From 2bb4ccbd95d7fbf58540c8d3d55cbabc8fb95e28 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Wed, 24 Feb 2021 09:48:31 -0700 Subject: tools headers UAPI: Update tools' copy of linux/coresight-pmu.h To get the changes in the commit: "coresight: etm-perf: Clarify comment on perf options". Signed-off-by: Leo Yan Reviewed-by: Suzuki K Poulose Reviewed-by: Mathieu Poirier Cc: Mike Leach Link: https://lore.kernel.org/r/20210213113220.292229-2-leo.yan@linaro.org Link: https://lore.kernel.org/r/20210224164835.3497311-3-mathieu.poirier@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/linux/coresight-pmu.h | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) (limited to 'tools/include/linux') diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h index b0e35eec6499..5dc47cfdcf07 100644 --- a/tools/include/linux/coresight-pmu.h +++ b/tools/include/linux/coresight-pmu.h @@ -10,11 +10,18 @@ #define CORESIGHT_ETM_PMU_NAME "cs_etm" #define CORESIGHT_ETM_PMU_SEED 0x10 -/* ETMv3.5/PTM's ETMCR config bit */ -#define ETM_OPT_CYCACC 12 -#define ETM_OPT_CTXTID 14 -#define ETM_OPT_TS 28 -#define ETM_OPT_RETSTK 29 +/* + * Below are the definition of bit offsets for perf option, and works as + * arbitrary values for all ETM versions. + * + * Most of them are orignally from ETMv3.5/PTM's ETMCR config, therefore, + * ETMv3.5/PTM doesn't define ETMCR config bits with prefix "ETM3_" and + * directly use below macros as config bits. + */ +#define ETM_OPT_CYCACC 12 +#define ETM_OPT_CTXTID 14 +#define ETM_OPT_TS 28 +#define ETM_OPT_RETSTK 29 /* ETMv4 CONFIGR programming bits for the ETM OPTs */ #define ETM4_CFG_BIT_CYCACC 4 -- cgit From 30cb76aabfb4deab4ffef54882f86df319b4d862 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Wed, 24 Feb 2021 09:48:33 -0700 Subject: perf cs-etm: Support PID tracing in config If the kernel is running at EL2, the pid of a task is exposed via VMID instead of the CONTEXTID. Add support for this in the perf tool. This patch respects user setting if user has specified any configs from "contextid", "contextid1" or "contextid2"; otherwise, it dynamically sets config based on PMU format "contextid". Signed-off-by: Suzuki K Poulose Co-developed-by: Leo Yan Signed-off-by: Leo Yan Reviewed-by: Mike Leach Reviewed-by: Mathieu Poirier Cc: Al Grant Link: https://lore.kernel.org/r/20210213113220.292229-4-leo.yan@linaro.org Link: https://lore.kernel.org/r/20210224164835.3497311-5-mathieu.poirier@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/linux/coresight-pmu.h | 3 ++ tools/perf/arch/arm/util/cs-etm.c | 61 +++++++++++++++++++++++++++++-------- 2 files changed, 52 insertions(+), 12 deletions(-) (limited to 'tools/include/linux') diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h index 5dc47cfdcf07..4ac5c081af93 100644 --- a/tools/include/linux/coresight-pmu.h +++ b/tools/include/linux/coresight-pmu.h @@ -20,14 +20,17 @@ */ #define ETM_OPT_CYCACC 12 #define ETM_OPT_CTXTID 14 +#define ETM_OPT_CTXTID2 15 #define ETM_OPT_TS 28 #define ETM_OPT_RETSTK 29 /* ETMv4 CONFIGR programming bits for the ETM OPTs */ #define ETM4_CFG_BIT_CYCACC 4 #define ETM4_CFG_BIT_CTXTID 6 +#define ETM4_CFG_BIT_VMID 7 #define ETM4_CFG_BIT_TS 11 #define ETM4_CFG_BIT_RETSTK 12 +#define ETM4_CFG_BIT_VMID_OPT 15 static inline int coresight_get_trace_id(int cpu) { diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 5b2bb7fc5ee1..911c7f2b3581 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -67,6 +67,7 @@ static int cs_etm_set_context_id(struct auxtrace_record *itr, char path[PATH_MAX]; int err = -EINVAL; u32 val; + u64 contextid; ptr = container_of(itr, struct cs_etm_recording, itr); cs_etm_pmu = ptr->cs_etm_pmu; @@ -86,25 +87,59 @@ static int cs_etm_set_context_id(struct auxtrace_record *itr, goto out; } + /* User has configured for PID tracing, respects it. */ + contextid = evsel->core.attr.config & + (BIT(ETM_OPT_CTXTID) | BIT(ETM_OPT_CTXTID2)); + /* - * TRCIDR2.CIDSIZE, bit [9-5], indicates whether contextID tracing - * is supported: - * 0b00000 Context ID tracing is not supported. - * 0b00100 Maximum of 32-bit Context ID size. - * All other values are reserved. + * If user doesn't configure the contextid format, parse PMU format and + * enable PID tracing according to the "contextid" format bits: + * + * If bit ETM_OPT_CTXTID is set, trace CONTEXTIDR_EL1; + * If bit ETM_OPT_CTXTID2 is set, trace CONTEXTIDR_EL2. */ - val = BMVAL(val, 5, 9); - if (!val || val != 0x4) { - err = -EINVAL; - goto out; + if (!contextid) + contextid = perf_pmu__format_bits(&cs_etm_pmu->format, + "contextid"); + + if (contextid & BIT(ETM_OPT_CTXTID)) { + /* + * TRCIDR2.CIDSIZE, bit [9-5], indicates whether contextID + * tracing is supported: + * 0b00000 Context ID tracing is not supported. + * 0b00100 Maximum of 32-bit Context ID size. + * All other values are reserved. + */ + val = BMVAL(val, 5, 9); + if (!val || val != 0x4) { + pr_err("%s: CONTEXTIDR_EL1 isn't supported\n", + CORESIGHT_ETM_PMU_NAME); + err = -EINVAL; + goto out; + } + } + + if (contextid & BIT(ETM_OPT_CTXTID2)) { + /* + * TRCIDR2.VMIDOPT[30:29] != 0 and + * TRCIDR2.VMIDSIZE[14:10] == 0b00100 (32bit virtual contextid) + * We can't support CONTEXTIDR in VMID if the size of the + * virtual context id is < 32bit. + * Any value of VMIDSIZE >= 4 (i.e, > 32bit) is fine for us. + */ + if (!BMVAL(val, 29, 30) || BMVAL(val, 10, 14) < 4) { + pr_err("%s: CONTEXTIDR_EL2 isn't supported\n", + CORESIGHT_ETM_PMU_NAME); + err = -EINVAL; + goto out; + } } /* All good, let the kernel know */ - evsel->core.attr.config |= (1 << ETM_OPT_CTXTID); + evsel->core.attr.config |= contextid; err = 0; out: - return err; } @@ -485,7 +520,9 @@ static u64 cs_etmv4_get_config(struct auxtrace_record *itr) config |= BIT(ETM4_CFG_BIT_TS); if (config_opts & BIT(ETM_OPT_RETSTK)) config |= BIT(ETM4_CFG_BIT_RETSTK); - + if (config_opts & BIT(ETM_OPT_CTXTID2)) + config |= BIT(ETM4_CFG_BIT_VMID) | + BIT(ETM4_CFG_BIT_VMID_OPT); return config; } -- cgit From 2942a671a37b61186e1073c76a17b1a631111f83 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 7 Mar 2021 14:30:24 -0800 Subject: tools include: Add __sum16 and __wsum definitions. This adds definitions available in the uapi version. Explanation: In the kernel include of types.h the uapi version is included. In tools the uapi/linux/types.h and linux/types.h are distinct. For BPF programs a definition of __wsum is needed by the generated bpf_helpers.h. The definition comes either from a generated vmlinux.h or from that may be transitively included from bpf.h. The perf build prefers linux/types.h over uapi/linux/types.h for *. To allow tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c to compile with the same include path used for perf then these definitions are necessary. There is likely a wider conversation about exactly how types.h should be specified and the include order used by the perf build - it is somewhat confusing that tools/include/uapi/linux/bpf.h is using the non-uapi types.h. *see tools/perf/Makefile.config: ... INC_FLAGS += -I$(srctree)/tools/include/ INC_FLAGS += -I$(srctree)/tools/arch/$(SRCARCH)/include/uapi INC_FLAGS += -I$(srctree)/tools/include/uapi ... The include directories are scanned from left-to-right: https://gcc.gnu.org/onlinedocs/gcc/Directory-Options.html As tools/include/linux/types.h appears before tools/include/uapi/linux/types.h then I say it is preferred. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Alexei Starovoitov Cc: Andrii Nakryiko Cc: Daniel Borkmann Cc: Jiri Olsa Cc: John Fastabend Cc: KP Singh Cc: Mark Rutland Cc: Martin KaFai Lau Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Song Liu Cc: Stephane Eranian Cc: Tiezhu Yang Cc: Yonghong Song Cc: bpf@vger.kernel.org Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20210307223024.4081067-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/linux/types.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'tools/include/linux') diff --git a/tools/include/linux/types.h b/tools/include/linux/types.h index e9c5a215837d..6e14a533ab4e 100644 --- a/tools/include/linux/types.h +++ b/tools/include/linux/types.h @@ -61,6 +61,9 @@ typedef __u32 __bitwise __be32; typedef __u64 __bitwise __le64; typedef __u64 __bitwise __be64; +typedef __u16 __bitwise __sum16; +typedef __u32 __bitwise __wsum; + typedef struct { int counter; } atomic_t; -- cgit From b046664872dd78a8bebe3d5f3bb9da9baa93f5ca Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Thu, 11 Mar 2021 15:23:07 +0100 Subject: static_call: Move struct static_call_key definition to static_call_types.h Having the definition of static_call() in static_call_types.h makes no sense as long struct static_call_key isn't defined there, as the generic implementation of static_call() is referencing this structure. So move the definition of struct static_call_key to static_call_types.h. Signed-off-by: Juergen Gross Signed-off-by: Borislav Petkov Acked-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210311142319.4723-3-jgross@suse.com --- include/linux/static_call.h | 18 ------------------ include/linux/static_call_types.h | 18 ++++++++++++++++++ tools/include/linux/static_call_types.h | 18 ++++++++++++++++++ 3 files changed, 36 insertions(+), 18 deletions(-) (limited to 'tools/include/linux') diff --git a/include/linux/static_call.h b/include/linux/static_call.h index 85ecc789f4ff..76b881259144 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -128,16 +128,6 @@ struct static_call_mod { struct static_call_site *sites; }; -struct static_call_key { - void *func; - union { - /* bit 0: 0 = mods, 1 = sites */ - unsigned long type; - struct static_call_mod *mods; - struct static_call_site *sites; - }; -}; - /* For finding the key associated with a trampoline */ struct static_call_tramp_key { s32 tramp; @@ -187,10 +177,6 @@ extern long __static_call_return0(void); static inline int static_call_init(void) { return 0; } -struct static_call_key { - void *func; -}; - #define __DEFINE_STATIC_CALL(name, _func, _func_init) \ DECLARE_STATIC_CALL(name, _func); \ struct static_call_key STATIC_CALL_KEY(name) = { \ @@ -243,10 +229,6 @@ static inline long __static_call_return0(void) static inline int static_call_init(void) { return 0; } -struct static_call_key { - void *func; -}; - static inline long __static_call_return0(void) { return 0; diff --git a/include/linux/static_call_types.h b/include/linux/static_call_types.h index ae5662d368b9..5a00b8b2cf9f 100644 --- a/include/linux/static_call_types.h +++ b/include/linux/static_call_types.h @@ -58,11 +58,25 @@ struct static_call_site { __raw_static_call(name); \ }) +struct static_call_key { + void *func; + union { + /* bit 0: 0 = mods, 1 = sites */ + unsigned long type; + struct static_call_mod *mods; + struct static_call_site *sites; + }; +}; + #else /* !CONFIG_HAVE_STATIC_CALL_INLINE */ #define __STATIC_CALL_ADDRESSABLE(name) #define __static_call(name) __raw_static_call(name) +struct static_call_key { + void *func; +}; + #endif /* CONFIG_HAVE_STATIC_CALL_INLINE */ #ifdef MODULE @@ -77,6 +91,10 @@ struct static_call_site { #else +struct static_call_key { + void *func; +}; + #define static_call(name) \ ((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func)) diff --git a/tools/include/linux/static_call_types.h b/tools/include/linux/static_call_types.h index ae5662d368b9..5a00b8b2cf9f 100644 --- a/tools/include/linux/static_call_types.h +++ b/tools/include/linux/static_call_types.h @@ -58,11 +58,25 @@ struct static_call_site { __raw_static_call(name); \ }) +struct static_call_key { + void *func; + union { + /* bit 0: 0 = mods, 1 = sites */ + unsigned long type; + struct static_call_mod *mods; + struct static_call_site *sites; + }; +}; + #else /* !CONFIG_HAVE_STATIC_CALL_INLINE */ #define __STATIC_CALL_ADDRESSABLE(name) #define __static_call(name) __raw_static_call(name) +struct static_call_key { + void *func; +}; + #endif /* CONFIG_HAVE_STATIC_CALL_INLINE */ #ifdef MODULE @@ -77,6 +91,10 @@ struct static_call_site { #else +struct static_call_key { + void *func; +}; + #define static_call(name) \ ((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func)) -- cgit From 93281c4a96572a34504244969b938e035204778d Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Tue, 3 Nov 2020 17:28:30 +0100 Subject: x86/insn: Add an insn_decode() API Users of the instruction decoder should use this to decode instruction bytes. For that, have insn*() helpers return an int value to denote success/failure. When there's an error fetching the next insn byte and the insn falls short, return -ENODATA to denote that. While at it, make insn_get_opcode() more stricter as to whether what has seen so far is a valid insn and if not. Copy linux/kconfig.h for the tools-version of the decoder so that it can use IS_ENABLED(). Also, cast the INSN_MODE_KERN dummy define value to (enum insn_mode) for tools use of the decoder because perf tool builds with -Werror and errors out with -Werror=sign-compare otherwise. Signed-off-by: Borislav Petkov Acked-by: Masami Hiramatsu Link: https://lkml.kernel.org/r/20210304174237.31945-5-bp@alien8.de --- arch/x86/include/asm/insn.h | 24 +++-- arch/x86/lib/insn.c | 216 +++++++++++++++++++++++++++++-------- tools/arch/x86/include/asm/insn.h | 24 +++-- tools/arch/x86/lib/insn.c | 222 +++++++++++++++++++++++++++++--------- tools/include/linux/kconfig.h | 73 +++++++++++++ 5 files changed, 452 insertions(+), 107 deletions(-) create mode 100644 tools/include/linux/kconfig.h (limited to 'tools/include/linux') diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h index 93f84600ac2c..de9fe760c1e7 100644 --- a/arch/x86/include/asm/insn.h +++ b/arch/x86/include/asm/insn.h @@ -132,13 +132,23 @@ struct insn { #define X86_VEX_M_MAX 0x1f /* VEX3.M Maximum value */ extern void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64); -extern void insn_get_prefixes(struct insn *insn); -extern void insn_get_opcode(struct insn *insn); -extern void insn_get_modrm(struct insn *insn); -extern void insn_get_sib(struct insn *insn); -extern void insn_get_displacement(struct insn *insn); -extern void insn_get_immediate(struct insn *insn); -extern void insn_get_length(struct insn *insn); +extern int insn_get_prefixes(struct insn *insn); +extern int insn_get_opcode(struct insn *insn); +extern int insn_get_modrm(struct insn *insn); +extern int insn_get_sib(struct insn *insn); +extern int insn_get_displacement(struct insn *insn); +extern int insn_get_immediate(struct insn *insn); +extern int insn_get_length(struct insn *insn); + +enum insn_mode { + INSN_MODE_32, + INSN_MODE_64, + /* Mode is determined by the current kernel build. */ + INSN_MODE_KERN, + INSN_NUM_MODES, +}; + +extern int insn_decode(struct insn *insn, const void *kaddr, int buf_len, enum insn_mode m); /* Attribute will be determined after getting ModRM (for opcode groups) */ static inline void insn_get_attribute(struct insn *insn) diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c index ed1e0335aa14..bb58004497f8 100644 --- a/arch/x86/lib/insn.c +++ b/arch/x86/lib/insn.c @@ -14,6 +14,9 @@ #include /*__ignore_sync_check__ */ #include /* __ignore_sync_check__ */ +#include +#include + #include /* __ignore_sync_check__ */ #define leXX_to_cpu(t, r) \ @@ -112,8 +115,12 @@ static void insn_get_emulate_prefix(struct insn *insn) * Populates the @insn->prefixes bitmap, and updates @insn->next_byte * to point to the (first) opcode. No effect if @insn->prefixes.got * is already set. + * + * * Returns: + * 0: on success + * < 0: on error */ -void insn_get_prefixes(struct insn *insn) +int insn_get_prefixes(struct insn *insn) { struct insn_field *prefixes = &insn->prefixes; insn_attr_t attr; @@ -121,7 +128,7 @@ void insn_get_prefixes(struct insn *insn) int i, nb; if (prefixes->got) - return; + return 0; insn_get_emulate_prefix(insn); @@ -231,8 +238,10 @@ vex_end: prefixes->got = 1; + return 0; + err_out: - return; + return -ENODATA; } /** @@ -244,16 +253,25 @@ err_out: * If necessary, first collects any preceding (prefix) bytes. * Sets @insn->opcode.value = opcode1. No effect if @insn->opcode.got * is already 1. + * + * Returns: + * 0: on success + * < 0: on error */ -void insn_get_opcode(struct insn *insn) +int insn_get_opcode(struct insn *insn) { struct insn_field *opcode = &insn->opcode; + int pfx_id, ret; insn_byte_t op; - int pfx_id; + if (opcode->got) - return; - if (!insn->prefixes.got) - insn_get_prefixes(insn); + return 0; + + if (!insn->prefixes.got) { + ret = insn_get_prefixes(insn); + if (ret) + return ret; + } /* Get first opcode */ op = get_next(insn_byte_t, insn); @@ -268,9 +286,13 @@ void insn_get_opcode(struct insn *insn) insn->attr = inat_get_avx_attribute(op, m, p); if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) || (!inat_accept_vex(insn->attr) && - !inat_is_group(insn->attr))) - insn->attr = 0; /* This instruction is bad */ - goto end; /* VEX has only 1 byte for opcode */ + !inat_is_group(insn->attr))) { + /* This instruction is bad */ + insn->attr = 0; + return -EINVAL; + } + /* VEX has only 1 byte for opcode */ + goto end; } insn->attr = inat_get_opcode_attribute(op); @@ -281,13 +303,18 @@ void insn_get_opcode(struct insn *insn) pfx_id = insn_last_prefix_id(insn); insn->attr = inat_get_escape_attribute(op, pfx_id, insn->attr); } - if (inat_must_vex(insn->attr)) - insn->attr = 0; /* This instruction is bad */ + + if (inat_must_vex(insn->attr)) { + /* This instruction is bad */ + insn->attr = 0; + return -EINVAL; + } end: opcode->got = 1; + return 0; err_out: - return; + return -ENODATA; } /** @@ -297,15 +324,25 @@ err_out: * Populates @insn->modrm and updates @insn->next_byte to point past the * ModRM byte, if any. If necessary, first collects the preceding bytes * (prefixes and opcode(s)). No effect if @insn->modrm.got is already 1. + * + * Returns: + * 0: on success + * < 0: on error */ -void insn_get_modrm(struct insn *insn) +int insn_get_modrm(struct insn *insn) { struct insn_field *modrm = &insn->modrm; insn_byte_t pfx_id, mod; + int ret; + if (modrm->got) - return; - if (!insn->opcode.got) - insn_get_opcode(insn); + return 0; + + if (!insn->opcode.got) { + ret = insn_get_opcode(insn); + if (ret) + return ret; + } if (inat_has_modrm(insn->attr)) { mod = get_next(insn_byte_t, insn); @@ -314,17 +351,22 @@ void insn_get_modrm(struct insn *insn) pfx_id = insn_last_prefix_id(insn); insn->attr = inat_get_group_attribute(mod, pfx_id, insn->attr); - if (insn_is_avx(insn) && !inat_accept_vex(insn->attr)) - insn->attr = 0; /* This is bad */ + if (insn_is_avx(insn) && !inat_accept_vex(insn->attr)) { + /* Bad insn */ + insn->attr = 0; + return -EINVAL; + } } } if (insn->x86_64 && inat_is_force64(insn->attr)) insn->opnd_bytes = 8; + modrm->got = 1; + return 0; err_out: - return; + return -ENODATA; } @@ -338,11 +380,16 @@ err_out: int insn_rip_relative(struct insn *insn) { struct insn_field *modrm = &insn->modrm; + int ret; if (!insn->x86_64) return 0; - if (!modrm->got) - insn_get_modrm(insn); + + if (!modrm->got) { + ret = insn_get_modrm(insn); + if (ret) + return 0; + } /* * For rip-relative instructions, the mod field (top 2 bits) * is zero and the r/m field (bottom 3 bits) is 0x5. @@ -356,15 +403,25 @@ int insn_rip_relative(struct insn *insn) * * If necessary, first collects the instruction up to and including the * ModRM byte. + * + * Returns: + * 0: if decoding succeeded + * < 0: otherwise. */ -void insn_get_sib(struct insn *insn) +int insn_get_sib(struct insn *insn) { insn_byte_t modrm; + int ret; if (insn->sib.got) - return; - if (!insn->modrm.got) - insn_get_modrm(insn); + return 0; + + if (!insn->modrm.got) { + ret = insn_get_modrm(insn); + if (ret) + return ret; + } + if (insn->modrm.nbytes) { modrm = insn->modrm.bytes[0]; if (insn->addr_bytes != 2 && @@ -375,8 +432,10 @@ void insn_get_sib(struct insn *insn) } insn->sib.got = 1; + return 0; + err_out: - return; + return -ENODATA; } @@ -387,15 +446,25 @@ err_out: * If necessary, first collects the instruction up to and including the * SIB byte. * Displacement value is sign-expanded. + * + * * Returns: + * 0: if decoding succeeded + * < 0: otherwise. */ -void insn_get_displacement(struct insn *insn) +int insn_get_displacement(struct insn *insn) { insn_byte_t mod, rm, base; + int ret; if (insn->displacement.got) - return; - if (!insn->sib.got) - insn_get_sib(insn); + return 0; + + if (!insn->sib.got) { + ret = insn_get_sib(insn); + if (ret) + return ret; + } + if (insn->modrm.nbytes) { /* * Interpreting the modrm byte: @@ -437,9 +506,10 @@ void insn_get_displacement(struct insn *insn) } out: insn->displacement.got = 1; + return 0; err_out: - return; + return -ENODATA; } /* Decode moffset16/32/64. Return 0 if failed */ @@ -538,20 +608,30 @@ err_out: } /** - * insn_get_immediate() - Get the immediates of instruction + * insn_get_immediate() - Get the immediate in an instruction * @insn: &struct insn containing instruction * * If necessary, first collects the instruction up to and including the * displacement bytes. * Basically, most of immediates are sign-expanded. Unsigned-value can be - * get by bit masking with ((1 << (nbytes * 8)) - 1) + * computed by bit masking with ((1 << (nbytes * 8)) - 1) + * + * Returns: + * 0: on success + * < 0: on error */ -void insn_get_immediate(struct insn *insn) +int insn_get_immediate(struct insn *insn) { + int ret; + if (insn->immediate.got) - return; - if (!insn->displacement.got) - insn_get_displacement(insn); + return 0; + + if (!insn->displacement.got) { + ret = insn_get_displacement(insn); + if (ret) + return ret; + } if (inat_has_moffset(insn->attr)) { if (!__get_moffset(insn)) @@ -598,9 +678,10 @@ void insn_get_immediate(struct insn *insn) } done: insn->immediate.got = 1; + return 0; err_out: - return; + return -ENODATA; } /** @@ -609,13 +690,58 @@ err_out: * * If necessary, first collects the instruction up to and including the * immediates bytes. - */ -void insn_get_length(struct insn *insn) + * + * Returns: + * - 0 on success + * - < 0 on error +*/ +int insn_get_length(struct insn *insn) { + int ret; + if (insn->length) - return; - if (!insn->immediate.got) - insn_get_immediate(insn); + return 0; + + if (!insn->immediate.got) { + ret = insn_get_immediate(insn); + if (ret) + return ret; + } + insn->length = (unsigned char)((unsigned long)insn->next_byte - (unsigned long)insn->kaddr); + + return 0; +} + +/** + * insn_decode() - Decode an x86 instruction + * @insn: &struct insn to be initialized + * @kaddr: address (in kernel memory) of instruction (or copy thereof) + * @buf_len: length of the insn buffer at @kaddr + * @m: insn mode, see enum insn_mode + * + * Returns: + * 0: if decoding succeeded + * < 0: otherwise. + */ +int insn_decode(struct insn *insn, const void *kaddr, int buf_len, enum insn_mode m) +{ + int ret; + +/* #define INSN_MODE_KERN -1 __ignore_sync_check__ mode is only valid in the kernel */ + + if (m == INSN_MODE_KERN) + insn_init(insn, kaddr, buf_len, IS_ENABLED(CONFIG_X86_64)); + else + insn_init(insn, kaddr, buf_len, m == INSN_MODE_64); + + ret = insn_get_length(insn); + if (ret) + return ret; + + if (insn_complete(insn)) + return 0; + + return -EINVAL; } diff --git a/tools/arch/x86/include/asm/insn.h b/tools/arch/x86/include/asm/insn.h index 7e1239aa7dd9..2fe19b1a8765 100644 --- a/tools/arch/x86/include/asm/insn.h +++ b/tools/arch/x86/include/asm/insn.h @@ -132,13 +132,23 @@ struct insn { #define X86_VEX_M_MAX 0x1f /* VEX3.M Maximum value */ extern void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64); -extern void insn_get_prefixes(struct insn *insn); -extern void insn_get_opcode(struct insn *insn); -extern void insn_get_modrm(struct insn *insn); -extern void insn_get_sib(struct insn *insn); -extern void insn_get_displacement(struct insn *insn); -extern void insn_get_immediate(struct insn *insn); -extern void insn_get_length(struct insn *insn); +extern int insn_get_prefixes(struct insn *insn); +extern int insn_get_opcode(struct insn *insn); +extern int insn_get_modrm(struct insn *insn); +extern int insn_get_sib(struct insn *insn); +extern int insn_get_displacement(struct insn *insn); +extern int insn_get_immediate(struct insn *insn); +extern int insn_get_length(struct insn *insn); + +enum insn_mode { + INSN_MODE_32, + INSN_MODE_64, + /* Mode is determined by the current kernel build. */ + INSN_MODE_KERN, + INSN_NUM_MODES, +}; + +extern int insn_decode(struct insn *insn, const void *kaddr, int buf_len, enum insn_mode m); /* Attribute will be determined after getting ModRM (for opcode groups) */ static inline void insn_get_attribute(struct insn *insn) diff --git a/tools/arch/x86/lib/insn.c b/tools/arch/x86/lib/insn.c index 1174c43b3944..be2b057f91d4 100644 --- a/tools/arch/x86/lib/insn.c +++ b/tools/arch/x86/lib/insn.c @@ -11,10 +11,13 @@ #else #include #endif -#include "../include/asm/inat.h" /* __ignore_sync_check__ */ -#include "../include/asm/insn.h" /* __ignore_sync_check__ */ +#include /*__ignore_sync_check__ */ +#include /* __ignore_sync_check__ */ -#include "../include/asm/emulate_prefix.h" /* __ignore_sync_check__ */ +#include +#include + +#include /* __ignore_sync_check__ */ #define leXX_to_cpu(t, r) \ ({ \ @@ -112,8 +115,12 @@ static void insn_get_emulate_prefix(struct insn *insn) * Populates the @insn->prefixes bitmap, and updates @insn->next_byte * to point to the (first) opcode. No effect if @insn->prefixes.got * is already set. + * + * * Returns: + * 0: on success + * < 0: on error */ -void insn_get_prefixes(struct insn *insn) +int insn_get_prefixes(struct insn *insn) { struct insn_field *prefixes = &insn->prefixes; insn_attr_t attr; @@ -121,7 +128,7 @@ void insn_get_prefixes(struct insn *insn) int i, nb; if (prefixes->got) - return; + return 0; insn_get_emulate_prefix(insn); @@ -231,8 +238,10 @@ vex_end: prefixes->got = 1; + return 0; + err_out: - return; + return -ENODATA; } /** @@ -244,16 +253,25 @@ err_out: * If necessary, first collects any preceding (prefix) bytes. * Sets @insn->opcode.value = opcode1. No effect if @insn->opcode.got * is already 1. + * + * Returns: + * 0: on success + * < 0: on error */ -void insn_get_opcode(struct insn *insn) +int insn_get_opcode(struct insn *insn) { struct insn_field *opcode = &insn->opcode; + int pfx_id, ret; insn_byte_t op; - int pfx_id; + if (opcode->got) - return; - if (!insn->prefixes.got) - insn_get_prefixes(insn); + return 0; + + if (!insn->prefixes.got) { + ret = insn_get_prefixes(insn); + if (ret) + return ret; + } /* Get first opcode */ op = get_next(insn_byte_t, insn); @@ -268,9 +286,13 @@ void insn_get_opcode(struct insn *insn) insn->attr = inat_get_avx_attribute(op, m, p); if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) || (!inat_accept_vex(insn->attr) && - !inat_is_group(insn->attr))) - insn->attr = 0; /* This instruction is bad */ - goto end; /* VEX has only 1 byte for opcode */ + !inat_is_group(insn->attr))) { + /* This instruction is bad */ + insn->attr = 0; + return -EINVAL; + } + /* VEX has only 1 byte for opcode */ + goto end; } insn->attr = inat_get_opcode_attribute(op); @@ -281,13 +303,18 @@ void insn_get_opcode(struct insn *insn) pfx_id = insn_last_prefix_id(insn); insn->attr = inat_get_escape_attribute(op, pfx_id, insn->attr); } - if (inat_must_vex(insn->attr)) - insn->attr = 0; /* This instruction is bad */ + + if (inat_must_vex(insn->attr)) { + /* This instruction is bad */ + insn->attr = 0; + return -EINVAL; + } end: opcode->got = 1; + return 0; err_out: - return; + return -ENODATA; } /** @@ -297,15 +324,25 @@ err_out: * Populates @insn->modrm and updates @insn->next_byte to point past the * ModRM byte, if any. If necessary, first collects the preceding bytes * (prefixes and opcode(s)). No effect if @insn->modrm.got is already 1. + * + * Returns: + * 0: on success + * < 0: on error */ -void insn_get_modrm(struct insn *insn) +int insn_get_modrm(struct insn *insn) { struct insn_field *modrm = &insn->modrm; insn_byte_t pfx_id, mod; + int ret; + if (modrm->got) - return; - if (!insn->opcode.got) - insn_get_opcode(insn); + return 0; + + if (!insn->opcode.got) { + ret = insn_get_opcode(insn); + if (ret) + return ret; + } if (inat_has_modrm(insn->attr)) { mod = get_next(insn_byte_t, insn); @@ -314,17 +351,22 @@ void insn_get_modrm(struct insn *insn) pfx_id = insn_last_prefix_id(insn); insn->attr = inat_get_group_attribute(mod, pfx_id, insn->attr); - if (insn_is_avx(insn) && !inat_accept_vex(insn->attr)) - insn->attr = 0; /* This is bad */ + if (insn_is_avx(insn) && !inat_accept_vex(insn->attr)) { + /* Bad insn */ + insn->attr = 0; + return -EINVAL; + } } } if (insn->x86_64 && inat_is_force64(insn->attr)) insn->opnd_bytes = 8; + modrm->got = 1; + return 0; err_out: - return; + return -ENODATA; } @@ -338,11 +380,16 @@ err_out: int insn_rip_relative(struct insn *insn) { struct insn_field *modrm = &insn->modrm; + int ret; if (!insn->x86_64) return 0; - if (!modrm->got) - insn_get_modrm(insn); + + if (!modrm->got) { + ret = insn_get_modrm(insn); + if (ret) + return 0; + } /* * For rip-relative instructions, the mod field (top 2 bits) * is zero and the r/m field (bottom 3 bits) is 0x5. @@ -356,15 +403,25 @@ int insn_rip_relative(struct insn *insn) * * If necessary, first collects the instruction up to and including the * ModRM byte. + * + * Returns: + * 0: if decoding succeeded + * < 0: otherwise. */ -void insn_get_sib(struct insn *insn) +int insn_get_sib(struct insn *insn) { insn_byte_t modrm; + int ret; if (insn->sib.got) - return; - if (!insn->modrm.got) - insn_get_modrm(insn); + return 0; + + if (!insn->modrm.got) { + ret = insn_get_modrm(insn); + if (ret) + return ret; + } + if (insn->modrm.nbytes) { modrm = insn->modrm.bytes[0]; if (insn->addr_bytes != 2 && @@ -375,8 +432,10 @@ void insn_get_sib(struct insn *insn) } insn->sib.got = 1; + return 0; + err_out: - return; + return -ENODATA; } @@ -387,15 +446,25 @@ err_out: * If necessary, first collects the instruction up to and including the * SIB byte. * Displacement value is sign-expanded. + * + * * Returns: + * 0: if decoding succeeded + * < 0: otherwise. */ -void insn_get_displacement(struct insn *insn) +int insn_get_displacement(struct insn *insn) { insn_byte_t mod, rm, base; + int ret; if (insn->displacement.got) - return; - if (!insn->sib.got) - insn_get_sib(insn); + return 0; + + if (!insn->sib.got) { + ret = insn_get_sib(insn); + if (ret) + return ret; + } + if (insn->modrm.nbytes) { /* * Interpreting the modrm byte: @@ -437,9 +506,10 @@ void insn_get_displacement(struct insn *insn) } out: insn->displacement.got = 1; + return 0; err_out: - return; + return -ENODATA; } /* Decode moffset16/32/64. Return 0 if failed */ @@ -538,20 +608,30 @@ err_out: } /** - * insn_get_immediate() - Get the immediates of instruction + * insn_get_immediate() - Get the immediate in an instruction * @insn: &struct insn containing instruction * * If necessary, first collects the instruction up to and including the * displacement bytes. * Basically, most of immediates are sign-expanded. Unsigned-value can be - * get by bit masking with ((1 << (nbytes * 8)) - 1) + * computed by bit masking with ((1 << (nbytes * 8)) - 1) + * + * Returns: + * 0: on success + * < 0: on error */ -void insn_get_immediate(struct insn *insn) +int insn_get_immediate(struct insn *insn) { + int ret; + if (insn->immediate.got) - return; - if (!insn->displacement.got) - insn_get_displacement(insn); + return 0; + + if (!insn->displacement.got) { + ret = insn_get_displacement(insn); + if (ret) + return ret; + } if (inat_has_moffset(insn->attr)) { if (!__get_moffset(insn)) @@ -598,9 +678,10 @@ void insn_get_immediate(struct insn *insn) } done: insn->immediate.got = 1; + return 0; err_out: - return; + return -ENODATA; } /** @@ -609,13 +690,58 @@ err_out: * * If necessary, first collects the instruction up to and including the * immediates bytes. - */ -void insn_get_length(struct insn *insn) + * + * Returns: + * - 0 on success + * - < 0 on error +*/ +int insn_get_length(struct insn *insn) { + int ret; + if (insn->length) - return; - if (!insn->immediate.got) - insn_get_immediate(insn); + return 0; + + if (!insn->immediate.got) { + ret = insn_get_immediate(insn); + if (ret) + return ret; + } + insn->length = (unsigned char)((unsigned long)insn->next_byte - (unsigned long)insn->kaddr); + + return 0; +} + +/** + * insn_decode() - Decode an x86 instruction + * @insn: &struct insn to be initialized + * @kaddr: address (in kernel memory) of instruction (or copy thereof) + * @buf_len: length of the insn buffer at @kaddr + * @m: insn mode, see enum insn_mode + * + * Returns: + * 0: if decoding succeeded + * < 0: otherwise. + */ +int insn_decode(struct insn *insn, const void *kaddr, int buf_len, enum insn_mode m) +{ + int ret; + +#define INSN_MODE_KERN (enum insn_mode)-1 /* __ignore_sync_check__ mode is only valid in the kernel */ + + if (m == INSN_MODE_KERN) + insn_init(insn, kaddr, buf_len, IS_ENABLED(CONFIG_X86_64)); + else + insn_init(insn, kaddr, buf_len, m == INSN_MODE_64); + + ret = insn_get_length(insn); + if (ret) + return ret; + + if (insn_complete(insn)) + return 0; + + return -EINVAL; } diff --git a/tools/include/linux/kconfig.h b/tools/include/linux/kconfig.h new file mode 100644 index 000000000000..1555a0c4f345 --- /dev/null +++ b/tools/include/linux/kconfig.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _TOOLS_LINUX_KCONFIG_H +#define _TOOLS_LINUX_KCONFIG_H + +/* CONFIG_CC_VERSION_TEXT (Do not delete this comment. See help in Kconfig) */ + +#ifdef CONFIG_CPU_BIG_ENDIAN +#define __BIG_ENDIAN 4321 +#else +#define __LITTLE_ENDIAN 1234 +#endif + +#define __ARG_PLACEHOLDER_1 0, +#define __take_second_arg(__ignored, val, ...) val + +/* + * The use of "&&" / "||" is limited in certain expressions. + * The following enable to calculate "and" / "or" with macro expansion only. + */ +#define __and(x, y) ___and(x, y) +#define ___and(x, y) ____and(__ARG_PLACEHOLDER_##x, y) +#define ____and(arg1_or_junk, y) __take_second_arg(arg1_or_junk y, 0) + +#define __or(x, y) ___or(x, y) +#define ___or(x, y) ____or(__ARG_PLACEHOLDER_##x, y) +#define ____or(arg1_or_junk, y) __take_second_arg(arg1_or_junk 1, y) + +/* + * Helper macros to use CONFIG_ options in C/CPP expressions. Note that + * these only work with boolean and tristate options. + */ + +/* + * Getting something that works in C and CPP for an arg that may or may + * not be defined is tricky. Here, if we have "#define CONFIG_BOOGER 1" + * we match on the placeholder define, insert the "0," for arg1 and generate + * the triplet (0, 1, 0). Then the last step cherry picks the 2nd arg (a one). + * When CONFIG_BOOGER is not defined, we generate a (... 1, 0) pair, and when + * the last step cherry picks the 2nd arg, we get a zero. + */ +#define __is_defined(x) ___is_defined(x) +#define ___is_defined(val) ____is_defined(__ARG_PLACEHOLDER_##val) +#define ____is_defined(arg1_or_junk) __take_second_arg(arg1_or_junk 1, 0) + +/* + * IS_BUILTIN(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y', 0 + * otherwise. For boolean options, this is equivalent to + * IS_ENABLED(CONFIG_FOO). + */ +#define IS_BUILTIN(option) __is_defined(option) + +/* + * IS_MODULE(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'm', 0 + * otherwise. + */ +#define IS_MODULE(option) __is_defined(option##_MODULE) + +/* + * IS_REACHABLE(CONFIG_FOO) evaluates to 1 if the currently compiled + * code can call a function defined in code compiled based on CONFIG_FOO. + * This is similar to IS_ENABLED(), but returns false when invoked from + * built-in code when CONFIG_FOO is set to 'm'. + */ +#define IS_REACHABLE(option) __or(IS_BUILTIN(option), \ + __and(IS_MODULE(option), __is_defined(MODULE))) + +/* + * IS_ENABLED(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y' or 'm', + * 0 otherwise. + */ +#define IS_ENABLED(option) __or(IS_BUILTIN(option), IS_MODULE(option)) + +#endif /* _TOOLS_LINUX_KCONFIG_H */ -- cgit From 2fc83c2cd77703cfcfc1ffaa092614fb1f837292 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 14 Apr 2021 10:54:09 -0500 Subject: tools include: Add an initial math64.h Add an initial math64.h similar to linux/math64.h with functions mul_u64_u64_div64() and mul_u64_u32_shr(). This isn't a direct copy of include/linux/math64.h as that doesn't define mul_u64_u64_div64(). Implementation was written by Peter Zilkstra based on linux/math64.h and div64.h[1]. The original implementation was not optimal on arm64 as __int128 division is not optimal with a call out to __udivti3, so I dropped the __int128 variant of mul_u64_u64_div64(). [1] https://lore.kernel.org/lkml/20200322101848.GF2452@worktop.programming.kicks-ass.net/ Signed-off-by: Rob Herring Acked-by: Jiri Olsa Acked-by: Namhyung Kim Cc: Catalin Marinas Cc: Itaru Kitayama Cc: Mark Rutland Cc: Peter Zijlstra Cc: Will Deacon Link: http://lore.kernel.org/lkml/20210414155412.3697605-2-robh@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/linux/math64.h | 75 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 75 insertions(+) create mode 100644 tools/include/linux/math64.h (limited to 'tools/include/linux') diff --git a/tools/include/linux/math64.h b/tools/include/linux/math64.h new file mode 100644 index 000000000000..4ad45d5943dc --- /dev/null +++ b/tools/include/linux/math64.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_MATH64_H +#define _LINUX_MATH64_H + +#include + +#ifdef __x86_64__ +static inline u64 mul_u64_u64_div64(u64 a, u64 b, u64 c) +{ + u64 q; + + asm ("mulq %2; divq %3" : "=a" (q) + : "a" (a), "rm" (b), "rm" (c) + : "rdx"); + + return q; +} +#define mul_u64_u64_div64 mul_u64_u64_div64 +#endif + +#ifdef __SIZEOF_INT128__ +static inline u64 mul_u64_u32_shr(u64 a, u32 b, unsigned int shift) +{ + return (u64)(((unsigned __int128)a * b) >> shift); +} + +#else + +#ifdef __i386__ +static inline u64 mul_u32_u32(u32 a, u32 b) +{ + u32 high, low; + + asm ("mull %[b]" : "=a" (low), "=d" (high) + : [a] "a" (a), [b] "rm" (b) ); + + return low | ((u64)high) << 32; +} +#else +static inline u64 mul_u32_u32(u32 a, u32 b) +{ + return (u64)a * b; +} +#endif + +static inline u64 mul_u64_u32_shr(u64 a, u32 b, unsigned int shift) +{ + u32 ah, al; + u64 ret; + + al = a; + ah = a >> 32; + + ret = mul_u32_u32(al, b) >> shift; + if (ah) + ret += mul_u32_u32(ah, b) << (32 - shift); + + return ret; +} + +#endif /* __SIZEOF_INT128__ */ + +#ifndef mul_u64_u64_div64 +static inline u64 mul_u64_u64_div64(u64 a, u64 b, u64 c) +{ + u64 quot, rem; + + quot = a / c; + rem = a % c; + + return quot * b + (rem * b) / c; +} +#endif + +#endif /* _LINUX_MATH64_H */ -- cgit From e5b9252d9000fc82324af5864701c1daffeebd7e Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Thu, 6 May 2021 18:02:46 -0700 Subject: tools: bitmap: sync function declarations with the kernel Some functions in tools/include/linux/bitmap.h declare nbits as int. In the kernel nbits is declared as unsigned int. Link: https://lkml.kernel.org/r/20210401003153.97325-3-yury.norov@gmail.com Signed-off-by: Yury Norov Acked-by: Rasmus Villemoes Cc: Alexey Klimov Cc: Andy Shevchenko Cc: Arnd Bergmann Cc: David Sterba Cc: Dennis Zhou Cc: Geert Uytterhoeven Cc: Jianpeng Ma Cc: Joe Perches Cc: John Paul Adrian Glaubitz Cc: Josh Poimboeuf Cc: Rich Felker Cc: Stefano Brivio Cc: Wei Yang Cc: Wolfram Sang Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/include/linux/bitmap.h | 8 ++++---- tools/lib/bitmap.c | 4 ++-- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'tools/include/linux') diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h index 477a1cae513f..7cbd23e56d48 100644 --- a/tools/include/linux/bitmap.h +++ b/tools/include/linux/bitmap.h @@ -30,7 +30,7 @@ void bitmap_clear(unsigned long *map, unsigned int start, int len); #define small_const_nbits(nbits) \ (__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG) -static inline void bitmap_zero(unsigned long *dst, int nbits) +static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = 0UL; @@ -66,7 +66,7 @@ static inline int bitmap_full(const unsigned long *src, unsigned int nbits) return find_first_zero_bit(src, nbits) == nbits; } -static inline int bitmap_weight(const unsigned long *src, int nbits) +static inline int bitmap_weight(const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits)); @@ -74,7 +74,7 @@ static inline int bitmap_weight(const unsigned long *src, int nbits) } static inline void bitmap_or(unsigned long *dst, const unsigned long *src1, - const unsigned long *src2, int nbits) + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = *src1 | *src2; @@ -141,7 +141,7 @@ static inline void bitmap_free(unsigned long *bitmap) * @buf: buffer to store output * @size: size of @buf */ -size_t bitmap_scnprintf(unsigned long *bitmap, int nbits, +size_t bitmap_scnprintf(unsigned long *bitmap, unsigned int nbits, char *buf, size_t size); /** diff --git a/tools/lib/bitmap.c b/tools/lib/bitmap.c index 5043747ef6c5..f4e914712b6f 100644 --- a/tools/lib/bitmap.c +++ b/tools/lib/bitmap.c @@ -28,11 +28,11 @@ void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, dst[k] = bitmap1[k] | bitmap2[k]; } -size_t bitmap_scnprintf(unsigned long *bitmap, int nbits, +size_t bitmap_scnprintf(unsigned long *bitmap, unsigned int nbits, char *buf, size_t size) { /* current bit is 'cur', most recently seen range is [rbot, rtop] */ - int cur, rbot, rtop; + unsigned int cur, rbot, rtop; bool first = true; size_t ret = 0; -- cgit From a719101f19d2b4f107c8a79ed8b2866832a1816f Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Thu, 6 May 2021 18:02:49 -0700 Subject: tools: sync BITMAP_LAST_WORD_MASK() macro with the kernel Kernel version generates better code. Link: https://lkml.kernel.org/r/20210401003153.97325-4-yury.norov@gmail.com Signed-off-by: Yury Norov Acked-by: Rasmus Villemoes Cc: Alexey Klimov Cc: Andy Shevchenko Cc: Arnd Bergmann Cc: David Sterba Cc: Dennis Zhou Cc: Geert Uytterhoeven Cc: Jianpeng Ma Cc: Joe Perches Cc: John Paul Adrian Glaubitz Cc: Josh Poimboeuf Cc: Rich Felker Cc: Stefano Brivio Cc: Wei Yang Cc: Wolfram Sang Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/include/linux/bitmap.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'tools/include/linux') diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h index 7cbd23e56d48..4aabc23ec747 100644 --- a/tools/include/linux/bitmap.h +++ b/tools/include/linux/bitmap.h @@ -20,12 +20,7 @@ int __bitmap_equal(const unsigned long *bitmap1, void bitmap_clear(unsigned long *map, unsigned int start, int len); #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) - -#define BITMAP_LAST_WORD_MASK(nbits) \ -( \ - ((nbits) % BITS_PER_LONG) ? \ - (1UL<<((nbits) % BITS_PER_LONG))-1 : ~0UL \ -) +#define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1))) #define small_const_nbits(nbits) \ (__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG) -- cgit From 78e48f0667ff11ee444e057c757896062b6ad06b Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Thu, 6 May 2021 18:03:00 -0700 Subject: tools: sync small_const_nbits() macro with the kernel Sync implementation with the kernel and move the macro from tools/include/linux/bitmap.h to tools/include/asm-generic/bitsperlong.h Link: https://lkml.kernel.org/r/20210401003153.97325-7-yury.norov@gmail.com Signed-off-by: Yury Norov Acked-by: Rasmus Villemoes Cc: Alexey Klimov Cc: Andy Shevchenko Cc: Arnd Bergmann Cc: David Sterba Cc: Dennis Zhou Cc: Geert Uytterhoeven Cc: Jianpeng Ma Cc: Joe Perches Cc: John Paul Adrian Glaubitz Cc: Josh Poimboeuf Cc: Rich Felker Cc: Stefano Brivio Cc: Wei Yang Cc: Wolfram Sang Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/include/asm-generic/bitsperlong.h | 3 +++ tools/include/linux/bitmap.h | 3 --- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'tools/include/linux') diff --git a/tools/include/asm-generic/bitsperlong.h b/tools/include/asm-generic/bitsperlong.h index 8f2283052333..2093d56ddd11 100644 --- a/tools/include/asm-generic/bitsperlong.h +++ b/tools/include/asm-generic/bitsperlong.h @@ -18,4 +18,7 @@ #define BITS_PER_LONG_LONG 64 #endif +#define small_const_nbits(nbits) \ + (__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG && (nbits) > 0) + #endif /* __ASM_GENERIC_BITS_PER_LONG */ diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h index 4aabc23ec747..330dbf7509cc 100644 --- a/tools/include/linux/bitmap.h +++ b/tools/include/linux/bitmap.h @@ -22,9 +22,6 @@ void bitmap_clear(unsigned long *map, unsigned int start, int len); #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1))) -#define small_const_nbits(nbits) \ - (__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG) - static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { if (small_const_nbits(nbits)) -- cgit From f747e6667ebb2ffb8133486c9cd19800d72b0d98 Mon Sep 17 00:00:00 2001 From: Rikard Falkeborn Date: Sat, 22 May 2021 17:42:02 -0700 Subject: linux/bits.h: fix compilation error with GENMASK GENMASK() has an input check which uses __builtin_choose_expr() to enable a compile time sanity check of its inputs if they are known at compile time. However, it turns out that __builtin_constant_p() does not always return a compile time constant [0]. It was thought this problem was fixed with gcc 4.9 [1], but apparently this is not the case [2]. Switch to use __is_constexpr() instead which always returns a compile time constant, regardless of its inputs. Link: https://lore.kernel.org/lkml/42b4342b-aefc-a16a-0d43-9f9c0d63ba7a@rasmusvillemoes.dk [0] Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=19449 [1] Link: https://lore.kernel.org/lkml/1ac7bbc2-45d9-26ed-0b33-bf382b8d858b@I-love.SAKURA.ne.jp [2] Link: https://lkml.kernel.org/r/20210511203716.117010-1-rikard.falkeborn@gmail.com Signed-off-by: Rikard Falkeborn Reported-by: Tetsuo Handa Acked-by: Arnd Bergmann Reviewed-by: Andy Shevchenko Cc: Ard Biesheuvel Cc: Yury Norov Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bits.h | 2 +- include/linux/const.h | 8 ++++++++ include/linux/minmax.h | 10 ++-------- tools/include/linux/bits.h | 2 +- tools/include/linux/const.h | 8 ++++++++ 5 files changed, 20 insertions(+), 10 deletions(-) (limited to 'tools/include/linux') diff --git a/include/linux/bits.h b/include/linux/bits.h index 7f475d59a097..87d112650dfb 100644 --- a/include/linux/bits.h +++ b/include/linux/bits.h @@ -22,7 +22,7 @@ #include #define GENMASK_INPUT_CHECK(h, l) \ (BUILD_BUG_ON_ZERO(__builtin_choose_expr( \ - __builtin_constant_p((l) > (h)), (l) > (h), 0))) + __is_constexpr((l) > (h)), (l) > (h), 0))) #else /* * BUILD_BUG_ON_ZERO is not available in h files included from asm files, diff --git a/include/linux/const.h b/include/linux/const.h index 81b8aae5a855..435ddd72d2c4 100644 --- a/include/linux/const.h +++ b/include/linux/const.h @@ -3,4 +3,12 @@ #include +/* + * This returns a constant expression while determining if an argument is + * a constant expression, most importantly without evaluating the argument. + * Glory to Martin Uecker + */ +#define __is_constexpr(x) \ + (sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8))) + #endif /* _LINUX_CONST_H */ diff --git a/include/linux/minmax.h b/include/linux/minmax.h index c0f57b0c64d9..5433c08fcc68 100644 --- a/include/linux/minmax.h +++ b/include/linux/minmax.h @@ -2,6 +2,8 @@ #ifndef _LINUX_MINMAX_H #define _LINUX_MINMAX_H +#include + /* * min()/max()/clamp() macros must accomplish three things: * @@ -17,14 +19,6 @@ #define __typecheck(x, y) \ (!!(sizeof((typeof(x) *)1 == (typeof(y) *)1))) -/* - * This returns a constant expression while determining if an argument is - * a constant expression, most importantly without evaluating the argument. - * Glory to Martin Uecker - */ -#define __is_constexpr(x) \ - (sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8))) - #define __no_side_effects(x, y) \ (__is_constexpr(x) && __is_constexpr(y)) diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h index 7f475d59a097..87d112650dfb 100644 --- a/tools/include/linux/bits.h +++ b/tools/include/linux/bits.h @@ -22,7 +22,7 @@ #include #define GENMASK_INPUT_CHECK(h, l) \ (BUILD_BUG_ON_ZERO(__builtin_choose_expr( \ - __builtin_constant_p((l) > (h)), (l) > (h), 0))) + __is_constexpr((l) > (h)), (l) > (h), 0))) #else /* * BUILD_BUG_ON_ZERO is not available in h files included from asm files, diff --git a/tools/include/linux/const.h b/tools/include/linux/const.h index 81b8aae5a855..435ddd72d2c4 100644 --- a/tools/include/linux/const.h +++ b/tools/include/linux/const.h @@ -3,4 +3,12 @@ #include +/* + * This returns a constant expression while determining if an argument is + * a constant expression, most importantly without evaluating the argument. + * Glory to Martin Uecker + */ +#define __is_constexpr(x) \ + (sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8))) + #endif /* _LINUX_CONST_H */ -- cgit