@@ -250,13 +250,14 @@ $(BASEDIR)/include/asm-x86/asm-macros.h:
# sure we pick up changes when the compiler used has changed.)
ifeq ($(MAKECMDGOALS),asm-offsets.s)
-as-ISA-list := CLWB EPT FSGSBASE INVPCID MOVDIR64B RDRAND RDSEED SSE4_2 VMX XSAVEOPT
+as-ISA-list := CLWB ENQCMD EPT FSGSBASE INVPCID MOVDIR64B RDRAND RDSEED SSE4_2 VMX XSAVEOPT
CLWB-insn := clwb (%rax)
EPT-insn := invept (%rax),%rax
FSGSBASE-insn := rdfsbase %rax
INVPCID-insn := invpcid (%rax),%rax
MOVDIR64B-insn := movdir64b (%rax),%rax
+ENQCMD-insn := enqcmd (%rax),%rax
RDRAND-insn := rdrand %eax
RDSEED-insn := rdseed %eax
SSE4_2-insn := crc32 %eax,%eax
@@ -854,6 +854,7 @@ struct x86_emulate_state {
rmw_xor,
} rmw;
enum {
+ blk_enqcmd,
blk_movdir,
} blk;
uint8_t modrm, modrm_mod, modrm_reg, modrm_rm;
@@ -900,6 +901,7 @@ typedef union {
uint64_t __attribute__ ((aligned(16))) xmm[2];
uint64_t __attribute__ ((aligned(32))) ymm[4];
uint64_t __attribute__ ((aligned(64))) zmm[8];
+ uint32_t data32[16];
} mmval_t;
/*
@@ -1909,6 +1911,7 @@ in_protmode(
#define vcpu_has_rdpid() (ctxt->cpuid->feat.rdpid)
#define vcpu_has_movdiri() (ctxt->cpuid->feat.movdiri)
#define vcpu_has_movdir64b() (ctxt->cpuid->feat.movdir64b)
+#define vcpu_has_enqcmd() (ctxt->cpuid->feat.enqcmd)
#define vcpu_has_avx512_4vnniw() (ctxt->cpuid->feat.avx512_4vnniw)
#define vcpu_has_avx512_4fmaps() (ctxt->cpuid->feat.avx512_4fmaps)
#define vcpu_has_avx512_bf16() (ctxt->cpuid->feat.avx512_bf16)
@@ -10101,6 +10104,36 @@ x86_emulate(
state->simd_size = simd_none;
break;
+ case X86EMUL_OPC_F2(0x0f38, 0xf8): /* enqcmd r,m512 */
+ case X86EMUL_OPC_F3(0x0f38, 0xf8): /* enqcmds r,m512 */
+ host_and_vcpu_must_have(enqcmd);
+ generate_exception_if(ea.type != OP_MEM, EXC_UD);
+ generate_exception_if(vex.pfx != vex_f2 && !mode_ring0(), EXC_GP, 0);
+ src.val = truncate_ea(*dst.reg);
+ generate_exception_if(!is_aligned(x86_seg_es, src.val, 64, ctxt, ops),
+ EXC_GP, 0);
+ fail_if(!ops->blk);
+ BUILD_BUG_ON(sizeof(*mmvalp) < 64);
+ if ( (rc = ops->read(ea.mem.seg, ea.mem.off, mmvalp, 64,
+ ctxt)) != X86EMUL_OKAY )
+ goto done;
+ if ( vex.pfx == vex_f2 ) /* enqcmd */
+ {
+ fail_if(!ops->read_msr);
+ if ( (rc = ops->read_msr(MSR_IA32_PASID,
+ &msr_val, ctxt)) != X86EMUL_OKAY )
+ goto done;
+ generate_exception_if(!(msr_val & PASID_VALID), EXC_GP, 0);
+ mmvalp->data32[0] = MASK_EXTR(msr_val, PASID_PASID_MASK);
+ }
+ mmvalp->data32[0] &= ~0x7ff00000;
+ state->blk = blk_enqcmd;
+ if ( (rc = ops->blk(x86_seg_es, src.val, mmvalp, 64, &_regs.eflags,
+ state, ctxt)) != X86EMUL_OKAY )
+ goto done;
+ state->simd_size = simd_none;
+ break;
+
case X86EMUL_OPC(0x0f38, 0xf9): /* movdiri mem,r */
vcpu_must_have(movdiri);
generate_exception_if(dst.type != OP_MEM, EXC_UD);
@@ -11378,11 +11411,36 @@ int x86_emul_blk(
{
switch ( state->blk )
{
+ bool zf;
+
/*
* Throughout this switch(), memory clobbers are used to compensate
* that other operands may not properly express the (full) memory
* ranges covered.
*/
+ case blk_enqcmd:
+ ASSERT(bytes == 64);
+ if ( ((unsigned long)ptr & 0x3f) )
+ {
+ ASSERT_UNREACHABLE();
+ return X86EMUL_UNHANDLEABLE;
+ }
+ *eflags &= ~EFLAGS_MASK;
+#ifdef HAVE_AS_ENQCMD
+ asm ( "enqcmds (%[src]), %[dst]" ASM_FLAG_OUT(, "; setz %0")
+ : [zf] ASM_FLAG_OUT("=@ccz", "=qm") (zf)
+ : [src] "r" (data), [dst] "r" (ptr) : "memory" );
+#else
+ /* enqcmds (%rsi), %rdi */
+ asm ( ".byte 0xf3, 0x0f, 0x38, 0xf8, 0x3e"
+ ASM_FLAG_OUT(, "; setz %[zf]")
+ : [zf] ASM_FLAG_OUT("=@ccz", "=qm") (zf)
+ : "S" (data), "D" (ptr) : "memory" );
+#endif
+ if ( zf )
+ *eflags |= X86_EFLAGS_ZF;
+ break;
+
case blk_movdir:
ASSERT(bytes == 64);
if ( ((unsigned long)ptr & 0x3f) )
@@ -121,6 +121,7 @@
#define cpu_has_avx512_vpopcntdq boot_cpu_has(X86_FEATURE_AVX512_VPOPCNTDQ)
#define cpu_has_rdpid boot_cpu_has(X86_FEATURE_RDPID)
#define cpu_has_movdir64b boot_cpu_has(X86_FEATURE_MOVDIR64B)
+#define cpu_has_enqcmd boot_cpu_has(X86_FEATURE_ENQCMD)
/* CPUID level 0x80000007.edx */
#define cpu_has_itsc boot_cpu_has(X86_FEATURE_ITSC)
@@ -412,6 +412,10 @@
#define MSR_IA32_TSC_DEADLINE 0x000006E0
#define MSR_IA32_ENERGY_PERF_BIAS 0x000001b0
+#define MSR_IA32_PASID 0x00000d93
+#define PASID_PASID_MASK 0x000fffff
+#define PASID_VALID 0x80000000
+
/* Platform Shared Resource MSRs */
#define MSR_IA32_CMT_EVTSEL 0x00000c8d
#define MSR_IA32_CMT_EVTSEL_UE_MASK 0x0000ffff
@@ -239,6 +239,7 @@ XEN_CPUFEATURE(RDPID, 6*32+22) /
XEN_CPUFEATURE(CLDEMOTE, 6*32+25) /*A CLDEMOTE instruction */
XEN_CPUFEATURE(MOVDIRI, 6*32+27) /*A MOVDIRI instruction */
XEN_CPUFEATURE(MOVDIR64B, 6*32+28) /*A MOVDIR64B instruction */
+XEN_CPUFEATURE(ENQCMD, 6*32+29) /* ENQCMD{,S} instructions */
/* AMD-defined CPU features, CPUID level 0x80000007.edx, word 7 */
XEN_CPUFEATURE(ITSC, 7*32+ 8) /* Invariant TSC */
Introduce a new blk() hook, paralleling the rmw() on in certain way, but being intended for larger data sizes, and hence its HVM intermediate handling function doesn't fall back to splitting the operation if the requested virtual address can't be mapped. Note that the ISA extensions document revision 037 doesn't specify exception behavior for ModRM.mod == 0b11; assuming #UD here. No tests are being added to the harness - this would be quite hard, we can't just issue the insns against RAM. Their similarity with MOVDIR64B should have the test case there be god enough to cover any fundamental flaws. Signed-off-by: Jan Beulich <jbeulich@suse.com> --- TBD: This doesn't (can't) consult PASID translation tables yet, as we have no VMX code for this so far. I guess for this we will want to replace the direct ->read_msr(MSR_IA32_PASID, ...) with a new ->read_pasid() hook. --- v5: New.