From 3c1a4322bba79aad2d3f6f996b7e1c336bd909b3 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Tue, 23 Nov 2021 19:52:00 +1000 Subject: KVM: PPC: Book3S HV: Change dec_expires to be relative to guest timebase Change dec_expires to be relative to the guest timebase, and allow it to be moved into low level P9 guest entry functions, to improve SPR access scheduling. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20211123095231.1036501-23-npiggin@gmail.com --- arch/powerpc/kvm/book3s_hv_nested.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/powerpc/kvm/book3s_hv_nested.c') diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index ed8a2c9f5629..7bed0b91245e 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -358,6 +358,7 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) /* convert TB values/offsets to host (L0) values */ hdec_exp = l2_hv.hdec_expiry - vc->tb_offset; vc->tb_offset += l2_hv.tb_offset; + vcpu->arch.dec_expires += l2_hv.tb_offset; /* set L1 state to L2 state */ vcpu->arch.nested = l2; @@ -399,6 +400,8 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) if (l2_regs.msr & MSR_TS_MASK) vcpu->arch.shregs.msr |= MSR_TS_S; vc->tb_offset = saved_l1_hv.tb_offset; + /* XXX: is this always the same delta as saved_l1_hv.tb_offset? */ + vcpu->arch.dec_expires -= l2_hv.tb_offset; restore_hv_regs(vcpu, &saved_l1_hv); vcpu->arch.purr += delta_purr; vcpu->arch.spurr += delta_spurr; -- cgit v1.2.3 From 46dea77f790c1e7ab2e9f7452e34de0dc5da9b13 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Tue, 23 Nov 2021 19:52:22 +1000 Subject: KVM: PPC: Book3S HV Nested: Avoid extra mftb() in nested entry mftb() is expensive and one can be avoided on nested guest dispatch. If the time checking code distinguishes between the L0 timer and the nested HV timer, then both can be tested in the same place with the same mftb() value. This also nicely illustrates the relationship between the L0 and nested HV timers. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20211123095231.1036501-45-npiggin@gmail.com --- arch/powerpc/include/asm/kvm_asm.h | 1 + arch/powerpc/kvm/book3s_hv.c | 12 ++++++++++++ arch/powerpc/kvm/book3s_hv_nested.c | 5 ----- 3 files changed, 13 insertions(+), 5 deletions(-) (limited to 'arch/powerpc/kvm/book3s_hv_nested.c') diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h index fbbf3cec92e9..d68d71987d5c 100644 --- a/arch/powerpc/include/asm/kvm_asm.h +++ b/arch/powerpc/include/asm/kvm_asm.h @@ -79,6 +79,7 @@ #define BOOK3S_INTERRUPT_FP_UNAVAIL 0x800 #define BOOK3S_INTERRUPT_DECREMENTER 0x900 #define BOOK3S_INTERRUPT_HV_DECREMENTER 0x980 +#define BOOK3S_INTERRUPT_NESTED_HV_DECREMENTER 0x1980 #define BOOK3S_INTERRUPT_DOORBELL 0xa00 #define BOOK3S_INTERRUPT_SYSCALL 0xc00 #define BOOK3S_INTERRUPT_TRACE 0xd00 diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index df4e3f88398d..65c9157579a3 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -1486,6 +1486,10 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, run->ready_for_interrupt_injection = 1; switch (vcpu->arch.trap) { /* We're good on these - the host merely wanted to get our attention */ + case BOOK3S_INTERRUPT_NESTED_HV_DECREMENTER: + WARN_ON_ONCE(1); /* Should never happen */ + vcpu->arch.trap = BOOK3S_INTERRUPT_HV_DECREMENTER; + fallthrough; case BOOK3S_INTERRUPT_HV_DECREMENTER: vcpu->stat.dec_exits++; r = RESUME_GUEST; @@ -1814,6 +1818,12 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu) vcpu->stat.ext_intr_exits++; r = RESUME_GUEST; break; + /* These need to go to the nested HV */ + case BOOK3S_INTERRUPT_NESTED_HV_DECREMENTER: + vcpu->arch.trap = BOOK3S_INTERRUPT_HV_DECREMENTER; + vcpu->stat.dec_exits++; + r = RESUME_HOST; + break; /* SR/HMI/PMI are HV interrupts that host has handled. Resume guest.*/ case BOOK3S_INTERRUPT_HMI: case BOOK3S_INTERRUPT_PERFMON: @@ -3993,6 +4003,8 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, return BOOK3S_INTERRUPT_HV_DECREMENTER; if (next_timer < time_limit) time_limit = next_timer; + else if (*tb >= time_limit) /* nested time limit */ + return BOOK3S_INTERRUPT_NESTED_HV_DECREMENTER; vcpu->arch.ceded = 0; diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index 7bed0b91245e..e57c08b968c0 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -375,11 +375,6 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) vcpu->arch.ret = RESUME_GUEST; vcpu->arch.trap = 0; do { - if (mftb() >= hdec_exp) { - vcpu->arch.trap = BOOK3S_INTERRUPT_HV_DECREMENTER; - r = RESUME_HOST; - break; - } r = kvmhv_run_single_vcpu(vcpu, hdec_exp, lpcr); } while (is_kvmppc_resume_guest(r)); -- cgit v1.2.3 From 792020907b11c6f9246c21977cab3bad985ae4b6 Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Wed, 1 Sep 2021 18:45:50 +1000 Subject: KVM: PPC: Book3S: Suppress failed alloc warning in H_COPY_TOFROM_GUEST H_COPY_TOFROM_GUEST is an hcall for an upper level VM to access its nested VMs memory. The userspace can trigger WARN_ON_ONCE(!(gfp & __GFP_NOWARN)) in __alloc_pages() by constructing a tiny VM which only does H_COPY_TOFROM_GUEST with a too big GPR9 (number of bytes to copy). This silences the warning by adding __GFP_NOWARN. Spotted by syzkaller. Signed-off-by: Alexey Kardashevskiy Reviewed-by: Fabiano Rosas Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20210901084550.1658699-1-aik@ozlabs.ru --- arch/powerpc/kvm/book3s_hv_nested.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/kvm/book3s_hv_nested.c') diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index e57c08b968c0..a2e34efb8d31 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -580,7 +580,7 @@ long kvmhv_copy_tofrom_guest_nested(struct kvm_vcpu *vcpu) if (eaddr & (0xFFFUL << 52)) return H_PARAMETER; - buf = kzalloc(n, GFP_KERNEL); + buf = kzalloc(n, GFP_KERNEL | __GFP_NOWARN); if (!buf) return H_NO_MEM; -- cgit v1.2.3