提交 a9df174b 编写于 作者: S Suraj Jitindar Singh 提交者: Zheng Zengkai

KVM: PPC: Book3S HV: Fix TLB management on SMT8 POWER9 and POWER10 processors

stable inclusion
from stable-5.10.50
commit 9b282912372785b1b841d0b7b16d1c61bf2539c0
bugzilla: 174522 https://gitee.com/openeuler/kernel/issues/I4DNFY

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=9b282912372785b1b841d0b7b16d1c61bf2539c0

--------------------------------

[ Upstream commit 77bbbc0c ]

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: NPaul Mackerras <paulus@ozlabs.org>
Signed-off-by: NNicholas Piggin <npiggin@gmail.com>
Reviewed-by: NFabiano Rosas <farosas@linux.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210602040441.3984352-1-npiggin@gmail.comSigned-off-by: NSasha Levin <sashal@kernel.org>
Signed-off-by: NChen Jun <chenjun102@huawei.com>
Acked-by: NWeilong Chen <chenweilong@huawei.com>
Signed-off-by: NChen Jun <chenjun102@huawei.com>
Signed-off-by: NZheng Zengkai <zhengzengkai@huawei.com>
上级 4077a0ca
......@@ -98,6 +98,36 @@ static inline int cpu_last_thread_sibling(int cpu)
return cpu | (threads_per_core - 1);
}
/*
* tlb_thread_siblings are siblings which share a TLB. This is not
* architected, is not something a hypervisor could emulate and a future
* CPU may change behaviour even in compat mode, so this should only be
* used on PowerNV, and only with care.
*/
static inline int cpu_first_tlb_thread_sibling(int cpu)
{
if (cpu_has_feature(CPU_FTR_ARCH_300) && (threads_per_core == 8))
return cpu & ~0x6; /* Big Core */
else
return cpu_first_thread_sibling(cpu);
}
static inline int cpu_last_tlb_thread_sibling(int cpu)
{
if (cpu_has_feature(CPU_FTR_ARCH_300) && (threads_per_core == 8))
return cpu | 0x6; /* Big Core */
else
return cpu_last_thread_sibling(cpu);
}
static inline int cpu_tlb_thread_sibling_step(void)
{
if (cpu_has_feature(CPU_FTR_ARCH_300) && (threads_per_core == 8))
return 2; /* Big Core */
else
return 1;
}
static inline u32 get_tensr(void)
{
#ifdef CONFIG_BOOKE
......
......@@ -2578,7 +2578,7 @@ 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;
......@@ -2592,9 +2592,10 @@ 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)
......@@ -2625,8 +2626,8 @@ 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;
......
......@@ -893,7 +893,7 @@ 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;
......
......@@ -56,7 +56,7 @@ 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);
}
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册