x86/svm: Drop support for AMD's Lightweight Profiling

Lightweight Profiling was introduced in Bulldozer (Fam15h), but was dropped
from Zen (Fam17h) processors.  Furthermore, LWP was dropped from Fam15/16 CPUs
when IBPB for Spectre v2 was introduced in microcode, owing to LWP not being
used in practice.

As a result, CPUs which are operating within specification (i.e. with up to
date microcode) no longer have this feature, and therefore are not using it.

Drop support from Xen.  The main motivation here is to remove unnecessary
complexity from CPUID handling, but it also tidies up the SVM code nicely.

Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Brian Woods <brian.woods@amd.com>

diff --git a/xen/arch/x86/cpuid.c b/xen/arch/x86/cpuid.c
index 6f593251bb4969436a23e986bedac5e73b940282..666fbbbdb12a1e03b53a2245855042e4399666fe 100644 (file)
--- a/xen/arch/x86/cpuid.c
+++ b/xen/arch/x86/cpuid.c
@@ -163,14 +163,6 @@ static void recalculate_xstate(struct cpuid_policy *p)
                           xstate_sizes[X86_XCR0_PKRU_POS]);
     }
 
-    if ( p->extd.lwp )
-    {
-        xstates |= X86_XCR0_LWP;
-        xstate_size = max(xstate_size,
-                          xstate_offsets[X86_XCR0_LWP_POS] +
-                          xstate_sizes[X86_XCR0_LWP_POS]);
-    }
-
     p->xstate.max_size  =  xstate_size;
     p->xstate.xcr0_low  =  xstates & ~XSTATE_XSAVES_ONLY;
     p->xstate.xcr0_high = (xstates & ~XSTATE_XSAVES_ONLY) >> 32;
@@ -265,8 +257,7 @@ static void recalculate_misc(struct cpuid_policy *p)
         zero_leaves(p->extd.raw, 0xb, 0x18);
 
         p->extd.raw[0x1b] = EMPTY_LEAF; /* IBS - not supported. */
-
-        p->extd.raw[0x1c].a = 0; /* LWP.a entirely dynamic. */
+        p->extd.raw[0x1c] = EMPTY_LEAF; /* LWP - not supported. */
         break;
     }
 }
@@ -581,11 +572,6 @@ void recalculate_cpuid_policy(struct domain *d)
 
     if ( !p->extd.page1gb )
         p->extd.raw[0x19] = EMPTY_LEAF;
-
-    if ( p->extd.lwp )
-        p->extd.raw[0x1c].d &= max->extd.raw[0x1c].d;
-    else
-        p->extd.raw[0x1c] = EMPTY_LEAF;
 }
 
 int init_domain_cpuid_policy(struct domain *d)
@@ -972,12 +958,6 @@ void guest_cpuid(const struct vcpu *v, uint32_t leaf,
                 res->d |= cpufeat_mask(X86_FEATURE_MTRR);
         }
         break;
-
-    case 0x8000001c:
-        if ( (v->arch.xcr0 & X86_XCR0_LWP) && cpu_has_svm )
-            /* Turn on available bit and other features specified in lwp_cfg. */
-            res->a = (res->d & v->arch.hvm.svm.guest_lwp_cfg) | 1;
-        break;
     }
 }
 

diff --git a/xen/arch/x86/hvm/svm/svm.c b/xen/arch/x86/hvm/svm/svm.c
index 0beb31bbe9f87eca6e5a42c8e9cb55f76a00b13f..9f2649315754b0e030d792a30da8d4fcaa765181 100644 (file)
--- a/xen/arch/x86/hvm/svm/svm.c
+++ b/xen/arch/x86/hvm/svm/svm.c
@@ -939,72 +939,6 @@ static void svm_init_hypercall_page(struct domain *d, void *hypercall_page)
     *(u16 *)(hypercall_page + (__HYPERVISOR_iret * 32)) = 0x0b0f; /* ud2 */
 }
 
-static void svm_lwp_interrupt(struct cpu_user_regs *regs)
-{
-    struct vcpu *curr = current;
-
-    ack_APIC_irq();
-    vlapic_set_irq(
-        vcpu_vlapic(curr),
-        (curr->arch.hvm.svm.guest_lwp_cfg >> 40) & 0xff,
-        0);
-}
-
-static inline void svm_lwp_save(struct vcpu *v)
-{
-    /* Don't mess up with other guests. Disable LWP for next VCPU. */
-    if ( v->arch.hvm.svm.guest_lwp_cfg )
-    {
-        wrmsrl(MSR_AMD64_LWP_CFG, 0x0);
-        wrmsrl(MSR_AMD64_LWP_CBADDR, 0x0);
-    }
-}
-
-static inline void svm_lwp_load(struct vcpu *v)
-{
-    /* Only LWP_CFG is reloaded. LWP_CBADDR will be reloaded via xrstor. */
-   if ( v->arch.hvm.svm.guest_lwp_cfg )
-       wrmsrl(MSR_AMD64_LWP_CFG, v->arch.hvm.svm.cpu_lwp_cfg);
-}
-
-/* Update LWP_CFG MSR (0xc0000105). Return -1 if error; otherwise returns 0. */
-static int svm_update_lwp_cfg(struct vcpu *v, uint64_t msr_content)
-{
-    uint32_t msr_low;
-    static uint8_t lwp_intr_vector;
-
-    if ( xsave_enabled(v) && cpu_has_lwp )
-    {
-        msr_low = (uint32_t)msr_content;
-        
-        /* generate #GP if guest tries to turn on unsupported features. */
-        if ( msr_low & ~v->domain->arch.cpuid->extd.raw[0x1c].d )
-            return -1;
-
-        v->arch.hvm.svm.guest_lwp_cfg = msr_content;
-
-        /* setup interrupt handler if needed */
-        if ( (msr_content & 0x80000000) && ((msr_content >> 40) & 0xff) )
-        {
-            alloc_direct_apic_vector(&lwp_intr_vector, svm_lwp_interrupt);
-            v->arch.hvm.svm.cpu_lwp_cfg = (msr_content & 0xffff00ffffffffffULL)
-                | ((uint64_t)lwp_intr_vector << 40);
-        }
-        else
-        {
-            /* otherwise disable it */
-            v->arch.hvm.svm.cpu_lwp_cfg = msr_content & 0xffff00ff7fffffffULL;
-        }
-        
-        wrmsrl(MSR_AMD64_LWP_CFG, v->arch.hvm.svm.cpu_lwp_cfg);
-
-        /* track nonalzy state if LWP_CFG is non-zero. */
-        v->arch.nonlazy_xstate_used = !!(msr_content);
-    }
-
-    return 0;
-}
-
 static inline void svm_tsc_ratio_save(struct vcpu *v)
 {
     /* Other vcpus might not have vtsc enabled. So disable TSC_RATIO here. */
@@ -1034,7 +968,6 @@ static void svm_ctxt_switch_from(struct vcpu *v)
         svm_fpu_leave(v);
 
     svm_save_dr(v);
-    svm_lwp_save(v);
     svm_tsc_ratio_save(v);
 
     svm_sync_vmcb(v, vmcb_needs_vmload);
@@ -1066,7 +999,6 @@ static void svm_ctxt_switch_to(struct vcpu *v)
 
     svm_vmsave_pa(per_cpu(host_vmcb, cpu));
     vmcb->cleanbits.bytes = 0;
-    svm_lwp_load(v);
     svm_tsc_ratio_load(v);
 
     if ( cpu_has_msr_tsc_aux )
@@ -2002,10 +1934,6 @@ static int svm_msr_read_intercept(unsigned int msr, uint64_t *msr_content)
         *msr_content = vmcb_get_lastinttoip(vmcb);
         break;
 
-    case MSR_AMD64_LWP_CFG:
-        *msr_content = v->arch.hvm.svm.guest_lwp_cfg;
-        break;
-
     case MSR_K7_PERFCTR0:
     case MSR_K7_PERFCTR1:
     case MSR_K7_PERFCTR2:
@@ -2177,11 +2105,6 @@ static int svm_msr_write_intercept(unsigned int msr, uint64_t msr_content)
         vmcb_set_lastinttoip(vmcb, msr_content);
         break;
 
-    case MSR_AMD64_LWP_CFG:
-        if ( svm_update_lwp_cfg(v, msr_content) < 0 )
-            goto gpf;
-        break;
-
     case MSR_K7_PERFCTR0:
     case MSR_K7_PERFCTR1:
     case MSR_K7_PERFCTR2:

diff --git a/xen/arch/x86/hvm/svm/vmcb.c b/xen/arch/x86/hvm/svm/vmcb.c
index 9d1c5bf6af98217c1dbee47b23cf0603cc39ac73..71ee7102f76ff05c7531e7304ae58fe0e43ac0fb 100644 (file)
--- a/xen/arch/x86/hvm/svm/vmcb.c
+++ b/xen/arch/x86/hvm/svm/vmcb.c
@@ -100,11 +100,6 @@ static int construct_vmcb(struct vcpu *v)
     svm_disable_intercept_for_msr(v, MSR_STAR);
     svm_disable_intercept_for_msr(v, MSR_SYSCALL_MASK);
 
-    /* LWP_CBADDR MSR is saved and restored by FPU code. So SVM doesn't need to
-     * intercept it. */
-    if ( cpu_has_lwp )
-        svm_disable_intercept_for_msr(v, MSR_AMD64_LWP_CBADDR);
-
     vmcb->_msrpm_base_pa = virt_to_maddr(svm->msrpm);
     vmcb->_iopm_base_pa = __pa(v->domain->arch.hvm.io_bitmap);
 

diff --git a/xen/arch/x86/msr.c b/xen/arch/x86/msr.c
index 883b57b2d59e0fc52bea898d03273379117cd0d0..5a2ef7884968a483e3705e0a562d2d5840793c4d 100644 (file)
--- a/xen/arch/x86/msr.c
+++ b/xen/arch/x86/msr.c
@@ -132,6 +132,8 @@ int guest_rdmsr(struct vcpu *v, uint32_t msr, uint64_t *val)
     case MSR_FLUSH_CMD:
         /* Write-only */
     case MSR_TSX_FORCE_ABORT:
+    case MSR_AMD64_LWP_CFG:
+    case MSR_AMD64_LWP_CBADDR:
         /* Not offered to guests. */
         goto gp_fault;
 
@@ -272,6 +274,8 @@ int guest_wrmsr(struct vcpu *v, uint32_t msr, uint64_t val)
     case MSR_ARCH_CAPABILITIES:
         /* Read-only */
     case MSR_TSX_FORCE_ABORT:
+    case MSR_AMD64_LWP_CFG:
+    case MSR_AMD64_LWP_CBADDR:
         /* Not offered to guests. */
         goto gp_fault;
 

diff --git a/xen/arch/x86/xstate.c b/xen/arch/x86/xstate.c
index 858d1a6573e3d1eb87eefe849013451a4fb5a889..3da609a6b02b3270762712de1fe542bfda378e27 100644 (file)
--- a/xen/arch/x86/xstate.c
+++ b/xen/arch/x86/xstate.c
@@ -725,8 +725,7 @@ int handle_xsetbv(u32 index, u64 new_bv)
     curr->arch.xcr0 = new_bv;
     curr->arch.xcr0_accum |= new_bv;
 
-    /* LWP sets nonlazy_xstate_used independently. */
-    if ( new_bv & (XSTATE_NONLAZY & ~X86_XCR0_LWP) )
+    if ( new_bv & XSTATE_NONLAZY )
         curr->arch.nonlazy_xstate_used = 1;
 
     mask &= curr->fpu_dirtied ? ~XSTATE_FP_SSE : XSTATE_NONLAZY;

diff --git a/xen/include/asm-x86/cpufeature.h b/xen/include/asm-x86/cpufeature.h
index bf5f37ec3605554518d8329759841b63e1ffe3d0..b97dd6ed9c6eeb900506986a02c4fc61356cfa35 100644 (file)
--- a/xen/include/asm-x86/cpufeature.h
+++ b/xen/include/asm-x86/cpufeature.h
@@ -78,7 +78,6 @@
 #define cpu_has_svm             boot_cpu_has(X86_FEATURE_SVM)
 #define cpu_has_sse4a           boot_cpu_has(X86_FEATURE_SSE4A)
 #define cpu_has_xop             boot_cpu_has(X86_FEATURE_XOP)
-#define cpu_has_lwp             boot_cpu_has(X86_FEATURE_LWP)
 #define cpu_has_fma4            boot_cpu_has(X86_FEATURE_FMA4)
 #define cpu_has_tbm             boot_cpu_has(X86_FEATURE_TBM)
 

diff --git a/xen/include/asm-x86/hvm/svm/vmcb.h b/xen/include/asm-x86/hvm/svm/vmcb.h
index 70177059e74c13eedd5b9a4b17d3fba75ac3fe9a..5c710286f7fd7084927461f221ef6d15b77dc0ce 100644 (file)
--- a/xen/include/asm-x86/hvm/svm/vmcb.h
+++ b/xen/include/asm-x86/hvm/svm/vmcb.h
@@ -534,10 +534,6 @@ struct svm_vcpu {
     uint64_t guest_sysenter_cs;
     uint64_t guest_sysenter_esp;
     uint64_t guest_sysenter_eip;
-
-    /* AMD lightweight profiling MSR */
-    uint64_t guest_lwp_cfg;      /* guest version */
-    uint64_t cpu_lwp_cfg;        /* CPU version */
 };
 
 struct vmcb_struct *alloc_vmcb(void);

diff --git a/xen/include/asm-x86/xstate.h b/xen/include/asm-x86/xstate.h
index 47f602b855fcd7ed6b87780b4ce7e4f0dfb79165..7ab0bdde89cf4871df35b51809ffddf7220c7a53 100644 (file)
--- a/xen/include/asm-x86/xstate.h
+++ b/xen/include/asm-x86/xstate.h
@@ -35,8 +35,7 @@ extern uint32_t mxcsr_mask;
                         XSTATE_NONLAZY)
 
 #define XSTATE_ALL     (~(1ULL << 63))
-#define XSTATE_NONLAZY (X86_XCR0_LWP | X86_XCR0_BNDREGS | X86_XCR0_BNDCSR | \
-                        X86_XCR0_PKRU)
+#define XSTATE_NONLAZY (X86_XCR0_BNDREGS | X86_XCR0_BNDCSR | X86_XCR0_PKRU)
 #define XSTATE_LAZY    (XSTATE_ALL & ~XSTATE_NONLAZY)
 #define XSTATE_XSAVES_ONLY         0
 #define XSTATE_COMPACTION_ENABLED  (1ULL << 63)

diff --git a/xen/include/public/arch-x86/cpufeatureset.h b/xen/include/public/arch-x86/cpufeatureset.h
index cf28118cabc11dee3b6046d3c6d92a97c76f0d00..e4651b4434447705e4a29b201b3758424c1060f9 100644 (file)
--- a/xen/include/public/arch-x86/cpufeatureset.h
+++ b/xen/include/public/arch-x86/cpufeatureset.h
@@ -176,7 +176,7 @@ XEN_CPUFEATURE(IBS,           3*32+10) /*   Instruction Based Sampling */
 XEN_CPUFEATURE(XOP,           3*32+11) /*A  extended AVX instructions */
 XEN_CPUFEATURE(SKINIT,        3*32+12) /*   SKINIT/STGI instructions */
 XEN_CPUFEATURE(WDT,           3*32+13) /*   Watchdog timer */
-XEN_CPUFEATURE(LWP,           3*32+15) /*S  Light Weight Profiling */
+XEN_CPUFEATURE(LWP,           3*32+15) /*   Light Weight Profiling */
 XEN_CPUFEATURE(FMA4,          3*32+16) /*A  4 operands MAC instructions */
 XEN_CPUFEATURE(NODEID_MSR,    3*32+19) /*   NodeId MSR */
 XEN_CPUFEATURE(TBM,           3*32+21) /*A  trailing bit manipulations */