From 439793d4b3c99e550daebd868bbd58967c93d0b3 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Wed, 1 Aug 2012 17:01:42 +0300 Subject: KVM: x86: update KVM_SAVE_MSRS_BEGIN to correct value When MSR_KVM_PV_EOI_EN was added to msrs_to_save array KVM_SAVE_MSRS_BEGIN was not updated accordingly. Signed-off-by: Gleb Natapov Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- arch/x86/kvm/x86.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 42bce48f6928..dce75b760312 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -806,7 +806,7 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc); * kvm-specific. Those are put in the beginning of the list. */ -#define KVM_SAVE_MSRS_BEGIN 9 +#define KVM_SAVE_MSRS_BEGIN 10 static u32 msrs_to_save[] = { MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, -- cgit v1.2.3 From 35f2d16bb9ace0fb2671b8232839944ad9057c6f Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Mon, 20 Aug 2012 18:35:39 +0900 Subject: KVM: MMU: Fix mmu_shrink() so that it can free mmu pages as intended Although the possible race described in commit 85b7059169e128c57a3a8a3e588fb89cb2031da1 KVM: MMU: fix shrinking page from the empty mmu was correct, the real cause of that issue was a more trivial bug of mmu_shrink() introduced by commit 1952639665e92481c34c34c3e2a71bf3e66ba362 KVM: MMU: do not iterate over all VMs in mmu_shrink() Here is the bug: if (kvm->arch.n_used_mmu_pages > 0) { if (!nr_to_scan--) break; continue; } We skip VMs whose n_used_mmu_pages is not zero and try to shrink others: in other words we try to shrink empty ones by mistake. This patch reverses the logic so that mmu_shrink() can free pages from the first VM whose n_used_mmu_pages is not zero. Note that we also add comments explaining the role of nr_to_scan which is not practically important now, hoping this will be improved in the future. Signed-off-by: Takuya Yoshikawa Cc: Gleb Natapov Signed-off-by: Avi Kivity --- arch/x86/kvm/mmu.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 01ca00423938..7fbd0d273ea8 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -4112,17 +4112,22 @@ static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc) int idx; LIST_HEAD(invalid_list); + /* + * Never scan more than sc->nr_to_scan VM instances. + * Will not hit this condition practically since we do not try + * to shrink more than one VM and it is very unlikely to see + * !n_used_mmu_pages so many times. + */ + if (!nr_to_scan--) + break; /* * n_used_mmu_pages is accessed without holding kvm->mmu_lock * here. We may skip a VM instance errorneosly, but we do not * want to shrink a VM that only started to populate its MMU * anyway. */ - if (kvm->arch.n_used_mmu_pages > 0) { - if (!nr_to_scan--) - break; + if (!kvm->arch.n_used_mmu_pages) continue; - } idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); -- cgit v1.2.3 From 5ad105e569c45dcfad50d724c61d5061248be755 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Sun, 19 Aug 2012 14:34:31 +0300 Subject: KVM: x86 emulator: use stack size attribute to mask rsp in stack ops The sub-register used to access the stack (sp, esp, or rsp) is not determined by the address size attribute like other memory references, but by the stack segment's B bit (if not in x86_64 mode). Fix by using the existing stack_mask() to figure out the correct mask. This long-existing bug was exposed by a combination of a27685c33acccce (emulate invalid guest state by default), which causes many more instructions to be emulated, and a seabios change (possibly a bug) which causes the high 16 bits of esp to become polluted across calls to real mode software interrupts. Signed-off-by: Avi Kivity Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/emulate.c | 30 +++++++++++++++++++++--------- 1 file changed, 21 insertions(+), 9 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 97d9a9914ba8..a3b57a27be88 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -475,13 +475,26 @@ register_address(struct x86_emulate_ctxt *ctxt, unsigned long reg) return address_mask(ctxt, reg); } +static void masked_increment(ulong *reg, ulong mask, int inc) +{ + assign_masked(reg, *reg + inc, mask); +} + static inline void register_address_increment(struct x86_emulate_ctxt *ctxt, unsigned long *reg, int inc) { + ulong mask; + if (ctxt->ad_bytes == sizeof(unsigned long)) - *reg += inc; + mask = ~0UL; else - *reg = (*reg & ~ad_mask(ctxt)) | ((*reg + inc) & ad_mask(ctxt)); + mask = ad_mask(ctxt); + masked_increment(reg, mask, inc); +} + +static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc) +{ + masked_increment(&ctxt->regs[VCPU_REGS_RSP], stack_mask(ctxt), inc); } static inline void jmp_rel(struct x86_emulate_ctxt *ctxt, int rel) @@ -1522,8 +1535,8 @@ static int push(struct x86_emulate_ctxt *ctxt, void *data, int bytes) { struct segmented_address addr; - register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], -bytes); - addr.ea = register_address(ctxt, ctxt->regs[VCPU_REGS_RSP]); + rsp_increment(ctxt, -bytes); + addr.ea = ctxt->regs[VCPU_REGS_RSP] & stack_mask(ctxt); addr.seg = VCPU_SREG_SS; return segmented_write(ctxt, addr, data, bytes); @@ -1542,13 +1555,13 @@ static int emulate_pop(struct x86_emulate_ctxt *ctxt, int rc; struct segmented_address addr; - addr.ea = register_address(ctxt, ctxt->regs[VCPU_REGS_RSP]); + addr.ea = ctxt->regs[VCPU_REGS_RSP] & stack_mask(ctxt); addr.seg = VCPU_SREG_SS; rc = segmented_read(ctxt, addr, dest, len); if (rc != X86EMUL_CONTINUE) return rc; - register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], len); + rsp_increment(ctxt, len); return rc; } @@ -1688,8 +1701,7 @@ static int em_popa(struct x86_emulate_ctxt *ctxt) while (reg >= VCPU_REGS_RAX) { if (reg == VCPU_REGS_RSP) { - register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], - ctxt->op_bytes); + rsp_increment(ctxt, ctxt->op_bytes); --reg; } @@ -2825,7 +2837,7 @@ static int em_ret_near_imm(struct x86_emulate_ctxt *ctxt) rc = emulate_pop(ctxt, &ctxt->dst.val, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) return rc; - register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], ctxt->src.val); + rsp_increment(ctxt, ctxt->src.val); return X86EMUL_CONTINUE; } -- cgit v1.2.3