July 2024 - Linux-stable-mirror

FAILED: patch "[PATCH] nilfs2: fix kernel bug on rename operation of broken" 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 a9e1ddc09ca55746079cc479aa3eb6411f0d99d4 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024071540-widow-expansion-f3c5@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^.. Possible dependencies: a9e1ddc09ca5 ("nilfs2: fix kernel bug on rename operation of broken directory") 6f133c97e5ce ("nilfs2: convert nilfs_rename() to use folios") a4bf041e44d5 ("nilfs2: convert nilfs_find_entry to use a folio") 9b77f66f9927 ("nilfs2: switch to kmap_local for directory handling") 09a46acb3697 ("nilfs2: return the mapped address from nilfs_get_page()") 6af2191f8358 ("nilfs2: remove page_address() from nilfs_delete_entry") 6bb09fa1b44f ("nilfs2: remove page_address() from nilfs_set_link") 8cf57c6df818 ("nilfs2: eliminate staggered calls to kunmap in nilfs_rename") 584db20c181f ("nilfs2: move page release outside of nilfs_delete_entry and nilfs_set_link") b3e1cc3935ff ("nilfs2: convert to new timestamp accessors") e21d4f419402 ("nilfs2: convert to ctime accessor functions") 21a87d88c225 ("nilfs2: fix NULL pointer dereference at nilfs_bmap_lookup_at_level()") 79ea65563ad8 ("nilfs2: Remove check for PageError") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From a9e1ddc09ca55746079cc479aa3eb6411f0d99d4 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Date: Sat, 29 Jun 2024 01:51:07 +0900 Subject: [PATCH] nilfs2: fix kernel bug on rename operation of broken directory Syzbot reported that in rename directory operation on broken directory on nilfs2, __block_write_begin_int() called to prepare block write may fail BUG_ON check for access exceeding the folio/page size. This is because nilfs_dotdot(), which gets parent directory reference entry ("..") of the directory to be moved or renamed, does not check consistency enough, and may return location exceeding folio/page size for broken directories. Fix this issue by checking required directory entries ("." and "..") in the first chunk of the directory in nilfs_dotdot(). Link: https://lkml.kernel.org/r/20240628165107.9006-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Reported-by: syzbot+d3abed1ad3d367fa2627(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=d3abed1ad3d367fa2627 Fixes: 2ba466d74ed7 ("nilfs2: directory entry operations") Tested-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index dddfa604491a..4a29b0138d75 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -383,11 +383,39 @@ struct nilfs_dir_entry *nilfs_find_entry(struct inode *dir, struct nilfs_dir_entry *nilfs_dotdot(struct inode *dir, struct folio **foliop) { - struct nilfs_dir_entry *de = nilfs_get_folio(dir, 0, foliop); + struct folio *folio; + struct nilfs_dir_entry *de, *next_de; + size_t limit; + char *msg; + de = nilfs_get_folio(dir, 0, &folio); if (IS_ERR(de)) return NULL; - return nilfs_next_entry(de); + + limit = nilfs_last_byte(dir, 0); /* is a multiple of chunk size */ + if (unlikely(!limit || le64_to_cpu(de->inode) != dir->i_ino || + !nilfs_match(1, ".", de))) { + msg = "missing '.'"; + goto fail; + } + + next_de = nilfs_next_entry(de); + /* + * If "next_de" has not reached the end of the chunk, there is + * at least one more record. Check whether it matches "..". + */ + if (unlikely((char *)next_de == (char *)de + nilfs_chunk_size(dir) || + !nilfs_match(2, "..", next_de))) { + msg = "missing '..'"; + goto fail; + } + *foliop = folio; + return next_de; + +fail: + nilfs_error(dir->i_sb, "directory #%lu %s", dir->i_ino, msg); + folio_release_kmap(folio, de); + return NULL; } ino_t nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr)

2 months, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] nilfs2: fix kernel bug on rename operation of broken" 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 a9e1ddc09ca55746079cc479aa3eb6411f0d99d4 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024071539-chess-overrun-78ac@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: a9e1ddc09ca5 ("nilfs2: fix kernel bug on rename operation of broken directory") 6f133c97e5ce ("nilfs2: convert nilfs_rename() to use folios") a4bf041e44d5 ("nilfs2: convert nilfs_find_entry to use a folio") 9b77f66f9927 ("nilfs2: switch to kmap_local for directory handling") 09a46acb3697 ("nilfs2: return the mapped address from nilfs_get_page()") 6af2191f8358 ("nilfs2: remove page_address() from nilfs_delete_entry") 6bb09fa1b44f ("nilfs2: remove page_address() from nilfs_set_link") 8cf57c6df818 ("nilfs2: eliminate staggered calls to kunmap in nilfs_rename") 584db20c181f ("nilfs2: move page release outside of nilfs_delete_entry and nilfs_set_link") b3e1cc3935ff ("nilfs2: convert to new timestamp accessors") e21d4f419402 ("nilfs2: convert to ctime accessor functions") 21a87d88c225 ("nilfs2: fix NULL pointer dereference at nilfs_bmap_lookup_at_level()") 79ea65563ad8 ("nilfs2: Remove check for PageError") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From a9e1ddc09ca55746079cc479aa3eb6411f0d99d4 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Date: Sat, 29 Jun 2024 01:51:07 +0900 Subject: [PATCH] nilfs2: fix kernel bug on rename operation of broken directory Syzbot reported that in rename directory operation on broken directory on nilfs2, __block_write_begin_int() called to prepare block write may fail BUG_ON check for access exceeding the folio/page size. This is because nilfs_dotdot(), which gets parent directory reference entry ("..") of the directory to be moved or renamed, does not check consistency enough, and may return location exceeding folio/page size for broken directories. Fix this issue by checking required directory entries ("." and "..") in the first chunk of the directory in nilfs_dotdot(). Link: https://lkml.kernel.org/r/20240628165107.9006-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Reported-by: syzbot+d3abed1ad3d367fa2627(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=d3abed1ad3d367fa2627 Fixes: 2ba466d74ed7 ("nilfs2: directory entry operations") Tested-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index dddfa604491a..4a29b0138d75 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -383,11 +383,39 @@ struct nilfs_dir_entry *nilfs_find_entry(struct inode *dir, struct nilfs_dir_entry *nilfs_dotdot(struct inode *dir, struct folio **foliop) { - struct nilfs_dir_entry *de = nilfs_get_folio(dir, 0, foliop); + struct folio *folio; + struct nilfs_dir_entry *de, *next_de; + size_t limit; + char *msg; + de = nilfs_get_folio(dir, 0, &folio); if (IS_ERR(de)) return NULL; - return nilfs_next_entry(de); + + limit = nilfs_last_byte(dir, 0); /* is a multiple of chunk size */ + if (unlikely(!limit || le64_to_cpu(de->inode) != dir->i_ino || + !nilfs_match(1, ".", de))) { + msg = "missing '.'"; + goto fail; + } + + next_de = nilfs_next_entry(de); + /* + * If "next_de" has not reached the end of the chunk, there is + * at least one more record. Check whether it matches "..". + */ + if (unlikely((char *)next_de == (char *)de + nilfs_chunk_size(dir) || + !nilfs_match(2, "..", next_de))) { + msg = "missing '..'"; + goto fail; + } + *foliop = folio; + return next_de; + +fail: + nilfs_error(dir->i_sb, "directory #%lu %s", dir->i_ino, msg); + folio_release_kmap(folio, de); + return NULL; } ino_t nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr)

2 months, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] nilfs2: fix kernel bug on rename operation of broken" 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 a9e1ddc09ca55746079cc479aa3eb6411f0d99d4 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024071538-overreach-eatable-7ae6@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: a9e1ddc09ca5 ("nilfs2: fix kernel bug on rename operation of broken directory") 6f133c97e5ce ("nilfs2: convert nilfs_rename() to use folios") a4bf041e44d5 ("nilfs2: convert nilfs_find_entry to use a folio") 9b77f66f9927 ("nilfs2: switch to kmap_local for directory handling") 09a46acb3697 ("nilfs2: return the mapped address from nilfs_get_page()") 6af2191f8358 ("nilfs2: remove page_address() from nilfs_delete_entry") 6bb09fa1b44f ("nilfs2: remove page_address() from nilfs_set_link") 8cf57c6df818 ("nilfs2: eliminate staggered calls to kunmap in nilfs_rename") 584db20c181f ("nilfs2: move page release outside of nilfs_delete_entry and nilfs_set_link") b3e1cc3935ff ("nilfs2: convert to new timestamp accessors") e21d4f419402 ("nilfs2: convert to ctime accessor functions") 21a87d88c225 ("nilfs2: fix NULL pointer dereference at nilfs_bmap_lookup_at_level()") 79ea65563ad8 ("nilfs2: Remove check for PageError") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From a9e1ddc09ca55746079cc479aa3eb6411f0d99d4 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Date: Sat, 29 Jun 2024 01:51:07 +0900 Subject: [PATCH] nilfs2: fix kernel bug on rename operation of broken directory Syzbot reported that in rename directory operation on broken directory on nilfs2, __block_write_begin_int() called to prepare block write may fail BUG_ON check for access exceeding the folio/page size. This is because nilfs_dotdot(), which gets parent directory reference entry ("..") of the directory to be moved or renamed, does not check consistency enough, and may return location exceeding folio/page size for broken directories. Fix this issue by checking required directory entries ("." and "..") in the first chunk of the directory in nilfs_dotdot(). Link: https://lkml.kernel.org/r/20240628165107.9006-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Reported-by: syzbot+d3abed1ad3d367fa2627(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=d3abed1ad3d367fa2627 Fixes: 2ba466d74ed7 ("nilfs2: directory entry operations") Tested-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index dddfa604491a..4a29b0138d75 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -383,11 +383,39 @@ struct nilfs_dir_entry *nilfs_find_entry(struct inode *dir, struct nilfs_dir_entry *nilfs_dotdot(struct inode *dir, struct folio **foliop) { - struct nilfs_dir_entry *de = nilfs_get_folio(dir, 0, foliop); + struct folio *folio; + struct nilfs_dir_entry *de, *next_de; + size_t limit; + char *msg; + de = nilfs_get_folio(dir, 0, &folio); if (IS_ERR(de)) return NULL; - return nilfs_next_entry(de); + + limit = nilfs_last_byte(dir, 0); /* is a multiple of chunk size */ + if (unlikely(!limit || le64_to_cpu(de->inode) != dir->i_ino || + !nilfs_match(1, ".", de))) { + msg = "missing '.'"; + goto fail; + } + + next_de = nilfs_next_entry(de); + /* + * If "next_de" has not reached the end of the chunk, there is + * at least one more record. Check whether it matches "..". + */ + if (unlikely((char *)next_de == (char *)de + nilfs_chunk_size(dir) || + !nilfs_match(2, "..", next_de))) { + msg = "missing '..'"; + goto fail; + } + *foliop = folio; + return next_de; + +fail: + nilfs_error(dir->i_sb, "directory #%lu %s", dir->i_ino, msg); + folio_release_kmap(folio, de); + return NULL; } ino_t nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr)

2 months, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] nilfs2: fix kernel bug on rename operation of broken" 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 a9e1ddc09ca55746079cc479aa3eb6411f0d99d4 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024071537-wilt-goliath-e654@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: a9e1ddc09ca5 ("nilfs2: fix kernel bug on rename operation of broken directory") 6f133c97e5ce ("nilfs2: convert nilfs_rename() to use folios") a4bf041e44d5 ("nilfs2: convert nilfs_find_entry to use a folio") 9b77f66f9927 ("nilfs2: switch to kmap_local for directory handling") 09a46acb3697 ("nilfs2: return the mapped address from nilfs_get_page()") 6af2191f8358 ("nilfs2: remove page_address() from nilfs_delete_entry") 6bb09fa1b44f ("nilfs2: remove page_address() from nilfs_set_link") 8cf57c6df818 ("nilfs2: eliminate staggered calls to kunmap in nilfs_rename") 584db20c181f ("nilfs2: move page release outside of nilfs_delete_entry and nilfs_set_link") b3e1cc3935ff ("nilfs2: convert to new timestamp accessors") e21d4f419402 ("nilfs2: convert to ctime accessor functions") 21a87d88c225 ("nilfs2: fix NULL pointer dereference at nilfs_bmap_lookup_at_level()") 79ea65563ad8 ("nilfs2: Remove check for PageError") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From a9e1ddc09ca55746079cc479aa3eb6411f0d99d4 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Date: Sat, 29 Jun 2024 01:51:07 +0900 Subject: [PATCH] nilfs2: fix kernel bug on rename operation of broken directory Syzbot reported that in rename directory operation on broken directory on nilfs2, __block_write_begin_int() called to prepare block write may fail BUG_ON check for access exceeding the folio/page size. This is because nilfs_dotdot(), which gets parent directory reference entry ("..") of the directory to be moved or renamed, does not check consistency enough, and may return location exceeding folio/page size for broken directories. Fix this issue by checking required directory entries ("." and "..") in the first chunk of the directory in nilfs_dotdot(). Link: https://lkml.kernel.org/r/20240628165107.9006-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Reported-by: syzbot+d3abed1ad3d367fa2627(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=d3abed1ad3d367fa2627 Fixes: 2ba466d74ed7 ("nilfs2: directory entry operations") Tested-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index dddfa604491a..4a29b0138d75 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -383,11 +383,39 @@ struct nilfs_dir_entry *nilfs_find_entry(struct inode *dir, struct nilfs_dir_entry *nilfs_dotdot(struct inode *dir, struct folio **foliop) { - struct nilfs_dir_entry *de = nilfs_get_folio(dir, 0, foliop); + struct folio *folio; + struct nilfs_dir_entry *de, *next_de; + size_t limit; + char *msg; + de = nilfs_get_folio(dir, 0, &folio); if (IS_ERR(de)) return NULL; - return nilfs_next_entry(de); + + limit = nilfs_last_byte(dir, 0); /* is a multiple of chunk size */ + if (unlikely(!limit || le64_to_cpu(de->inode) != dir->i_ino || + !nilfs_match(1, ".", de))) { + msg = "missing '.'"; + goto fail; + } + + next_de = nilfs_next_entry(de); + /* + * If "next_de" has not reached the end of the chunk, there is + * at least one more record. Check whether it matches "..". + */ + if (unlikely((char *)next_de == (char *)de + nilfs_chunk_size(dir) || + !nilfs_match(2, "..", next_de))) { + msg = "missing '..'"; + goto fail; + } + *foliop = folio; + return next_de; + +fail: + nilfs_error(dir->i_sb, "directory #%lu %s", dir->i_ino, msg); + folio_release_kmap(folio, de); + return NULL; } ino_t nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr)

2 months, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] nilfs2: fix kernel bug on rename operation of broken" 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 a9e1ddc09ca55746079cc479aa3eb6411f0d99d4 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024071537-acetone-vastly-d974@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: a9e1ddc09ca5 ("nilfs2: fix kernel bug on rename operation of broken directory") 6f133c97e5ce ("nilfs2: convert nilfs_rename() to use folios") a4bf041e44d5 ("nilfs2: convert nilfs_find_entry to use a folio") 9b77f66f9927 ("nilfs2: switch to kmap_local for directory handling") 09a46acb3697 ("nilfs2: return the mapped address from nilfs_get_page()") 6af2191f8358 ("nilfs2: remove page_address() from nilfs_delete_entry") 6bb09fa1b44f ("nilfs2: remove page_address() from nilfs_set_link") 8cf57c6df818 ("nilfs2: eliminate staggered calls to kunmap in nilfs_rename") 584db20c181f ("nilfs2: move page release outside of nilfs_delete_entry and nilfs_set_link") b3e1cc3935ff ("nilfs2: convert to new timestamp accessors") e21d4f419402 ("nilfs2: convert to ctime accessor functions") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From a9e1ddc09ca55746079cc479aa3eb6411f0d99d4 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Date: Sat, 29 Jun 2024 01:51:07 +0900 Subject: [PATCH] nilfs2: fix kernel bug on rename operation of broken directory Syzbot reported that in rename directory operation on broken directory on nilfs2, __block_write_begin_int() called to prepare block write may fail BUG_ON check for access exceeding the folio/page size. This is because nilfs_dotdot(), which gets parent directory reference entry ("..") of the directory to be moved or renamed, does not check consistency enough, and may return location exceeding folio/page size for broken directories. Fix this issue by checking required directory entries ("." and "..") in the first chunk of the directory in nilfs_dotdot(). Link: https://lkml.kernel.org/r/20240628165107.9006-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Reported-by: syzbot+d3abed1ad3d367fa2627(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=d3abed1ad3d367fa2627 Fixes: 2ba466d74ed7 ("nilfs2: directory entry operations") Tested-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index dddfa604491a..4a29b0138d75 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -383,11 +383,39 @@ struct nilfs_dir_entry *nilfs_find_entry(struct inode *dir, struct nilfs_dir_entry *nilfs_dotdot(struct inode *dir, struct folio **foliop) { - struct nilfs_dir_entry *de = nilfs_get_folio(dir, 0, foliop); + struct folio *folio; + struct nilfs_dir_entry *de, *next_de; + size_t limit; + char *msg; + de = nilfs_get_folio(dir, 0, &folio); if (IS_ERR(de)) return NULL; - return nilfs_next_entry(de); + + limit = nilfs_last_byte(dir, 0); /* is a multiple of chunk size */ + if (unlikely(!limit || le64_to_cpu(de->inode) != dir->i_ino || + !nilfs_match(1, ".", de))) { + msg = "missing '.'"; + goto fail; + } + + next_de = nilfs_next_entry(de); + /* + * If "next_de" has not reached the end of the chunk, there is + * at least one more record. Check whether it matches "..". + */ + if (unlikely((char *)next_de == (char *)de + nilfs_chunk_size(dir) || + !nilfs_match(2, "..", next_de))) { + msg = "missing '..'"; + goto fail; + } + *foliop = folio; + return next_de; + +fail: + nilfs_error(dir->i_sb, "directory #%lu %s", dir->i_ino, msg); + folio_release_kmap(folio, de); + return NULL; } ino_t nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr)

2 months, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] nilfs2: fix kernel bug on rename operation of broken" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-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-6.6.y git checkout FETCH_HEAD git cherry-pick -x a9e1ddc09ca55746079cc479aa3eb6411f0d99d4 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024071536-overstay-scholar-83a6@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: a9e1ddc09ca5 ("nilfs2: fix kernel bug on rename operation of broken directory") 6f133c97e5ce ("nilfs2: convert nilfs_rename() to use folios") a4bf041e44d5 ("nilfs2: convert nilfs_find_entry to use a folio") 9b77f66f9927 ("nilfs2: switch to kmap_local for directory handling") 09a46acb3697 ("nilfs2: return the mapped address from nilfs_get_page()") 6af2191f8358 ("nilfs2: remove page_address() from nilfs_delete_entry") 6bb09fa1b44f ("nilfs2: remove page_address() from nilfs_set_link") 8cf57c6df818 ("nilfs2: eliminate staggered calls to kunmap in nilfs_rename") 584db20c181f ("nilfs2: move page release outside of nilfs_delete_entry and nilfs_set_link") b3e1cc3935ff ("nilfs2: convert to new timestamp accessors") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From a9e1ddc09ca55746079cc479aa3eb6411f0d99d4 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Date: Sat, 29 Jun 2024 01:51:07 +0900 Subject: [PATCH] nilfs2: fix kernel bug on rename operation of broken directory Syzbot reported that in rename directory operation on broken directory on nilfs2, __block_write_begin_int() called to prepare block write may fail BUG_ON check for access exceeding the folio/page size. This is because nilfs_dotdot(), which gets parent directory reference entry ("..") of the directory to be moved or renamed, does not check consistency enough, and may return location exceeding folio/page size for broken directories. Fix this issue by checking required directory entries ("." and "..") in the first chunk of the directory in nilfs_dotdot(). Link: https://lkml.kernel.org/r/20240628165107.9006-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Reported-by: syzbot+d3abed1ad3d367fa2627(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=d3abed1ad3d367fa2627 Fixes: 2ba466d74ed7 ("nilfs2: directory entry operations") Tested-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index dddfa604491a..4a29b0138d75 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -383,11 +383,39 @@ struct nilfs_dir_entry *nilfs_find_entry(struct inode *dir, struct nilfs_dir_entry *nilfs_dotdot(struct inode *dir, struct folio **foliop) { - struct nilfs_dir_entry *de = nilfs_get_folio(dir, 0, foliop); + struct folio *folio; + struct nilfs_dir_entry *de, *next_de; + size_t limit; + char *msg; + de = nilfs_get_folio(dir, 0, &folio); if (IS_ERR(de)) return NULL; - return nilfs_next_entry(de); + + limit = nilfs_last_byte(dir, 0); /* is a multiple of chunk size */ + if (unlikely(!limit || le64_to_cpu(de->inode) != dir->i_ino || + !nilfs_match(1, ".", de))) { + msg = "missing '.'"; + goto fail; + } + + next_de = nilfs_next_entry(de); + /* + * If "next_de" has not reached the end of the chunk, there is + * at least one more record. Check whether it matches "..". + */ + if (unlikely((char *)next_de == (char *)de + nilfs_chunk_size(dir) || + !nilfs_match(2, "..", next_de))) { + msg = "missing '..'"; + goto fail; + } + *foliop = folio; + return next_de; + +fail: + nilfs_error(dir->i_sb, "directory #%lu %s", dir->i_ino, msg); + folio_release_kmap(folio, de); + return NULL; } ino_t nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr)

2 months, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] mm/filemap: skip to create PMD-sized page cache if needed" 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 3390916aca7af1893ed2ebcdfee1d6fdb65bb058 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024071536-overreach-kite-5c51@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: 3390916aca7a ("mm/filemap: skip to create PMD-sized page cache if needed") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 3390916aca7af1893ed2ebcdfee1d6fdb65bb058 Mon Sep 17 00:00:00 2001 From: Gavin Shan <gshan(a)redhat.com> Date: Thu, 27 Jun 2024 10:39:51 +1000 Subject: [PATCH] mm/filemap: skip to create PMD-sized page cache if needed On ARM64, HPAGE_PMD_ORDER is 13 when the base page size is 64KB. The PMD-sized page cache can't be supported by xarray as the following error messages indicate. ------------[ cut here ]------------ WARNING: CPU: 35 PID: 7484 at lib/xarray.c:1025 xas_split_alloc+0xf8/0x128 Modules linked in: nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib \ nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct \ nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 \ ip_set rfkill nf_tables nfnetlink vfat fat virtio_balloon drm \ fuse xfs libcrc32c crct10dif_ce ghash_ce sha2_ce sha256_arm64 \ sha1_ce virtio_net net_failover virtio_console virtio_blk failover \ dimlib virtio_mmio CPU: 35 PID: 7484 Comm: test Kdump: loaded Tainted: G W 6.10.0-rc5-gavin+ #9 Hardware name: QEMU KVM Virtual Machine, BIOS edk2-20240524-1.el9 05/24/2024 pstate: 83400005 (Nzcv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--) pc : xas_split_alloc+0xf8/0x128 lr : split_huge_page_to_list_to_order+0x1c4/0x720 sp : ffff800087a4f6c0 x29: ffff800087a4f6c0 x28: ffff800087a4f720 x27: 000000001fffffff x26: 0000000000000c40 x25: 000000000000000d x24: ffff00010625b858 x23: ffff800087a4f720 x22: ffffffdfc0780000 x21: 0000000000000000 x20: 0000000000000000 x19: ffffffdfc0780000 x18: 000000001ff40000 x17: 00000000ffffffff x16: 0000018000000000 x15: 51ec004000000000 x14: 0000e00000000000 x13: 0000000000002000 x12: 0000000000000020 x11: 51ec000000000000 x10: 51ece1c0ffff8000 x9 : ffffbeb961a44d28 x8 : 0000000000000003 x7 : ffffffdfc0456420 x6 : ffff0000e1aa6eb8 x5 : 20bf08b4fe778fca x4 : ffffffdfc0456420 x3 : 0000000000000c40 x2 : 000000000000000d x1 : 000000000000000c x0 : 0000000000000000 Call trace: xas_split_alloc+0xf8/0x128 split_huge_page_to_list_to_order+0x1c4/0x720 truncate_inode_partial_folio+0xdc/0x160 truncate_inode_pages_range+0x1b4/0x4a8 truncate_pagecache_range+0x84/0xa0 xfs_flush_unmap_range+0x70/0x90 [xfs] xfs_file_fallocate+0xfc/0x4d8 [xfs] vfs_fallocate+0x124/0x2e8 ksys_fallocate+0x4c/0xa0 __arm64_sys_fallocate+0x24/0x38 invoke_syscall.constprop.0+0x7c/0xd8 do_el0_svc+0xb4/0xd0 el0_svc+0x44/0x1d8 el0t_64_sync_handler+0x134/0x150 el0t_64_sync+0x17c/0x180 Fix it by skipping to allocate PMD-sized page cache when its size is larger than MAX_PAGECACHE_ORDER. For this specific case, we will fall to regular path where the readahead window is determined by BDI's sysfs file (read_ahead_kb). Link: https://lkml.kernel.org/r/20240627003953.1262512-4-gshan@redhat.com Fixes: 4687fdbb805a ("mm/filemap: Support VM_HUGEPAGE for file mappings") Signed-off-by: Gavin Shan <gshan(a)redhat.com> Suggested-by: David Hildenbrand <david(a)redhat.com> Acked-by: David Hildenbrand <david(a)redhat.com> Cc: Darrick J. Wong <djwong(a)kernel.org> Cc: Don Dutile <ddutile(a)redhat.com> Cc: Hugh Dickins <hughd(a)google.com> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Ryan Roberts <ryan.roberts(a)arm.com> Cc: William Kucharski <william.kucharski(a)oracle.com> Cc: Zhenyu Zhang <zhenyzha(a)redhat.com> Cc: <stable(a)vger.kernel.org> [5.18+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/filemap.c b/mm/filemap.c index 54b15bb96056..fedefb10d947 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3124,7 +3124,7 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* Use the readahead code, even if readahead is disabled */ - if (vm_flags & VM_HUGEPAGE) { + if ((vm_flags & VM_HUGEPAGE) && HPAGE_PMD_ORDER <= MAX_PAGECACHE_ORDER) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); ractl._index &= ~((unsigned long)HPAGE_PMD_NR - 1); ra->size = HPAGE_PMD_NR;

2 months, 3 weeks

1
0
0 0

[PATCH 00/12] thermal/drivers: simplify probe()

by Krzysztof Kozlowski

Simplify error handling in probe() and also fix one possible issue in remove(). Best regards, Krzysztof --- Krzysztof Kozlowski (12): thermal/drivers/broadcom: fix race between removal and clock disable thermal/drivers/broadcom: simplify probe() with local dev variable thermal/drivers/broadcom: simplify with dev_err_probe() thermal/drivers/exynos: simplify probe() with local dev variable thermal/drivers/exynos: simplify with dev_err_probe() thermal/drivers/hisi: simplify with dev_err_probe() thermal/drivers/imx: simplify probe() with local dev variable thermal/drivers/imx: simplify with dev_err_probe() thermal/drivers/qcom-spmi-adc-tm5: simplify with dev_err_probe() thermal/drivers/qcom-tsens: simplify with dev_err_probe() thermal/drivers/generic-adc: simplify probe() with local dev variable thermal/drivers/generic-adc: simplify with dev_err_probe() drivers/thermal/broadcom/bcm2835_thermal.c | 49 +++++++-------------------- drivers/thermal/hisi_thermal.c | 9 ++--- drivers/thermal/imx_thermal.c | 42 +++++++++++------------ drivers/thermal/qcom/qcom-spmi-adc-tm5.c | 9 ++--- drivers/thermal/qcom/tsens.c | 8 ++--- drivers/thermal/samsung/exynos_tmu.c | 54 +++++++++++++----------------- drivers/thermal/thermal-generic-adc.c | 27 +++++++-------- 7 files changed, 76 insertions(+), 122 deletions(-) --- base-commit: 2e0171396caa83c9d908ba2676ba59bce333b550 change-id: 20240709-thermal-probe-a747013ed28d Best regards, -- Krzysztof Kozlowski <krzysztof.kozlowski(a)linaro.org>

2 months, 3 weeks

2
2
0 0

FAILED: patch "[PATCH] mm/filemap: make MAX_PAGECACHE_ORDER acceptable to xarray" 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 099d90642a711caae377f53309abfe27e8724a8b # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024071553-sturdily-proud-355b@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: 099d90642a71 ("mm/filemap: make MAX_PAGECACHE_ORDER acceptable to xarray") 79c137454815 ("filemap: add helper mapping_max_folio_size()") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 099d90642a711caae377f53309abfe27e8724a8b Mon Sep 17 00:00:00 2001 From: Gavin Shan <gshan(a)redhat.com> Date: Thu, 27 Jun 2024 10:39:49 +1000 Subject: [PATCH] mm/filemap: make MAX_PAGECACHE_ORDER acceptable to xarray Patch series "mm/filemap: Limit page cache size to that supported by xarray", v2. Currently, xarray can't support arbitrary page cache size. More details can be found from the WARN_ON() statement in xas_split_alloc(). In our test whose code is attached below, we hit the WARN_ON() on ARM64 system where the base page size is 64KB and huge page size is 512MB. The issue was reported long time ago and some discussions on it can be found here [1]. [1] https://www.spinics.net/lists/linux-xfs/msg75404.html In order to fix the issue, we need to adjust MAX_PAGECACHE_ORDER to one supported by xarray and avoid PMD-sized page cache if needed. The code changes are suggested by David Hildenbrand. PATCH[1] adjusts MAX_PAGECACHE_ORDER to that supported by xarray PATCH[2-3] avoids PMD-sized page cache in the synchronous readahead path PATCH[4] avoids PMD-sized page cache for shmem files if needed Test program ============ # cat test.c #define _GNU_SOURCE #include <stdio.h> #include <stdlib.h> #include <unistd.h> #include <string.h> #include <fcntl.h> #include <errno.h> #include <sys/syscall.h> #include <sys/mman.h> #define TEST_XFS_FILENAME "/tmp/data" #define TEST_SHMEM_FILENAME "/dev/shm/data" #define TEST_MEM_SIZE 0x20000000 int main(int argc, char **argv) { const char *filename; int fd = 0; void *buf = (void *)-1, *p; int pgsize = getpagesize(); int ret; if (pgsize != 0x10000) { fprintf(stderr, "64KB base page size is required\n"); return -EPERM; } system("echo force > /sys/kernel/mm/transparent_hugepage/shmem_enabled"); system("rm -fr /tmp/data"); system("rm -fr /dev/shm/data"); system("echo 1 > /proc/sys/vm/drop_caches"); /* Open xfs or shmem file */ filename = TEST_XFS_FILENAME; if (argc > 1 && !strcmp(argv[1], "shmem")) filename = TEST_SHMEM_FILENAME; fd = open(filename, O_CREAT | O_RDWR | O_TRUNC); if (fd < 0) { fprintf(stderr, "Unable to open <%s>\n", filename); return -EIO; } /* Extend file size */ ret = ftruncate(fd, TEST_MEM_SIZE); if (ret) { fprintf(stderr, "Error %d to ftruncate()\n", ret); goto cleanup; } /* Create VMA */ buf = mmap(NULL, TEST_MEM_SIZE, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); if (buf == (void *)-1) { fprintf(stderr, "Unable to mmap <%s>\n", filename); goto cleanup; } fprintf(stdout, "mapped buffer at 0x%p\n", buf); ret = madvise(buf, TEST_MEM_SIZE, MADV_HUGEPAGE); if (ret) { fprintf(stderr, "Unable to madvise(MADV_HUGEPAGE)\n"); goto cleanup; } /* Populate VMA */ ret = madvise(buf, TEST_MEM_SIZE, MADV_POPULATE_WRITE); if (ret) { fprintf(stderr, "Error %d to madvise(MADV_POPULATE_WRITE)\n", ret); goto cleanup; } /* Punch the file to enforce xarray split */ ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, TEST_MEM_SIZE - pgsize, pgsize); if (ret) fprintf(stderr, "Error %d to fallocate()\n", ret); cleanup: if (buf != (void *)-1) munmap(buf, TEST_MEM_SIZE); if (fd > 0) close(fd); return 0; } # gcc test.c -o test # cat /proc/1/smaps | grep KernelPageSize | head -n 1 KernelPageSize: 64 kB # ./test shmem : ------------[ cut here ]------------ WARNING: CPU: 17 PID: 5253 at lib/xarray.c:1025 xas_split_alloc+0xf8/0x128 Modules linked in: nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib \ nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct \ nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 \ ip_set nf_tables rfkill nfnetlink vfat fat virtio_balloon \ drm fuse xfs libcrc32c crct10dif_ce ghash_ce sha2_ce sha256_arm64 \ virtio_net sha1_ce net_failover failover virtio_console virtio_blk \ dimlib virtio_mmio CPU: 17 PID: 5253 Comm: test Kdump: loaded Tainted: G W 6.10.0-rc5-gavin+ #12 Hardware name: QEMU KVM Virtual Machine, BIOS edk2-20240524-1.el9 05/24/2024 pstate: 83400005 (Nzcv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--) pc : xas_split_alloc+0xf8/0x128 lr : split_huge_page_to_list_to_order+0x1c4/0x720 sp : ffff80008a92f5b0 x29: ffff80008a92f5b0 x28: ffff80008a92f610 x27: ffff80008a92f728 x26: 0000000000000cc0 x25: 000000000000000d x24: ffff0000cf00c858 x23: ffff80008a92f610 x22: ffffffdfc0600000 x21: 0000000000000000 x20: 0000000000000000 x19: ffffffdfc0600000 x18: 0000000000000000 x17: 0000000000000000 x16: 0000018000000000 x15: 3374004000000000 x14: 0000e00000000000 x13: 0000000000002000 x12: 0000000000000020 x11: 3374000000000000 x10: 3374e1c0ffff6000 x9 : ffffb463a84c681c x8 : 0000000000000003 x7 : 0000000000000000 x6 : ffff00011c976ce0 x5 : ffffb463aa47e378 x4 : 0000000000000000 x3 : 0000000000000cc0 x2 : 000000000000000d x1 : 000000000000000c x0 : 0000000000000000 Call trace: xas_split_alloc+0xf8/0x128 split_huge_page_to_list_to_order+0x1c4/0x720 truncate_inode_partial_folio+0xdc/0x160 shmem_undo_range+0x2bc/0x6a8 shmem_fallocate+0x134/0x430 vfs_fallocate+0x124/0x2e8 ksys_fallocate+0x4c/0xa0 __arm64_sys_fallocate+0x24/0x38 invoke_syscall.constprop.0+0x7c/0xd8 do_el0_svc+0xb4/0xd0 el0_svc+0x44/0x1d8 el0t_64_sync_handler+0x134/0x150 el0t_64_sync+0x17c/0x180 This patch (of 4): The largest page cache order can be HPAGE_PMD_ORDER (13) on ARM64 with 64KB base page size. The xarray entry with this order can't be split as the following error messages indicate. ------------[ cut here ]------------ WARNING: CPU: 35 PID: 7484 at lib/xarray.c:1025 xas_split_alloc+0xf8/0x128 Modules linked in: nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib \ nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct \ nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 \ ip_set rfkill nf_tables nfnetlink vfat fat virtio_balloon drm \ fuse xfs libcrc32c crct10dif_ce ghash_ce sha2_ce sha256_arm64 \ sha1_ce virtio_net net_failover virtio_console virtio_blk failover \ dimlib virtio_mmio CPU: 35 PID: 7484 Comm: test Kdump: loaded Tainted: G W 6.10.0-rc5-gavin+ #9 Hardware name: QEMU KVM Virtual Machine, BIOS edk2-20240524-1.el9 05/24/2024 pstate: 83400005 (Nzcv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--) pc : xas_split_alloc+0xf8/0x128 lr : split_huge_page_to_list_to_order+0x1c4/0x720 sp : ffff800087a4f6c0 x29: ffff800087a4f6c0 x28: ffff800087a4f720 x27: 000000001fffffff x26: 0000000000000c40 x25: 000000000000000d x24: ffff00010625b858 x23: ffff800087a4f720 x22: ffffffdfc0780000 x21: 0000000000000000 x20: 0000000000000000 x19: ffffffdfc0780000 x18: 000000001ff40000 x17: 00000000ffffffff x16: 0000018000000000 x15: 51ec004000000000 x14: 0000e00000000000 x13: 0000000000002000 x12: 0000000000000020 x11: 51ec000000000000 x10: 51ece1c0ffff8000 x9 : ffffbeb961a44d28 x8 : 0000000000000003 x7 : ffffffdfc0456420 x6 : ffff0000e1aa6eb8 x5 : 20bf08b4fe778fca x4 : ffffffdfc0456420 x3 : 0000000000000c40 x2 : 000000000000000d x1 : 000000000000000c x0 : 0000000000000000 Call trace: xas_split_alloc+0xf8/0x128 split_huge_page_to_list_to_order+0x1c4/0x720 truncate_inode_partial_folio+0xdc/0x160 truncate_inode_pages_range+0x1b4/0x4a8 truncate_pagecache_range+0x84/0xa0 xfs_flush_unmap_range+0x70/0x90 [xfs] xfs_file_fallocate+0xfc/0x4d8 [xfs] vfs_fallocate+0x124/0x2e8 ksys_fallocate+0x4c/0xa0 __arm64_sys_fallocate+0x24/0x38 invoke_syscall.constprop.0+0x7c/0xd8 do_el0_svc+0xb4/0xd0 el0_svc+0x44/0x1d8 el0t_64_sync_handler+0x134/0x150 el0t_64_sync+0x17c/0x180 Fix it by decreasing MAX_PAGECACHE_ORDER to the largest supported order by xarray. For this specific case, MAX_PAGECACHE_ORDER is dropped from 13 to 11 when CONFIG_BASE_SMALL is disabled. Link: https://lkml.kernel.org/r/20240627003953.1262512-1-gshan@redhat.com Link: https://lkml.kernel.org/r/20240627003953.1262512-2-gshan@redhat.com Fixes: 793917d997df ("mm/readahead: Add large folio readahead") Signed-off-by: Gavin Shan <gshan(a)redhat.com> Suggested-by: David Hildenbrand <david(a)redhat.com> Acked-by: David Hildenbrand <david(a)redhat.com> Cc: Darrick J. Wong <djwong(a)kernel.org> Cc: Don Dutile <ddutile(a)redhat.com> Cc: Hugh Dickins <hughd(a)google.com> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Ryan Roberts <ryan.roberts(a)arm.com> Cc: William Kucharski <william.kucharski(a)oracle.com> Cc: Zhenyu Zhang <zhenyzha(a)redhat.com> Cc: <stable(a)vger.kernel.org> [5.18+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 59f1df0cde5a..a0a026d2d244 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -354,11 +354,18 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) * a good order (that's 1MB if you're using 4kB pages) */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define MAX_PAGECACHE_ORDER HPAGE_PMD_ORDER +#define PREFERRED_MAX_PAGECACHE_ORDER HPAGE_PMD_ORDER #else -#define MAX_PAGECACHE_ORDER 8 +#define PREFERRED_MAX_PAGECACHE_ORDER 8 #endif +/* + * xas_split_alloc() does not support arbitrary orders. This implies no + * 512MB THP on ARM64 with 64KB base page size. + */ +#define MAX_XAS_ORDER (XA_CHUNK_SHIFT * 2 - 1) +#define MAX_PAGECACHE_ORDER min(MAX_XAS_ORDER, PREFERRED_MAX_PAGECACHE_ORDER) + /** * mapping_set_large_folios() - Indicate the file supports large folios. * @mapping: The file.

2 months, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] mm: gup: stop abusing try_grab_folio" failed to apply to 6.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.9-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-6.9.y git checkout FETCH_HEAD git cherry-pick -x f442fa6141379a20b48ae3efabee827a3d260787 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024071539-recopy-opulently-c509@gregkh' --subject-prefix 'PATCH 6.9.y' HEAD^.. Possible dependencies: f442fa614137 ("mm: gup: stop abusing try_grab_folio") 01d89b93e176 ("mm/gup: fix hugepd handling in hugetlb rework") 9cbe4954c6d9 ("gup: use folios for gup_devmap") 53e45c4f6d4f ("mm: convert put_devmap_managed_page_refs() to put_devmap_managed_folio_refs()") 6785c54a1b43 ("mm: remove put_devmap_managed_page()") 25176ad09ca3 ("mm/treewide: rename CONFIG_HAVE_FAST_GUP to CONFIG_HAVE_GUP_FAST") 23babe1934d7 ("mm/gup: consistently name GUP-fast functions") a12083d721d7 ("mm/gup: handle hugepd for follow_page()") 4418c522f683 ("mm/gup: handle huge pmd for follow_pmd_mask()") 1b1676180246 ("mm/gup: handle huge pud for follow_pud_mask()") caf8cab79857 ("mm/gup: cache *pudp in follow_pud_mask()") 878b0c451621 ("mm/gup: handle hugetlb for no_page_table()") f3c94c625fe3 ("mm/gup: refactor record_subpages() to find 1st small page") 607c63195d63 ("mm/gup: drop gup_fast_folio_allowed() in hugepd processing") f002882ca369 ("mm: merge folio_is_secretmem() and folio_fast_pin_allowed() into gup_fast_folio_allowed()") 1965e933ddeb ("mm/treewide: replace pXd_huge() with pXd_leaf()") 7db86dc389aa ("mm/gup: merge pXd huge mapping checks") 089f92141ed0 ("mm/gup: check p4d presence before going on") e6fd5564c07c ("mm/gup: cache p4d in follow_p4d_mask()") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From f442fa6141379a20b48ae3efabee827a3d260787 Mon Sep 17 00:00:00 2001 From: Yang Shi <yang(a)os.amperecomputing.com> Date: Fri, 28 Jun 2024 12:14:58 -0700 Subject: [PATCH] mm: gup: stop abusing try_grab_folio A kernel warning was reported when pinning folio in CMA memory when launching SEV virtual machine. The splat looks like: [ 464.325306] WARNING: CPU: 13 PID: 6734 at mm/gup.c:1313 __get_user_pages+0x423/0x520 [ 464.325464] CPU: 13 PID: 6734 Comm: qemu-kvm Kdump: loaded Not tainted 6.6.33+ #6 [ 464.325477] RIP: 0010:__get_user_pages+0x423/0x520 [ 464.325515] Call Trace: [ 464.325520] <TASK> [ 464.325523] ? __get_user_pages+0x423/0x520 [ 464.325528] ? __warn+0x81/0x130 [ 464.325536] ? __get_user_pages+0x423/0x520 [ 464.325541] ? report_bug+0x171/0x1a0 [ 464.325549] ? handle_bug+0x3c/0x70 [ 464.325554] ? exc_invalid_op+0x17/0x70 [ 464.325558] ? asm_exc_invalid_op+0x1a/0x20 [ 464.325567] ? __get_user_pages+0x423/0x520 [ 464.325575] __gup_longterm_locked+0x212/0x7a0 [ 464.325583] internal_get_user_pages_fast+0xfb/0x190 [ 464.325590] pin_user_pages_fast+0x47/0x60 [ 464.325598] sev_pin_memory+0xca/0x170 [kvm_amd] [ 464.325616] sev_mem_enc_register_region+0x81/0x130 [kvm_amd] Per the analysis done by yangge, when starting the SEV virtual machine, it will call pin_user_pages_fast(..., FOLL_LONGTERM, ...) to pin the memory. But the page is in CMA area, so fast GUP will fail then fallback to the slow path due to the longterm pinnalbe check in try_grab_folio(). The slow path will try to pin the pages then migrate them out of CMA area. But the slow path also uses try_grab_folio() to pin the page, it will also fail due to the same check then the above warning is triggered. In addition, the try_grab_folio() is supposed to be used in fast path and it elevates folio refcount by using add ref unless zero. We are guaranteed to have at least one stable reference in slow path, so the simple atomic add could be used. The performance difference should be trivial, but the misuse may be confusing and misleading. Redefined try_grab_folio() to try_grab_folio_fast(), and try_grab_page() to try_grab_folio(), and use them in the proper paths. This solves both the abuse and the kernel warning. The proper naming makes their usecase more clear and should prevent from abusing in the future. peterx said: : The user will see the pin fails, for gpu-slow it further triggers the WARN : right below that failure (as in the original report): : : folio = try_grab_folio(page, page_increm - 1, : foll_flags); : if (WARN_ON_ONCE(!folio)) { <------------------------ here : /* : * Release the 1st page ref if the : * folio is problematic, fail hard. : */ : gup_put_folio(page_folio(page), 1, : foll_flags); : ret = -EFAULT; : goto out; : } [1] https://lore.kernel.org/linux-mm/1719478388-31917-1-git-send-email-yangge11… [shy828301(a)gmail.com: fix implicit declaration of function try_grab_folio_fast] Link: https://lkml.kernel.org/r/CAHbLzkowMSso-4Nufc9hcMehQsK9PNz3OSu-+eniU-2Mm-xj… Link: https://lkml.kernel.org/r/20240628191458.2605553-1-yang@os.amperecomputing.… Fixes: 57edfcfd3419 ("mm/gup: accelerate thp gup even for "pages != NULL"") Signed-off-by: Yang Shi <yang(a)os.amperecomputing.com> Reported-by: yangge <yangge1116(a)126.com> Cc: Christoph Hellwig <hch(a)infradead.org> Cc: David Hildenbrand <david(a)redhat.com> Cc: Peter Xu <peterx(a)redhat.com> Cc: <stable(a)vger.kernel.org> [6.6+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/gup.c b/mm/gup.c index 469799f805f1..f1d6bc06eb52 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -97,95 +97,6 @@ static inline struct folio *try_get_folio(struct page *page, int refs) return folio; } -/** - * try_grab_folio() - Attempt to get or pin a folio. - * @page: pointer to page to be grabbed - * @refs: the value to (effectively) add to the folio's refcount - * @flags: gup flags: these are the FOLL_* flag values. - * - * "grab" names in this file mean, "look at flags to decide whether to use - * FOLL_PIN or FOLL_GET behavior, when incrementing the folio's refcount. - * - * Either FOLL_PIN or FOLL_GET (or neither) must be set, but not both at the - * same time. (That's true throughout the get_user_pages*() and - * pin_user_pages*() APIs.) Cases: - * - * FOLL_GET: folio's refcount will be incremented by @refs. - * - * FOLL_PIN on large folios: folio's refcount will be incremented by - * @refs, and its pincount will be incremented by @refs. - * - * FOLL_PIN on single-page folios: folio's refcount will be incremented by - * @refs * GUP_PIN_COUNTING_BIAS. - * - * Return: The folio containing @page (with refcount appropriately - * incremented) for success, or NULL upon failure. If neither FOLL_GET - * nor FOLL_PIN was set, that's considered failure, and furthermore, - * a likely bug in the caller, so a warning is also emitted. - */ -struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags) -{ - struct folio *folio; - - if (WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == 0)) - return NULL; - - if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page))) - return NULL; - - if (flags & FOLL_GET) - return try_get_folio(page, refs); - - /* FOLL_PIN is set */ - - /* - * Don't take a pin on the zero page - it's not going anywhere - * and it is used in a *lot* of places. - */ - if (is_zero_page(page)) - return page_folio(page); - - folio = try_get_folio(page, refs); - if (!folio) - return NULL; - - /* - * Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a - * right zone, so fail and let the caller fall back to the slow - * path. - */ - if (unlikely((flags & FOLL_LONGTERM) && - !folio_is_longterm_pinnable(folio))) { - if (!put_devmap_managed_folio_refs(folio, refs)) - folio_put_refs(folio, refs); - return NULL; - } - - /* - * When pinning a large folio, use an exact count to track it. - * - * However, be sure to *also* increment the normal folio - * refcount field at least once, so that the folio really - * is pinned. That's why the refcount from the earlier - * try_get_folio() is left intact. - */ - if (folio_test_large(folio)) - atomic_add(refs, &folio->_pincount); - else - folio_ref_add(folio, - refs * (GUP_PIN_COUNTING_BIAS - 1)); - /* - * Adjust the pincount before re-checking the PTE for changes. - * This is essentially a smp_mb() and is paired with a memory - * barrier in folio_try_share_anon_rmap_*(). - */ - smp_mb__after_atomic(); - - node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs); - - return folio; -} - static void gup_put_folio(struct folio *folio, int refs, unsigned int flags) { if (flags & FOLL_PIN) { @@ -203,58 +114,59 @@ static void gup_put_folio(struct folio *folio, int refs, unsigned int flags) } /** - * try_grab_page() - elevate a page's refcount by a flag-dependent amount - * @page: pointer to page to be grabbed - * @flags: gup flags: these are the FOLL_* flag values. + * try_grab_folio() - add a folio's refcount by a flag-dependent amount + * @folio: pointer to folio to be grabbed + * @refs: the value to (effectively) add to the folio's refcount + * @flags: gup flags: these are the FOLL_* flag values * * This might not do anything at all, depending on the flags argument. * * "grab" names in this file mean, "look at flags to decide whether to use - * FOLL_PIN or FOLL_GET behavior, when incrementing the page's refcount. + * FOLL_PIN or FOLL_GET behavior, when incrementing the folio's refcount. * * Either FOLL_PIN or FOLL_GET (or neither) may be set, but not both at the same - * time. Cases: please see the try_grab_folio() documentation, with - * "refs=1". + * time. * * Return: 0 for success, or if no action was required (if neither FOLL_PIN * nor FOLL_GET was set, nothing is done). A negative error code for failure: * - * -ENOMEM FOLL_GET or FOLL_PIN was set, but the page could not + * -ENOMEM FOLL_GET or FOLL_PIN was set, but the folio could not * be grabbed. + * + * It is called when we have a stable reference for the folio, typically in + * GUP slow path. */ -int __must_check try_grab_page(struct page *page, unsigned int flags) +int __must_check try_grab_folio(struct folio *folio, int refs, + unsigned int flags) { - struct folio *folio = page_folio(page); - if (WARN_ON_ONCE(folio_ref_count(folio) <= 0)) return -ENOMEM; - if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page))) + if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(&folio->page))) return -EREMOTEIO; if (flags & FOLL_GET) - folio_ref_inc(folio); + folio_ref_add(folio, refs); else if (flags & FOLL_PIN) { /* * Don't take a pin on the zero page - it's not going anywhere * and it is used in a *lot* of places. */ - if (is_zero_page(page)) + if (is_zero_folio(folio)) return 0; /* - * Similar to try_grab_folio(): be sure to *also* - * increment the normal page refcount field at least once, + * Increment the normal page refcount field at least once, * so that the page really is pinned. */ if (folio_test_large(folio)) { - folio_ref_add(folio, 1); - atomic_add(1, &folio->_pincount); + folio_ref_add(folio, refs); + atomic_add(refs, &folio->_pincount); } else { - folio_ref_add(folio, GUP_PIN_COUNTING_BIAS); + folio_ref_add(folio, refs * GUP_PIN_COUNTING_BIAS); } - node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, 1); + node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs); } return 0; @@ -515,6 +427,102 @@ static int record_subpages(struct page *page, unsigned long sz, return nr; } + +/** + * try_grab_folio_fast() - Attempt to get or pin a folio in fast path. + * @page: pointer to page to be grabbed + * @refs: the value to (effectively) add to the folio's refcount + * @flags: gup flags: these are the FOLL_* flag values. + * + * "grab" names in this file mean, "look at flags to decide whether to use + * FOLL_PIN or FOLL_GET behavior, when incrementing the folio's refcount. + * + * Either FOLL_PIN or FOLL_GET (or neither) must be set, but not both at the + * same time. (That's true throughout the get_user_pages*() and + * pin_user_pages*() APIs.) Cases: + * + * FOLL_GET: folio's refcount will be incremented by @refs. + * + * FOLL_PIN on large folios: folio's refcount will be incremented by + * @refs, and its pincount will be incremented by @refs. + * + * FOLL_PIN on single-page folios: folio's refcount will be incremented by + * @refs * GUP_PIN_COUNTING_BIAS. + * + * Return: The folio containing @page (with refcount appropriately + * incremented) for success, or NULL upon failure. If neither FOLL_GET + * nor FOLL_PIN was set, that's considered failure, and furthermore, + * a likely bug in the caller, so a warning is also emitted. + * + * It uses add ref unless zero to elevate the folio refcount and must be called + * in fast path only. + */ +static struct folio *try_grab_folio_fast(struct page *page, int refs, + unsigned int flags) +{ + struct folio *folio; + + /* Raise warn if it is not called in fast GUP */ + VM_WARN_ON_ONCE(!irqs_disabled()); + + if (WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == 0)) + return NULL; + + if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page))) + return NULL; + + if (flags & FOLL_GET) + return try_get_folio(page, refs); + + /* FOLL_PIN is set */ + + /* + * Don't take a pin on the zero page - it's not going anywhere + * and it is used in a *lot* of places. + */ + if (is_zero_page(page)) + return page_folio(page); + + folio = try_get_folio(page, refs); + if (!folio) + return NULL; + + /* + * Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a + * right zone, so fail and let the caller fall back to the slow + * path. + */ + if (unlikely((flags & FOLL_LONGTERM) && + !folio_is_longterm_pinnable(folio))) { + if (!put_devmap_managed_folio_refs(folio, refs)) + folio_put_refs(folio, refs); + return NULL; + } + + /* + * When pinning a large folio, use an exact count to track it. + * + * However, be sure to *also* increment the normal folio + * refcount field at least once, so that the folio really + * is pinned. That's why the refcount from the earlier + * try_get_folio() is left intact. + */ + if (folio_test_large(folio)) + atomic_add(refs, &folio->_pincount); + else + folio_ref_add(folio, + refs * (GUP_PIN_COUNTING_BIAS - 1)); + /* + * Adjust the pincount before re-checking the PTE for changes. + * This is essentially a smp_mb() and is paired with a memory + * barrier in folio_try_share_anon_rmap_*(). + */ + smp_mb__after_atomic(); + + node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs); + + return folio; +} #endif /* CONFIG_ARCH_HAS_HUGEPD || CONFIG_HAVE_GUP_FAST */ #ifdef CONFIG_ARCH_HAS_HUGEPD @@ -535,7 +543,7 @@ static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end, */ static int gup_hugepte(struct vm_area_struct *vma, pte_t *ptep, unsigned long sz, unsigned long addr, unsigned long end, unsigned int flags, - struct page **pages, int *nr) + struct page **pages, int *nr, bool fast) { unsigned long pte_end; struct page *page; @@ -558,9 +566,15 @@ static int gup_hugepte(struct vm_area_struct *vma, pte_t *ptep, unsigned long sz page = pte_page(pte); refs = record_subpages(page, sz, addr, end, pages + *nr); - folio = try_grab_folio(page, refs, flags); - if (!folio) - return 0; + if (fast) { + folio = try_grab_folio_fast(page, refs, flags); + if (!folio) + return 0; + } else { + folio = page_folio(page); + if (try_grab_folio(folio, refs, flags)) + return 0; + } if (unlikely(pte_val(pte) != pte_val(ptep_get(ptep)))) { gup_put_folio(folio, refs, flags); @@ -588,7 +602,7 @@ static int gup_hugepte(struct vm_area_struct *vma, pte_t *ptep, unsigned long sz static int gup_hugepd(struct vm_area_struct *vma, hugepd_t hugepd, unsigned long addr, unsigned int pdshift, unsigned long end, unsigned int flags, - struct page **pages, int *nr) + struct page **pages, int *nr, bool fast) { pte_t *ptep; unsigned long sz = 1UL << hugepd_shift(hugepd); @@ -598,7 +612,8 @@ static int gup_hugepd(struct vm_area_struct *vma, hugepd_t hugepd, ptep = hugepte_offset(hugepd, addr, pdshift); do { next = hugepte_addr_end(addr, end, sz); - ret = gup_hugepte(vma, ptep, sz, addr, end, flags, pages, nr); + ret = gup_hugepte(vma, ptep, sz, addr, end, flags, pages, nr, + fast); if (ret != 1) return ret; } while (ptep++, addr = next, addr != end); @@ -625,7 +640,7 @@ static struct page *follow_hugepd(struct vm_area_struct *vma, hugepd_t hugepd, ptep = hugepte_offset(hugepd, addr, pdshift); ptl = huge_pte_lock(h, vma->vm_mm, ptep); ret = gup_hugepd(vma, hugepd, addr, pdshift, addr + PAGE_SIZE, - flags, &page, &nr); + flags, &page, &nr, false); spin_unlock(ptl); if (ret == 1) { @@ -642,7 +657,7 @@ static struct page *follow_hugepd(struct vm_area_struct *vma, hugepd_t hugepd, static inline int gup_hugepd(struct vm_area_struct *vma, hugepd_t hugepd, unsigned long addr, unsigned int pdshift, unsigned long end, unsigned int flags, - struct page **pages, int *nr) + struct page **pages, int *nr, bool fast) { return 0; } @@ -729,7 +744,7 @@ static struct page *follow_huge_pud(struct vm_area_struct *vma, gup_must_unshare(vma, flags, page)) return ERR_PTR(-EMLINK); - ret = try_grab_page(page, flags); + ret = try_grab_folio(page_folio(page), 1, flags); if (ret) page = ERR_PTR(ret); else @@ -806,7 +821,7 @@ static struct page *follow_huge_pmd(struct vm_area_struct *vma, VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && !PageAnonExclusive(page), page); - ret = try_grab_page(page, flags); + ret = try_grab_folio(page_folio(page), 1, flags); if (ret) return ERR_PTR(ret); @@ -968,8 +983,8 @@ static struct page *follow_page_pte(struct vm_area_struct *vma, VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && !PageAnonExclusive(page), page); - /* try_grab_page() does nothing unless FOLL_GET or FOLL_PIN is set. */ - ret = try_grab_page(page, flags); + /* try_grab_folio() does nothing unless FOLL_GET or FOLL_PIN is set. */ + ret = try_grab_folio(page_folio(page), 1, flags); if (unlikely(ret)) { page = ERR_PTR(ret); goto out; @@ -1233,7 +1248,7 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address, goto unmap; *page = pte_page(entry); } - ret = try_grab_page(*page, gup_flags); + ret = try_grab_folio(page_folio(*page), 1, gup_flags); if (unlikely(ret)) goto unmap; out: @@ -1636,20 +1651,19 @@ static long __get_user_pages(struct mm_struct *mm, * pages. */ if (page_increm > 1) { - struct folio *folio; + struct folio *folio = page_folio(page); /* * Since we already hold refcount on the * large folio, this should never fail. */ - folio = try_grab_folio(page, page_increm - 1, - foll_flags); - if (WARN_ON_ONCE(!folio)) { + if (try_grab_folio(folio, page_increm - 1, + foll_flags)) { /* * Release the 1st page ref if the * folio is problematic, fail hard. */ - gup_put_folio(page_folio(page), 1, + gup_put_folio(folio, 1, foll_flags); ret = -EFAULT; goto out; @@ -2797,7 +2811,6 @@ EXPORT_SYMBOL(get_user_pages_unlocked); * This code is based heavily on the PowerPC implementation by Nick Piggin. */ #ifdef CONFIG_HAVE_GUP_FAST - /* * Used in the GUP-fast path to determine whether GUP is permitted to work on * a specific folio. @@ -2962,7 +2975,7 @@ static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, VM_BUG_ON(!pfn_valid(pte_pfn(pte))); page = pte_page(pte); - folio = try_grab_folio(page, 1, flags); + folio = try_grab_folio_fast(page, 1, flags); if (!folio) goto pte_unmap; @@ -3049,7 +3062,7 @@ static int gup_fast_devmap_leaf(unsigned long pfn, unsigned long addr, break; } - folio = try_grab_folio(page, 1, flags); + folio = try_grab_folio_fast(page, 1, flags); if (!folio) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); break; @@ -3138,7 +3151,7 @@ static int gup_fast_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr, page = pmd_page(orig); refs = record_subpages(page, PMD_SIZE, addr, end, pages + *nr); - folio = try_grab_folio(page, refs, flags); + folio = try_grab_folio_fast(page, refs, flags); if (!folio) return 0; @@ -3182,7 +3195,7 @@ static int gup_fast_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr, page = pud_page(orig); refs = record_subpages(page, PUD_SIZE, addr, end, pages + *nr); - folio = try_grab_folio(page, refs, flags); + folio = try_grab_folio_fast(page, refs, flags); if (!folio) return 0; @@ -3222,7 +3235,7 @@ static int gup_fast_pgd_leaf(pgd_t orig, pgd_t *pgdp, unsigned long addr, page = pgd_page(orig); refs = record_subpages(page, PGDIR_SIZE, addr, end, pages + *nr); - folio = try_grab_folio(page, refs, flags); + folio = try_grab_folio_fast(page, refs, flags); if (!folio) return 0; @@ -3276,7 +3289,8 @@ static int gup_fast_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, * pmd format and THP pmd format */ if (gup_hugepd(NULL, __hugepd(pmd_val(pmd)), addr, - PMD_SHIFT, next, flags, pages, nr) != 1) + PMD_SHIFT, next, flags, pages, nr, + true) != 1) return 0; } else if (!gup_fast_pte_range(pmd, pmdp, addr, next, flags, pages, nr)) @@ -3306,7 +3320,8 @@ static int gup_fast_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, return 0; } else if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) { if (gup_hugepd(NULL, __hugepd(pud_val(pud)), addr, - PUD_SHIFT, next, flags, pages, nr) != 1) + PUD_SHIFT, next, flags, pages, nr, + true) != 1) return 0; } else if (!gup_fast_pmd_range(pudp, pud, addr, next, flags, pages, nr)) @@ -3333,7 +3348,8 @@ static int gup_fast_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, BUILD_BUG_ON(p4d_leaf(p4d)); if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) { if (gup_hugepd(NULL, __hugepd(p4d_val(p4d)), addr, - P4D_SHIFT, next, flags, pages, nr) != 1) + P4D_SHIFT, next, flags, pages, nr, + true) != 1) return 0; } else if (!gup_fast_pud_range(p4dp, p4d, addr, next, flags, pages, nr)) @@ -3362,7 +3378,8 @@ static void gup_fast_pgd_range(unsigned long addr, unsigned long end, return; } else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) { if (gup_hugepd(NULL, __hugepd(pgd_val(pgd)), addr, - PGDIR_SHIFT, next, flags, pages, nr) != 1) + PGDIR_SHIFT, next, flags, pages, nr, + true) != 1) return; } else if (!gup_fast_p4d_range(pgdp, pgd, addr, next, flags, pages, nr)) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index db7946a0a28c..2120f7478e55 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1331,7 +1331,7 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, if (!*pgmap) return ERR_PTR(-EFAULT); page = pfn_to_page(pfn); - ret = try_grab_page(page, flags); + ret = try_grab_folio(page_folio(page), 1, flags); if (ret) page = ERR_PTR(ret); diff --git a/mm/internal.h b/mm/internal.h index 6902b7dd8509..cc2c5e07fad3 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -1182,8 +1182,8 @@ int migrate_device_coherent_page(struct page *page); /* * mm/gup.c */ -struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags); -int __must_check try_grab_page(struct page *page, unsigned int flags); +int __must_check try_grab_folio(struct folio *folio, int refs, + unsigned int flags); /* * mm/huge_memory.c

2 months, 3 weeks

1
0
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror July 2024