ + if (!vma_migratable(vma)) + qp->has_unmovable = true; /* * Do not abort immediately since there may be @@ -550,16 +549,13 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, * need migrate other LRU pages. */ if (migrate_folio_add(folio, qp->pagelist, flags)) - has_unmovable = true; + qp->has_unmovable = true; } else break; } pte_unmap_unlock(mapped_pte, ptl); cond_resched(); - if (has_unmovable) - return 1; - return addr != end ? -EIO : 0; } @@ -599,7 +595,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, * Detecting misplaced folio but allow migrating folios which * have been queued. */ - ret = 1; + qp->has_unmovable = true; goto unlock; } @@ -620,7 +616,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, * Failed to isolate folio but allow migrating pages * which have been queued. */ - ret = 1; + qp->has_unmovable = true; } unlock: spin_unlock(ptl); @@ -756,12 +752,15 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, .start = start, .end = end, .first = NULL, + .has_unmovable = false, }; const struct mm_walk_ops *ops = lock_vma ? &queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops; err = walk_page_range(mm, start, end, ops, &qp); + if (qp.has_unmovable) + err = 1; if (!qp.first) /* whole range in hole */ err = -EFAULT; @@ -1358,7 +1357,7 @@ static long do_mbind(unsigned long start, unsigned long len, putback_movable_pages(&pagelist); } - if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT))) + if (((ret > 0) || nr_failed) && (flags & MPOL_MF_STRICT)) err = -EIO; } else { up_out:

2 years, 1 month

1
0
0 0

FAILED: patch "[PATCH] mm: mempolicy: keep VMA walk if both MPOL_MF_STRICT and" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x 24526268f4e38c9ec0c4a30de4f37ad2a2a84e47 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100427-urban-cognition-691b@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 24526268f4e38c9ec0c4a30de4f37ad2a2a84e47 Mon Sep 17 00:00:00 2001 From: Yang Shi <yang(a)os.amperecomputing.com> Date: Wed, 20 Sep 2023 15:32:42 -0700 Subject: [PATCH] mm: mempolicy: keep VMA walk if both MPOL_MF_STRICT and MPOL_MF_MOVE are specified When calling mbind() with MPOL_MF_{MOVE|MOVEALL} | MPOL_MF_STRICT, kernel should attempt to migrate all existing pages, and return -EIO if there is misplaced or unmovable page. Then commit 6f4576e3687b ("mempolicy: apply page table walker on queue_pages_range()") messed up the return value and didn't break VMA scan early ianymore when MPOL_MF_STRICT alone. The return value problem was fixed by commit a7f40cfe3b7a ("mm: mempolicy: make mbind() return -EIO when MPOL_MF_STRICT is specified"), but it broke the VMA walk early if unmovable page is met, it may cause some pages are not migrated as expected. The code should conceptually do: if (MPOL_MF_MOVE|MOVEALL) scan all vmas try to migrate the existing pages return success else if (MPOL_MF_MOVE* | MPOL_MF_STRICT) scan all vmas try to migrate the existing pages return -EIO if unmovable or migration failed else /* MPOL_MF_STRICT alone */ break early if meets unmovable and don't call mbind_range() at all else /* none of those flags */ check the ranges in test_walk, EFAULT without mbind_range() if discontig. Fixed the behavior. Link: https://lkml.kernel.org/r/20230920223242.3425775-1-yang@os.amperecomputing.… Fixes: a7f40cfe3b7a ("mm: mempolicy: make mbind() return -EIO when MPOL_MF_STRICT is specified") Signed-off-by: Yang Shi <yang(a)os.amperecomputing.com> Cc: Hugh Dickins <hughd(a)google.com> Cc: Suren Baghdasaryan <surenb(a)google.com> Cc: Matthew Wilcox <willy(a)infradead.org> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: Rafael Aquini <aquini(a)redhat.com> Cc: Kirill A. Shutemov <kirill(a)shutemov.name> Cc: David Rientjes <rientjes(a)google.com> Cc: <stable(a)vger.kernel.org> [4.9+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 42b5567e3773..f1b00d6ac7ee 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -426,6 +426,7 @@ struct queue_pages { unsigned long start; unsigned long end; struct vm_area_struct *first; + bool has_unmovable; }; /* @@ -446,9 +447,8 @@ static inline bool queue_folio_required(struct folio *folio, /* * queue_folios_pmd() has three possible return values: * 0 - folios are placed on the right node or queued successfully, or - * special page is met, i.e. huge zero page. - * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were - * specified. + * special page is met, i.e. zero page, or unmovable page is found + * but continue walking (indicated by queue_pages.has_unmovable). * -EIO - is migration entry or only MPOL_MF_STRICT was specified and an * existing folio was already on a node that does not follow the * policy. @@ -479,7 +479,7 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { if (!vma_migratable(walk->vma) || migrate_folio_add(folio, qp->pagelist, flags)) { - ret = 1; + qp->has_unmovable = true; goto unlock; } } else @@ -495,9 +495,8 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, * * queue_folios_pte_range() has three possible return values: * 0 - folios are placed on the right node or queued successfully, or - * special page is met, i.e. zero page. - * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were - * specified. + * special page is met, i.e. zero page, or unmovable page is found + * but continue walking (indicated by queue_pages.has_unmovable). * -EIO - only MPOL_MF_STRICT was specified and an existing folio was already * on a node that does not follow the policy. */ @@ -508,7 +507,6 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, struct folio *folio; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; - bool has_unmovable = false; pte_t *pte, *mapped_pte; pte_t ptent; spinlock_t *ptl; @@ -538,11 +536,12 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, if (!queue_folio_required(folio, qp)) continue; if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { - /* MPOL_MF_STRICT must be specified if we get here */ - if (!vma_migratable(vma)) { - has_unmovable = true; - break; - } + /* + * MPOL_MF_STRICT must be specified if we get here. + * Continue walking vmas due to MPOL_MF_MOVE* flags. + */ + if (!vma_migratable(vma)) + qp->has_unmovable = true; /* * Do not abort immediately since there may be @@ -550,16 +549,13 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, * need migrate other LRU pages. */ if (migrate_folio_add(folio, qp->pagelist, flags)) - has_unmovable = true; + qp->has_unmovable = true; } else break; } pte_unmap_unlock(mapped_pte, ptl); cond_resched(); - if (has_unmovable) - return 1; - return addr != end ? -EIO : 0; } @@ -599,7 +595,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, * Detecting misplaced folio but allow migrating folios which * have been queued. */ - ret = 1; + qp->has_unmovable = true; goto unlock; } @@ -620,7 +616,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, * Failed to isolate folio but allow migrating pages * which have been queued. */ - ret = 1; + qp->has_unmovable = true; } unlock: spin_unlock(ptl); @@ -756,12 +752,15 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, .start = start, .end = end, .first = NULL, + .has_unmovable = false, }; const struct mm_walk_ops *ops = lock_vma ? &queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops; err = walk_page_range(mm, start, end, ops, &qp); + if (qp.has_unmovable) + err = 1; if (!qp.first) /* whole range in hole */ err = -EFAULT; @@ -1358,7 +1357,7 @@ static long do_mbind(unsigned long start, unsigned long len, putback_movable_pages(&pagelist); } - if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT))) + if (((ret > 0) || nr_failed) && (flags & MPOL_MF_STRICT)) err = -EIO; } else { up_out:

2 years, 1 month

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror October 2023