diff options
Diffstat (limited to 'tools')
142 files changed, 3146 insertions, 590 deletions
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index f209ea151dca..3051f86a9b5f 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -87,9 +87,11 @@ struct kvm_regs { /* Supported VGICv3 address types */ #define KVM_VGIC_V3_ADDR_TYPE_DIST 2 #define KVM_VGIC_V3_ADDR_TYPE_REDIST 3 +#define KVM_VGIC_ITS_ADDR_TYPE 4 #define KVM_VGIC_V3_DIST_SIZE SZ_64K #define KVM_VGIC_V3_REDIST_SIZE (2 * SZ_64K) +#define KVM_VGIC_V3_ITS_SIZE (2 * SZ_64K) #define KVM_ARM_VCPU_POWER_OFF 0 /* CPU is started in OFF state */ #define KVM_ARM_VCPU_EL1_32BIT 1 /* CPU running a 32bit VM */ diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h index 3b8e99ef9d58..a2ffec4139ad 100644 --- a/tools/arch/s390/include/uapi/asm/kvm.h +++ b/tools/arch/s390/include/uapi/asm/kvm.h @@ -93,6 +93,47 @@ struct kvm_s390_vm_cpu_machine { __u64 fac_list[256]; }; +#define KVM_S390_VM_CPU_PROCESSOR_FEAT 2 +#define KVM_S390_VM_CPU_MACHINE_FEAT 3 + +#define KVM_S390_VM_CPU_FEAT_NR_BITS 1024 +#define KVM_S390_VM_CPU_FEAT_ESOP 0 +#define KVM_S390_VM_CPU_FEAT_SIEF2 1 +#define KVM_S390_VM_CPU_FEAT_64BSCAO 2 +#define KVM_S390_VM_CPU_FEAT_SIIF 3 +#define KVM_S390_VM_CPU_FEAT_GPERE 4 +#define KVM_S390_VM_CPU_FEAT_GSLS 5 +#define KVM_S390_VM_CPU_FEAT_IB 6 +#define KVM_S390_VM_CPU_FEAT_CEI 7 +#define KVM_S390_VM_CPU_FEAT_IBS 8 +#define KVM_S390_VM_CPU_FEAT_SKEY 9 +#define KVM_S390_VM_CPU_FEAT_CMMA 10 +#define KVM_S390_VM_CPU_FEAT_PFMFI 11 +#define KVM_S390_VM_CPU_FEAT_SIGPIF 12 +struct kvm_s390_vm_cpu_feat { + __u64 feat[16]; +}; + +#define KVM_S390_VM_CPU_PROCESSOR_SUBFUNC 4 +#define KVM_S390_VM_CPU_MACHINE_SUBFUNC 5 +/* for "test bit" instructions MSB 0 bit ordering, for "query" raw blocks */ +struct kvm_s390_vm_cpu_subfunc { + __u8 plo[32]; /* always */ + __u8 ptff[16]; /* with TOD-clock steering */ + __u8 kmac[16]; /* with MSA */ + __u8 kmc[16]; /* with MSA */ + __u8 km[16]; /* with MSA */ + __u8 kimd[16]; /* with MSA */ + __u8 klmd[16]; /* with MSA */ + __u8 pckmo[16]; /* with MSA3 */ + __u8 kmctr[16]; /* with MSA4 */ + __u8 kmf[16]; /* with MSA4 */ + __u8 kmo[16]; /* with MSA4 */ + __u8 pcc[16]; /* with MSA4 */ + __u8 ppno[16]; /* with MSA5 */ + __u8 reserved[1824]; +}; + /* kvm attributes for crypto */ #define KVM_S390_VM_CRYPTO_ENABLE_AES_KW 0 #define KVM_S390_VM_CRYPTO_ENABLE_DEA_KW 1 diff --git a/tools/arch/s390/include/uapi/asm/sie.h b/tools/arch/s390/include/uapi/asm/sie.h index 8fb5d4a6dd25..3ac634368939 100644 --- a/tools/arch/s390/include/uapi/asm/sie.h +++ b/tools/arch/s390/include/uapi/asm/sie.h @@ -140,6 +140,7 @@ exit_code_ipa0(0xB2, 0x4c, "TAR"), \ exit_code_ipa0(0xB2, 0x50, "CSP"), \ exit_code_ipa0(0xB2, 0x54, "MVPG"), \ + exit_code_ipa0(0xB2, 0x56, "STHYI"), \ exit_code_ipa0(0xB2, 0x58, "BSG"), \ exit_code_ipa0(0xB2, 0x5a, "BSA"), \ exit_code_ipa0(0xB2, 0x5f, "CHSC"), \ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 4a413485f9eb..92a8308b96f6 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -225,7 +225,6 @@ #define X86_FEATURE_RDSEED ( 9*32+18) /* The RDSEED instruction */ #define X86_FEATURE_ADX ( 9*32+19) /* The ADCX and ADOX instructions */ #define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */ -#define X86_FEATURE_PCOMMIT ( 9*32+22) /* PCOMMIT instruction */ #define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */ #define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */ #define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ @@ -301,10 +300,6 @@ #define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */ #define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */ #define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */ -#define X86_BUG_NULL_SEG X86_BUG(9) /* Nulling a selector preserves the base */ -#define X86_BUG_SWAPGS_FENCE X86_BUG(10) /* SWAPGS without input dep on GS */ - - #ifdef CONFIG_X86_32 /* * 64-bit kernels don't use X86_BUG_ESPFIX. Make the define conditional @@ -312,5 +307,7 @@ */ #define X86_BUG_ESPFIX X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */ #endif - +#define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */ +#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */ +#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 911e9358ceb1..85599ad4d024 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -56,5 +56,7 @@ #define DISABLED_MASK14 0 #define DISABLED_MASK15 0 #define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE) +#define DISABLED_MASK17 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h index 4916144e3c42..fac9a5c0abe9 100644 --- a/tools/arch/x86/include/asm/required-features.h +++ b/tools/arch/x86/include/asm/required-features.h @@ -99,5 +99,7 @@ #define REQUIRED_MASK14 0 #define REQUIRED_MASK15 0 #define REQUIRED_MASK16 0 +#define REQUIRED_MASK17 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h index 5b15d94a33f8..37fee272618f 100644 --- a/tools/arch/x86/include/uapi/asm/vmx.h +++ b/tools/arch/x86/include/uapi/asm/vmx.h @@ -78,7 +78,6 @@ #define EXIT_REASON_PML_FULL 62 #define EXIT_REASON_XSAVES 63 #define EXIT_REASON_XRSTORS 64 -#define EXIT_REASON_PCOMMIT 65 #define VMX_EXIT_REASONS \ { EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \ @@ -127,8 +126,7 @@ { EXIT_REASON_INVVPID, "INVVPID" }, \ { EXIT_REASON_INVPCID, "INVPCID" }, \ { EXIT_REASON_XSAVES, "XSAVES" }, \ - { EXIT_REASON_XRSTORS, "XRSTORS" }, \ - { EXIT_REASON_PCOMMIT, "PCOMMIT" } + { EXIT_REASON_XRSTORS, "XRSTORS" } #define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1 #define VMX_ABORT_LOAD_HOST_MSR_FAIL 4 diff --git a/tools/gpio/gpio-event-mon.c b/tools/gpio/gpio-event-mon.c index 448ed96b3b4f..1c14c2595158 100644 --- a/tools/gpio/gpio-event-mon.c +++ b/tools/gpio/gpio-event-mon.c @@ -1,5 +1,5 @@ /* - * gpio-hammer - example swiss army knife to shake GPIO lines on a system + * gpio-event-mon - monitor GPIO line events from userspace * * Copyright (C) 2016 Linus Walleij * diff --git a/tools/iio/iio_generic_buffer.c b/tools/iio/iio_generic_buffer.c index 0e8a1f7a292d..f39c0e9c0d5c 100644 --- a/tools/iio/iio_generic_buffer.c +++ b/tools/iio/iio_generic_buffer.c @@ -348,7 +348,7 @@ int main(int argc, char **argv) int notrigger = 0; char *dummy; - struct iio_channel_info *channels; + struct iio_channel_info *channels = NULL; register_cleanup(); @@ -456,7 +456,7 @@ int main(int argc, char **argv) if (notrigger) { printf("trigger-less mode selected\n"); - } if (trig_num >= 0) { + } else if (trig_num >= 0) { char *trig_dev_name; ret = asprintf(&trig_dev_name, "%strigger%d", iio_dir, trig_num); if (ret < 0) { diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h index 28f5493da491..43c1c5021e4b 100644 --- a/tools/include/linux/bitmap.h +++ b/tools/include/linux/bitmap.h @@ -3,6 +3,7 @@ #include <string.h> #include <linux/bitops.h> +#include <stdlib.h> #define DECLARE_BITMAP(name,bits) \ unsigned long name[BITS_TO_LONGS(bits)] @@ -10,6 +11,8 @@ int __bitmap_weight(const unsigned long *bitmap, int bits); void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, int bits); +int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int bits); #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) @@ -65,4 +68,38 @@ static inline int test_and_set_bit(int nr, unsigned long *addr) return (old & mask) != 0; } +/** + * bitmap_alloc - Allocate bitmap + * @nr: Bit to set + */ +static inline unsigned long *bitmap_alloc(int nbits) +{ + return calloc(1, BITS_TO_LONGS(nbits) * sizeof(unsigned long)); +} + +/* + * bitmap_scnprintf - print bitmap list into buffer + * @bitmap: bitmap + * @nbits: size of bitmap + * @buf: buffer to store output + * @size: size of @buf + */ +size_t bitmap_scnprintf(unsigned long *bitmap, int nbits, + char *buf, size_t size); + +/** + * bitmap_and - Do logical and on bitmaps + * @dst: resulting bitmap + * @src1: operand 1 + * @src2: operand 2 + * @nbits: size of bitmap + */ +static inline int bitmap_and(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) +{ + if (small_const_nbits(nbits)) + return (*dst = *src1 & *src2 & BITMAP_LAST_WORD_MASK(nbits)) != 0; + return __bitmap_and(dst, src1, src2, nbits); +} + #endif /* _PERF_BITOPS_H */ diff --git a/tools/include/linux/string.h b/tools/include/linux/string.h index b96879477311..f436d2420a18 100644 --- a/tools/include/linux/string.h +++ b/tools/include/linux/string.h @@ -8,7 +8,11 @@ void *memdup(const void *src, size_t len); int strtobool(const char *s, bool *res); -#ifdef __GLIBC__ +/* + * glibc based builds needs the extern while uClibc doesn't. + * However uClibc headers also define __GLIBC__ hence the hack below + */ +#if defined(__GLIBC__) && !defined(__UCLIBC__) extern size_t strlcpy(char *dest, const char *src, size_t size); #endif diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 406459b935a2..da218fec6056 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -84,6 +84,7 @@ enum bpf_map_type { BPF_MAP_TYPE_PERCPU_HASH, BPF_MAP_TYPE_PERCPU_ARRAY, BPF_MAP_TYPE_STACK_TRACE, + BPF_MAP_TYPE_CGROUP_ARRAY, }; enum bpf_prog_type { @@ -93,6 +94,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SCHED_CLS, BPF_PROG_TYPE_SCHED_ACT, BPF_PROG_TYPE_TRACEPOINT, + BPF_PROG_TYPE_XDP, }; #define BPF_PSEUDO_MAP_FD 1 @@ -313,6 +315,66 @@ enum bpf_func_id { */ BPF_FUNC_skb_get_tunnel_opt, BPF_FUNC_skb_set_tunnel_opt, + + /** + * bpf_skb_change_proto(skb, proto, flags) + * Change protocol of the skb. Currently supported is + * v4 -> v6, v6 -> v4 transitions. The helper will also + * resize the skb. eBPF program is expected to fill the + * new headers via skb_store_bytes and lX_csum_replace. + * @skb: pointer to skb + * @proto: new skb->protocol type + * @flags: reserved + * Return: 0 on success or negative error + */ + BPF_FUNC_skb_change_proto, + + /** + * bpf_skb_change_type(skb, type) + * Change packet type of skb. + * @skb: pointer to skb + * @type: new skb->pkt_type type + * Return: 0 on success or negative error + */ + BPF_FUNC_skb_change_type, + + /** + * bpf_skb_in_cgroup(skb, map, index) - Check cgroup2 membership of skb + * @skb: pointer to skb + * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type + * @index: index of the cgroup in the bpf_map + * Return: + * == 0 skb failed the cgroup2 descendant test + * == 1 skb succeeded the cgroup2 descendant test + * < 0 error + */ + BPF_FUNC_skb_in_cgroup, + + /** + * bpf_get_hash_recalc(skb) + * Retrieve and possibly recalculate skb->hash. + * @skb: pointer to skb + * Return: hash + */ + BPF_FUNC_get_hash_recalc, + + /** + * u64 bpf_get_current_task(void) + * Returns current task_struct + * Return: current + */ + BPF_FUNC_get_current_task, + + /** + * bpf_probe_write_user(void *dst, void *src, int len) + * safely attempt to write to a location + * @dst: destination address in userspace + * @src: source address on stack + * @len: number of bytes to copy + * Return: 0 on success or negative error + */ + BPF_FUNC_probe_write_user, + __BPF_FUNC_MAX_ID, }; @@ -347,9 +409,11 @@ enum bpf_func_id { #define BPF_F_ZERO_CSUM_TX (1ULL << 1) #define BPF_F_DONT_FRAGMENT (1ULL << 2) -/* BPF_FUNC_perf_event_output flags. */ +/* BPF_FUNC_perf_event_output and BPF_FUNC_perf_event_read flags. */ #define BPF_F_INDEX_MASK 0xffffffffULL #define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK +/* BPF_FUNC_perf_event_output for sk_buff input context. */ +#define BPF_F_CTXLEN_MASK (0xfffffULL << 32) /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure @@ -386,4 +450,24 @@ struct bpf_tunnel_key { __u32 tunnel_label; }; +/* User return codes for XDP prog type. + * A valid XDP program must return one of these defined values. All other + * return codes are reserved for future use. Unknown return codes will result + * in packet drop. + */ +enum xdp_action { + XDP_ABORTED = 0, + XDP_DROP, + XDP_PASS, + XDP_TX, +}; + +/* user accessible metadata for XDP packet hook + * new fields must be added to the end of this structure + */ +struct xdp_md { + __u32 data; + __u32 data_end; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/tools/lguest/lguest.c b/tools/lguest/lguest.c index d9836c5eb694..11c8d9bc762e 100644 --- a/tools/lguest/lguest.c +++ b/tools/lguest/lguest.c @@ -3266,6 +3266,9 @@ int main(int argc, char *argv[]) } } + /* If we exit via err(), this kills all the threads, restores tty. */ + atexit(cleanup_devices); + /* We always have a console device, and it's always device 1. */ setup_console(); @@ -3369,9 +3372,6 @@ int main(int argc, char *argv[]) /* Ensure that we terminate if a device-servicing child dies. */ signal(SIGCHLD, kill_launcher); - /* If we exit via err(), this kills all the threads, restores tty. */ - atexit(cleanup_devices); - /* If requested, chroot to a directory */ if (chroot_path) { if (chroot(chroot_path) != 0) diff --git a/tools/lib/api/Build b/tools/lib/api/Build index 954c644f7ad9..6e2373db5598 100644 --- a/tools/lib/api/Build +++ b/tools/lib/api/Build @@ -2,3 +2,8 @@ libapi-y += fd/ libapi-y += fs/ libapi-y += cpu.o libapi-y += debug.o +libapi-y += str_error_r.o + +$(OUTPUT)str_error_r.o: ../str_error_r.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,cc_o_c) diff --git a/tools/lib/bitmap.c b/tools/lib/bitmap.c index 0a1adc1111fd..38748b0e342f 100644 --- a/tools/lib/bitmap.c +++ b/tools/lib/bitmap.c @@ -29,3 +29,47 @@ void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, for (k = 0; k < nr; k++) dst[k] = bitmap1[k] | bitmap2[k]; } + +size_t bitmap_scnprintf(unsigned long *bitmap, int nbits, + char *buf, size_t size) +{ + /* current bit is 'cur', most recently seen range is [rbot, rtop] */ + int cur, rbot, rtop; + bool first = true; + size_t ret = 0; + + rbot = cur = find_first_bit(bitmap, nbits); + while (cur < nbits) { + rtop = cur; + cur = find_next_bit(bitmap, nbits, cur + 1); + if (cur < nbits && cur <= rtop + 1) + continue; + + if (!first) + ret += scnprintf(buf + ret, size - ret, ","); + + first = false; + + ret += scnprintf(buf + ret, size - ret, "%d", rbot); + if (rbot < rtop) + ret += scnprintf(buf + ret, size - ret, "-%d", rtop); + + rbot = cur; + } + return ret; +} + +int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int bits) +{ + unsigned int k; + unsigned int lim = bits/BITS_PER_LONG; + unsigned long result = 0; + + for (k = 0; k < lim; k++) + result |= (dst[k] = bitmap1[k] & bitmap2[k]); + if (bits % BITS_PER_LONG) + result |= (dst[k] = bitmap1[k] & bitmap2[k] & + BITMAP_LAST_WORD_MASK(bits)); + return result != 0; +} diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 32e6b6bc6f7d..b699aea9a025 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -37,6 +37,10 @@ #include "libbpf.h" #include "bpf.h" +#ifndef EM_BPF +#define EM_BPF 247 +#endif + #define __printf(a, b) __attribute__((format(printf, a, b))) __printf(1, 2) @@ -439,7 +443,8 @@ static int bpf_object__elf_init(struct bpf_object *obj) } ep = &obj->efile.ehdr; - if ((ep->e_type != ET_REL) || (ep->e_machine != 0)) { + /* Old LLVM set e_machine to EM_NONE */ + if ((ep->e_type != ET_REL) || (ep->e_machine && (ep->e_machine != EM_BPF))) { pr_warning("%s is not an eBPF object file\n", obj->path); err = -LIBBPF_ERRNO__FORMAT; diff --git a/tools/lib/traceevent/.gitignore b/tools/lib/traceevent/.gitignore index 3c60335fe7be..9e9f25fb1922 100644 --- a/tools/lib/traceevent/.gitignore +++ b/tools/lib/traceevent/.gitignore @@ -1,2 +1,3 @@ TRACEEVENT-CFLAGS libtraceevent-dynamic-list +libtraceevent.so.* diff --git a/tools/objtool/.gitignore b/tools/objtool/.gitignore index a0b3128bb31f..d3102c865a95 100644 --- a/tools/objtool/.gitignore +++ b/tools/objtool/.gitignore @@ -1,2 +1,3 @@ arch/x86/insn/inat-tables.c objtool +fixdep diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile index 0b437700f688..041b493ad3ab 100644 --- a/tools/objtool/Makefile +++ b/tools/objtool/Makefile @@ -51,7 +51,7 @@ $(OBJTOOL): $(LIBSUBCMD) $(OBJTOOL_IN) diff -I'^#include' arch/x86/insn/insn.h ../../arch/x86/include/asm/insn.h >/dev/null && \ diff -I'^#include' arch/x86/insn/inat.h ../../arch/x86/include/asm/inat.h >/dev/null && \ diff -I'^#include' arch/x86/insn/inat_types.h ../../arch/x86/include/asm/inat_types.h >/dev/null) \ - || echo "Warning: objtool: x86 instruction decoder differs from kernel" >&2 )) || true + || echo "warning: objtool: x86 instruction decoder differs from kernel" >&2 )) || true $(QUIET_LINK)$(CC) $(OBJTOOL_IN) $(LDFLAGS) -o $@ diff --git a/tools/objtool/arch/x86/insn/gen-insn-attr-x86.awk b/tools/objtool/arch/x86/insn/gen-insn-attr-x86.awk index 093a892026f9..a3d2c62fd805 100644 --- a/tools/objtool/arch/x86/insn/gen-insn-attr-x86.awk +++ b/tools/objtool/arch/x86/insn/gen-insn-attr-x86.awk @@ -72,12 +72,14 @@ BEGIN { lprefix_expr = "\\((66|F2|F3)\\)" max_lprefix = 4 - # All opcodes starting with lower-case 'v' or with (v1) superscript + # All opcodes starting with lower-case 'v', 'k' or with (v1) superscript # accepts VEX prefix - vexok_opcode_expr = "^v.*" + vexok_opcode_expr = "^[vk].*" vexok_expr = "\\(v1\\)" # All opcodes with (v) superscript supports *only* VEX prefix vexonly_expr = "\\(v\\)" + # All opcodes with (ev) superscript supports *only* EVEX prefix + evexonly_expr = "\\(ev\\)" prefix_expr = "\\(Prefix\\)" prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ" @@ -95,6 +97,7 @@ BEGIN { prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ" prefix_num["VEX+1byte"] = "INAT_PFX_VEX2" prefix_num["VEX+2byte"] = "INAT_PFX_VEX3" + prefix_num["EVEX"] = "INAT_PFX_EVEX" clear_vars() } @@ -319,7 +322,9 @@ function convert_operands(count,opnd, i,j,imm,mod) flags = add_flags(flags, "INAT_MODRM") # check VEX codes - if (match(ext, vexonly_expr)) + if (match(ext, evexonly_expr)) + flags = add_flags(flags, "INAT_VEXOK | INAT_EVEXONLY") + else if (match(ext, vexonly_expr)) flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY") else if (match(ext, vexok_expr) || match(opcode, vexok_opcode_expr)) flags = add_flags(flags, "INAT_VEXOK") diff --git a/tools/objtool/arch/x86/insn/inat.h b/tools/objtool/arch/x86/insn/inat.h index 611645e903a8..125ecd2a300d 100644 --- a/tools/objtool/arch/x86/insn/inat.h +++ b/tools/objtool/arch/x86/insn/inat.h @@ -48,6 +48,7 @@ /* AVX VEX prefixes */ #define INAT_PFX_VEX2 13 /* 2-bytes VEX prefix */ #define INAT_PFX_VEX3 14 /* 3-bytes VEX prefix */ +#define INAT_PFX_EVEX 15 /* EVEX prefix */ #define INAT_LSTPFX_MAX 3 #define INAT_LGCPFX_MAX 11 @@ -89,6 +90,7 @@ #define INAT_VARIANT (1 << (INAT_FLAG_OFFS + 4)) #define INAT_VEXOK (1 << (INAT_FLAG_OFFS + 5)) #define INAT_VEXONLY (1 << (INAT_FLAG_OFFS + 6)) +#define INAT_EVEXONLY (1 << (INAT_FLAG_OFFS + 7)) /* Attribute making macros for attribute tables */ #define INAT_MAKE_PREFIX(pfx) (pfx << INAT_PFX_OFFS) #define INAT_MAKE_ESCAPE(esc) (esc << INAT_ESC_OFFS) @@ -141,7 +143,13 @@ static inline int inat_last_prefix_id(insn_attr_t attr) static inline int inat_is_vex_prefix(insn_attr_t attr) { attr &= INAT_PFX_MASK; - return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3; + return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3 || + attr == INAT_PFX_EVEX; +} + +static inline int inat_is_evex_prefix(insn_attr_t attr) +{ + return (attr & INAT_PFX_MASK) == INAT_PFX_EVEX; } static inline int inat_is_vex3_prefix(insn_attr_t attr) @@ -216,6 +224,11 @@ static inline int inat_accept_vex(insn_attr_t attr) static inline int inat_must_vex(insn_attr_t attr) { - return attr & INAT_VEXONLY; + return attr & (INAT_VEXONLY | INAT_EVEXONLY); +} + +static inline int inat_must_evex(insn_attr_t attr) +{ + return attr & INAT_EVEXONLY; } #endif diff --git a/tools/objtool/arch/x86/insn/insn.c b/tools/objtool/arch/x86/insn/insn.c index 9f26eae6c9f0..ca983e2bea8b 100644 --- a/tools/objtool/arch/x86/insn/insn.c +++ b/tools/objtool/arch/x86/insn/insn.c @@ -155,14 +155,24 @@ found: /* * In 32-bits mode, if the [7:6] bits (mod bits of * ModRM) on the second byte are not 11b, it is - * LDS or LES. + * LDS or LES or BOUND. */ if (X86_MODRM_MOD(b2) != 3) goto vex_end; } insn->vex_prefix.bytes[0] = b; insn->vex_prefix.bytes[1] = b2; - if (inat_is_vex3_prefix(attr)) { + if (inat_is_evex_prefix(attr)) { + b2 = peek_nbyte_next(insn_byte_t, insn, 2); + insn->vex_prefix.bytes[2] = b2; + b2 = peek_nbyte_next(insn_byte_t, insn, 3); + insn->vex_prefix.bytes[3] = b2; + insn->vex_prefix.nbytes = 4; + insn->next_byte += 4; + if (insn->x86_64 && X86_VEX_W(b2)) + /* VEX.W overrides opnd_size */ + insn->opnd_bytes = 8; + } else if (inat_is_vex3_prefix(attr)) { b2 = peek_nbyte_next(insn_byte_t, insn, 2); insn->vex_prefix.bytes[2] = b2; insn->vex_prefix.nbytes = 3; @@ -221,7 +231,9 @@ void insn_get_opcode(struct insn *insn) m = insn_vex_m_bits(insn); p = insn_vex_p_bits(insn); insn->attr = inat_get_avx_attribute(op, m, p); - if (!inat_accept_vex(insn->attr) && !inat_is_group(insn->attr)) + 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 */ } diff --git a/tools/objtool/arch/x86/insn/insn.h b/tools/objtool/arch/x86/insn/insn.h index dd12da0f4593..e23578c7b1be 100644 --- a/tools/objtool/arch/x86/insn/insn.h +++ b/tools/objtool/arch/x86/insn/insn.h @@ -91,6 +91,7 @@ struct insn { #define X86_VEX_B(vex) ((vex) & 0x20) /* VEX3 Byte1 */ #define X86_VEX_L(vex) ((vex) & 0x04) /* VEX3 Byte2, VEX2 Byte1 */ /* VEX bit fields */ +#define X86_EVEX_M(vex) ((vex) & 0x03) /* EVEX Byte1 */ #define X86_VEX3_M(vex) ((vex) & 0x1f) /* VEX3 Byte1 */ #define X86_VEX2_M 1 /* VEX2.M always 1 */ #define X86_VEX_V(vex) (((vex) & 0x78) >> 3) /* VEX3 Byte2, VEX2 Byte1 */ @@ -133,6 +134,13 @@ static inline int insn_is_avx(struct insn *insn) return (insn->vex_prefix.value != 0); } +static inline int insn_is_evex(struct insn *insn) +{ + if (!insn->prefixes.got) + insn_get_prefixes(insn); + return (insn->vex_prefix.nbytes == 4); +} + /* Ensure this instruction is decoded completely */ static inline int insn_complete(struct insn *insn) { @@ -144,8 +152,10 @@ static inline insn_byte_t insn_vex_m_bits(struct insn *insn) { if (insn->vex_prefix.nbytes == 2) /* 2 bytes VEX */ return X86_VEX2_M; - else + else if (insn->vex_prefix.nbytes == 3) /* 3 bytes VEX */ return X86_VEX3_M(insn->vex_prefix.bytes[1]); + else /* EVEX */ + return X86_EVEX_M(insn->vex_prefix.bytes[1]); } static inline insn_byte_t insn_vex_p_bits(struct insn *insn) diff --git a/tools/objtool/arch/x86/insn/x86-opcode-map.txt b/tools/objtool/arch/x86/insn/x86-opcode-map.txt index d388de72eaca..767be7c76034 100644 --- a/tools/objtool/arch/x86/insn/x86-opcode-map.txt +++ b/tools/objtool/arch/x86/insn/x86-opcode-map.txt @@ -13,12 +13,17 @@ # opcode: escape # escaped-name # EndTable # +# mnemonics that begin with lowercase 'v' accept a VEX or EVEX prefix +# mnemonics that begin with lowercase 'k' accept a VEX prefix +# #<group maps> # GrpTable: GrpXXX # reg: mnemonic [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...] # EndTable # # AVX Superscripts +# (ev): this opcode requires EVEX prefix. +# (evo): this opcode is changed by EVEX prefix (EVEX opcode) # (v): this opcode requires VEX prefix. # (v1): this opcode only supports 128bit VEX. # @@ -137,7 +142,7 @@ AVXcode: # 0x60 - 0x6f 60: PUSHA/PUSHAD (i64) 61: POPA/POPAD (i64) -62: BOUND Gv,Ma (i64) +62: BOUND Gv,Ma (i64) | EVEX (Prefix) 63: ARPL Ew,Gw (i64) | MOVSXD Gv,Ev (o64) 64: SEG=FS (Prefix) 65: SEG=GS (Prefix) @@ -399,17 +404,17 @@ AVXcode: 1 3f: # 0x0f 0x40-0x4f 40: CMOVO Gv,Ev -41: CMOVNO Gv,Ev -42: CMOVB/C/NAE Gv,Ev +41: CMOVNO Gv,Ev | kandw/q Vk,Hk,Uk | kandb/d Vk,Hk,Uk (66) +42: CMOVB/C/NAE Gv,Ev | kandnw/q Vk,Hk,Uk | kandnb/d Vk,Hk,Uk (66) 43: CMOVAE/NB/NC Gv,Ev -44: CMOVE/Z Gv,Ev -45: CMOVNE/NZ Gv,Ev -46: CMOVBE/NA Gv,Ev -47: CMOVA/NBE Gv,Ev +44: CMOVE/Z Gv,Ev | knotw/q Vk,Uk | knotb/d Vk,Uk (66) +45: CMOVNE/NZ Gv,Ev | korw/q Vk,Hk,Uk | korb/d Vk,Hk,Uk (66) +46: CMOVBE/NA Gv,Ev | kxnorw/q Vk,Hk,Uk | kxnorb/d Vk,Hk,Uk (66) +47: CMOVA/NBE Gv,Ev | kxorw/q Vk,Hk,Uk | kxorb/d Vk,Hk,Uk (66) 48: CMOVS Gv,Ev 49: CMOVNS Gv,Ev -4a: CMOVP/PE Gv,Ev -4b: CMOVNP/PO Gv,Ev +4a: CMOVP/PE Gv,Ev | kaddw/q Vk,Hk,Uk | kaddb/d Vk,Hk,Uk (66) +4b: CMOVNP/PO Gv,Ev | kunpckbw Vk,Hk,Uk (66) | kunpckwd/dq Vk,Hk,Uk 4c: CMOVL/NGE Gv,Ev 4d: CMOVNL/GE Gv,Ev 4e: CMOVLE/NG Gv,Ev @@ -426,7 +431,7 @@ AVXcode: 1 58: vaddps Vps,Hps,Wps | vaddpd Vpd,Hpd,Wpd (66) | vaddss Vss,Hss,Wss (F3),(v1) | vaddsd Vsd,Hsd,Wsd (F2),(v1) 59: vmulps Vps,Hps,Wps | vmulpd Vpd,Hpd,Wpd (66) | vmulss Vss,Hss,Wss (F3),(v1) | vmulsd Vsd,Hsd,Wsd (F2),(v1) 5a: vcvtps2pd Vpd,Wps | vcvtpd2ps Vps,Wpd (66) | vcvtss2sd Vsd,Hx,Wss (F3),(v1) | vcvtsd2ss Vss,Hx,Wsd (F2),(v1) -5b: vcvtdq2ps Vps,Wdq | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3) +5b: vcvtdq2ps Vps,Wdq | vcvtqq2ps Vps,Wqq (evo) | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3) 5c: vsubps Vps,Hps,Wps | vsubpd Vpd,Hpd,Wpd (66) | vsubss Vss,Hss,Wss (F3),(v1) | vsubsd Vsd,Hsd,Wsd (F2),(v1) 5d: vminps Vps,Hps,Wps | vminpd Vpd,Hpd,Wpd (66) | vminss Vss,Hss,Wss (F3),(v1) | vminsd Vsd,Hsd,Wsd (F2),(v1) 5e: vdivps Vps,Hps,Wps | vdivpd Vpd,Hpd,Wpd (66) | vdivss Vss,Hss,Wss (F3),(v1) | vdivsd Vsd,Hsd,Wsd (F2),(v1) @@ -447,7 +452,7 @@ AVXcode: 1 6c: vpunpcklqdq Vx,Hx,Wx (66),(v1) 6d: vpunpckhqdq Vx,Hx,Wx (66),(v1) 6e: movd/q Pd,Ey | vmovd/q Vy,Ey (66),(v1) -6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqu Vx,Wx (F3) +6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqa32/64 Vx,Wx (66),(evo) | vmovdqu Vx,Wx (F3) | vmovdqu32/64 Vx,Wx (F3),(evo) | vmovdqu8/16 Vx,Wx (F2),(ev) # 0x0f 0x70-0x7f 70: pshufw Pq,Qq,Ib | vpshufd Vx,Wx,Ib (66),(v1) | vpshufhw Vx,Wx,Ib (F3),(v1) | vpshuflw Vx,Wx,Ib (F2),(v1) 71: Grp12 (1A) @@ -458,14 +463,14 @@ AVXcode: 1 76: pcmpeqd Pq,Qq | vpcmpeqd Vx,Hx,Wx (66),(v1) # Note: Remove (v), because vzeroall and vzeroupper becomes emms without VEX. 77: emms | vzeroupper | vzeroall -78: VMREAD Ey,Gy -79: VMWRITE Gy,Ey -7a: -7b: +78: VMREAD Ey,Gy | vcvttps2udq/pd2udq Vx,Wpd (evo) | vcvttsd2usi Gv,Wx (F2),(ev) | vcvttss2usi Gv,Wx (F3),(ev) | vcvttps2uqq/pd2uqq Vx,Wx (66),(ev) +79: VMWRITE Gy,Ey | vcvtps2udq/pd2udq Vx,Wpd (evo) | vcvtsd2usi Gv,Wx (F2),(ev) | vcvtss2usi Gv,Wx (F3),(ev) | vcvtps2uqq/pd2uqq Vx,Wx (66),(ev) +7a: vcvtudq2pd/uqq2pd Vpd,Wx (F3),(ev) | vcvtudq2ps/uqq2ps Vpd,Wx (F2),(ev) | vcvttps2qq/pd2qq Vx,Wx (66),(ev) +7b: vcvtusi2sd Vpd,Hpd,Ev (F2),(ev) | vcvtusi2ss Vps,Hps,Ev (F3),(ev) | vcvtps2qq/pd2qq Vx,Wx (66),(ev) 7c: vhaddpd Vpd,Hpd,Wpd (66) | vhaddps Vps,Hps,Wps (F2) 7d: vhsubpd Vpd,Hpd,Wpd (66) | vhsubps Vps,Hps,Wps (F2) 7e: movd/q Ey,Pd | vmovd/q Ey,Vy (66),(v1) | vmovq Vq,Wq (F3),(v1) -7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqu Wx,Vx (F3) +7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqa32/64 Wx,Vx (66),(evo) | vmovdqu Wx,Vx (F3) | vmovdqu32/64 Wx,Vx (F3),(evo) | vmovdqu8/16 Wx,Vx (F2),(ev) # 0x0f 0x80-0x8f # Note: "forced64" is Intel CPU behavior (see comment about CALL insn). 80: JO Jz (f64) @@ -485,16 +490,16 @@ AVXcode: 1 8e: JLE/JNG Jz (f64) 8f: JNLE/JG Jz (f64) # 0x0f 0x90-0x9f -90: SETO Eb -91: SETNO Eb -92: SETB/C/NAE Eb -93: SETAE/NB/NC Eb +90: SETO Eb | kmovw/q Vk,Wk | kmovb/d Vk,Wk (66) +91: SETNO Eb | kmovw/q Mv,Vk | kmovb/d Mv,Vk (66) +92: SETB/C/NAE Eb | kmovw Vk,Rv | kmovb Vk,Rv (66) | kmovq/d Vk,Rv (F2) +93: SETAE/NB/NC Eb | kmovw Gv,Uk | kmovb Gv,Uk (66) | kmovq/d Gv,Uk (F2) 94: SETE/Z Eb 95: SETNE/NZ Eb 96: SETBE/NA Eb 97: SETA/NBE Eb -98: SETS Eb -99: SETNS Eb +98: SETS Eb | kortestw/q Vk,Uk | kortestb/d Vk,Uk (66) +99: SETNS Eb | ktestw/q Vk,Uk | ktestb/d Vk,Uk (66) 9a: SETP/PE Eb 9b: SETNP/PO Eb 9c: SETL/NGE Eb @@ -564,11 +569,11 @@ d7: pmovmskb Gd,Nq | vpmovmskb Gd,Ux (66),(v1) d8: psubusb Pq,Qq | vpsubusb Vx,Hx,Wx (66),(v1) d9: psubusw Pq,Qq | vpsubusw Vx,Hx,Wx (66),(v1) da: pminub Pq,Qq | vpminub Vx,Hx,Wx (66),(v1) -db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1) +db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1) | vpandd/q Vx,Hx,Wx (66),(evo) dc: paddusb Pq,Qq | vpaddusb Vx,Hx,Wx (66),(v1) dd: paddusw Pq,Qq | vpaddusw Vx,Hx,Wx (66),(v1) de: pmaxub Pq,Qq | vpmaxub Vx,Hx,Wx (66),(v1) -df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1) +df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1) | vpandnd/q Vx,Hx,Wx (66),(evo) # 0x0f 0xe0-0xef e0: pavgb Pq,Qq | vpavgb Vx,Hx,Wx (66),(v1) e1: psraw Pq,Qq | vpsraw Vx,Hx,Wx (66),(v1) @@ -576,16 +581,16 @@ e2: psrad Pq,Qq | vpsrad Vx,Hx,Wx (66),(v1) e3: pavgw Pq,Qq | vpavgw Vx,Hx,Wx (66),(v1) e4: pmulhuw Pq,Qq | vpmulhuw Vx,Hx,Wx (66),(v1) e5: pmulhw Pq,Qq | vpmulhw Vx,Hx,Wx (66),(v1) -e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtpd2dq Vx,Wpd (F2) +e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtdq2pd/qq2pd Vx,Wdq (F3),(evo) | vcvtpd2dq Vx,Wpd (F2) e7: movntq Mq,Pq | vmovntdq Mx,Vx (66) e8: psubsb Pq,Qq | vpsubsb Vx,Hx,Wx (66),(v1) e9: psubsw Pq,Qq | vpsubsw Vx,Hx,Wx (66),(v1) ea: pminsw Pq,Qq | vpminsw Vx,Hx,Wx (66),(v1) -eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1) +eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1) | vpord/q Vx,Hx,Wx (66),(evo) ec: paddsb Pq,Qq | vpaddsb Vx,Hx,Wx (66),(v1) ed: paddsw Pq,Qq | vpaddsw Vx,Hx,Wx (66),(v1) ee: pmaxsw Pq,Qq | vpmaxsw Vx,Hx,Wx (66),(v1) -ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1) +ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1) | vpxord/q Vx,Hx,Wx (66),(evo) # 0x0f 0xf0-0xff f0: vlddqu Vx,Mx (F2) f1: psllw Pq,Qq | vpsllw Vx,Hx,Wx (66),(v1) @@ -626,81 +631,105 @@ AVXcode: 2 0e: vtestps Vx,Wx (66),(v) 0f: vtestpd Vx,Wx (66),(v) # 0x0f 0x38 0x10-0x1f -10: pblendvb Vdq,Wdq (66) -11: -12: -13: vcvtph2ps Vx,Wx,Ib (66),(v) -14: blendvps Vdq,Wdq (66) -15: blendvpd Vdq,Wdq (66) -16: vpermps Vqq,Hqq,Wqq (66),(v) +10: pblendvb Vdq,Wdq (66) | vpsrlvw Vx,Hx,Wx (66),(evo) | vpmovuswb Wx,Vx (F3),(ev) +11: vpmovusdb Wx,Vd (F3),(ev) | vpsravw Vx,Hx,Wx (66),(ev) +12: vpmovusqb Wx,Vq (F3),(ev) | vpsllvw Vx,Hx,Wx (66),(ev) +13: vcvtph2ps Vx,Wx (66),(v) | vpmovusdw Wx,Vd (F3),(ev) +14: blendvps Vdq,Wdq (66) | vpmovusqw Wx,Vq (F3),(ev) | vprorvd/q Vx,Hx,Wx (66),(evo) +15: blendvpd Vdq,Wdq (66) | vpmovusqd Wx,Vq (F3),(ev) | vprolvd/q Vx,Hx,Wx (66),(evo) +16: vpermps Vqq,Hqq,Wqq (66),(v) | vpermps/d Vqq,Hqq,Wqq (66),(evo) 17: vptest Vx,Wx (66) 18: vbroadcastss Vx,Wd (66),(v) -19: vbroadcastsd Vqq,Wq (66),(v) -1a: vbroadcastf128 Vqq,Mdq (66),(v) -1b: +19: vbroadcastsd Vqq,Wq (66),(v) | vbroadcastf32x2 Vqq,Wq (66),(evo) +1a: vbroadcastf128 Vqq,Mdq (66),(v) | vbroadcastf32x4/64x2 Vqq,Wq (66),(evo) +1b: vbroadcastf32x8/64x4 Vqq,Mdq (66),(ev) 1c: pabsb Pq,Qq | vpabsb Vx,Wx (66),(v1) 1d: pabsw Pq,Qq | vpabsw Vx,Wx (66),(v1) 1e: pabsd Pq,Qq | vpabsd Vx,Wx (66),(v1) -1f: +1f: vpabsq Vx,Wx (66),(ev) # 0x0f 0x38 0x20-0x2f -20: vpmovsxbw Vx,Ux/Mq (66),(v1) -21: vpmovsxbd Vx,Ux/Md (66),(v1) -22: vpmovsxbq Vx,Ux/Mw (66),(v1) -23: vpmovsxwd Vx,Ux/Mq (66),(v1) -24: vpmovsxwq Vx,Ux/Md (66),(v1) -25: vpmovsxdq Vx,Ux/Mq (66),(v1) -26: -27: -28: vpmuldq Vx,Hx,Wx (66),(v1) -29: vpcmpeqq Vx,Hx,Wx (66),(v1) -2a: vmovntdqa Vx,Mx (66),(v1) +20: vpmovsxbw Vx,Ux/Mq (66),(v1) | vpmovswb Wx,Vx (F3),(ev) +21: vpmovsxbd Vx,Ux/Md (66),(v1) | vpmovsdb Wx,Vd (F3),(ev) +22: vpmovsxbq Vx,Ux/Mw (66),(v1) | vpmovsqb Wx,Vq (F3),(ev) +23: vpmovsxwd Vx,Ux/Mq (66),(v1) | vpmovsdw Wx,Vd (F3),(ev) +24: vpmovsxwq Vx,Ux/Md (66),(v1) | vpmovsqw Wx,Vq (F3),(ev) +25: vpmovsxdq Vx,Ux/Mq (66),(v1) | vpmovsqd Wx,Vq (F3),(ev) +26: vptestmb/w Vk,Hx,Wx (66),(ev) | vptestnmb/w Vk,Hx,Wx (F3),(ev) +27: vptestmd/q Vk,Hx,Wx (66),(ev) | vptestnmd/q Vk,Hx,Wx (F3),(ev) +28: vpmuldq Vx,Hx,Wx (66),(v1) | vpmovm2b/w Vx,Uk (F3),(ev) +29: vpcmpeqq Vx,Hx,Wx (66),(v1) | vpmovb2m/w2m Vk,Ux (F3),(ev) +2a: vmovntdqa Vx,Mx (66),(v1) | vpbroadcastmb2q Vx,Uk (F3),(ev) 2b: vpackusdw Vx,Hx,Wx (66),(v1) -2c: vmaskmovps Vx,Hx,Mx (66),(v) -2d: vmaskmovpd Vx,Hx,Mx (66),(v) +2c: vmaskmovps Vx,Hx,Mx (66),(v) | vscalefps/d Vx,Hx,Wx (66),(evo) +2d: vmaskmovpd Vx,Hx,Mx (66),(v) | vscalefss/d Vx,Hx,Wx (66),(evo) 2e: vmaskmovps Mx,Hx,Vx (66),(v) 2f: vmaskmovpd Mx,Hx,Vx (66),(v) # 0x0f 0x38 0x30-0x3f -30: vpmovzxbw Vx,Ux/Mq (66),(v1) -31: vpmovzxbd Vx,Ux/Md (66),(v1) -32: vpmovzxbq Vx,Ux/Mw (66),(v1) -33: vpmovzxwd Vx,Ux/Mq (66),(v1) -34: vpmovzxwq Vx,Ux/Md (66),(v1) -35: vpmovzxdq Vx,Ux/Mq (66),(v1) -36: vpermd Vqq,Hqq,Wqq (66),(v) +30: vpmovzxbw Vx,Ux/Mq (66),(v1) | vpmovwb Wx,Vx (F3),(ev) +31: vpmovzxbd Vx,Ux/Md (66),(v1) | vpmovdb Wx,Vd (F3),(ev) +32: vpmovzxbq Vx,Ux/Mw (66),(v1) | vpmovqb Wx,Vq (F3),(ev) +33: vpmovzxwd Vx,Ux/Mq (66),(v1) | vpmovdw Wx,Vd (F3),(ev) +34: vpmovzxwq Vx,Ux/Md (66),(v1) | vpmovqw Wx,Vq (F3),(ev) +35: vpmovzxdq Vx,Ux/Mq (66),(v1) | vpmovqd Wx,Vq (F3),(ev) +36: vpermd Vqq,Hqq,Wqq (66),(v) | vpermd/q Vqq,Hqq,Wqq (66),(evo) 37: vpcmpgtq Vx,Hx,Wx (66),(v1) -38: vpminsb Vx,Hx,Wx (66),(v1) -39: vpminsd Vx,Hx,Wx (66),(v1) -3a: vpminuw Vx,Hx,Wx (66),(v1) -3b: vpminud Vx,Hx,Wx (66),(v1) +38: vpminsb Vx,Hx,Wx (66),(v1) | vpmovm2d/q Vx,Uk (F3),(ev) +39: vpminsd Vx,Hx,Wx (66),(v1) | vpminsd/q Vx,Hx,Wx (66),(evo) | vpmovd2m/q2m Vk,Ux (F3),(ev) +3a: vpminuw Vx,Hx,Wx (66),(v1) | vpbroadcastmw2d Vx,Uk (F3),(ev) +3b: vpminud Vx,Hx,Wx (66),(v1) | vpminud/q Vx,Hx,Wx (66),(evo) 3c: vpmaxsb Vx,Hx,Wx (66),(v1) -3d: vpmaxsd Vx,Hx,Wx (66),(v1) +3d: vpmaxsd Vx,Hx,Wx (66),(v1) | vpmaxsd/q Vx,Hx,Wx (66),(evo) 3e: vpmaxuw Vx,Hx,Wx (66),(v1) -3f: vpmaxud Vx,Hx,Wx (66),(v1) +3f: vpmaxud Vx,Hx,Wx (66),(v1) | vpmaxud/q Vx,Hx,Wx (66),(evo) # 0x0f 0x38 0x40-0x8f -40: vpmulld Vx,Hx,Wx (66),(v1) +40: vpmulld Vx,Hx,Wx (66),(v1) | vpmulld/q Vx,Hx,Wx (66),(evo) 41: vphminposuw Vdq,Wdq (66),(v1) -42: -43: -44: +42: vgetexpps/d Vx,Wx (66),(ev) +43: vgetexpss/d Vx,Hx,Wx (66),(ev) +44: vplzcntd/q Vx,Wx (66),(ev) 45: vpsrlvd/q Vx,Hx,Wx (66),(v) -46: vpsravd Vx,Hx,Wx (66),(v) +46: vpsravd Vx,Hx,Wx (66),(v) | vpsravd/q Vx,Hx,Wx (66),(evo) 47: vpsllvd/q Vx,Hx,Wx (66),(v) -# Skip 0x48-0x57 +# Skip 0x48-0x4b +4c: vrcp14ps/d Vpd,Wpd (66),(ev) +4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev) +4e: vrsqrt14ps/d Vpd,Wpd (66),(ev) +4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev) +# Skip 0x50-0x57 58: vpbroadcastd Vx,Wx (66),(v) -59: vpbroadcastq Vx,Wx (66),(v) -5a: vbroadcasti128 Vqq,Mdq (66),(v) -# Skip 0x5b-0x77 +59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo) +5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo) +5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev) +# Skip 0x5c-0x63 +64: vpblendmd/q Vx,Hx,Wx (66),(ev) +65: vblendmps/d Vx,Hx,Wx (66),(ev) +66: vpblendmb/w Vx,Hx,Wx (66),(ev) +# Skip 0x67-0x74 +75: vpermi2b/w Vx,Hx,Wx (66),(ev) +76: vpermi2d/q Vx,Hx,Wx (66),(ev) +77: vpermi2ps/d Vx,Hx,Wx (66),(ev) 78: vpbroadcastb Vx,Wx (66),(v) 79: vpbroadcastw Vx,Wx (66),(v) -# Skip 0x7a-0x7f +7a: vpbroadcastb Vx,Rv (66),(ev) +7b: vpbroadcastw Vx,Rv (66),(ev) +7c: vpbroadcastd/q Vx,Rv (66),(ev) +7d: vpermt2b/w Vx,Hx,Wx (66),(ev) +7e: vpermt2d/q Vx,Hx,Wx (66),(ev) +7f: vpermt2ps/d Vx,Hx,Wx (66),(ev) 80: INVEPT Gy,Mdq (66) 81: INVPID Gy,Mdq (66) 82: INVPCID Gy,Mdq (66) +83: vpmultishiftqb Vx,Hx,Wx (66),(ev) +88: vexpandps/d Vpd,Wpd (66),(ev) +89: vpexpandd/q Vx,Wx (66),(ev) +8a: vcompressps/d Wx,Vx (66),(ev) +8b: vpcompressd/q Wx,Vx (66),(ev) 8c: vpmaskmovd/q Vx,Hx,Mx (66),(v) +8d: vpermb/w Vx,Hx,Wx (66),(ev) 8e: vpmaskmovd/q Mx,Vx,Hx (66),(v) # 0x0f 0x38 0x90-0xbf (FMA) -90: vgatherdd/q Vx,Hx,Wx (66),(v) -91: vgatherqd/q Vx,Hx,Wx (66),(v) +90: vgatherdd/q Vx,Hx,Wx (66),(v) | vpgatherdd/q Vx,Wx (66),(evo) +91: vgatherqd/q Vx,Hx,Wx (66),(v) | vpgatherqd/q Vx,Wx (66),(evo) 92: vgatherdps/d Vx,Hx,Wx (66),(v) 93: vgatherqps/d Vx,Hx,Wx (66),(v) 94: @@ -715,6 +744,10 @@ AVXcode: 2 9d: vfnmadd132ss/d Vx,Hx,Wx (66),(v),(v1) 9e: vfnmsub132ps/d Vx,Hx,Wx (66),(v) 9f: vfnmsub132ss/d Vx,Hx,Wx (66),(v),(v1) +a0: vpscatterdd/q Wx,Vx (66),(ev) +a1: vpscatterqd/q Wx,Vx (66),(ev) +a2: vscatterdps/d Wx,Vx (66),(ev) +a3: vscatterqps/d Wx,Vx (66),(ev) a6: vfmaddsub213ps/d Vx,Hx,Wx (66),(v) a7: vfmsubadd213ps/d Vx,Hx,Wx (66),(v) a8: vfmadd213ps/d Vx,Hx,Wx (66),(v) @@ -725,6 +758,8 @@ ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v) ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1) ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v) af: vfnmsub213ss/d Vx,Hx,Wx (66),(v),(v1) +b4: vpmadd52luq Vx,Hx,Wx (66),(ev) +b5: vpmadd52huq Vx,Hx,Wx (66),(ev) b6: vfmaddsub231ps/d Vx,Hx,Wx (66),(v) b7: vfmsubadd231ps/d Vx,Hx,Wx (66),(v) b8: vfmadd231ps/d Vx,Hx,Wx (66),(v) @@ -736,12 +771,15 @@ bd: vfnmadd231ss/d Vx,Hx,Wx (66),(v),(v1) be: vfnmsub231ps/d Vx,Hx,Wx (66),(v) bf: vfnmsub231ss/d Vx,Hx,Wx (66),(v),(v1) # 0x0f 0x38 0xc0-0xff -c8: sha1nexte Vdq,Wdq +c4: vpconflictd/q Vx,Wx (66),(ev) +c6: Grp18 (1A) +c7: Grp19 (1A) +c8: sha1nexte Vdq,Wdq | vexp2ps/d Vx,Wx (66),(ev) c9: sha1msg1 Vdq,Wdq -ca: sha1msg2 Vdq,Wdq -cb: sha256rnds2 Vdq,Wdq -cc: sha256msg1 Vdq,Wdq -cd: sha256msg2 Vdq,Wdq +ca: sha1msg2 Vdq,Wdq | vrcp28ps/d Vx,Wx (66),(ev) +cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev) +cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev) +cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev) db: VAESIMC Vdq,Wdq (66),(v1) dc: VAESENC Vdq,Hdq,Wdq (66),(v1) dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1) @@ -763,15 +801,15 @@ AVXcode: 3 00: vpermq Vqq,Wqq,Ib (66),(v) 01: vpermpd Vqq,Wqq,Ib (66),(v) 02: vpblendd Vx,Hx,Wx,Ib (66),(v) -03: +03: valignd/q Vx,Hx,Wx,Ib (66),(ev) 04: vpermilps Vx,Wx,Ib (66),(v) 05: vpermilpd Vx,Wx,Ib (66),(v) 06: vperm2f128 Vqq,Hqq,Wqq,Ib (66),(v) 07: -08: vroundps Vx,Wx,Ib (66) -09: vroundpd Vx,Wx,Ib (66) -0a: vroundss Vss,Wss,Ib (66),(v1) -0b: vroundsd Vsd,Wsd,Ib (66),(v1) +08: vroundps Vx,Wx,Ib (66) | vrndscaleps Vx,Wx,Ib (66),(evo) +09: vroundpd Vx,Wx,Ib (66) | vrndscalepd Vx,Wx,Ib (66),(evo) +0a: vroundss Vss,Wss,Ib (66),(v1) | vrndscaless Vx,Hx,Wx,Ib (66),(evo) +0b: vroundsd Vsd,Wsd,Ib (66),(v1) | vrndscalesd Vx,Hx,Wx,Ib (66),(evo) 0c: vblendps Vx,Hx,Wx,Ib (66) 0d: vblendpd Vx,Hx,Wx,Ib (66) 0e: vpblendw Vx,Hx,Wx,Ib (66),(v1) @@ -780,26 +818,51 @@ AVXcode: 3 15: vpextrw Rd/Mw,Vdq,Ib (66),(v1) 16: vpextrd/q Ey,Vdq,Ib (66),(v1) 17: vextractps Ed,Vdq,Ib (66),(v1) -18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v) -19: vextractf128 Wdq,Vqq,Ib (66),(v) +18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v) | vinsertf32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo) +19: vextractf128 Wdq,Vqq,Ib (66),(v) | vextractf32x4/64x2 Wdq,Vqq,Ib (66),(evo) +1a: vinsertf32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev) +1b: vextractf32x8/64x4 Wdq,Vqq,Ib (66),(ev) 1d: vcvtps2ph Wx,Vx,Ib (66),(v) +1e: vpcmpud/q Vk,Hd,Wd,Ib (66),(ev) +1f: vpcmpd/q Vk,Hd,Wd,Ib (66),(ev) 20: vpinsrb Vdq,Hdq,Ry/Mb,Ib (66),(v1) 21: vinsertps Vdq,Hdq,Udq/Md,Ib (66),(v1) 22: vpinsrd/q Vdq,Hdq,Ey,Ib (66),(v1) -38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v) -39: vextracti128 Wdq,Vqq,Ib (66),(v) +23: vshuff32x4/64x2 Vx,Hx,Wx,Ib (66),(ev) +25: vpternlogd/q Vx,Hx,Wx,Ib (66),(ev) +26: vgetmantps/d Vx,Wx,Ib (66),(ev) +27: vgetmantss/d Vx,Hx,Wx,Ib (66),(ev) +30: kshiftrb/w Vk,Uk,Ib (66),(v) +31: kshiftrd/q Vk,Uk,Ib (66),(v) +32: kshiftlb/w Vk,Uk,Ib (66),(v) +33: kshiftld/q Vk,Uk,Ib (66),(v) +38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v) | vinserti32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo) +39: vextracti128 Wdq,Vqq,Ib (66),(v) | vextracti32x4/64x2 Wdq,Vqq,Ib (66),(evo) +3a: vinserti32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev) +3b: vextracti32x8/64x4 Wdq,Vqq,Ib (66),(ev) +3e: vpcmpub/w Vk,Hk,Wx,Ib (66),(ev) +3f: vpcmpb/w Vk,Hk,Wx,Ib (66),(ev) 40: vdpps Vx,Hx,Wx,Ib (66) 41: vdppd Vdq,Hdq,Wdq,Ib (66),(v1) -42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) +42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) | vdbpsadbw Vx,Hx,Wx,Ib (66),(evo) +43: vshufi32x4/64x2 Vx,Hx,Wx,Ib (66),(ev) 44: vpclmulqdq Vdq,Hdq,Wdq,Ib (66),(v1) 46: vperm2i128 Vqq,Hqq,Wqq,Ib (66),(v) 4a: vblendvps Vx,Hx,Wx,Lx (66),(v) 4b: vblendvpd Vx,Hx,Wx,Lx (66),(v) 4c: vpblendvb Vx,Hx,Wx,Lx (66),(v1) +50: vrangeps/d Vx,Hx,Wx,Ib (66),(ev) +51: vrangess/d Vx,Hx,Wx,Ib (66),(ev) +54: vfixupimmps/d Vx,Hx,Wx,Ib (66),(ev) +55: vfixupimmss/d Vx,Hx,Wx,Ib (66),(ev) +56: vreduceps/d Vx,Wx,Ib (66),(ev) +57: vreducess/d Vx,Hx,Wx,Ib (66),(ev) 60: vpcmpestrm Vdq,Wdq,Ib (66),(v1) 61: vpcmpestri Vdq,Wdq,Ib (66),(v1) 62: vpcmpistrm Vdq,Wdq,Ib (66),(v1) 63: vpcmpistri Vdq,Wdq,Ib (66),(v1) +66: vfpclassps/d Vk,Wx,Ib (66),(ev) +67: vfpclassss/d Vk,Wx,Ib (66),(ev) cc: sha1rnds4 Vdq,Wdq,Ib df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1) f0: RORX Gy,Ey,Ib (F2),(v) @@ -927,8 +990,10 @@ GrpTable: Grp12 EndTable GrpTable: Grp13 +0: vprord/q Hx,Wx,Ib (66),(ev) +1: vprold/q Hx,Wx,Ib (66),(ev) 2: psrld Nq,Ib (11B) | vpsrld Hx,Ux,Ib (66),(11B),(v1) -4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1) +4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1) | vpsrad/q Hx,Ux,Ib (66),(evo) 6: pslld Nq,Ib (11B) | vpslld Hx,Ux,Ib (66),(11B),(v1) EndTable @@ -947,7 +1012,7 @@ GrpTable: Grp15 4: XSAVE 5: XRSTOR | lfence (11B) 6: XSAVEOPT | clwb (66) | mfence (11B) -7: clflush | clflushopt (66) | sfence (11B) | pcommit (66),(11B) +7: clflush | clflushopt (66) | sfence (11B) EndTable GrpTable: Grp16 @@ -963,6 +1028,20 @@ GrpTable: Grp17 3: BLSI By,Ey (v) EndTable +GrpTable: Grp18 +1: vgatherpf0dps/d Wx (66),(ev) +2: vgatherpf1dps/d Wx (66),(ev) +5: vscatterpf0dps/d Wx (66),(ev) +6: vscatterpf1dps/d Wx (66),(ev) +EndTable + +GrpTable: Grp19 +1: vgatherpf0qps/d Wx (66),(ev) +2: vgatherpf1qps/d Wx (66),(ev) +5: vscatterpf0qps/d Wx (66),(ev) +6: vscatterpf1qps/d Wx (66),(ev) +EndTable + # AMD's Prefetch Group GrpTable: GrpP 0: PREFETCH diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c index 17fa7fc34fdf..bd09d0effef8 100644 --- a/tools/objtool/builtin-check.c +++ b/tools/objtool/builtin-check.c @@ -107,6 +107,12 @@ static struct instruction *next_insn_same_sec(struct objtool_file *file, insn->offset < func->offset + func->len; \ insn = list_next_entry(insn, list)) +#define func_for_each_insn_continue_reverse(file, func, insn) \ + for (insn = list_prev_entry(insn, list); \ + &insn->list != &file->insn_list && \ + insn->sec == func->sec && insn->offset >= func->offset; \ + insn = list_prev_entry(insn, list)) + #define sec_for_each_insn_from(file, insn) \ for (; insn; insn = next_insn_same_sec(file, insn)) @@ -664,65 +670,95 @@ static int add_switch_table(struct objtool_file *file, struct symbol *func, return 0; } -static int add_func_switch_tables(struct objtool_file *file, - struct symbol *func) +/* + * find_switch_table() - Given a dynamic jump, find the switch jump table in + * .rodata associated with it. + * + * There are 3 basic patterns: + * + * 1. jmpq *[rodata addr](,%reg,8) + * + * This is the most common case by far. It jumps to an address in a simple + * jump table which is stored in .rodata. + * + * 2. jmpq *[rodata addr](%rip) + * + * This is caused by a rare GCC quirk, currently only seen in three driver + * functions in the kernel, only with certain obscure non-distro configs. + * + * As part of an optimization, GCC makes a copy of an existing switch jump + * table, modifies it, and then hard-codes the jump (albeit with an indirect + * jump) to use a single entry in the table. The rest of the jump table and + * some of its jump targets remain as dead code. + * + * In such a case we can just crudely ignore all unreachable instruction + * warnings for the entire object file. Ideally we would just ignore them + * for the function, but that would require redesigning the code quite a + * bit. And honestly that's just not worth doing: unreachable instruction + * warnings are of questionable value anyway, and this is such a rare issue. + * + * 3. mov [rodata addr],%reg1 + * ... some instructions ... + * jmpq *(%reg1,%reg2,8) + * + * This is a fairly uncommon pattern which is new for GCC 6. As of this + * writing, there are 11 occurrences of it in the allmodconfig kernel. + * + * TODO: Once we have DWARF CFI and smarter instruction decoding logic, + * ensure the same register is used in the mov and jump instructions. + */ +static struct rela *find_switch_table(struct objtool_file *file, + struct symbol *func, + struct instruction *insn) { - struct instruction *insn, *prev_jump; - struct rela *text_rela, *rodata_rela, *prev_rela = NULL; - int ret; + struct rela *text_rela, *rodata_rela; - prev_jump = NULL; + text_rela = find_rela_by_dest_range(insn->sec, insn->offset, insn->len); + if (text_rela && text_rela->sym == file->rodata->sym) { + /* case 1 */ + rodata_rela = find_rela_by_dest(file->rodata, + text_rela->addend); + if (rodata_rela) + return rodata_rela; - func_for_each_insn(file, func, insn) { - if (insn->type != INSN_JUMP_DYNAMIC) - continue; + /* case 2 */ + rodata_rela = find_rela_by_dest(file->rodata, + text_rela->addend + 4); + if (!rodata_rela) + return NULL; + file->ignore_unreachables = true; + return rodata_rela; + } + + /* case 3 */ + func_for_each_insn_continue_reverse(file, func, insn) { + if (insn->type == INSN_JUMP_UNCONDITIONAL || + insn->type == INSN_JUMP_DYNAMIC) + break; text_rela = find_rela_by_dest_range(insn->sec, insn->offset, insn->len); - if (!text_rela || text_rela->sym != file->rodata->sym) - continue; + if (text_rela && text_rela->sym == file->rodata->sym) + return find_rela_by_dest(file->rodata, + text_rela->addend); + } - /* common case: jmpq *[addr](,%rax,8) */ - rodata_rela = find_rela_by_dest(file->rodata, - text_rela->addend); + return NULL; +} - /* - * rare case: jmpq *[addr](%rip) - * - * This check is for a rare gcc quirk, currently only seen in - * three driver functions in the kernel, only with certain - * obscure non-distro configs. - * - * As part of an optimization, gcc makes a copy of an existing - * switch jump table, modifies it, and then hard-codes the jump - * (albeit with an indirect jump) to use a single entry in the - * table. The rest of the jump table and some of its jump - * targets remain as dead code. - * - * In such a case we can just crudely ignore all unreachable - * instruction warnings for the entire object file. Ideally we - * would just ignore them for the function, but that would - * require redesigning the code quite a bit. And honestly - * that's just not worth doing: unreachable instruction - * warnings are of questionable value anyway, and this is such - * a rare issue. - * - * kbuild reports: - * - https://lkml.kernel.org/r/201603231906.LWcVUpxm%25fengguang.wu@intel.com - * - https://lkml.kernel.org/r/201603271114.K9i45biy%25fengguang.wu@intel.com - * - https://lkml.kernel.org/r/201603291058.zuJ6ben1%25fengguang.wu@intel.com - * - * gcc bug: - * - https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70604 - */ - if (!rodata_rela) { - rodata_rela = find_rela_by_dest(file->rodata, - text_rela->addend + 4); - if (rodata_rela) - file->ignore_unreachables = true; - } +static int add_func_switch_tables(struct objtool_file *file, + struct symbol *func) +{ + struct instruction *insn, *prev_jump = NULL; + struct rela *rela, *prev_rela = NULL; + int ret; - if (!rodata_rela) + func_for_each_insn(file, func, insn) { + if (insn->type != INSN_JUMP_DYNAMIC) + continue; + + rela = find_switch_table(file, func, insn); + if (!rela) continue; /* @@ -732,13 +768,13 @@ static int add_func_switch_tables(struct objtool_file *file, */ if (prev_jump) { ret = add_switch_table(file, func, prev_jump, prev_rela, - rodata_rela); + rela); if (ret) return ret; } prev_jump = insn; - prev_rela = rodata_rela; + prev_rela = rela; } if (prev_jump) { diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt index 736da44596e4..b303bcdd8ed1 100644 --- a/tools/perf/Documentation/perf-probe.txt +++ b/tools/perf/Documentation/perf-probe.txt @@ -176,10 +176,18 @@ Each probe argument follows below syntax. 'NAME' specifies the name of this argument (optional). You can use the name of local variable, local data structure member (e.g. var->field, var.field2), local array with fixed index (e.g. array[1], var->array[0], var->pointer[2]), or kprobe-tracer argument format (e.g. $retval, %ax, etc). Note that the name of this argument will be set as the last member name if you specify a local data structure member (e.g. field2 for 'var->field1.field2'.) '$vars' and '$params' special arguments are also available for NAME, '$vars' is expanded to the local variables (including function parameters) which can access at given probe point. '$params' is expanded to only the function parameters. -'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type. +'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. Currently, basic types (u8/u16/u32/u64/s8/s16/s32/s64), signedness casting (u/s), "string" and bitfield are supported. (see TYPES for detail) On x86 systems %REG is always the short form of the register: for example %AX. %RAX or %EAX is not valid. +TYPES +----- +Basic types (u8/u16/u32/u64/s8/s16/s32/s64) are integer types. Prefix 's' and 'u' means those types are signed and unsigned respectively. Traced arguments are shown in decimal (signed) or hex (unsigned). You can also use 's' or 'u' to specify only signedness and leave its size auto-detected by perf probe. +String type is a special type, which fetches a "null-terminated" string from kernel space. This means it will fail and store NULL if the string container has been paged out. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type. +Bitfield is another special type, which takes 3 parameters, bit-width, bit-offset, and container-size (usually 32). The syntax is; + + b<bit-width>@<bit-offset>/<container-size> + LINE SYNTAX ----------- Line range is described by following syntax. diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 69966abf65d1..379a2bed07c0 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -192,6 +192,9 @@ OPTIONS --period:: Record the sample period. +--sample-cpu:: + Record the sample cpu. + -n:: --no-samples:: Don't sample. diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 1f6c70594f0f..053bbbd84ece 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -116,8 +116,8 @@ OPTIONS --fields:: Comma separated list of fields to print. Options are: comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, - srcline, period, iregs, brstack, brstacksym, flags. - Field list can be prepended with the type, trace, sw or hw, + srcline, period, iregs, brstack, brstacksym, flags, bpf-output, + callindent. Field list can be prepended with the type, trace, sw or hw, to indicate to which event type the field list applies. e.g., -F sw:comm,tid,time,ip,sym and -F trace:time,cpu,trace diff --git a/tools/perf/config/Makefile b/tools/perf/Makefile.config index 24803c58049a..24803c58049a 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/Makefile.config diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 6641abb97f0a..2d9087501633 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -161,7 +161,7 @@ TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/ BPF_DIR = $(srctree)/tools/lib/bpf/ SUBCMD_DIR = $(srctree)/tools/lib/subcmd/ -# include config/Makefile by default and rule out +# include Makefile.config by default and rule out # non-config cases config := 1 @@ -183,7 +183,7 @@ ifeq ($(filter feature-dump,$(MAKECMDGOALS)),feature-dump) FEATURE_TESTS := all endif endif -include config/Makefile +include Makefile.config endif ifeq ($(config),0) @@ -706,7 +706,7 @@ $(INSTALL_DOC_TARGETS): ### Cleaning rules # -# This is here, not in config/Makefile, because config/Makefile does +# This is here, not in Makefile.config, because Makefile.config does # not get included for the clean target: # config-clean: diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c index c6d0f91731a1..35745a733100 100644 --- a/tools/perf/arch/powerpc/util/sym-handling.c +++ b/tools/perf/arch/powerpc/util/sym-handling.c @@ -54,10 +54,6 @@ int arch__compare_symbol_names(const char *namea, const char *nameb) #endif #if defined(_CALL_ELF) && _CALL_ELF == 2 -bool arch__prefers_symtab(void) -{ - return true; -} #ifdef HAVE_LIBELF_SUPPORT void arch__sym_update(struct symbol *s, GElf_Sym *sym) @@ -100,4 +96,29 @@ void arch__fix_tev_from_maps(struct perf_probe_event *pev, tev->point.offset += lep_offset; } } + +#ifdef HAVE_LIBELF_SUPPORT +void arch__post_process_probe_trace_events(struct perf_probe_event *pev, + int ntevs) +{ + struct probe_trace_event *tev; + struct map *map; + struct symbol *sym = NULL; + struct rb_node *tmp; + int i = 0; + + map = get_target_map(pev->target, pev->uprobes); + if (!map || map__load(map, NULL) < 0) + return; + + for (i = 0; i < ntevs; i++) { + tev = &pev->tevs[i]; + map__for_each_symbol(map, sym, tmp) { + if (map->unmap_ip(map, sym->start) == tev->point.address) + arch__fix_tev_from_maps(pev, tev, map, sym); + } + } +} +#endif /* HAVE_LIBELF_SUPPORT */ + #endif diff --git a/tools/perf/arch/s390/util/Build b/tools/perf/arch/s390/util/Build index 8a61372bb47a..5bd7b9260cc0 100644 --- a/tools/perf/arch/s390/util/Build +++ b/tools/perf/arch/s390/util/Build @@ -2,3 +2,5 @@ libperf-y += header.o libperf-y += kvm-stat.o libperf-$(CONFIG_DWARF) += dwarf-regs.o + +libperf-y += machine.o diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c new file mode 100644 index 000000000000..b9a95a1a8e69 --- /dev/null +++ b/tools/perf/arch/s390/util/machine.c @@ -0,0 +1,19 @@ +#include <unistd.h> +#include <stdio.h> +#include <string.h> +#include "util.h" +#include "machine.h" +#include "api/fs/fs.h" + +int arch__fix_module_text_start(u64 *start, const char *name) +{ + char path[PATH_MAX]; + + snprintf(path, PATH_MAX, "module/%.*s/sections/.text", + (int)strlen(name) - 2, name + 1); + + if (sysfs__read_ull(path, (unsigned long long *)start) < 0) + return -1; + + return 0; +} diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-32.c b/tools/perf/arch/x86/tests/insn-x86-dat-32.c index 3918dd52e903..0f196eec9f48 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-32.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-32.c @@ -1664,5 +1664,3 @@ "0f c7 1d 78 56 34 12 \txrstors 0x12345678",}, {{0x0f, 0xc7, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", "0f c7 9c c8 78 56 34 12 \txrstors 0x12345678(%eax,%ecx,8)",}, -{{0x66, 0x0f, 0xae, 0xf8, }, 4, 0, "", "", -"66 0f ae f8 \tpcommit ",}, diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-64.c b/tools/perf/arch/x86/tests/insn-x86-dat-64.c index 9c8c61e06d5a..af25bc8240d0 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-64.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-64.c @@ -1696,5 +1696,3 @@ "0f c7 9c c8 78 56 34 12 \txrstors 0x12345678(%rax,%rcx,8)",}, {{0x41, 0x0f, 0xc7, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", "41 0f c7 9c c8 78 56 34 12 \txrstors 0x12345678(%r8,%rcx,8)",}, -{{0x66, 0x0f, 0xae, 0xf8, }, 4, 0, "", "", -"66 0f ae f8 \tpcommit ",}, diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-src.c b/tools/perf/arch/x86/tests/insn-x86-dat-src.c index 76e0ec379c8b..979487dae8d4 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-src.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-src.c @@ -2655,10 +2655,6 @@ int main(void) #endif /* #ifndef __x86_64__ */ - /* pcommit */ - - asm volatile("pcommit"); - /* Following line is a marker for the awk script - do not change */ asm volatile("rdtsc"); /* Stop here */ diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index fb51457ba338..a2412e9d883b 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -501,7 +501,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, struct intel_pt_recording *ptr = container_of(itr, struct intel_pt_recording, itr); struct perf_pmu *intel_pt_pmu = ptr->intel_pt_pmu; - bool have_timing_info; + bool have_timing_info, need_immediate = false; struct perf_evsel *evsel, *intel_pt_evsel = NULL; const struct cpu_map *cpus = evlist->cpus; bool privileged = geteuid() == 0 || perf_event_paranoid() < 0; @@ -655,6 +655,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, ptr->have_sched_switch = 3; } else { opts->record_switch_events = true; + need_immediate = true; if (cpu_wide) ptr->have_sched_switch = 3; else @@ -700,6 +701,9 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, tracking_evsel->attr.freq = 0; tracking_evsel->attr.sample_period = 1; + if (need_immediate) + tracking_evsel->immediate = true; + /* In per-cpu case, always need the time of mmap events etc */ if (!cpu_map__empty(cpus)) { perf_evsel__set_sample_bit(tracking_evsel, TIME); diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index b1d491c2e704..fdde1bd3e306 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -608,6 +608,7 @@ static const struct { const char *compact; } gfp_compact_table[] = { { "GFP_TRANSHUGE", "THP" }, + { "GFP_TRANSHUGE_LIGHT", "THL" }, { "GFP_HIGHUSER_MOVABLE", "HUM" }, { "GFP_HIGHUSER", "HU" }, { "GFP_USER", "U" }, diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index d608a2c9e48c..d1ce29be560e 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -88,6 +88,9 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) if (mem->operation & MEM_OPERATION_LOAD) perf_mem_events[PERF_MEM_EVENTS__LOAD].record = true; + if (mem->operation & MEM_OPERATION_STORE) + perf_mem_events[PERF_MEM_EVENTS__STORE].record = true; + if (perf_mem_events[PERF_MEM_EVENTS__LOAD].record) rec_argv[i++] = "-W"; diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 8f2c16d9275f..6355902fbfc8 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1434,6 +1434,7 @@ struct option __record_options[] = { OPT_BOOLEAN('s', "stat", &record.opts.inherit_stat, "per thread counts"), OPT_BOOLEAN('d', "data", &record.opts.sample_address, "Record the sample addresses"), + OPT_BOOLEAN(0, "sample-cpu", &record.opts.sample_cpu, "Record the sample cpu"), OPT_BOOLEAN_SET('T', "timestamp", &record.opts.sample_time, &record.opts.sample_time_set, "Record the sample timestamps"), diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 971ff91b16cb..c859e59dfe3e 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -371,14 +371,16 @@ static int perf_session__check_output_opt(struct perf_session *session) if (!no_callchain) { bool use_callchain = false; + bool not_pipe = false; evlist__for_each_entry(session->evlist, evsel) { + not_pipe = true; if (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) { use_callchain = true; break; } } - if (!use_callchain) + if (not_pipe && !use_callchain) symbol_conf.use_callchain = false; } @@ -1690,8 +1692,13 @@ static int list_available_scripts(const struct option *opt __maybe_unused, snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path()); scripts_dir = opendir(scripts_path); - if (!scripts_dir) - return -1; + if (!scripts_dir) { + fprintf(stdout, + "open(%s) failed.\n" + "Check \"PERF_EXEC_PATH\" env to set scripts dir.\n", + scripts_path); + exit(-1); + } for_each_lang(scripts_path, scripts_dir, lang_dirent) { snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path, @@ -2116,7 +2123,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) "Valid types: hw,sw,trace,raw. " "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso," "addr,symoff,period,iregs,brstack,brstacksym,flags," - "callindent", parse_output_fields), + "bpf-output,callindent", parse_output_fields), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]", diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 0c16d20d7e32..3c7452b39f57 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -331,7 +331,7 @@ static int read_counter(struct perf_evsel *counter) return 0; } -static void read_counters(bool close_counters) +static void read_counters(void) { struct perf_evsel *counter; @@ -341,11 +341,6 @@ static void read_counters(bool close_counters) if (perf_stat_process_counter(&stat_config, counter)) pr_warning("failed to process counter %s\n", counter->name); - - if (close_counters) { - perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), - thread_map__nr(evsel_list->threads)); - } } } @@ -353,7 +348,7 @@ static void process_interval(void) { struct timespec ts, rs; - read_counters(false); + read_counters(); clock_gettime(CLOCK_MONOTONIC, &ts); diff_timespec(&rs, &ts, &ref_time); @@ -380,6 +375,17 @@ static void enable_counters(void) perf_evlist__enable(evsel_list); } +static void disable_counters(void) +{ + /* + * If we don't have tracee (attaching to task or cpu), counters may + * still be running. To get accurate group ratios, we must stop groups + * from counting before reading their constituent counters. + */ + if (!target__none(&target)) + perf_evlist__disable(evsel_list); +} + static volatile int workload_exec_errno; /* @@ -657,11 +663,20 @@ try_again: } } + disable_counters(); + t1 = rdclock(); update_stats(&walltime_nsecs_stats, t1 - t0); - read_counters(true); + /* + * Closing a group leader splits the group, and as we only disable + * group leaders, results in remaining events becoming enabled. To + * avoid arbitrary skew, we must read all counters before closing any + * group leaders. + */ + read_counters(); + perf_evlist__close(evsel_list); return WEXITSTATUS(status); } diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index bd108683fcb8..418ed94756d3 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -128,10 +128,14 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he) return err; } - err = symbol__annotate(sym, map, 0); + err = symbol__disassemble(sym, map, 0); if (err == 0) { out_assign: top->sym_filter_entry = he; + } else { + char msg[BUFSIZ]; + symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg)); + pr_err("Couldn't annotate %s: %s\n", sym->name, msg); } pthread_mutex_unlock(¬es->lock); diff --git a/tools/perf/perf.h b/tools/perf/perf.h index a7e0f1497244..cb0f1356ff81 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -52,6 +52,7 @@ struct record_opts { bool sample_weight; bool sample_time; bool sample_time_set; + bool sample_cpu; bool period; bool running_time; bool full_auxtrace; diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/Build b/tools/perf/scripts/perl/Perf-Trace-Util/Build index 928e110179cb..34faecf774ae 100644 --- a/tools/perf/scripts/perl/Perf-Trace-Util/Build +++ b/tools/perf/scripts/perl/Perf-Trace-Util/Build @@ -1,3 +1,5 @@ libperf-y += Context.o -CFLAGS_Context.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs -Wno-undef -Wno-switch-default +CFLAGS_Context.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes +CFLAGS_Context.o += -Wno-unused-parameter -Wno-nested-externs -Wno-undef +CFLAGS_Context.o += -Wno-switch-default -Wno-shadow diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index cb20ae1c0d35..dc51bc570e51 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -41,6 +41,7 @@ perf-y += event-times.o perf-y += backward-ring-buffer.o perf-y += sdt.o perf-y += is_printable_array.o +perf-y += bitmap.o $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build $(call rule_mkdir) diff --git a/tools/perf/tests/bitmap.c b/tools/perf/tests/bitmap.c new file mode 100644 index 000000000000..9abe6c13090f --- /dev/null +++ b/tools/perf/tests/bitmap.c @@ -0,0 +1,53 @@ +#include <linux/compiler.h> +#include <linux/bitmap.h> +#include "tests.h" +#include "cpumap.h" +#include "debug.h" + +#define NBITS 100 + +static unsigned long *get_bitmap(const char *str, int nbits) +{ + struct cpu_map *map = cpu_map__new(str); + unsigned long *bm = NULL; + int i; + + bm = bitmap_alloc(nbits); + + if (map && bm) { + bitmap_zero(bm, nbits); + + for (i = 0; i < map->nr; i++) + set_bit(map->map[i], bm); + } + + if (map) + cpu_map__put(map); + return bm; +} + +static int test_bitmap(const char *str) +{ + unsigned long *bm = get_bitmap(str, NBITS); + char buf[100]; + int ret; + + bitmap_scnprintf(bm, NBITS, buf, sizeof(buf)); + pr_debug("bitmap: %s\n", buf); + + ret = !strcmp(buf, str); + free(bm); + return ret; +} + +int test__bitmap_print(int subtest __maybe_unused) +{ + TEST_ASSERT_VAL("failed to convert map", test_bitmap("1")); + TEST_ASSERT_VAL("failed to convert map", test_bitmap("1,5")); + TEST_ASSERT_VAL("failed to convert map", test_bitmap("1,3,5,7,9,11,13,15,17,19,21-40")); + TEST_ASSERT_VAL("failed to convert map", test_bitmap("2-5")); + TEST_ASSERT_VAL("failed to convert map", test_bitmap("1,3-6,8-10,24,35-37")); + TEST_ASSERT_VAL("failed to convert map", test_bitmap("1,3-6,8-10,24,35-37")); + TEST_ASSERT_VAL("failed to convert map", test_bitmap("1-10,12-20,22-30,32-40")); + return 0; +} diff --git a/tools/perf/tests/bpf-script-example.c b/tools/perf/tests/bpf-script-example.c index e53bc91fa260..268e5f8e4aa2 100644 --- a/tools/perf/tests/bpf-script-example.c +++ b/tools/perf/tests/bpf-script-example.c @@ -31,8 +31,8 @@ struct bpf_map_def SEC("maps") flip_table = { .max_entries = 1, }; -SEC("func=sys_epoll_wait") -int bpf_func__sys_epoll_wait(void *ctx) +SEC("func=SyS_epoll_wait") +int bpf_func__SyS_epoll_wait(void *ctx) { int ind =0; int *flag = bpf_map_lookup_elem(&flip_table, &ind); diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 10eb30686c9c..778668a2a966 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -226,6 +226,10 @@ static struct test generic_tests[] = { .func = test__is_printable_array, }, { + .desc = "Test bitmap print", + .func = test__bitmap_print, + }, + { .func = NULL, }, }; diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 68a69a195545..2af156a8d4e5 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -33,44 +33,86 @@ static unsigned int hex(char c) return c - 'A' + 10; } -static size_t read_objdump_line(const char *line, size_t line_len, void *buf, - size_t len) +static size_t read_objdump_chunk(const char **line, unsigned char **buf, + size_t *buf_len) { - const char *p; - size_t i, j = 0; - - /* Skip to a colon */ - p = strchr(line, ':'); - if (!p) - return 0; - i = p + 1 - line; + size_t bytes_read = 0; + unsigned char *chunk_start = *buf; /* Read bytes */ - while (j < len) { + while (*buf_len > 0) { char c1, c2; - /* Skip spaces */ - for (; i < line_len; i++) { - if (!isspace(line[i])) - break; - } /* Get 2 hex digits */ - if (i >= line_len || !isxdigit(line[i])) + c1 = *(*line)++; + if (!isxdigit(c1)) break; - c1 = line[i++]; - if (i >= line_len || !isxdigit(line[i])) + c2 = *(*line)++; + if (!isxdigit(c2)) break; - c2 = line[i++]; - /* Followed by a space */ - if (i < line_len && line[i] && !isspace(line[i])) + + /* Store byte and advance buf */ + **buf = (hex(c1) << 4) | hex(c2); + (*buf)++; + (*buf_len)--; + bytes_read++; + + /* End of chunk? */ + if (isspace(**line)) break; - /* Store byte */ - *(unsigned char *)buf = (hex(c1) << 4) | hex(c2); - buf += 1; - j++; } + + /* + * objdump will display raw insn as LE if code endian + * is LE and bytes_per_chunk > 1. In that case reverse + * the chunk we just read. + * + * see disassemble_bytes() at binutils/objdump.c for details + * how objdump chooses display endian) + */ + if (bytes_read > 1 && !bigendian()) { + unsigned char *chunk_end = chunk_start + bytes_read - 1; + unsigned char tmp; + + while (chunk_start < chunk_end) { + tmp = *chunk_start; + *chunk_start = *chunk_end; + *chunk_end = tmp; + chunk_start++; + chunk_end--; + } + } + + return bytes_read; +} + +static size_t read_objdump_line(const char *line, unsigned char *buf, + size_t buf_len) +{ + const char *p; + size_t ret, bytes_read = 0; + + /* Skip to a colon */ + p = strchr(line, ':'); + if (!p) + return 0; + p++; + + /* Skip initial spaces */ + while (*p) { + if (!isspace(*p)) + break; + p++; + } + + do { + ret = read_objdump_chunk(&p, &buf, &buf_len); + bytes_read += ret; + p++; + } while (ret > 0); + /* return number of successfully read bytes */ - return j; + return bytes_read; } static int read_objdump_output(FILE *f, void *buf, size_t *len, u64 start_addr) @@ -95,7 +137,7 @@ static int read_objdump_output(FILE *f, void *buf, size_t *len, u64 start_addr) } /* read objdump data into temporary buffer */ - read_bytes = read_objdump_line(line, ret, tmp, sizeof(tmp)); + read_bytes = read_objdump_line(line, tmp, sizeof(tmp)); if (!read_bytes) continue; @@ -152,7 +194,7 @@ static int read_via_objdump(const char *filename, u64 addr, void *buf, ret = read_objdump_output(f, buf, &len, addr); if (len) { - pr_debug("objdump read too few bytes\n"); + pr_debug("objdump read too few bytes: %zd\n", len); if (!ret) ret = len; } diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index 9bfc0e06c61a..7c196c585472 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -90,6 +90,7 @@ int test__backward_ring_buffer(int subtest); int test__cpu_map_print(int subtest); int test__sdt_event(int subtest); int test__is_printable_array(int subtest); +int test__bitmap_print(int subtest); #if defined(__arm__) || defined(__aarch64__) #ifdef HAVE_DWARF_UNWIND_SUPPORT diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index 29dc6d20364e..2e2d10022355 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -1026,7 +1026,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, .use_navkeypressed = true, }, }; - int ret = -1; + int ret = -1, err; int nr_pcnt = 1; size_t sizeof_bdl = sizeof(struct browser_disasm_line); @@ -1050,8 +1050,11 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, (nr_pcnt - 1); } - if (symbol__annotate(sym, map, sizeof_bdl) < 0) { - ui__error("%s", ui_helpline__last_msg); + err = symbol__disassemble(sym, map, sizeof_bdl); + if (err) { + char msg[BUFSIZ]; + symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg)); + ui__error("Couldn't annotate %s:\n%s", sym->name, msg); goto out_free_offsets; } diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c index 9c7ff8d31b27..42d319927762 100644 --- a/tools/perf/ui/gtk/annotate.c +++ b/tools/perf/ui/gtk/annotate.c @@ -162,12 +162,16 @@ static int symbol__gtk_annotate(struct symbol *sym, struct map *map, GtkWidget *notebook; GtkWidget *scrolled_window; GtkWidget *tab_label; + int err; if (map->dso->annotate_warned) return -1; - if (symbol__annotate(sym, map, 0) < 0) { - ui__error("%s", ui_helpline__current); + err = symbol__disassemble(sym, map, 0); + if (err) { + char msg[BUFSIZ]; + symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg)); + ui__error("Couldn't annotate %s: %s\n", sym->name, msg); return -1; } diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 2fa7d8b69873..91c5f6e1af59 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -70,7 +70,6 @@ libperf-y += stat.o libperf-y += stat-shadow.o libperf-y += record.o libperf-y += srcline.o -libperf-y += str_error_r.o libperf-y += data.o libperf-y += tsc.o libperf-y += cloexec.o @@ -176,10 +175,6 @@ $(OUTPUT)util/libstring.o: ../lib/string.c FORCE $(call rule_mkdir) $(call if_changed_dep,cc_o_c) -$(OUTPUT)util/str_error_r.o: ../lib/str_error_r.c FORCE - $(call rule_mkdir) - $(call if_changed_dep,cc_o_c) - $(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE $(call rule_mkdir) $(call if_changed_dep,cc_o_c) diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index e9825fe825fd..4024d309bb00 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1123,7 +1123,46 @@ static void delete_last_nop(struct symbol *sym) } } -int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize) +int symbol__strerror_disassemble(struct symbol *sym __maybe_unused, struct map *map, + int errnum, char *buf, size_t buflen) +{ + struct dso *dso = map->dso; + + BUG_ON(buflen == 0); + + if (errnum >= 0) { + str_error_r(errnum, buf, buflen); + return 0; + } + + switch (errnum) { + case SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX: { + char bf[SBUILD_ID_SIZE + 15] = " with build id "; + char *build_id_msg = NULL; + + if (dso->has_build_id) { + build_id__sprintf(dso->build_id, + sizeof(dso->build_id), bf + 15); + build_id_msg = bf; + } + scnprintf(buf, buflen, + "No vmlinux file%s\nwas found in the path.\n\n" + "Note that annotation using /proc/kcore requires CAP_SYS_RAWIO capability.\n\n" + "Please use:\n\n" + " perf buildid-cache -vu vmlinux\n\n" + "or:\n\n" + " --vmlinux vmlinux\n", build_id_msg ?: ""); + } + break; + default: + scnprintf(buf, buflen, "Internal error: Invalid %d error code\n", errnum); + break; + } + + return 0; +} + +int symbol__disassemble(struct symbol *sym, struct map *map, size_t privsize) { struct dso *dso = map->dso; char *filename = dso__build_id_filename(dso, NULL, 0); @@ -1134,22 +1173,20 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize) char symfs_filename[PATH_MAX]; struct kcore_extract kce; bool delete_extract = false; + int stdout_fd[2]; int lineno = 0; int nline; + pid_t pid; if (filename) symbol__join_symfs(symfs_filename, filename); if (filename == NULL) { - if (dso->has_build_id) { - pr_err("Can't annotate %s: not enough memory\n", - sym->name); - return -ENOMEM; - } + if (dso->has_build_id) + return ENOMEM; goto fallback; - } else if (dso__is_kcore(dso)) { - goto fallback; - } else if (readlink(symfs_filename, command, sizeof(command)) < 0 || + } else if (dso__is_kcore(dso) || + readlink(symfs_filename, command, sizeof(command)) < 0 || strstr(command, DSO__NAME_KALLSYMS) || access(symfs_filename, R_OK)) { free(filename); @@ -1166,27 +1203,7 @@ fallback: if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS && !dso__is_kcore(dso)) { - char bf[SBUILD_ID_SIZE + 15] = " with build id "; - char *build_id_msg = NULL; - - if (dso->annotate_warned) - goto out_free_filename; - - if (dso->has_build_id) { - build_id__sprintf(dso->build_id, - sizeof(dso->build_id), bf + 15); - build_id_msg = bf; - } - err = -ENOENT; - dso->annotate_warned = 1; - pr_err("Can't annotate %s:\n\n" - "No vmlinux file%s\nwas found in the path.\n\n" - "Note that annotation using /proc/kcore requires CAP_SYS_RAWIO capability.\n\n" - "Please use:\n\n" - " perf buildid-cache -vu vmlinux\n\n" - "or:\n\n" - " --vmlinux vmlinux\n", - sym->name, build_id_msg ?: ""); + err = SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX; goto out_free_filename; } @@ -1258,9 +1275,32 @@ fallback: pr_debug("Executing: %s\n", command); - file = popen(command, "r"); + err = -1; + if (pipe(stdout_fd) < 0) { + pr_err("Failure creating the pipe to run %s\n", command); + goto out_remove_tmp; + } + + pid = fork(); + if (pid < 0) { + pr_err("Failure forking to run %s\n", command); + goto out_close_stdout; + } + + if (pid == 0) { + close(stdout_fd[0]); + dup2(stdout_fd[1], 1); + close(stdout_fd[1]); + execl("/bin/sh", "sh", "-c", command, NULL); + perror(command); + exit(-1); + } + + close(stdout_fd[1]); + + file = fdopen(stdout_fd[0], "r"); if (!file) { - pr_err("Failure running %s\n", command); + pr_err("Failure creating FILE stream for %s\n", command); /* * If we were using debug info should retry with * original binary. @@ -1286,9 +1326,11 @@ fallback: if (dso__is_kcore(dso)) delete_last_nop(sym); - pclose(file); - + fclose(file); + err = 0; out_remove_tmp: + close(stdout_fd[0]); + if (dso__needs_decompress(dso)) unlink(symfs_filename); out_free_filename: @@ -1297,6 +1339,10 @@ out_free_filename: if (free_filename) free(filename); return err; + +out_close_stdout: + close(stdout_fd[1]); + goto out_remove_tmp; } static void insert_source_line(struct rb_root *root, struct source_line *src_line) @@ -1663,7 +1709,7 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map, struct rb_root source_line = RB_ROOT; u64 len; - if (symbol__annotate(sym, map, 0) < 0) + if (symbol__disassemble(sym, map, 0) < 0) return -1; len = symbol__size(sym); diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index a23084f54128..f67ccb027561 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -155,7 +155,27 @@ int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 addr); int symbol__alloc_hist(struct symbol *sym); void symbol__annotate_zero_histograms(struct symbol *sym); -int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize); +int symbol__disassemble(struct symbol *sym, struct map *map, size_t privsize); + +enum symbol_disassemble_errno { + SYMBOL_ANNOTATE_ERRNO__SUCCESS = 0, + + /* + * Choose an arbitrary negative big number not to clash with standard + * errno since SUS requires the errno has distinct positive values. + * See 'Issue 6' in the link below. + * + * http://pubs.opengroup.org/onlinepubs/9699919799/basedefs/errno.h.html + */ + __SYMBOL_ANNOTATE_ERRNO__START = -10000, + + SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX = __SYMBOL_ANNOTATE_ERRNO__START, + + __SYMBOL_ANNOTATE_ERRNO__END, +}; + +int symbol__strerror_disassemble(struct symbol *sym, struct map *map, + int errnum, char *buf, size_t buflen); int symbol__annotate_init(struct map *map, struct symbol *sym); int symbol__annotate_printf(struct symbol *sym, struct map *map, diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 2a40b8e1def7..097b3ed77fdd 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -239,31 +239,13 @@ void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr) int perf_evlist__add_default(struct perf_evlist *evlist) { - struct perf_event_attr attr = { - .type = PERF_TYPE_HARDWARE, - .config = PERF_COUNT_HW_CPU_CYCLES, - }; - struct perf_evsel *evsel; - - event_attr_init(&attr); + struct perf_evsel *evsel = perf_evsel__new_cycles(); - perf_event_attr__set_max_precise_ip(&attr); - - evsel = perf_evsel__new(&attr); if (evsel == NULL) - goto error; - - /* use asprintf() because free(evsel) assumes name is allocated */ - if (asprintf(&evsel->name, "cycles%.*s", - attr.precise_ip ? attr.precise_ip + 1 : 0, ":ppp") < 0) - goto error_free; + return -ENOMEM; perf_evlist__add(evlist, evsel); return 0; -error_free: - perf_evsel__delete(evsel); -error: - return -ENOMEM; } int perf_evlist__add_dummy(struct perf_evlist *evlist) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 8c54df61fe64..21fd573106ed 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -253,6 +253,34 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) return evsel; } +struct perf_evsel *perf_evsel__new_cycles(void) +{ + struct perf_event_attr attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + }; + struct perf_evsel *evsel; + + event_attr_init(&attr); + + perf_event_attr__set_max_precise_ip(&attr); + + evsel = perf_evsel__new(&attr); + if (evsel == NULL) + goto out; + + /* use asprintf() because free(evsel) assumes name is allocated */ + if (asprintf(&evsel->name, "cycles%.*s", + attr.precise_ip ? attr.precise_ip + 1 : 0, ":ppp") < 0) + goto error_free; +out: + return evsel; +error_free: + perf_evsel__delete(evsel); + evsel = NULL; + goto out; +} + /* * Returns pointer with encoded error via <linux/err.h> interface. */ @@ -479,17 +507,17 @@ static int __perf_evsel__hw_cache_name(u64 config, char *bf, size_t size) u8 op, result, type = (config >> 0) & 0xff; const char *err = "unknown-ext-hardware-cache-type"; - if (type > PERF_COUNT_HW_CACHE_MAX) + if (type >= PERF_COUNT_HW_CACHE_MAX) goto out_err; op = (config >> 8) & 0xff; err = "unknown-ext-hardware-cache-op"; - if (op > PERF_COUNT_HW_CACHE_OP_MAX) + if (op >= PERF_COUNT_HW_CACHE_OP_MAX) goto out_err; result = (config >> 16) & 0xff; err = "unknown-ext-hardware-cache-result"; - if (result > PERF_COUNT_HW_CACHE_RESULT_MAX) + if (result >= PERF_COUNT_HW_CACHE_RESULT_MAX) goto out_err; err = "invalid-cache"; @@ -854,7 +882,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, perf_evsel__set_sample_bit(evsel, REGS_INTR); } - if (target__has_cpu(&opts->target)) + if (target__has_cpu(&opts->target) || opts->sample_cpu) perf_evsel__set_sample_bit(evsel, CPU); if (opts->period) diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 8a4a6c9f1480..4d44129e050b 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -175,6 +175,8 @@ static inline struct perf_evsel *perf_evsel__newtp(const char *sys, const char * return perf_evsel__newtp_idx(sys, name, 0); } +struct perf_evsel *perf_evsel__new_cycles(void); + struct event_format *event_format__new(const char *sys, const char *name); void perf_evsel__init(struct perf_evsel *evsel, diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index a18d142cdca3..de15dbcdcecf 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -1672,7 +1672,7 @@ static void __hists__insert_output_entry(struct rb_root *entries, } static void output_resort(struct hists *hists, struct ui_progress *prog, - bool use_callchain) + bool use_callchain, hists__resort_cb_t cb) { struct rb_root *root; struct rb_node *next; @@ -1711,6 +1711,9 @@ static void output_resort(struct hists *hists, struct ui_progress *prog, n = rb_entry(next, struct hist_entry, rb_node_in); next = rb_next(&n->rb_node_in); + if (cb && cb(n)) + continue; + __hists__insert_output_entry(&hists->entries, n, min_callchain_hits, use_callchain); hists__inc_stats(hists, n); @@ -1731,12 +1734,18 @@ void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *pro else use_callchain = symbol_conf.use_callchain; - output_resort(evsel__hists(evsel), prog, use_callchain); + output_resort(evsel__hists(evsel), prog, use_callchain, NULL); } void hists__output_resort(struct hists *hists, struct ui_progress *prog) { - output_resort(hists, prog, symbol_conf.use_callchain); + output_resort(hists, prog, symbol_conf.use_callchain, NULL); +} + +void hists__output_resort_cb(struct hists *hists, struct ui_progress *prog, + hists__resort_cb_t cb) +{ + output_resort(hists, prog, symbol_conf.use_callchain, cb); } static bool can_goto_child(struct hist_entry *he, enum hierarchy_move_dir hmd) diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 49aa4fac148f..0a1edf1ab450 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -153,8 +153,12 @@ int hist_entry__snprintf_alignment(struct hist_entry *he, struct perf_hpp *hpp, struct perf_hpp_fmt *fmt, int printed); void hist_entry__delete(struct hist_entry *he); +typedef int (*hists__resort_cb_t)(struct hist_entry *he); + void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *prog); void hists__output_resort(struct hists *hists, struct ui_progress *prog); +void hists__output_resort_cb(struct hists *hists, struct ui_progress *prog, + hists__resort_cb_t cb); int hists__collapse_resort(struct hists *hists, struct ui_progress *prog); void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel); diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index 9c8f15da86ce..8ff6c6a61291 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -123,8 +123,6 @@ struct intel_pt_decoder { bool have_calc_cyc_to_tsc; int exec_mode; unsigned int insn_bytes; - uint64_t sign_bit; - uint64_t sign_bits; uint64_t period; enum intel_pt_period_type period_type; uint64_t tot_insn_cnt; @@ -191,9 +189,6 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params) decoder->data = params->data; decoder->return_compression = params->return_compression; - decoder->sign_bit = (uint64_t)1 << 47; - decoder->sign_bits = ~(((uint64_t)1 << 48) - 1); - decoder->period = params->period; decoder->period_type = params->period_type; @@ -362,21 +357,30 @@ int intel_pt__strerror(int code, char *buf, size_t buflen) return 0; } -static uint64_t intel_pt_calc_ip(struct intel_pt_decoder *decoder, - const struct intel_pt_pkt *packet, +static uint64_t intel_pt_calc_ip(const struct intel_pt_pkt *packet, uint64_t last_ip) { uint64_t ip; switch (packet->count) { - case 2: + case 1: ip = (last_ip & (uint64_t)0xffffffffffff0000ULL) | packet->payload; break; - case 4: + case 2: ip = (last_ip & (uint64_t)0xffffffff00000000ULL) | packet->payload; break; + case 3: + ip = packet->payload; + /* Sign-extend 6-byte ip */ + if (ip & (uint64_t)0x800000000000ULL) + ip |= (uint64_t)0xffff000000000000ULL; + break; + case 4: + ip = (last_ip & (uint64_t)0xffff000000000000ULL) | + packet->payload; + break; case 6: ip = packet->payload; break; @@ -384,16 +388,12 @@ static uint64_t intel_pt_calc_ip(struct intel_pt_decoder *decoder, return 0; } - if (ip & decoder->sign_bit) - return ip | decoder->sign_bits; - return ip; } static inline void intel_pt_set_last_ip(struct intel_pt_decoder *decoder) { - decoder->last_ip = intel_pt_calc_ip(decoder, &decoder->packet, - decoder->last_ip); + decoder->last_ip = intel_pt_calc_ip(&decoder->packet, decoder->last_ip); } static inline void intel_pt_set_ip(struct intel_pt_decoder *decoder) @@ -1657,6 +1657,12 @@ next: } } +static inline bool intel_pt_have_ip(struct intel_pt_decoder *decoder) +{ + return decoder->last_ip || decoder->packet.count == 0 || + decoder->packet.count == 3 || decoder->packet.count == 6; +} + /* Walk PSB+ packets to get in sync. */ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder) { @@ -1677,8 +1683,7 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder) case INTEL_PT_FUP: decoder->pge = true; - if (decoder->last_ip || decoder->packet.count == 6 || - decoder->packet.count == 0) { + if (intel_pt_have_ip(decoder)) { uint64_t current_ip = decoder->ip; intel_pt_set_ip(decoder); @@ -1767,8 +1772,7 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder) case INTEL_PT_TIP_PGE: case INTEL_PT_TIP: decoder->pge = decoder->packet.type != INTEL_PT_TIP_PGD; - if (decoder->last_ip || decoder->packet.count == 6 || - decoder->packet.count == 0) + if (intel_pt_have_ip(decoder)) intel_pt_set_ip(decoder); if (decoder->ip) return 0; @@ -1776,9 +1780,7 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder) case INTEL_PT_FUP: if (decoder->overflow) { - if (decoder->last_ip || - decoder->packet.count == 6 || - decoder->packet.count == 0) + if (intel_pt_have_ip(decoder)) intel_pt_set_ip(decoder); if (decoder->ip) return 0; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c index b1257c816310..4f7b32020487 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c @@ -292,36 +292,46 @@ static int intel_pt_get_ip(enum intel_pt_pkt_type type, unsigned int byte, const unsigned char *buf, size_t len, struct intel_pt_pkt *packet) { - switch (byte >> 5) { + int ip_len; + + packet->count = byte >> 5; + + switch (packet->count) { case 0: - packet->count = 0; + ip_len = 0; break; case 1: if (len < 3) return INTEL_PT_NEED_MORE_BYTES; - packet->count = 2; + ip_len = 2; packet->payload = le16_to_cpu(*(uint16_t *)(buf + 1)); break; case 2: if (len < 5) return INTEL_PT_NEED_MORE_BYTES; - packet->count = 4; + ip_len = 4; packet->payload = le32_to_cpu(*(uint32_t *)(buf + 1)); break; case 3: - case 6: + case 4: if (len < 7) return INTEL_PT_NEED_MORE_BYTES; - packet->count = 6; + ip_len = 6; memcpy_le64(&packet->payload, buf + 1, 6); break; + case 6: + if (len < 9) + return INTEL_PT_NEED_MORE_BYTES; + ip_len = 8; + packet->payload = le64_to_cpu(*(uint64_t *)(buf + 1)); + break; default: return INTEL_PT_BAD_PACKET; } packet->type = type; - return packet->count + 1; + return ip_len + 1; } static int intel_pt_get_mode(const unsigned char *buf, size_t len, diff --git a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt index ec378cd7b71e..767be7c76034 100644 --- a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt +++ b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt @@ -1012,7 +1012,7 @@ GrpTable: Grp15 4: XSAVE 5: XRSTOR | lfence (11B) 6: XSAVEOPT | clwb (66) | mfence (11B) -7: clflush | clflushopt (66) | sfence (11B) | pcommit (66),(11B) +7: clflush | clflushopt (66) | sfence (11B) EndTable GrpTable: Grp16 diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c index 9f3305f6b6d5..95f0884aae02 100644 --- a/tools/perf/util/jitdump.c +++ b/tools/perf/util/jitdump.c @@ -1,3 +1,4 @@ +#include <sys/sysmacros.h> #include <sys/types.h> #include <stdio.h> #include <stdlib.h> diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index bc2cdbd09a25..cb6388dbdd98 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1093,12 +1093,20 @@ static int machine__set_modules_path(struct machine *machine) return map_groups__set_modules_path_dir(&machine->kmaps, modules_path, 0); } +int __weak arch__fix_module_text_start(u64 *start __maybe_unused, + const char *name __maybe_unused) +{ + return 0; +} static int machine__create_module(void *arg, const char *name, u64 start) { struct machine *machine = arg; struct map *map; + if (arch__fix_module_text_start(&start, name) < 0) + return -1; + map = machine__findnew_module_map(machine, start, name); if (map == NULL) return -1; diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 41ac9cfd416b..20739f746bc4 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -216,6 +216,7 @@ struct symbol *machine__find_kernel_function_by_name(struct machine *machine, struct map *machine__findnew_module_map(struct machine *machine, u64 start, const char *filename); +int arch__fix_module_text_start(u64 *start, const char *name); int __machine__load_kallsyms(struct machine *machine, const char *filename, enum map_type type, bool no_kcore, symbol_filter_t filter); diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 953dc1ab2ed7..28733962cd80 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -170,15 +170,17 @@ static struct map *kernel_get_module_map(const char *module) module = "kernel"; for (pos = maps__first(maps); pos; pos = map__next(pos)) { + /* short_name is "[module]" */ if (strncmp(pos->dso->short_name + 1, module, - pos->dso->short_name_len - 2) == 0) { + pos->dso->short_name_len - 2) == 0 && + module[pos->dso->short_name_len - 2] == '\0') { return pos; } } return NULL; } -static struct map *get_target_map(const char *target, bool user) +struct map *get_target_map(const char *target, bool user) { /* Init maps of given executable or kernel */ if (user) @@ -385,7 +387,7 @@ static int find_alternative_probe_point(struct debuginfo *dinfo, if (uprobes) address = sym->start; else - address = map->unmap_ip(map, sym->start); + address = map->unmap_ip(map, sym->start) - map->reloc; break; } if (!address) { @@ -664,22 +666,14 @@ static int add_module_to_probe_trace_events(struct probe_trace_event *tevs, return ret; } -/* Post processing the probe events */ -static int post_process_probe_trace_events(struct probe_trace_event *tevs, - int ntevs, const char *module, - bool uprobe) +static int +post_process_kernel_probe_trace_events(struct probe_trace_event *tevs, + int ntevs) { struct ref_reloc_sym *reloc_sym; char *tmp; int i, skipped = 0; - if (uprobe) - return add_exec_to_probe_trace_events(tevs, ntevs, module); - - /* Note that currently ref_reloc_sym based probe is not for drivers */ - if (module) - return add_module_to_probe_trace_events(tevs, ntevs, module); - reloc_sym = kernel_get_ref_reloc_sym(); if (!reloc_sym) { pr_warning("Relocated base symbol is not found!\n"); @@ -711,6 +705,34 @@ static int post_process_probe_trace_events(struct probe_trace_event *tevs, return skipped; } +void __weak +arch__post_process_probe_trace_events(struct perf_probe_event *pev __maybe_unused, + int ntevs __maybe_unused) +{ +} + +/* Post processing the probe events */ +static int post_process_probe_trace_events(struct perf_probe_event *pev, + struct probe_trace_event *tevs, + int ntevs, const char *module, + bool uprobe) +{ + int ret; + + if (uprobe) + ret = add_exec_to_probe_trace_events(tevs, ntevs, module); + else if (module) + /* Currently ref_reloc_sym based probe is not for drivers */ + ret = add_module_to_probe_trace_events(tevs, ntevs, module); + else + ret = post_process_kernel_probe_trace_events(tevs, ntevs); + + if (ret >= 0) + arch__post_process_probe_trace_events(pev, ntevs); + + return ret; +} + /* Try to find perf_probe_event with debuginfo */ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, struct probe_trace_event **tevs) @@ -749,7 +771,7 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, if (ntevs > 0) { /* Succeeded to find trace events */ pr_debug("Found %d probe_trace_events.\n", ntevs); - ret = post_process_probe_trace_events(*tevs, ntevs, + ret = post_process_probe_trace_events(pev, *tevs, ntevs, pev->target, pev->uprobes); if (ret < 0 || ret == ntevs) { clear_probe_trace_events(*tevs, ntevs); @@ -2936,8 +2958,6 @@ errout: return err; } -bool __weak arch__prefers_symtab(void) { return false; } - /* Concatinate two arrays */ static void *memcat(void *a, size_t sz_a, void *b, size_t sz_b) { @@ -3158,12 +3178,6 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev, if (ret > 0 || pev->sdt) /* SDT can be found only in the cache */ return ret == 0 ? -ENOENT : ret; /* Found in probe cache */ - if (arch__prefers_symtab() && !perf_probe_event_need_dwarf(pev)) { - ret = find_probe_trace_events_from_map(pev, tevs); - if (ret > 0) - return ret; /* Found in symbol table */ - } - /* Convert perf_probe_event with debuginfo */ ret = try_to_find_probe_trace_events(pev, tevs); if (ret != 0) diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index e18ea9fe6385..f4f45db77c1c 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -158,7 +158,6 @@ int show_line_range(struct line_range *lr, const char *module, bool user); int show_available_vars(struct perf_probe_event *pevs, int npevs, struct strfilter *filter); int show_available_funcs(const char *module, struct strfilter *filter, bool user); -bool arch__prefers_symtab(void); void arch__fix_tev_from_maps(struct perf_probe_event *pev, struct probe_trace_event *tev, struct map *map, struct symbol *sym); @@ -173,4 +172,9 @@ int e_snprintf(char *str, size_t size, const char *format, ...) int copy_to_probe_trace_arg(struct probe_trace_arg *tvar, struct perf_probe_arg *pvar); +struct map *get_target_map(const char *target, bool user); + +void arch__post_process_probe_trace_events(struct perf_probe_event *pev, + int ntevs); + #endif /*_PROBE_EVENT_H */ diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index 9aed9c332da6..9c3b9ed5b3c3 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -133,7 +133,7 @@ int probe_file__open_both(int *kfd, int *ufd, int flag) /* Get raw string list of current kprobe_events or uprobe_events */ struct strlist *probe_file__get_rawlist(int fd) { - int ret, idx; + int ret, idx, fddup; FILE *fp; char buf[MAX_CMDLEN]; char *p; @@ -143,8 +143,17 @@ struct strlist *probe_file__get_rawlist(int fd) return NULL; sl = strlist__new(NULL, NULL); + if (sl == NULL) + return NULL; + + fddup = dup(fd); + if (fddup < 0) + goto out_free_sl; + + fp = fdopen(fddup, "r"); + if (!fp) + goto out_close_fddup; - fp = fdopen(dup(fd), "r"); while (!feof(fp)) { p = fgets(buf, MAX_CMDLEN, fp); if (!p) @@ -156,13 +165,21 @@ struct strlist *probe_file__get_rawlist(int fd) ret = strlist__add(sl, buf); if (ret < 0) { pr_debug("strlist__add failed (%d)\n", ret); - strlist__delete(sl); - return NULL; + goto out_close_fp; } } fclose(fp); return sl; + +out_close_fp: + fclose(fp); + goto out_free_sl; +out_close_fddup: + close(fddup); +out_free_sl: + strlist__delete(sl); + return NULL; } static struct strlist *__probe_file__get_namelist(int fd, bool include_group) @@ -447,12 +464,17 @@ static int probe_cache__load(struct probe_cache *pcache) { struct probe_cache_entry *entry = NULL; char buf[MAX_CMDLEN], *p; - int ret = 0; + int ret = 0, fddup; FILE *fp; - fp = fdopen(dup(pcache->fd), "r"); - if (!fp) + fddup = dup(pcache->fd); + if (fddup < 0) + return -errno; + fp = fdopen(fddup, "r"); + if (!fp) { + close(fddup); return -EINVAL; + } while (!feof(fp)) { if (!fgets(buf, MAX_CMDLEN, fp)) diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index f2d9ff064e2d..5c290c682afe 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -297,10 +297,13 @@ static int convert_variable_type(Dwarf_Die *vr_die, char sbuf[STRERR_BUFSIZE]; int bsize, boffs, total; int ret; + char sign; /* TODO: check all types */ - if (cast && strcmp(cast, "string") != 0) { + if (cast && strcmp(cast, "string") != 0 && + strcmp(cast, "s") != 0 && strcmp(cast, "u") != 0) { /* Non string type is OK */ + /* and respect signedness cast */ tvar->type = strdup(cast); return (tvar->type == NULL) ? -ENOMEM : 0; } @@ -361,6 +364,13 @@ static int convert_variable_type(Dwarf_Die *vr_die, return (tvar->type == NULL) ? -ENOMEM : 0; } + if (cast && (strcmp(cast, "u") == 0)) + sign = 'u'; + else if (cast && (strcmp(cast, "s") == 0)) + sign = 's'; + else + sign = die_is_signed_type(&type) ? 's' : 'u'; + ret = dwarf_bytesize(&type); if (ret <= 0) /* No size ... try to use default type */ @@ -373,8 +383,7 @@ static int convert_variable_type(Dwarf_Die *vr_die, dwarf_diename(&type), MAX_BASIC_TYPE_BITS); ret = MAX_BASIC_TYPE_BITS; } - ret = snprintf(buf, 16, "%c%d", - die_is_signed_type(&type) ? 's' : 'u', ret); + ret = snprintf(buf, 16, "%c%d", sign, ret); formatted: if (ret < 0 || ret >= 16) { diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 5065ec98049c..b7d4f4aeee61 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -13,7 +13,6 @@ util/cpumap.c ../lib/bitmap.c ../lib/find_bit.c ../lib/hweight.c -../lib/str_error_r.c ../lib/vsprintf.c util/thread_map.c util/util.c diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 947d21f38398..3d3cb8392c86 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -588,7 +588,11 @@ static char *get_trace_output(struct hist_entry *he) } else { pevent_event_info(&seq, evsel->tp_format, &rec); } - return seq.buffer; + /* + * Trim the buffer, it starts at 4KB and we're not going to + * add anything more to this buffer. + */ + return realloc(seq.buffer, seq.len + 1); } static int64_t diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index a34321e9b44d..a811c13a74d6 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -837,7 +837,8 @@ int dso__load_sym(struct dso *dso, struct map *map, sec = syms_ss->symtab; shdr = syms_ss->symshdr; - if (elf_section_by_name(elf, &ehdr, &tshdr, ".text", NULL)) + if (elf_section_by_name(runtime_ss->elf, &runtime_ss->ehdr, &tshdr, + ".text", NULL)) dso->text_offset = tshdr.sh_addr - tshdr.sh_offset; if (runtime_ss->opdsec) diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c index 8cdcf4641c51..21c4d9b23c24 100644 --- a/tools/perf/util/target.c +++ b/tools/perf/util/target.c @@ -122,11 +122,7 @@ int target__strerror(struct target *target, int errnum, BUG_ON(buflen == 0); if (errnum >= 0) { - const char *err = str_error_r(errnum, buf, buflen); - - if (err != buf) - scnprintf(buf, buflen, "%s", err); - + str_error_r(errnum, buf, buflen); return 0; } diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index cf5e250bc78e..783a53fb7a4e 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -66,7 +66,7 @@ static int entry(u64 ip, struct unwind_info *ui) if (__report_module(&al, ip, ui)) return -1; - e->ip = ip; + e->ip = al.addr; e->map = al.map; e->sym = al.sym; diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 97c0f8fc5561..20c2e5743903 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -542,7 +542,7 @@ static int entry(u64 ip, struct thread *thread, thread__find_addr_location(thread, PERF_RECORD_MISC_USER, MAP__FUNCTION, ip, &al); - e.ip = ip; + e.ip = al.addr; e.map = al.map; e.sym = al.sym; diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild index 785985677159..ad6dd0543019 100644 --- a/tools/testing/nvdimm/Kbuild +++ b/tools/testing/nvdimm/Kbuild @@ -11,12 +11,14 @@ ldflags-y += --wrap=__devm_release_region ldflags-y += --wrap=__request_region ldflags-y += --wrap=__release_region ldflags-y += --wrap=devm_memremap_pages -ldflags-y += --wrap=phys_to_pfn_t +ldflags-y += --wrap=insert_resource +ldflags-y += --wrap=remove_resource DRIVERS := ../../../drivers NVDIMM_SRC := $(DRIVERS)/nvdimm -ACPI_SRC := $(DRIVERS)/acpi +ACPI_SRC := $(DRIVERS)/acpi/nfit DAX_SRC := $(DRIVERS)/dax +ccflags-y := -I$(src)/$(NVDIMM_SRC)/ obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o obj-$(CONFIG_BLK_DEV_PMEM) += nd_pmem.o @@ -27,10 +29,12 @@ obj-$(CONFIG_ACPI_NFIT) += nfit.o obj-$(CONFIG_DEV_DAX) += dax.o obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem.o -nfit-y := $(ACPI_SRC)/nfit.o +nfit-y := $(ACPI_SRC)/core.o +nfit-$(CONFIG_X86_MCE) += $(ACPI_SRC)/mce.o nfit-y += config_check.o nd_pmem-y := $(NVDIMM_SRC)/pmem.o +nd_pmem-y += pmem-dax.o nd_pmem-y += config_check.o nd_btt-y := $(NVDIMM_SRC)/btt.o diff --git a/tools/testing/nvdimm/config_check.c b/tools/testing/nvdimm/config_check.c index adf18bfeca00..878daf3429e8 100644 --- a/tools/testing/nvdimm/config_check.c +++ b/tools/testing/nvdimm/config_check.c @@ -10,6 +10,7 @@ void check(void) BUILD_BUG_ON(!IS_MODULE(CONFIG_LIBNVDIMM)); BUILD_BUG_ON(!IS_MODULE(CONFIG_BLK_DEV_PMEM)); BUILD_BUG_ON(!IS_MODULE(CONFIG_ND_BTT)); + BUILD_BUG_ON(!IS_MODULE(CONFIG_ND_PFN)); BUILD_BUG_ON(!IS_MODULE(CONFIG_ND_BLK)); BUILD_BUG_ON(!IS_MODULE(CONFIG_ACPI_NFIT)); BUILD_BUG_ON(!IS_MODULE(CONFIG_DEV_DAX)); diff --git a/tools/testing/nvdimm/pmem-dax.c b/tools/testing/nvdimm/pmem-dax.c new file mode 100644 index 000000000000..c9b8c48f85fc --- /dev/null +++ b/tools/testing/nvdimm/pmem-dax.c @@ -0,0 +1,54 @@ +/* + * Copyright (c) 2014-2016, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ +#include "test/nfit_test.h" +#include <linux/blkdev.h> +#include <pmem.h> +#include <nd.h> + +long pmem_direct_access(struct block_device *bdev, sector_t sector, + void **kaddr, pfn_t *pfn, long size) +{ + struct pmem_device *pmem = bdev->bd_queue->queuedata; + resource_size_t offset = sector * 512 + pmem->data_offset; + + if (unlikely(is_bad_pmem(&pmem->bb, sector, size))) + return -EIO; + + /* + * Limit dax to a single page at a time given vmalloc()-backed + * in the nfit_test case. + */ + if (get_nfit_res(pmem->phys_addr + offset)) { + struct page *page; + + *kaddr = pmem->virt_addr + offset; + page = vmalloc_to_page(pmem->virt_addr + offset); + *pfn = page_to_pfn_t(page); + dev_dbg_ratelimited(disk_to_dev(bdev->bd_disk)->parent, + "%s: sector: %#llx pfn: %#lx\n", __func__, + (unsigned long long) sector, page_to_pfn(page)); + + return PAGE_SIZE; + } + + *kaddr = pmem->virt_addr + offset; + *pfn = phys_to_pfn_t(pmem->phys_addr + offset, pmem->pfn_flags); + + /* + * If badblocks are present, limit known good range to the + * requested range. + */ + if (unlikely(pmem->bb.count)) + return size; + return pmem->size - pmem->pfn_pad - offset; +} diff --git a/tools/testing/nvdimm/test/Kbuild b/tools/testing/nvdimm/test/Kbuild index 9241064970fe..d32f25bba42a 100644 --- a/tools/testing/nvdimm/test/Kbuild +++ b/tools/testing/nvdimm/test/Kbuild @@ -1,5 +1,5 @@ ccflags-y := -I$(src)/../../../../drivers/nvdimm/ -ccflags-y += -I$(src)/../../../../drivers/acpi/ +ccflags-y += -I$(src)/../../../../drivers/acpi/nfit/ obj-m += nfit_test.o obj-m += nfit_test_iomap.o diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c index c842095f2801..c29f8dca9e67 100644 --- a/tools/testing/nvdimm/test/iomap.c +++ b/tools/testing/nvdimm/test/iomap.c @@ -10,11 +10,13 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * General Public License for more details. */ +#include <linux/memremap.h> #include <linux/rculist.h> #include <linux/export.h> #include <linux/ioport.h> #include <linux/module.h> #include <linux/types.h> +#include <linux/pfn_t.h> #include <linux/io.h> #include <linux/mm.h> #include "nfit_test.h" @@ -52,7 +54,7 @@ static struct nfit_test_resource *__get_nfit_res(resource_size_t resource) return NULL; } -static struct nfit_test_resource *get_nfit_res(resource_size_t resource) +struct nfit_test_resource *get_nfit_res(resource_size_t resource) { struct nfit_test_resource *res; @@ -62,6 +64,7 @@ static struct nfit_test_resource *get_nfit_res(resource_size_t resource) return res; } +EXPORT_SYMBOL(get_nfit_res); void __iomem *__nfit_test_ioremap(resource_size_t offset, unsigned long size, void __iomem *(*fallback_fn)(resource_size_t, unsigned long)) @@ -97,10 +100,6 @@ void *__wrap_devm_memremap(struct device *dev, resource_size_t offset, } EXPORT_SYMBOL(__wrap_devm_memremap); -#ifdef __HAVE_ARCH_PTE_DEVMAP -#include <linux/memremap.h> -#include <linux/pfn_t.h> - void *__wrap_devm_memremap_pages(struct device *dev, struct resource *res, struct percpu_ref *ref, struct vmem_altmap *altmap) { @@ -122,19 +121,6 @@ pfn_t __wrap_phys_to_pfn_t(phys_addr_t addr, unsigned long flags) return phys_to_pfn_t(addr, flags); } EXPORT_SYMBOL(__wrap_phys_to_pfn_t); -#else -/* to be removed post 4.5-rc1 */ -void *__wrap_devm_memremap_pages(struct device *dev, struct resource *res) -{ - resource_size_t offset = res->start; - struct nfit_test_resource *nfit_res = get_nfit_res(offset); - - if (nfit_res) - return nfit_res->buf + offset - nfit_res->res->start; - return devm_memremap_pages(dev, res); -} -EXPORT_SYMBOL(__wrap_devm_memremap_pages); -#endif void *__wrap_memremap(resource_size_t offset, size_t size, unsigned long flags) @@ -229,6 +215,22 @@ struct resource *__wrap___request_region(struct resource *parent, } EXPORT_SYMBOL(__wrap___request_region); +int __wrap_insert_resource(struct resource *parent, struct resource *res) +{ + if (get_nfit_res(res->start)) + return 0; + return insert_resource(parent, res); +} +EXPORT_SYMBOL(__wrap_insert_resource); + +int __wrap_remove_resource(struct resource *res) +{ + if (get_nfit_res(res->start)) + return 0; + return remove_resource(res); +} +EXPORT_SYMBOL(__wrap_remove_resource); + struct resource *__wrap___devm_request_region(struct device *dev, struct resource *parent, resource_size_t start, resource_size_t n, const char *name) diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index c919866853a0..dd48f421844c 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -13,6 +13,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/platform_device.h> #include <linux/dma-mapping.h> +#include <linux/workqueue.h> #include <linux/libnvdimm.h> #include <linux/vmalloc.h> #include <linux/device.h> @@ -98,11 +99,13 @@ enum { NUM_PM = 3, NUM_DCR = 5, + NUM_HINTS = 8, NUM_BDW = NUM_DCR, NUM_SPA = NUM_PM + NUM_DCR + NUM_BDW, NUM_MEM = NUM_DCR + NUM_BDW + 2 /* spa0 iset */ + 4 /* spa1 iset */, DIMM_SIZE = SZ_32M, LABEL_SIZE = SZ_128K, + SPA_VCD_SIZE = SZ_4M, SPA0_SIZE = DIMM_SIZE, SPA1_SIZE = DIMM_SIZE*2, SPA2_SIZE = DIMM_SIZE, @@ -470,11 +473,7 @@ static void release_nfit_res(void *data) list_del(&nfit_res->list); spin_unlock(&nfit_test_lock); - if (is_vmalloc_addr(nfit_res->buf)) - vfree(nfit_res->buf); - else - dma_free_coherent(nfit_res->dev, resource_size(res), - nfit_res->buf, res->start); + vfree(nfit_res->buf); kfree(res); kfree(nfit_res); } @@ -507,9 +506,7 @@ static void *__test_alloc(struct nfit_test *t, size_t size, dma_addr_t *dma, return nfit_res->buf; err: - if (buf && !is_vmalloc_addr(buf)) - dma_free_coherent(dev, size, buf, *dma); - else if (buf) + if (buf) vfree(buf); kfree(res); kfree(nfit_res); @@ -524,15 +521,6 @@ static void *test_alloc(struct nfit_test *t, size_t size, dma_addr_t *dma) return __test_alloc(t, size, dma, buf); } -static void *test_alloc_coherent(struct nfit_test *t, size_t size, - dma_addr_t *dma) -{ - struct device *dev = &t->pdev.dev; - void *buf = dma_alloc_coherent(dev, size, dma, GFP_KERNEL); - - return __test_alloc(t, size, dma, buf); -} - static struct nfit_test_resource *nfit_test_lookup(resource_size_t addr) { int i; @@ -584,7 +572,8 @@ static int nfit_test0_alloc(struct nfit_test *t) + offsetof(struct acpi_nfit_control_region, window_size) * NUM_DCR + sizeof(struct acpi_nfit_data_region) * NUM_BDW - + sizeof(struct acpi_nfit_flush_address) * NUM_DCR; + + (sizeof(struct acpi_nfit_flush_address) + + sizeof(u64) * NUM_HINTS) * NUM_DCR; int i; t->nfit_buf = test_alloc(t, nfit_size, &t->nfit_dma); @@ -592,15 +581,15 @@ static int nfit_test0_alloc(struct nfit_test *t) return -ENOMEM; t->nfit_size = nfit_size; - t->spa_set[0] = test_alloc_coherent(t, SPA0_SIZE, &t->spa_set_dma[0]); + t->spa_set[0] = test_alloc(t, SPA0_SIZE, &t->spa_set_dma[0]); if (!t->spa_set[0]) return -ENOMEM; - t->spa_set[1] = test_alloc_coherent(t, SPA1_SIZE, &t->spa_set_dma[1]); + t->spa_set[1] = test_alloc(t, SPA1_SIZE, &t->spa_set_dma[1]); if (!t->spa_set[1]) return -ENOMEM; - t->spa_set[2] = test_alloc_coherent(t, SPA0_SIZE, &t->spa_set_dma[2]); + t->spa_set[2] = test_alloc(t, SPA0_SIZE, &t->spa_set_dma[2]); if (!t->spa_set[2]) return -ENOMEM; @@ -614,7 +603,8 @@ static int nfit_test0_alloc(struct nfit_test *t) return -ENOMEM; sprintf(t->label[i], "label%d", i); - t->flush[i] = test_alloc(t, 8, &t->flush_dma[i]); + t->flush[i] = test_alloc(t, sizeof(u64) * NUM_HINTS, + &t->flush_dma[i]); if (!t->flush[i]) return -ENOMEM; } @@ -630,7 +620,7 @@ static int nfit_test0_alloc(struct nfit_test *t) static int nfit_test1_alloc(struct nfit_test *t) { - size_t nfit_size = sizeof(struct acpi_nfit_system_address) + size_t nfit_size = sizeof(struct acpi_nfit_system_address) * 2 + sizeof(struct acpi_nfit_memory_map) + offsetof(struct acpi_nfit_control_region, window_size); @@ -639,15 +629,31 @@ static int nfit_test1_alloc(struct nfit_test *t) return -ENOMEM; t->nfit_size = nfit_size; - t->spa_set[0] = test_alloc_coherent(t, SPA2_SIZE, &t->spa_set_dma[0]); + t->spa_set[0] = test_alloc(t, SPA2_SIZE, &t->spa_set_dma[0]); if (!t->spa_set[0]) return -ENOMEM; + t->spa_set[1] = test_alloc(t, SPA_VCD_SIZE, &t->spa_set_dma[1]); + if (!t->spa_set[1]) + return -ENOMEM; + return ars_state_init(&t->pdev.dev, &t->ars_state); } +static void dcr_common_init(struct acpi_nfit_control_region *dcr) +{ + dcr->vendor_id = 0xabcd; + dcr->device_id = 0; + dcr->revision_id = 1; + dcr->valid_fields = 1; + dcr->manufacturing_location = 0xa; + dcr->manufacturing_date = cpu_to_be16(2016); +} + static void nfit_test0_setup(struct nfit_test *t) { + const int flush_hint_size = sizeof(struct acpi_nfit_flush_address) + + (sizeof(u64) * NUM_HINTS); struct acpi_nfit_desc *acpi_desc; struct acpi_nfit_memory_map *memdev; void *nfit_buf = t->nfit_buf; @@ -655,7 +661,7 @@ static void nfit_test0_setup(struct nfit_test *t) struct acpi_nfit_control_region *dcr; struct acpi_nfit_data_region *bdw; struct acpi_nfit_flush_address *flush; - unsigned int offset; + unsigned int offset, i; /* * spa0 (interleave first half of dimm0 and dimm1, note storage @@ -972,9 +978,7 @@ static void nfit_test0_setup(struct nfit_test *t) dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION; dcr->header.length = sizeof(struct acpi_nfit_control_region); dcr->region_index = 0+1; - dcr->vendor_id = 0xabcd; - dcr->device_id = 0; - dcr->revision_id = 1; + dcr_common_init(dcr); dcr->serial_number = ~handle[0]; dcr->code = NFIT_FIC_BLK; dcr->windows = 1; @@ -989,9 +993,7 @@ static void nfit_test0_setup(struct nfit_test *t) dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION; dcr->header.length = sizeof(struct acpi_nfit_control_region); dcr->region_index = 1+1; - dcr->vendor_id = 0xabcd; - dcr->device_id = 0; - dcr->revision_id = 1; + dcr_common_init(dcr); dcr->serial_number = ~handle[1]; dcr->code = NFIT_FIC_BLK; dcr->windows = 1; @@ -1006,9 +1008,7 @@ static void nfit_test0_setup(struct nfit_test *t) dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION; dcr->header.length = sizeof(struct acpi_nfit_control_region); dcr->region_index = 2+1; - dcr->vendor_id = 0xabcd; - dcr->device_id = 0; - dcr->revision_id = 1; + dcr_common_init(dcr); dcr->serial_number = ~handle[2]; dcr->code = NFIT_FIC_BLK; dcr->windows = 1; @@ -1023,9 +1023,7 @@ static void nfit_test0_setup(struct nfit_test *t) dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION; dcr->header.length = sizeof(struct acpi_nfit_control_region); dcr->region_index = 3+1; - dcr->vendor_id = 0xabcd; - dcr->device_id = 0; - dcr->revision_id = 1; + dcr_common_init(dcr); dcr->serial_number = ~handle[3]; dcr->code = NFIT_FIC_BLK; dcr->windows = 1; @@ -1042,9 +1040,7 @@ static void nfit_test0_setup(struct nfit_test *t) dcr->header.length = offsetof(struct acpi_nfit_control_region, window_size); dcr->region_index = 4+1; - dcr->vendor_id = 0xabcd; - dcr->device_id = 0; - dcr->revision_id = 1; + dcr_common_init(dcr); dcr->serial_number = ~handle[0]; dcr->code = NFIT_FIC_BYTEN; dcr->windows = 0; @@ -1056,9 +1052,7 @@ static void nfit_test0_setup(struct nfit_test *t) dcr->header.length = offsetof(struct acpi_nfit_control_region, window_size); dcr->region_index = 5+1; - dcr->vendor_id = 0xabcd; - dcr->device_id = 0; - dcr->revision_id = 1; + dcr_common_init(dcr); dcr->serial_number = ~handle[1]; dcr->code = NFIT_FIC_BYTEN; dcr->windows = 0; @@ -1070,9 +1064,7 @@ static void nfit_test0_setup(struct nfit_test *t) dcr->header.length = offsetof(struct acpi_nfit_control_region, window_size); dcr->region_index = 6+1; - dcr->vendor_id = 0xabcd; - dcr->device_id = 0; - dcr->revision_id = 1; + dcr_common_init(dcr); dcr->serial_number = ~handle[2]; dcr->code = NFIT_FIC_BYTEN; dcr->windows = 0; @@ -1084,9 +1076,7 @@ static void nfit_test0_setup(struct nfit_test *t) dcr->header.length = offsetof(struct acpi_nfit_control_region, window_size); dcr->region_index = 7+1; - dcr->vendor_id = 0xabcd; - dcr->device_id = 0; - dcr->revision_id = 1; + dcr_common_init(dcr); dcr->serial_number = ~handle[3]; dcr->code = NFIT_FIC_BYTEN; dcr->windows = 0; @@ -1141,45 +1131,47 @@ static void nfit_test0_setup(struct nfit_test *t) /* flush0 (dimm0) */ flush = nfit_buf + offset; flush->header.type = ACPI_NFIT_TYPE_FLUSH_ADDRESS; - flush->header.length = sizeof(struct acpi_nfit_flush_address); + flush->header.length = flush_hint_size; flush->device_handle = handle[0]; - flush->hint_count = 1; - flush->hint_address[0] = t->flush_dma[0]; + flush->hint_count = NUM_HINTS; + for (i = 0; i < NUM_HINTS; i++) + flush->hint_address[i] = t->flush_dma[0] + i * sizeof(u64); /* flush1 (dimm1) */ - flush = nfit_buf + offset + sizeof(struct acpi_nfit_flush_address) * 1; + flush = nfit_buf + offset + flush_hint_size * 1; flush->header.type = ACPI_NFIT_TYPE_FLUSH_ADDRESS; - flush->header.length = sizeof(struct acpi_nfit_flush_address); + flush->header.length = flush_hint_size; flush->device_handle = handle[1]; - flush->hint_count = 1; - flush->hint_address[0] = t->flush_dma[1]; + flush->hint_count = NUM_HINTS; + for (i = 0; i < NUM_HINTS; i++) + flush->hint_address[i] = t->flush_dma[1] + i * sizeof(u64); /* flush2 (dimm2) */ - flush = nfit_buf + offset + sizeof(struct acpi_nfit_flush_address) * 2; + flush = nfit_buf + offset + flush_hint_size * 2; flush->header.type = ACPI_NFIT_TYPE_FLUSH_ADDRESS; - flush->header.length = sizeof(struct acpi_nfit_flush_address); + flush->header.length = flush_hint_size; flush->device_handle = handle[2]; - flush->hint_count = 1; - flush->hint_address[0] = t->flush_dma[2]; + flush->hint_count = NUM_HINTS; + for (i = 0; i < NUM_HINTS; i++) + flush->hint_address[i] = t->flush_dma[2] + i * sizeof(u64); /* flush3 (dimm3) */ - flush = nfit_buf + offset + sizeof(struct acpi_nfit_flush_address) * 3; + flush = nfit_buf + offset + flush_hint_size * 3; flush->header.type = ACPI_NFIT_TYPE_FLUSH_ADDRESS; - flush->header.length = sizeof(struct acpi_nfit_flush_address); + flush->header.length = flush_hint_size; flush->device_handle = handle[3]; - flush->hint_count = 1; - flush->hint_address[0] = t->flush_dma[3]; + flush->hint_count = NUM_HINTS; + for (i = 0; i < NUM_HINTS; i++) + flush->hint_address[i] = t->flush_dma[3] + i * sizeof(u64); if (t->setup_hotplug) { - offset = offset + sizeof(struct acpi_nfit_flush_address) * 4; + offset = offset + flush_hint_size * 4; /* dcr-descriptor4: blk */ dcr = nfit_buf + offset; dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION; dcr->header.length = sizeof(struct acpi_nfit_control_region); dcr->region_index = 8+1; - dcr->vendor_id = 0xabcd; - dcr->device_id = 0; - dcr->revision_id = 1; + dcr_common_init(dcr); dcr->serial_number = ~handle[4]; dcr->code = NFIT_FIC_BLK; dcr->windows = 1; @@ -1196,9 +1188,7 @@ static void nfit_test0_setup(struct nfit_test *t) dcr->header.length = offsetof(struct acpi_nfit_control_region, window_size); dcr->region_index = 9+1; - dcr->vendor_id = 0xabcd; - dcr->device_id = 0; - dcr->revision_id = 1; + dcr_common_init(dcr); dcr->serial_number = ~handle[4]; dcr->code = NFIT_FIC_BYTEN; dcr->windows = 0; @@ -1300,10 +1290,12 @@ static void nfit_test0_setup(struct nfit_test *t) /* flush3 (dimm4) */ flush = nfit_buf + offset; flush->header.type = ACPI_NFIT_TYPE_FLUSH_ADDRESS; - flush->header.length = sizeof(struct acpi_nfit_flush_address); + flush->header.length = flush_hint_size; flush->device_handle = handle[4]; - flush->hint_count = 1; - flush->hint_address[0] = t->flush_dma[4]; + flush->hint_count = NUM_HINTS; + for (i = 0; i < NUM_HINTS; i++) + flush->hint_address[i] = t->flush_dma[4] + + i * sizeof(u64); } post_ars_status(&t->ars_state, t->spa_set_dma[0], SPA0_SIZE); @@ -1339,7 +1331,16 @@ static void nfit_test1_setup(struct nfit_test *t) spa->address = t->spa_set_dma[0]; spa->length = SPA2_SIZE; - offset += sizeof(*spa); + /* virtual cd region */ + spa = nfit_buf + sizeof(*spa); + spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; + spa->header.length = sizeof(*spa); + memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_VCD), 16); + spa->range_index = 0; + spa->address = t->spa_set_dma[1]; + spa->length = SPA_VCD_SIZE; + + offset += sizeof(*spa) * 2; /* mem-region0 (spa0, dimm0) */ memdev = nfit_buf + offset; memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP; @@ -1365,9 +1366,7 @@ static void nfit_test1_setup(struct nfit_test *t) dcr->header.length = offsetof(struct acpi_nfit_control_region, window_size); dcr->region_index = 0+1; - dcr->vendor_id = 0xabcd; - dcr->device_id = 0; - dcr->revision_id = 1; + dcr_common_init(dcr); dcr->serial_number = ~0; dcr->code = NFIT_FIC_BYTE; dcr->windows = 0; @@ -1462,43 +1461,34 @@ static int nfit_test_probe(struct platform_device *pdev) nfit_test->setup(nfit_test); acpi_desc = &nfit_test->acpi_desc; acpi_nfit_desc_init(acpi_desc, &pdev->dev); - acpi_desc->nfit = nfit_test->nfit_buf; acpi_desc->blk_do_io = nfit_test_blk_do_io; nd_desc = &acpi_desc->nd_desc; nd_desc->provider_name = NULL; + nd_desc->module = THIS_MODULE; nd_desc->ndctl = nfit_test_ctl; - acpi_desc->nvdimm_bus = nvdimm_bus_register(&pdev->dev, nd_desc); - if (!acpi_desc->nvdimm_bus) - return -ENXIO; - rc = acpi_nfit_init(acpi_desc, nfit_test->nfit_size); - if (rc) { - nvdimm_bus_unregister(acpi_desc->nvdimm_bus); + rc = acpi_nfit_init(acpi_desc, nfit_test->nfit_buf, + nfit_test->nfit_size); + if (rc) return rc; - } if (nfit_test->setup != nfit_test0_setup) return 0; + flush_work(&acpi_desc->work); nfit_test->setup_hotplug = 1; nfit_test->setup(nfit_test); - rc = acpi_nfit_init(acpi_desc, nfit_test->nfit_size); - if (rc) { - nvdimm_bus_unregister(acpi_desc->nvdimm_bus); + rc = acpi_nfit_init(acpi_desc, nfit_test->nfit_buf, + nfit_test->nfit_size); + if (rc) return rc; - } return 0; } static int nfit_test_remove(struct platform_device *pdev) { - struct nfit_test *nfit_test = to_nfit_test(&pdev->dev); - struct acpi_nfit_desc *acpi_desc = &nfit_test->acpi_desc; - - nvdimm_bus_unregister(acpi_desc->nvdimm_bus); - return 0; } @@ -1523,12 +1513,6 @@ static struct platform_driver nfit_test_driver = { .id_table = nfit_test_id, }; -#ifdef CONFIG_CMA_SIZE_MBYTES -#define CMA_SIZE_MBYTES CONFIG_CMA_SIZE_MBYTES -#else -#define CMA_SIZE_MBYTES 0 -#endif - static __init int nfit_test_init(void) { int rc, i; @@ -1538,7 +1522,6 @@ static __init int nfit_test_init(void) for (i = 0; i < NUM_NFITS; i++) { struct nfit_test *nfit_test; struct platform_device *pdev; - static int once; nfit_test = kzalloc(sizeof(*nfit_test), GFP_KERNEL); if (!nfit_test) { @@ -1577,20 +1560,6 @@ static __init int nfit_test_init(void) goto err_register; instances[i] = nfit_test; - - if (!once++) { - dma_addr_t dma; - void *buf; - - buf = dma_alloc_coherent(&pdev->dev, SZ_128M, &dma, - GFP_KERNEL); - if (!buf) { - rc = -ENOMEM; - dev_warn(&pdev->dev, "need 128M of free cma\n"); - goto err_register; - } - dma_free_coherent(&pdev->dev, SZ_128M, buf, dma); - } } rc = platform_driver_register(&nfit_test_driver); diff --git a/tools/testing/nvdimm/test/nfit_test.h b/tools/testing/nvdimm/test/nfit_test.h index 96c5e16d7db9..9f18e2a4a862 100644 --- a/tools/testing/nvdimm/test/nfit_test.h +++ b/tools/testing/nvdimm/test/nfit_test.h @@ -12,6 +12,7 @@ */ #ifndef __NFIT_TEST_H__ #define __NFIT_TEST_H__ +#include <linux/list.h> struct nfit_test_resource { struct list_head list; @@ -26,4 +27,5 @@ void __iomem *__wrap_ioremap_nocache(resource_size_t offset, void __wrap_iounmap(volatile void __iomem *addr); void nfit_test_setup(nfit_test_lookup_fn lookup); void nfit_test_teardown(void); +struct nfit_test_resource *get_nfit_res(resource_size_t resource); #endif diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile index 3b530467148e..9d0919ed52a4 100644 --- a/tools/testing/radix-tree/Makefile +++ b/tools/testing/radix-tree/Makefile @@ -1,5 +1,5 @@ -CFLAGS += -I. -g -Wall -D_LGPL_SOURCE +CFLAGS += -I. -g -O2 -Wall -D_LGPL_SOURCE LDFLAGS += -lpthread -lurcu TARGETS = main OFILES = main.o radix-tree.o linux.o test.o tag_check.o find_next_bit.o \ diff --git a/tools/testing/radix-tree/linux/gfp.h b/tools/testing/radix-tree/linux/gfp.h index 0e37f7a760eb..5201b915f631 100644 --- a/tools/testing/radix-tree/linux/gfp.h +++ b/tools/testing/radix-tree/linux/gfp.h @@ -1,7 +1,7 @@ #ifndef _GFP_H #define _GFP_H -#define __GFP_BITS_SHIFT 22 +#define __GFP_BITS_SHIFT 26 #define __GFP_BITS_MASK ((gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) #define __GFP_WAIT 1 #define __GFP_ACCOUNT 0 diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c index 39d9b9568fe2..05d7bc488971 100644 --- a/tools/testing/radix-tree/multiorder.c +++ b/tools/testing/radix-tree/multiorder.c @@ -124,6 +124,8 @@ static void multiorder_check(unsigned long index, int order) unsigned long i; unsigned long min = index & ~((1UL << order) - 1); unsigned long max = min + (1UL << order); + void **slot; + struct item *item2 = item_create(min); RADIX_TREE(tree, GFP_KERNEL); printf("Multiorder index %ld, order %d\n", index, order); @@ -139,13 +141,19 @@ static void multiorder_check(unsigned long index, int order) item_check_absent(&tree, i); for (i = max; i < 2*max; i++) item_check_absent(&tree, i); + for (i = min; i < max; i++) + assert(radix_tree_insert(&tree, i, item2) == -EEXIST); + + slot = radix_tree_lookup_slot(&tree, index); + free(*slot); + radix_tree_replace_slot(slot, item2); for (i = min; i < max; i++) { - static void *entry = (void *) - (0xA0 | RADIX_TREE_EXCEPTIONAL_ENTRY); - assert(radix_tree_insert(&tree, i, entry) == -EEXIST); + struct item *item = item_lookup(&tree, i); + assert(item != 0); + assert(item->index == min); } - assert(item_delete(&tree, index) != 0); + assert(item_delete(&tree, min) != 0); for (i = 0; i < 2*max; i++) item_check_absent(&tree, i); diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile index 4e400eb83657..d4300602bf37 100644 --- a/tools/testing/selftests/exec/Makefile +++ b/tools/testing/selftests/exec/Makefile @@ -18,7 +18,8 @@ execveat.denatured: execveat $(CC) $(CFLAGS) -o $@ $^ TEST_PROGS := execveat -TEST_FILES := $(DEPS) +# Makefile is a run-time dependency, since it's accessed by the execveat test +TEST_FILES := $(DEPS) Makefile include ../lib.mk diff --git a/tools/testing/selftests/lib/printf.sh b/tools/testing/selftests/lib/printf.sh index 4fdc70fe6980..4fdc70fe6980 100644..100755 --- a/tools/testing/selftests/lib/printf.sh +++ b/tools/testing/selftests/lib/printf.sh diff --git a/tools/testing/selftests/media_tests/.gitignore b/tools/testing/selftests/media_tests/.gitignore index 1c0711708b98..8745eba39012 100644 --- a/tools/testing/selftests/media_tests/.gitignore +++ b/tools/testing/selftests/media_tests/.gitignore @@ -1 +1,3 @@ media_device_test +media_device_open +video_device_test diff --git a/tools/testing/selftests/media_tests/Makefile b/tools/testing/selftests/media_tests/Makefile index 7071bcc1d066..6b34a0199468 100644 --- a/tools/testing/selftests/media_tests/Makefile +++ b/tools/testing/selftests/media_tests/Makefile @@ -1,7 +1,7 @@ -TEST_PROGS := media_device_test +TEST_PROGS := media_device_test media_device_open video_device_test all: $(TEST_PROGS) include ../lib.mk clean: - rm -fr media_device_test + rm -fr media_device_test media_device_open video_device_test diff --git a/tools/testing/selftests/media_tests/bind_unbind_sample.sh b/tools/testing/selftests/media_tests/bind_unbind_sample.sh new file mode 100755 index 000000000000..9f362f10631a --- /dev/null +++ b/tools/testing/selftests/media_tests/bind_unbind_sample.sh @@ -0,0 +1,12 @@ +#!/bin/bash +# Find device number in /sys/bus/usb/drivers/drivername +# Edit this file to update the driver numer and name +# Example test for uvcvideo driver +#i=0 +# while :; do +# i=$((i+1)) +# echo 1-5:1.0 > /sys/bus/usb/drivers/uvcvideo/unbind; +# echo 1-5:1.0 > /sys/bus/usb/drivers/uvcvideo/bind; +# clear +# echo $i +#done diff --git a/tools/testing/selftests/media_tests/media_device_open.c b/tools/testing/selftests/media_tests/media_device_open.c new file mode 100644 index 000000000000..44343c091a20 --- /dev/null +++ b/tools/testing/selftests/media_tests/media_device_open.c @@ -0,0 +1,81 @@ +/* + * media_device_open.c - Media Controller Device Open Test + * + * Copyright (c) 2016 Shuah Khan <shuahkh@osg.samsung.com> + * Copyright (c) 2016 Samsung Electronics Co., Ltd. + * + * This file is released under the GPLv2. + */ + +/* + * This file adds a test for Media Controller API. + * This test should be run as root and should not be + * included in the Kselftest run. This test should be + * run when hardware and driver that makes use Media + * Controller API are present in the system. + * + * This test opens user specified Media Device and calls + * MEDIA_IOC_DEVICE_INFO ioctl, closes the file, and exits. + * + * Usage: + * sudo ./media_device_open -d /dev/mediaX + * + * Run this test is a loop and run bind/unbind on the driver. +*/ + +#include <stdio.h> +#include <unistd.h> +#include <stdlib.h> +#include <errno.h> +#include <string.h> +#include <fcntl.h> +#include <sys/ioctl.h> +#include <sys/stat.h> +#include <linux/media.h> + +int main(int argc, char **argv) +{ + int opt; + char media_device[256]; + int count = 0; + struct media_device_info mdi; + int ret; + int fd; + + if (argc < 2) { + printf("Usage: %s [-d </dev/mediaX>]\n", argv[0]); + exit(-1); + } + + /* Process arguments */ + while ((opt = getopt(argc, argv, "d:")) != -1) { + switch (opt) { + case 'd': + strncpy(media_device, optarg, sizeof(media_device) - 1); + media_device[sizeof(media_device)-1] = '\0'; + break; + default: + printf("Usage: %s [-d </dev/mediaX>]\n", argv[0]); + exit(-1); + } + } + + if (getuid() != 0) { + printf("Please run the test as root - Exiting.\n"); + exit(-1); + } + + /* Open Media device and keep it open */ + fd = open(media_device, O_RDWR); + if (fd == -1) { + printf("Media Device open errno %s\n", strerror(errno)); + exit(-1); + } + + ret = ioctl(fd, MEDIA_IOC_DEVICE_INFO, &mdi); + if (ret < 0) + printf("Media Device Info errno %s\n", strerror(errno)); + else + printf("Media device model %s driver %s\n", + mdi.model, mdi.driver); +} diff --git a/tools/testing/selftests/media_tests/media_device_test.c b/tools/testing/selftests/media_tests/media_device_test.c index cbf53a032ab5..5d49943e77d0 100644 --- a/tools/testing/selftests/media_tests/media_device_test.c +++ b/tools/testing/selftests/media_tests/media_device_test.c @@ -1,5 +1,5 @@ /* - * media_devkref_test.c - Media Controller Device Kref API Test + * media_device_test.c - Media Controller Device ioctl loop Test * * Copyright (c) 2016 Shuah Khan <shuahkh@osg.samsung.com> * Copyright (c) 2016 Samsung Electronics Co., Ltd. @@ -35,13 +35,14 @@ #include <fcntl.h> #include <sys/ioctl.h> #include <sys/stat.h> +#include <time.h> #include <linux/media.h> int main(int argc, char **argv) { int opt; char media_device[256]; - int count = 0; + int count; struct media_device_info mdi; int ret; int fd; @@ -69,6 +70,10 @@ int main(int argc, char **argv) exit(-1); } + /* Generate random number of interations */ + srand((unsigned int) time(NULL)); + count = rand(); + /* Open Media device and keep it open */ fd = open(media_device, O_RDWR); if (fd == -1) { @@ -82,14 +87,16 @@ int main(int argc, char **argv) "other Oops in the dmesg. Enable KaSan kernel\n" "config option for use-after-free error detection.\n\n"); - while (count < 100) { + printf("Running test for %d iternations\n", count); + + while (count > 0) { ret = ioctl(fd, MEDIA_IOC_DEVICE_INFO, &mdi); if (ret < 0) printf("Media Device Info errno %s\n", strerror(errno)); else - printf("Media device model %s driver %s\n", - mdi.model, mdi.driver); + printf("Media device model %s driver %s - count %d\n", + mdi.model, mdi.driver, count); sleep(10); - count++; + count--; } } diff --git a/tools/testing/selftests/media_tests/open_loop_test.sh b/tools/testing/selftests/media_tests/open_loop_test.sh new file mode 100755 index 000000000000..dcd3c17efc17 --- /dev/null +++ b/tools/testing/selftests/media_tests/open_loop_test.sh @@ -0,0 +1,10 @@ +#!/bin/bash + i=0 +file=/dev/media$1 + while :; do + echo $file + i=$((i+1)) + R=$(./media_device_open -d $file); + # clear + echo -e "Loop $i\n$R" + done diff --git a/tools/testing/selftests/media_tests/regression_test.txt b/tools/testing/selftests/media_tests/regression_test.txt new file mode 100644 index 000000000000..2627367681f7 --- /dev/null +++ b/tools/testing/selftests/media_tests/regression_test.txt @@ -0,0 +1,43 @@ +Testing for regressions in Media Controller API register, ioctl, syscall, +and unregister paths. There have a few problems that result in user-after +free on media_device, media_devnode, and cdev pointers when the driver is +unbound while ioctl is in progress. + +Test Procedure: + +Run bin/unbind loop while ioctls are in progress. +Run rmmod and modprobe. +Disconnect the device. + +Setup: + +Build media_device_test +cd tools/testing/selftests/media_tests +make + +Regressions test for cdev user-after free error on /dev/mediaX when driver +is unbound: + +Start media_device_test to regression test media devnode dynamic alloc +and cdev user-after-free fixes. This opens media dev files and sits in +a loop running media ioctl MEDIA_IOC_DEVICE_INFO command once every 10 +seconds. The idea is when device file goes away, media devnode and cdev +should stick around until this test exits. + +The test for a random number of iterations or until user kills it with a +sleep 10 in between the ioctl calls. + +sudo ./media_device_test -d /dev/mediaX + +Regression test for media_devnode unregister race with ioctl_syscall: + +Start 6 open_loop_test.sh tests with different /dev/mediaX files. When +device file goes away after unbind, device file name changes. Start the +test with possible device names. If we start with /dev/media0 for example, +after unbind, /dev/media1 or /dev/media2 could get created. The idea is +keep ioctls going while bind/unbind runs. + +Copy bind_unbind_sample.txt and make changes to specify the driver name +and number to run bind and unbind. Start the bind_unbind.sh + +Run dmesg looking for any user-after free errors or mutex lock errors. diff --git a/tools/testing/selftests/media_tests/video_device_test.c b/tools/testing/selftests/media_tests/video_device_test.c new file mode 100644 index 000000000000..66d419c28653 --- /dev/null +++ b/tools/testing/selftests/media_tests/video_device_test.c @@ -0,0 +1,100 @@ +/* + * video_device_test - Video Device Test + * + * Copyright (c) 2016 Shuah Khan <shuahkh@osg.samsung.com> + * Copyright (c) 2016 Samsung Electronics Co., Ltd. + * + * This file is released under the GPLv2. + */ + +/* + * This file adds a test for Video Device. This test should not be included + * in the Kselftest run. This test should be run when hardware and driver + * that makes use of V4L2 API is present. + * + * This test opens user specified Video Device and calls video ioctls in a + * loop once every 10 seconds. + * + * Usage: + * sudo ./video_device_test -d /dev/videoX + * + * While test is running, remove the device or unbind the driver and + * ensure there are no use after free errors and other Oops in the + * dmesg. + * When possible, enable KaSan kernel config option for use-after-free + * error detection. +*/ + +#include <stdio.h> +#include <unistd.h> +#include <stdlib.h> +#include <errno.h> +#include <string.h> +#include <fcntl.h> +#include <sys/ioctl.h> +#include <sys/stat.h> +#include <time.h> +#include <linux/videodev2.h> + +int main(int argc, char **argv) +{ + int opt; + char video_dev[256]; + int count; + struct v4l2_tuner vtuner; + struct v4l2_capability vcap; + int ret; + int fd; + + if (argc < 2) { + printf("Usage: %s [-d </dev/videoX>]\n", argv[0]); + exit(-1); + } + + /* Process arguments */ + while ((opt = getopt(argc, argv, "d:")) != -1) { + switch (opt) { + case 'd': + strncpy(video_dev, optarg, sizeof(video_dev) - 1); + video_dev[sizeof(video_dev)-1] = '\0'; + break; + default: + printf("Usage: %s [-d </dev/videoX>]\n", argv[0]); + exit(-1); + } + } + + /* Generate random number of interations */ + srand((unsigned int) time(NULL)); + count = rand(); + + /* Open Video device and keep it open */ + fd = open(video_dev, O_RDWR); + if (fd == -1) { + printf("Video Device open errno %s\n", strerror(errno)); + exit(-1); + } + + printf("\nNote:\n" + "While test is running, remove the device or unbind\n" + "driver and ensure there are no use after free errors\n" + "and other Oops in the dmesg. When possible, enable KaSan\n" + "kernel config option for use-after-free error detection.\n\n"); + + while (count > 0) { + ret = ioctl(fd, VIDIOC_QUERYCAP, &vcap); + if (ret < 0) + printf("VIDIOC_QUERYCAP errno %s\n", strerror(errno)); + else + printf("Video device driver %s\n", vcap.driver); + + ret = ioctl(fd, VIDIOC_G_TUNER, &vtuner); + if (ret < 0) + printf("VIDIOC_G_TUNER, errno %s\n", strerror(errno)); + else + printf("type %d rangelow %d rangehigh %d\n", + vtuner.type, vtuner.rangelow, vtuner.rangehigh); + sleep(10); + count--; + } +} diff --git a/tools/testing/selftests/ntb/ntb_test.sh b/tools/testing/selftests/ntb/ntb_test.sh new file mode 100755 index 000000000000..a676d3eefefb --- /dev/null +++ b/tools/testing/selftests/ntb/ntb_test.sh @@ -0,0 +1,422 @@ +#!/bin/bash +# Copyright (c) 2016 Microsemi. All Rights Reserved. +# +# This program is free software; you can redistribute it and/or +# modify it under the terms of the GNU General Public License as +# published by the Free Software Foundation; either version 2 of +# the License, or (at your option) any later version. +# +# This program is distributed in the hope that it would be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# Author: Logan Gunthorpe <logang@deltatee.com> + +REMOTE_HOST= +LIST_DEVS=FALSE + +DEBUGFS=${DEBUGFS-/sys/kernel/debug} + +PERF_RUN_ORDER=32 +MAX_MW_SIZE=0 +RUN_DMA_TESTS= +DONT_CLEANUP= +MW_SIZE=65536 + +function show_help() +{ + echo "Usage: $0 [OPTIONS] LOCAL_DEV REMOTE_DEV" + echo "Run tests on a pair of NTB endpoints." + echo + echo "If the NTB device loops back to the same host then," + echo "just specifying the two PCI ids on the command line is" + echo "sufficient. Otherwise, if the NTB link spans two hosts" + echo "use the -r option to specify the hostname for the remote" + echo "device. SSH will then be used to test the remote side." + echo "An SSH key between the root users of the host would then" + echo "be highly recommended." + echo + echo "Options:" + echo " -C don't cleanup ntb modules on exit" + echo " -d run dma tests" + echo " -h show this help message" + echo " -l list available local and remote PCI ids" + echo " -r REMOTE_HOST specify the remote's hostname to connect" + echo " to for the test (using ssh)" + echo " -p NUM ntb_perf run order (default: $PERF_RUN_ORDER)" + echo " -w max_mw_size maxmium memory window size" + echo +} + +function parse_args() +{ + OPTIND=0 + while getopts "Cdhlm:r:p:w:" opt; do + case "$opt" in + C) DONT_CLEANUP=1 ;; + d) RUN_DMA_TESTS=1 ;; + h) show_help; exit 0 ;; + l) LIST_DEVS=TRUE ;; + m) MW_SIZE=${OPTARG} ;; + r) REMOTE_HOST=${OPTARG} ;; + p) PERF_RUN_ORDER=${OPTARG} ;; + w) MAX_MW_SIZE=${OPTARG} ;; + \?) + echo "Invalid option: -$OPTARG" >&2 + exit 1 + ;; + esac + done +} + +parse_args "$@" +shift $((OPTIND-1)) +LOCAL_DEV=$1 +shift +parse_args "$@" +shift $((OPTIND-1)) +REMOTE_DEV=$1 +shift +parse_args "$@" + +set -e + +function _modprobe() +{ + modprobe "$@" +} + +function split_remote() +{ + VPATH=$1 + REMOTE= + + if [[ "$VPATH" == *":/"* ]]; then + REMOTE=${VPATH%%:*} + VPATH=${VPATH#*:} + fi +} + +function read_file() +{ + split_remote $1 + if [[ "$REMOTE" != "" ]]; then + ssh "$REMOTE" cat "$VPATH" + else + cat "$VPATH" + fi +} + +function write_file() +{ + split_remote $2 + VALUE=$1 + + if [[ "$REMOTE" != "" ]]; then + ssh "$REMOTE" "echo \"$VALUE\" > \"$VPATH\"" + else + echo "$VALUE" > "$VPATH" + fi +} + +function link_test() +{ + LOC=$1 + REM=$2 + EXP=0 + + echo "Running link tests on: $(basename $LOC) / $(basename $REM)" + + if ! write_file "N" "$LOC/link" 2> /dev/null; then + echo " Unsupported" + return + fi + + write_file "N" "$LOC/link_event" + + if [[ $(read_file "$REM/link") != "N" ]]; then + echo "Expected remote link to be down in $REM/link" >&2 + exit -1 + fi + + write_file "Y" "$LOC/link" + write_file "Y" "$LOC/link_event" + + echo " Passed" +} + +function doorbell_test() +{ + LOC=$1 + REM=$2 + EXP=0 + + echo "Running db tests on: $(basename $LOC) / $(basename $REM)" + + write_file "c 0xFFFFFFFF" "$REM/db" + + for ((i=1; i <= 8; i++)); do + let DB=$(read_file "$REM/db") || true + if [[ "$DB" != "$EXP" ]]; then + echo "Doorbell doesn't match expected value $EXP " \ + "in $REM/db" >&2 + exit -1 + fi + + let "MASK=1 << ($i-1)" || true + let "EXP=$EXP | $MASK" || true + write_file "s $MASK" "$LOC/peer_db" + done + + echo " Passed" +} + +function read_spad() +{ + VPATH=$1 + IDX=$2 + + ROW=($(read_file "$VPATH" | grep -e "^$IDX")) + let VAL=${ROW[1]} || true + echo $VAL +} + +function scratchpad_test() +{ + LOC=$1 + REM=$2 + CNT=$(read_file "$LOC/spad" | wc -l) + + echo "Running spad tests on: $(basename $LOC) / $(basename $REM)" + + for ((i = 0; i < $CNT; i++)); do + VAL=$RANDOM + write_file "$i $VAL" "$LOC/peer_spad" + RVAL=$(read_spad "$REM/spad" $i) + + if [[ "$VAL" != "$RVAL" ]]; then + echo "Scratchpad doesn't match expected value $VAL " \ + "in $REM/spad, got $RVAL" >&2 + exit -1 + fi + + done + + echo " Passed" +} + +function write_mw() +{ + split_remote $2 + + if [[ "$REMOTE" != "" ]]; then + ssh "$REMOTE" \ + dd if=/dev/urandom "of=$VPATH" 2> /dev/null || true + else + dd if=/dev/urandom "of=$VPATH" 2> /dev/null || true + fi +} + +function mw_test() +{ + IDX=$1 + LOC=$2 + REM=$3 + + echo "Running $IDX tests on: $(basename $LOC) / $(basename $REM)" + + write_mw "$LOC/$IDX" + + split_remote "$LOC/$IDX" + if [[ "$REMOTE" == "" ]]; then + A=$VPATH + else + A=/tmp/ntb_test.$$.A + ssh "$REMOTE" cat "$VPATH" > "$A" + fi + + split_remote "$REM/peer_$IDX" + if [[ "$REMOTE" == "" ]]; then + B=$VPATH + else + B=/tmp/ntb_test.$$.B + ssh "$REMOTE" cat "$VPATH" > "$B" + fi + + cmp -n $MW_SIZE "$A" "$B" + if [[ $? != 0 ]]; then + echo "Memory window $MW did not match!" >&2 + fi + + if [[ "$A" == "/tmp/*" ]]; then + rm "$A" + fi + + if [[ "$B" == "/tmp/*" ]]; then + rm "$B" + fi + + echo " Passed" +} + +function pingpong_test() +{ + LOC=$1 + REM=$2 + + echo "Running ping pong tests on: $(basename $LOC) / $(basename $REM)" + + LOC_START=$(read_file $LOC/count) + REM_START=$(read_file $REM/count) + + sleep 7 + + LOC_END=$(read_file $LOC/count) + REM_END=$(read_file $REM/count) + + if [[ $LOC_START == $LOC_END ]] || [[ $REM_START == $REM_END ]]; then + echo "Ping pong counter not incrementing!" >&2 + exit 1 + fi + + echo " Passed" +} + +function perf_test() +{ + USE_DMA=$1 + + if [[ $USE_DMA == "1" ]]; then + WITH="with" + else + WITH="without" + fi + + _modprobe ntb_perf run_order=$PERF_RUN_ORDER \ + max_mw_size=$MAX_MW_SIZE use_dma=$USE_DMA + + echo "Running local perf test $WITH DMA" + write_file "" $LOCAL_PERF/run + echo -n " " + read_file $LOCAL_PERF/run + echo " Passed" + + echo "Running remote perf test $WITH DMA" + write_file "" $REMOTE_PERF/run + echo -n " " + read_file $LOCAL_PERF/run + echo " Passed" + + _modprobe -r ntb_perf +} + +function ntb_tool_tests() +{ + LOCAL_TOOL=$DEBUGFS/ntb_tool/$LOCAL_DEV + REMOTE_TOOL=$REMOTE_HOST:$DEBUGFS/ntb_tool/$REMOTE_DEV + + echo "Starting ntb_tool tests..." + + _modprobe ntb_tool + + write_file Y $LOCAL_TOOL/link_event + write_file Y $REMOTE_TOOL/link_event + + link_test $LOCAL_TOOL $REMOTE_TOOL + link_test $REMOTE_TOOL $LOCAL_TOOL + + for PEER_TRANS in $(ls $LOCAL_TOOL/peer_trans*); do + PT=$(basename $PEER_TRANS) + write_file $MW_SIZE $LOCAL_TOOL/$PT + write_file $MW_SIZE $REMOTE_TOOL/$PT + done + + doorbell_test $LOCAL_TOOL $REMOTE_TOOL + doorbell_test $REMOTE_TOOL $LOCAL_TOOL + scratchpad_test $LOCAL_TOOL $REMOTE_TOOL + scratchpad_test $REMOTE_TOOL $LOCAL_TOOL + + for MW in $(ls $LOCAL_TOOL/mw*); do + MW=$(basename $MW) + + mw_test $MW $LOCAL_TOOL $REMOTE_TOOL + mw_test $MW $REMOTE_TOOL $LOCAL_TOOL + done + + _modprobe -r ntb_tool +} + +function ntb_pingpong_tests() +{ + LOCAL_PP=$DEBUGFS/ntb_pingpong/$LOCAL_DEV + REMOTE_PP=$REMOTE_HOST:$DEBUGFS/ntb_pingpong/$REMOTE_DEV + + echo "Starting ntb_pingpong tests..." + + _modprobe ntb_pingpong + + pingpong_test $LOCAL_PP $REMOTE_PP + + _modprobe -r ntb_pingpong +} + +function ntb_perf_tests() +{ + LOCAL_PERF=$DEBUGFS/ntb_perf/$LOCAL_DEV + REMOTE_PERF=$REMOTE_HOST:$DEBUGFS/ntb_perf/$REMOTE_DEV + + echo "Starting ntb_perf tests..." + + perf_test 0 + + if [[ $RUN_DMA_TESTS ]]; then + perf_test 1 + fi +} + +function cleanup() +{ + set +e + _modprobe -r ntb_tool 2> /dev/null + _modprobe -r ntb_perf 2> /dev/null + _modprobe -r ntb_pingpong 2> /dev/null + _modprobe -r ntb_transport 2> /dev/null + set -e +} + +cleanup + +if ! [[ $$DONT_CLEANUP ]]; then + trap cleanup EXIT +fi + +if [ "$(id -u)" != "0" ]; then + echo "This script must be run as root" 1>&2 + exit 1 +fi + +if [[ "$LIST_DEVS" == TRUE ]]; then + echo "Local Devices:" + ls -1 /sys/bus/ntb/devices + echo + + if [[ "$REMOTE_HOST" != "" ]]; then + echo "Remote Devices:" + ssh $REMOTE_HOST ls -1 /sys/bus/ntb/devices + fi + + exit 0 +fi + +if [[ "$LOCAL_DEV" == $"" ]] || [[ "$REMOTE_DEV" == $"" ]]; then + show_help + exit 1 +fi + +ntb_tool_tests +echo +ntb_pingpong_tests +echo +ntb_perf_tests +echo diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile index 4ca83fe80654..1cc6d64c39b7 100644 --- a/tools/testing/selftests/powerpc/Makefile +++ b/tools/testing/selftests/powerpc/Makefile @@ -8,11 +8,12 @@ ifeq ($(ARCH),powerpc) GIT_VERSION = $(shell git describe --always --long --dirty || echo "unknown") -CFLAGS := -Wall -O2 -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CURDIR) $(CFLAGS) +CFLAGS := -std=gnu99 -Wall -O2 -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CURDIR) $(CFLAGS) export CFLAGS -SUB_DIRS = benchmarks \ +SUB_DIRS = alignment \ + benchmarks \ copyloops \ context_switch \ dscr \ diff --git a/tools/testing/selftests/powerpc/alignment/.gitignore b/tools/testing/selftests/powerpc/alignment/.gitignore new file mode 100644 index 000000000000..1d980e3d7039 --- /dev/null +++ b/tools/testing/selftests/powerpc/alignment/.gitignore @@ -0,0 +1,5 @@ +copy_unaligned +copy_first_unaligned +paste_unaligned +paste_last_unaligned +copy_paste_unaligned_common diff --git a/tools/testing/selftests/powerpc/alignment/Makefile b/tools/testing/selftests/powerpc/alignment/Makefile new file mode 100644 index 000000000000..ad6a4e49da91 --- /dev/null +++ b/tools/testing/selftests/powerpc/alignment/Makefile @@ -0,0 +1,10 @@ +TEST_PROGS := copy_unaligned copy_first_unaligned paste_unaligned paste_last_unaligned + +all: $(TEST_PROGS) + +$(TEST_PROGS): ../harness.c ../utils.c copy_paste_unaligned_common.c + +include ../../lib.mk + +clean: + rm -f $(TEST_PROGS) diff --git a/tools/testing/selftests/powerpc/alignment/copy_first_unaligned.c b/tools/testing/selftests/powerpc/alignment/copy_first_unaligned.c new file mode 100644 index 000000000000..47b73b3a08bd --- /dev/null +++ b/tools/testing/selftests/powerpc/alignment/copy_first_unaligned.c @@ -0,0 +1,41 @@ +/* + * Copyright 2016, Chris Smart, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Calls to copy_first which are not 128-byte aligned should be + * caught and sent a SIGBUS. + * + */ + +#include <string.h> +#include <unistd.h> +#include "utils.h" +#include "instructions.h" +#include "copy_paste_unaligned_common.h" + +unsigned int expected_instruction = PPC_INST_COPY_FIRST; +unsigned int instruction_mask = 0xfc2007fe; + +int test_copy_first_unaligned(void) +{ + /* Only run this test on a P9 or later */ + SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_00)); + + /* Register our signal handler with SIGBUS */ + setup_signal_handler(); + + /* +1 makes buf unaligned */ + copy_first(cacheline_buf+1); + + /* We should not get here */ + return 1; +} + +int main(int argc, char *argv[]) +{ + return test_harness(test_copy_first_unaligned, "test_copy_first_unaligned"); +} diff --git a/tools/testing/selftests/powerpc/alignment/copy_paste_unaligned_common.c b/tools/testing/selftests/powerpc/alignment/copy_paste_unaligned_common.c new file mode 100644 index 000000000000..d35fa5f5d2d3 --- /dev/null +++ b/tools/testing/selftests/powerpc/alignment/copy_paste_unaligned_common.c @@ -0,0 +1,53 @@ +/* + * Copyright 2016, Chris Smart, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Common code for copy, copy_first, paste and paste_last unaligned + * tests. + * + */ + +#include <signal.h> +#include <string.h> +#include <unistd.h> +#include "utils.h" +#include "instructions.h" +#include "copy_paste_unaligned_common.h" + +unsigned int expected_instruction; +unsigned int instruction_mask; + +char cacheline_buf[128] __cacheline_aligned; + +void signal_action_handler(int signal_num, siginfo_t *info, void *ptr) +{ + ucontext_t *ctx = ptr; +#if defined(__powerpc64__) + unsigned int *pc = (unsigned int *)ctx->uc_mcontext.gp_regs[PT_NIP]; +#else + unsigned int *pc = (unsigned int *)ctx->uc_mcontext.uc_regs->gregs[PT_NIP]; +#endif + + /* + * Check that the signal was on the correct instruction, using a + * mask because the compiler assigns the register at RB. + */ + if ((*pc & instruction_mask) == expected_instruction) + _exit(0); /* We hit the right instruction */ + + _exit(1); +} + +void setup_signal_handler(void) +{ + struct sigaction signal_action; + + memset(&signal_action, 0, sizeof(signal_action)); + signal_action.sa_sigaction = signal_action_handler; + signal_action.sa_flags = SA_SIGINFO; + sigaction(SIGBUS, &signal_action, NULL); +} diff --git a/tools/testing/selftests/powerpc/alignment/copy_paste_unaligned_common.h b/tools/testing/selftests/powerpc/alignment/copy_paste_unaligned_common.h new file mode 100644 index 000000000000..053899fe506e --- /dev/null +++ b/tools/testing/selftests/powerpc/alignment/copy_paste_unaligned_common.h @@ -0,0 +1,26 @@ +/* + * Copyright 2016, Chris Smart, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Declarations for common code for copy, copy_first, paste and + * paste_last unaligned tests. + * + */ + +#ifndef _SELFTESTS_POWERPC_COPY_PASTE_H +#define _SELFTESTS_POWERPC_COPY_PASTE_H + +#include <signal.h> + +int main(int argc, char *argv[]); +void signal_action_handler(int signal_num, siginfo_t *info, void *ptr); +void setup_signal_handler(void); +extern char cacheline_buf[128] __cacheline_aligned; +extern unsigned int expected_instruction; +extern unsigned int instruction_mask; + +#endif /* _SELFTESTS_POWERPC_COPY_PASTE_H */ diff --git a/tools/testing/selftests/powerpc/alignment/copy_unaligned.c b/tools/testing/selftests/powerpc/alignment/copy_unaligned.c new file mode 100644 index 000000000000..3a4e26461554 --- /dev/null +++ b/tools/testing/selftests/powerpc/alignment/copy_unaligned.c @@ -0,0 +1,41 @@ +/* + * Copyright 2016, Chris Smart, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Calls to copy which are not 128-byte aligned should be caught + * and sent a SIGBUS. + * + */ + +#include <string.h> +#include <unistd.h> +#include "utils.h" +#include "instructions.h" +#include "copy_paste_unaligned_common.h" + +unsigned int expected_instruction = PPC_INST_COPY; +unsigned int instruction_mask = 0xfc0007fe; + +int test_copy_unaligned(void) +{ + /* Only run this test on a P9 or later */ + SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_00)); + + /* Register our signal handler with SIGBUS */ + setup_signal_handler(); + + /* +1 makes buf unaligned */ + copy(cacheline_buf+1); + + /* We should not get here */ + return 1; +} + +int main(int argc, char *argv[]) +{ + return test_harness(test_copy_unaligned, "test_copy_unaligned"); +} diff --git a/tools/testing/selftests/powerpc/alignment/paste_last_unaligned.c b/tools/testing/selftests/powerpc/alignment/paste_last_unaligned.c new file mode 100644 index 000000000000..6e0ad045fcc3 --- /dev/null +++ b/tools/testing/selftests/powerpc/alignment/paste_last_unaligned.c @@ -0,0 +1,43 @@ +/* + * Copyright 2016, Chris Smart, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Calls to paste_last which are not 128-byte aligned should be + * caught and sent a SIGBUS. + * + */ + +#include <string.h> +#include <unistd.h> +#include "utils.h" +#include "instructions.h" +#include "copy_paste_unaligned_common.h" + +unsigned int expected_instruction = PPC_INST_PASTE_LAST; +unsigned int instruction_mask = 0xfc2007ff; + +int test_paste_last_unaligned(void) +{ + /* Only run this test on a P9 or later */ + SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_00)); + + /* Register our signal handler with SIGBUS */ + setup_signal_handler(); + + copy(cacheline_buf); + + /* +1 makes buf unaligned */ + paste_last(cacheline_buf+1); + + /* We should not get here */ + return 1; +} + +int main(int argc, char *argv[]) +{ + return test_harness(test_paste_last_unaligned, "test_paste_last_unaligned"); +} diff --git a/tools/testing/selftests/powerpc/alignment/paste_unaligned.c b/tools/testing/selftests/powerpc/alignment/paste_unaligned.c new file mode 100644 index 000000000000..6f982b45e4bd --- /dev/null +++ b/tools/testing/selftests/powerpc/alignment/paste_unaligned.c @@ -0,0 +1,43 @@ +/* + * Copyright 2016, Chris Smart, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Calls to paste which are not 128-byte aligned should be caught + * and sent a SIGBUS. + * + */ + +#include <string.h> +#include <unistd.h> +#include "utils.h" +#include "instructions.h" +#include "copy_paste_unaligned_common.h" + +unsigned int expected_instruction = PPC_INST_PASTE; +unsigned int instruction_mask = 0xfc0007fe; + +int test_paste_unaligned(void) +{ + /* Only run this test on a P9 or later */ + SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_00)); + + /* Register our signal handler with SIGBUS */ + setup_signal_handler(); + + copy(cacheline_buf); + + /* +1 makes buf unaligned */ + paste(cacheline_buf+1); + + /* We should not get here */ + return 1; +} + +int main(int argc, char *argv[]) +{ + return test_harness(test_paste_unaligned, "test_paste_unaligned"); +} diff --git a/tools/testing/selftests/powerpc/benchmarks/.gitignore b/tools/testing/selftests/powerpc/benchmarks/.gitignore index 6fa673316ac2..bce49ebd869e 100644 --- a/tools/testing/selftests/powerpc/benchmarks/.gitignore +++ b/tools/testing/selftests/powerpc/benchmarks/.gitignore @@ -1,2 +1,4 @@ gettimeofday context_switch +mmap_bench +futex_bench
\ No newline at end of file diff --git a/tools/testing/selftests/powerpc/benchmarks/Makefile b/tools/testing/selftests/powerpc/benchmarks/Makefile index 912445ff7ce7..a9adfb7de78f 100644 --- a/tools/testing/selftests/powerpc/benchmarks/Makefile +++ b/tools/testing/selftests/powerpc/benchmarks/Makefile @@ -1,4 +1,4 @@ -TEST_PROGS := gettimeofday context_switch +TEST_PROGS := gettimeofday context_switch mmap_bench futex_bench CFLAGS += -O2 @@ -7,6 +7,7 @@ all: $(TEST_PROGS) $(TEST_PROGS): ../harness.c context_switch: ../utils.c +context_switch: CFLAGS += -maltivec -mvsx -mabi=altivec context_switch: LDLIBS += -lpthread include ../../lib.mk diff --git a/tools/testing/selftests/powerpc/benchmarks/context_switch.c b/tools/testing/selftests/powerpc/benchmarks/context_switch.c index 7b785941adec..a36883ad48a4 100644 --- a/tools/testing/selftests/powerpc/benchmarks/context_switch.c +++ b/tools/testing/selftests/powerpc/benchmarks/context_switch.c @@ -25,7 +25,9 @@ #include <sys/types.h> #include <sys/shm.h> #include <linux/futex.h> - +#ifdef __powerpc__ +#include <altivec.h> +#endif #include "../utils.h" static unsigned int timeout = 30; @@ -37,12 +39,15 @@ static int touch_fp = 1; double fp; static int touch_vector = 1; -typedef int v4si __attribute__ ((vector_size (16))); -v4si a, b, c; +vector int a, b, c; #ifdef __powerpc__ static int touch_altivec = 1; +/* + * Note: LTO (Link Time Optimisation) doesn't play well with this function + * attribute. Be very careful enabling LTO for this test. + */ static void __attribute__((__target__("no-vsx"))) altivec_touch_fn(void) { c = a + b; @@ -369,11 +374,11 @@ static void usage(void) fprintf(stderr, "\t\t--process\tUse processes (default threads)\n"); fprintf(stderr, "\t\t--timeout=X\tDuration in seconds to run (default 30)\n"); fprintf(stderr, "\t\t--vdso\t\ttouch VDSO\n"); - fprintf(stderr, "\t\t--fp\t\ttouch FP\n"); + fprintf(stderr, "\t\t--no-fp\t\tDon't touch FP\n"); #ifdef __powerpc__ - fprintf(stderr, "\t\t--altivec\ttouch altivec\n"); + fprintf(stderr, "\t\t--no-altivec\tDon't touch altivec\n"); #endif - fprintf(stderr, "\t\t--vector\ttouch vector\n"); + fprintf(stderr, "\t\t--no-vector\tDon't touch vector\n"); } int main(int argc, char *argv[]) diff --git a/tools/testing/selftests/powerpc/benchmarks/futex_bench.c b/tools/testing/selftests/powerpc/benchmarks/futex_bench.c new file mode 100644 index 000000000000..2fc711d9150d --- /dev/null +++ b/tools/testing/selftests/powerpc/benchmarks/futex_bench.c @@ -0,0 +1,42 @@ +/* + * Copyright 2016, Anton Blanchard, Michael Ellerman, IBM Corp. + * Licensed under GPLv2. + */ + +#define _GNU_SOURCE + +#include <stdio.h> +#include <sys/syscall.h> +#include <time.h> +#include <unistd.h> +#include <linux/futex.h> + +#include "utils.h" + +#define ITERATIONS 100000000 + +#define futex(A, B, C, D, E, F) syscall(__NR_futex, A, B, C, D, E, F) + +int test_futex(void) +{ + struct timespec ts_start, ts_end; + unsigned long i = ITERATIONS; + + clock_gettime(CLOCK_MONOTONIC, &ts_start); + + while (i--) { + unsigned int addr = 0; + futex(&addr, FUTEX_WAKE, 1, NULL, NULL, 0); + } + + clock_gettime(CLOCK_MONOTONIC, &ts_end); + + printf("time = %.6f\n", ts_end.tv_sec - ts_start.tv_sec + (ts_end.tv_nsec - ts_start.tv_nsec) / 1e9); + + return 0; +} + +int main(void) +{ + return test_harness(test_futex, "futex_bench"); +} diff --git a/tools/testing/selftests/powerpc/benchmarks/mmap_bench.c b/tools/testing/selftests/powerpc/benchmarks/mmap_bench.c new file mode 100644 index 000000000000..8d084a2d6e74 --- /dev/null +++ b/tools/testing/selftests/powerpc/benchmarks/mmap_bench.c @@ -0,0 +1,41 @@ +/* + * Copyright 2016, Anton Blanchard, Michael Ellerman, IBM Corp. + * Licensed under GPLv2. + */ + +#include <stdio.h> +#include <stdlib.h> +#include <sys/mman.h> +#include <time.h> + +#include "utils.h" + +#define ITERATIONS 5000000 + +#define MEMSIZE (128 * 1024 * 1024) + +int test_mmap(void) +{ + struct timespec ts_start, ts_end; + unsigned long i = ITERATIONS; + + clock_gettime(CLOCK_MONOTONIC, &ts_start); + + while (i--) { + char *c = mmap(NULL, MEMSIZE, PROT_READ|PROT_WRITE, + MAP_PRIVATE|MAP_ANONYMOUS, -1, 0); + FAIL_IF(c == MAP_FAILED); + munmap(c, MEMSIZE); + } + + clock_gettime(CLOCK_MONOTONIC, &ts_end); + + printf("time = %.6f\n", ts_end.tv_sec - ts_start.tv_sec + (ts_end.tv_nsec - ts_start.tv_nsec) / 1e9); + + return 0; +} + +int main(void) +{ + return test_harness(test_mmap, "mmap_bench"); +} diff --git a/tools/testing/selftests/powerpc/instructions.h b/tools/testing/selftests/powerpc/instructions.h new file mode 100644 index 000000000000..0fb0bd3b28c9 --- /dev/null +++ b/tools/testing/selftests/powerpc/instructions.h @@ -0,0 +1,68 @@ +#ifndef _SELFTESTS_POWERPC_INSTRUCTIONS_H +#define _SELFTESTS_POWERPC_INSTRUCTIONS_H + +#include <stdio.h> +#include <stdlib.h> + +/* This defines the "copy" instruction from Power ISA 3.0 Book II, section 4.4. */ +#define __COPY(RA, RB, L) \ + (0x7c00060c | (RA) << (31-15) | (RB) << (31-20) | (L) << (31-10)) +#define COPY(RA, RB, L) \ + .long __COPY((RA), (RB), (L)) + +static inline void copy(void *i) +{ + asm volatile(str(COPY(0, %0, 0))";" + : + : "b" (i) + : "memory" + ); +} + +static inline void copy_first(void *i) +{ + asm volatile(str(COPY(0, %0, 1))";" + : + : "b" (i) + : "memory" + ); +} + +/* This defines the "paste" instruction from Power ISA 3.0 Book II, section 4.4. */ +#define __PASTE(RA, RB, L, RC) \ + (0x7c00070c | (RA) << (31-15) | (RB) << (31-20) | (L) << (31-10) | (RC) << (31-31)) +#define PASTE(RA, RB, L, RC) \ + .long __PASTE((RA), (RB), (L), (RC)) + +static inline int paste(void *i) +{ + int cr; + + asm volatile(str(PASTE(0, %1, 0, 0))";" + "mfcr %0;" + : "=r" (cr) + : "b" (i) + : "memory" + ); + return cr; +} + +static inline int paste_last(void *i) +{ + int cr; + + asm volatile(str(PASTE(0, %1, 1, 1))";" + "mfcr %0;" + : "=r" (cr) + : "b" (i) + : "memory" + ); + return cr; +} + +#define PPC_INST_COPY __COPY(0, 0, 0) +#define PPC_INST_COPY_FIRST __COPY(0, 0, 1) +#define PPC_INST_PASTE __PASTE(0, 0, 0, 0) +#define PPC_INST_PASTE_LAST __PASTE(0, 0, 1, 1) + +#endif /* _SELFTESTS_POWERPC_INSTRUCTIONS_H */ diff --git a/tools/testing/selftests/powerpc/mm/.gitignore b/tools/testing/selftests/powerpc/mm/.gitignore index b43ade0ec861..e715a3f2fbf4 100644 --- a/tools/testing/selftests/powerpc/mm/.gitignore +++ b/tools/testing/selftests/powerpc/mm/.gitignore @@ -1,3 +1,4 @@ hugetlb_vs_thp_test subpage_prot tempfile +prot_sao
\ No newline at end of file diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile index ee179e22308c..3bdb96eae558 100644 --- a/tools/testing/selftests/powerpc/mm/Makefile +++ b/tools/testing/selftests/powerpc/mm/Makefile @@ -1,13 +1,15 @@ noarg: $(MAKE) -C ../ -TEST_PROGS := hugetlb_vs_thp_test subpage_prot +TEST_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao TEST_FILES := tempfile all: $(TEST_PROGS) $(TEST_FILES) $(TEST_PROGS): ../harness.c +prot_sao: ../utils.c + include ../../lib.mk tempfile: diff --git a/tools/testing/selftests/powerpc/mm/prot_sao.c b/tools/testing/selftests/powerpc/mm/prot_sao.c new file mode 100644 index 000000000000..611530d43fa9 --- /dev/null +++ b/tools/testing/selftests/powerpc/mm/prot_sao.c @@ -0,0 +1,42 @@ +/* + * Copyright 2016, Michael Ellerman, IBM Corp. + * Licensed under GPLv2. + */ + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> + +#include <asm/cputable.h> + +#include "utils.h" + +#define SIZE (64 * 1024) + +int test_prot_sao(void) +{ + char *p; + + /* 2.06 or later should support SAO */ + SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06)); + + /* + * Ensure we can ask for PROT_SAO. + * We can't really verify that it does the right thing, but at least we + * confirm the kernel will accept it. + */ + p = mmap(NULL, SIZE, PROT_READ | PROT_WRITE | PROT_SAO, + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + FAIL_IF(p == MAP_FAILED); + + /* Write to the mapping, to at least cause a fault */ + memset(p, 0xaa, SIZE); + + return 0; +} + +int main(void) +{ + return test_harness(test_prot_sao, "prot-sao"); +} diff --git a/tools/testing/selftests/powerpc/pmu/ebb/.gitignore b/tools/testing/selftests/powerpc/pmu/ebb/.gitignore index 42bddbed8b64..44b7df14a936 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/.gitignore +++ b/tools/testing/selftests/powerpc/pmu/ebb/.gitignore @@ -20,3 +20,5 @@ back_to_back_ebbs_test lost_exception_test no_handler_test cycles_with_mmcr2_test +ebb_lmr +ebb_lmr_regs
\ No newline at end of file diff --git a/tools/testing/selftests/powerpc/pmu/ebb/Makefile b/tools/testing/selftests/powerpc/pmu/ebb/Makefile index 8d2279c4bb4b..6b0453e60d53 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/Makefile +++ b/tools/testing/selftests/powerpc/pmu/ebb/Makefile @@ -14,7 +14,7 @@ TEST_PROGS := reg_access_test event_attributes_test cycles_test \ fork_cleanup_test ebb_on_child_test \ ebb_on_willing_child_test back_to_back_ebbs_test \ lost_exception_test no_handler_test \ - cycles_with_mmcr2_test + cycles_with_mmcr2_test ebb_lmr ebb_lmr_regs all: $(TEST_PROGS) diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr.c new file mode 100644 index 000000000000..c47ebd55ba4d --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr.c @@ -0,0 +1,143 @@ +/* + * Copyright 2016, Jack Miller, IBM Corp. + * Licensed under GPLv2. + */ + +#include <stdlib.h> +#include <stdio.h> + +#include "ebb.h" +#include "ebb_lmr.h" + +#define SIZE (32 * 1024 * 1024) /* 32M */ +#define LM_SIZE 0 /* Smallest encoding, 32M */ + +#define SECTIONS 64 /* 1 per bit in LMSER */ +#define SECTION_SIZE (SIZE / SECTIONS) +#define SECTION_LONGS (SECTION_SIZE / sizeof(long)) + +static unsigned long *test_mem; + +static int lmr_count = 0; + +void ebb_lmr_handler(void) +{ + lmr_count++; +} + +void ldmx_full_section(unsigned long *mem, int section) +{ + unsigned long *ptr; + int i; + + for (i = 0; i < SECTION_LONGS; i++) { + ptr = &mem[(SECTION_LONGS * section) + i]; + ldmx((unsigned long) &ptr); + ebb_lmr_reset(); + } +} + +unsigned long section_masks[] = { + 0x8000000000000000, + 0xFF00000000000000, + 0x0000000F70000000, + 0x8000000000000001, + 0xF0F0F0F0F0F0F0F0, + 0x0F0F0F0F0F0F0F0F, + 0x0 +}; + +int ebb_lmr_section_test(unsigned long *mem) +{ + unsigned long *mask = section_masks; + int i; + + for (; *mask; mask++) { + mtspr(SPRN_LMSER, *mask); + printf("Testing mask 0x%016lx\n", mfspr(SPRN_LMSER)); + + for (i = 0; i < 64; i++) { + lmr_count = 0; + ldmx_full_section(mem, i); + if (*mask & (1UL << (63 - i))) + FAIL_IF(lmr_count != SECTION_LONGS); + else + FAIL_IF(lmr_count); + } + } + + return 0; +} + +int ebb_lmr(void) +{ + int i; + + SKIP_IF(!lmr_is_supported()); + + setup_ebb_handler(ebb_lmr_handler); + + ebb_global_enable(); + + FAIL_IF(posix_memalign((void **)&test_mem, SIZE, SIZE) != 0); + + mtspr(SPRN_LMSER, 0); + + FAIL_IF(mfspr(SPRN_LMSER) != 0); + + mtspr(SPRN_LMRR, ((unsigned long)test_mem | LM_SIZE)); + + FAIL_IF(mfspr(SPRN_LMRR) != ((unsigned long)test_mem | LM_SIZE)); + + /* Read every single byte to ensure we get no false positives */ + for (i = 0; i < SECTIONS; i++) + ldmx_full_section(test_mem, i); + + FAIL_IF(lmr_count != 0); + + /* Turn on the first section */ + + mtspr(SPRN_LMSER, (1UL << 63)); + FAIL_IF(mfspr(SPRN_LMSER) != (1UL << 63)); + + /* Enable LM (BESCR) */ + + mtspr(SPRN_BESCR, mfspr(SPRN_BESCR) | BESCR_LME); + FAIL_IF(!(mfspr(SPRN_BESCR) & BESCR_LME)); + + ldmx((unsigned long)&test_mem); + + FAIL_IF(lmr_count != 1); // exactly one exception + FAIL_IF(mfspr(SPRN_BESCR) & BESCR_LME); // LM now disabled + FAIL_IF(!(mfspr(SPRN_BESCR) & BESCR_LMEO)); // occurred bit set + + printf("Simple LMR EBB OK\n"); + + /* This shouldn't cause an EBB since it's been disabled */ + ldmx((unsigned long)&test_mem); + FAIL_IF(lmr_count != 1); + + printf("LMR disable on EBB OK\n"); + + ebb_lmr_reset(); + + /* This should cause an EBB or reset is broken */ + ldmx((unsigned long)&test_mem); + FAIL_IF(lmr_count != 2); + + printf("LMR reset EBB OK\n"); + + ebb_lmr_reset(); + + return ebb_lmr_section_test(test_mem); +} + +int main(void) +{ + int ret = test_harness(ebb_lmr, "ebb_lmr"); + + if (test_mem) + free(test_mem); + + return ret; +} diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr.h b/tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr.h new file mode 100644 index 000000000000..ef50abd557cd --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr.h @@ -0,0 +1,39 @@ +#ifndef _SELFTESTS_POWERPC_PMU_EBB_LMR_H +#define _SELFTESTS_POWERPC_PMU_EBB_LMR_H + +#include "reg.h" + +#ifndef PPC_FEATURE2_ARCH_3_00 +#define PPC_FEATURE2_ARCH_3_00 0x00800000 +#endif + +#define lmr_is_supported() have_hwcap2(PPC_FEATURE2_ARCH_3_00) + +static inline void ebb_lmr_reset(void) +{ + unsigned long bescr = mfspr(SPRN_BESCR); + bescr &= ~(BESCR_LMEO); + bescr |= BESCR_LME; + mtspr(SPRN_BESCR, bescr); +} + +#define LDMX(t, a, b)\ + (0x7c00026a | \ + (((t) & 0x1f) << 21) | \ + (((a) & 0x1f) << 16) | \ + (((b) & 0x1f) << 11)) + +static inline unsigned long ldmx(unsigned long address) +{ + unsigned long ret; + + asm volatile ("mr 9, %1\r\n" + ".long " __stringify(LDMX(9, 0, 9)) "\r\n" + "mr %0, 9\r\n":"=r"(ret) + :"r"(address) + :"r9"); + + return ret; +} + +#endif diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr_regs.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr_regs.c new file mode 100644 index 000000000000..aff4241fd88a --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr_regs.c @@ -0,0 +1,37 @@ +/* + * Copyright 2016, Jack Miller, IBM Corp. + * Licensed under GPLv2. + */ + +#include <stdlib.h> +#include <stdio.h> +#include <unistd.h> + +#include "ebb.h" +#include "ebb_lmr.h" + +#define CHECKS 10000 + +int ebb_lmr_regs(void) +{ + int i; + + SKIP_IF(!lmr_is_supported()); + + ebb_global_enable(); + + for (i = 0; i < CHECKS; i++) { + mtspr(SPRN_LMRR, i << 25); // skip size and rsvd bits + mtspr(SPRN_LMSER, i); + + FAIL_IF(mfspr(SPRN_LMRR) != (i << 25)); + FAIL_IF(mfspr(SPRN_LMSER) != i); + } + + return 0; +} + +int main(void) +{ + return test_harness(ebb_lmr_regs, "ebb_lmr_regs"); +} diff --git a/tools/testing/selftests/powerpc/pmu/ebb/instruction_count_test.c b/tools/testing/selftests/powerpc/pmu/ebb/instruction_count_test.c index 5da355135df2..ae9a79086111 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/instruction_count_test.c +++ b/tools/testing/selftests/powerpc/pmu/ebb/instruction_count_test.c @@ -51,7 +51,7 @@ static int do_count_loop(struct event *event, uint64_t instructions, printf("Looped for %lu instructions, overhead %lu\n", instructions, overhead); printf("Expected %lu\n", expected); printf("Actual %llu\n", event->result.value); - printf("Error %ld, %f%%\n", difference, percentage); + printf("Delta %ld, %f%%\n", difference, percentage); printf("Took %d EBBs\n", ebb_state.stats.ebb_count); } diff --git a/tools/testing/selftests/powerpc/pmu/lib.c b/tools/testing/selftests/powerpc/pmu/lib.c index a361ad3334ce..8b992fa5b478 100644 --- a/tools/testing/selftests/powerpc/pmu/lib.c +++ b/tools/testing/selftests/powerpc/pmu/lib.c @@ -190,7 +190,7 @@ int parse_proc_maps(void) bool require_paranoia_below(int level) { - unsigned long current; + long current; char *end, buf[16]; FILE *f; int rc; @@ -208,7 +208,7 @@ bool require_paranoia_below(int level) goto out_close; } - current = strtoul(buf, &end, 10); + current = strtol(buf, &end, 10); if (end == buf) { printf("Couldn't parse " PARANOID_PATH "?\n"); @@ -216,7 +216,7 @@ bool require_paranoia_below(int level) } if (current >= level) - goto out; + goto out_close; rc = 0; out_close: diff --git a/tools/testing/selftests/powerpc/reg.h b/tools/testing/selftests/powerpc/reg.h index 65bfdeeebdee..fddf368ed82f 100644 --- a/tools/testing/selftests/powerpc/reg.h +++ b/tools/testing/selftests/powerpc/reg.h @@ -34,6 +34,11 @@ #define BESCR_PMEO 0x1 /* PMU Event-based exception Occurred */ #define BESCR_PME (0x1ul << 32) /* PMU Event-based exception Enable */ +#define BESCR_LME (0x1ul << 34) /* Load Monitor Enable */ +#define BESCR_LMEO (0x1ul << 2) /* Load Monitor Exception Occurred */ + +#define SPRN_LMRR 813 /* Load Monitor Region Register */ +#define SPRN_LMSER 814 /* Load Monitor Section Enable Register */ #define SPRN_PMC1 771 #define SPRN_PMC2 772 diff --git a/tools/testing/selftests/powerpc/tm/.gitignore b/tools/testing/selftests/powerpc/tm/.gitignore index bb942db845bf..82c0a9ce6e74 100644 --- a/tools/testing/selftests/powerpc/tm/.gitignore +++ b/tools/testing/selftests/powerpc/tm/.gitignore @@ -6,3 +6,4 @@ tm-vmxcopy tm-fork tm-tar tm-tmspr +tm-exec diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile index d0505dbd22d5..9d301d785d9e 100644 --- a/tools/testing/selftests/powerpc/tm/Makefile +++ b/tools/testing/selftests/powerpc/tm/Makefile @@ -1,11 +1,14 @@ -TEST_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack tm-vmxcopy tm-fork tm-tar tm-tmspr +TEST_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack \ + tm-vmxcopy tm-fork tm-tar tm-tmspr tm-exec tm-execed all: $(TEST_PROGS) $(TEST_PROGS): ../harness.c ../utils.c +CFLAGS += -mhtm + tm-syscall: tm-syscall-asm.S -tm-syscall: CFLAGS += -mhtm -I../../../../../usr/include +tm-syscall: CFLAGS += -I../../../../../usr/include tm-tmspr: CFLAGS += -pthread include ../../lib.mk diff --git a/tools/testing/selftests/powerpc/tm/tm-exec.c b/tools/testing/selftests/powerpc/tm/tm-exec.c new file mode 100644 index 000000000000..3d27fa0ece04 --- /dev/null +++ b/tools/testing/selftests/powerpc/tm/tm-exec.c @@ -0,0 +1,70 @@ +/* + * Copyright 2016, Cyril Bur, IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Syscalls can be performed provided the transactions are suspended. + * The exec() class of syscall is unique as a new process is loaded. + * + * It makes little sense for after an exec() call for the previously + * suspended transaction to still exist. + */ + +#define _GNU_SOURCE +#include <errno.h> +#include <inttypes.h> +#include <libgen.h> +#include <pthread.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> + +#include "utils.h" +#include "tm.h" + +static char *path; + +static int test_exec(void) +{ + SKIP_IF(!have_htm()); + + asm __volatile__( + "tbegin.;" + "blt 1f; " + "tsuspend.;" + "1: ;" + : : : "memory"); + + execl(path, "tm-exec", "--child", NULL); + + /* Shouldn't get here */ + perror("execl() failed"); + return 1; +} + +static int after_exec(void) +{ + asm __volatile__( + "tbegin.;" + "blt 1f;" + "tsuspend.;" + "1: ;" + : : : "memory"); + + FAIL_IF(failure_is_nesting()); + return 0; +} + +int main(int argc, char *argv[]) +{ + path = argv[0]; + + if (argc > 1 && strcmp(argv[1], "--child") == 0) + return after_exec(); + + return test_harness(test_exec, "tm_exec"); +} diff --git a/tools/testing/selftests/powerpc/tm/tm-syscall.c b/tools/testing/selftests/powerpc/tm/tm-syscall.c index 60560cb20e38..454b965a2db3 100644 --- a/tools/testing/selftests/powerpc/tm/tm-syscall.c +++ b/tools/testing/selftests/powerpc/tm/tm-syscall.c @@ -27,21 +27,6 @@ unsigned retries = 0; #define TEST_DURATION 10 /* seconds */ #define TM_RETRIES 100 -long failure_code(void) -{ - return __builtin_get_texasru() >> 24; -} - -bool failure_is_persistent(void) -{ - return (failure_code() & TM_CAUSE_PERSISTENT) == TM_CAUSE_PERSISTENT; -} - -bool failure_is_syscall(void) -{ - return (failure_code() & TM_CAUSE_SYSCALL) == TM_CAUSE_SYSCALL; -} - pid_t getppid_tm(bool suspend) { int i; diff --git a/tools/testing/selftests/powerpc/tm/tm.h b/tools/testing/selftests/powerpc/tm/tm.h index 24144b25772c..60318bad7d7a 100644 --- a/tools/testing/selftests/powerpc/tm/tm.h +++ b/tools/testing/selftests/powerpc/tm/tm.h @@ -6,8 +6,9 @@ #ifndef _SELFTESTS_POWERPC_TM_TM_H #define _SELFTESTS_POWERPC_TM_TM_H -#include <stdbool.h> +#include <asm/tm.h> #include <asm/cputable.h> +#include <stdbool.h> #include "../utils.h" @@ -31,4 +32,24 @@ static inline bool have_htm_nosc(void) #endif } +static inline long failure_code(void) +{ + return __builtin_get_texasru() >> 24; +} + +static inline bool failure_is_persistent(void) +{ + return (failure_code() & TM_CAUSE_PERSISTENT) == TM_CAUSE_PERSISTENT; +} + +static inline bool failure_is_syscall(void) +{ + return (failure_code() & TM_CAUSE_SYSCALL) == TM_CAUSE_SYSCALL; +} + +static inline bool failure_is_nesting(void) +{ + return (__builtin_get_texasru() & 0x400000); +} + #endif /* _SELFTESTS_POWERPC_TM_TM_H */ diff --git a/tools/testing/selftests/powerpc/utils.h b/tools/testing/selftests/powerpc/utils.h index a985cfaa535e..fbd33e52ef8f 100644 --- a/tools/testing/selftests/powerpc/utils.h +++ b/tools/testing/selftests/powerpc/utils.h @@ -27,6 +27,11 @@ int test_harness(int (test_function)(void), char *name); extern void *get_auxv_entry(int type); int pick_online_cpu(void); +static inline bool have_hwcap(unsigned long ftr) +{ + return ((unsigned long)get_auxv_entry(AT_HWCAP) & ftr) == ftr; +} + static inline bool have_hwcap2(unsigned long ftr2) { return ((unsigned long)get_auxv_entry(AT_HWCAP2) & ftr2) == ftr2; diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 2e58549b2f02..03f1fa495d74 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -1021,8 +1021,8 @@ void tracer_stop(int sig) typedef void tracer_func_t(struct __test_metadata *_metadata, pid_t tracee, int status, void *args); -void tracer(struct __test_metadata *_metadata, int fd, pid_t tracee, - tracer_func_t tracer_func, void *args) +void start_tracer(struct __test_metadata *_metadata, int fd, pid_t tracee, + tracer_func_t tracer_func, void *args, bool ptrace_syscall) { int ret = -1; struct sigaction action = { @@ -1042,12 +1042,16 @@ void tracer(struct __test_metadata *_metadata, int fd, pid_t tracee, /* Wait for attach stop */ wait(NULL); - ret = ptrace(PTRACE_SETOPTIONS, tracee, NULL, PTRACE_O_TRACESECCOMP); + ret = ptrace(PTRACE_SETOPTIONS, tracee, NULL, ptrace_syscall ? + PTRACE_O_TRACESYSGOOD : + PTRACE_O_TRACESECCOMP); ASSERT_EQ(0, ret) { TH_LOG("Failed to set PTRACE_O_TRACESECCOMP"); kill(tracee, SIGKILL); } - ptrace(PTRACE_CONT, tracee, NULL, 0); + ret = ptrace(ptrace_syscall ? PTRACE_SYSCALL : PTRACE_CONT, + tracee, NULL, 0); + ASSERT_EQ(0, ret); /* Unblock the tracee */ ASSERT_EQ(1, write(fd, "A", 1)); @@ -1063,12 +1067,13 @@ void tracer(struct __test_metadata *_metadata, int fd, pid_t tracee, /* Child is dead. Time to go. */ return; - /* Make sure this is a seccomp event. */ - ASSERT_EQ(true, IS_SECCOMP_EVENT(status)); + /* Check if this is a seccomp event. */ + ASSERT_EQ(!ptrace_syscall, IS_SECCOMP_EVENT(status)); tracer_func(_metadata, tracee, status, args); - ret = ptrace(PTRACE_CONT, tracee, NULL, NULL); + ret = ptrace(ptrace_syscall ? PTRACE_SYSCALL : PTRACE_CONT, + tracee, NULL, 0); ASSERT_EQ(0, ret); } /* Directly report the status of our test harness results. */ @@ -1079,7 +1084,7 @@ void tracer(struct __test_metadata *_metadata, int fd, pid_t tracee, void cont_handler(int num) { } pid_t setup_trace_fixture(struct __test_metadata *_metadata, - tracer_func_t func, void *args) + tracer_func_t func, void *args, bool ptrace_syscall) { char sync; int pipefd[2]; @@ -1095,7 +1100,8 @@ pid_t setup_trace_fixture(struct __test_metadata *_metadata, signal(SIGALRM, cont_handler); if (tracer_pid == 0) { close(pipefd[0]); - tracer(_metadata, pipefd[1], tracee, func, args); + start_tracer(_metadata, pipefd[1], tracee, func, args, + ptrace_syscall); syscall(__NR_exit, 0); } close(pipefd[1]); @@ -1177,7 +1183,7 @@ FIXTURE_SETUP(TRACE_poke) /* Launch tracer. */ self->tracer = setup_trace_fixture(_metadata, tracer_poke, - &self->tracer_args); + &self->tracer_args, false); } FIXTURE_TEARDOWN(TRACE_poke) @@ -1399,6 +1405,29 @@ void tracer_syscall(struct __test_metadata *_metadata, pid_t tracee, } +void tracer_ptrace(struct __test_metadata *_metadata, pid_t tracee, + int status, void *args) +{ + int ret, nr; + unsigned long msg; + static bool entry; + + /* Make sure we got an empty message. */ + ret = ptrace(PTRACE_GETEVENTMSG, tracee, NULL, &msg); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, msg); + + /* The only way to tell PTRACE_SYSCALL entry/exit is by counting. */ + entry = !entry; + if (!entry) + return; + + nr = get_syscall(_metadata, tracee); + + if (nr == __NR_getpid) + change_syscall(_metadata, tracee, __NR_getppid); +} + FIXTURE_DATA(TRACE_syscall) { struct sock_fprog prog; pid_t tracer, mytid, mypid, parent; @@ -1440,7 +1469,8 @@ FIXTURE_SETUP(TRACE_syscall) ASSERT_NE(self->parent, self->mypid); /* Launch tracer. */ - self->tracer = setup_trace_fixture(_metadata, tracer_syscall, NULL); + self->tracer = setup_trace_fixture(_metadata, tracer_syscall, NULL, + false); } FIXTURE_TEARDOWN(TRACE_syscall) @@ -1500,6 +1530,130 @@ TEST_F(TRACE_syscall, syscall_dropped) EXPECT_NE(self->mytid, syscall(__NR_gettid)); } +TEST_F(TRACE_syscall, skip_after_RET_TRACE) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_LD|BPF_W|BPF_ABS, + offsetof(struct seccomp_data, nr)), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | EPERM), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + long ret; + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret); + + /* Install fixture filter. */ + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); + ASSERT_EQ(0, ret); + + /* Install "errno on getppid" filter. */ + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); + ASSERT_EQ(0, ret); + + /* Tracer will redirect getpid to getppid, and we should see EPERM. */ + EXPECT_EQ(-1, syscall(__NR_getpid)); + EXPECT_EQ(EPERM, errno); +} + +TEST_F_SIGNAL(TRACE_syscall, kill_after_RET_TRACE, SIGSYS) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_LD|BPF_W|BPF_ABS, + offsetof(struct seccomp_data, nr)), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + long ret; + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret); + + /* Install fixture filter. */ + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); + ASSERT_EQ(0, ret); + + /* Install "death on getppid" filter. */ + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); + ASSERT_EQ(0, ret); + + /* Tracer will redirect getpid to getppid, and we should die. */ + EXPECT_NE(self->mypid, syscall(__NR_getpid)); +} + +TEST_F(TRACE_syscall, skip_after_ptrace) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_LD|BPF_W|BPF_ABS, + offsetof(struct seccomp_data, nr)), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | EPERM), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + long ret; + + /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ + teardown_trace_fixture(_metadata, self->tracer); + self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, + true); + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret); + + /* Install "errno on getppid" filter. */ + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); + ASSERT_EQ(0, ret); + + /* Tracer will redirect getpid to getppid, and we should see EPERM. */ + EXPECT_EQ(-1, syscall(__NR_getpid)); + EXPECT_EQ(EPERM, errno); +} + +TEST_F_SIGNAL(TRACE_syscall, kill_after_ptrace, SIGSYS) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_LD|BPF_W|BPF_ABS, + offsetof(struct seccomp_data, nr)), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + long ret; + + /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ + teardown_trace_fixture(_metadata, self->tracer); + self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, + true); + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret); + + /* Install "death on getppid" filter. */ + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); + ASSERT_EQ(0, ret); + + /* Tracer will redirect getpid to getppid, and we should die. */ + EXPECT_NE(self->mypid, syscall(__NR_getpid)); +} + #ifndef __NR_seccomp # if defined(__i386__) # define __NR_seccomp 354 diff --git a/tools/testing/selftests/timers/Makefile b/tools/testing/selftests/timers/Makefile index 4a1be1b75a7f..1d5556869137 100644 --- a/tools/testing/selftests/timers/Makefile +++ b/tools/testing/selftests/timers/Makefile @@ -10,7 +10,7 @@ TEST_PROGS = posix_timers nanosleep nsleep-lat set-timer-lat mqueue-lat \ TEST_PROGS_EXTENDED = alarmtimer-suspend valid-adjtimex adjtick change_skew \ skew_consistency clocksource-switch leap-a-day \ - leapcrash set-tai set-2038 + leapcrash set-tai set-2038 set-tz bins = $(TEST_PROGS) $(TEST_PROGS_EXTENDED) @@ -30,6 +30,7 @@ run_destructive_tests: run_tests ./clocksource-switch ./leap-a-day -s -i 10 ./leapcrash + ./set-tz ./set-tai ./set-2038 diff --git a/tools/testing/selftests/timers/rtctest.c b/tools/testing/selftests/timers/rtctest.c index 624bce51b27d..4230d3052e5d 100644 --- a/tools/testing/selftests/timers/rtctest.c +++ b/tools/testing/selftests/timers/rtctest.c @@ -144,11 +144,12 @@ test_READ: retval = ioctl(fd, RTC_ALM_SET, &rtc_tm); if (retval == -1) { - if (errno == ENOTTY) { + if (errno == EINVAL) { fprintf(stderr, "\n...Alarm IRQs not supported.\n"); goto test_PIE; } + perror("RTC_ALM_SET ioctl"); exit(errno); } @@ -166,6 +167,12 @@ test_READ: /* Enable alarm interrupts */ retval = ioctl(fd, RTC_AIE_ON, 0); if (retval == -1) { + if (errno == EINVAL) { + fprintf(stderr, + "\n...Alarm IRQs not supported.\n"); + goto test_PIE; + } + perror("RTC_AIE_ON ioctl"); exit(errno); } @@ -193,7 +200,7 @@ test_PIE: retval = ioctl(fd, RTC_IRQP_READ, &tmp); if (retval == -1) { /* not all RTCs support periodic IRQs */ - if (errno == ENOTTY) { + if (errno == EINVAL) { fprintf(stderr, "\nNo periodic IRQ support\n"); goto done; } @@ -211,7 +218,7 @@ test_PIE: retval = ioctl(fd, RTC_IRQP_SET, tmp); if (retval == -1) { /* not all RTCs can change their periodic IRQ rate */ - if (errno == ENOTTY) { + if (errno == EINVAL) { fprintf(stderr, "\n...Periodic IRQ rate is fixed\n"); goto done; diff --git a/tools/testing/selftests/timers/set-tz.c b/tools/testing/selftests/timers/set-tz.c new file mode 100644 index 000000000000..f4184928b16b --- /dev/null +++ b/tools/testing/selftests/timers/set-tz.c @@ -0,0 +1,119 @@ +/* Set tz value + * by: John Stultz <john.stultz@linaro.org> + * (C) Copyright Linaro 2016 + * Licensed under the GPLv2 + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + + +#include <stdio.h> +#include <stdlib.h> +#include <time.h> +#include <sys/time.h> +#include <sys/timex.h> +#include <string.h> +#include <signal.h> +#include <unistd.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + +int set_tz(int min, int dst) +{ + struct timezone tz; + + tz.tz_minuteswest = min; + tz.tz_dsttime = dst; + + return settimeofday(0, &tz); +} + +int get_tz_min(void) +{ + struct timezone tz; + struct timeval tv; + + memset(&tz, 0, sizeof(tz)); + gettimeofday(&tv, &tz); + return tz.tz_minuteswest; +} + +int get_tz_dst(void) +{ + struct timezone tz; + struct timeval tv; + + memset(&tz, 0, sizeof(tz)); + gettimeofday(&tv, &tz); + return tz.tz_dsttime; +} + +int main(int argc, char **argv) +{ + int i, ret; + int min, dst; + + min = get_tz_min(); + dst = get_tz_dst(); + printf("tz_minuteswest started at %i, dst at %i\n", min, dst); + + printf("Checking tz_minuteswest can be properly set: "); + for (i = -15*60; i < 15*60; i += 30) { + ret = set_tz(i, dst); + ret = get_tz_min(); + if (ret != i) { + printf("[FAILED] expected: %i got %i\n", i, ret); + goto err; + } + } + printf("[OK]\n"); + + printf("Checking invalid tz_minuteswest values are caught: "); + + if (!set_tz(-15*60-1, dst)) { + printf("[FAILED] %i didn't return failure!\n", -15*60-1); + goto err; + } + + if (!set_tz(15*60+1, dst)) { + printf("[FAILED] %i didn't return failure!\n", 15*60+1); + goto err; + } + + if (!set_tz(-24*60, dst)) { + printf("[FAILED] %i didn't return failure!\n", -24*60); + goto err; + } + + if (!set_tz(24*60, dst)) { + printf("[FAILED] %i didn't return failure!\n", 24*60); + goto err; + } + + printf("[OK]\n"); + + set_tz(min, dst); + return ksft_exit_pass(); + +err: + set_tz(min, dst); + return ksft_exit_fail(); +} diff --git a/tools/testing/selftests/vm/compaction_test.c b/tools/testing/selftests/vm/compaction_test.c index 00c4f65d12da..6d1437f895b8 100644 --- a/tools/testing/selftests/vm/compaction_test.c +++ b/tools/testing/selftests/vm/compaction_test.c @@ -101,7 +101,7 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) /* Start with the initial condition of 0 huge pages*/ if (write(fd, "0", sizeof(char)) != sizeof(char)) { - perror("Failed to write to /proc/sys/vm/nr_hugepages\n"); + perror("Failed to write 0 to /proc/sys/vm/nr_hugepages\n"); goto close_fd; } @@ -110,14 +110,14 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) /* Request a large number of huge pages. The Kernel will allocate as much as it can */ if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) { - perror("Failed to write to /proc/sys/vm/nr_hugepages\n"); + perror("Failed to write 100000 to /proc/sys/vm/nr_hugepages\n"); goto close_fd; } lseek(fd, 0, SEEK_SET); if (read(fd, nr_hugepages, sizeof(nr_hugepages)) <= 0) { - perror("Failed to read from /proc/sys/vm/nr_hugepages\n"); + perror("Failed to re-read from /proc/sys/vm/nr_hugepages\n"); goto close_fd; } @@ -138,7 +138,7 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) if (write(fd, initial_nr_hugepages, strlen(initial_nr_hugepages)) != strlen(initial_nr_hugepages)) { - perror("Failed to write to /proc/sys/vm/nr_hugepages\n"); + perror("Failed to write value to /proc/sys/vm/nr_hugepages\n"); goto close_fd; } diff --git a/tools/testing/selftests/vm/on-fault-limit.c b/tools/testing/selftests/vm/on-fault-limit.c index 245acccce42d..0ae458f32fdb 100644 --- a/tools/testing/selftests/vm/on-fault-limit.c +++ b/tools/testing/selftests/vm/on-fault-limit.c @@ -20,7 +20,7 @@ static int test_limit(void) return ret; } - if (mlockall(MCL_CURRENT | MCL_ONFAULT | MCL_FUTURE)) { + if (mlockall(MCL_ONFAULT | MCL_FUTURE)) { perror("mlockall"); return ret; } diff --git a/tools/virtio/linux/dma-mapping.h b/tools/virtio/linux/dma-mapping.h index 4f93af89ae16..18601f6689b9 100644 --- a/tools/virtio/linux/dma-mapping.h +++ b/tools/virtio/linux/dma-mapping.h @@ -14,4 +14,20 @@ enum dma_data_direction { DMA_NONE = 3, }; +#define dma_alloc_coherent(d, s, hp, f) ({ \ + void *__dma_alloc_coherent_p = kmalloc((s), (f)); \ + *(hp) = (unsigned long)__dma_alloc_coherent_p; \ + __dma_alloc_coherent_p; \ +}) + +#define dma_free_coherent(d, s, p, h) kfree(p) + +#define dma_map_page(d, p, o, s, dir) (page_to_phys(p) + (o)) + +#define dma_map_single(d, p, s, dir) (virt_to_phys(p)) +#define dma_mapping_error(...) (0) + +#define dma_unmap_single(...) do { } while (0) +#define dma_unmap_page(...) do { } while (0) + #endif diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h index 033849948215..d9554fc3f340 100644 --- a/tools/virtio/linux/kernel.h +++ b/tools/virtio/linux/kernel.h @@ -20,7 +20,9 @@ #define PAGE_SIZE getpagesize() #define PAGE_MASK (~(PAGE_SIZE-1)) +#define PAGE_ALIGN(x) ((x + PAGE_SIZE - 1) & PAGE_MASK) +typedef unsigned long long phys_addr_t; typedef unsigned long long dma_addr_t; typedef size_t __kernel_size_t; typedef unsigned int __wsum; @@ -57,6 +59,11 @@ static inline void *kzalloc(size_t s, gfp_t gfp) return p; } +static inline void *alloc_pages_exact(size_t s, gfp_t gfp) +{ + return kmalloc(s, gfp); +} + static inline void kfree(void *p) { if (p >= __kfree_ignore_start && p < __kfree_ignore_end) @@ -64,6 +71,11 @@ static inline void kfree(void *p) free(p); } +static inline void free_pages_exact(void *p, size_t s) +{ + kfree(p); +} + static inline void *krealloc(void *p, size_t s, gfp_t gfp) { return realloc(p, s); @@ -105,6 +117,8 @@ static inline void free_page(unsigned long addr) #define dev_err(dev, format, ...) fprintf (stderr, format, ## __VA_ARGS__) #define dev_warn(dev, format, ...) fprintf (stderr, format, ## __VA_ARGS__) +#define WARN_ON_ONCE(cond) ((cond) && fprintf (stderr, "WARNING\n")) + #define min(x, y) ({ \ typeof(x) _min1 = (x); \ typeof(y) _min2 = (y); \ diff --git a/tools/virtio/linux/slab.h b/tools/virtio/linux/slab.h index 81baeac8ae40..7e1c1197d439 100644 --- a/tools/virtio/linux/slab.h +++ b/tools/virtio/linux/slab.h @@ -1,2 +1,6 @@ #ifndef LINUX_SLAB_H +#define GFP_KERNEL 0 +#define GFP_ATOMIC 0 +#define __GFP_NOWARN 0 +#define __GFP_ZERO 0 #endif diff --git a/tools/virtio/linux/virtio.h b/tools/virtio/linux/virtio.h index ee125e714053..9377c8b4ac16 100644 --- a/tools/virtio/linux/virtio.h +++ b/tools/virtio/linux/virtio.h @@ -3,8 +3,12 @@ #include <linux/scatterlist.h> #include <linux/kernel.h> +struct device { + void *parent; +}; + struct virtio_device { - void *dev; + struct device dev; u64 features; }; diff --git a/tools/virtio/linux/virtio_config.h b/tools/virtio/linux/virtio_config.h index 57a6964a1e35..9ba11815e0a1 100644 --- a/tools/virtio/linux/virtio_config.h +++ b/tools/virtio/linux/virtio_config.h @@ -40,6 +40,19 @@ static inline void __virtio_clear_bit(struct virtio_device *vdev, #define virtio_has_feature(dev, feature) \ (__virtio_test_bit((dev), feature)) +/** + * virtio_has_iommu_quirk - determine whether this device has the iommu quirk + * @vdev: the device + */ +static inline bool virtio_has_iommu_quirk(const struct virtio_device *vdev) +{ + /* + * Note the reverse polarity of the quirk feature (compared to most + * other features), this is for compatibility with legacy systems. + */ + return !virtio_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM); +} + static inline bool virtio_is_little_endian(struct virtio_device *vdev) { return virtio_has_feature(vdev, VIRTIO_F_VERSION_1) || diff --git a/tools/virtio/ringtest/ptr_ring.c b/tools/virtio/ringtest/ptr_ring.c index 68e4f9f0da3a..bd2ad1d3b7a9 100644 --- a/tools/virtio/ringtest/ptr_ring.c +++ b/tools/virtio/ringtest/ptr_ring.c @@ -13,6 +13,7 @@ #define cache_line_size() SMP_CACHE_BYTES #define ____cacheline_aligned_in_smp __attribute__ ((aligned (SMP_CACHE_BYTES))) #define unlikely(x) (__builtin_expect(!!(x), 0)) +#define likely(x) (__builtin_expect(!!(x), 1)) #define ALIGN(x, a) (((x) + (a) - 1) / (a) * (a)) typedef pthread_spinlock_t spinlock_t; |