June 2019 - Linux-stable-mirror

FAILED: patch "[PATCH] KVM: arm64: Filter out invalid core register IDs in" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From df205b5c63281e4f32caac22adda18fd68795e80 Mon Sep 17 00:00:00 2001 From: Dave Martin <Dave.Martin(a)arm.com> Date: Wed, 12 Jun 2019 13:44:49 +0100 Subject: [PATCH] KVM: arm64: Filter out invalid core register IDs in KVM_GET_REG_LIST Since commit d26c25a9d19b ("arm64: KVM: Tighten guest core register access from userspace"), KVM_{GET,SET}_ONE_REG rejects register IDs that do not correspond to a single underlying architectural register. KVM_GET_REG_LIST was not changed to match however: instead, it simply yields a list of 32-bit register IDs that together cover the whole kvm_regs struct. This means that if userspace tries to use the resulting list of IDs directly to drive calls to KVM_*_ONE_REG, some of those calls will now fail. This was not the intention. Instead, iterating KVM_*_ONE_REG over the list of IDs returned by KVM_GET_REG_LIST should be guaranteed to work. This patch fixes the problem by splitting validate_core_offset() into a backend core_reg_size_from_offset() which does all of the work except for checking that the size field in the register ID matches, and kvm_arm_copy_reg_indices() and num_core_regs() are converted to use this to enumerate the valid offsets. kvm_arm_copy_reg_indices() now also sets the register ID size field appropriately based on the value returned, so the register ID supplied to userspace is fully qualified for use with the register access ioctls. Cc: stable(a)vger.kernel.org Fixes: d26c25a9d19b ("arm64: KVM: Tighten guest core register access from userspace") Signed-off-by: Dave Martin <Dave.Martin(a)arm.com> Reviewed-by: Andrew Jones <drjones(a)redhat.com> Tested-by: Andrew Jones <drjones(a)redhat.com> Signed-off-by: Marc Zyngier <marc.zyngier(a)arm.com> diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index ae734fcfd4ea..c8aa00179363 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -70,10 +70,8 @@ static u64 core_reg_offset_from_id(u64 id) return id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_CORE); } -static int validate_core_offset(const struct kvm_vcpu *vcpu, - const struct kvm_one_reg *reg) +static int core_reg_size_from_offset(const struct kvm_vcpu *vcpu, u64 off) { - u64 off = core_reg_offset_from_id(reg->id); int size; switch (off) { @@ -103,8 +101,7 @@ static int validate_core_offset(const struct kvm_vcpu *vcpu, return -EINVAL; } - if (KVM_REG_SIZE(reg->id) != size || - !IS_ALIGNED(off, size / sizeof(__u32))) + if (!IS_ALIGNED(off, size / sizeof(__u32))) return -EINVAL; /* @@ -115,6 +112,21 @@ static int validate_core_offset(const struct kvm_vcpu *vcpu, if (vcpu_has_sve(vcpu) && core_reg_offset_is_vreg(off)) return -EINVAL; + return size; +} + +static int validate_core_offset(const struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg) +{ + u64 off = core_reg_offset_from_id(reg->id); + int size = core_reg_size_from_offset(vcpu, off); + + if (size < 0) + return -EINVAL; + + if (KVM_REG_SIZE(reg->id) != size) + return -EINVAL; + return 0; } @@ -447,19 +459,34 @@ static int copy_core_reg_indices(const struct kvm_vcpu *vcpu, { unsigned int i; int n = 0; - const u64 core_reg = KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE; for (i = 0; i < sizeof(struct kvm_regs) / sizeof(__u32); i++) { - /* - * The KVM_REG_ARM64_SVE regs must be used instead of - * KVM_REG_ARM_CORE for accessing the FPSIMD V-registers on - * SVE-enabled vcpus: - */ - if (vcpu_has_sve(vcpu) && core_reg_offset_is_vreg(i)) + u64 reg = KVM_REG_ARM64 | KVM_REG_ARM_CORE | i; + int size = core_reg_size_from_offset(vcpu, i); + + if (size < 0) + continue; + + switch (size) { + case sizeof(__u32): + reg |= KVM_REG_SIZE_U32; + break; + + case sizeof(__u64): + reg |= KVM_REG_SIZE_U64; + break; + + case sizeof(__uint128_t): + reg |= KVM_REG_SIZE_U128; + break; + + default: + WARN_ON(1); continue; + } if (uindices) { - if (put_user(core_reg | i, uindices)) + if (put_user(reg, uindices)) return -EFAULT; uindices++; }

5 years, 11 months

1
0
0 0

FAILED: patch "[PATCH] KVM: arm64: Filter out invalid core register IDs in" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From df205b5c63281e4f32caac22adda18fd68795e80 Mon Sep 17 00:00:00 2001 From: Dave Martin <Dave.Martin(a)arm.com> Date: Wed, 12 Jun 2019 13:44:49 +0100 Subject: [PATCH] KVM: arm64: Filter out invalid core register IDs in KVM_GET_REG_LIST Since commit d26c25a9d19b ("arm64: KVM: Tighten guest core register access from userspace"), KVM_{GET,SET}_ONE_REG rejects register IDs that do not correspond to a single underlying architectural register. KVM_GET_REG_LIST was not changed to match however: instead, it simply yields a list of 32-bit register IDs that together cover the whole kvm_regs struct. This means that if userspace tries to use the resulting list of IDs directly to drive calls to KVM_*_ONE_REG, some of those calls will now fail. This was not the intention. Instead, iterating KVM_*_ONE_REG over the list of IDs returned by KVM_GET_REG_LIST should be guaranteed to work. This patch fixes the problem by splitting validate_core_offset() into a backend core_reg_size_from_offset() which does all of the work except for checking that the size field in the register ID matches, and kvm_arm_copy_reg_indices() and num_core_regs() are converted to use this to enumerate the valid offsets. kvm_arm_copy_reg_indices() now also sets the register ID size field appropriately based on the value returned, so the register ID supplied to userspace is fully qualified for use with the register access ioctls. Cc: stable(a)vger.kernel.org Fixes: d26c25a9d19b ("arm64: KVM: Tighten guest core register access from userspace") Signed-off-by: Dave Martin <Dave.Martin(a)arm.com> Reviewed-by: Andrew Jones <drjones(a)redhat.com> Tested-by: Andrew Jones <drjones(a)redhat.com> Signed-off-by: Marc Zyngier <marc.zyngier(a)arm.com> diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index ae734fcfd4ea..c8aa00179363 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -70,10 +70,8 @@ static u64 core_reg_offset_from_id(u64 id) return id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_CORE); } -static int validate_core_offset(const struct kvm_vcpu *vcpu, - const struct kvm_one_reg *reg) +static int core_reg_size_from_offset(const struct kvm_vcpu *vcpu, u64 off) { - u64 off = core_reg_offset_from_id(reg->id); int size; switch (off) { @@ -103,8 +101,7 @@ static int validate_core_offset(const struct kvm_vcpu *vcpu, return -EINVAL; } - if (KVM_REG_SIZE(reg->id) != size || - !IS_ALIGNED(off, size / sizeof(__u32))) + if (!IS_ALIGNED(off, size / sizeof(__u32))) return -EINVAL; /* @@ -115,6 +112,21 @@ static int validate_core_offset(const struct kvm_vcpu *vcpu, if (vcpu_has_sve(vcpu) && core_reg_offset_is_vreg(off)) return -EINVAL; + return size; +} + +static int validate_core_offset(const struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg) +{ + u64 off = core_reg_offset_from_id(reg->id); + int size = core_reg_size_from_offset(vcpu, off); + + if (size < 0) + return -EINVAL; + + if (KVM_REG_SIZE(reg->id) != size) + return -EINVAL; + return 0; } @@ -447,19 +459,34 @@ static int copy_core_reg_indices(const struct kvm_vcpu *vcpu, { unsigned int i; int n = 0; - const u64 core_reg = KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE; for (i = 0; i < sizeof(struct kvm_regs) / sizeof(__u32); i++) { - /* - * The KVM_REG_ARM64_SVE regs must be used instead of - * KVM_REG_ARM_CORE for accessing the FPSIMD V-registers on - * SVE-enabled vcpus: - */ - if (vcpu_has_sve(vcpu) && core_reg_offset_is_vreg(i)) + u64 reg = KVM_REG_ARM64 | KVM_REG_ARM_CORE | i; + int size = core_reg_size_from_offset(vcpu, i); + + if (size < 0) + continue; + + switch (size) { + case sizeof(__u32): + reg |= KVM_REG_SIZE_U32; + break; + + case sizeof(__u64): + reg |= KVM_REG_SIZE_U64; + break; + + case sizeof(__uint128_t): + reg |= KVM_REG_SIZE_U128; + break; + + default: + WARN_ON(1); continue; + } if (uindices) { - if (put_user(core_reg | i, uindices)) + if (put_user(reg, uindices)) return -EFAULT; uindices++; }

5 years, 11 months

1
0
0 0

FAILED: patch "[PATCH] KVM: arm64: Filter out invalid core register IDs in" failed to apply to 5.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.19-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From df205b5c63281e4f32caac22adda18fd68795e80 Mon Sep 17 00:00:00 2001 From: Dave Martin <Dave.Martin(a)arm.com> Date: Wed, 12 Jun 2019 13:44:49 +0100 Subject: [PATCH] KVM: arm64: Filter out invalid core register IDs in KVM_GET_REG_LIST Since commit d26c25a9d19b ("arm64: KVM: Tighten guest core register access from userspace"), KVM_{GET,SET}_ONE_REG rejects register IDs that do not correspond to a single underlying architectural register. KVM_GET_REG_LIST was not changed to match however: instead, it simply yields a list of 32-bit register IDs that together cover the whole kvm_regs struct. This means that if userspace tries to use the resulting list of IDs directly to drive calls to KVM_*_ONE_REG, some of those calls will now fail. This was not the intention. Instead, iterating KVM_*_ONE_REG over the list of IDs returned by KVM_GET_REG_LIST should be guaranteed to work. This patch fixes the problem by splitting validate_core_offset() into a backend core_reg_size_from_offset() which does all of the work except for checking that the size field in the register ID matches, and kvm_arm_copy_reg_indices() and num_core_regs() are converted to use this to enumerate the valid offsets. kvm_arm_copy_reg_indices() now also sets the register ID size field appropriately based on the value returned, so the register ID supplied to userspace is fully qualified for use with the register access ioctls. Cc: stable(a)vger.kernel.org Fixes: d26c25a9d19b ("arm64: KVM: Tighten guest core register access from userspace") Signed-off-by: Dave Martin <Dave.Martin(a)arm.com> Reviewed-by: Andrew Jones <drjones(a)redhat.com> Tested-by: Andrew Jones <drjones(a)redhat.com> Signed-off-by: Marc Zyngier <marc.zyngier(a)arm.com> diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index ae734fcfd4ea..c8aa00179363 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -70,10 +70,8 @@ static u64 core_reg_offset_from_id(u64 id) return id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_CORE); } -static int validate_core_offset(const struct kvm_vcpu *vcpu, - const struct kvm_one_reg *reg) +static int core_reg_size_from_offset(const struct kvm_vcpu *vcpu, u64 off) { - u64 off = core_reg_offset_from_id(reg->id); int size; switch (off) { @@ -103,8 +101,7 @@ static int validate_core_offset(const struct kvm_vcpu *vcpu, return -EINVAL; } - if (KVM_REG_SIZE(reg->id) != size || - !IS_ALIGNED(off, size / sizeof(__u32))) + if (!IS_ALIGNED(off, size / sizeof(__u32))) return -EINVAL; /* @@ -115,6 +112,21 @@ static int validate_core_offset(const struct kvm_vcpu *vcpu, if (vcpu_has_sve(vcpu) && core_reg_offset_is_vreg(off)) return -EINVAL; + return size; +} + +static int validate_core_offset(const struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg) +{ + u64 off = core_reg_offset_from_id(reg->id); + int size = core_reg_size_from_offset(vcpu, off); + + if (size < 0) + return -EINVAL; + + if (KVM_REG_SIZE(reg->id) != size) + return -EINVAL; + return 0; } @@ -447,19 +459,34 @@ static int copy_core_reg_indices(const struct kvm_vcpu *vcpu, { unsigned int i; int n = 0; - const u64 core_reg = KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE; for (i = 0; i < sizeof(struct kvm_regs) / sizeof(__u32); i++) { - /* - * The KVM_REG_ARM64_SVE regs must be used instead of - * KVM_REG_ARM_CORE for accessing the FPSIMD V-registers on - * SVE-enabled vcpus: - */ - if (vcpu_has_sve(vcpu) && core_reg_offset_is_vreg(i)) + u64 reg = KVM_REG_ARM64 | KVM_REG_ARM_CORE | i; + int size = core_reg_size_from_offset(vcpu, i); + + if (size < 0) + continue; + + switch (size) { + case sizeof(__u32): + reg |= KVM_REG_SIZE_U32; + break; + + case sizeof(__u64): + reg |= KVM_REG_SIZE_U64; + break; + + case sizeof(__uint128_t): + reg |= KVM_REG_SIZE_U128; + break; + + default: + WARN_ON(1); continue; + } if (uindices) { - if (put_user(core_reg | i, uindices)) + if (put_user(reg, uindices)) return -EFAULT; uindices++; }

5 years, 11 months

1
0
0 0

FAILED: patch "[PATCH] KVM: arm64: Filter out invalid core register IDs in" failed to apply to 5.0-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.0-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From df205b5c63281e4f32caac22adda18fd68795e80 Mon Sep 17 00:00:00 2001 From: Dave Martin <Dave.Martin(a)arm.com> Date: Wed, 12 Jun 2019 13:44:49 +0100 Subject: [PATCH] KVM: arm64: Filter out invalid core register IDs in KVM_GET_REG_LIST Since commit d26c25a9d19b ("arm64: KVM: Tighten guest core register access from userspace"), KVM_{GET,SET}_ONE_REG rejects register IDs that do not correspond to a single underlying architectural register. KVM_GET_REG_LIST was not changed to match however: instead, it simply yields a list of 32-bit register IDs that together cover the whole kvm_regs struct. This means that if userspace tries to use the resulting list of IDs directly to drive calls to KVM_*_ONE_REG, some of those calls will now fail. This was not the intention. Instead, iterating KVM_*_ONE_REG over the list of IDs returned by KVM_GET_REG_LIST should be guaranteed to work. This patch fixes the problem by splitting validate_core_offset() into a backend core_reg_size_from_offset() which does all of the work except for checking that the size field in the register ID matches, and kvm_arm_copy_reg_indices() and num_core_regs() are converted to use this to enumerate the valid offsets. kvm_arm_copy_reg_indices() now also sets the register ID size field appropriately based on the value returned, so the register ID supplied to userspace is fully qualified for use with the register access ioctls. Cc: stable(a)vger.kernel.org Fixes: d26c25a9d19b ("arm64: KVM: Tighten guest core register access from userspace") Signed-off-by: Dave Martin <Dave.Martin(a)arm.com> Reviewed-by: Andrew Jones <drjones(a)redhat.com> Tested-by: Andrew Jones <drjones(a)redhat.com> Signed-off-by: Marc Zyngier <marc.zyngier(a)arm.com> diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index ae734fcfd4ea..c8aa00179363 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -70,10 +70,8 @@ static u64 core_reg_offset_from_id(u64 id) return id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_CORE); } -static int validate_core_offset(const struct kvm_vcpu *vcpu, - const struct kvm_one_reg *reg) +static int core_reg_size_from_offset(const struct kvm_vcpu *vcpu, u64 off) { - u64 off = core_reg_offset_from_id(reg->id); int size; switch (off) { @@ -103,8 +101,7 @@ static int validate_core_offset(const struct kvm_vcpu *vcpu, return -EINVAL; } - if (KVM_REG_SIZE(reg->id) != size || - !IS_ALIGNED(off, size / sizeof(__u32))) + if (!IS_ALIGNED(off, size / sizeof(__u32))) return -EINVAL; /* @@ -115,6 +112,21 @@ static int validate_core_offset(const struct kvm_vcpu *vcpu, if (vcpu_has_sve(vcpu) && core_reg_offset_is_vreg(off)) return -EINVAL; + return size; +} + +static int validate_core_offset(const struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg) +{ + u64 off = core_reg_offset_from_id(reg->id); + int size = core_reg_size_from_offset(vcpu, off); + + if (size < 0) + return -EINVAL; + + if (KVM_REG_SIZE(reg->id) != size) + return -EINVAL; + return 0; } @@ -447,19 +459,34 @@ static int copy_core_reg_indices(const struct kvm_vcpu *vcpu, { unsigned int i; int n = 0; - const u64 core_reg = KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE; for (i = 0; i < sizeof(struct kvm_regs) / sizeof(__u32); i++) { - /* - * The KVM_REG_ARM64_SVE regs must be used instead of - * KVM_REG_ARM_CORE for accessing the FPSIMD V-registers on - * SVE-enabled vcpus: - */ - if (vcpu_has_sve(vcpu) && core_reg_offset_is_vreg(i)) + u64 reg = KVM_REG_ARM64 | KVM_REG_ARM_CORE | i; + int size = core_reg_size_from_offset(vcpu, i); + + if (size < 0) + continue; + + switch (size) { + case sizeof(__u32): + reg |= KVM_REG_SIZE_U32; + break; + + case sizeof(__u64): + reg |= KVM_REG_SIZE_U64; + break; + + case sizeof(__uint128_t): + reg |= KVM_REG_SIZE_U128; + break; + + default: + WARN_ON(1); continue; + } if (uindices) { - if (put_user(core_reg | i, uindices)) + if (put_user(reg, uindices)) return -EFAULT; uindices++; }

5 years, 11 months

1
0
0 0

FAILED: patch "[PATCH] arm64: ssbd: explicitly depend on <linux/prctl.h>" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From adeaa21a4b6954e878f3f7d1c5659ed9c1fe567a Mon Sep 17 00:00:00 2001 From: Anisse Astier <aastier(a)freebox.fr> Date: Mon, 17 Jun 2019 15:22:21 +0200 Subject: [PATCH] arm64: ssbd: explicitly depend on <linux/prctl.h> Fix ssbd.c which depends implicitly on asm/ptrace.h including linux/prctl.h (through for example linux/compat.h, then linux/time.h, linux/seqlock.h, linux/spinlock.h and linux/irqflags.h), and uses PR_SPEC* defines. This is an issue since we'll soon be removing the include from asm/ptrace.h. Fixes: 9cdc0108baa8 ("arm64: ssbd: Add prctl interface for per-thread mitigation") Cc: stable(a)vger.kernel.org Signed-off-by: Anisse Astier <aastier(a)freebox.fr> Signed-off-by: Will Deacon <will.deacon(a)arm.com> diff --git a/arch/arm64/kernel/ssbd.c b/arch/arm64/kernel/ssbd.c index 885f13e58708..52cfc6148355 100644 --- a/arch/arm64/kernel/ssbd.c +++ b/arch/arm64/kernel/ssbd.c @@ -5,6 +5,7 @@ #include <linux/compat.h> #include <linux/errno.h> +#include <linux/prctl.h> #include <linux/sched.h> #include <linux/sched/task_stack.h> #include <linux/thread_info.h>

5 years, 11 months

1
0
0 0

FAILED: patch "[PATCH] Btrfs: fix race between block group removal and block group" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 8eaf40c0e24e98899a0f3ac9d25a33aafe13822a Mon Sep 17 00:00:00 2001 From: Filipe Manana <fdmanana(a)suse.com> Date: Wed, 12 Jun 2019 11:05:42 +0100 Subject: [PATCH] Btrfs: fix race between block group removal and block group allocation If a task is removing the block group that currently has the highest start offset amongst all existing block groups, there is a short time window where it races with a concurrent block group allocation, resulting in a transaction abort with an error code of EEXIST. The following diagram explains the race in detail: Task A Task B btrfs_remove_block_group(bg offset X) remove_extent_mapping(em offset X) -> removes extent map X from the tree of extent maps (fs_info->mapping_tree), so the next call to find_next_chunk() will return offset X btrfs_alloc_chunk() find_next_chunk() --> returns offset X __btrfs_alloc_chunk(offset X) btrfs_make_block_group() btrfs_create_block_group_cache() --> creates btrfs_block_group_cache object with a key corresponding to the block group item in the extent, the key is: (offset X, BTRFS_BLOCK_GROUP_ITEM_KEY, 1G) --> adds the btrfs_block_group_cache object to the list new_bgs of the transaction handle btrfs_end_transaction(trans handle) __btrfs_end_transaction() btrfs_create_pending_block_groups() --> sees the new btrfs_block_group_cache in the new_bgs list of the transaction handle --> its call to btrfs_insert_item() fails with -EEXIST when attempting to insert the block group item key (offset X, BTRFS_BLOCK_GROUP_ITEM_KEY, 1G) because task A has not removed that key yet --> aborts the running transaction with error -EEXIST btrfs_del_item() -> removes the block group's key from the extent tree, key is (offset X, BTRFS_BLOCK_GROUP_ITEM_KEY, 1G) A sample transaction abort trace: [78912.403537] ------------[ cut here ]------------ [78912.403811] BTRFS: Transaction aborted (error -17) [78912.404082] WARNING: CPU: 2 PID: 20465 at fs/btrfs/extent-tree.c:10551 btrfs_create_pending_block_groups+0x196/0x250 [btrfs] (...) [78912.405642] CPU: 2 PID: 20465 Comm: btrfs Tainted: G W 5.0.0-btrfs-next-46 #1 [78912.405941] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.2-0-gf9626ccb91-prebuilt.qemu-project.org 04/01/2014 [78912.406586] RIP: 0010:btrfs_create_pending_block_groups+0x196/0x250 [btrfs] (...) [78912.407636] RSP: 0018:ffff9d3d4b7e3b08 EFLAGS: 00010282 [78912.407997] RAX: 0000000000000000 RBX: ffff90959a3796f0 RCX: 0000000000000006 [78912.408369] RDX: 0000000000000007 RSI: 0000000000000001 RDI: ffff909636b16860 [78912.408746] RBP: ffff909626758a58 R08: 0000000000000000 R09: 0000000000000000 [78912.409144] R10: ffff9095ff462400 R11: 0000000000000000 R12: ffff90959a379588 [78912.409521] R13: ffff909626758ab0 R14: ffff9095036c0000 R15: ffff9095299e1158 [78912.409899] FS: 00007f387f16f700(0000) GS:ffff909636b00000(0000) knlGS:0000000000000000 [78912.410285] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [78912.410673] CR2: 00007f429fc87cbc CR3: 000000014440a004 CR4: 00000000003606e0 [78912.411095] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [78912.411496] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [78912.411898] Call Trace: [78912.412318] __btrfs_end_transaction+0x5b/0x1c0 [btrfs] [78912.412746] btrfs_inc_block_group_ro+0xcf/0x160 [btrfs] [78912.413179] scrub_enumerate_chunks+0x188/0x5b0 [btrfs] [78912.413622] ? __mutex_unlock_slowpath+0x100/0x2a0 [78912.414078] btrfs_scrub_dev+0x2ef/0x720 [btrfs] [78912.414535] ? __sb_start_write+0xd4/0x1c0 [78912.414963] ? mnt_want_write_file+0x24/0x50 [78912.415403] btrfs_ioctl+0x17fb/0x3120 [btrfs] [78912.415832] ? lock_acquire+0xa6/0x190 [78912.416256] ? do_vfs_ioctl+0xa2/0x6f0 [78912.416685] ? btrfs_ioctl_get_supported_features+0x30/0x30 [btrfs] [78912.417116] do_vfs_ioctl+0xa2/0x6f0 [78912.417534] ? __fget+0x113/0x200 [78912.417954] ksys_ioctl+0x70/0x80 [78912.418369] __x64_sys_ioctl+0x16/0x20 [78912.418812] do_syscall_64+0x60/0x1b0 [78912.419231] entry_SYSCALL_64_after_hwframe+0x49/0xbe [78912.419644] RIP: 0033:0x7f3880252dd7 (...) [78912.420957] RSP: 002b:00007f387f16ed68 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 [78912.421426] RAX: ffffffffffffffda RBX: 000055f5becc1df0 RCX: 00007f3880252dd7 [78912.421889] RDX: 000055f5becc1df0 RSI: 00000000c400941b RDI: 0000000000000003 [78912.422354] RBP: 0000000000000000 R08: 00007f387f16f700 R09: 0000000000000000 [78912.422790] R10: 00007f387f16f700 R11: 0000000000000246 R12: 0000000000000000 [78912.423202] R13: 00007ffda49c266f R14: 0000000000000000 R15: 00007f388145e040 [78912.425505] ---[ end trace eb9bfe7c426fc4d3 ]--- Fix this by calling remove_extent_mapping(), at btrfs_remove_block_group(), only at the very end, after removing the block group item key from the extent tree (and removing the free space tree entry if we are using the free space tree feature). Fixes: 04216820fe83d5 ("Btrfs: fix race between fs trimming and block group remove/allocation") CC: stable(a)vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index c7adff343ba9..5faf057f6f37 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -10831,17 +10831,6 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, remove_em = (atomic_read(&block_group->trimming) == 0); spin_unlock(&block_group->lock); - if (remove_em) { - struct extent_map_tree *em_tree; - - em_tree = &fs_info->mapping_tree.map_tree; - write_lock(&em_tree->lock); - remove_extent_mapping(em_tree, em); - write_unlock(&em_tree->lock); - /* once for the tree */ - free_extent_map(em); - } - mutex_unlock(&fs_info->chunk_mutex); ret = remove_block_group_free_space(trans, block_group); @@ -10858,6 +10847,19 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, goto out; ret = btrfs_del_item(trans, root, path); + if (ret) + goto out; + + if (remove_em) { + struct extent_map_tree *em_tree; + + em_tree = &fs_info->mapping_tree.map_tree; + write_lock(&em_tree->lock); + remove_extent_mapping(em_tree, em); + write_unlock(&em_tree->lock); + /* once for the tree */ + free_extent_map(em); + } out: if (remove_rsv) btrfs_delayed_refs_rsv_release(fs_info, 1);

5 years, 11 months

1
0
0 0

FAILED: patch "[PATCH] Btrfs: fix race between block group removal and block group" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 8eaf40c0e24e98899a0f3ac9d25a33aafe13822a Mon Sep 17 00:00:00 2001 From: Filipe Manana <fdmanana(a)suse.com> Date: Wed, 12 Jun 2019 11:05:42 +0100 Subject: [PATCH] Btrfs: fix race between block group removal and block group allocation If a task is removing the block group that currently has the highest start offset amongst all existing block groups, there is a short time window where it races with a concurrent block group allocation, resulting in a transaction abort with an error code of EEXIST. The following diagram explains the race in detail: Task A Task B btrfs_remove_block_group(bg offset X) remove_extent_mapping(em offset X) -> removes extent map X from the tree of extent maps (fs_info->mapping_tree), so the next call to find_next_chunk() will return offset X btrfs_alloc_chunk() find_next_chunk() --> returns offset X __btrfs_alloc_chunk(offset X) btrfs_make_block_group() btrfs_create_block_group_cache() --> creates btrfs_block_group_cache object with a key corresponding to the block group item in the extent, the key is: (offset X, BTRFS_BLOCK_GROUP_ITEM_KEY, 1G) --> adds the btrfs_block_group_cache object to the list new_bgs of the transaction handle btrfs_end_transaction(trans handle) __btrfs_end_transaction() btrfs_create_pending_block_groups() --> sees the new btrfs_block_group_cache in the new_bgs list of the transaction handle --> its call to btrfs_insert_item() fails with -EEXIST when attempting to insert the block group item key (offset X, BTRFS_BLOCK_GROUP_ITEM_KEY, 1G) because task A has not removed that key yet --> aborts the running transaction with error -EEXIST btrfs_del_item() -> removes the block group's key from the extent tree, key is (offset X, BTRFS_BLOCK_GROUP_ITEM_KEY, 1G) A sample transaction abort trace: [78912.403537] ------------[ cut here ]------------ [78912.403811] BTRFS: Transaction aborted (error -17) [78912.404082] WARNING: CPU: 2 PID: 20465 at fs/btrfs/extent-tree.c:10551 btrfs_create_pending_block_groups+0x196/0x250 [btrfs] (...) [78912.405642] CPU: 2 PID: 20465 Comm: btrfs Tainted: G W 5.0.0-btrfs-next-46 #1 [78912.405941] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.2-0-gf9626ccb91-prebuilt.qemu-project.org 04/01/2014 [78912.406586] RIP: 0010:btrfs_create_pending_block_groups+0x196/0x250 [btrfs] (...) [78912.407636] RSP: 0018:ffff9d3d4b7e3b08 EFLAGS: 00010282 [78912.407997] RAX: 0000000000000000 RBX: ffff90959a3796f0 RCX: 0000000000000006 [78912.408369] RDX: 0000000000000007 RSI: 0000000000000001 RDI: ffff909636b16860 [78912.408746] RBP: ffff909626758a58 R08: 0000000000000000 R09: 0000000000000000 [78912.409144] R10: ffff9095ff462400 R11: 0000000000000000 R12: ffff90959a379588 [78912.409521] R13: ffff909626758ab0 R14: ffff9095036c0000 R15: ffff9095299e1158 [78912.409899] FS: 00007f387f16f700(0000) GS:ffff909636b00000(0000) knlGS:0000000000000000 [78912.410285] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [78912.410673] CR2: 00007f429fc87cbc CR3: 000000014440a004 CR4: 00000000003606e0 [78912.411095] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [78912.411496] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [78912.411898] Call Trace: [78912.412318] __btrfs_end_transaction+0x5b/0x1c0 [btrfs] [78912.412746] btrfs_inc_block_group_ro+0xcf/0x160 [btrfs] [78912.413179] scrub_enumerate_chunks+0x188/0x5b0 [btrfs] [78912.413622] ? __mutex_unlock_slowpath+0x100/0x2a0 [78912.414078] btrfs_scrub_dev+0x2ef/0x720 [btrfs] [78912.414535] ? __sb_start_write+0xd4/0x1c0 [78912.414963] ? mnt_want_write_file+0x24/0x50 [78912.415403] btrfs_ioctl+0x17fb/0x3120 [btrfs] [78912.415832] ? lock_acquire+0xa6/0x190 [78912.416256] ? do_vfs_ioctl+0xa2/0x6f0 [78912.416685] ? btrfs_ioctl_get_supported_features+0x30/0x30 [btrfs] [78912.417116] do_vfs_ioctl+0xa2/0x6f0 [78912.417534] ? __fget+0x113/0x200 [78912.417954] ksys_ioctl+0x70/0x80 [78912.418369] __x64_sys_ioctl+0x16/0x20 [78912.418812] do_syscall_64+0x60/0x1b0 [78912.419231] entry_SYSCALL_64_after_hwframe+0x49/0xbe [78912.419644] RIP: 0033:0x7f3880252dd7 (...) [78912.420957] RSP: 002b:00007f387f16ed68 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 [78912.421426] RAX: ffffffffffffffda RBX: 000055f5becc1df0 RCX: 00007f3880252dd7 [78912.421889] RDX: 000055f5becc1df0 RSI: 00000000c400941b RDI: 0000000000000003 [78912.422354] RBP: 0000000000000000 R08: 00007f387f16f700 R09: 0000000000000000 [78912.422790] R10: 00007f387f16f700 R11: 0000000000000246 R12: 0000000000000000 [78912.423202] R13: 00007ffda49c266f R14: 0000000000000000 R15: 00007f388145e040 [78912.425505] ---[ end trace eb9bfe7c426fc4d3 ]--- Fix this by calling remove_extent_mapping(), at btrfs_remove_block_group(), only at the very end, after removing the block group item key from the extent tree (and removing the free space tree entry if we are using the free space tree feature). Fixes: 04216820fe83d5 ("Btrfs: fix race between fs trimming and block group remove/allocation") CC: stable(a)vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index c7adff343ba9..5faf057f6f37 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -10831,17 +10831,6 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, remove_em = (atomic_read(&block_group->trimming) == 0); spin_unlock(&block_group->lock); - if (remove_em) { - struct extent_map_tree *em_tree; - - em_tree = &fs_info->mapping_tree.map_tree; - write_lock(&em_tree->lock); - remove_extent_mapping(em_tree, em); - write_unlock(&em_tree->lock); - /* once for the tree */ - free_extent_map(em); - } - mutex_unlock(&fs_info->chunk_mutex); ret = remove_block_group_free_space(trans, block_group); @@ -10858,6 +10847,19 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, goto out; ret = btrfs_del_item(trans, root, path); + if (ret) + goto out; + + if (remove_em) { + struct extent_map_tree *em_tree; + + em_tree = &fs_info->mapping_tree.map_tree; + write_lock(&em_tree->lock); + remove_extent_mapping(em_tree, em); + write_unlock(&em_tree->lock); + /* once for the tree */ + free_extent_map(em); + } out: if (remove_rsv) btrfs_delayed_refs_rsv_release(fs_info, 1);

5 years, 11 months

1
0
0 0

FAILED: patch "[PATCH] Btrfs: fix race between block group removal and block group" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 8eaf40c0e24e98899a0f3ac9d25a33aafe13822a Mon Sep 17 00:00:00 2001 From: Filipe Manana <fdmanana(a)suse.com> Date: Wed, 12 Jun 2019 11:05:42 +0100 Subject: [PATCH] Btrfs: fix race between block group removal and block group allocation If a task is removing the block group that currently has the highest start offset amongst all existing block groups, there is a short time window where it races with a concurrent block group allocation, resulting in a transaction abort with an error code of EEXIST. The following diagram explains the race in detail: Task A Task B btrfs_remove_block_group(bg offset X) remove_extent_mapping(em offset X) -> removes extent map X from the tree of extent maps (fs_info->mapping_tree), so the next call to find_next_chunk() will return offset X btrfs_alloc_chunk() find_next_chunk() --> returns offset X __btrfs_alloc_chunk(offset X) btrfs_make_block_group() btrfs_create_block_group_cache() --> creates btrfs_block_group_cache object with a key corresponding to the block group item in the extent, the key is: (offset X, BTRFS_BLOCK_GROUP_ITEM_KEY, 1G) --> adds the btrfs_block_group_cache object to the list new_bgs of the transaction handle btrfs_end_transaction(trans handle) __btrfs_end_transaction() btrfs_create_pending_block_groups() --> sees the new btrfs_block_group_cache in the new_bgs list of the transaction handle --> its call to btrfs_insert_item() fails with -EEXIST when attempting to insert the block group item key (offset X, BTRFS_BLOCK_GROUP_ITEM_KEY, 1G) because task A has not removed that key yet --> aborts the running transaction with error -EEXIST btrfs_del_item() -> removes the block group's key from the extent tree, key is (offset X, BTRFS_BLOCK_GROUP_ITEM_KEY, 1G) A sample transaction abort trace: [78912.403537] ------------[ cut here ]------------ [78912.403811] BTRFS: Transaction aborted (error -17) [78912.404082] WARNING: CPU: 2 PID: 20465 at fs/btrfs/extent-tree.c:10551 btrfs_create_pending_block_groups+0x196/0x250 [btrfs] (...) [78912.405642] CPU: 2 PID: 20465 Comm: btrfs Tainted: G W 5.0.0-btrfs-next-46 #1 [78912.405941] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.2-0-gf9626ccb91-prebuilt.qemu-project.org 04/01/2014 [78912.406586] RIP: 0010:btrfs_create_pending_block_groups+0x196/0x250 [btrfs] (...) [78912.407636] RSP: 0018:ffff9d3d4b7e3b08 EFLAGS: 00010282 [78912.407997] RAX: 0000000000000000 RBX: ffff90959a3796f0 RCX: 0000000000000006 [78912.408369] RDX: 0000000000000007 RSI: 0000000000000001 RDI: ffff909636b16860 [78912.408746] RBP: ffff909626758a58 R08: 0000000000000000 R09: 0000000000000000 [78912.409144] R10: ffff9095ff462400 R11: 0000000000000000 R12: ffff90959a379588 [78912.409521] R13: ffff909626758ab0 R14: ffff9095036c0000 R15: ffff9095299e1158 [78912.409899] FS: 00007f387f16f700(0000) GS:ffff909636b00000(0000) knlGS:0000000000000000 [78912.410285] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [78912.410673] CR2: 00007f429fc87cbc CR3: 000000014440a004 CR4: 00000000003606e0 [78912.411095] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [78912.411496] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [78912.411898] Call Trace: [78912.412318] __btrfs_end_transaction+0x5b/0x1c0 [btrfs] [78912.412746] btrfs_inc_block_group_ro+0xcf/0x160 [btrfs] [78912.413179] scrub_enumerate_chunks+0x188/0x5b0 [btrfs] [78912.413622] ? __mutex_unlock_slowpath+0x100/0x2a0 [78912.414078] btrfs_scrub_dev+0x2ef/0x720 [btrfs] [78912.414535] ? __sb_start_write+0xd4/0x1c0 [78912.414963] ? mnt_want_write_file+0x24/0x50 [78912.415403] btrfs_ioctl+0x17fb/0x3120 [btrfs] [78912.415832] ? lock_acquire+0xa6/0x190 [78912.416256] ? do_vfs_ioctl+0xa2/0x6f0 [78912.416685] ? btrfs_ioctl_get_supported_features+0x30/0x30 [btrfs] [78912.417116] do_vfs_ioctl+0xa2/0x6f0 [78912.417534] ? __fget+0x113/0x200 [78912.417954] ksys_ioctl+0x70/0x80 [78912.418369] __x64_sys_ioctl+0x16/0x20 [78912.418812] do_syscall_64+0x60/0x1b0 [78912.419231] entry_SYSCALL_64_after_hwframe+0x49/0xbe [78912.419644] RIP: 0033:0x7f3880252dd7 (...) [78912.420957] RSP: 002b:00007f387f16ed68 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 [78912.421426] RAX: ffffffffffffffda RBX: 000055f5becc1df0 RCX: 00007f3880252dd7 [78912.421889] RDX: 000055f5becc1df0 RSI: 00000000c400941b RDI: 0000000000000003 [78912.422354] RBP: 0000000000000000 R08: 00007f387f16f700 R09: 0000000000000000 [78912.422790] R10: 00007f387f16f700 R11: 0000000000000246 R12: 0000000000000000 [78912.423202] R13: 00007ffda49c266f R14: 0000000000000000 R15: 00007f388145e040 [78912.425505] ---[ end trace eb9bfe7c426fc4d3 ]--- Fix this by calling remove_extent_mapping(), at btrfs_remove_block_group(), only at the very end, after removing the block group item key from the extent tree (and removing the free space tree entry if we are using the free space tree feature). Fixes: 04216820fe83d5 ("Btrfs: fix race between fs trimming and block group remove/allocation") CC: stable(a)vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index c7adff343ba9..5faf057f6f37 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -10831,17 +10831,6 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, remove_em = (atomic_read(&block_group->trimming) == 0); spin_unlock(&block_group->lock); - if (remove_em) { - struct extent_map_tree *em_tree; - - em_tree = &fs_info->mapping_tree.map_tree; - write_lock(&em_tree->lock); - remove_extent_mapping(em_tree, em); - write_unlock(&em_tree->lock); - /* once for the tree */ - free_extent_map(em); - } - mutex_unlock(&fs_info->chunk_mutex); ret = remove_block_group_free_space(trans, block_group); @@ -10858,6 +10847,19 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, goto out; ret = btrfs_del_item(trans, root, path); + if (ret) + goto out; + + if (remove_em) { + struct extent_map_tree *em_tree; + + em_tree = &fs_info->mapping_tree.map_tree; + write_lock(&em_tree->lock); + remove_extent_mapping(em_tree, em); + write_unlock(&em_tree->lock); + /* once for the tree */ + free_extent_map(em); + } out: if (remove_rsv) btrfs_delayed_refs_rsv_release(fs_info, 1);

5 years, 11 months

1
0
0 0

FAILED: patch "[PATCH] Btrfs: fix race between block group removal and block group" 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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 8eaf40c0e24e98899a0f3ac9d25a33aafe13822a Mon Sep 17 00:00:00 2001 From: Filipe Manana <fdmanana(a)suse.com> Date: Wed, 12 Jun 2019 11:05:42 +0100 Subject: [PATCH] Btrfs: fix race between block group removal and block group allocation If a task is removing the block group that currently has the highest start offset amongst all existing block groups, there is a short time window where it races with a concurrent block group allocation, resulting in a transaction abort with an error code of EEXIST. The following diagram explains the race in detail: Task A Task B btrfs_remove_block_group(bg offset X) remove_extent_mapping(em offset X) -> removes extent map X from the tree of extent maps (fs_info->mapping_tree), so the next call to find_next_chunk() will return offset X btrfs_alloc_chunk() find_next_chunk() --> returns offset X __btrfs_alloc_chunk(offset X) btrfs_make_block_group() btrfs_create_block_group_cache() --> creates btrfs_block_group_cache object with a key corresponding to the block group item in the extent, the key is: (offset X, BTRFS_BLOCK_GROUP_ITEM_KEY, 1G) --> adds the btrfs_block_group_cache object to the list new_bgs of the transaction handle btrfs_end_transaction(trans handle) __btrfs_end_transaction() btrfs_create_pending_block_groups() --> sees the new btrfs_block_group_cache in the new_bgs list of the transaction handle --> its call to btrfs_insert_item() fails with -EEXIST when attempting to insert the block group item key (offset X, BTRFS_BLOCK_GROUP_ITEM_KEY, 1G) because task A has not removed that key yet --> aborts the running transaction with error -EEXIST btrfs_del_item() -> removes the block group's key from the extent tree, key is (offset X, BTRFS_BLOCK_GROUP_ITEM_KEY, 1G) A sample transaction abort trace: [78912.403537] ------------[ cut here ]------------ [78912.403811] BTRFS: Transaction aborted (error -17) [78912.404082] WARNING: CPU: 2 PID: 20465 at fs/btrfs/extent-tree.c:10551 btrfs_create_pending_block_groups+0x196/0x250 [btrfs] (...) [78912.405642] CPU: 2 PID: 20465 Comm: btrfs Tainted: G W 5.0.0-btrfs-next-46 #1 [78912.405941] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.2-0-gf9626ccb91-prebuilt.qemu-project.org 04/01/2014 [78912.406586] RIP: 0010:btrfs_create_pending_block_groups+0x196/0x250 [btrfs] (...) [78912.407636] RSP: 0018:ffff9d3d4b7e3b08 EFLAGS: 00010282 [78912.407997] RAX: 0000000000000000 RBX: ffff90959a3796f0 RCX: 0000000000000006 [78912.408369] RDX: 0000000000000007 RSI: 0000000000000001 RDI: ffff909636b16860 [78912.408746] RBP: ffff909626758a58 R08: 0000000000000000 R09: 0000000000000000 [78912.409144] R10: ffff9095ff462400 R11: 0000000000000000 R12: ffff90959a379588 [78912.409521] R13: ffff909626758ab0 R14: ffff9095036c0000 R15: ffff9095299e1158 [78912.409899] FS: 00007f387f16f700(0000) GS:ffff909636b00000(0000) knlGS:0000000000000000 [78912.410285] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [78912.410673] CR2: 00007f429fc87cbc CR3: 000000014440a004 CR4: 00000000003606e0 [78912.411095] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [78912.411496] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [78912.411898] Call Trace: [78912.412318] __btrfs_end_transaction+0x5b/0x1c0 [btrfs] [78912.412746] btrfs_inc_block_group_ro+0xcf/0x160 [btrfs] [78912.413179] scrub_enumerate_chunks+0x188/0x5b0 [btrfs] [78912.413622] ? __mutex_unlock_slowpath+0x100/0x2a0 [78912.414078] btrfs_scrub_dev+0x2ef/0x720 [btrfs] [78912.414535] ? __sb_start_write+0xd4/0x1c0 [78912.414963] ? mnt_want_write_file+0x24/0x50 [78912.415403] btrfs_ioctl+0x17fb/0x3120 [btrfs] [78912.415832] ? lock_acquire+0xa6/0x190 [78912.416256] ? do_vfs_ioctl+0xa2/0x6f0 [78912.416685] ? btrfs_ioctl_get_supported_features+0x30/0x30 [btrfs] [78912.417116] do_vfs_ioctl+0xa2/0x6f0 [78912.417534] ? __fget+0x113/0x200 [78912.417954] ksys_ioctl+0x70/0x80 [78912.418369] __x64_sys_ioctl+0x16/0x20 [78912.418812] do_syscall_64+0x60/0x1b0 [78912.419231] entry_SYSCALL_64_after_hwframe+0x49/0xbe [78912.419644] RIP: 0033:0x7f3880252dd7 (...) [78912.420957] RSP: 002b:00007f387f16ed68 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 [78912.421426] RAX: ffffffffffffffda RBX: 000055f5becc1df0 RCX: 00007f3880252dd7 [78912.421889] RDX: 000055f5becc1df0 RSI: 00000000c400941b RDI: 0000000000000003 [78912.422354] RBP: 0000000000000000 R08: 00007f387f16f700 R09: 0000000000000000 [78912.422790] R10: 00007f387f16f700 R11: 0000000000000246 R12: 0000000000000000 [78912.423202] R13: 00007ffda49c266f R14: 0000000000000000 R15: 00007f388145e040 [78912.425505] ---[ end trace eb9bfe7c426fc4d3 ]--- Fix this by calling remove_extent_mapping(), at btrfs_remove_block_group(), only at the very end, after removing the block group item key from the extent tree (and removing the free space tree entry if we are using the free space tree feature). Fixes: 04216820fe83d5 ("Btrfs: fix race between fs trimming and block group remove/allocation") CC: stable(a)vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index c7adff343ba9..5faf057f6f37 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -10831,17 +10831,6 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, remove_em = (atomic_read(&block_group->trimming) == 0); spin_unlock(&block_group->lock); - if (remove_em) { - struct extent_map_tree *em_tree; - - em_tree = &fs_info->mapping_tree.map_tree; - write_lock(&em_tree->lock); - remove_extent_mapping(em_tree, em); - write_unlock(&em_tree->lock); - /* once for the tree */ - free_extent_map(em); - } - mutex_unlock(&fs_info->chunk_mutex); ret = remove_block_group_free_space(trans, block_group); @@ -10858,6 +10847,19 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, goto out; ret = btrfs_del_item(trans, root, path); + if (ret) + goto out; + + if (remove_em) { + struct extent_map_tree *em_tree; + + em_tree = &fs_info->mapping_tree.map_tree; + write_lock(&em_tree->lock); + remove_extent_mapping(em_tree, em); + write_unlock(&em_tree->lock); + /* once for the tree */ + free_extent_map(em); + } out: if (remove_rsv) btrfs_delayed_refs_rsv_release(fs_info, 1);

5 years, 11 months

1
0
0 0

FAILED: patch "[PATCH] Btrfs: fix race between block group removal and block group" failed to apply to 5.0-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.0-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 8eaf40c0e24e98899a0f3ac9d25a33aafe13822a Mon Sep 17 00:00:00 2001 From: Filipe Manana <fdmanana(a)suse.com> Date: Wed, 12 Jun 2019 11:05:42 +0100 Subject: [PATCH] Btrfs: fix race between block group removal and block group allocation If a task is removing the block group that currently has the highest start offset amongst all existing block groups, there is a short time window where it races with a concurrent block group allocation, resulting in a transaction abort with an error code of EEXIST. The following diagram explains the race in detail: Task A Task B btrfs_remove_block_group(bg offset X) remove_extent_mapping(em offset X) -> removes extent map X from the tree of extent maps (fs_info->mapping_tree), so the next call to find_next_chunk() will return offset X btrfs_alloc_chunk() find_next_chunk() --> returns offset X __btrfs_alloc_chunk(offset X) btrfs_make_block_group() btrfs_create_block_group_cache() --> creates btrfs_block_group_cache object with a key corresponding to the block group item in the extent, the key is: (offset X, BTRFS_BLOCK_GROUP_ITEM_KEY, 1G) --> adds the btrfs_block_group_cache object to the list new_bgs of the transaction handle btrfs_end_transaction(trans handle) __btrfs_end_transaction() btrfs_create_pending_block_groups() --> sees the new btrfs_block_group_cache in the new_bgs list of the transaction handle --> its call to btrfs_insert_item() fails with -EEXIST when attempting to insert the block group item key (offset X, BTRFS_BLOCK_GROUP_ITEM_KEY, 1G) because task A has not removed that key yet --> aborts the running transaction with error -EEXIST btrfs_del_item() -> removes the block group's key from the extent tree, key is (offset X, BTRFS_BLOCK_GROUP_ITEM_KEY, 1G) A sample transaction abort trace: [78912.403537] ------------[ cut here ]------------ [78912.403811] BTRFS: Transaction aborted (error -17) [78912.404082] WARNING: CPU: 2 PID: 20465 at fs/btrfs/extent-tree.c:10551 btrfs_create_pending_block_groups+0x196/0x250 [btrfs] (...) [78912.405642] CPU: 2 PID: 20465 Comm: btrfs Tainted: G W 5.0.0-btrfs-next-46 #1 [78912.405941] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.2-0-gf9626ccb91-prebuilt.qemu-project.org 04/01/2014 [78912.406586] RIP: 0010:btrfs_create_pending_block_groups+0x196/0x250 [btrfs] (...) [78912.407636] RSP: 0018:ffff9d3d4b7e3b08 EFLAGS: 00010282 [78912.407997] RAX: 0000000000000000 RBX: ffff90959a3796f0 RCX: 0000000000000006 [78912.408369] RDX: 0000000000000007 RSI: 0000000000000001 RDI: ffff909636b16860 [78912.408746] RBP: ffff909626758a58 R08: 0000000000000000 R09: 0000000000000000 [78912.409144] R10: ffff9095ff462400 R11: 0000000000000000 R12: ffff90959a379588 [78912.409521] R13: ffff909626758ab0 R14: ffff9095036c0000 R15: ffff9095299e1158 [78912.409899] FS: 00007f387f16f700(0000) GS:ffff909636b00000(0000) knlGS:0000000000000000 [78912.410285] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [78912.410673] CR2: 00007f429fc87cbc CR3: 000000014440a004 CR4: 00000000003606e0 [78912.411095] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [78912.411496] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [78912.411898] Call Trace: [78912.412318] __btrfs_end_transaction+0x5b/0x1c0 [btrfs] [78912.412746] btrfs_inc_block_group_ro+0xcf/0x160 [btrfs] [78912.413179] scrub_enumerate_chunks+0x188/0x5b0 [btrfs] [78912.413622] ? __mutex_unlock_slowpath+0x100/0x2a0 [78912.414078] btrfs_scrub_dev+0x2ef/0x720 [btrfs] [78912.414535] ? __sb_start_write+0xd4/0x1c0 [78912.414963] ? mnt_want_write_file+0x24/0x50 [78912.415403] btrfs_ioctl+0x17fb/0x3120 [btrfs] [78912.415832] ? lock_acquire+0xa6/0x190 [78912.416256] ? do_vfs_ioctl+0xa2/0x6f0 [78912.416685] ? btrfs_ioctl_get_supported_features+0x30/0x30 [btrfs] [78912.417116] do_vfs_ioctl+0xa2/0x6f0 [78912.417534] ? __fget+0x113/0x200 [78912.417954] ksys_ioctl+0x70/0x80 [78912.418369] __x64_sys_ioctl+0x16/0x20 [78912.418812] do_syscall_64+0x60/0x1b0 [78912.419231] entry_SYSCALL_64_after_hwframe+0x49/0xbe [78912.419644] RIP: 0033:0x7f3880252dd7 (...) [78912.420957] RSP: 002b:00007f387f16ed68 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 [78912.421426] RAX: ffffffffffffffda RBX: 000055f5becc1df0 RCX: 00007f3880252dd7 [78912.421889] RDX: 000055f5becc1df0 RSI: 00000000c400941b RDI: 0000000000000003 [78912.422354] RBP: 0000000000000000 R08: 00007f387f16f700 R09: 0000000000000000 [78912.422790] R10: 00007f387f16f700 R11: 0000000000000246 R12: 0000000000000000 [78912.423202] R13: 00007ffda49c266f R14: 0000000000000000 R15: 00007f388145e040 [78912.425505] ---[ end trace eb9bfe7c426fc4d3 ]--- Fix this by calling remove_extent_mapping(), at btrfs_remove_block_group(), only at the very end, after removing the block group item key from the extent tree (and removing the free space tree entry if we are using the free space tree feature). Fixes: 04216820fe83d5 ("Btrfs: fix race between fs trimming and block group remove/allocation") CC: stable(a)vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index c7adff343ba9..5faf057f6f37 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -10831,17 +10831,6 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, remove_em = (atomic_read(&block_group->trimming) == 0); spin_unlock(&block_group->lock); - if (remove_em) { - struct extent_map_tree *em_tree; - - em_tree = &fs_info->mapping_tree.map_tree; - write_lock(&em_tree->lock); - remove_extent_mapping(em_tree, em); - write_unlock(&em_tree->lock); - /* once for the tree */ - free_extent_map(em); - } - mutex_unlock(&fs_info->chunk_mutex); ret = remove_block_group_free_space(trans, block_group); @@ -10858,6 +10847,19 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, goto out; ret = btrfs_del_item(trans, root, path); + if (ret) + goto out; + + if (remove_em) { + struct extent_map_tree *em_tree; + + em_tree = &fs_info->mapping_tree.map_tree; + write_lock(&em_tree->lock); + remove_extent_mapping(em_tree, em); + write_unlock(&em_tree->lock); + /* once for the tree */ + free_extent_map(em); + } out: if (remove_rsv) btrfs_delayed_refs_rsv_release(fs_info, 1);

5 years, 11 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror June 2019