- Kernel - mailweb.openeuler.org

[PATCH OLK-6.6 v2] bpf: Fail verification for sign-extension of packet data/data_end/data_meta
by Chen Zhongjin 04 Nov '24

04 Nov '24

From: Yonghong Song <yonghong.song(a)linux.dev> mainline inclusion from mainline-v6.12-rc1 commit 92de36080c93296ef9005690705cba260b9bd68a category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAYPJQ CVE: CVE-2024-47702 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- syzbot reported a kernel crash due to commit 1f1e864b6555 ("bpf: Handle sign-extenstin ctx member accesses"). The reason is due to sign-extension of 32-bit load for packet data/data_end/data_meta uapi field. The original code looks like: r2 = *(s32 *)(r1 + 76) /* load __sk_buff->data */ r3 = *(u32 *)(r1 + 80) /* load __sk_buff->data_end */ r0 = r2 r0 += 8 if r3 > r0 goto +1 ... Note that __sk_buff->data load has 32-bit sign extension. After verification and convert_ctx_accesses(), the final asm code looks like: r2 = *(u64 *)(r1 +208) r2 = (s32)r2 r3 = *(u64 *)(r1 +80) r0 = r2 r0 += 8 if r3 > r0 goto pc+1 ... Note that 'r2 = (s32)r2' may make the kernel __sk_buff->data address invalid which may cause runtime failure. Currently, in C code, typically we have void *data = (void *)(long)skb->data; void *data_end = (void *)(long)skb->data_end; ... and it will generate r2 = *(u64 *)(r1 +208) r3 = *(u64 *)(r1 +80) r0 = r2 r0 += 8 if r3 > r0 goto pc+1 If we allow sign-extension, void *data = (void *)(long)(int)skb->data; void *data_end = (void *)(long)skb->data_end; ... the generated code looks like r2 = *(u64 *)(r1 +208) r2 <<= 32 r2 s>>= 32 r3 = *(u64 *)(r1 +80) r0 = r2 r0 += 8 if r3 > r0 goto pc+1 and this will cause verification failure since "r2 <<= 32" is not allowed as "r2" is a packet pointer. To fix this issue for case r2 = *(s32 *)(r1 + 76) /* load __sk_buff->data */ this patch added additional checking in is_valid_access() callback function for packet data/data_end/data_meta access. If those accesses are with sign-extenstion, the verification will fail. [1] https://lore.kernel.org/bpf/000000000000c90eee061d236d37@google.com/ Reported-by: syzbot+ad9ec60c8eaf69e6f99c(a)syzkaller.appspotmail.com Fixes: 1f1e864b6555 ("bpf: Handle sign-extenstin ctx member accesses") Acked-by: Eduard Zingerman <eddyz87(a)gmail.com> Signed-off-by: Yonghong Song <yonghong.song(a)linux.dev> Link: https://lore.kernel.org/r/20240723153439.2429035-1-yonghong.song@linux.dev Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Signed-off-by: Andrii Nakryiko <andrii(a)kernel.org> Conflicts: kernel/bpf/verifier.c [patch set:("bpf, lsm: Add check for BPF LSM return value") was not merged] include/linux/bpf.h [fix struct bpf_insn_access_aux KABI breakage] Signed-off-by: Chen Zhongjin <chenzhongjin(a)huawei.com> --- include/linux/bpf.h | 1 + kernel/bpf/verifier.c | 5 +++-- net/core/filter.c | 21 ++++++++++++++++----- 3 files changed, 20 insertions(+), 7 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8c4c2c39a6c1..c9351ab31e05 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -920,6 +920,7 @@ struct bpf_insn_access_aux { }; }; struct bpf_verifier_log *log; /* for verbose logs */ + KABI_EXTEND(bool is_ldsx) }; static inline void diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index d1041517a984..82f2be2ddd06 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5549,11 +5549,12 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, /* check access to 'struct bpf_context' fields. Supports fixed offsets only */ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, int size, enum bpf_access_type t, enum bpf_reg_type *reg_type, - struct btf **btf, u32 *btf_id) + struct btf **btf, u32 *btf_id, bool is_ldsx) { struct bpf_insn_access_aux info = { .reg_type = *reg_type, .log = &env->log, + .is_ldsx = is_ldsx, }; if (env->ops->is_valid_access && @@ -6802,7 +6803,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn return err; err = check_ctx_access(env, insn_idx, off, size, t, &reg_type, &btf, - &btf_id); + &btf_id, is_ldsx); if (err) verbose_linfo(env, insn_idx, "; "); if (!err && t == BPF_READ && value_regno >= 0) { diff --git a/net/core/filter.c b/net/core/filter.c index e16d746c23da..e4f1dc9f222b 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -8601,13 +8601,16 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type if (off + size > offsetofend(struct __sk_buff, cb[4])) return false; break; + case bpf_ctx_range(struct __sk_buff, data): + case bpf_ctx_range(struct __sk_buff, data_meta): + case bpf_ctx_range(struct __sk_buff, data_end): + if (info->is_ldsx || size != size_default) + return false; + break; case bpf_ctx_range_till(struct __sk_buff, remote_ip6[0], remote_ip6[3]): case bpf_ctx_range_till(struct __sk_buff, local_ip6[0], local_ip6[3]): case bpf_ctx_range_till(struct __sk_buff, remote_ip4, remote_ip4): case bpf_ctx_range_till(struct __sk_buff, local_ip4, local_ip4): - case bpf_ctx_range(struct __sk_buff, data): - case bpf_ctx_range(struct __sk_buff, data_meta): - case bpf_ctx_range(struct __sk_buff, data_end): if (size != size_default) return false; break; @@ -9051,6 +9054,14 @@ static bool xdp_is_valid_access(int off, int size, } } return false; + } else { + switch (off) { + case offsetof(struct xdp_md, data_meta): + case offsetof(struct xdp_md, data): + case offsetof(struct xdp_md, data_end): + if (info->is_ldsx) + return false; + } } switch (off) { @@ -9381,12 +9392,12 @@ static bool flow_dissector_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct __sk_buff, data): - if (size != size_default) + if (info->is_ldsx || size != size_default) return false; info->reg_type = PTR_TO_PACKET; return true; case bpf_ctx_range(struct __sk_buff, data_end): - if (size != size_default) + if (info->is_ldsx || size != size_default) return false; info->reg_type = PTR_TO_PACKET_END; return true; -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS-SP1] [Backport] exfat: fix memory leak in exfat_load_bitmap()
by Yongjian Sun 04 Nov '24

04 Nov '24

From: Yuezhang Mo <Yuezhang.Mo(a)sony.com> mainline inclusion from mainline-v6.12-rc1 commit d2b537b3e533f28e0d97293fe9293161fe8cd137 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAYRBG CVE: CVE-2024-50013 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- If the first directory entry in the root directory is not a bitmap directory entry, 'bh' will not be released and reassigned, which will cause a memory leak. Fixes: 1e49a94cf707 ("exfat: add bitmap operations") Cc: stable(a)vger.kernel.org Signed-off-by: Yuezhang Mo <Yuezhang.Mo(a)sony.com> Reviewed-by: Aoyama Wataru <wataru.aoyama(a)sony.com> Signed-off-by: Namjae Jeon <linkinjeon(a)kernel.org> Signed-off-by: Yongjian Sun <sunyongjian1(a)huawei.com> --- fs/exfat/balloc.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/exfat/balloc.c b/fs/exfat/balloc.c index 258b6bb5762a..702187cea05d 100644 --- a/fs/exfat/balloc.c +++ b/fs/exfat/balloc.c @@ -110,11 +110,8 @@ int exfat_load_bitmap(struct super_block *sb) return -EIO; type = exfat_get_entry_type(ep); - if (type == TYPE_UNUSED) - break; - if (type != TYPE_BITMAP) - continue; - if (ep->dentry.bitmap.flags == 0x0) { + if (type == TYPE_BITMAP && + ep->dentry.bitmap.flags == 0x0) { int err; err = exfat_allocate_bitmap(sb, ep); @@ -122,6 +119,9 @@ int exfat_load_bitmap(struct super_block *sb) return err; } brelse(bh); + + if (type == TYPE_UNUSED) + return -EINVAL; } if (exfat_get_next_cluster(sb, &clu.dir)) -- 2.39.2

2 13

[PATCH OLK-6.6] ext4: update orig_path in ext4_find_extent()
by Baokun Li 04 Nov '24

04 Nov '24

stable inclusion from stable-v6.6.55 commit f55ecc58d07a6c1f6d6d5b5af125c25f8da0bda2 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAZ5OQ CVE: CVE-2024-49881 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 5b4b2dcace35f618fe361a87bae6f0d13af31bc1 upstream. In ext4_find_extent(), if the path is not big enough, we free it and set *orig_path to NULL. But after reallocating and successfully initializing the path, we don't update *orig_path, in which case the caller gets a valid path but a NULL ppath, and this may cause a NULL pointer dereference or a path memory leak. For example: ext4_split_extent path = *ppath = 2000 ext4_find_extent if (depth > path[0].p_maxdepth) kfree(path = 2000); *orig_path = path = NULL; path = kcalloc() = 3000 ext4_split_extent_at(*ppath = NULL) path = *ppath; ex = path[depth].p_ext; // NULL pointer dereference! ================================================================== BUG: kernel NULL pointer dereference, address: 0000000000000010 CPU: 6 UID: 0 PID: 576 Comm: fsstress Not tainted 6.11.0-rc2-dirty #847 RIP: 0010:ext4_split_extent_at+0x6d/0x560 Call Trace: <TASK> ext4_split_extent.isra.0+0xcb/0x1b0 ext4_ext_convert_to_initialized+0x168/0x6c0 ext4_ext_handle_unwritten_extents+0x325/0x4d0 ext4_ext_map_blocks+0x520/0xdb0 ext4_map_blocks+0x2b0/0x690 ext4_iomap_begin+0x20e/0x2c0 [...] ================================================================== Therefore, *orig_path is updated when the extent lookup succeeds, so that the caller can safely use path or *ppath. Fixes: 10809df84a4d ("ext4: teach ext4_ext_find_extent() to realloc path if necessary") Cc: stable(a)kernel.org Signed-off-by: Baokun Li <libaokun1(a)huawei.com> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://patch.msgid.link/20240822023545.1994557-6-libaokun@huaweicloud.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Baokun Li <libaokun1(a)huawei.com> --- fs/ext4/extents.c | 3 ++- fs/ext4/move_extent.c | 1 - 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index ef37cee9c27e..d9c51d42f21a 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -968,6 +968,8 @@ ext4_find_extent(struct inode *inode, ext4_lblk_t block, ext4_ext_show_path(inode, path); + if (orig_path) + *orig_path = path; return path; err: @@ -3260,7 +3262,6 @@ static int ext4_split_extent_at(handle_t *handle, } depth = ext_depth(inode); ex = path[depth].p_ext; - *ppath = path; if (EXT4_EXT_MAY_ZEROOUT & split_flag) { if (split_flag & (EXT4_EXT_DATA_VALID1|EXT4_EXT_DATA_VALID2)) { diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 2b6288c2df43..45191e01fbbc 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -36,7 +36,6 @@ get_ext_path(struct inode *inode, ext4_lblk_t lblock, *ppath = NULL; return -ENODATA; } - *ppath = path; return 0; } -- 2.46.1

2 1

[PATCH openEuler-1.0-LTS] ext4: update orig_path in ext4_find_extent()
by Baokun Li 04 Nov '24

04 Nov '24

stable inclusion from stable-v5.10.227 commit 6766937d0327000ac1b87c97bbecdd28b0dd6599 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAZ5OQ CVE: CVE-2024-49881 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 5b4b2dcace35f618fe361a87bae6f0d13af31bc1 upstream. In ext4_find_extent(), if the path is not big enough, we free it and set *orig_path to NULL. But after reallocating and successfully initializing the path, we don't update *orig_path, in which case the caller gets a valid path but a NULL ppath, and this may cause a NULL pointer dereference or a path memory leak. For example: ext4_split_extent path = *ppath = 2000 ext4_find_extent if (depth > path[0].p_maxdepth) kfree(path = 2000); *orig_path = path = NULL; path = kcalloc() = 3000 ext4_split_extent_at(*ppath = NULL) path = *ppath; ex = path[depth].p_ext; // NULL pointer dereference! ================================================================== BUG: kernel NULL pointer dereference, address: 0000000000000010 CPU: 6 UID: 0 PID: 576 Comm: fsstress Not tainted 6.11.0-rc2-dirty #847 RIP: 0010:ext4_split_extent_at+0x6d/0x560 Call Trace: <TASK> ext4_split_extent.isra.0+0xcb/0x1b0 ext4_ext_convert_to_initialized+0x168/0x6c0 ext4_ext_handle_unwritten_extents+0x325/0x4d0 ext4_ext_map_blocks+0x520/0xdb0 ext4_map_blocks+0x2b0/0x690 ext4_iomap_begin+0x20e/0x2c0 [...] ================================================================== Therefore, *orig_path is updated when the extent lookup succeeds, so that the caller can safely use path or *ppath. Fixes: 10809df84a4d ("ext4: teach ext4_ext_find_extent() to realloc path if necessary") Cc: stable(a)kernel.org Signed-off-by: Baokun Li <libaokun1(a)huawei.com> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://patch.msgid.link/20240822023545.1994557-6-libaokun@huaweicloud.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Baokun Li <libaokun1(a)huawei.com> --- fs/ext4/extents.c | 3 ++- fs/ext4/move_extent.c | 1 - 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 19a77f4ef8bd..447c81f82788 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -1011,6 +1011,8 @@ ext4_find_extent(struct inode *inode, ext4_lblk_t block, ext4_ext_show_path(inode, path); + if (orig_path) + *orig_path = path; return path; err: @@ -3384,7 +3386,6 @@ static int ext4_split_extent_at(handle_t *handle, } depth = ext_depth(inode); ex = path[depth].p_ext; - *ppath = path; if (EXT4_EXT_MAY_ZEROOUT & split_flag) { if (split_flag & (EXT4_EXT_DATA_VALID1|EXT4_EXT_DATA_VALID2)) { diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 4616d41216f3..5a1faad7cf81 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -37,7 +37,6 @@ get_ext_path(struct inode *inode, ext4_lblk_t lblock, *ppath = NULL; return -ENODATA; } - *ppath = path; return 0; } -- 2.46.1

2 1

[PATCH OLK-5.10] ext4: update orig_path in ext4_find_extent()
by Baokun Li 04 Nov '24

04 Nov '24

stable inclusion from stable-v5.10.227 commit 6766937d0327000ac1b87c97bbecdd28b0dd6599 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAZ5OQ CVE: CVE-2024-49881 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 5b4b2dcace35f618fe361a87bae6f0d13af31bc1 upstream. In ext4_find_extent(), if the path is not big enough, we free it and set *orig_path to NULL. But after reallocating and successfully initializing the path, we don't update *orig_path, in which case the caller gets a valid path but a NULL ppath, and this may cause a NULL pointer dereference or a path memory leak. For example: ext4_split_extent path = *ppath = 2000 ext4_find_extent if (depth > path[0].p_maxdepth) kfree(path = 2000); *orig_path = path = NULL; path = kcalloc() = 3000 ext4_split_extent_at(*ppath = NULL) path = *ppath; ex = path[depth].p_ext; // NULL pointer dereference! ================================================================== BUG: kernel NULL pointer dereference, address: 0000000000000010 CPU: 6 UID: 0 PID: 576 Comm: fsstress Not tainted 6.11.0-rc2-dirty #847 RIP: 0010:ext4_split_extent_at+0x6d/0x560 Call Trace: <TASK> ext4_split_extent.isra.0+0xcb/0x1b0 ext4_ext_convert_to_initialized+0x168/0x6c0 ext4_ext_handle_unwritten_extents+0x325/0x4d0 ext4_ext_map_blocks+0x520/0xdb0 ext4_map_blocks+0x2b0/0x690 ext4_iomap_begin+0x20e/0x2c0 [...] ================================================================== Therefore, *orig_path is updated when the extent lookup succeeds, so that the caller can safely use path or *ppath. Fixes: 10809df84a4d ("ext4: teach ext4_ext_find_extent() to realloc path if necessary") Cc: stable(a)kernel.org Signed-off-by: Baokun Li <libaokun1(a)huawei.com> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://patch.msgid.link/20240822023545.1994557-6-libaokun@huaweicloud.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Baokun Li <libaokun1(a)huawei.com> --- fs/ext4/extents.c | 3 ++- fs/ext4/move_extent.c | 1 - 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 4db1d47ccf0b..334e3d34b411 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -960,6 +960,8 @@ ext4_find_extent(struct inode *inode, ext4_lblk_t block, ext4_ext_show_path(inode, path); + if (orig_path) + *orig_path = path; return path; err: @@ -3261,7 +3263,6 @@ static int ext4_split_extent_at(handle_t *handle, } depth = ext_depth(inode); ex = path[depth].p_ext; - *ppath = path; if (EXT4_EXT_MAY_ZEROOUT & split_flag) { if (split_flag & (EXT4_EXT_DATA_VALID1|EXT4_EXT_DATA_VALID2)) { diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index f3d06beb79b2..886d2b161c23 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -36,7 +36,6 @@ get_ext_path(struct inode *inode, ext4_lblk_t lblock, *ppath = NULL; return -ENODATA; } - *ppath = path; return 0; } -- 2.46.1

2 1

[PATCH OLK-6.6] rseq/mm_cid: change the mm_cid macro default status and keep KABI consistent
by He Yujie 04 Nov '24

04 Nov '24

hulk inclusion category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IB1OJX -------------------------------- Changing the mm_cid macro to disable status by modifying Kconfig: def_bool n, and reserving the field for task_struct and mm_struct by using KABI_REPLACE to keep KABI consistent. Fixes: af7f588d8f73 ("sched: Introduce per-memory-map concurrency ID") Signed-off-by: He Yujie <coka.heyujie(a)huawei.com> --- arch/arm64/configs/openeuler_defconfig | 2 +- arch/x86/configs/openeuler_defconfig | 2 +- include/linux/mm_types.h | 6 ++++-- include/linux/sched.h | 7 +++++++ init/Kconfig | 2 +- 5 files changed, 14 insertions(+), 5 deletions(-) diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index 96ca8b990e22..67d02760f856 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -179,7 +179,7 @@ CONFIG_FAIR_GROUP_SCHED=y CONFIG_CFS_BANDWIDTH=y CONFIG_RT_GROUP_SCHED=y CONFIG_QOS_SCHED_DYNAMIC_AFFINITY=y -CONFIG_SCHED_MM_CID=y +# CONFIG_SCHED_MM_CID is not set CONFIG_QOS_SCHED_SMART_GRID=y CONFIG_CGROUP_PIDS=y CONFIG_CGROUP_RDMA=y diff --git a/arch/x86/configs/openeuler_defconfig b/arch/x86/configs/openeuler_defconfig index d95d966f7fb2..ea83b730a3be 100644 --- a/arch/x86/configs/openeuler_defconfig +++ b/arch/x86/configs/openeuler_defconfig @@ -197,7 +197,7 @@ CONFIG_FAIR_GROUP_SCHED=y CONFIG_CFS_BANDWIDTH=y CONFIG_RT_GROUP_SCHED=y CONFIG_QOS_SCHED_DYNAMIC_AFFINITY=y -CONFIG_SCHED_MM_CID=y +# CONFIG_SCHED_MM_CID is not set # CONFIG_QOS_SCHED_SMART_GRID is not set CONFIG_CGROUP_PIDS=y CONFIG_CGROUP_RDMA=y diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 793c16b99237..fdc047bdbc49 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -711,12 +711,10 @@ struct vm_area_struct { KABI_RESERVE(4) } __randomize_layout; -#ifdef CONFIG_SCHED_MM_CID struct mm_cid { u64 time; int cid; }; -#endif struct kioctx_table; struct iommu_mm_data; @@ -789,6 +787,10 @@ struct mm_struct { * When the next mm_cid scan is due (in jiffies). */ unsigned long mm_cid_next_scan; +#else + KABI_REPLACE(struct mm_cid __percpu *pcpu_cid, + struct mm_cid __percpu *pcpu_cid) + KABI_REPLACE(unsigned long mm_cid_next_scan, unsigned long mm_cid_next_scan) #endif #ifdef CONFIG_MMU atomic_long_t pgtables_bytes; /* size of all page tables */ diff --git a/include/linux/sched.h b/include/linux/sched.h index f40411aa7b70..7b1c53f71ee4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1355,6 +1355,13 @@ struct task_struct { int migrate_from_cpu; int mm_cid_active; /* Whether cid bitmap is active */ struct callback_head cid_work; +#else + KABI_REPLACE(int mm_cid, int mm_cid) + KABI_REPLACE(int last_mm_cid, int last_mm_cid) + KABI_REPLACE(int migrate_from_cpu, int migrate_from_cpu) + KABI_REPLACE(int mm_cid_active, int mm_cid_active) + KABI_REPLACE(struct callback_head cid_work, + struct callback_head cid_work) #endif struct tlbflush_unmap_batch tlb_ubc; diff --git a/init/Kconfig b/init/Kconfig index 6ea4eafecab1..2d6ae58a5bf7 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1137,7 +1137,7 @@ config QOS_SCHED_DYNAMIC_AFFINITY cpus allowed. config SCHED_MM_CID - def_bool y + def_bool n depends on SMP && RSEQ config UCLAMP_TASK_GROUP -- 2.34.1

2 1

[PATCH openEuler-22.03-LTS-SP1] wifi: cfg80211: fix buffer overflow in elem comparison
by Yi Yang 04 Nov '24

04 Nov '24

From: Johannes Berg <johannes.berg(a)intel.com> stable inclusion from stable-v5.10.158 commit 9e6b79a3cd17620d467311b30d56f2648f6880aa category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAYREV CVE: CVE-2022-49023 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 9f16b5c82a025cd4c864737409234ddc44fb166a ] For vendor elements, the code here assumes that 5 octets are present without checking. Since the element itself is already checked to fit, we only need to check the length. Reported-and-tested-by: Sönke Huster <shuster(a)seemoo.tu-darmstadt.de> Fixes: 0b8fb8235be8 ("cfg80211: Parsing of Multiple BSSID information in scanning") Signed-off-by: Johannes Berg <johannes.berg(a)intel.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yi Yang <yiyang13(a)huawei.com> --- net/wireless/scan.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 729d8e089db1..944bddabfceb 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -330,7 +330,8 @@ static size_t cfg80211_gen_new_ie(const u8 *ie, size_t ielen, * determine if they are the same ie. */ if (tmp_old[0] == WLAN_EID_VENDOR_SPECIFIC) { - if (!memcmp(tmp_old + 2, tmp + 2, 5)) { + if (tmp_old[1] >= 5 && tmp[1] >= 5 && + !memcmp(tmp_old + 2, tmp + 2, 5)) { /* same vendor ie, copy from * subelement */ -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS-SP1] memcg_write_event_control(): fix a user-triggerable oops
by Jinjiang Tu 04 Nov '24

04 Nov '24

From: Al Viro <viro(a)zeniv.linux.org.uk> stable inclusion from stable-v5.10.225 commit ad149f5585345e383baa65f1539d816cd715fd3b category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAQOJK CVE: CVE-2024-45021 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 046667c4d3196938e992fba0dfcde570aa85cd0e upstream. we are *not* guaranteed that anything past the terminating NUL is mapped (let alone initialized with anything sane). Fixes: 0dea116876ee ("cgroup: implement eventfd-based generic API for notifications") Cc: stable(a)vger.kernel.org Cc: Andrew Morton <akpm(a)linux-foundation.org> Acked-by: Michal Hocko <mhocko(a)suse.com> Signed-off-by: Al Viro <viro(a)zeniv.linux.org.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Jinjiang Tu <tujinjiang(a)huawei.com> --- mm/memcontrol.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index aefaa33147b1..ac365005f7a1 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5436,9 +5436,12 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, buf = endp + 1; cfd = simple_strtoul(buf, &endp, 10); - if ((*endp != ' ') && (*endp != '\0')) + if (*endp == '\0') + buf = endp; + else if (*endp == ' ') + buf = endp + 1; + else return -EINVAL; - buf = endp + 1; event = kzalloc(sizeof(*event), GFP_KERNEL); if (!event) -- 2.34.1

2 1

[PATCH OLK-5.10] memcg_write_event_control(): fix a user-triggerable oops
by Jinjiang Tu 04 Nov '24

04 Nov '24

From: Al Viro <viro(a)zeniv.linux.org.uk> stable inclusion from stable-v5.10.225 commit ad149f5585345e383baa65f1539d816cd715fd3b category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAQOJK CVE: CVE-2024-45021 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 046667c4d3196938e992fba0dfcde570aa85cd0e upstream. we are *not* guaranteed that anything past the terminating NUL is mapped (let alone initialized with anything sane). Fixes: 0dea116876ee ("cgroup: implement eventfd-based generic API for notifications") Cc: stable(a)vger.kernel.org Cc: Andrew Morton <akpm(a)linux-foundation.org> Acked-by: Michal Hocko <mhocko(a)suse.com> Signed-off-by: Al Viro <viro(a)zeniv.linux.org.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Jinjiang Tu <tujinjiang(a)huawei.com> --- mm/memcontrol.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index aefaa33147b1..ac365005f7a1 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5436,9 +5436,12 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, buf = endp + 1; cfd = simple_strtoul(buf, &endp, 10); - if ((*endp != ' ') && (*endp != '\0')) + if (*endp == '\0') + buf = endp; + else if (*endp == ' ') + buf = endp + 1; + else return -EINVAL; - buf = endp + 1; event = kzalloc(sizeof(*event), GFP_KERNEL); if (!event) -- 2.34.1

2 1

[PATCH OLK-6.6] mm: gup: stop abusing try_grab_folio
by Jinjiang Tu 04 Nov '24

04 Nov '24

From: Yang Shi <yang(a)os.amperecomputing.com> stable inclusion from stable-v6.6.47 commit 26273f5f4cf68b29414e403837093408a9c98e1f category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAN4MO CVE: CVE-2024-44943 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit f442fa6141379a20b48ae3efabee827a3d260787 upstream. 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> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: mm/gup.c [Context conflicts when removing old try_grab_folio().] Signed-off-by: Jinjiang Tu <tujinjiang(a)huawei.com> --- mm/gup.c | 251 ++++++++++++++++++++++++----------------------- mm/huge_memory.c | 6 +- mm/hugetlb.c | 2 +- mm/internal.h | 4 +- 4 files changed, 135 insertions(+), 128 deletions(-) diff --git a/mm/gup.c b/mm/gup.c index 16f029cd8544..33e8e66b3a77 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_page_refs(&folio->page, 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; @@ -647,8 +559,8 @@ 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; @@ -899,7 +811,7 @@ 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: @@ -1302,20 +1214,19 @@ 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; @@ -2546,6 +2457,102 @@ static void __maybe_unused undo_dev_pagemap(int *nr, int nr_start, } } +/** + * 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_page_refs(&folio->page, 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; +} + #ifdef CONFIG_ARCH_HAS_PTE_SPECIAL /* * Fast-gup relies on pte change detection to avoid concurrent pgtable @@ -2610,7 +2617,7 @@ static int gup_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; @@ -2704,7 +2711,7 @@ static int __gup_device_huge(unsigned long pfn, unsigned long addr, SetPageReferenced(page); pages[*nr] = page; - if (unlikely(try_grab_page(page, flags))) { + if (unlikely(try_grab_folio(page_folio(page), 1, flags))) { undo_dev_pagemap(nr, nr_start, flags, pages); break; } @@ -2813,7 +2820,7 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, page = nth_page(pte_page(pte), (addr & (sz - 1)) >> PAGE_SHIFT); refs = record_subpages(page, addr, end, pages + *nr); - folio = try_grab_folio(page, refs, flags); + folio = try_grab_folio_fast(page, refs, flags); if (!folio) return 0; @@ -2884,7 +2891,7 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, page = nth_page(pmd_page(orig), (addr & ~PMD_MASK) >> PAGE_SHIFT); refs = record_subpages(page, addr, end, pages + *nr); - folio = try_grab_folio(page, refs, flags); + folio = try_grab_folio_fast(page, refs, flags); if (!folio) return 0; @@ -2928,7 +2935,7 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, page = nth_page(pud_page(orig), (addr & ~PUD_MASK) >> PAGE_SHIFT); refs = record_subpages(page, addr, end, pages + *nr); - folio = try_grab_folio(page, refs, flags); + folio = try_grab_folio_fast(page, refs, flags); if (!folio) return 0; @@ -2968,7 +2975,7 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, page = nth_page(pgd_page(orig), (addr & ~PGDIR_MASK) >> PAGE_SHIFT); refs = record_subpages(page, addr, end, pages + *nr); - folio = try_grab_folio(page, refs, flags); + folio = try_grab_folio_fast(page, refs, flags); if (!folio) return 0; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index ea560ea7b39e..eafe846739f4 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1553,7 +1553,7 @@ 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); @@ -1714,7 +1714,7 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, 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); @@ -1976,7 +1976,7 @@ struct page *follow_trans_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); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 89e142c6b897..6d53d52652f3 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -6749,7 +6749,7 @@ struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma, * try_grab_page() should always be able to get the page here, * because we hold the ptl lock and have verified pte_present(). */ - ret = try_grab_page(page, flags); + ret = try_grab_folio(page_folio(page), 1, flags); if (WARN_ON_ONCE(ret)) { page = ERR_PTR(ret); diff --git a/mm/internal.h b/mm/internal.h index 08e32fe3d481..37c17f921dae 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -1231,8 +1231,8 @@ 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 -- 2.34.1

2 1