summaryrefslogtreecommitdiff
path: root/arch/x86/kvm/emulate.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-01-31 09:30:41 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2020-01-31 09:30:41 -0800
commite813e65038389b66d2f8dd87588694caf8dc2923 (patch)
tree4595d8ebaf672b79b412bd663a13907fd785478d /arch/x86/kvm/emulate.c
parentccaaaf6fe5a5e1fffca5cca0f3fc4ec84d7ae752 (diff)
parent4cbc418a44d5067133271bb6eeac2382f2bf94f7 (diff)
downloadlwn-e813e65038389b66d2f8dd87588694caf8dc2923.tar.gz
lwn-e813e65038389b66d2f8dd87588694caf8dc2923.zip
Merge tag 'kvm-5.6-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull KVM updates from Paolo Bonzini: "This is the first batch of KVM changes. ARM: - cleanups and corner case fixes. PPC: - Bugfixes x86: - Support for mapping DAX areas with large nested page table entries. - Cleanups and bugfixes here too. A particularly important one is a fix for FPU load when the thread has TIF_NEED_FPU_LOAD. There is also a race condition which could be used in guest userspace to exploit the guest kernel, for which the embargo expired today. - Fast path for IPI delivery vmexits, shaving about 200 clock cycles from IPI latency. - Protect against "Spectre-v1/L1TF" (bring data in the cache via speculative out of bound accesses, use L1TF on the sibling hyperthread to read it), which unfortunately is an even bigger whack-a-mole game than SpectreV1. Sean continues his mission to rewrite KVM. In addition to a sizable number of x86 patches, this time he contributed a pretty large refactoring of vCPU creation that affects all architectures but should not have any visible effect. s390 will come next week together with some more x86 patches" * tag 'kvm-5.6-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (204 commits) x86/KVM: Clean up host's steal time structure x86/KVM: Make sure KVM_VCPU_FLUSH_TLB flag is not missed x86/kvm: Cache gfn to pfn translation x86/kvm: Introduce kvm_(un)map_gfn() x86/kvm: Be careful not to clear KVM_VCPU_FLUSH_TLB bit KVM: PPC: Book3S PR: Fix -Werror=return-type build failure KVM: PPC: Book3S HV: Release lock on page-out failure path KVM: arm64: Treat emulated TVAL TimerValue as a signed 32-bit integer KVM: arm64: pmu: Only handle supported event counters KVM: arm64: pmu: Fix chained SW_INCR counters KVM: arm64: pmu: Don't mark a counter as chained if the odd one is disabled KVM: arm64: pmu: Don't increment SW_INCR if PMCR.E is unset KVM: x86: Use a typedef for fastop functions KVM: X86: Add 'else' to unify fastop and execute call path KVM: x86: inline memslot_valid_for_gpte KVM: x86/mmu: Use huge pages for DAX-backed files KVM: x86/mmu: Remove lpage_is_disallowed() check from set_spte() KVM: x86/mmu: Fold max_mapping_level() into kvm_mmu_hugepage_adjust() KVM: x86/mmu: Zap any compound page when collapsing sptes KVM: x86/mmu: Remove obsolete gfn restoration in FNAME(fetch) ...
Diffstat (limited to 'arch/x86/kvm/emulate.c')
-rw-r--r--arch/x86/kvm/emulate.c133
1 files changed, 85 insertions, 48 deletions
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 952d1a4f4d7e..ddbc61984227 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -22,6 +22,7 @@
#include "kvm_cache_regs.h"
#include <asm/kvm_emulate.h>
#include <linux/stringify.h>
+#include <asm/fpu/api.h>
#include <asm/debugreg.h>
#include <asm/nospec-branch.h>
@@ -310,7 +311,9 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt)
#define ON64(x)
#endif
-static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *));
+typedef void (*fastop_t)(struct fastop *);
+
+static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
#define __FOP_FUNC(name) \
".align " __stringify(FASTOP_SIZE) " \n\t" \
@@ -1075,8 +1078,23 @@ static void fetch_register_operand(struct operand *op)
}
}
-static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg)
+static void emulator_get_fpu(void)
+{
+ fpregs_lock();
+
+ fpregs_assert_state_consistent();
+ if (test_thread_flag(TIF_NEED_FPU_LOAD))
+ switch_fpu_return();
+}
+
+static void emulator_put_fpu(void)
{
+ fpregs_unlock();
+}
+
+static void read_sse_reg(sse128_t *data, int reg)
+{
+ emulator_get_fpu();
switch (reg) {
case 0: asm("movdqa %%xmm0, %0" : "=m"(*data)); break;
case 1: asm("movdqa %%xmm1, %0" : "=m"(*data)); break;
@@ -1098,11 +1116,12 @@ static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg)
#endif
default: BUG();
}
+ emulator_put_fpu();
}
-static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data,
- int reg)
+static void write_sse_reg(sse128_t *data, int reg)
{
+ emulator_get_fpu();
switch (reg) {
case 0: asm("movdqa %0, %%xmm0" : : "m"(*data)); break;
case 1: asm("movdqa %0, %%xmm1" : : "m"(*data)); break;
@@ -1124,10 +1143,12 @@ static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data,
#endif
default: BUG();
}
+ emulator_put_fpu();
}
-static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
+static void read_mmx_reg(u64 *data, int reg)
{
+ emulator_get_fpu();
switch (reg) {
case 0: asm("movq %%mm0, %0" : "=m"(*data)); break;
case 1: asm("movq %%mm1, %0" : "=m"(*data)); break;
@@ -1139,10 +1160,12 @@ static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
case 7: asm("movq %%mm7, %0" : "=m"(*data)); break;
default: BUG();
}
+ emulator_put_fpu();
}
-static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
+static void write_mmx_reg(u64 *data, int reg)
{
+ emulator_get_fpu();
switch (reg) {
case 0: asm("movq %0, %%mm0" : : "m"(*data)); break;
case 1: asm("movq %0, %%mm1" : : "m"(*data)); break;
@@ -1154,6 +1177,7 @@ static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
case 7: asm("movq %0, %%mm7" : : "m"(*data)); break;
default: BUG();
}
+ emulator_put_fpu();
}
static int em_fninit(struct x86_emulate_ctxt *ctxt)
@@ -1161,7 +1185,9 @@ static int em_fninit(struct x86_emulate_ctxt *ctxt)
if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
return emulate_nm(ctxt);
+ emulator_get_fpu();
asm volatile("fninit");
+ emulator_put_fpu();
return X86EMUL_CONTINUE;
}
@@ -1172,7 +1198,9 @@ static int em_fnstcw(struct x86_emulate_ctxt *ctxt)
if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
return emulate_nm(ctxt);
+ emulator_get_fpu();
asm volatile("fnstcw %0": "+m"(fcw));
+ emulator_put_fpu();
ctxt->dst.val = fcw;
@@ -1186,7 +1214,9 @@ static int em_fnstsw(struct x86_emulate_ctxt *ctxt)
if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
return emulate_nm(ctxt);
+ emulator_get_fpu();
asm volatile("fnstsw %0": "+m"(fsw));
+ emulator_put_fpu();
ctxt->dst.val = fsw;
@@ -1205,7 +1235,7 @@ static void decode_register_operand(struct x86_emulate_ctxt *ctxt,
op->type = OP_XMM;
op->bytes = 16;
op->addr.xmm = reg;
- read_sse_reg(ctxt, &op->vec_val, reg);
+ read_sse_reg(&op->vec_val, reg);
return;
}
if (ctxt->d & Mmx) {
@@ -1256,7 +1286,7 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt,
op->type = OP_XMM;
op->bytes = 16;
op->addr.xmm = ctxt->modrm_rm;
- read_sse_reg(ctxt, &op->vec_val, ctxt->modrm_rm);
+ read_sse_reg(&op->vec_val, ctxt->modrm_rm);
return rc;
}
if (ctxt->d & Mmx) {
@@ -1833,10 +1863,10 @@ static int writeback(struct x86_emulate_ctxt *ctxt, struct operand *op)
op->bytes * op->count);
break;
case OP_XMM:
- write_sse_reg(ctxt, &op->vec_val, op->addr.xmm);
+ write_sse_reg(&op->vec_val, op->addr.xmm);
break;
case OP_MM:
- write_mmx_reg(ctxt, &op->mm_val, op->addr.mm);
+ write_mmx_reg(&op->mm_val, op->addr.mm);
break;
case OP_NONE:
/* no writeback */
@@ -2348,12 +2378,7 @@ static int em_lseg(struct x86_emulate_ctxt *ctxt)
static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt)
{
#ifdef CONFIG_X86_64
- u32 eax, ebx, ecx, edx;
-
- eax = 0x80000001;
- ecx = 0;
- ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false);
- return edx & bit(X86_FEATURE_LM);
+ return ctxt->ops->guest_has_long_mode(ctxt);
#else
return false;
#endif
@@ -3618,18 +3643,11 @@ static int em_mov(struct x86_emulate_ctxt *ctxt)
return X86EMUL_CONTINUE;
}
-#define FFL(x) bit(X86_FEATURE_##x)
-
static int em_movbe(struct x86_emulate_ctxt *ctxt)
{
- u32 ebx, ecx, edx, eax = 1;
u16 tmp;
- /*
- * Check MOVBE is set in the guest-visible CPUID leaf.
- */
- ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false);
- if (!(ecx & FFL(MOVBE)))
+ if (!ctxt->ops->guest_has_movbe(ctxt))
return emulate_ud(ctxt);
switch (ctxt->op_bytes) {
@@ -4027,10 +4045,7 @@ static int em_movsxd(struct x86_emulate_ctxt *ctxt)
static int check_fxsr(struct x86_emulate_ctxt *ctxt)
{
- u32 eax = 1, ebx, ecx = 0, edx;
-
- ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false);
- if (!(edx & FFL(FXSR)))
+ if (!ctxt->ops->guest_has_fxsr(ctxt))
return emulate_ud(ctxt);
if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
@@ -4092,8 +4107,12 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt)
if (rc != X86EMUL_CONTINUE)
return rc;
+ emulator_get_fpu();
+
rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state));
+ emulator_put_fpu();
+
if (rc != X86EMUL_CONTINUE)
return rc;
@@ -4136,6 +4155,8 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
if (rc != X86EMUL_CONTINUE)
return rc;
+ emulator_get_fpu();
+
if (size < __fxstate_size(16)) {
rc = fxregs_fixup(&fx_state, size);
if (rc != X86EMUL_CONTINUE)
@@ -4151,6 +4172,8 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state));
out:
+ emulator_put_fpu();
+
return rc;
}
@@ -5210,16 +5233,28 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
ctxt->ad_bytes = def_ad_bytes ^ 6;
break;
case 0x26: /* ES override */
+ has_seg_override = true;
+ ctxt->seg_override = VCPU_SREG_ES;
+ break;
case 0x2e: /* CS override */
+ has_seg_override = true;
+ ctxt->seg_override = VCPU_SREG_CS;
+ break;
case 0x36: /* SS override */
+ has_seg_override = true;
+ ctxt->seg_override = VCPU_SREG_SS;
+ break;
case 0x3e: /* DS override */
has_seg_override = true;
- ctxt->seg_override = (ctxt->b >> 3) & 3;
+ ctxt->seg_override = VCPU_SREG_DS;
break;
case 0x64: /* FS override */
+ has_seg_override = true;
+ ctxt->seg_override = VCPU_SREG_FS;
+ break;
case 0x65: /* GS override */
has_seg_override = true;
- ctxt->seg_override = ctxt->b & 7;
+ ctxt->seg_override = VCPU_SREG_GS;
break;
case 0x40 ... 0x4f: /* REX */
if (mode != X86EMUL_MODE_PROT64)
@@ -5303,10 +5338,15 @@ done_prefixes:
}
break;
case Escape:
- if (ctxt->modrm > 0xbf)
- opcode = opcode.u.esc->high[ctxt->modrm - 0xc0];
- else
+ if (ctxt->modrm > 0xbf) {
+ size_t size = ARRAY_SIZE(opcode.u.esc->high);
+ u32 index = array_index_nospec(
+ ctxt->modrm - 0xc0, size);
+
+ opcode = opcode.u.esc->high[index];
+ } else {
opcode = opcode.u.esc->op[(ctxt->modrm >> 3) & 7];
+ }
break;
case InstrDual:
if ((ctxt->modrm >> 6) == 3)
@@ -5448,7 +5488,9 @@ static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt)
{
int rc;
+ emulator_get_fpu();
rc = asm_safe("fwait");
+ emulator_put_fpu();
if (unlikely(rc != X86EMUL_CONTINUE))
return emulate_exception(ctxt, MF_VECTOR, 0, false);
@@ -5456,14 +5498,13 @@ static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt)
return X86EMUL_CONTINUE;
}
-static void fetch_possible_mmx_operand(struct x86_emulate_ctxt *ctxt,
- struct operand *op)
+static void fetch_possible_mmx_operand(struct operand *op)
{
if (op->type == OP_MM)
- read_mmx_reg(ctxt, &op->mm_val, op->addr.mm);
+ read_mmx_reg(&op->mm_val, op->addr.mm);
}
-static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *))
+static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop)
{
ulong flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF;
@@ -5539,10 +5580,10 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
* Now that we know the fpu is exception safe, we can fetch
* operands from it.
*/
- fetch_possible_mmx_operand(ctxt, &ctxt->src);
- fetch_possible_mmx_operand(ctxt, &ctxt->src2);
+ fetch_possible_mmx_operand(&ctxt->src);
+ fetch_possible_mmx_operand(&ctxt->src2);
if (!(ctxt->d & Mov))
- fetch_possible_mmx_operand(ctxt, &ctxt->dst);
+ fetch_possible_mmx_operand(&ctxt->dst);
}
if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && ctxt->intercept) {
@@ -5641,14 +5682,10 @@ special_insn:
ctxt->eflags &= ~X86_EFLAGS_RF;
if (ctxt->execute) {
- if (ctxt->d & Fastop) {
- void (*fop)(struct fastop *) = (void *)ctxt->execute;
- rc = fastop(ctxt, fop);
- if (rc != X86EMUL_CONTINUE)
- goto done;
- goto writeback;
- }
- rc = ctxt->execute(ctxt);
+ if (ctxt->d & Fastop)
+ rc = fastop(ctxt, (fastop_t)ctxt->execute);
+ else
+ rc = ctxt->execute(ctxt);
if (rc != X86EMUL_CONTINUE)
goto done;
goto writeback;