Provide support for this insn, which is a prereq to FRED. CPUID-wise
introduce both its, FRED's, and the NMI_SRC bit at this occasion, thus
allowing to also express the dependency right away.

While adding a testcase, also add a SWAPGS one. In order to not affect
the behavior of pre-existing tests, install write_{segment,msr} hooks
only transiently.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
---
Instead of ->read_segment() we could of course also use ->read_msr() to
fetch the original GS base. I don't think I can see a clear advantage of
either approach; the way it's done it matches how we handle SWAPGS.

For PV save_segments() would need adjustment, but the insn being
restricted to ring 0 means PV guests can't use it anyway (unless we
wanted to emulate it as another privileged insn).
---
v6: Use MSR constants in test harness. S->s in cpufeatureset.h. Add
    NMI_SRC feature bits. Re-base.
v5: Re-base.
v3: Add dependency on LM. Re-base.
v2: Use X86_EXC_*. Add comments.

--- a/tools/tests/x86_emulator/predicates.c
+++ b/tools/tests/x86_emulator/predicates.c
@@ -326,6 +326,7 @@ static const struct {
     { { 0x00, 0x18 }, { 2, 2 }, T, R }, /* ltr */
     { { 0x00, 0x20 }, { 2, 2 }, T, R }, /* verr */
     { { 0x00, 0x28 }, { 2, 2 }, T, R }, /* verw */
+    { { 0x00, 0x30 }, { 0, 2 }, T, R, pfx_f2 }, /* lkgs */
     { { 0x01, 0x00 }, { 2, 2 }, F, W }, /* sgdt */
     { { 0x01, 0x08 }, { 2, 2 }, F, W }, /* sidt */
     { { 0x01, 0x10 }, { 2, 2 }, F, R }, /* lgdt */
--- a/tools/tests/x86_emulator/test_x86_emulator.c
+++ b/tools/tests/x86_emulator/test_x86_emulator.c
@@ -672,6 +672,10 @@ static int blk(
     return x86_emul_blk((void *)offset, p_data, bytes, eflags, state, ctxt);
 }
 
+#ifdef __x86_64__
+static unsigned long gs_base, gs_base_shadow;
+#endif
+
 static int read_segment(
     enum x86_segment seg,
     struct segment_register *reg,
@@ -681,8 +685,30 @@ static int read_segment(
         return X86EMUL_UNHANDLEABLE;
     memset(reg, 0, sizeof(*reg));
     reg->p = 1;
+
+#ifdef __x86_64__
+    if ( seg == x86_seg_gs )
+        reg->base = gs_base;
+#endif
+
+    return X86EMUL_OKAY;
+}
+
+#ifdef __x86_64__
+static int write_segment(
+    enum x86_segment seg,
+    const struct segment_register *reg,
+    struct x86_emulate_ctxt *ctxt)
+{
+    if ( !is_x86_user_segment(seg) )
+        return X86EMUL_UNHANDLEABLE;
+
+    if ( seg == x86_seg_gs )
+        gs_base = reg->base;
+
     return X86EMUL_OKAY;
 }
+#endif
 
 static int read_msr(
     unsigned int reg,
@@ -695,6 +721,20 @@ static int read_msr(
         *val = ctxt->addr_size > 32 ? EFER_LME | EFER_LMA : 0;
         return X86EMUL_OKAY;
 
+#ifdef __x86_64__
+    case MSR_GS_BASE:
+        if ( ctxt->addr_size < 64 )
+            break;
+        *val = gs_base;
+        return X86EMUL_OKAY;
+
+    case MSR_SHADOW_GS_BASE:
+        if ( ctxt->addr_size < 64 )
+            break;
+        *val = gs_base_shadow;
+        return X86EMUL_OKAY;
+#endif
+
     case MSR_TSC_AUX:
 #define TSC_AUX_VALUE 0xCACACACA
         *val = TSC_AUX_VALUE;
@@ -704,6 +744,31 @@ static int read_msr(
     return X86EMUL_UNHANDLEABLE;
 }
 
+#ifdef __x86_64__
+static int write_msr(
+    unsigned int reg,
+    uint64_t val,
+    struct x86_emulate_ctxt *ctxt)
+{
+    switch ( reg )
+    {
+    case MSR_GS_BASE:
+        if ( ctxt->addr_size < 64 || !is_canonical_address(val) )
+            break;
+        gs_base = val;
+        return X86EMUL_OKAY;
+
+    case MSR_SHADOW_GS_BASE:
+        if ( ctxt->addr_size < 64 || !is_canonical_address(val) )
+            break;
+        gs_base_shadow = val;
+        return X86EMUL_OKAY;
+    }
+
+    return X86EMUL_UNHANDLEABLE;
+}
+#endif
+
 #define INVPCID_ADDR 0x12345678
 #define INVPCID_PCID 0x123
 
@@ -1338,6 +1403,41 @@ int main(int argc, char **argv)
         printf("%u bytes read - ", bytes_read);
         goto fail;
     }
+    printf("okay\n");
+
+    emulops.write_segment = write_segment;
+    emulops.write_msr     = write_msr;
+
+    printf("%-40s", "Testing swapgs...");
+    instr[0] = 0x0f; instr[1] = 0x01; instr[2] = 0xf8;
+    regs.eip = (unsigned long)&instr[0];
+    gs_base = 0xffffeeeecccc8888UL;
+    gs_base_shadow = 0x0000111122224444UL;
+    rc = x86_emulate(&ctxt, &emulops);
+    if ( (rc != X86EMUL_OKAY) ||
+         (regs.eip != (unsigned long)&instr[3]) ||
+         (gs_base != 0x0000111122224444UL) ||
+         (gs_base_shadow != 0xffffeeeecccc8888UL) )
+        goto fail;
+    printf("okay\n");
+
+    printf("%-40s", "Testing lkgs 2(%rdx)...");
+    instr[0] = 0xf2; instr[1] = 0x0f; instr[2] = 0x00; instr[3] = 0x72; instr[4] = 0x02;
+    regs.eip = (unsigned long)&instr[0];
+    regs.edx = (unsigned long)res;
+    res[0]   = 0x00004444;
+    res[1]   = 0x8888cccc;
+    i = cpu_policy.extd.nscb; cpu_policy.extd.nscb = true; /* for AMD */
+    rc = x86_emulate(&ctxt, &emulops);
+    if ( (rc != X86EMUL_OKAY) ||
+         (regs.eip != (unsigned long)&instr[5]) ||
+         (gs_base != 0x0000111122224444UL) ||
+         gs_base_shadow )
+        goto fail;
+
+    cpu_policy.extd.nscb = i;
+    emulops.write_segment = NULL;
+    emulops.write_msr     = NULL;
 #endif
     printf("okay\n");
 
--- a/tools/tests/x86_emulator/x86-emulate.c
+++ b/tools/tests/x86_emulator/x86-emulate.c
@@ -85,6 +85,7 @@ bool emul_test_init(void)
     cpu_policy.feat.invpcid = true;
     cpu_policy.feat.adx = true;
     cpu_policy.feat.rdpid = true;
+    cpu_policy.feat.lkgs = true;
     cpu_policy.feat.wrmsrns = true;
     cpu_policy.extd.clzero = true;
 
--- a/xen/arch/x86/x86_emulate/decode.c
+++ b/xen/arch/x86/x86_emulate/decode.c
@@ -744,8 +744,12 @@ decode_twobyte(struct x86_emulate_state
         case 0:
             s->desc |= DstMem | SrcImplicit | Mov;
             break;
+        case 6:
+            if ( !(s->modrm_reg & 1) && mode_64bit() )
+            {
         case 2: case 4:
-            s->desc |= SrcMem16;
+                s->desc |= SrcMem16;
+            }
             break;
         }
         break;
--- a/xen/arch/x86/x86_emulate/private.h
+++ b/xen/arch/x86/x86_emulate/private.h
@@ -594,6 +594,7 @@ amd_like(const struct x86_emulate_ctxt *
 #define vcpu_has_avx_vnni()    (ctxt->cpuid->feat.avx_vnni)
 #define vcpu_has_avx512_bf16() (ctxt->cpuid->feat.avx512_bf16)
 #define vcpu_has_cmpccxadd()   (ctxt->cpuid->feat.cmpccxadd)
+#define vcpu_has_lkgs()        (ctxt->cpuid->feat.lkgs)
 #define vcpu_has_wrmsrns()     (ctxt->cpuid->feat.wrmsrns)
 #define vcpu_has_avx_ifma()    (ctxt->cpuid->feat.avx_ifma)
 #define vcpu_has_avx_vnni_int8() (ctxt->cpuid->feat.avx_vnni_int8)
--- a/xen/arch/x86/x86_emulate/x86_emulate.c
+++ b/xen/arch/x86/x86_emulate/x86_emulate.c
@@ -2871,8 +2871,35 @@ x86_emulate(
                 break;
             }
             break;
-        default:
-            generate_exception_if(true, X86_EXC_UD);
+        case 6: /* lkgs */
+            generate_exception_if((modrm_reg & 1) || vex.pfx != vex_f2,
+                                  X86_EXC_UD);
+            generate_exception_if(!mode_64bit() || !mode_ring0(), X86_EXC_UD);
+            vcpu_must_have(lkgs);
+            fail_if(!ops->read_segment || !ops->read_msr ||
+                    !ops->write_segment || !ops->write_msr);
+            if ( (rc = ops->read_msr(MSR_SHADOW_GS_BASE, &msr_val,
+                                     ctxt)) != X86EMUL_OKAY ||
+                 (rc = ops->read_segment(x86_seg_gs, &sreg,
+                                         ctxt)) != X86EMUL_OKAY )
+                goto done;
+            dst.orig_val = sreg.base; /* Preserve full GS Base. */
+            if ( (rc = protmode_load_seg(x86_seg_gs, src.val, false, &sreg,
+                                         ctxt, ops)) != X86EMUL_OKAY ||
+                 /* Write (32-bit) base into SHADOW_GS. */
+                 (rc = ops->write_msr(MSR_SHADOW_GS_BASE, sreg.base,
+                                      ctxt)) != X86EMUL_OKAY )
+                goto done;
+            sreg.base = dst.orig_val; /* Reinstate full GS Base. */
+            if ( (rc = ops->write_segment(x86_seg_gs, &sreg,
+                                          ctxt)) != X86EMUL_OKAY )
+            {
+                /* Best effort unwind (i.e. no real error checking). */
+                if ( ops->write_msr(MSR_SHADOW_GS_BASE, msr_val,
+                                    ctxt) == X86EMUL_EXCEPTION )
+                    x86_emul_reset_event(ctxt);
+                goto done;
+            }
             break;
         }
         break;
--- a/xen/include/public/arch-x86/cpufeatureset.h
+++ b/xen/include/public/arch-x86/cpufeatureset.h
@@ -307,7 +307,10 @@ XEN_CPUFEATURE(CMPCCXADD,    10*32+ 7) /
 XEN_CPUFEATURE(FZRM,         10*32+10) /*A  Fast Zero-length REP MOVSB */
 XEN_CPUFEATURE(FSRS,         10*32+11) /*A  Fast Short REP STOSB */
 XEN_CPUFEATURE(FSRCS,        10*32+12) /*A  Fast Short REP CMPSB/SCASB */
+XEN_CPUFEATURE(FRED,         10*32+17) /*   Flexible Return and Event Delivery */
+XEN_CPUFEATURE(LKGS,         10*32+18) /*s  Load Kernel GS Base */
 XEN_CPUFEATURE(WRMSRNS,      10*32+19) /*S  WRMSR Non-Serialising */
+XEN_CPUFEATURE(NMI_SRC,      10*32+20) /*   NMI-source reporting */
 XEN_CPUFEATURE(AMX_FP16,     10*32+21) /*   AMX FP16 instruction */
 XEN_CPUFEATURE(AVX_IFMA,     10*32+23) /*A  AVX-IFMA Instructions */
 
--- a/xen/tools/gen-cpuid.py
+++ b/xen/tools/gen-cpuid.py
@@ -274,7 +274,8 @@ def crunch_numbers(state):
         # superpages, PCID and PKU are only available in 4 level paging.
         # NO_LMSL indicates the absense of Long Mode Segment Limits, which
         # have been dropped in hardware.
-        LM: [CX16, PCID, LAHF_LM, PAGE1GB, PKU, NO_LMSL, AMX_TILE, CMPCCXADD],
+        LM: [CX16, PCID, LAHF_LM, PAGE1GB, PKU, NO_LMSL, AMX_TILE, CMPCCXADD,
+             LKGS],
 
         # AMD K6-2+ and K6-III processors shipped with 3DNow+, beyond the
         # standard 3DNow in the earlier K6 processors.
@@ -343,6 +344,9 @@ def crunch_numbers(state):
         # computational instructions.  All further AMX features are built on top
         # of AMX-TILE.
         AMX_TILE: [AMX_BF16, AMX_INT8, AMX_FP16, AMX_COMPLEX],
+
+        # FRED builds on the LKGS instruction.
+        LKGS: [FRED],
     }
 
     deep_features = tuple(sorted(deps.keys()))