diff options
| author | Suraj Jitindar Singh <sjitindarsingh@gmail.com> | 2021-06-02 14:04:41 +1000 |
|---|---|---|
| committer | Michael Ellerman <mpe@ellerman.id.au> | 2021-06-21 09:22:34 +1000 |
| commit | 77bbbc0cf84834ed130838f7ac1988567f4d0288 (patch) | |
| tree | 96646e55740a14f82c68b88bd399c74ec4b25b53 /arch/powerpc/kvm | |
| parent | fae5c9f3664ba278137e54a2083b39b90c64093a (diff) | |
| download | linux-77bbbc0cf84834ed130838f7ac1988567f4d0288.tar.bz2 | |
KVM: PPC: Book3S HV: Fix TLB management on SMT8 POWER9 and POWER10 processors
The POWER9 vCPU TLB management code assumes all threads in a core share
a TLB, and that TLBIEL execued by one thread will invalidate TLBs for
all threads. This is not the case for SMT8 capable POWER9 and POWER10
(big core) processors, where the TLB is split between groups of threads.
This results in TLB multi-hits, random data corruption, etc.
Fix this by introducing cpu_first_tlb_thread_sibling etc., to determine
which siblings share TLBs, and use that in the guest TLB flushing code.
[npiggin@gmail.com: add changelog and comment]
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Fabiano Rosas <farosas@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210602040441.3984352-1-npiggin@gmail.com
Diffstat (limited to 'arch/powerpc/kvm')
| -rw-r--r-- | arch/powerpc/kvm/book3s_hv.c | 13 | ||||
| -rw-r--r-- | arch/powerpc/kvm/book3s_hv_builtin.c | 2 | ||||
| -rw-r--r-- | arch/powerpc/kvm/book3s_hv_rm_mmu.c | 2 |
3 files changed, 9 insertions, 8 deletions
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index f4dc4f0c34b5..c0f1299736b9 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -2820,7 +2820,7 @@ static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu) cpumask_t *cpu_in_guest; int i; - cpu = cpu_first_thread_sibling(cpu); + cpu = cpu_first_tlb_thread_sibling(cpu); if (nested) { cpumask_set_cpu(cpu, &nested->need_tlb_flush); cpu_in_guest = &nested->cpu_in_guest; @@ -2834,9 +2834,10 @@ static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu) * the other side is the first smp_mb() in kvmppc_run_core(). */ smp_mb(); - for (i = 0; i < threads_per_core; ++i) - if (cpumask_test_cpu(cpu + i, cpu_in_guest)) - smp_call_function_single(cpu + i, do_nothing, NULL, 1); + for (i = cpu; i <= cpu_last_tlb_thread_sibling(cpu); + i += cpu_tlb_thread_sibling_step()) + if (cpumask_test_cpu(i, cpu_in_guest)) + smp_call_function_single(i, do_nothing, NULL, 1); } static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu) @@ -2867,8 +2868,8 @@ static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu) */ if (prev_cpu != pcpu) { if (prev_cpu >= 0 && - cpu_first_thread_sibling(prev_cpu) != - cpu_first_thread_sibling(pcpu)) + cpu_first_tlb_thread_sibling(prev_cpu) != + cpu_first_tlb_thread_sibling(pcpu)) radix_flush_cpu(kvm, prev_cpu, vcpu); if (nested) nested->prev_cpu[vcpu->arch.nested_vcpu_id] = pcpu; diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index 259492bb4153..be8ef1c5b1bf 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -721,7 +721,7 @@ void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu, * Thus we make all 4 threads use the same bit. */ if (cpu_has_feature(CPU_FTR_ARCH_300)) - pcpu = cpu_first_thread_sibling(pcpu); + pcpu = cpu_first_tlb_thread_sibling(pcpu); if (nested) need_tlb_flush = &nested->need_tlb_flush; diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index f487ebb3a70a..8b70de4595f0 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -71,7 +71,7 @@ static int global_invalidates(struct kvm *kvm) * so use the bit for the first thread to represent the core. */ if (cpu_has_feature(CPU_FTR_ARCH_300)) - cpu = cpu_first_thread_sibling(cpu); + cpu = cpu_first_tlb_thread_sibling(cpu); cpumask_clear_cpu(cpu, &kvm->arch.need_tlb_flush); } |