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

FAILED: patch "[PATCH] x86/kvm: move kvm_load/put_guest_xcr0 into atomic context" 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 1811d979c71621aafc7b879477202d286f7e863b Mon Sep 17 00:00:00 2001 From: WANG Chao <chao.wang(a)ucloud.cn> Date: Fri, 12 Apr 2019 15:55:39 +0800 Subject: [PATCH] x86/kvm: move kvm_load/put_guest_xcr0 into atomic context guest xcr0 could leak into host when MCE happens in guest mode. Because do_machine_check() could schedule out at a few places. For example: kvm_load_guest_xcr0 ... kvm_x86_ops->run(vcpu) { vmx_vcpu_run vmx_complete_atomic_exit kvm_machine_check do_machine_check do_memory_failure memory_failure lock_page In this case, host_xcr0 is 0x2ff, guest vcpu xcr0 is 0xff. After schedule out, host cpu has guest xcr0 loaded (0xff). In __switch_to { switch_fpu_finish copy_kernel_to_fpregs XRSTORS If any bit i in XSTATE_BV[i] == 1 and xcr0[i] == 0, XRSTORS will generate #GP (In this case, bit 9). Then ex_handler_fprestore kicks in and tries to reinitialize fpu by restoring init fpu state. Same story as last #GP, except we get DOUBLE FAULT this time. Cc: stable(a)vger.kernel.org Signed-off-by: WANG Chao <chao.wang(a)ucloud.cn> Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index c6815aef2cac..675cecb3fa9c 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -5636,6 +5636,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) svm->vmcb->save.cr2 = vcpu->arch.cr2; clgi(); + kvm_load_guest_xcr0(vcpu); /* * If this vCPU has touched SPEC_CTRL, restore the guest's value if @@ -5781,6 +5782,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) kvm_before_interrupt(&svm->vcpu); + kvm_put_guest_xcr0(vcpu); stgi(); /* Any pending NMI will happen here */ diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 7a8f75fc6b7e..88060a621db2 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6410,6 +6410,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) vmx_set_interrupt_shadow(vcpu, 0); + kvm_load_guest_xcr0(vcpu); + if (static_cpu_has(X86_FEATURE_PKU) && kvm_read_cr4_bits(vcpu, X86_CR4_PKE) && vcpu->arch.pkru != vmx->host_pkru) @@ -6506,6 +6508,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) __write_pkru(vmx->host_pkru); } + kvm_put_guest_xcr0(vcpu); + vmx->nested.nested_run_pending = 0; vmx->idt_vectoring_info = 0; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 455f156f56ed..f05891b8df7c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -800,7 +800,7 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw) } EXPORT_SYMBOL_GPL(kvm_lmsw); -static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) +void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) { if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) && !vcpu->guest_xcr0_loaded) { @@ -810,8 +810,9 @@ static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) vcpu->guest_xcr0_loaded = 1; } } +EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0); -static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) +void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) { if (vcpu->guest_xcr0_loaded) { if (vcpu->arch.xcr0 != host_xcr0) @@ -819,6 +820,7 @@ static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) vcpu->guest_xcr0_loaded = 0; } } +EXPORT_SYMBOL_GPL(kvm_put_guest_xcr0); static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { @@ -7865,8 +7867,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto cancel_injection; } - kvm_load_guest_xcr0(vcpu); - if (req_immediate_exit) { kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_x86_ops->request_immediate_exit(vcpu); @@ -7919,8 +7919,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); - kvm_put_guest_xcr0(vcpu); - kvm_before_interrupt(vcpu); kvm_x86_ops->handle_external_intr(vcpu); kvm_after_interrupt(vcpu); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 28406aa1136d..aedc5d0d4989 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -347,4 +347,6 @@ static inline void kvm_after_interrupt(struct kvm_vcpu *vcpu) __this_cpu_write(current_vcpu, NULL); } +void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu); +void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu); #endif

6 years, 6 months

1
0
0 0

FAILED: patch "[PATCH] x86/kvm: move kvm_load/put_guest_xcr0 into atomic context" 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 1811d979c71621aafc7b879477202d286f7e863b Mon Sep 17 00:00:00 2001 From: WANG Chao <chao.wang(a)ucloud.cn> Date: Fri, 12 Apr 2019 15:55:39 +0800 Subject: [PATCH] x86/kvm: move kvm_load/put_guest_xcr0 into atomic context guest xcr0 could leak into host when MCE happens in guest mode. Because do_machine_check() could schedule out at a few places. For example: kvm_load_guest_xcr0 ... kvm_x86_ops->run(vcpu) { vmx_vcpu_run vmx_complete_atomic_exit kvm_machine_check do_machine_check do_memory_failure memory_failure lock_page In this case, host_xcr0 is 0x2ff, guest vcpu xcr0 is 0xff. After schedule out, host cpu has guest xcr0 loaded (0xff). In __switch_to { switch_fpu_finish copy_kernel_to_fpregs XRSTORS If any bit i in XSTATE_BV[i] == 1 and xcr0[i] == 0, XRSTORS will generate #GP (In this case, bit 9). Then ex_handler_fprestore kicks in and tries to reinitialize fpu by restoring init fpu state. Same story as last #GP, except we get DOUBLE FAULT this time. Cc: stable(a)vger.kernel.org Signed-off-by: WANG Chao <chao.wang(a)ucloud.cn> Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index c6815aef2cac..675cecb3fa9c 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -5636,6 +5636,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) svm->vmcb->save.cr2 = vcpu->arch.cr2; clgi(); + kvm_load_guest_xcr0(vcpu); /* * If this vCPU has touched SPEC_CTRL, restore the guest's value if @@ -5781,6 +5782,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) kvm_before_interrupt(&svm->vcpu); + kvm_put_guest_xcr0(vcpu); stgi(); /* Any pending NMI will happen here */ diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 7a8f75fc6b7e..88060a621db2 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6410,6 +6410,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) vmx_set_interrupt_shadow(vcpu, 0); + kvm_load_guest_xcr0(vcpu); + if (static_cpu_has(X86_FEATURE_PKU) && kvm_read_cr4_bits(vcpu, X86_CR4_PKE) && vcpu->arch.pkru != vmx->host_pkru) @@ -6506,6 +6508,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) __write_pkru(vmx->host_pkru); } + kvm_put_guest_xcr0(vcpu); + vmx->nested.nested_run_pending = 0; vmx->idt_vectoring_info = 0; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 455f156f56ed..f05891b8df7c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -800,7 +800,7 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw) } EXPORT_SYMBOL_GPL(kvm_lmsw); -static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) +void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) { if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) && !vcpu->guest_xcr0_loaded) { @@ -810,8 +810,9 @@ static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) vcpu->guest_xcr0_loaded = 1; } } +EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0); -static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) +void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) { if (vcpu->guest_xcr0_loaded) { if (vcpu->arch.xcr0 != host_xcr0) @@ -819,6 +820,7 @@ static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) vcpu->guest_xcr0_loaded = 0; } } +EXPORT_SYMBOL_GPL(kvm_put_guest_xcr0); static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { @@ -7865,8 +7867,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto cancel_injection; } - kvm_load_guest_xcr0(vcpu); - if (req_immediate_exit) { kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_x86_ops->request_immediate_exit(vcpu); @@ -7919,8 +7919,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); - kvm_put_guest_xcr0(vcpu); - kvm_before_interrupt(vcpu); kvm_x86_ops->handle_external_intr(vcpu); kvm_after_interrupt(vcpu); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 28406aa1136d..aedc5d0d4989 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -347,4 +347,6 @@ static inline void kvm_after_interrupt(struct kvm_vcpu *vcpu) __this_cpu_write(current_vcpu, NULL); } +void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu); +void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu); #endif

6 years, 6 months

1
0
0 0

FAILED: patch "[PATCH] x86/kvm: move kvm_load/put_guest_xcr0 into atomic context" 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 1811d979c71621aafc7b879477202d286f7e863b Mon Sep 17 00:00:00 2001 From: WANG Chao <chao.wang(a)ucloud.cn> Date: Fri, 12 Apr 2019 15:55:39 +0800 Subject: [PATCH] x86/kvm: move kvm_load/put_guest_xcr0 into atomic context guest xcr0 could leak into host when MCE happens in guest mode. Because do_machine_check() could schedule out at a few places. For example: kvm_load_guest_xcr0 ... kvm_x86_ops->run(vcpu) { vmx_vcpu_run vmx_complete_atomic_exit kvm_machine_check do_machine_check do_memory_failure memory_failure lock_page In this case, host_xcr0 is 0x2ff, guest vcpu xcr0 is 0xff. After schedule out, host cpu has guest xcr0 loaded (0xff). In __switch_to { switch_fpu_finish copy_kernel_to_fpregs XRSTORS If any bit i in XSTATE_BV[i] == 1 and xcr0[i] == 0, XRSTORS will generate #GP (In this case, bit 9). Then ex_handler_fprestore kicks in and tries to reinitialize fpu by restoring init fpu state. Same story as last #GP, except we get DOUBLE FAULT this time. Cc: stable(a)vger.kernel.org Signed-off-by: WANG Chao <chao.wang(a)ucloud.cn> Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index c6815aef2cac..675cecb3fa9c 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -5636,6 +5636,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) svm->vmcb->save.cr2 = vcpu->arch.cr2; clgi(); + kvm_load_guest_xcr0(vcpu); /* * If this vCPU has touched SPEC_CTRL, restore the guest's value if @@ -5781,6 +5782,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) kvm_before_interrupt(&svm->vcpu); + kvm_put_guest_xcr0(vcpu); stgi(); /* Any pending NMI will happen here */ diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 7a8f75fc6b7e..88060a621db2 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6410,6 +6410,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) vmx_set_interrupt_shadow(vcpu, 0); + kvm_load_guest_xcr0(vcpu); + if (static_cpu_has(X86_FEATURE_PKU) && kvm_read_cr4_bits(vcpu, X86_CR4_PKE) && vcpu->arch.pkru != vmx->host_pkru) @@ -6506,6 +6508,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) __write_pkru(vmx->host_pkru); } + kvm_put_guest_xcr0(vcpu); + vmx->nested.nested_run_pending = 0; vmx->idt_vectoring_info = 0; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 455f156f56ed..f05891b8df7c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -800,7 +800,7 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw) } EXPORT_SYMBOL_GPL(kvm_lmsw); -static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) +void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) { if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) && !vcpu->guest_xcr0_loaded) { @@ -810,8 +810,9 @@ static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) vcpu->guest_xcr0_loaded = 1; } } +EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0); -static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) +void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) { if (vcpu->guest_xcr0_loaded) { if (vcpu->arch.xcr0 != host_xcr0) @@ -819,6 +820,7 @@ static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) vcpu->guest_xcr0_loaded = 0; } } +EXPORT_SYMBOL_GPL(kvm_put_guest_xcr0); static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { @@ -7865,8 +7867,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto cancel_injection; } - kvm_load_guest_xcr0(vcpu); - if (req_immediate_exit) { kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_x86_ops->request_immediate_exit(vcpu); @@ -7919,8 +7919,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); - kvm_put_guest_xcr0(vcpu); - kvm_before_interrupt(vcpu); kvm_x86_ops->handle_external_intr(vcpu); kvm_after_interrupt(vcpu); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 28406aa1136d..aedc5d0d4989 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -347,4 +347,6 @@ static inline void kvm_after_interrupt(struct kvm_vcpu *vcpu) __this_cpu_write(current_vcpu, NULL); } +void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu); +void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu); #endif

6 years, 6 months

1
0
0 0

FAILED: patch "[PATCH] x86/kvm: move kvm_load/put_guest_xcr0 into atomic context" 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 1811d979c71621aafc7b879477202d286f7e863b Mon Sep 17 00:00:00 2001 From: WANG Chao <chao.wang(a)ucloud.cn> Date: Fri, 12 Apr 2019 15:55:39 +0800 Subject: [PATCH] x86/kvm: move kvm_load/put_guest_xcr0 into atomic context guest xcr0 could leak into host when MCE happens in guest mode. Because do_machine_check() could schedule out at a few places. For example: kvm_load_guest_xcr0 ... kvm_x86_ops->run(vcpu) { vmx_vcpu_run vmx_complete_atomic_exit kvm_machine_check do_machine_check do_memory_failure memory_failure lock_page In this case, host_xcr0 is 0x2ff, guest vcpu xcr0 is 0xff. After schedule out, host cpu has guest xcr0 loaded (0xff). In __switch_to { switch_fpu_finish copy_kernel_to_fpregs XRSTORS If any bit i in XSTATE_BV[i] == 1 and xcr0[i] == 0, XRSTORS will generate #GP (In this case, bit 9). Then ex_handler_fprestore kicks in and tries to reinitialize fpu by restoring init fpu state. Same story as last #GP, except we get DOUBLE FAULT this time. Cc: stable(a)vger.kernel.org Signed-off-by: WANG Chao <chao.wang(a)ucloud.cn> Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index c6815aef2cac..675cecb3fa9c 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -5636,6 +5636,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) svm->vmcb->save.cr2 = vcpu->arch.cr2; clgi(); + kvm_load_guest_xcr0(vcpu); /* * If this vCPU has touched SPEC_CTRL, restore the guest's value if @@ -5781,6 +5782,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) kvm_before_interrupt(&svm->vcpu); + kvm_put_guest_xcr0(vcpu); stgi(); /* Any pending NMI will happen here */ diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 7a8f75fc6b7e..88060a621db2 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6410,6 +6410,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) vmx_set_interrupt_shadow(vcpu, 0); + kvm_load_guest_xcr0(vcpu); + if (static_cpu_has(X86_FEATURE_PKU) && kvm_read_cr4_bits(vcpu, X86_CR4_PKE) && vcpu->arch.pkru != vmx->host_pkru) @@ -6506,6 +6508,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) __write_pkru(vmx->host_pkru); } + kvm_put_guest_xcr0(vcpu); + vmx->nested.nested_run_pending = 0; vmx->idt_vectoring_info = 0; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 455f156f56ed..f05891b8df7c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -800,7 +800,7 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw) } EXPORT_SYMBOL_GPL(kvm_lmsw); -static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) +void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) { if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) && !vcpu->guest_xcr0_loaded) { @@ -810,8 +810,9 @@ static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) vcpu->guest_xcr0_loaded = 1; } } +EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0); -static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) +void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) { if (vcpu->guest_xcr0_loaded) { if (vcpu->arch.xcr0 != host_xcr0) @@ -819,6 +820,7 @@ static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) vcpu->guest_xcr0_loaded = 0; } } +EXPORT_SYMBOL_GPL(kvm_put_guest_xcr0); static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { @@ -7865,8 +7867,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto cancel_injection; } - kvm_load_guest_xcr0(vcpu); - if (req_immediate_exit) { kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_x86_ops->request_immediate_exit(vcpu); @@ -7919,8 +7919,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); - kvm_put_guest_xcr0(vcpu); - kvm_before_interrupt(vcpu); kvm_x86_ops->handle_external_intr(vcpu); kvm_after_interrupt(vcpu); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 28406aa1136d..aedc5d0d4989 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -347,4 +347,6 @@ static inline void kvm_after_interrupt(struct kvm_vcpu *vcpu) __this_cpu_write(current_vcpu, NULL); } +void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu); +void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu); #endif

6 years, 6 months

1
0
0 0

FAILED: patch "[PATCH] coredump: fix race condition between" 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 04f5866e41fb70690e28397487d8bd8eea7d712a Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli <aarcange(a)redhat.com> Date: Thu, 18 Apr 2019 17:50:52 -0700 Subject: [PATCH] coredump: fix race condition between mmget_not_zero()/get_task_mm() and core dumping The core dumping code has always run without holding the mmap_sem for writing, despite that is the only way to ensure that the entire vma layout will not change from under it. Only using some signal serialization on the processes belonging to the mm is not nearly enough. This was pointed out earlier. For example in Hugh's post from Jul 2017: https://lkml.kernel.org/r/alpine.LSU.2.11.1707191716030.2055@eggly.anvils "Not strictly relevant here, but a related note: I was very surprised to discover, only quite recently, how handle_mm_fault() may be called without down_read(mmap_sem) - when core dumping. That seems a misguided optimization to me, which would also be nice to correct" In particular because the growsdown and growsup can move the vm_start/vm_end the various loops the core dump does around the vma will not be consistent if page faults can happen concurrently. Pretty much all users calling mmget_not_zero()/get_task_mm() and then taking the mmap_sem had the potential to introduce unexpected side effects in the core dumping code. Adding mmap_sem for writing around the ->core_dump invocation is a viable long term fix, but it requires removing all copy user and page faults and to replace them with get_dump_page() for all binary formats which is not suitable as a short term fix. For the time being this solution manually covers the places that can confuse the core dump either by altering the vma layout or the vma flags while it runs. Once ->core_dump runs under mmap_sem for writing the function mmget_still_valid() can be dropped. Allowing mmap_sem protected sections to run in parallel with the coredump provides some minor parallelism advantage to the swapoff code (which seems to be safe enough by never mangling any vma field and can keep doing swapins in parallel to the core dumping) and to some other corner case. In order to facilitate the backporting I added "Fixes: 86039bd3b4e6" however the side effect of this same race condition in /proc/pid/mem should be reproducible since before 2.6.12-rc2 so I couldn't add any other "Fixes:" because there's no hash beyond the git genesis commit. Because find_extend_vma() is the only location outside of the process context that could modify the "mm" structures under mmap_sem for reading, by adding the mmget_still_valid() check to it, all other cases that take the mmap_sem for reading don't need the new check after mmget_not_zero()/get_task_mm(). The expand_stack() in page fault context also doesn't need the new check, because all tasks under core dumping are frozen. Link: http://lkml.kernel.org/r/20190325224949.11068-1-aarcange@redhat.com Fixes: 86039bd3b4e6 ("userfaultfd: add new syscall to provide memory externalization") Signed-off-by: Andrea Arcangeli <aarcange(a)redhat.com> Reported-by: Jann Horn <jannh(a)google.com> Suggested-by: Oleg Nesterov <oleg(a)redhat.com> Acked-by: Peter Xu <peterx(a)redhat.com> Reviewed-by: Mike Rapoport <rppt(a)linux.ibm.com> Reviewed-by: Oleg Nesterov <oleg(a)redhat.com> Reviewed-by: Jann Horn <jannh(a)google.com> Acked-by: Jason Gunthorpe <jgg(a)mellanox.com> Acked-by: Michal Hocko <mhocko(a)suse.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 70b7d80431a9..f2e7ffe6fc54 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -993,6 +993,8 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile) * will only be one mm, so no big deal. */ down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto skip_mm; mutex_lock(&ufile->umap_lock); list_for_each_entry_safe (priv, next_priv, &ufile->umaps, list) { @@ -1007,6 +1009,7 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile) vma->vm_flags &= ~(VM_SHARED | VM_MAYSHARE); } mutex_unlock(&ufile->umap_lock); + skip_mm: up_write(&mm->mmap_sem); mmput(mm); } diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 92a91e7816d8..95ca1fe7283c 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1143,6 +1143,24 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, count = -EINTR; goto out_mm; } + /* + * Avoid to modify vma->vm_flags + * without locked ops while the + * coredump reads the vm_flags. + */ + if (!mmget_still_valid(mm)) { + /* + * Silently return "count" + * like if get_task_mm() + * failed. FIXME: should this + * function have returned + * -ESRCH if get_task_mm() + * failed like if + * get_proc_task() fails? + */ + up_write(&mm->mmap_sem); + goto out_mm; + } for (vma = mm->mmap; vma; vma = vma->vm_next) { vma->vm_flags &= ~VM_SOFTDIRTY; vma_set_page_prot(vma); diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 89800fc7dc9d..f5de1e726356 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -629,6 +629,8 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, /* the various vma->vm_userfaultfd_ctx still points to it */ down_write(&mm->mmap_sem); + /* no task can run (and in turn coredump) yet */ + VM_WARN_ON(!mmget_still_valid(mm)); for (vma = mm->mmap; vma; vma = vma->vm_next) if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) { vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; @@ -883,6 +885,8 @@ static int userfaultfd_release(struct inode *inode, struct file *file) * taking the mmap_sem for writing. */ down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto skip_mm; prev = NULL; for (vma = mm->mmap; vma; vma = vma->vm_next) { cond_resched(); @@ -905,6 +909,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file) vma->vm_flags = new_flags; vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; } +skip_mm: up_write(&mm->mmap_sem); mmput(mm); wakeup: @@ -1333,6 +1338,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, goto out; down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto out_unlock; vma = find_vma_prev(mm, start, &prev); if (!vma) goto out_unlock; @@ -1520,6 +1527,8 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, goto out; down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto out_unlock; vma = find_vma_prev(mm, start, &prev); if (!vma) goto out_unlock; diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 0cd9f10423fb..a3fda9f024c3 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -49,6 +49,27 @@ static inline void mmdrop(struct mm_struct *mm) __mmdrop(mm); } +/* + * This has to be called after a get_task_mm()/mmget_not_zero() + * followed by taking the mmap_sem for writing before modifying the + * vmas or anything the coredump pretends not to change from under it. + * + * NOTE: find_extend_vma() called from GUP context is the only place + * that can modify the "mm" (notably the vm_start/end) under mmap_sem + * for reading and outside the context of the process, so it is also + * the only case that holds the mmap_sem for reading that must call + * this function. Generally if the mmap_sem is hold for reading + * there's no need of this check after get_task_mm()/mmget_not_zero(). + * + * This function can be obsoleted and the check can be removed, after + * the coredump code will hold the mmap_sem for writing before + * invoking the ->core_dump methods. + */ +static inline bool mmget_still_valid(struct mm_struct *mm) +{ + return likely(!mm->core_state); +} + /** * mmget() - Pin the address space associated with a &struct mm_struct. * @mm: The address space to pin. diff --git a/mm/mmap.c b/mm/mmap.c index 41eb48d9b527..bd7b9f293b39 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -45,6 +45,7 @@ #include <linux/moduleparam.h> #include <linux/pkeys.h> #include <linux/oom.h> +#include <linux/sched/mm.h> #include <linux/uaccess.h> #include <asm/cacheflush.h> @@ -2525,7 +2526,8 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr) vma = find_vma_prev(mm, addr, &prev); if (vma && (vma->vm_start <= addr)) return vma; - if (!prev || expand_stack(prev, addr)) + /* don't alter vm_end if the coredump is running */ + if (!prev || !mmget_still_valid(mm) || expand_stack(prev, addr)) return NULL; if (prev->vm_flags & VM_LOCKED) populate_vma_page_range(prev, addr, prev->vm_end, NULL); @@ -2551,6 +2553,9 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr) return vma; if (!(vma->vm_flags & VM_GROWSDOWN)) return NULL; + /* don't alter vm_start if the coredump is running */ + if (!mmget_still_valid(mm)) + return NULL; start = vma->vm_start; if (expand_stack(vma, addr)) return NULL;

6 years, 6 months

1
0
0 0

FAILED: patch "[PATCH] coredump: fix race condition between" 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 04f5866e41fb70690e28397487d8bd8eea7d712a Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli <aarcange(a)redhat.com> Date: Thu, 18 Apr 2019 17:50:52 -0700 Subject: [PATCH] coredump: fix race condition between mmget_not_zero()/get_task_mm() and core dumping The core dumping code has always run without holding the mmap_sem for writing, despite that is the only way to ensure that the entire vma layout will not change from under it. Only using some signal serialization on the processes belonging to the mm is not nearly enough. This was pointed out earlier. For example in Hugh's post from Jul 2017: https://lkml.kernel.org/r/alpine.LSU.2.11.1707191716030.2055@eggly.anvils "Not strictly relevant here, but a related note: I was very surprised to discover, only quite recently, how handle_mm_fault() may be called without down_read(mmap_sem) - when core dumping. That seems a misguided optimization to me, which would also be nice to correct" In particular because the growsdown and growsup can move the vm_start/vm_end the various loops the core dump does around the vma will not be consistent if page faults can happen concurrently. Pretty much all users calling mmget_not_zero()/get_task_mm() and then taking the mmap_sem had the potential to introduce unexpected side effects in the core dumping code. Adding mmap_sem for writing around the ->core_dump invocation is a viable long term fix, but it requires removing all copy user and page faults and to replace them with get_dump_page() for all binary formats which is not suitable as a short term fix. For the time being this solution manually covers the places that can confuse the core dump either by altering the vma layout or the vma flags while it runs. Once ->core_dump runs under mmap_sem for writing the function mmget_still_valid() can be dropped. Allowing mmap_sem protected sections to run in parallel with the coredump provides some minor parallelism advantage to the swapoff code (which seems to be safe enough by never mangling any vma field and can keep doing swapins in parallel to the core dumping) and to some other corner case. In order to facilitate the backporting I added "Fixes: 86039bd3b4e6" however the side effect of this same race condition in /proc/pid/mem should be reproducible since before 2.6.12-rc2 so I couldn't add any other "Fixes:" because there's no hash beyond the git genesis commit. Because find_extend_vma() is the only location outside of the process context that could modify the "mm" structures under mmap_sem for reading, by adding the mmget_still_valid() check to it, all other cases that take the mmap_sem for reading don't need the new check after mmget_not_zero()/get_task_mm(). The expand_stack() in page fault context also doesn't need the new check, because all tasks under core dumping are frozen. Link: http://lkml.kernel.org/r/20190325224949.11068-1-aarcange@redhat.com Fixes: 86039bd3b4e6 ("userfaultfd: add new syscall to provide memory externalization") Signed-off-by: Andrea Arcangeli <aarcange(a)redhat.com> Reported-by: Jann Horn <jannh(a)google.com> Suggested-by: Oleg Nesterov <oleg(a)redhat.com> Acked-by: Peter Xu <peterx(a)redhat.com> Reviewed-by: Mike Rapoport <rppt(a)linux.ibm.com> Reviewed-by: Oleg Nesterov <oleg(a)redhat.com> Reviewed-by: Jann Horn <jannh(a)google.com> Acked-by: Jason Gunthorpe <jgg(a)mellanox.com> Acked-by: Michal Hocko <mhocko(a)suse.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 70b7d80431a9..f2e7ffe6fc54 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -993,6 +993,8 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile) * will only be one mm, so no big deal. */ down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto skip_mm; mutex_lock(&ufile->umap_lock); list_for_each_entry_safe (priv, next_priv, &ufile->umaps, list) { @@ -1007,6 +1009,7 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile) vma->vm_flags &= ~(VM_SHARED | VM_MAYSHARE); } mutex_unlock(&ufile->umap_lock); + skip_mm: up_write(&mm->mmap_sem); mmput(mm); } diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 92a91e7816d8..95ca1fe7283c 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1143,6 +1143,24 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, count = -EINTR; goto out_mm; } + /* + * Avoid to modify vma->vm_flags + * without locked ops while the + * coredump reads the vm_flags. + */ + if (!mmget_still_valid(mm)) { + /* + * Silently return "count" + * like if get_task_mm() + * failed. FIXME: should this + * function have returned + * -ESRCH if get_task_mm() + * failed like if + * get_proc_task() fails? + */ + up_write(&mm->mmap_sem); + goto out_mm; + } for (vma = mm->mmap; vma; vma = vma->vm_next) { vma->vm_flags &= ~VM_SOFTDIRTY; vma_set_page_prot(vma); diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 89800fc7dc9d..f5de1e726356 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -629,6 +629,8 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, /* the various vma->vm_userfaultfd_ctx still points to it */ down_write(&mm->mmap_sem); + /* no task can run (and in turn coredump) yet */ + VM_WARN_ON(!mmget_still_valid(mm)); for (vma = mm->mmap; vma; vma = vma->vm_next) if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) { vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; @@ -883,6 +885,8 @@ static int userfaultfd_release(struct inode *inode, struct file *file) * taking the mmap_sem for writing. */ down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto skip_mm; prev = NULL; for (vma = mm->mmap; vma; vma = vma->vm_next) { cond_resched(); @@ -905,6 +909,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file) vma->vm_flags = new_flags; vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; } +skip_mm: up_write(&mm->mmap_sem); mmput(mm); wakeup: @@ -1333,6 +1338,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, goto out; down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto out_unlock; vma = find_vma_prev(mm, start, &prev); if (!vma) goto out_unlock; @@ -1520,6 +1527,8 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, goto out; down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto out_unlock; vma = find_vma_prev(mm, start, &prev); if (!vma) goto out_unlock; diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 0cd9f10423fb..a3fda9f024c3 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -49,6 +49,27 @@ static inline void mmdrop(struct mm_struct *mm) __mmdrop(mm); } +/* + * This has to be called after a get_task_mm()/mmget_not_zero() + * followed by taking the mmap_sem for writing before modifying the + * vmas or anything the coredump pretends not to change from under it. + * + * NOTE: find_extend_vma() called from GUP context is the only place + * that can modify the "mm" (notably the vm_start/end) under mmap_sem + * for reading and outside the context of the process, so it is also + * the only case that holds the mmap_sem for reading that must call + * this function. Generally if the mmap_sem is hold for reading + * there's no need of this check after get_task_mm()/mmget_not_zero(). + * + * This function can be obsoleted and the check can be removed, after + * the coredump code will hold the mmap_sem for writing before + * invoking the ->core_dump methods. + */ +static inline bool mmget_still_valid(struct mm_struct *mm) +{ + return likely(!mm->core_state); +} + /** * mmget() - Pin the address space associated with a &struct mm_struct. * @mm: The address space to pin. diff --git a/mm/mmap.c b/mm/mmap.c index 41eb48d9b527..bd7b9f293b39 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -45,6 +45,7 @@ #include <linux/moduleparam.h> #include <linux/pkeys.h> #include <linux/oom.h> +#include <linux/sched/mm.h> #include <linux/uaccess.h> #include <asm/cacheflush.h> @@ -2525,7 +2526,8 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr) vma = find_vma_prev(mm, addr, &prev); if (vma && (vma->vm_start <= addr)) return vma; - if (!prev || expand_stack(prev, addr)) + /* don't alter vm_end if the coredump is running */ + if (!prev || !mmget_still_valid(mm) || expand_stack(prev, addr)) return NULL; if (prev->vm_flags & VM_LOCKED) populate_vma_page_range(prev, addr, prev->vm_end, NULL); @@ -2551,6 +2553,9 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr) return vma; if (!(vma->vm_flags & VM_GROWSDOWN)) return NULL; + /* don't alter vm_start if the coredump is running */ + if (!mmget_still_valid(mm)) + return NULL; start = vma->vm_start; if (expand_stack(vma, addr)) return NULL;

6 years, 6 months

1
0
0 0

FAILED: patch "[PATCH] scsi: core: set result when the command cannot be dispatched" 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 be549d49115422f846b6d96ee8fd7173a5f7ceb0 Mon Sep 17 00:00:00 2001 From: Jaesoo Lee <jalee(a)purestorage.com> Date: Tue, 9 Apr 2019 17:02:22 -0700 Subject: [PATCH] scsi: core: set result when the command cannot be dispatched When SCSI blk-mq is enabled, there is a bug in handling errors in scsi_queue_rq. Specifically, the bug is not setting result field of scsi_request correctly when the dispatch of the command has been failed. Since the upper layer code including the sg_io ioctl expects to receive any error status from result field of scsi_request, the error is silently ignored and this could cause data corruptions for some applications. Fixes: d285203cf647 ("scsi: add support for a blk-mq based I/O path.") Cc: <stable(a)vger.kernel.org> Signed-off-by: Jaesoo Lee <jalee(a)purestorage.com> Reviewed-by: Hannes Reinecke <hare(a)suse.com> Reviewed-by: Bart Van Assche <bvanassche(a)acm.org> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 601b9f1de267..07dfc17d4824 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1706,8 +1706,12 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx, ret = BLK_STS_DEV_RESOURCE; break; default: + if (unlikely(!scsi_device_online(sdev))) + scsi_req(req)->result = DID_NO_CONNECT << 16; + else + scsi_req(req)->result = DID_ERROR << 16; /* - * Make sure to release all allocated ressources when + * Make sure to release all allocated resources when * we hit an error, as we will never see this command * again. */

6 years, 6 months

1
0
0 0

FAILED: patch "[PATCH] scsi: core: set result when the command cannot be dispatched" 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 be549d49115422f846b6d96ee8fd7173a5f7ceb0 Mon Sep 17 00:00:00 2001 From: Jaesoo Lee <jalee(a)purestorage.com> Date: Tue, 9 Apr 2019 17:02:22 -0700 Subject: [PATCH] scsi: core: set result when the command cannot be dispatched When SCSI blk-mq is enabled, there is a bug in handling errors in scsi_queue_rq. Specifically, the bug is not setting result field of scsi_request correctly when the dispatch of the command has been failed. Since the upper layer code including the sg_io ioctl expects to receive any error status from result field of scsi_request, the error is silently ignored and this could cause data corruptions for some applications. Fixes: d285203cf647 ("scsi: add support for a blk-mq based I/O path.") Cc: <stable(a)vger.kernel.org> Signed-off-by: Jaesoo Lee <jalee(a)purestorage.com> Reviewed-by: Hannes Reinecke <hare(a)suse.com> Reviewed-by: Bart Van Assche <bvanassche(a)acm.org> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 601b9f1de267..07dfc17d4824 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1706,8 +1706,12 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx, ret = BLK_STS_DEV_RESOURCE; break; default: + if (unlikely(!scsi_device_online(sdev))) + scsi_req(req)->result = DID_NO_CONNECT << 16; + else + scsi_req(req)->result = DID_ERROR << 16; /* - * Make sure to release all allocated ressources when + * Make sure to release all allocated resources when * we hit an error, as we will never see this command * again. */

6 years, 6 months

1
0
0 0

FAILED: patch "[PATCH] iio: core: fix a possible circular locking dependency" 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 7f75591fc5a123929a29636834d1bcb8b5c9fee3 Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier <fabrice.gasnier(a)st.com> Date: Mon, 25 Mar 2019 14:01:23 +0100 Subject: [PATCH] iio: core: fix a possible circular locking dependency This fixes a possible circular locking dependency detected warning seen with: - CONFIG_PROVE_LOCKING=y - consumer/provider IIO devices (ex: "voltage-divider" consumer of "adc") When using the IIO consumer interface, e.g. iio_channel_get(), the consumer device will likely call iio_read_channel_raw() or similar that rely on 'info_exist_lock' mutex. typically: ... mutex_lock(&chan->indio_dev->info_exist_lock); if (chan->indio_dev->info == NULL) { ret = -ENODEV; goto err_unlock; } ret = do_some_ops() err_unlock: mutex_unlock(&chan->indio_dev->info_exist_lock); return ret; ... Same mutex is also hold in iio_device_unregister(). The following deadlock warning happens when: - the consumer device has called an API like iio_read_channel_raw() at least once. - the consumer driver is unregistered, removed (unbind from sysfs) ====================================================== WARNING: possible circular locking dependency detected 4.19.24 #577 Not tainted ------------------------------------------------------ sh/372 is trying to acquire lock: (kn->count#30){++++}, at: kernfs_remove_by_name_ns+0x3c/0x84 but task is already holding lock: (&dev->info_exist_lock){+.+.}, at: iio_device_unregister+0x18/0x60 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&dev->info_exist_lock){+.+.}: __mutex_lock+0x70/0xa3c mutex_lock_nested+0x1c/0x24 iio_read_channel_raw+0x1c/0x60 iio_read_channel_info+0xa8/0xb0 dev_attr_show+0x1c/0x48 sysfs_kf_seq_show+0x84/0xec seq_read+0x154/0x528 __vfs_read+0x2c/0x15c vfs_read+0x8c/0x110 ksys_read+0x4c/0xac ret_fast_syscall+0x0/0x28 0xbedefb60 -> #0 (kn->count#30){++++}: lock_acquire+0xd8/0x268 __kernfs_remove+0x288/0x374 kernfs_remove_by_name_ns+0x3c/0x84 remove_files+0x34/0x78 sysfs_remove_group+0x40/0x9c sysfs_remove_groups+0x24/0x34 device_remove_attrs+0x38/0x64 device_del+0x11c/0x360 cdev_device_del+0x14/0x2c iio_device_unregister+0x24/0x60 release_nodes+0x1bc/0x200 device_release_driver_internal+0x1a0/0x230 unbind_store+0x80/0x130 kernfs_fop_write+0x100/0x1e4 __vfs_write+0x2c/0x160 vfs_write+0xa4/0x17c ksys_write+0x4c/0xac ret_fast_syscall+0x0/0x28 0xbe906840 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&dev->info_exist_lock); lock(kn->count#30); lock(&dev->info_exist_lock); lock(kn->count#30); *** DEADLOCK *** ... cdev_device_del() can be called without holding the lock. It should be safe as info_exist_lock prevents kernelspace consumers to use the exported routines during/after provider removal. cdev_device_del() is for userspace. Help to reproduce: See example: Documentation/devicetree/bindings/iio/afe/voltage-divider.txt sysv { compatible = "voltage-divider"; io-channels = <&adc 0>; output-ohms = <22>; full-ohms = <222>; }; First, go to iio:deviceX for the "voltage-divider", do one read: $ cd /sys/bus/iio/devices/iio:deviceX $ cat in_voltage0_raw Then, unbind the consumer driver. It triggers above deadlock warning. $ cd /sys/bus/platform/drivers/iio-rescale/ $ echo sysv > unbind Note I don't actually expect stable will pick this up all the way back into IIO being in staging, but if's probably valid that far back. Signed-off-by: Fabrice Gasnier <fabrice.gasnier(a)st.com> Fixes: ac917a81117c ("staging:iio:core set the iio_dev.info pointer to null on unregister") Cc: <Stable(a)vger.kernel.org> Signed-off-by: Jonathan Cameron <Jonathan.Cameron(a)huawei.com> diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index 4700fd5d8c90..9c4d92115504 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -1743,10 +1743,10 @@ EXPORT_SYMBOL(__iio_device_register); **/ void iio_device_unregister(struct iio_dev *indio_dev) { - mutex_lock(&indio_dev->info_exist_lock); - cdev_device_del(&indio_dev->chrdev, &indio_dev->dev); + mutex_lock(&indio_dev->info_exist_lock); + iio_device_unregister_debugfs(indio_dev); iio_disable_all_buffers(indio_dev);

6 years, 6 months

1
0
0 0

FAILED: patch "[PATCH] iio: core: fix a possible circular locking dependency" 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 7f75591fc5a123929a29636834d1bcb8b5c9fee3 Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier <fabrice.gasnier(a)st.com> Date: Mon, 25 Mar 2019 14:01:23 +0100 Subject: [PATCH] iio: core: fix a possible circular locking dependency This fixes a possible circular locking dependency detected warning seen with: - CONFIG_PROVE_LOCKING=y - consumer/provider IIO devices (ex: "voltage-divider" consumer of "adc") When using the IIO consumer interface, e.g. iio_channel_get(), the consumer device will likely call iio_read_channel_raw() or similar that rely on 'info_exist_lock' mutex. typically: ... mutex_lock(&chan->indio_dev->info_exist_lock); if (chan->indio_dev->info == NULL) { ret = -ENODEV; goto err_unlock; } ret = do_some_ops() err_unlock: mutex_unlock(&chan->indio_dev->info_exist_lock); return ret; ... Same mutex is also hold in iio_device_unregister(). The following deadlock warning happens when: - the consumer device has called an API like iio_read_channel_raw() at least once. - the consumer driver is unregistered, removed (unbind from sysfs) ====================================================== WARNING: possible circular locking dependency detected 4.19.24 #577 Not tainted ------------------------------------------------------ sh/372 is trying to acquire lock: (kn->count#30){++++}, at: kernfs_remove_by_name_ns+0x3c/0x84 but task is already holding lock: (&dev->info_exist_lock){+.+.}, at: iio_device_unregister+0x18/0x60 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&dev->info_exist_lock){+.+.}: __mutex_lock+0x70/0xa3c mutex_lock_nested+0x1c/0x24 iio_read_channel_raw+0x1c/0x60 iio_read_channel_info+0xa8/0xb0 dev_attr_show+0x1c/0x48 sysfs_kf_seq_show+0x84/0xec seq_read+0x154/0x528 __vfs_read+0x2c/0x15c vfs_read+0x8c/0x110 ksys_read+0x4c/0xac ret_fast_syscall+0x0/0x28 0xbedefb60 -> #0 (kn->count#30){++++}: lock_acquire+0xd8/0x268 __kernfs_remove+0x288/0x374 kernfs_remove_by_name_ns+0x3c/0x84 remove_files+0x34/0x78 sysfs_remove_group+0x40/0x9c sysfs_remove_groups+0x24/0x34 device_remove_attrs+0x38/0x64 device_del+0x11c/0x360 cdev_device_del+0x14/0x2c iio_device_unregister+0x24/0x60 release_nodes+0x1bc/0x200 device_release_driver_internal+0x1a0/0x230 unbind_store+0x80/0x130 kernfs_fop_write+0x100/0x1e4 __vfs_write+0x2c/0x160 vfs_write+0xa4/0x17c ksys_write+0x4c/0xac ret_fast_syscall+0x0/0x28 0xbe906840 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&dev->info_exist_lock); lock(kn->count#30); lock(&dev->info_exist_lock); lock(kn->count#30); *** DEADLOCK *** ... cdev_device_del() can be called without holding the lock. It should be safe as info_exist_lock prevents kernelspace consumers to use the exported routines during/after provider removal. cdev_device_del() is for userspace. Help to reproduce: See example: Documentation/devicetree/bindings/iio/afe/voltage-divider.txt sysv { compatible = "voltage-divider"; io-channels = <&adc 0>; output-ohms = <22>; full-ohms = <222>; }; First, go to iio:deviceX for the "voltage-divider", do one read: $ cd /sys/bus/iio/devices/iio:deviceX $ cat in_voltage0_raw Then, unbind the consumer driver. It triggers above deadlock warning. $ cd /sys/bus/platform/drivers/iio-rescale/ $ echo sysv > unbind Note I don't actually expect stable will pick this up all the way back into IIO being in staging, but if's probably valid that far back. Signed-off-by: Fabrice Gasnier <fabrice.gasnier(a)st.com> Fixes: ac917a81117c ("staging:iio:core set the iio_dev.info pointer to null on unregister") Cc: <Stable(a)vger.kernel.org> Signed-off-by: Jonathan Cameron <Jonathan.Cameron(a)huawei.com> diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index 4700fd5d8c90..9c4d92115504 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -1743,10 +1743,10 @@ EXPORT_SYMBOL(__iio_device_register); **/ void iio_device_unregister(struct iio_dev *indio_dev) { - mutex_lock(&indio_dev->info_exist_lock); - cdev_device_del(&indio_dev->chrdev, &indio_dev->dev); + mutex_lock(&indio_dev->info_exist_lock); + iio_device_unregister_debugfs(indio_dev); iio_disable_all_buffers(indio_dev);

6 years, 6 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror