- Linux-stable-mirror - lists.linaro.org

[PATCH 6.6.y] nvme-rdma: unquiesce admin_q before destroy it

by Feng Liu

From: "Chunguang.xu" <chunguang.xu(a)shopee.com> [ Upstream commit 5858b687559809f05393af745cbadf06dee61295 ] Kernel will hang on destroy admin_q while we create ctrl failed, such as following calltrace: PID: 23644 TASK: ff2d52b40f439fc0 CPU: 2 COMMAND: "nvme" #0 [ff61d23de260fb78] __schedule at ffffffff8323bc15 #1 [ff61d23de260fc08] schedule at ffffffff8323c014 #2 [ff61d23de260fc28] blk_mq_freeze_queue_wait at ffffffff82a3dba1 #3 [ff61d23de260fc78] blk_freeze_queue at ffffffff82a4113a #4 [ff61d23de260fc90] blk_cleanup_queue at ffffffff82a33006 #5 [ff61d23de260fcb0] nvme_rdma_destroy_admin_queue at ffffffffc12686ce #6 [ff61d23de260fcc8] nvme_rdma_setup_ctrl at ffffffffc1268ced #7 [ff61d23de260fd28] nvme_rdma_create_ctrl at ffffffffc126919b #8 [ff61d23de260fd68] nvmf_dev_write at ffffffffc024f362 #9 [ff61d23de260fe38] vfs_write at ffffffff827d5f25 RIP: 00007fda7891d574 RSP: 00007ffe2ef06958 RFLAGS: 00000202 RAX: ffffffffffffffda RBX: 000055e8122a4d90 RCX: 00007fda7891d574 RDX: 000000000000012b RSI: 000055e8122a4d90 RDI: 0000000000000004 RBP: 00007ffe2ef079c0 R8: 000000000000012b R9: 000055e8122a4d90 R10: 0000000000000000 R11: 0000000000000202 R12: 0000000000000004 R13: 000055e8122923c0 R14: 000000000000012b R15: 00007fda78a54500 ORIG_RAX: 0000000000000001 CS: 0033 SS: 002b This due to we have quiesced admi_q before cancel requests, but forgot to unquiesce before destroy it, as a result we fail to drain the pending requests, and hang on blk_mq_freeze_queue_wait() forever. Here try to reuse nvme_rdma_teardown_admin_queue() to fix this issue and simplify the code. Fixes: 958dc1d32c80 ("nvme-rdma: add clean action for failed reconnection") Reported-by: Yingfu.zhou <yingfu.zhou(a)shopee.com> Signed-off-by: Chunguang.xu <chunguang.xu(a)shopee.com> Signed-off-by: Yue.zhao <yue.zhao(a)shopee.com> Reviewed-by: Christoph Hellwig <hch(a)lst.de> Reviewed-by: Hannes Reinecke <hare(a)suse.de> Signed-off-by: Keith Busch <kbusch(a)kernel.org> [Minor context change fixed] Signed-off-by: Feng Liu <Feng.Liu3(a)windriver.com> Signed-off-by: He Zhe <Zhe.He(a)windriver.com> --- Verified the build test. --- drivers/nvme/host/rdma.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index c04317a966b3..055b95d2ce93 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1083,13 +1083,7 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new) nvme_rdma_free_io_queues(ctrl); } destroy_admin: - nvme_quiesce_admin_queue(&ctrl->ctrl); - blk_sync_queue(ctrl->ctrl.admin_q); - nvme_rdma_stop_queue(&ctrl->queues[0]); - nvme_cancel_admin_tagset(&ctrl->ctrl); - if (new) - nvme_remove_admin_tag_set(&ctrl->ctrl); - nvme_rdma_destroy_admin_queue(ctrl); + nvme_rdma_teardown_admin_queue(ctrl, new); return ret; } -- 2.34.1

2 months, 3 weeks

2
1
0 0

[PATCH v6.12] nfsd: don't ignore the return code of svc_proc_register()

by cel＠kernel.org

From: Jeff Layton <jlayton(a)kernel.org> [ Upstream commit 930b64ca0c511521f0abdd1d57ce52b2a6e3476b ] Currently, nfsd_proc_stat_init() ignores the return value of svc_proc_register(). If the procfile creation fails, then the kernel will WARN when it tries to remove the entry later. Fix nfsd_proc_stat_init() to return the same type of pointer as svc_proc_register(), and fix up nfsd_net_init() to check that and fail the nfsd_net construction if it occurs. svc_proc_register() can fail if the dentry can't be allocated, or if an identical dentry already exists. The second case is pretty unlikely in the nfsd_net construction codepath, so if this happens, return -ENOMEM. Reported-by: syzbot+e34ad04f27991521104c(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-nfs/67a47501.050a0220.19061f.05f9.GAE@google.… Cc: stable(a)vger.kernel.org # v6.9 Signed-off-by: Jeff Layton <jlayton(a)kernel.org> Signed-off-by: Chuck Lever <chuck.lever(a)oracle.com> --- fs/nfsd/nfsctl.c | 9 ++++++++- fs/nfsd/stats.c | 4 ++-- fs/nfsd/stats.h | 2 +- 3 files changed, 11 insertions(+), 4 deletions(-) I did not have any problem cherry-picking 930b64 onto v6.12.23. This built and ran some simple NFSD tests in my lab. diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index e83629f39604..2e835e7c107e 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -2244,8 +2244,14 @@ static __net_init int nfsd_net_init(struct net *net) NFSD_STATS_COUNTERS_NUM); if (retval) goto out_repcache_error; + memset(&nn->nfsd_svcstats, 0, sizeof(nn->nfsd_svcstats)); nn->nfsd_svcstats.program = &nfsd_programs[0]; + if (!nfsd_proc_stat_init(net)) { + retval = -ENOMEM; + goto out_proc_error; + } + for (i = 0; i < sizeof(nn->nfsd_versions); i++) nn->nfsd_versions[i] = nfsd_support_version(i); for (i = 0; i < sizeof(nn->nfsd4_minorversions); i++) @@ -2255,12 +2261,13 @@ static __net_init int nfsd_net_init(struct net *net) nfsd4_init_leases_net(nn); get_random_bytes(&nn->siphash_key, sizeof(nn->siphash_key)); seqlock_init(&nn->writeverf_lock); - nfsd_proc_stat_init(net); #if IS_ENABLED(CONFIG_NFS_LOCALIO) INIT_LIST_HEAD(&nn->local_clients); #endif return 0; +out_proc_error: + percpu_counter_destroy_many(nn->counter, NFSD_STATS_COUNTERS_NUM); out_repcache_error: nfsd_idmap_shutdown(net); out_idmap_error: diff --git a/fs/nfsd/stats.c b/fs/nfsd/stats.c index bb22893f1157..f7eaf95e20fc 100644 --- a/fs/nfsd/stats.c +++ b/fs/nfsd/stats.c @@ -73,11 +73,11 @@ static int nfsd_show(struct seq_file *seq, void *v) DEFINE_PROC_SHOW_ATTRIBUTE(nfsd); -void nfsd_proc_stat_init(struct net *net) +struct proc_dir_entry *nfsd_proc_stat_init(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - svc_proc_register(net, &nn->nfsd_svcstats, &nfsd_proc_ops); + return svc_proc_register(net, &nn->nfsd_svcstats, &nfsd_proc_ops); } void nfsd_proc_stat_shutdown(struct net *net) diff --git a/fs/nfsd/stats.h b/fs/nfsd/stats.h index 04aacb6c36e2..e4efb0e4e56d 100644 --- a/fs/nfsd/stats.h +++ b/fs/nfsd/stats.h @@ -10,7 +10,7 @@ #include <uapi/linux/nfsd/stats.h> #include <linux/percpu_counter.h> -void nfsd_proc_stat_init(struct net *net); +struct proc_dir_entry *nfsd_proc_stat_init(struct net *net); void nfsd_proc_stat_shutdown(struct net *net); static inline void nfsd_stats_rc_hits_inc(struct nfsd_net *nn) -- 2.47.0

2 months, 3 weeks

2
1
0 0

[PATCH 6.12.y] libbpf: Prevent compiler warnings/errors

by He Zhe

From: Eder Zulian <ezulian(a)redhat.com> commit 7f4ec77f3fee41dd6a41f03a40703889e6e8f7b2 upstream. Initialize 'new_off' and 'pad_bits' to 0 and 'pad_type' to NULL in btf_dump_emit_bit_padding to prevent compiler warnings/errors which are observed when compiling with 'EXTRA_CFLAGS=-g -Og' options, but do not happen when compiling with current default options. For example, when compiling libbpf with $ make "EXTRA_CFLAGS=-g -Og" -C tools/lib/bpf/ clean all Clang version 17.0.6 and GCC 13.3.1 fail to compile btf_dump.c due to following errors: btf_dump.c: In function ‘btf_dump_emit_bit_padding’: btf_dump.c:903:42: error: ‘new_off’ may be used uninitialized [-Werror=maybe-uninitialized] 903 | if (new_off > cur_off && new_off <= next_off) { | ~~~~~~~~^~~~~~~~~~~ btf_dump.c:870:13: note: ‘new_off’ was declared here 870 | int new_off, pad_bits, bits, i; | ^~~~~~~ btf_dump.c:917:25: error: ‘pad_type’ may be used uninitialized [-Werror=maybe-uninitialized] 917 | btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 918 | in_bitfield ? new_off - cur_off : 0); | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ btf_dump.c:871:21: note: ‘pad_type’ was declared here 871 | const char *pad_type; | ^~~~~~~~ btf_dump.c:930:20: error: ‘pad_bits’ may be used uninitialized [-Werror=maybe-uninitialized] 930 | if (bits == pad_bits) { | ^ btf_dump.c:870:22: note: ‘pad_bits’ was declared here 870 | int new_off, pad_bits, bits, i; | ^~~~~~~~ cc1: all warnings being treated as errors Signed-off-by: Eder Zulian <ezulian(a)redhat.com> Signed-off-by: Andrii Nakryiko <andrii(a)kernel.org> Acked-by: Jiri Olsa <jolsa(a)kernel.org> Link: https://lore.kernel.org/bpf/20241022172329.3871958-3-ezulian@redhat.com Signed-off-by: He Zhe <zhe.he(a)windriver.com> Signed-off-by: Xiangyu Chen <xiangyu.chen(a)windriver.com> --- Build test passed. --- tools/lib/bpf/btf_dump.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 0a7327541c17..46cce18c8308 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -867,8 +867,8 @@ static void btf_dump_emit_bit_padding(const struct btf_dump *d, } pads[] = { {"long", d->ptr_sz * 8}, {"int", 32}, {"short", 16}, {"char", 8} }; - int new_off, pad_bits, bits, i; - const char *pad_type; + int new_off = 0, pad_bits = 0, bits, i; + const char *pad_type = NULL; if (cur_off >= next_off) return; /* no gap */ -- 2.34.1

2 months, 3 weeks

2
1
0 0

[PATCH 5.15] ext4: fix timer use-after-free on failed mount

by Xiangyu Chen

From: Xiaxi Shen <shenxiaxi26(a)gmail.com> commit 0ce160c5bdb67081a62293028dc85758a8efb22a upstream. Syzbot has found an ODEBUG bug in ext4_fill_super The del_timer_sync function cancels the s_err_report timer, which reminds about filesystem errors daily. We should guarantee the timer is no longer active before kfree(sbi). When filesystem mounting fails, the flow goes to failed_mount3, where an error occurs when ext4_stop_mmpd is called, causing a read I/O failure. This triggers the ext4_handle_error function that ultimately re-arms the timer, leaving the s_err_report timer active before kfree(sbi) is called. Fix the issue by canceling the s_err_report timer after calling ext4_stop_mmpd. Signed-off-by: Xiaxi Shen <shenxiaxi26(a)gmail.com> Reported-and-tested-by: syzbot+59e0101c430934bc9a36(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=59e0101c430934bc9a36 Link: https://patch.msgid.link/20240715043336.98097-1-shenxiaxi26@gmail.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Cc: stable(a)kernel.org [Minor context change fixed] Signed-off-by: Xiangyu Chen <xiangyu.chen(a)windriver.com> Signed-off-by: He Zhe <zhe.he(a)windriver.com> --- Verified the build test. --- fs/ext4/super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 126b582d85fc..8f33b6db8aae 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5085,8 +5085,8 @@ failed_mount9: __maybe_unused failed_mount3: /* flush s_error_work before sbi destroy */ flush_work(&sbi->s_error_work); - del_timer_sync(&sbi->s_err_report); ext4_stop_mmpd(sbi); + del_timer_sync(&sbi->s_err_report); failed_mount2: rcu_read_lock(); group_desc = rcu_dereference(sbi->s_group_desc); -- 2.34.1

2 months, 3 weeks

2
3
0 0

[PATCH 5.15.y] bpf: avoid holding freeze_mutex during mmap operation

by David Sauerwein

From: Andrii Nakryiko <andrii(a)kernel.org> [ Upstream commit bc27c52eea189e8f7492d40739b7746d67b65beb ] We use map->freeze_mutex to prevent races between map_freeze() and memory mapping BPF map contents with writable permissions. The way we naively do this means we'll hold freeze_mutex for entire duration of all the mm and VMA manipulations, which is completely unnecessary. This can potentially also lead to deadlocks, as reported by syzbot in [0]. So, instead, hold freeze_mutex only during writeability checks, bump (proactively) "write active" count for the map, unlock the mutex and proceed with mmap logic. And only if something went wrong during mmap logic, then undo that "write active" counter increment. [0] https://lore.kernel.org/bpf/678dcbc9.050a0220.303755.0066.GAE@google.com/ Fixes: fc9702273e2e ("bpf: Add mmap() support for BPF_MAP_TYPE_ARRAY") Reported-by: syzbot+4dc041c686b7c816a71e(a)syzkaller.appspotmail.com Signed-off-by: Andrii Nakryiko <andrii(a)kernel.org> Link: https://lore.kernel.org/r/20250129012246.1515826-2-andrii@kernel.org Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: David Sauerwein <dssauerw(a)amazon.de> --- kernel/bpf/syscall.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 7fce461eae10..6f309248f13f 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -654,7 +654,7 @@ static const struct vm_operations_struct bpf_map_default_vmops = { static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) { struct bpf_map *map = filp->private_data; - int err; + int err = 0; if (!map->ops->map_mmap || map_value_has_spin_lock(map) || map_value_has_timer(map)) @@ -679,7 +679,12 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) err = -EACCES; goto out; } + bpf_map_write_active_inc(map); } +out: + mutex_unlock(&map->freeze_mutex); + if (err) + return err; /* set default open/close callbacks */ vma->vm_ops = &bpf_map_default_vmops; @@ -690,13 +695,11 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) vma->vm_flags &= ~VM_MAYWRITE; err = map->ops->map_mmap(map, vma); - if (err) - goto out; + if (err) { + if (vma->vm_flags & VM_WRITE) + bpf_map_write_active_dec(map); + } - if (vma->vm_flags & VM_MAYWRITE) - bpf_map_write_active_inc(map); -out: - mutex_unlock(&map->freeze_mutex); return err; } -- 2.47.1

2 months, 3 weeks

2
1
0 0

[PATCH 0/2] Stable-6.6 backport x86/xen: fix memblock_reserve() usage on PVH

by Jason Andryuk

For stable-6.6. ("x86/xen: fix memblock_reserve() usage on PVH") is the fix, but it depends on ("x86/xen: move xen_reserve_extra_memory()") as a prerequisite. Both need fixups as they predate the removal of the Xen hypercall_page. Roger Pau Monne (2): x86/xen: move xen_reserve_extra_memory() x86/xen: fix memblock_reserve() usage on PVH arch/x86/include/asm/xen/hypervisor.h | 5 -- arch/x86/platform/pvh/enlighten.c | 3 - arch/x86/xen/enlighten_pvh.c | 93 +++++++++++++++------------ 3 files changed, 51 insertions(+), 50 deletions(-) -- 2.49.0

2 months, 3 weeks

2
4
0 0

[PATCH 6.1.y] bpf: Prevent tail call between progs attached to different hooks

by jianqi.ren.cn＠windriver.com

From: Xu Kuohai <xukuohai(a)huawei.com> [ Upstream commit 28ead3eaabc16ecc907cfb71876da028080f6356 ] bpf progs can be attached to kernel functions, and the attached functions can take different parameters or return different return values. If prog attached to one kernel function tail calls prog attached to another kernel function, the ctx access or return value verification could be bypassed. For example, if prog1 is attached to func1 which takes only 1 parameter and prog2 is attached to func2 which takes two parameters. Since verifier assumes the bpf ctx passed to prog2 is constructed based on func2's prototype, verifier allows prog2 to access the second parameter from the bpf ctx passed to it. The problem is that verifier does not prevent prog1 from passing its bpf ctx to prog2 via tail call. In this case, the bpf ctx passed to prog2 is constructed from func1 instead of func2, that is, the assumption for ctx access verification is bypassed. Another example, if BPF LSM prog1 is attached to hook file_alloc_security, and BPF LSM prog2 is attached to hook bpf_lsm_audit_rule_known. Verifier knows the return value rules for these two hooks, e.g. it is legal for bpf_lsm_audit_rule_known to return positive number 1, and it is illegal for file_alloc_security to return positive number. So verifier allows prog2 to return positive number 1, but does not allow prog1 to return positive number. The problem is that verifier does not prevent prog1 from calling prog2 via tail call. In this case, prog2's return value 1 will be used as the return value for prog1's hook file_alloc_security. That is, the return value rule is bypassed. This patch adds restriction for tail call to prevent such bypasses. Signed-off-by: Xu Kuohai <xukuohai(a)huawei.com> Link: https://lore.kernel.org/r/20240719110059.797546-4-xukuohai@huaweicloud.com Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Signed-off-by: Andrii Nakryiko <andrii(a)kernel.org> [Minor conflict resolved due to code context change.] Signed-off-by: Jianqi Ren <jianqi.ren.cn(a)windriver.com> Signed-off-by: He Zhe <zhe.he(a)windriver.com> --- Verified the build test --- include/linux/bpf.h | 1 + kernel/bpf/core.c | 19 +++++++++++++++++-- 2 files changed, 18 insertions(+), 2 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 2189c0d18fa7..e9c1338851e3 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -250,6 +250,7 @@ struct bpf_map { * same prog type, JITed flag and xdp_has_frags flag. */ struct { + const struct btf_type *attach_func_proto; spinlock_t lock; enum bpf_prog_type type; bool jited; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 83b416af4da1..c281f5b8705e 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2121,6 +2121,7 @@ bool bpf_prog_map_compatible(struct bpf_map *map, { enum bpf_prog_type prog_type = resolve_prog_type(fp); bool ret; + struct bpf_prog_aux *aux = fp->aux; if (fp->kprobe_override) return false; @@ -2132,12 +2133,26 @@ bool bpf_prog_map_compatible(struct bpf_map *map, */ map->owner.type = prog_type; map->owner.jited = fp->jited; - map->owner.xdp_has_frags = fp->aux->xdp_has_frags; + map->owner.xdp_has_frags = aux->xdp_has_frags; + map->owner.attach_func_proto = aux->attach_func_proto; ret = true; } else { ret = map->owner.type == prog_type && map->owner.jited == fp->jited && - map->owner.xdp_has_frags == fp->aux->xdp_has_frags; + map->owner.xdp_has_frags == aux->xdp_has_frags; + if (ret && + map->owner.attach_func_proto != aux->attach_func_proto) { + switch (prog_type) { + case BPF_PROG_TYPE_TRACING: + case BPF_PROG_TYPE_LSM: + case BPF_PROG_TYPE_EXT: + case BPF_PROG_TYPE_STRUCT_OPS: + ret = false; + break; + default: + break; + } + } } spin_unlock(&map->owner.lock); -- 2.34.1

2 months, 3 weeks

2
1
0 0

[PATCH 6.1.y] bpf: avoid holding freeze_mutex during mmap operation

by David Sauerwein

From: Andrii Nakryiko <andrii(a)kernel.org> [ Upstream commit bc27c52eea189e8f7492d40739b7746d67b65beb ] We use map->freeze_mutex to prevent races between map_freeze() and memory mapping BPF map contents with writable permissions. The way we naively do this means we'll hold freeze_mutex for entire duration of all the mm and VMA manipulations, which is completely unnecessary. This can potentially also lead to deadlocks, as reported by syzbot in [0]. So, instead, hold freeze_mutex only during writeability checks, bump (proactively) "write active" count for the map, unlock the mutex and proceed with mmap logic. And only if something went wrong during mmap logic, then undo that "write active" counter increment. [0] https://lore.kernel.org/bpf/678dcbc9.050a0220.303755.0066.GAE@google.com/ Fixes: fc9702273e2e ("bpf: Add mmap() support for BPF_MAP_TYPE_ARRAY") Reported-by: syzbot+4dc041c686b7c816a71e(a)syzkaller.appspotmail.com Signed-off-by: Andrii Nakryiko <andrii(a)kernel.org> Link: https://lore.kernel.org/r/20250129012246.1515826-2-andrii@kernel.org Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: David Sauerwein <dssauerw(a)amazon.de> --- kernel/bpf/syscall.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 7a4004f09bae..27fdf1b2fc46 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -813,7 +813,7 @@ static const struct vm_operations_struct bpf_map_default_vmops = { static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) { struct bpf_map *map = filp->private_data; - int err; + int err = 0; if (!map->ops->map_mmap || map_value_has_spin_lock(map) || map_value_has_timer(map) || map_value_has_kptrs(map)) @@ -838,7 +838,12 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) err = -EACCES; goto out; } + bpf_map_write_active_inc(map); } +out: + mutex_unlock(&map->freeze_mutex); + if (err) + return err; /* set default open/close callbacks */ vma->vm_ops = &bpf_map_default_vmops; @@ -849,13 +854,11 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) vma->vm_flags &= ~VM_MAYWRITE; err = map->ops->map_mmap(map, vma); - if (err) - goto out; + if (err) { + if (vma->vm_flags & VM_WRITE) + bpf_map_write_active_dec(map); + } - if (vma->vm_flags & VM_MAYWRITE) - bpf_map_write_active_inc(map); -out: - mutex_unlock(&map->freeze_mutex); return err; } -- 2.47.1

2 months, 3 weeks

2
1
0 0

[PATCH v6.13] nfsd: don't ignore the return code of svc_proc_register()

by cel＠kernel.org

From: Jeff Layton <jlayton(a)kernel.org> [ Upstream commit 930b64ca0c511521f0abdd1d57ce52b2a6e3476b ] Currently, nfsd_proc_stat_init() ignores the return value of svc_proc_register(). If the procfile creation fails, then the kernel will WARN when it tries to remove the entry later. Fix nfsd_proc_stat_init() to return the same type of pointer as svc_proc_register(), and fix up nfsd_net_init() to check that and fail the nfsd_net construction if it occurs. svc_proc_register() can fail if the dentry can't be allocated, or if an identical dentry already exists. The second case is pretty unlikely in the nfsd_net construction codepath, so if this happens, return -ENOMEM. Reported-by: syzbot+e34ad04f27991521104c(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-nfs/67a47501.050a0220.19061f.05f9.GAE@google.… Cc: stable(a)vger.kernel.org # v6.9 Signed-off-by: Jeff Layton <jlayton(a)kernel.org> Signed-off-by: Chuck Lever <chuck.lever(a)oracle.com> --- fs/nfsd/nfsctl.c | 9 ++++++++- fs/nfsd/stats.c | 4 ++-- fs/nfsd/stats.h | 2 +- 3 files changed, 11 insertions(+), 4 deletions(-) I did not have any problem cherry-picking 930b64 onto v6.13.11. This built and ran some simple NFSD tests in my lab. diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index e83629f39604..2e835e7c107e 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -2244,8 +2244,14 @@ static __net_init int nfsd_net_init(struct net *net) NFSD_STATS_COUNTERS_NUM); if (retval) goto out_repcache_error; + memset(&nn->nfsd_svcstats, 0, sizeof(nn->nfsd_svcstats)); nn->nfsd_svcstats.program = &nfsd_programs[0]; + if (!nfsd_proc_stat_init(net)) { + retval = -ENOMEM; + goto out_proc_error; + } + for (i = 0; i < sizeof(nn->nfsd_versions); i++) nn->nfsd_versions[i] = nfsd_support_version(i); for (i = 0; i < sizeof(nn->nfsd4_minorversions); i++) @@ -2255,12 +2261,13 @@ static __net_init int nfsd_net_init(struct net *net) nfsd4_init_leases_net(nn); get_random_bytes(&nn->siphash_key, sizeof(nn->siphash_key)); seqlock_init(&nn->writeverf_lock); - nfsd_proc_stat_init(net); #if IS_ENABLED(CONFIG_NFS_LOCALIO) INIT_LIST_HEAD(&nn->local_clients); #endif return 0; +out_proc_error: + percpu_counter_destroy_many(nn->counter, NFSD_STATS_COUNTERS_NUM); out_repcache_error: nfsd_idmap_shutdown(net); out_idmap_error: diff --git a/fs/nfsd/stats.c b/fs/nfsd/stats.c index bb22893f1157..f7eaf95e20fc 100644 --- a/fs/nfsd/stats.c +++ b/fs/nfsd/stats.c @@ -73,11 +73,11 @@ static int nfsd_show(struct seq_file *seq, void *v) DEFINE_PROC_SHOW_ATTRIBUTE(nfsd); -void nfsd_proc_stat_init(struct net *net) +struct proc_dir_entry *nfsd_proc_stat_init(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - svc_proc_register(net, &nn->nfsd_svcstats, &nfsd_proc_ops); + return svc_proc_register(net, &nn->nfsd_svcstats, &nfsd_proc_ops); } void nfsd_proc_stat_shutdown(struct net *net) diff --git a/fs/nfsd/stats.h b/fs/nfsd/stats.h index 04aacb6c36e2..e4efb0e4e56d 100644 --- a/fs/nfsd/stats.h +++ b/fs/nfsd/stats.h @@ -10,7 +10,7 @@ #include <uapi/linux/nfsd/stats.h> #include <linux/percpu_counter.h> -void nfsd_proc_stat_init(struct net *net); +struct proc_dir_entry *nfsd_proc_stat_init(struct net *net); void nfsd_proc_stat_shutdown(struct net *net); static inline void nfsd_stats_rc_hits_inc(struct nfsd_net *nn) -- 2.47.0

2 months, 3 weeks

2
1
0 0

[PATCH 5.10.y] bpf: avoid holding freeze_mutex during mmap operation

by David Sauerwein

From: Andrii Nakryiko <andrii(a)kernel.org> [ Upstream commit bc27c52eea189e8f7492d40739b7746d67b65beb ] We use map->freeze_mutex to prevent races between map_freeze() and memory mapping BPF map contents with writable permissions. The way we naively do this means we'll hold freeze_mutex for entire duration of all the mm and VMA manipulations, which is completely unnecessary. This can potentially also lead to deadlocks, as reported by syzbot in [0]. So, instead, hold freeze_mutex only during writeability checks, bump (proactively) "write active" count for the map, unlock the mutex and proceed with mmap logic. And only if something went wrong during mmap logic, then undo that "write active" counter increment. [0] https://lore.kernel.org/bpf/678dcbc9.050a0220.303755.0066.GAE@google.com/ Fixes: fc9702273e2e ("bpf: Add mmap() support for BPF_MAP_TYPE_ARRAY") Reported-by: syzbot+4dc041c686b7c816a71e(a)syzkaller.appspotmail.com Signed-off-by: Andrii Nakryiko <andrii(a)kernel.org> Link: https://lore.kernel.org/r/20250129012246.1515826-2-andrii@kernel.org Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: David Sauerwein <dssauerw(a)amazon.de> --- kernel/bpf/syscall.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 008bb4e5c4dd..dc3d9a111cf1 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -647,7 +647,7 @@ static const struct vm_operations_struct bpf_map_default_vmops = { static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) { struct bpf_map *map = filp->private_data; - int err; + int err = 0; if (!map->ops->map_mmap || map_value_has_spin_lock(map)) return -ENOTSUPP; @@ -671,7 +671,12 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) err = -EACCES; goto out; } + bpf_map_write_active_inc(map); } +out: + mutex_unlock(&map->freeze_mutex); + if (err) + return err; /* set default open/close callbacks */ vma->vm_ops = &bpf_map_default_vmops; @@ -682,13 +687,11 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) vma->vm_flags &= ~VM_MAYWRITE; err = map->ops->map_mmap(map, vma); - if (err) - goto out; + if (err) { + if (vma->vm_flags & VM_WRITE) + bpf_map_write_active_dec(map); + } - if (vma->vm_flags & VM_MAYWRITE) - bpf_map_write_active_inc(map); -out: - mutex_unlock(&map->freeze_mutex); return err; } -- 2.47.1

2 months, 3 weeks

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror