RISC-V KVM tracks guest interrupt state with two bitmaps: - irqs_pending: interrupts that should be visible to the guest - irqs_pending_mask: interrupts whose pending state changed The current code updates those bitmaps with independent atomic bitops and assumes a multiple-producer, single-consumer protocol. That model does not actually hold. kvm_riscv_vcpu_sync_interrupts() is not a pure consumer. When the guest changes guest-visible HVIP state, sync_interrupts() writes both irqs_pending and irqs_pending_mask to reflect the new guest state back into KVM state. As a result, irqs_pending and irqs_pending_mask form a single logical state transition, but they are not updated atomically as a pair. This allows a race where a newly injected interrupt is lost. For example: CPU0 CPU1 ---- ---- kvm_riscv_vcpu_set_interrupt(VS_SOFT) set_bit(VS_SOFT, irqs_pending) kvm_riscv_vcpu_sync_interrupts() sees guest-cleared HVIP.VSSIP sets irqs_pending_mask clears irqs_pending set_bit(VS_SOFT, irqs_pending_mask) kvm_vcpu_kick() After that interleaving, a later flush can update HVIP without VSSIP even though a new virtual interrupt was injected. In practice, the guest can remain blocked in WFI with work pending. The same pending/mask protocol is shared by VS soft interrupts, PMU overflow delivery, and AIA high interrupt synchronization, so the race is not limited to one interrupt source. Fix this by serializing all updates to irqs_pending and irqs_pending_mask with a per-vCPU raw spinlock. This keeps the pending bit and the dirty mask as one state transition across: - set/unset interrupt - guest HVIP sync - interrupt flush to guest CSR state - vCPU reset - AIA CSR writes that clear dirty state Use non-atomic bitmap operations while holding the lock. Hold the lock across the AIA sync, flush, and pending checks as well, so both bitmap words share the same serialization domain. This intentionally replaces the existing lockless protocol instead of trying to repair it with additional barriers. The problem is not memory ordering on a single field; it is that two separate bitmaps encode one shared state machine while both producers and sync paths can modify them. A per-vCPU raw spinlock keeps the fix small, local, and suitable for backporting. Fixes: cce69aff689e ("RISC-V: KVM: Implement VCPU interrupts and requests handling") Cc: stable@vger.kernel.org Signed-off-by: Xie Bo --- Changes in v3: - Rebase onto Linux 7.2-rc3. - Use non-atomic bitmap operations under irqs_pending_lock. - Hold irqs_pending_lock across the AIA sync/flush helpers and add lockdep assertions for their locking contract. - Protect kvm_riscv_vcpu_has_interrupts() with irqs_pending_lock. Changes in v2: - Expand the race description and user-visible failure mode. arch/riscv/include/asm/kvm_host.h | 10 ++--- arch/riscv/kvm/aia.c | 33 ++++++++++++---- arch/riscv/kvm/vcpu.c | 63 +++++++++++++++++++++---------- arch/riscv/kvm/vcpu_onereg.c | 13 +++++-- 4 files changed, 82 insertions(+), 37 deletions(-) diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index 60017ceec9d..e2d5808169e 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -209,13 +209,13 @@ struct kvm_vcpu_arch { /* * VCPU interrupts * - * We have a lockless approach for tracking pending VCPU interrupts - * implemented using atomic bitops. The irqs_pending bitmap represent - * pending interrupts whereas irqs_pending_mask represent bits changed - * in irqs_pending. Our approach is modeled around multiple producer - * and single consumer problem where the consumer is the VCPU itself. + * The irqs_pending bitmap represents pending interrupts whereas + * irqs_pending_mask represents bits changed in irqs_pending. Updates + * to these bitmaps are serialized so vcpu interrupt sync/flush cannot + * drop a newly injected interrupt while syncing guest-visible HVIP. */ #define KVM_RISCV_VCPU_NR_IRQS 64 + raw_spinlock_t irqs_pending_lock; DECLARE_BITMAP(irqs_pending, KVM_RISCV_VCPU_NR_IRQS); DECLARE_BITMAP(irqs_pending_mask, KVM_RISCV_VCPU_NR_IRQS); diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c index bafb009c5ce..225e4aed81a 100644 --- a/arch/riscv/kvm/aia.c +++ b/arch/riscv/kvm/aia.c @@ -53,12 +53,15 @@ void kvm_riscv_vcpu_aia_flush_interrupts(struct kvm_vcpu *vcpu) struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; unsigned long mask, val; + lockdep_assert_held(&vcpu->arch.irqs_pending_lock); + if (!kvm_riscv_aia_available()) return; - if (READ_ONCE(vcpu->arch.irqs_pending_mask[1])) { - mask = xchg_acquire(&vcpu->arch.irqs_pending_mask[1], 0); - val = READ_ONCE(vcpu->arch.irqs_pending[1]) & mask; + mask = vcpu->arch.irqs_pending_mask[1]; + if (mask) { + vcpu->arch.irqs_pending_mask[1] = 0; + val = vcpu->arch.irqs_pending[1] & mask; csr->hviph &= ~mask; csr->hviph |= val; @@ -69,6 +72,8 @@ void kvm_riscv_vcpu_aia_sync_interrupts(struct kvm_vcpu *vcpu) { struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; + lockdep_assert_held(&vcpu->arch.irqs_pending_lock); + if (kvm_riscv_aia_available()) csr->vsieh = ncsr_read(CSR_VSIEH); } @@ -78,11 +83,13 @@ bool kvm_riscv_vcpu_aia_has_interrupts(struct kvm_vcpu *vcpu, u64 mask) { unsigned long seip; + lockdep_assert_held(&vcpu->arch.irqs_pending_lock); + if (!kvm_riscv_aia_available()) return false; #ifdef CONFIG_32BIT - if (READ_ONCE(vcpu->arch.irqs_pending[1]) & + if (vcpu->arch.irqs_pending[1] & (vcpu->arch.aia_context.guest_csr.vsieh & upper_32_bits(mask))) return true; #endif @@ -207,6 +214,9 @@ int kvm_riscv_vcpu_aia_set_csr(struct kvm_vcpu *vcpu, { struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; unsigned long regs_max = sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long); +#ifdef CONFIG_32BIT + unsigned long flags; +#endif if (!riscv_isa_extension_available(vcpu->arch.isa, SSAIA)) return -ENOENT; @@ -216,11 +226,18 @@ int kvm_riscv_vcpu_aia_set_csr(struct kvm_vcpu *vcpu, reg_num = array_index_nospec(reg_num, regs_max); if (kvm_riscv_aia_available()) { - ((unsigned long *)csr)[reg_num] = val; - #ifdef CONFIG_32BIT - if (reg_num == KVM_REG_RISCV_CSR_AIA_REG(siph)) - WRITE_ONCE(vcpu->arch.irqs_pending_mask[1], 0); + if (reg_num == KVM_REG_RISCV_CSR_AIA_REG(siph)) { + raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags); + ((unsigned long *)csr)[reg_num] = val; + vcpu->arch.irqs_pending_mask[1] = 0; + raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, + flags); + } else { + ((unsigned long *)csr)[reg_num] = val; + } +#else + ((unsigned long *)csr)[reg_num] = val; #endif } diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index cf6e231e76e..7d8d20839d4 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -80,6 +80,7 @@ static void kvm_riscv_vcpu_context_reset(struct kvm_vcpu *vcpu, static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu, bool kvm_sbi_reset) { + unsigned long flags; bool loaded; /** @@ -104,8 +105,10 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu, bool kvm_sbi_reset) kvm_riscv_vcpu_aia_reset(vcpu); + raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags); bitmap_zero(vcpu->arch.irqs_pending, KVM_RISCV_VCPU_NR_IRQS); bitmap_zero(vcpu->arch.irqs_pending_mask, KVM_RISCV_VCPU_NR_IRQS); + raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, flags); kvm_riscv_vcpu_pmu_reset(vcpu); @@ -151,6 +154,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) /* Setup VCPU hfence queue */ spin_lock_init(&vcpu->arch.hfence_lock); + raw_spin_lock_init(&vcpu->arch.irqs_pending_lock); spin_lock_init(&vcpu->arch.reset_state.lock); @@ -352,10 +356,13 @@ void kvm_riscv_vcpu_flush_interrupts(struct kvm_vcpu *vcpu) { struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; unsigned long mask, val; + unsigned long flags; - if (READ_ONCE(vcpu->arch.irqs_pending_mask[0])) { - mask = xchg_acquire(&vcpu->arch.irqs_pending_mask[0], 0); - val = READ_ONCE(vcpu->arch.irqs_pending[0]) & mask; + raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags); + mask = vcpu->arch.irqs_pending_mask[0]; + if (mask) { + vcpu->arch.irqs_pending_mask[0] = 0; + val = vcpu->arch.irqs_pending[0] & mask; csr->hvip &= ~mask; csr->hvip |= val; @@ -363,11 +370,13 @@ void kvm_riscv_vcpu_flush_interrupts(struct kvm_vcpu *vcpu) /* Flush AIA high interrupts */ kvm_riscv_vcpu_aia_flush_interrupts(vcpu); + raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, flags); } void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu) { unsigned long hvip; + unsigned long flags; struct kvm_vcpu_arch *v = &vcpu->arch; struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; @@ -376,27 +385,29 @@ void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu) /* Sync-up HVIP.VSSIP bit changes does by Guest */ hvip = ncsr_read(CSR_HVIP); + raw_spin_lock_irqsave(&v->irqs_pending_lock, flags); if ((csr->hvip ^ hvip) & (1UL << IRQ_VS_SOFT)) { if (hvip & (1UL << IRQ_VS_SOFT)) { - if (!test_and_set_bit(IRQ_VS_SOFT, - v->irqs_pending_mask)) - set_bit(IRQ_VS_SOFT, v->irqs_pending); + if (!__test_and_set_bit(IRQ_VS_SOFT, + v->irqs_pending_mask)) + __set_bit(IRQ_VS_SOFT, v->irqs_pending); } else { - if (!test_and_set_bit(IRQ_VS_SOFT, - v->irqs_pending_mask)) - clear_bit(IRQ_VS_SOFT, v->irqs_pending); + if (!__test_and_set_bit(IRQ_VS_SOFT, + v->irqs_pending_mask)) + __clear_bit(IRQ_VS_SOFT, v->irqs_pending); } } /* Sync up the HVIP.LCOFIP bit changes (only clear) by the guest */ if ((csr->hvip ^ hvip) & (1UL << IRQ_PMU_OVF)) { if (!(hvip & (1UL << IRQ_PMU_OVF)) && - !test_and_set_bit(IRQ_PMU_OVF, v->irqs_pending_mask)) - clear_bit(IRQ_PMU_OVF, v->irqs_pending); + !__test_and_set_bit(IRQ_PMU_OVF, v->irqs_pending_mask)) + __clear_bit(IRQ_PMU_OVF, v->irqs_pending); } /* Sync-up AIA high interrupts */ kvm_riscv_vcpu_aia_sync_interrupts(vcpu); + raw_spin_unlock_irqrestore(&v->irqs_pending_lock, flags); /* Sync-up timer CSRs */ kvm_riscv_vcpu_timer_sync(vcpu); @@ -404,6 +415,8 @@ void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu) int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq) { + unsigned long flags; + /* * We only allow VS-mode software, timer, and external * interrupts when irq is one of the local interrupts @@ -416,9 +429,10 @@ int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq) irq != IRQ_PMU_OVF) return -EINVAL; - set_bit(irq, vcpu->arch.irqs_pending); - smp_mb__before_atomic(); - set_bit(irq, vcpu->arch.irqs_pending_mask); + raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags); + __set_bit(irq, vcpu->arch.irqs_pending); + __set_bit(irq, vcpu->arch.irqs_pending_mask); + raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, flags); kvm_vcpu_kick(vcpu); @@ -427,6 +441,8 @@ int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq) int kvm_riscv_vcpu_unset_interrupt(struct kvm_vcpu *vcpu, unsigned int irq) { + unsigned long flags; + /* * We only allow VS-mode software, timer, counter overflow and external * interrupts when irq is one of the local interrupts @@ -439,26 +455,33 @@ int kvm_riscv_vcpu_unset_interrupt(struct kvm_vcpu *vcpu, unsigned int irq) irq != IRQ_PMU_OVF) return -EINVAL; - clear_bit(irq, vcpu->arch.irqs_pending); - smp_mb__before_atomic(); - set_bit(irq, vcpu->arch.irqs_pending_mask); + raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags); + __clear_bit(irq, vcpu->arch.irqs_pending); + __set_bit(irq, vcpu->arch.irqs_pending_mask); + raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, flags); return 0; } bool kvm_riscv_vcpu_has_interrupts(struct kvm_vcpu *vcpu, u64 mask) { + unsigned long flags; unsigned long ie; + bool ret; + raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags); ie = ((vcpu->arch.guest_csr.vsie & VSIP_VALID_MASK) << VSIP_TO_HVIP_SHIFT) & (unsigned long)mask; ie |= vcpu->arch.guest_csr.vsie & ~IRQ_LOCAL_MASK & (unsigned long)mask; - if (READ_ONCE(vcpu->arch.irqs_pending[0]) & ie) - return true; + ret = vcpu->arch.irqs_pending[0] & ie; /* Check AIA high interrupts */ - return kvm_riscv_vcpu_aia_has_interrupts(vcpu, mask); + if (!ret) + ret = kvm_riscv_vcpu_aia_has_interrupts(vcpu, mask); + raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, flags); + + return ret; } void __kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu) diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c index bb920e8923c..cba3682944b 100644 --- a/arch/riscv/kvm/vcpu_onereg.c +++ b/arch/riscv/kvm/vcpu_onereg.c @@ -298,6 +298,7 @@ static int kvm_riscv_vcpu_general_set_csr(struct kvm_vcpu *vcpu, { struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; unsigned long regs_max = sizeof(struct kvm_riscv_csr) / sizeof(unsigned long); + unsigned long flags; if (reg_num >= regs_max) return -ENOENT; @@ -309,10 +310,14 @@ static int kvm_riscv_vcpu_general_set_csr(struct kvm_vcpu *vcpu, reg_val <<= VSIP_TO_HVIP_SHIFT; } - ((unsigned long *)csr)[reg_num] = reg_val; - - if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) - WRITE_ONCE(vcpu->arch.irqs_pending_mask[0], 0); + if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) { + raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags); + ((unsigned long *)csr)[reg_num] = reg_val; + vcpu->arch.irqs_pending_mask[0] = 0; + raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, flags); + } else { + ((unsigned long *)csr)[reg_num] = reg_val; + } return 0; } -- 2.54.0