Home Home > GIT Browse
summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorTakashi Iwai <tiwai@suse.de>2018-06-14 07:39:52 +0200
committerTakashi Iwai <tiwai@suse.de>2018-06-14 07:39:52 +0200
commita070d005a5eb6470be616dc5f1711839e253ff9c (patch)
tree0a5452ec1a25b39f3124a7a4adbfbb10a6e11034
parent7155d9ceb3b1466ecc214da96faf63d9c22f89ae (diff)
parent8169cae859748e22e0bde87f770c9c82b6e7a932 (diff)
Merge branch 'SLE12-SP3' into openSUSE-42.3rpm-4.4.136-56
-rw-r--r--arch/x86/include/asm/fpu/internal.h4
-rw-r--r--arch/x86/kernel/fpu/core.c56
-rw-r--r--arch/x86/kernel/fpu/init.c172
-rw-r--r--arch/x86/kernel/fpu/xstate.c4
-rw-r--r--arch/x86/kernel/traps.c3
-rw-r--r--arch/x86/kvm/cpuid.c4
-rw-r--r--arch/x86/kvm/svm.c43
-rw-r--r--arch/x86/kvm/vmx.c112
-rw-r--r--arch/x86/kvm/x86.c17
9 files changed, 140 insertions, 275 deletions
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index d132f326d62e..11432cf4b01c 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -44,6 +44,7 @@ extern void fpu__init_cpu_xstate(void);
extern void fpu__init_system(struct cpuinfo_x86 *c);
extern void fpu__init_check_bugs(void);
extern void fpu__resume_cpu(void);
+extern u64 fpu__get_supported_xfeatures_mask(void);
/*
* Debugging facility:
@@ -597,7 +598,8 @@ switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu)
* If the task has used the math, pre-load the FPU on xsave processors
* or if the past 5 consecutive context-switches used math.
*/
- fpu.preload = new_fpu->fpstate_active &&
+ fpu.preload = static_cpu_has(X86_FEATURE_FPU) &&
+ new_fpu->fpstate_active &&
(use_eager_fpu() || new_fpu->counter > 5);
if (old_fpu->fpregs_active) {
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 9a16eb6e7c3b..6fdb248dac90 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -115,6 +115,10 @@ void __kernel_fpu_begin(void)
kernel_fpu_disable();
if (fpu->fpregs_active) {
+ /*
+ * Ignore return value -- we don't care if reg state
+ * is clobbered.
+ */
copy_fpregs_to_fpstate(fpu);
} else {
this_cpu_write(fpu_fpregs_owner_ctx, NULL);
@@ -190,8 +194,12 @@ void fpu__save(struct fpu *fpu)
preempt_disable();
if (fpu->fpregs_active) {
- if (!copy_fpregs_to_fpstate(fpu))
- fpregs_deactivate(fpu);
+ if (!copy_fpregs_to_fpstate(fpu)) {
+ if (use_eager_fpu())
+ copy_kernel_to_fpregs(&fpu->state);
+ else
+ fpregs_deactivate(fpu);
+ }
}
preempt_enable();
}
@@ -224,14 +232,15 @@ void fpstate_init(union fpregs_state *state)
}
EXPORT_SYMBOL_GPL(fpstate_init);
-/*
- * Copy the current task's FPU state to a new task's FPU context.
- *
- * In both the 'eager' and the 'lazy' case we save hardware registers
- * directly to the destination buffer.
- */
-static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu)
+int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
{
+ dst_fpu->counter = 0;
+ dst_fpu->fpregs_active = 0;
+ dst_fpu->last_cpu = -1;
+
+ if (!src_fpu->fpstate_active || !cpu_has_fpu)
+ return 0;
+
WARN_ON_FPU(src_fpu != &current->thread.fpu);
/*
@@ -244,10 +253,9 @@ static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu)
/*
* Save current FPU registers directly into the child
* FPU context, without any memory-to-memory copying.
- *
- * If the FPU context got destroyed in the process (FNSAVE
- * done on old CPUs) then copy it back into the source
- * context and mark the current task for lazy restore.
+ * In lazy mode, if the FPU context isn't loaded into
+ * fpregs, CR0.TS will be set and do_device_not_available
+ * will load the FPU context.
*
* We have to do all this with preemption disabled,
* mostly because of the FNSAVE case, because in that
@@ -260,19 +268,13 @@ static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu)
preempt_disable();
if (!copy_fpregs_to_fpstate(dst_fpu)) {
memcpy(&src_fpu->state, &dst_fpu->state, xstate_size);
- fpregs_deactivate(src_fpu);
+
+ if (use_eager_fpu())
+ copy_kernel_to_fpregs(&src_fpu->state);
+ else
+ fpregs_deactivate(src_fpu);
}
preempt_enable();
-}
-
-int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
-{
- dst_fpu->counter = 0;
- dst_fpu->fpregs_active = 0;
- dst_fpu->last_cpu = -1;
-
- if (src_fpu->fpstate_active && cpu_has_fpu)
- fpu_copy(dst_fpu, src_fpu);
return 0;
}
@@ -473,8 +475,10 @@ static inline void copy_init_fpstate_to_fpregs(void)
{
if (use_xsave())
copy_kernel_to_xregs(&init_fpstate.xsave, -1);
- else
+ else if (static_cpu_has(X86_FEATURE_FXSR))
copy_kernel_to_fxregs(&init_fpstate.fxsave);
+ else
+ copy_kernel_to_fregs(&init_fpstate.fsave);
if (boot_cpu_has(X86_FEATURE_OSPKE))
copy_init_pkru_to_fpregs();
@@ -490,7 +494,7 @@ void fpu__clear(struct fpu *fpu)
{
WARN_ON_FPU(fpu != &current->thread.fpu); /* Almost certainly an anomaly */
- if (!use_eager_fpu()) {
+ if (!use_eager_fpu() || !static_cpu_has(X86_FEATURE_FPU)) {
/* FPU state will be reallocated lazily at the first use. */
fpu__drop(fpu);
} else {
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index dcfbb821e066..a5c0eeb880dd 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -3,8 +3,11 @@
*/
#include <asm/fpu/internal.h>
#include <asm/tlbflush.h>
+#include <asm/setup.h>
+#include <asm/cmdline.h>
#include <linux/sched.h>
+#include <linux/init.h>
/*
* Initialize the TS bit in CR0 according to the style of context-switches
@@ -75,13 +78,15 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
cr0 &= ~(X86_CR0_TS | X86_CR0_EM);
write_cr0(cr0);
- asm volatile("fninit ; fnstsw %0 ; fnstcw %1"
- : "+m" (fsw), "+m" (fcw));
+ if (!test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) {
+ asm volatile("fninit ; fnstsw %0 ; fnstcw %1"
+ : "+m" (fsw), "+m" (fcw));
- if (fsw == 0 && (fcw & 0x103f) == 0x003f)
- set_cpu_cap(c, X86_FEATURE_FPU);
- else
- clear_cpu_cap(c, X86_FEATURE_FPU);
+ if (fsw == 0 && (fcw & 0x103f) == 0x003f)
+ set_cpu_cap(c, X86_FEATURE_FPU);
+ else
+ clear_cpu_cap(c, X86_FEATURE_FPU);
+ }
#ifndef CONFIG_MATH_EMULATION
if (!cpu_has_fpu) {
@@ -130,7 +135,7 @@ static void __init fpu__init_system_generic(void)
* Set up the legacy init FPU context. (xstate init might overwrite this
* with a more modern format, if the CPU supports it.)
*/
- fpstate_init_fxstate(&init_fpstate.fxsave);
+ fpstate_init(&init_fpstate);
fpu__init_system_mxcsr();
}
@@ -258,7 +263,10 @@ static void __init fpu__init_system_xstate_size_legacy(void)
* not only saved the restores along the way, but we also have the
* FPU ready to be used for the original task.
*
- * 'eager' switching is used on modern CPUs, there we switch the FPU
+ * 'lazy' is deprecated because it's almost never a performance win
+ * and it's much more complicated than 'eager'.
+ *
+ * 'eager' switching is by default on all CPUs, there we switch the FPU
* state during every context switch, regardless of whether the task
* has used FPU instructions in that time slice or not. This is done
* because modern FPU context saving instructions are able to optimize
@@ -269,22 +277,48 @@ static void __init fpu__init_system_xstate_size_legacy(void)
* to use 'eager' restores, if we detect that a task is using the FPU
* frequently. See the fpu->counter logic in fpu/internal.h for that. ]
*/
-static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO;
+static enum { ENABLE, DISABLE } eagerfpu = ENABLE;
-static int __init eager_fpu_setup(char *s)
+/*
+ * Find supported xfeatures based on cpu features and command-line input.
+ * This must be called after fpu__init_parse_early_param() is called and
+ * xfeatures_mask is enumerated.
+ */
+u64 __init fpu__get_supported_xfeatures_mask(void)
{
- if (!strcmp(s, "on"))
- eagerfpu = ENABLE;
- else if (!strcmp(s, "off"))
- eagerfpu = DISABLE;
- else if (!strcmp(s, "auto"))
- eagerfpu = AUTO;
- return 1;
+ /* Support all xfeatures known to us */
+ if (eagerfpu != DISABLE)
+ return XCNTXT_MASK;
+
+ /* Warning of xfeatures being disabled for no eagerfpu mode */
+ if (xfeatures_mask & XFEATURE_MASK_EAGER) {
+ pr_err("x86/fpu: eagerfpu switching disabled, disabling the following xstate features: 0x%llx.\n",
+ xfeatures_mask & XFEATURE_MASK_EAGER);
+ }
+
+ /* Return a mask that masks out all features requiring eagerfpu mode */
+ return ~XFEATURE_MASK_EAGER;
+}
+
+/*
+ * Disable features dependent on eagerfpu.
+ */
+static void __init fpu__clear_eager_fpu_features(void)
+{
+ setup_clear_cpu_cap(X86_FEATURE_MPX);
}
-__setup("eagerfpu=", eager_fpu_setup);
/*
* Pick the FPU context switching strategy:
+ *
+ * When eagerfpu is AUTO or ENABLE, we ensure it is ENABLE if either of
+ * the following is true:
+ *
+ * (1) the cpu has xsaveopt, as it has the optimization and doing eager
+ * FPU switching has a relatively low cost compared to a plain xsave;
+ * (2) the cpu has xsave features (e.g. MPX) that depend on eager FPU
+ * switching. Should the kernel boot with noxsaveopt, we support MPX
+ * with eager FPU switching at a higher cost.
*/
static void __init fpu__init_system_ctx_switch(void)
{
@@ -296,19 +330,11 @@ static void __init fpu__init_system_ctx_switch(void)
WARN_ON_FPU(current->thread.fpu.fpstate_active);
current_thread_info()->status = 0;
- /* Auto enable eagerfpu for xsaveopt */
if (cpu_has_xsaveopt && eagerfpu != DISABLE)
eagerfpu = ENABLE;
- if (xfeatures_mask & XFEATURE_MASK_EAGER) {
- if (eagerfpu == DISABLE) {
- pr_err("x86/fpu: eagerfpu switching disabled, disabling the following xstate features: 0x%llx.\n",
- xfeatures_mask & XFEATURE_MASK_EAGER);
- xfeatures_mask &= ~XFEATURE_MASK_EAGER;
- } else {
- eagerfpu = ENABLE;
- }
- }
+ if (xfeatures_mask & XFEATURE_MASK_EAGER)
+ eagerfpu = ENABLE;
if (eagerfpu == ENABLE)
setup_force_cpu_cap(X86_FEATURE_EAGER_FPU);
@@ -317,11 +343,42 @@ static void __init fpu__init_system_ctx_switch(void)
}
/*
+ * We parse fpu parameters early because fpu__init_system() is executed
+ * before parse_early_param().
+ */
+static void __init fpu__init_parse_early_param(void)
+{
+ if (cmdline_find_option_bool(boot_command_line, "eagerfpu=off")) {
+ eagerfpu = DISABLE;
+ fpu__clear_eager_fpu_features();
+ }
+
+ if (cmdline_find_option_bool(boot_command_line, "no387"))
+ setup_clear_cpu_cap(X86_FEATURE_FPU);
+
+ if (cmdline_find_option_bool(boot_command_line, "nofxsr")) {
+ setup_clear_cpu_cap(X86_FEATURE_FXSR);
+ setup_clear_cpu_cap(X86_FEATURE_FXSR_OPT);
+ setup_clear_cpu_cap(X86_FEATURE_XMM);
+ }
+
+ if (cmdline_find_option_bool(boot_command_line, "noxsave"))
+ fpu__xstate_clear_all_cpu_caps();
+
+ if (cmdline_find_option_bool(boot_command_line, "noxsaveopt"))
+ setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+
+ if (cmdline_find_option_bool(boot_command_line, "noxsaves"))
+ setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+}
+
+/*
* Called on the boot CPU once per system bootup, to set up the initial
* FPU state that is later cloned into all processes:
*/
void __init fpu__init_system(struct cpuinfo_x86 *c)
{
+ fpu__init_parse_early_param();
fpu__init_system_early_generic(c);
/*
@@ -345,62 +402,3 @@ void __init fpu__init_system(struct cpuinfo_x86 *c)
fpu__init_system_ctx_switch();
}
-
-/*
- * Boot parameter to turn off FPU support and fall back to math-emu:
- */
-static int __init no_387(char *s)
-{
- setup_clear_cpu_cap(X86_FEATURE_FPU);
- return 1;
-}
-__setup("no387", no_387);
-
-/*
- * Disable all xstate CPU features:
- */
-static int __init x86_noxsave_setup(char *s)
-{
- if (strlen(s))
- return 0;
-
- fpu__xstate_clear_all_cpu_caps();
-
- return 1;
-}
-__setup("noxsave", x86_noxsave_setup);
-
-/*
- * Disable the XSAVEOPT instruction specifically:
- */
-static int __init x86_noxsaveopt_setup(char *s)
-{
- setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
-
- return 1;
-}
-__setup("noxsaveopt", x86_noxsaveopt_setup);
-
-/*
- * Disable the XSAVES instruction:
- */
-static int __init x86_noxsaves_setup(char *s)
-{
- setup_clear_cpu_cap(X86_FEATURE_XSAVES);
-
- return 1;
-}
-__setup("noxsaves", x86_noxsaves_setup);
-
-/*
- * Disable FX save/restore and SSE support:
- */
-static int __init x86_nofxsr_setup(char *s)
-{
- setup_clear_cpu_cap(X86_FEATURE_FXSR);
- setup_clear_cpu_cap(X86_FEATURE_FXSR_OPT);
- setup_clear_cpu_cap(X86_FEATURE_XMM);
-
- return 1;
-}
-__setup("nofxsr", x86_nofxsr_setup);
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index ba5b5cb88346..35e4fba5b44d 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -59,6 +59,7 @@ void fpu__xstate_clear_all_cpu_caps(void)
setup_clear_cpu_cap(X86_FEATURE_AVX512BW);
setup_clear_cpu_cap(X86_FEATURE_AVX512VL);
setup_clear_cpu_cap(X86_FEATURE_MPX);
+ setup_clear_cpu_cap(X86_FEATURE_XGETBV1);
setup_clear_cpu_cap(X86_FEATURE_AVX512_4VNNIW);
setup_clear_cpu_cap(X86_FEATURE_AVX512_4FMAPS);
setup_clear_cpu_cap(X86_FEATURE_PKU);
@@ -645,8 +646,7 @@ void __init fpu__init_system_xstate(void)
BUG();
}
- /* Support only the state known to the OS: */
- xfeatures_mask = xfeatures_mask & XCNTXT_MASK;
+ xfeatures_mask &= fpu__get_supported_xfeatures_mask();
/* Enable xstate instructions to be able to continue with initialization: */
fpu__init_cpu_xstate();
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 42dc9503540e..bc3c41e5cb90 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -752,10 +752,9 @@ dotraplinkage void
do_device_not_available(struct pt_regs *regs, long error_code)
{
RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
- BUG_ON(use_eager_fpu());
#ifdef CONFIG_MATH_EMULATION
- if (read_cr0() & X86_CR0_EM) {
+ if (!boot_cpu_has(X86_FEATURE_FPU) && (read_cr0() & X86_CR0_EM)) {
struct math_emu_info info = { };
conditional_sti(regs);
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 7ac1d719e180..6d9bf529863e 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -122,10 +122,6 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
if (best && (best->eax & (F(XSAVES) | F(XSAVEC))))
best->ebx = xstate_required_size(vcpu->arch.xcr0, true);
- vcpu->arch.eager_fpu = use_eager_fpu();
- if (vcpu->arch.eager_fpu)
- kvm_x86_ops->fpu_activate(vcpu);
-
/*
* The existing code assumes virtual address is 48-bit in the canonical
* address checks; exit if it is ever changed.
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 3e2191ed13d4..381a63e68f1d 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1192,7 +1192,6 @@ static void init_vmcb(struct vcpu_svm *svm)
struct vmcb_control_area *control = &svm->vmcb->control;
struct vmcb_save_area *save = &svm->vmcb->save;
- svm->vcpu.fpu_active = 1;
svm->vcpu.arch.hflags = 0;
set_cr_intercept(svm, INTERCEPT_CR0_READ);
@@ -1951,15 +1950,12 @@ static void update_cr0_intercept(struct vcpu_svm *svm)
ulong gcr0 = svm->vcpu.arch.cr0;
u64 *hcr0 = &svm->vmcb->save.cr0;
- if (!svm->vcpu.fpu_active)
- *hcr0 |= SVM_CR0_SELECTIVE_MASK;
- else
- *hcr0 = (*hcr0 & ~SVM_CR0_SELECTIVE_MASK)
- | (gcr0 & SVM_CR0_SELECTIVE_MASK);
+ *hcr0 = (*hcr0 & ~SVM_CR0_SELECTIVE_MASK)
+ | (gcr0 & SVM_CR0_SELECTIVE_MASK);
mark_dirty(svm->vmcb, VMCB_CR);
- if (gcr0 == *hcr0 && svm->vcpu.fpu_active) {
+ if (gcr0 == *hcr0) {
clr_cr_intercept(svm, INTERCEPT_CR0_READ);
clr_cr_intercept(svm, INTERCEPT_CR0_WRITE);
} else {
@@ -1990,8 +1986,6 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
if (!npt_enabled)
cr0 |= X86_CR0_PG | X86_CR0_WP;
- if (!vcpu->fpu_active)
- cr0 |= X86_CR0_TS;
/*
* re-enable caching here because the QEMU bios
* does not do it - this results in some delay at
@@ -2209,22 +2203,6 @@ static int ac_interception(struct vcpu_svm *svm)
return 1;
}
-static void svm_fpu_activate(struct kvm_vcpu *vcpu)
-{
- struct vcpu_svm *svm = to_svm(vcpu);
-
- clr_exception_intercept(svm, NM_VECTOR);
-
- svm->vcpu.fpu_active = 1;
- update_cr0_intercept(svm);
-}
-
-static int nm_interception(struct vcpu_svm *svm)
-{
- svm_fpu_activate(&svm->vcpu);
- return 1;
-}
-
static bool is_erratum_383(void)
{
int err, i;
@@ -2622,9 +2600,6 @@ static int nested_svm_exit_special(struct vcpu_svm *svm)
if (!npt_enabled && svm->apf_reason == 0)
return NESTED_EXIT_HOST;
break;
- case SVM_EXIT_EXCP_BASE + NM_VECTOR:
- nm_interception(svm);
- break;
default:
break;
}
@@ -4104,7 +4079,6 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = {
[SVM_EXIT_EXCP_BASE + BP_VECTOR] = bp_interception,
[SVM_EXIT_EXCP_BASE + UD_VECTOR] = ud_interception,
[SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception,
- [SVM_EXIT_EXCP_BASE + NM_VECTOR] = nm_interception,
[SVM_EXIT_EXCP_BASE + MC_VECTOR] = mc_interception,
[SVM_EXIT_EXCP_BASE + AC_VECTOR] = ac_interception,
[SVM_EXIT_INTR] = intr_interception,
@@ -5190,14 +5164,6 @@ static bool svm_has_wbinvd_exit(void)
return true;
}
-static void svm_fpu_deactivate(struct kvm_vcpu *vcpu)
-{
- struct vcpu_svm *svm = to_svm(vcpu);
-
- set_exception_intercept(svm, NM_VECTOR);
- update_cr0_intercept(svm);
-}
-
#define PRE_EX(exit) { .exit_code = (exit), \
.stage = X86_ICPT_PRE_EXCEPT, }
#define POST_EX(exit) { .exit_code = (exit), \
@@ -5454,9 +5420,6 @@ static struct kvm_x86_ops svm_x86_ops = {
.get_pkru = svm_get_pkru,
.set_pkru = svm_set_pkru,
- .fpu_activate = svm_fpu_activate,
- .fpu_deactivate = svm_fpu_deactivate,
-
.tlb_flush = svm_flush_tlb,
.run = svm_vcpu_run,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 28d8b3976943..55e7e52aaf17 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1679,7 +1679,7 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu)
u32 eb;
eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) |
- (1u << NM_VECTOR) | (1u << DB_VECTOR) | (1u << AC_VECTOR);
+ (1u << DB_VECTOR) | (1u << AC_VECTOR);
if ((vcpu->guest_debug &
(KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) ==
(KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP))
@@ -1688,8 +1688,6 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu)
eb = ~0;
if (enable_ept)
eb &= ~(1u << PF_VECTOR); /* bypass_guest_pf = 0 */
- if (vcpu->fpu_active)
- eb &= ~(1u << NM_VECTOR);
/* When we are running a nested L2 guest and L1 specified for it a
* certain exception bitmap, we must trap the same exceptions and pass
@@ -2167,25 +2165,6 @@ static void vmx_vcpu_put(struct kvm_vcpu *vcpu)
}
}
-static void vmx_fpu_activate(struct kvm_vcpu *vcpu)
-{
- ulong cr0;
-
- if (vcpu->fpu_active)
- return;
- vcpu->fpu_active = 1;
- cr0 = vmcs_readl(GUEST_CR0);
- cr0 &= ~(X86_CR0_TS | X86_CR0_MP);
- cr0 |= kvm_read_cr0_bits(vcpu, X86_CR0_TS | X86_CR0_MP);
- vmcs_writel(GUEST_CR0, cr0);
- update_exception_bitmap(vcpu);
- vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS;
- if (is_guest_mode(vcpu))
- vcpu->arch.cr0_guest_owned_bits &=
- ~get_vmcs12(vcpu)->cr0_guest_host_mask;
- vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits);
-}
-
static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu);
/*
@@ -2204,33 +2183,6 @@ static inline unsigned long nested_read_cr4(struct vmcs12 *fields)
(fields->cr4_read_shadow & fields->cr4_guest_host_mask);
}
-static void vmx_fpu_deactivate(struct kvm_vcpu *vcpu)
-{
- /* Note that there is no vcpu->fpu_active = 0 here. The caller must
- * set this *before* calling this function.
- */
- vmx_decache_cr0_guest_bits(vcpu);
- vmcs_set_bits(GUEST_CR0, X86_CR0_TS | X86_CR0_MP);
- update_exception_bitmap(vcpu);
- vcpu->arch.cr0_guest_owned_bits = 0;
- vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits);
- if (is_guest_mode(vcpu)) {
- /*
- * L1's specified read shadow might not contain the TS bit,
- * so now that we turned on shadowing of this bit, we need to
- * set this bit of the shadow. Like in nested_vmx_run we need
- * nested_read_cr0(vmcs12), but vmcs12->guest_cr0 is not yet
- * up-to-date here because we just decached cr0.TS (and we'll
- * only update vmcs12->guest_cr0 on nested exit).
- */
- struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
- vmcs12->guest_cr0 = (vmcs12->guest_cr0 & ~X86_CR0_TS) |
- (vcpu->arch.cr0 & X86_CR0_TS);
- vmcs_writel(CR0_READ_SHADOW, nested_read_cr0(vmcs12));
- } else
- vmcs_writel(CR0_READ_SHADOW, vcpu->arch.cr0);
-}
-
static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu)
{
unsigned long rflags, save_rflags;
@@ -3829,9 +3781,6 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
if (enable_ept)
ept_update_paging_mode_cr0(&hw_cr0, cr0, vcpu);
- if (!vcpu->fpu_active)
- hw_cr0 |= X86_CR0_TS | X86_CR0_MP;
-
vmcs_writel(CR0_READ_SHADOW, cr0);
vmcs_writel(GUEST_CR0, hw_cr0);
vcpu->arch.cr0 = cr0;
@@ -4971,7 +4920,9 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
/* 22.2.1, 20.8.1 */
vm_entry_controls_init(vmx, vmcs_config.vmentry_ctrl);
- vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL);
+ vmx->vcpu.arch.cr0_guest_owned_bits = X86_CR0_TS;
+ vmcs_writel(CR0_GUEST_HOST_MASK, ~X86_CR0_TS);
+
set_cr4_guest_host_mask(vmx);
if (vmx_xsaves_supported())
@@ -5075,7 +5026,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
vmx_set_cr0(vcpu, cr0); /* enter rmode */
vmx_set_cr4(vcpu, 0);
vmx_set_efer(vcpu, 0);
- vmx_fpu_activate(vcpu);
+
update_exception_bitmap(vcpu);
vpid_sync_context(vmx->vpid);
@@ -5353,11 +5304,6 @@ static int handle_exception(struct kvm_vcpu *vcpu)
if (is_nmi(intr_info))
return 1; /* already handled by vmx_vcpu_run() */
- if (is_no_device(intr_info)) {
- vmx_fpu_activate(vcpu);
- return 1;
- }
-
if (is_invalid_opcode(intr_info)) {
if (is_guest_mode(vcpu)) {
kvm_queue_exception(vcpu, UD_VECTOR);
@@ -5555,22 +5501,6 @@ static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val)
return kvm_set_cr4(vcpu, val);
}
-/* called to set cr0 as approriate for clts instruction exit. */
-static void handle_clts(struct kvm_vcpu *vcpu)
-{
- if (is_guest_mode(vcpu)) {
- /*
- * We get here when L2 did CLTS, and L1 didn't shadow CR0.TS
- * but we did (!fpu_active). We need to keep GUEST_CR0.TS on,
- * just pretend it's off (also in arch.cr0 for fpu_activate).
- */
- vmcs_writel(CR0_READ_SHADOW,
- vmcs_readl(CR0_READ_SHADOW) & ~X86_CR0_TS);
- vcpu->arch.cr0 &= ~X86_CR0_TS;
- } else
- vmx_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS));
-}
-
static int handle_cr(struct kvm_vcpu *vcpu)
{
unsigned long exit_qualification, val;
@@ -5613,10 +5543,10 @@ static int handle_cr(struct kvm_vcpu *vcpu)
}
break;
case 2: /* clts */
- handle_clts(vcpu);
+ WARN_ONCE(1, "Guest should always own CR0.TS");
+ vmx_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS));
trace_kvm_cr_write(0, kvm_read_cr0(vcpu));
skip_emulated_instruction(vcpu);
- vmx_fpu_activate(vcpu);
return 1;
case 1: /*mov from cr*/
switch (cr) {
@@ -9935,8 +9865,8 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
vmx_set_efer(vcpu, vcpu->arch.efer);
/*
- * This sets GUEST_CR0 to vmcs12->guest_cr0, with possibly a modified
- * TS bit (for lazy fpu) and bits which we consider mandatory enabled.
+ * This sets GUEST_CR0 to vmcs12->guest_cr0, possibly modifying those
+ * bits which we consider mandatory enabled.
* The CR0_READ_SHADOW is what L2 should have expected to read given
* the specifications by L1; It's not enough to take
* vmcs12->cr0_read_shadow because on our cr0_guest_host_mask we we
@@ -10482,24 +10412,15 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
vmx_set_rflags(vcpu, X86_EFLAGS_FIXED);
/*
* Note that calling vmx_set_cr0 is important, even if cr0 hasn't
- * actually changed, because it depends on the current state of
- * fpu_active (which may have changed).
- * Note that vmx_set_cr0 refers to efer set above.
+ * actually changed, because vmx_set_cr0 refers to efer set above.
+ *
+ * CR0_GUEST_HOST_MASK is already set in the original vmcs01
+ * (KVM doesn't change it);
*/
+ vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS;
vmx_set_cr0(vcpu, vmcs12->host_cr0);
- /*
- * If we did fpu_activate()/fpu_deactivate() during L2's run, we need
- * to apply the same changes to L1's vmcs. We just set cr0 correctly,
- * but we also need to update cr0_guest_host_mask and exception_bitmap.
- */
- update_exception_bitmap(vcpu);
- vcpu->arch.cr0_guest_owned_bits = (vcpu->fpu_active ? X86_CR0_TS : 0);
- vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits);
- /*
- * Note that CR4_GUEST_HOST_MASK is already set in the original vmcs01
- * (KVM doesn't change it)- no reason to call set_cr4_guest_host_mask();
- */
+ /* Same as above - no reason to call set_cr4_guest_host_mask(). */
vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
vmx_set_cr4(vcpu, vmcs12->host_cr4);
@@ -11028,9 +10949,6 @@ static struct kvm_x86_ops vmx_x86_ops = {
.get_pkru = vmx_get_pkru,
.set_pkru = vmx_set_pkru,
- .fpu_activate = vmx_fpu_activate,
- .fpu_deactivate = vmx_fpu_deactivate,
-
.tlb_flush = vmx_flush_tlb,
.run = vmx_vcpu_run,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d5917313461c..77b05c1b23b8 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6531,10 +6531,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
r = 0;
goto out;
}
- if (kvm_check_request(KVM_REQ_DEACTIVATE_FPU, vcpu)) {
- vcpu->fpu_active = 0;
- kvm_x86_ops->fpu_deactivate(vcpu);
- }
if (kvm_check_request(KVM_REQ_APF_HALT, vcpu)) {
/* Page is swapped out. Do synthetic halt */
vcpu->arch.apf.halted = true;
@@ -6635,8 +6631,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
preempt_disable();
kvm_x86_ops->prepare_guest_switch(vcpu);
- if (vcpu->fpu_active)
- kvm_load_guest_fpu(vcpu);
+ kvm_load_guest_fpu(vcpu);
vcpu->mode = IN_GUEST_MODE;
srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
@@ -7386,16 +7381,6 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu);
__kernel_fpu_end();
++vcpu->stat.fpu_reload;
- /*
- * If using eager FPU mode, or if the guest is a frequent user
- * of the FPU, just leave the FPU active for next time.
- * Every 255 times fpu_counter rolls over to 0; a guest that uses
- * the FPU in bursts will revert to loading it on demand.
- */
- if (!vcpu->arch.eager_fpu) {
- if (++vcpu->fpu_counter < 5)
- kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
- }
trace_kvm_fpu(0);
}