diff options
Diffstat (limited to 'tools/arch/x86/include')
| -rw-r--r-- | tools/arch/x86/include/asm/inat.h | 15 | ||||
| -rw-r--r-- | tools/arch/x86/include/asm/insn.h | 51 | ||||
| -rw-r--r-- | tools/arch/x86/include/asm/io.h | 101 | ||||
| -rw-r--r-- | tools/arch/x86/include/asm/msr-index.h | 14 | ||||
| -rw-r--r-- | tools/arch/x86/include/asm/special_insns.h | 27 |
5 files changed, 199 insertions, 9 deletions
diff --git a/tools/arch/x86/include/asm/inat.h b/tools/arch/x86/include/asm/inat.h index 183aa662b165..099e926595bd 100644 --- a/tools/arch/x86/include/asm/inat.h +++ b/tools/arch/x86/include/asm/inat.h @@ -37,6 +37,8 @@ #define INAT_PFX_EVEX 15 /* EVEX prefix */ /* x86-64 REX2 prefix */ #define INAT_PFX_REX2 16 /* 0xD5 */ +/* AMD XOP prefix */ +#define INAT_PFX_XOP 17 /* 0x8F */ #define INAT_LSTPFX_MAX 3 #define INAT_LGCPFX_MAX 11 @@ -77,6 +79,7 @@ #define INAT_MOFFSET (1 << (INAT_FLAG_OFFS + 3)) #define INAT_VARIANT (1 << (INAT_FLAG_OFFS + 4)) #define INAT_VEXOK (1 << (INAT_FLAG_OFFS + 5)) +#define INAT_XOPOK INAT_VEXOK #define INAT_VEXONLY (1 << (INAT_FLAG_OFFS + 6)) #define INAT_EVEXONLY (1 << (INAT_FLAG_OFFS + 7)) #define INAT_NO_REX2 (1 << (INAT_FLAG_OFFS + 8)) @@ -111,6 +114,8 @@ extern insn_attr_t inat_get_group_attribute(insn_byte_t modrm, extern insn_attr_t inat_get_avx_attribute(insn_byte_t opcode, insn_byte_t vex_m, insn_byte_t vex_pp); +extern insn_attr_t inat_get_xop_attribute(insn_byte_t opcode, + insn_byte_t map_select); /* Attribute checking functions */ static inline int inat_is_legacy_prefix(insn_attr_t attr) @@ -164,6 +169,11 @@ static inline int inat_is_vex3_prefix(insn_attr_t attr) return (attr & INAT_PFX_MASK) == INAT_PFX_VEX3; } +static inline int inat_is_xop_prefix(insn_attr_t attr) +{ + return (attr & INAT_PFX_MASK) == INAT_PFX_XOP; +} + static inline int inat_is_escape(insn_attr_t attr) { return attr & INAT_ESC_MASK; @@ -229,6 +239,11 @@ static inline int inat_accept_vex(insn_attr_t attr) return attr & INAT_VEXOK; } +static inline int inat_accept_xop(insn_attr_t attr) +{ + return attr & INAT_XOPOK; +} + static inline int inat_must_vex(insn_attr_t attr) { return attr & (INAT_VEXONLY | INAT_EVEXONLY); diff --git a/tools/arch/x86/include/asm/insn.h b/tools/arch/x86/include/asm/insn.h index 0e5abd896ad4..c683d609934b 100644 --- a/tools/arch/x86/include/asm/insn.h +++ b/tools/arch/x86/include/asm/insn.h @@ -71,7 +71,10 @@ struct insn { * prefixes.bytes[3]: last prefix */ struct insn_field rex_prefix; /* REX prefix */ - struct insn_field vex_prefix; /* VEX prefix */ + union { + struct insn_field vex_prefix; /* VEX prefix */ + struct insn_field xop_prefix; /* XOP prefix */ + }; struct insn_field opcode; /* * opcode.bytes[0]: opcode1 * opcode.bytes[1]: opcode2 @@ -135,6 +138,17 @@ struct insn { #define X86_VEX_V(vex) (((vex) & 0x78) >> 3) /* VEX3 Byte2, VEX2 Byte1 */ #define X86_VEX_P(vex) ((vex) & 0x03) /* VEX3 Byte2, VEX2 Byte1 */ #define X86_VEX_M_MAX 0x1f /* VEX3.M Maximum value */ +/* XOP bit fields */ +#define X86_XOP_R(xop) ((xop) & 0x80) /* XOP Byte2 */ +#define X86_XOP_X(xop) ((xop) & 0x40) /* XOP Byte2 */ +#define X86_XOP_B(xop) ((xop) & 0x20) /* XOP Byte2 */ +#define X86_XOP_M(xop) ((xop) & 0x1f) /* XOP Byte2 */ +#define X86_XOP_W(xop) ((xop) & 0x80) /* XOP Byte3 */ +#define X86_XOP_V(xop) ((xop) & 0x78) /* XOP Byte3 */ +#define X86_XOP_L(xop) ((xop) & 0x04) /* XOP Byte3 */ +#define X86_XOP_P(xop) ((xop) & 0x03) /* XOP Byte3 */ +#define X86_XOP_M_MIN 0x08 /* Min of XOP.M */ +#define X86_XOP_M_MAX 0x1f /* Max of XOP.M */ extern void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64); extern int insn_get_prefixes(struct insn *insn); @@ -178,7 +192,7 @@ static inline insn_byte_t insn_rex2_m_bit(struct insn *insn) return X86_REX2_M(insn->rex_prefix.bytes[1]); } -static inline int insn_is_avx(struct insn *insn) +static inline int insn_is_avx_or_xop(struct insn *insn) { if (!insn->prefixes.got) insn_get_prefixes(insn); @@ -192,6 +206,22 @@ static inline int insn_is_evex(struct insn *insn) return (insn->vex_prefix.nbytes == 4); } +/* If we already know this is AVX/XOP encoded */ +static inline int avx_insn_is_xop(struct insn *insn) +{ + insn_attr_t attr = inat_get_opcode_attribute(insn->vex_prefix.bytes[0]); + + return inat_is_xop_prefix(attr); +} + +static inline int insn_is_xop(struct insn *insn) +{ + if (!insn_is_avx_or_xop(insn)) + return 0; + + return avx_insn_is_xop(insn); +} + static inline int insn_has_emulate_prefix(struct insn *insn) { return !!insn->emulate_prefix_size; @@ -222,11 +252,26 @@ static inline insn_byte_t insn_vex_w_bit(struct insn *insn) return X86_VEX_W(insn->vex_prefix.bytes[2]); } +static inline insn_byte_t insn_xop_map_bits(struct insn *insn) +{ + if (insn->xop_prefix.nbytes < 3) /* XOP is 3 bytes */ + return 0; + return X86_XOP_M(insn->xop_prefix.bytes[1]); +} + +static inline insn_byte_t insn_xop_p_bits(struct insn *insn) +{ + return X86_XOP_P(insn->vex_prefix.bytes[2]); +} + /* Get the last prefix id from last prefix or VEX prefix */ static inline int insn_last_prefix_id(struct insn *insn) { - if (insn_is_avx(insn)) + if (insn_is_avx_or_xop(insn)) { + if (avx_insn_is_xop(insn)) + return insn_xop_p_bits(insn); return insn_vex_p_bits(insn); /* VEX_p is a SIMD prefix id */ + } if (insn->prefixes.bytes[3]) return inat_get_last_prefix_id(insn->prefixes.bytes[3]); diff --git a/tools/arch/x86/include/asm/io.h b/tools/arch/x86/include/asm/io.h new file mode 100644 index 000000000000..ecad61a3ea52 --- /dev/null +++ b/tools/arch/x86/include/asm/io.h @@ -0,0 +1,101 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _TOOLS_ASM_X86_IO_H +#define _TOOLS_ASM_X86_IO_H + +#include <linux/compiler.h> +#include <linux/types.h> +#include "special_insns.h" + +#define build_mmio_read(name, size, type, reg, barrier) \ +static inline type name(const volatile void __iomem *addr) \ +{ type ret; asm volatile("mov" size " %1,%0":reg (ret) \ +:"m" (*(volatile type __force *)addr) barrier); return ret; } + +#define build_mmio_write(name, size, type, reg, barrier) \ +static inline void name(type val, volatile void __iomem *addr) \ +{ asm volatile("mov" size " %0,%1": :reg (val), \ +"m" (*(volatile type __force *)addr) barrier); } + +build_mmio_read(readb, "b", unsigned char, "=q", :"memory") +build_mmio_read(readw, "w", unsigned short, "=r", :"memory") +build_mmio_read(readl, "l", unsigned int, "=r", :"memory") + +build_mmio_read(__readb, "b", unsigned char, "=q", ) +build_mmio_read(__readw, "w", unsigned short, "=r", ) +build_mmio_read(__readl, "l", unsigned int, "=r", ) + +build_mmio_write(writeb, "b", unsigned char, "q", :"memory") +build_mmio_write(writew, "w", unsigned short, "r", :"memory") +build_mmio_write(writel, "l", unsigned int, "r", :"memory") + +build_mmio_write(__writeb, "b", unsigned char, "q", ) +build_mmio_write(__writew, "w", unsigned short, "r", ) +build_mmio_write(__writel, "l", unsigned int, "r", ) + +#define readb readb +#define readw readw +#define readl readl +#define readb_relaxed(a) __readb(a) +#define readw_relaxed(a) __readw(a) +#define readl_relaxed(a) __readl(a) +#define __raw_readb __readb +#define __raw_readw __readw +#define __raw_readl __readl + +#define writeb writeb +#define writew writew +#define writel writel +#define writeb_relaxed(v, a) __writeb(v, a) +#define writew_relaxed(v, a) __writew(v, a) +#define writel_relaxed(v, a) __writel(v, a) +#define __raw_writeb __writeb +#define __raw_writew __writew +#define __raw_writel __writel + +#ifdef __x86_64__ + +build_mmio_read(readq, "q", u64, "=r", :"memory") +build_mmio_read(__readq, "q", u64, "=r", ) +build_mmio_write(writeq, "q", u64, "r", :"memory") +build_mmio_write(__writeq, "q", u64, "r", ) + +#define readq_relaxed(a) __readq(a) +#define writeq_relaxed(v, a) __writeq(v, a) + +#define __raw_readq __readq +#define __raw_writeq __writeq + +/* Let people know that we have them */ +#define readq readq +#define writeq writeq + +#endif /* __x86_64__ */ + +#include <asm-generic/io.h> + +/** + * iosubmit_cmds512 - copy data to single MMIO location, in 512-bit units + * @dst: destination, in MMIO space (must be 512-bit aligned) + * @src: source + * @count: number of 512 bits quantities to submit + * + * Submit data from kernel space to MMIO space, in units of 512 bits at a + * time. Order of access is not guaranteed, nor is a memory barrier + * performed afterwards. + * + * Warning: Do not use this helper unless your driver has checked that the CPU + * instruction is supported on the platform. + */ +static inline void iosubmit_cmds512(void __iomem *dst, const void *src, + size_t count) +{ + const u8 *from = src; + const u8 *end = from + count * 64; + + while (from < end) { + movdir64b(dst, from); + from += 64; + } +} + +#endif /* _TOOLS_ASM_X86_IO_H */ diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index b65c3ba5fa14..f627196eb796 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -315,12 +315,14 @@ #define PERF_CAP_PT_IDX 16 #define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6 -#define PERF_CAP_PEBS_TRAP BIT_ULL(6) -#define PERF_CAP_ARCH_REG BIT_ULL(7) -#define PERF_CAP_PEBS_FORMAT 0xf00 -#define PERF_CAP_PEBS_BASELINE BIT_ULL(14) -#define PERF_CAP_PEBS_MASK (PERF_CAP_PEBS_TRAP | PERF_CAP_ARCH_REG | \ - PERF_CAP_PEBS_FORMAT | PERF_CAP_PEBS_BASELINE) +#define PERF_CAP_PEBS_TRAP BIT_ULL(6) +#define PERF_CAP_ARCH_REG BIT_ULL(7) +#define PERF_CAP_PEBS_FORMAT 0xf00 +#define PERF_CAP_PEBS_BASELINE BIT_ULL(14) +#define PERF_CAP_PEBS_TIMING_INFO BIT_ULL(17) +#define PERF_CAP_PEBS_MASK (PERF_CAP_PEBS_TRAP | PERF_CAP_ARCH_REG | \ + PERF_CAP_PEBS_FORMAT | PERF_CAP_PEBS_BASELINE | \ + PERF_CAP_PEBS_TIMING_INFO) #define MSR_IA32_RTIT_CTL 0x00000570 #define RTIT_CTL_TRACEEN BIT(0) diff --git a/tools/arch/x86/include/asm/special_insns.h b/tools/arch/x86/include/asm/special_insns.h new file mode 100644 index 000000000000..04af42a99c38 --- /dev/null +++ b/tools/arch/x86/include/asm/special_insns.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _TOOLS_ASM_X86_SPECIAL_INSNS_H +#define _TOOLS_ASM_X86_SPECIAL_INSNS_H + +/* The dst parameter must be 64-bytes aligned */ +static inline void movdir64b(void *dst, const void *src) +{ + const struct { char _[64]; } *__src = src; + struct { char _[64]; } *__dst = dst; + + /* + * MOVDIR64B %(rdx), rax. + * + * Both __src and __dst must be memory constraints in order to tell the + * compiler that no other memory accesses should be reordered around + * this one. + * + * Also, both must be supplied as lvalues because this tells + * the compiler what the object is (its size) the instruction accesses. + * I.e., not the pointers but what they point to, thus the deref'ing '*'. + */ + asm volatile(".byte 0x66, 0x0f, 0x38, 0xf8, 0x02" + : "+m" (*__dst) + : "m" (*__src), "a" (__dst), "d" (__src)); +} + +#endif /* _TOOLS_ASM_X86_SPECIAL_INSNS_H */ |