From: "Jan Beulich" <JBeulich@suse.com>
To: xen-devel <xen-devel@lists.xenproject.org>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Subject: [PATCH 04/17] x86emul: support F16C insns
Date: Wed, 21 Jun 2017 06:01:08 -0600 [thread overview]
Message-ID: <594A7C240200007800165322@prv-mh.provo.novell.com> (raw)
In-Reply-To: <594A733B020000780016527C@prv-mh.provo.novell.com>
[-- Attachment #1: Type: text/plain, Size: 6751 bytes --]
Note that this avoids emulating the behavior of VCVTPS2PH found on at
least some Intel CPUs, which update MXCSR even when the memory write
faults.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
--- a/tools/tests/x86_emulator/test_x86_emulator.c
+++ b/tools/tests/x86_emulator/test_x86_emulator.c
@@ -3028,6 +3028,47 @@ int main(int argc, char **argv)
printf("skipped\n");
#endif
+ printf("%-40s", "Testing vcvtph2ps (%ecx),%ymm1...");
+ if ( stack_exec && cpu_has_f16c )
+ {
+ decl_insn(vcvtph2ps);
+ decl_insn(vcvtps2ph);
+
+ asm volatile ( "vxorps %%xmm1, %%xmm1, %%xmm1\n"
+ put_insn(vcvtph2ps, "vcvtph2ps (%0), %%ymm1")
+ :: "c" (NULL) );
+
+ set_insn(vcvtph2ps);
+ res[1] = 0x40003c00; /* (1.0, 2.0) */
+ res[2] = 0x44004200; /* (3.0, 4.0) */
+ res[3] = 0x3400b800; /* (-.5, .25) */
+ res[4] = 0xbc000000; /* (0.0, -1.) */
+ memset(res + 5, 0xff, 16);
+ regs.ecx = (unsigned long)(res + 1);
+ rc = x86_emulate(&ctxt, &emulops);
+ asm volatile ( "vmovups %%ymm1, %0" : "=m" (res[16]) );
+ if ( rc != X86EMUL_OKAY || !check_eip(vcvtph2ps) )
+ goto fail;
+ printf("okay\n");
+
+ printf("%-40s", "Testing vcvtps2ph $0,%ymm1,(%edx)...");
+ asm volatile ( "vmovups %0, %%ymm1\n"
+ put_insn(vcvtps2ph, "vcvtps2ph $0, %%ymm1, (%1)")
+ :: "m" (res[16]), "d" (NULL) );
+
+ set_insn(vcvtps2ph);
+ memset(res + 7, 0, 32);
+ regs.edx = (unsigned long)(res + 7);
+ rc = x86_emulate(&ctxt, &emulops);
+ if ( rc != X86EMUL_OKAY || !check_eip(vcvtps2ph) ||
+ memcmp(res + 1, res + 7, 16) ||
+ res[11] || res[12] || res[13] || res[14] )
+ goto fail;
+ printf("okay\n");
+ }
+ else
+ printf("skipped\n");
+
#undef decl_insn
#undef put_insn
#undef set_insn
--- a/tools/tests/x86_emulator/x86_emulate.h
+++ b/tools/tests/x86_emulator/x86_emulate.h
@@ -127,6 +127,14 @@ static inline uint64_t xgetbv(uint32_t x
(res.c & (1U << 28)) != 0; \
})
+#define cpu_has_f16c ({ \
+ struct cpuid_leaf res; \
+ emul_test_cpuid(1, 0, &res, NULL); \
+ if ( !(res.c & (1U << 27)) || ((xgetbv(0) & 6) != 6) ) \
+ res.c = 0; \
+ (res.c & (1U << 29)) != 0; \
+})
+
#define cpu_has_avx2 ({ \
struct cpuid_leaf res; \
emul_test_cpuid(1, 0, &res, NULL); \
--- a/xen/arch/x86/x86_emulate/x86_emulate.c
+++ b/xen/arch/x86/x86_emulate/x86_emulate.c
@@ -369,6 +369,7 @@ static const struct {
[0x00 ... 0x0b] = { .simd_size = simd_packed_int },
[0x0c ... 0x0f] = { .simd_size = simd_packed_fp },
[0x10] = { .simd_size = simd_packed_int },
+ [0x13] = { .simd_size = simd_other, .two_op = 1 },
[0x14 ... 0x15] = { .simd_size = simd_packed_fp },
[0x17] = { .simd_size = simd_packed_int, .two_op = 1 },
[0x18 ... 0x19] = { .simd_size = simd_scalar_fp, .two_op = 1 },
@@ -411,6 +412,7 @@ static const struct {
[0x14 ... 0x17] = { .simd_size = simd_none, .to_mem = 1, .two_op = 1 },
[0x18] = { .simd_size = simd_128 },
[0x19] = { .simd_size = simd_128, .to_mem = 1, .two_op = 1 },
+ [0x1d] = { .simd_size = simd_other, .to_mem = 1, .two_op = 1 },
[0x20] = { .simd_size = simd_none },
[0x21] = { .simd_size = simd_other },
[0x22] = { .simd_size = simd_none },
@@ -1601,6 +1603,7 @@ static bool vcpu_has(
#define vcpu_has_popcnt() vcpu_has( 1, ECX, 23, ctxt, ops)
#define vcpu_has_aesni() vcpu_has( 1, ECX, 25, ctxt, ops)
#define vcpu_has_avx() vcpu_has( 1, ECX, 28, ctxt, ops)
+#define vcpu_has_f16c() vcpu_has( 1, ECX, 29, ctxt, ops)
#define vcpu_has_rdrand() vcpu_has( 1, ECX, 30, ctxt, ops)
#define vcpu_has_mmxext() (vcpu_has(0x80000001, EDX, 22, ctxt, ops) || \
vcpu_has_sse())
@@ -7216,6 +7219,12 @@ x86_emulate(
host_and_vcpu_must_have(sse4_1);
goto simd_0f38_common;
+ case X86EMUL_OPC_VEX_66(0x0f38, 0x13): /* vcvtph2ps xmm/mem,{x,y}mm */
+ generate_exception_if(vex.w, EXC_UD);
+ host_and_vcpu_must_have(f16c);
+ op_bytes = 8 << vex.l;
+ goto simd_0f_ymm;
+
case X86EMUL_OPC_VEX_66(0x0f38, 0x20): /* vpmovsxbw xmm/mem,{x,y}mm */
case X86EMUL_OPC_VEX_66(0x0f38, 0x21): /* vpmovsxbd xmm/mem,{x,y}mm */
case X86EMUL_OPC_VEX_66(0x0f38, 0x22): /* vpmovsxbq xmm/mem,{x,y}mm */
@@ -7607,6 +7616,50 @@ x86_emulate(
opc = init_prefixes(stub);
goto pextr;
+ case X86EMUL_OPC_VEX_66(0x0f3a, 0x1d): /* vcvtps2ph $imm8,{x,y}mm,xmm/mem */
+ {
+ uint32_t mxcsr;
+
+ generate_exception_if(vex.w || vex.reg != 0xf, EXC_UD);
+ host_and_vcpu_must_have(f16c);
+ fail_if(!ops->write);
+
+ opc = init_prefixes(stub);
+ opc[0] = b;
+ opc[1] = modrm;
+ if ( ea.type == OP_MEM )
+ {
+ /* Convert memory operand to (%rAX). */
+ vex.b = 1;
+ opc[1] &= 0x38;
+ }
+ opc[2] = imm1;
+ fic.insn_bytes = PFX_BYTES + 3;
+ opc[3] = 0xc3;
+
+ copy_VEX(opc, vex);
+ /* Latch MXCSR - we may need to restore it below. */
+ invoke_stub("stmxcsr %[mxcsr]", "",
+ "=m" (*mmvalp), "+m" (fic.exn_raised), [mxcsr] "=m" (mxcsr)
+ : "a" (mmvalp));
+
+ put_stub(stub);
+ check_xmm_exn(&fic);
+
+ if ( ea.type == OP_MEM )
+ {
+ rc = ops->write(ea.mem.seg, ea.mem.off, mmvalp, 8 << vex.l, ctxt);
+ if ( rc != X86EMUL_OKAY )
+ {
+ asm volatile ( "ldmxcsr %0" :: "m" (mxcsr) );
+ goto done;
+ }
+ }
+
+ state->simd_size = simd_none;
+ break;
+ }
+
case X86EMUL_OPC_66(0x0f3a, 0x20): /* pinsrb $imm8,r32/m8,xmm */
case X86EMUL_OPC_66(0x0f3a, 0x22): /* pinsr{d,q} $imm8,r/m,xmm */
host_and_vcpu_must_have(sse4_1);
--- a/xen/include/asm-x86/cpufeature.h
+++ b/xen/include/asm-x86/cpufeature.h
@@ -60,6 +60,7 @@
#define cpu_has_aesni boot_cpu_has(X86_FEATURE_AESNI)
#define cpu_has_xsave boot_cpu_has(X86_FEATURE_XSAVE)
#define cpu_has_avx boot_cpu_has(X86_FEATURE_AVX)
+#define cpu_has_f16c boot_cpu_has(X86_FEATURE_F16C)
#define cpu_has_rdrand boot_cpu_has(X86_FEATURE_RDRAND)
#define cpu_has_hypervisor boot_cpu_has(X86_FEATURE_HYPERVISOR)
[-- Attachment #2: x86emul-F16C.patch --]
[-- Type: text/plain, Size: 6778 bytes --]
x86emul: support F16C insns
Note that this avoids emulating the behavior of VCVTPS2PH found on at
least some Intel CPUs, which update MXCSR even when the memory write
faults.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
--- a/tools/tests/x86_emulator/test_x86_emulator.c
+++ b/tools/tests/x86_emulator/test_x86_emulator.c
@@ -3028,6 +3028,47 @@ int main(int argc, char **argv)
printf("skipped\n");
#endif
+ printf("%-40s", "Testing vcvtph2ps (%ecx),%ymm1...");
+ if ( stack_exec && cpu_has_f16c )
+ {
+ decl_insn(vcvtph2ps);
+ decl_insn(vcvtps2ph);
+
+ asm volatile ( "vxorps %%xmm1, %%xmm1, %%xmm1\n"
+ put_insn(vcvtph2ps, "vcvtph2ps (%0), %%ymm1")
+ :: "c" (NULL) );
+
+ set_insn(vcvtph2ps);
+ res[1] = 0x40003c00; /* (1.0, 2.0) */
+ res[2] = 0x44004200; /* (3.0, 4.0) */
+ res[3] = 0x3400b800; /* (-.5, .25) */
+ res[4] = 0xbc000000; /* (0.0, -1.) */
+ memset(res + 5, 0xff, 16);
+ regs.ecx = (unsigned long)(res + 1);
+ rc = x86_emulate(&ctxt, &emulops);
+ asm volatile ( "vmovups %%ymm1, %0" : "=m" (res[16]) );
+ if ( rc != X86EMUL_OKAY || !check_eip(vcvtph2ps) )
+ goto fail;
+ printf("okay\n");
+
+ printf("%-40s", "Testing vcvtps2ph $0,%ymm1,(%edx)...");
+ asm volatile ( "vmovups %0, %%ymm1\n"
+ put_insn(vcvtps2ph, "vcvtps2ph $0, %%ymm1, (%1)")
+ :: "m" (res[16]), "d" (NULL) );
+
+ set_insn(vcvtps2ph);
+ memset(res + 7, 0, 32);
+ regs.edx = (unsigned long)(res + 7);
+ rc = x86_emulate(&ctxt, &emulops);
+ if ( rc != X86EMUL_OKAY || !check_eip(vcvtps2ph) ||
+ memcmp(res + 1, res + 7, 16) ||
+ res[11] || res[12] || res[13] || res[14] )
+ goto fail;
+ printf("okay\n");
+ }
+ else
+ printf("skipped\n");
+
#undef decl_insn
#undef put_insn
#undef set_insn
--- a/tools/tests/x86_emulator/x86_emulate.h
+++ b/tools/tests/x86_emulator/x86_emulate.h
@@ -127,6 +127,14 @@ static inline uint64_t xgetbv(uint32_t x
(res.c & (1U << 28)) != 0; \
})
+#define cpu_has_f16c ({ \
+ struct cpuid_leaf res; \
+ emul_test_cpuid(1, 0, &res, NULL); \
+ if ( !(res.c & (1U << 27)) || ((xgetbv(0) & 6) != 6) ) \
+ res.c = 0; \
+ (res.c & (1U << 29)) != 0; \
+})
+
#define cpu_has_avx2 ({ \
struct cpuid_leaf res; \
emul_test_cpuid(1, 0, &res, NULL); \
--- a/xen/arch/x86/x86_emulate/x86_emulate.c
+++ b/xen/arch/x86/x86_emulate/x86_emulate.c
@@ -369,6 +369,7 @@ static const struct {
[0x00 ... 0x0b] = { .simd_size = simd_packed_int },
[0x0c ... 0x0f] = { .simd_size = simd_packed_fp },
[0x10] = { .simd_size = simd_packed_int },
+ [0x13] = { .simd_size = simd_other, .two_op = 1 },
[0x14 ... 0x15] = { .simd_size = simd_packed_fp },
[0x17] = { .simd_size = simd_packed_int, .two_op = 1 },
[0x18 ... 0x19] = { .simd_size = simd_scalar_fp, .two_op = 1 },
@@ -411,6 +412,7 @@ static const struct {
[0x14 ... 0x17] = { .simd_size = simd_none, .to_mem = 1, .two_op = 1 },
[0x18] = { .simd_size = simd_128 },
[0x19] = { .simd_size = simd_128, .to_mem = 1, .two_op = 1 },
+ [0x1d] = { .simd_size = simd_other, .to_mem = 1, .two_op = 1 },
[0x20] = { .simd_size = simd_none },
[0x21] = { .simd_size = simd_other },
[0x22] = { .simd_size = simd_none },
@@ -1601,6 +1603,7 @@ static bool vcpu_has(
#define vcpu_has_popcnt() vcpu_has( 1, ECX, 23, ctxt, ops)
#define vcpu_has_aesni() vcpu_has( 1, ECX, 25, ctxt, ops)
#define vcpu_has_avx() vcpu_has( 1, ECX, 28, ctxt, ops)
+#define vcpu_has_f16c() vcpu_has( 1, ECX, 29, ctxt, ops)
#define vcpu_has_rdrand() vcpu_has( 1, ECX, 30, ctxt, ops)
#define vcpu_has_mmxext() (vcpu_has(0x80000001, EDX, 22, ctxt, ops) || \
vcpu_has_sse())
@@ -7216,6 +7219,12 @@ x86_emulate(
host_and_vcpu_must_have(sse4_1);
goto simd_0f38_common;
+ case X86EMUL_OPC_VEX_66(0x0f38, 0x13): /* vcvtph2ps xmm/mem,{x,y}mm */
+ generate_exception_if(vex.w, EXC_UD);
+ host_and_vcpu_must_have(f16c);
+ op_bytes = 8 << vex.l;
+ goto simd_0f_ymm;
+
case X86EMUL_OPC_VEX_66(0x0f38, 0x20): /* vpmovsxbw xmm/mem,{x,y}mm */
case X86EMUL_OPC_VEX_66(0x0f38, 0x21): /* vpmovsxbd xmm/mem,{x,y}mm */
case X86EMUL_OPC_VEX_66(0x0f38, 0x22): /* vpmovsxbq xmm/mem,{x,y}mm */
@@ -7607,6 +7616,50 @@ x86_emulate(
opc = init_prefixes(stub);
goto pextr;
+ case X86EMUL_OPC_VEX_66(0x0f3a, 0x1d): /* vcvtps2ph $imm8,{x,y}mm,xmm/mem */
+ {
+ uint32_t mxcsr;
+
+ generate_exception_if(vex.w || vex.reg != 0xf, EXC_UD);
+ host_and_vcpu_must_have(f16c);
+ fail_if(!ops->write);
+
+ opc = init_prefixes(stub);
+ opc[0] = b;
+ opc[1] = modrm;
+ if ( ea.type == OP_MEM )
+ {
+ /* Convert memory operand to (%rAX). */
+ vex.b = 1;
+ opc[1] &= 0x38;
+ }
+ opc[2] = imm1;
+ fic.insn_bytes = PFX_BYTES + 3;
+ opc[3] = 0xc3;
+
+ copy_VEX(opc, vex);
+ /* Latch MXCSR - we may need to restore it below. */
+ invoke_stub("stmxcsr %[mxcsr]", "",
+ "=m" (*mmvalp), "+m" (fic.exn_raised), [mxcsr] "=m" (mxcsr)
+ : "a" (mmvalp));
+
+ put_stub(stub);
+ check_xmm_exn(&fic);
+
+ if ( ea.type == OP_MEM )
+ {
+ rc = ops->write(ea.mem.seg, ea.mem.off, mmvalp, 8 << vex.l, ctxt);
+ if ( rc != X86EMUL_OKAY )
+ {
+ asm volatile ( "ldmxcsr %0" :: "m" (mxcsr) );
+ goto done;
+ }
+ }
+
+ state->simd_size = simd_none;
+ break;
+ }
+
case X86EMUL_OPC_66(0x0f3a, 0x20): /* pinsrb $imm8,r32/m8,xmm */
case X86EMUL_OPC_66(0x0f3a, 0x22): /* pinsr{d,q} $imm8,r/m,xmm */
host_and_vcpu_must_have(sse4_1);
--- a/xen/include/asm-x86/cpufeature.h
+++ b/xen/include/asm-x86/cpufeature.h
@@ -60,6 +60,7 @@
#define cpu_has_aesni boot_cpu_has(X86_FEATURE_AESNI)
#define cpu_has_xsave boot_cpu_has(X86_FEATURE_XSAVE)
#define cpu_has_avx boot_cpu_has(X86_FEATURE_AVX)
+#define cpu_has_f16c boot_cpu_has(X86_FEATURE_F16C)
#define cpu_has_rdrand boot_cpu_has(X86_FEATURE_RDRAND)
#define cpu_has_hypervisor boot_cpu_has(X86_FEATURE_HYPERVISOR)
[-- Attachment #3: Type: text/plain, Size: 127 bytes --]
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
next prev parent reply other threads:[~2017-06-21 12:01 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-06-21 11:23 [PATCH 00/17] x86: emulator enhancements Jan Beulich
2017-06-21 11:59 ` [PATCH 01/17] x86emul: support remaining AVX insns Jan Beulich
2017-09-13 15:02 ` George Dunlap
2017-09-13 15:31 ` Jan Beulich
2017-06-21 11:59 ` [PATCH 02/17] x86emul: re-order cases of main switch statement Jan Beulich
2017-09-13 15:15 ` George Dunlap
2017-06-21 12:00 ` [PATCH 03/17] x86emul: build SIMD tests with -Os Jan Beulich
2017-09-13 15:19 ` George Dunlap
2017-09-13 15:34 ` Jan Beulich
2017-06-21 12:01 ` Jan Beulich [this message]
2017-09-13 17:10 ` [PATCH 04/17] x86emul: support F16C insns George Dunlap
2017-09-14 9:13 ` George Dunlap
2017-09-14 10:24 ` Jan Beulich
2017-06-21 12:01 ` [PATCH 05/17] x86emul: support FMA4 insns Jan Beulich
2017-06-21 12:02 ` [PATCH 06/17] x86emul: support FMA insns Jan Beulich
2017-06-21 12:02 ` [PATCH 07/17] x86emul: support most remaining AVX2 insns Jan Beulich
2017-06-21 12:03 ` [PATCH 08/17] x86emul: fold/eliminate some local variables Jan Beulich
2017-06-21 12:04 ` [PATCH 09/17] x86emul: support AVX2 gather insns Jan Beulich
2017-06-21 12:04 ` [PATCH 10/17] x86emul: add tables for XOP 08 and 09 extension spaces Jan Beulich
2017-06-21 12:05 ` [PATCH 11/17] x86emul: support XOP insns Jan Beulich
2017-06-21 12:05 ` [PATCH 12/17] x86emul: support 3DNow! insns Jan Beulich
2017-06-21 12:06 ` [PATCH 13/17] x86emul: re-order checks in test harness Jan Beulich
2017-06-21 12:07 ` [PATCH 14/17] x86emul: abstract out XCRn accesses Jan Beulich
2017-06-21 12:07 ` [PATCH 15/17] x86emul: adjust_bnd() should check XCR0 Jan Beulich
2017-06-21 12:08 ` [PATCH 16/17] x86emul: make all FPU emulation use the stub Jan Beulich
2017-06-21 12:09 ` [PATCH 17/17] x86/HVM: eliminate custom #MF/#XM handling Jan Beulich
2017-09-05 17:08 ` [PATCH 00/17] x86: emulator enhancements George Dunlap
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=594A7C240200007800165322@prv-mh.provo.novell.com \
--to=jbeulich@suse.com \
--cc=andrew.cooper3@citrix.com \
--cc=xen-devel@lists.xenproject.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.