diff options
Diffstat (limited to 'tools')
114 files changed, 3361 insertions, 858 deletions
diff --git a/tools/arch/mips/include/uapi/asm/perf_regs.h b/tools/arch/mips/include/uapi/asm/perf_regs.h new file mode 100644 index 000000000000..d0f4ecd616cf --- /dev/null +++ b/tools/arch/mips/include/uapi/asm/perf_regs.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _ASM_MIPS_PERF_REGS_H +#define _ASM_MIPS_PERF_REGS_H + +enum perf_event_mips_regs { + PERF_REG_MIPS_PC, + PERF_REG_MIPS_R1, + PERF_REG_MIPS_R2, + PERF_REG_MIPS_R3, + PERF_REG_MIPS_R4, + PERF_REG_MIPS_R5, + PERF_REG_MIPS_R6, + PERF_REG_MIPS_R7, + PERF_REG_MIPS_R8, + PERF_REG_MIPS_R9, + PERF_REG_MIPS_R10, + PERF_REG_MIPS_R11, + PERF_REG_MIPS_R12, + PERF_REG_MIPS_R13, + PERF_REG_MIPS_R14, + PERF_REG_MIPS_R15, + PERF_REG_MIPS_R16, + PERF_REG_MIPS_R17, + PERF_REG_MIPS_R18, + PERF_REG_MIPS_R19, + PERF_REG_MIPS_R20, + PERF_REG_MIPS_R21, + PERF_REG_MIPS_R22, + PERF_REG_MIPS_R23, + PERF_REG_MIPS_R24, + PERF_REG_MIPS_R25, + PERF_REG_MIPS_R26, + PERF_REG_MIPS_R27, + PERF_REG_MIPS_R28, + PERF_REG_MIPS_R29, + PERF_REG_MIPS_R30, + PERF_REG_MIPS_R31, + PERF_REG_MIPS_MAX = PERF_REG_MIPS_R31 + 1, +}; +#endif /* _ASM_MIPS_PERF_REGS_H */ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index b7dd944dc867..8f28fafa98b3 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -56,11 +56,8 @@ # define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31)) #endif -#ifdef CONFIG_IOMMU_SUPPORT -# define DISABLE_ENQCMD 0 -#else -# define DISABLE_ENQCMD (1 << (X86_FEATURE_ENQCMD & 31)) -#endif +/* Force disable because it's broken beyond repair */ +#define DISABLE_ENQCMD (1 << (X86_FEATURE_ENQCMD & 31)) #ifdef CONFIG_X86_SGX # define DISABLE_SGX 0 diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 5a3022c8af82..0662f644aad9 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -437,6 +437,8 @@ struct kvm_vmx_nested_state_hdr { __u16 flags; } smm; + __u16 pad; + __u32 flags; __u64 preemption_timer_deadline; }; diff --git a/tools/bootconfig/include/linux/bootconfig.h b/tools/bootconfig/include/linux/bootconfig.h index 078cbd2ba651..de7f30f99af3 100644 --- a/tools/bootconfig/include/linux/bootconfig.h +++ b/tools/bootconfig/include/linux/bootconfig.h @@ -4,4 +4,8 @@ #include "../../../../include/linux/bootconfig.h" +#ifndef fallthrough +# define fallthrough +#endif + #endif diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index 7362bef1a368..6cd6080cac04 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -399,6 +399,7 @@ static int apply_xbc(const char *path, const char *xbc_path) } /* TODO: Ensure the @path is initramfs/initrd image */ if (fstat(fd, &stat) < 0) { + ret = -errno; pr_err("Failed to get the size of %s\n", path); goto out; } diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst index 790944c35602..baee8591ac76 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst @@ -30,7 +30,8 @@ CGROUP COMMANDS | *ATTACH_TYPE* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** | | **bind4** | **bind6** | **post_bind4** | **post_bind6** | **connect4** | **connect6** | | **getpeername4** | **getpeername6** | **getsockname4** | **getsockname6** | **sendmsg4** | -| **sendmsg6** | **recvmsg4** | **recvmsg6** | **sysctl** | **getsockopt** | **setsockopt** } +| **sendmsg6** | **recvmsg4** | **recvmsg6** | **sysctl** | **getsockopt** | **setsockopt** | +| **sock_release** } | *ATTACH_FLAGS* := { **multi** | **override** } DESCRIPTION @@ -106,6 +107,7 @@ DESCRIPTION **getpeername6** call to getpeername(2) for an inet6 socket (since 5.8); **getsockname4** call to getsockname(2) for an inet4 socket (since 5.8); **getsockname6** call to getsockname(2) for an inet6 socket (since 5.8). + **sock_release** closing an userspace inet socket (since 5.9). **bpftool cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG* Detach *PROG* from the cgroup *CGROUP* and attach type diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 358c7309d419..fe1b38e7e887 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -44,7 +44,7 @@ PROG COMMANDS | **cgroup/connect4** | **cgroup/connect6** | **cgroup/getpeername4** | **cgroup/getpeername6** | | **cgroup/getsockname4** | **cgroup/getsockname6** | **cgroup/sendmsg4** | **cgroup/sendmsg6** | | **cgroup/recvmsg4** | **cgroup/recvmsg6** | **cgroup/sysctl** | -| **cgroup/getsockopt** | **cgroup/setsockopt** | +| **cgroup/getsockopt** | **cgroup/setsockopt** | **cgroup/sock_release** | | **struct_ops** | **fentry** | **fexit** | **freplace** | **sk_lookup** | } | *ATTACH_TYPE* := { diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index d67518bcbd44..cc33c5824a2f 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -478,7 +478,7 @@ _bpftool() cgroup/recvmsg4 cgroup/recvmsg6 \ cgroup/post_bind4 cgroup/post_bind6 \ cgroup/sysctl cgroup/getsockopt \ - cgroup/setsockopt struct_ops \ + cgroup/setsockopt cgroup/sock_release struct_ops \ fentry fexit freplace sk_lookup" -- \ "$cur" ) ) return 0 @@ -1021,7 +1021,7 @@ _bpftool() device bind4 bind6 post_bind4 post_bind6 connect4 connect6 \ getpeername4 getpeername6 getsockname4 getsockname6 \ sendmsg4 sendmsg6 recvmsg4 recvmsg6 sysctl getsockopt \ - setsockopt' + setsockopt sock_release' local ATTACH_FLAGS='multi override' local PROG_TYPE='id pinned tag name' case $prev in @@ -1032,7 +1032,7 @@ _bpftool() ingress|egress|sock_create|sock_ops|device|bind4|bind6|\ post_bind4|post_bind6|connect4|connect6|getpeername4|\ getpeername6|getsockname4|getsockname6|sendmsg4|sendmsg6|\ - recvmsg4|recvmsg6|sysctl|getsockopt|setsockopt) + recvmsg4|recvmsg6|sysctl|getsockopt|setsockopt|sock_release) COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \ "$cur" ) ) return 0 diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index d901cc1b904a..6e53b1d393f4 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -28,7 +28,8 @@ " connect6 | getpeername4 | getpeername6 |\n" \ " getsockname4 | getsockname6 | sendmsg4 |\n" \ " sendmsg6 | recvmsg4 | recvmsg6 |\n" \ - " sysctl | getsockopt | setsockopt }" + " sysctl | getsockopt | setsockopt |\n" \ + " sock_release }" static unsigned int query_flags; diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 3f067d2d7584..da4846c9856a 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -2138,7 +2138,7 @@ static int do_help(int argc, char **argv) " cgroup/getpeername4 | cgroup/getpeername6 |\n" " cgroup/getsockname4 | cgroup/getsockname6 | cgroup/sendmsg4 |\n" " cgroup/sendmsg6 | cgroup/recvmsg4 | cgroup/recvmsg6 |\n" - " cgroup/getsockopt | cgroup/setsockopt |\n" + " cgroup/getsockopt | cgroup/setsockopt | cgroup/sock_release |\n" " struct_ops | fentry | fexit | freplace | sk_lookup }\n" " ATTACH_TYPE := { msg_verdict | stream_verdict | stream_parser |\n" " flow_dissector }\n" diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index 6de5a7fc066b..d2a942086fcb 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -863,8 +863,7 @@ __SYSCALL(__NR_process_madvise, sys_process_madvise) __SC_COMP(__NR_epoll_pwait2, sys_epoll_pwait2, compat_sys_epoll_pwait2) #define __NR_mount_setattr 442 __SYSCALL(__NR_mount_setattr, sys_mount_setattr) -#define __NR_quotactl_path 443 -__SYSCALL(__NR_quotactl_path, sys_quotactl_path) +/* 443 is reserved for quotactl_path */ #define __NR_landlock_create_ruleset 444 __SYSCALL(__NR_landlock_create_ruleset, sys_landlock_create_ruleset) diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h index f44eb0a04afd..4c32e97dcdf0 100644 --- a/tools/include/uapi/linux/fs.h +++ b/tools/include/uapi/linux/fs.h @@ -185,7 +185,7 @@ struct fsxattr { #define BLKROTATIONAL _IO(0x12,126) #define BLKZEROOUT _IO(0x12,127) /* - * A jump here: 130-131 are reserved for zoned block devices + * A jump here: 130-136 are reserved for zoned block devices * (see uapi/linux/blkzoned.h) */ diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index 7d6687618d80..d1b327036ae4 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -289,6 +289,9 @@ struct sockaddr_in { /* Address indicating an error return. */ #define INADDR_NONE ((unsigned long int) 0xffffffff) +/* Dummy address for src of ICMP replies if no real address is set (RFC7600). */ +#define INADDR_DUMMY ((unsigned long int) 0xc0000008) + /* Network number for local host loopback. */ #define IN_LOOPBACKNET 127 diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 3fd9a7e9d90c..79d9c44d1ad7 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -8,6 +8,7 @@ * Note: you must update KVM_API_VERSION if you change this interface. */ +#include <linux/const.h> #include <linux/types.h> #include <linux/compiler.h> #include <linux/ioctl.h> @@ -1879,8 +1880,8 @@ struct kvm_hyperv_eventfd { * conversion after harvesting an entry. Also, it must not skip any * dirty bits, so that dirty bits are always harvested in sequence. */ -#define KVM_DIRTY_GFN_F_DIRTY BIT(0) -#define KVM_DIRTY_GFN_F_RESET BIT(1) +#define KVM_DIRTY_GFN_F_DIRTY _BITUL(0) +#define KVM_DIRTY_GFN_F_RESET _BITUL(1) #define KVM_DIRTY_GFN_F_MASK 0x3 /* diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index bf8143505c49..f92880a15645 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -464,7 +464,7 @@ struct perf_event_attr { /* * User provided data if sigtrap=1, passed back to user via - * siginfo_t::si_perf, e.g. to permit user to identify the event. + * siginfo_t::si_perf_data, e.g. to permit user to identify the event. */ __u64 sig_data; }; diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index e2a3cf437814..c41d9b2b59ac 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -3216,6 +3216,9 @@ static int add_dummy_ksym_var(struct btf *btf) const struct btf_var_secinfo *vs; const struct btf_type *sec; + if (!btf) + return 0; + sec_btf_id = btf__find_by_name_kind(btf, KSYMS_SEC, BTF_KIND_DATASEC); if (sec_btf_id < 0) diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index ee426226928f..acbcf6c7bdf8 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -41,6 +41,11 @@ #define ELF_C_READ_MMAP ELF_C_READ #endif +/* Older libelf all end up in this expression, for both 32 and 64 bit */ +#ifndef GELF_ST_VISIBILITY +#define GELF_ST_VISIBILITY(o) ((o) & 0x03) +#endif + #define BTF_INFO_ENC(kind, kind_flag, vlen) \ ((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN)) #define BTF_TYPE_ENC(name, info, size_or_type) (name), (info), (size_or_type) diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index 6061431ee04c..e9b619aa0cdf 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -1094,7 +1094,7 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr, goto out_put_ctx; } if (xsk->fd == umem->fd) - umem->rx_ring_setup_done = true; + umem->tx_ring_setup_done = true; } err = xsk_get_mmap_offsets(xsk->fd, &off); diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 24295d39713b..523aa4157f80 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -747,6 +747,10 @@ int arch_rewrite_retpolines(struct objtool_file *file) list_for_each_entry(insn, &file->retpoline_call_list, call_node) { + if (insn->type != INSN_JUMP_DYNAMIC && + insn->type != INSN_CALL_DYNAMIC) + continue; + if (!strcmp(insn->sec->name, ".text.__x86.indirect_thunk")) continue; diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 743c2e9d0f56..41bca1d13d8e 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -717,7 +717,7 @@ static int elf_add_string(struct elf *elf, struct section *strtab, char *str) struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name) { - struct section *symtab; + struct section *symtab, *symtab_shndx; struct symbol *sym; Elf_Data *data; Elf_Scn *s; @@ -769,6 +769,29 @@ struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name) symtab->len += data->d_size; symtab->changed = true; + symtab_shndx = find_section_by_name(elf, ".symtab_shndx"); + if (symtab_shndx) { + s = elf_getscn(elf->elf, symtab_shndx->idx); + if (!s) { + WARN_ELF("elf_getscn"); + return NULL; + } + + data = elf_newdata(s); + if (!data) { + WARN_ELF("elf_newdata"); + return NULL; + } + + data->d_buf = &sym->sym.st_size; /* conveniently 0 */ + data->d_size = sizeof(Elf32_Word); + data->d_align = 4; + data->d_type = ELF_T_WORD; + + symtab_shndx->len += 4; + symtab_shndx->changed = true; + } + sym->sec = find_section_by_index(elf, 0); elf_add_symbol(elf, sym); diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt index 1dcec73c910c..bcf3eca5afbe 100644 --- a/tools/perf/Documentation/perf-intel-pt.txt +++ b/tools/perf/Documentation/perf-intel-pt.txt @@ -108,9 +108,9 @@ displayed as follows: perf script --itrace=ibxwpe -F+flags -The flags are "bcrosyiABEx" which stand for branch, call, return, conditional, -system, asynchronous, interrupt, transaction abort, trace begin, trace end, and -in transaction, respectively. +The flags are "bcrosyiABExgh" which stand for branch, call, return, conditional, +system, asynchronous, interrupt, transaction abort, trace begin, trace end, +in transaction, VM-entry, and VM-exit respectively. perf script also supports higher level ways to dump instruction traces: diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 5b8b61075039..48a5f5b26dd4 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -183,14 +183,15 @@ OPTIONS At this point usage is displayed, and perf-script exits. The flags field is synthesized and may have a value when Instruction - Trace decoding. The flags are "bcrosyiABEx" which stand for branch, + Trace decoding. The flags are "bcrosyiABExgh" which stand for branch, call, return, conditional, system, asynchronous, interrupt, - transaction abort, trace begin, trace end, and in transaction, + transaction abort, trace begin, trace end, in transaction, VM-Entry, and VM-Exit respectively. Known combinations of flags are printed more nicely e.g. "call" for "bc", "return" for "br", "jcc" for "bo", "jmp" for "b", "int" for "bci", "iret" for "bri", "syscall" for "bcs", "sysret" for "brs", "async" for "by", "hw int" for "bcyi", "tx abrt" for "bA", "tr strt" for "bB", - "tr end" for "bE". However the "x" flag will be display separately in those + "tr end" for "bE", "vmentry" for "bcg", "vmexit" for "bch". + However the "x" flag will be displayed separately in those cases e.g. "jcc (x)" for a condition branch within a transaction. The callindent field is synthesized and may have a value when diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 406a9519145e..73df23dd664c 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -90,7 +90,6 @@ endif ifeq ($(ARCH),mips) NO_PERF_REGS := 0 CFLAGS += -I$(OUTPUT)arch/mips/include/generated - CFLAGS += -I../../arch/mips/include/uapi -I../../arch/mips/include/generated/uapi LIBUNWIND_LIBS = -lunwind -lunwind-mips endif diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl index 9974f5f8e49b..9cd1c34f31b5 100644 --- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl +++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl @@ -357,7 +357,7 @@ 440 n64 process_madvise sys_process_madvise 441 n64 epoll_pwait2 sys_epoll_pwait2 442 n64 mount_setattr sys_mount_setattr -443 n64 quotactl_path sys_quotactl_path +# 443 reserved for quotactl_path 444 n64 landlock_create_ruleset sys_landlock_create_ruleset 445 n64 landlock_add_rule sys_landlock_add_rule 446 n64 landlock_restrict_self sys_landlock_restrict_self diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index 2e68fbb57cc6..8f052ff4058c 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -522,7 +522,7 @@ 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr -443 common quotactl_path sys_quotactl_path +# 443 reserved for quotactl_path 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index 7e4a2aba366d..0690263df1dd 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -445,7 +445,7 @@ 440 common process_madvise sys_process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr sys_mount_setattr -443 common quotactl_path sys_quotactl_path sys_quotactl_path +# 443 reserved for quotactl_path 444 common landlock_create_ruleset sys_landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index ecd551b08d05..ce18119ea0d0 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -364,7 +364,7 @@ 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr -443 common quotactl_path sys_quotactl_path +# 443 reserved for quotactl_path 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c index 87f5b1a4a7fa..833405c27dae 100644 --- a/tools/perf/builtin-buildid-list.c +++ b/tools/perf/builtin-buildid-list.c @@ -80,6 +80,9 @@ static int perf_session__list_build_ids(bool force, bool with_hits) if (!perf_header__has_feat(&session->header, HEADER_BUILD_ID)) with_hits = true; + if (zstd_init(&(session->zstd_data), 0) < 0) + pr_warning("Decompression initialization failed. Reported data may be incomplete.\n"); + /* * in pipe-mode, the only way to get the buildids is to parse * the record stream. Buildids are stored as RECORD_HEADER_BUILD_ID diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 3337b5f93336..84803abeb942 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -2714,6 +2714,12 @@ int cmd_record(int argc, const char **argv) rec->no_buildid = true; } + if (rec->opts.record_cgroup && !perf_can_record_cgroup()) { + pr_err("Kernel has no cgroup sampling support.\n"); + err = -EINVAL; + goto out_opts; + } + if (rec->opts.kcore) rec->data.is_dir = true; diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 5a830ae09418..f9f74a514315 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -572,7 +572,8 @@ static int enable_counters(void) * - we have initial delay configured */ if (!target__none(&target) || stat_config.initial_delay) { - evlist__enable(evsel_list); + if (!all_counters_use_bpf) + evlist__enable(evsel_list); if (stat_config.initial_delay > 0) pr_info(EVLIST_ENABLED_MSG); } @@ -581,13 +582,19 @@ static int enable_counters(void) static void disable_counters(void) { + struct evsel *counter; + /* * 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)) - evlist__disable(evsel_list); + if (!target__none(&target)) { + evlist__for_each_entry(evsel_list, counter) + bpf_counter__disable(counter); + if (!all_counters_use_bpf) + evlist__disable(evsel_list); + } } static volatile int workload_exec_errno; diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index dd8ff287e930..c783558332b8 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -39,6 +39,7 @@ arch/x86/lib/x86-opcode-map.txt arch/x86/tools/gen-insn-attr-x86.awk arch/arm/include/uapi/asm/perf_regs.h arch/arm64/include/uapi/asm/perf_regs.h +arch/mips/include/uapi/asm/perf_regs.h arch/powerpc/include/uapi/asm/perf_regs.h arch/s390/include/uapi/asm/perf_regs.h arch/x86/include/uapi/asm/perf_regs.h diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 20cb91ef06ff..2f6b67189b42 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -443,6 +443,8 @@ int main(int argc, const char **argv) const char *cmd; char sbuf[STRERR_BUFSIZE]; + perf_debug_setup(); + /* libsubcmd init */ exec_cmd_init("perf", PREFIX, PERF_EXEC_PATH, EXEC_PATH_ENVIRONMENT); pager_init(PERF_PAGER_ENVIRONMENT); @@ -531,8 +533,6 @@ int main(int argc, const char **argv) */ pthread__block_sigwinch(); - perf_debug_setup(); - while (1) { static int done_help; diff --git a/tools/perf/pmu-events/arch/powerpc/power10/cache.json b/tools/perf/pmu-events/arch/powerpc/power10/cache.json index 616f29098c71..605be14f441c 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/cache.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/cache.json @@ -1,46 +1,56 @@ [ { - "EventCode": "1003C", + "EventCode": "0x1003C", "EventName": "PM_EXEC_STALL_DMISS_L2L3", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from either the local L2 or local L3." }, { - "EventCode": "34056", + "EventCode": "0x1E054", + "EventName": "PM_EXEC_STALL_DMISS_L21_L31", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from another core's L2 or L3 on the same chip." + }, + { + "EventCode": "0x34054", + "EventName": "PM_EXEC_STALL_DMISS_L2L3_NOCONFLICT", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local L2 or local L3, without a dispatch conflict." + }, + { + "EventCode": "0x34056", "EventName": "PM_EXEC_STALL_LOAD_FINISH", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was finishing a load after its data was reloaded from a data source beyond the local L1; cycles in which the LSU was processing an L1-hit; cycles in which the NTF instruction merged with another load in the LMQ." + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was finishing a load after its data was reloaded from a data source beyond the local L1; cycles in which the LSU was processing an L1-hit; cycles in which the NTF instruction merged with another load in the LMQ; cycles in which the NTF instruction is waiting for a data reload for a load miss, but the data comes back with a non-NTF instruction." }, { - "EventCode": "3006C", + "EventCode": "0x3006C", "EventName": "PM_RUN_CYC_SMT2_MODE", "BriefDescription": "Cycles when this thread's run latch is set and the core is in SMT2 mode." }, { - "EventCode": "300F4", + "EventCode": "0x300F4", "EventName": "PM_RUN_INST_CMPL_CONC", "BriefDescription": "PowerPC instructions completed by this thread when all threads in the core had the run-latch set." }, { - "EventCode": "4C016", + "EventCode": "0x4C016", "EventName": "PM_EXEC_STALL_DMISS_L2L3_CONFLICT", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local L2 or local L3, with a dispatch conflict." }, { - "EventCode": "4D014", + "EventCode": "0x4D014", "EventName": "PM_EXEC_STALL_LOAD", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a load instruction executing in the Load Store Unit." }, { - "EventCode": "4D016", + "EventCode": "0x4D016", "EventName": "PM_EXEC_STALL_PTESYNC", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a PTESYNC instruction executing in the Load Store Unit." }, { - "EventCode": "401EA", + "EventCode": "0x401EA", "EventName": "PM_THRESH_EXC_128", "BriefDescription": "Threshold counter exceeded a value of 128." }, { - "EventCode": "400F6", + "EventCode": "0x400F6", "EventName": "PM_BR_MPRED_CMPL", "BriefDescription": "A mispredicted branch completed. Includes direction and target." } diff --git a/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json b/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json index 703cd431ae5b..54acb55e2c8c 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json @@ -1,6 +1,6 @@ [ { - "EventCode": "4016E", + "EventCode": "0x4016E", "EventName": "PM_THRESH_NOT_MET", "BriefDescription": "Threshold counter did not meet threshold." } diff --git a/tools/perf/pmu-events/arch/powerpc/power10/frontend.json b/tools/perf/pmu-events/arch/powerpc/power10/frontend.json index eac8609dcc90..558f9530f54e 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/frontend.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/frontend.json @@ -1,216 +1,246 @@ [ { - "EventCode": "10004", + "EventCode": "0x10004", "EventName": "PM_EXEC_STALL_TRANSLATION", "BriefDescription": "Cycles in which the oldest instruction in the pipeline suffered a TLB miss or ERAT miss and waited for it to resolve." }, { - "EventCode": "10010", + "EventCode": "0x10006", + "EventName": "PM_DISP_STALL_HELD_OTHER_CYC", + "BriefDescription": "Cycles in which the NTC instruction is held at dispatch for any other reason." + }, + { + "EventCode": "0x10010", "EventName": "PM_PMC4_OVERFLOW", "BriefDescription": "The event selected for PMC4 caused the event counter to overflow." }, { - "EventCode": "10020", + "EventCode": "0x10020", "EventName": "PM_PMC4_REWIND", "BriefDescription": "The speculative event selected for PMC4 rewinds and the counter for PMC4 is not charged." }, { - "EventCode": "10038", + "EventCode": "0x10038", "EventName": "PM_DISP_STALL_TRANSLATION", "BriefDescription": "Cycles when dispatch was stalled for this thread because the MMU was handling a translation miss." }, { - "EventCode": "1003A", + "EventCode": "0x1003A", "EventName": "PM_DISP_STALL_BR_MPRED_IC_L2", "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L2 after suffering a branch mispredict." }, { - "EventCode": "1E050", + "EventCode": "0x1D05E", + "EventName": "PM_DISP_STALL_HELD_HALT_CYC", + "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because of power management." + }, + { + "EventCode": "0x1E050", "EventName": "PM_DISP_STALL_HELD_STF_MAPPER_CYC", "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because the STF mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR." }, { - "EventCode": "1F054", + "EventCode": "0x1F054", "EventName": "PM_DTLB_HIT", "BriefDescription": "The PTE required by the instruction was resident in the TLB (data TLB access). When MMCR1[16]=0 this event counts only demand hits. When MMCR1[16]=1 this event includes demand and prefetch. Applies to both HPT and RPT." }, { - "EventCode": "101E8", + "EventCode": "0x10064", + "EventName": "PM_DISP_STALL_IC_L2", + "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L2." + }, + { + "EventCode": "0x101E8", "EventName": "PM_THRESH_EXC_256", "BriefDescription": "Threshold counter exceeded a count of 256." }, { - "EventCode": "101EC", + "EventCode": "0x101EC", "EventName": "PM_THRESH_MET", "BriefDescription": "Threshold exceeded." }, { - "EventCode": "100F2", + "EventCode": "0x100F2", "EventName": "PM_1PLUS_PPC_CMPL", "BriefDescription": "Cycles in which at least one instruction is completed by this thread." }, { - "EventCode": "100F6", + "EventCode": "0x100F6", "EventName": "PM_IERAT_MISS", "BriefDescription": "IERAT Reloaded to satisfy an IERAT miss. All page sizes are counted by this event." }, { - "EventCode": "100F8", + "EventCode": "0x100F8", "EventName": "PM_DISP_STALL_CYC", "BriefDescription": "Cycles the ICT has no itags assigned to this thread (no instructions were dispatched during these cycles)." }, { - "EventCode": "20114", + "EventCode": "0x20006", + "EventName": "PM_DISP_STALL_HELD_ISSQ_FULL_CYC", + "BriefDescription": "Cycles in which the NTC instruction is held at dispatch due to Issue queue full. Includes issue queue and branch queue." + }, + { + "EventCode": "0x20114", "EventName": "PM_MRK_L2_RC_DISP", "BriefDescription": "Marked instruction RC dispatched in L2." }, { - "EventCode": "2C010", + "EventCode": "0x2C010", "EventName": "PM_EXEC_STALL_LSU", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the Load Store Unit. This does not include simple fixed point instructions." }, { - "EventCode": "2C016", + "EventCode": "0x2C016", "EventName": "PM_DISP_STALL_IERAT_ONLY_MISS", "BriefDescription": "Cycles when dispatch was stalled while waiting to resolve an instruction ERAT miss." }, { - "EventCode": "2C01E", + "EventCode": "0x2C01E", "EventName": "PM_DISP_STALL_BR_MPRED_IC_L3", "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L3 after suffering a branch mispredict." }, { - "EventCode": "2D01A", + "EventCode": "0x2D01A", "EventName": "PM_DISP_STALL_IC_MISS", "BriefDescription": "Cycles when dispatch was stalled for this thread due to an Icache Miss." }, { - "EventCode": "2D01C", - "EventName": "PM_CMPL_STALL_STCX", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a stcx waiting for resolution from the nest before completing." - }, - { - "EventCode": "2E018", + "EventCode": "0x2E018", "EventName": "PM_DISP_STALL_FETCH", "BriefDescription": "Cycles when dispatch was stalled for this thread because Fetch was being held." }, { - "EventCode": "2E01A", + "EventCode": "0x2E01A", "EventName": "PM_DISP_STALL_HELD_XVFC_MAPPER_CYC", "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because the XVFC mapper/SRB was full." }, { - "EventCode": "2C142", + "EventCode": "0x2C142", "EventName": "PM_MRK_XFER_FROM_SRC_PMC2", "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[15:27]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." }, { - "EventCode": "24050", + "EventCode": "0x24050", "EventName": "PM_IOPS_DISP", "BriefDescription": "Internal Operations dispatched. PM_IOPS_DISP / PM_INST_DISP will show the average number of internal operations per PowerPC instruction." }, { - "EventCode": "2405E", + "EventCode": "0x2405E", "EventName": "PM_ISSUE_CANCEL", "BriefDescription": "An instruction issued and the issue was later cancelled. Only one cancel per PowerPC instruction." }, { - "EventCode": "200FA", + "EventCode": "0x200FA", "EventName": "PM_BR_TAKEN_CMPL", "BriefDescription": "Branch Taken instruction completed." }, { - "EventCode": "30012", + "EventCode": "0x30004", + "EventName": "PM_DISP_STALL_FLUSH", + "BriefDescription": "Cycles when dispatch was stalled because of a flush that happened to an instruction(s) that was not yet NTC. PM_EXEC_STALL_NTC_FLUSH only includes instructions that were flushed after becoming NTC." + }, + { + "EventCode": "0x3000A", + "EventName": "PM_DISP_STALL_ITLB_MISS", + "BriefDescription": "Cycles when dispatch was stalled while waiting to resolve an instruction TLB miss." + }, + { + "EventCode": "0x30012", "EventName": "PM_FLUSH_COMPLETION", "BriefDescription": "The instruction that was next to complete (oldest in the pipeline) did not complete because it suffered a flush." }, { - "EventCode": "30014", + "EventCode": "0x30014", "EventName": "PM_EXEC_STALL_STORE", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a store instruction executing in the Load Store Unit." }, { - "EventCode": "30018", + "EventCode": "0x30018", "EventName": "PM_DISP_STALL_HELD_SCOREBOARD_CYC", "BriefDescription": "Cycles in which the NTC instruction is held at dispatch while waiting on the Scoreboard. This event combines VSCR and FPSCR together." }, { - "EventCode": "30026", + "EventCode": "0x30026", "EventName": "PM_EXEC_STALL_STORE_MISS", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a store whose cache line was not resident in the L1 and was waiting for allocation of the missing line into the L1." }, { - "EventCode": "3012A", + "EventCode": "0x3012A", "EventName": "PM_MRK_L2_RC_DONE", "BriefDescription": "L2 RC machine completed the transaction for the marked instruction." }, { - "EventCode": "3F046", + "EventCode": "0x3F046", "EventName": "PM_ITLB_HIT_1G", "BriefDescription": "Instruction TLB hit (IERAT reload) page size 1G, which implies Radix Page Table translation is in use. When MMCR1[17]=0 this event counts only for demand misses. When MMCR1[17]=1 this event includes demand misses and prefetches." }, { - "EventCode": "34058", + "EventCode": "0x34058", "EventName": "PM_DISP_STALL_BR_MPRED_ICMISS", "BriefDescription": "Cycles when dispatch was stalled after a mispredicted branch resulted in an instruction cache miss." }, { - "EventCode": "3D05C", + "EventCode": "0x3D05C", "EventName": "PM_DISP_STALL_HELD_RENAME_CYC", "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because the mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR and XVFC." }, { - "EventCode": "3E052", + "EventCode": "0x3E052", "EventName": "PM_DISP_STALL_IC_L3", "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L3." }, { - "EventCode": "3E054", + "EventCode": "0x3E054", "EventName": "PM_LD_MISS_L1", "BriefDescription": "Load Missed L1, counted at execution time (can be greater than loads finished). LMQ merges are not included in this count. i.e. if a load instruction misses on an address that is already allocated on the LMQ, this event will not increment for that load). Note that this count is per slice, so if a load spans multiple slices this event will increment multiple times for a single load." }, { - "EventCode": "301EA", + "EventCode": "0x301EA", "EventName": "PM_THRESH_EXC_1024", "BriefDescription": "Threshold counter exceeded a value of 1024." }, { - "EventCode": "300FA", + "EventCode": "0x300FA", "EventName": "PM_INST_FROM_L3MISS", "BriefDescription": "The processor's instruction cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss." }, { - "EventCode": "40006", + "EventCode": "0x40006", "EventName": "PM_ISSUE_KILL", "BriefDescription": "Cycles in which an instruction or group of instructions were cancelled after being issued. This event increments once per occurrence, regardless of how many instructions are included in the issue group." }, { - "EventCode": "40116", + "EventCode": "0x40116", "EventName": "PM_MRK_LARX_FIN", "BriefDescription": "Marked load and reserve instruction (LARX) finished. LARX and STCX are instructions used to acquire a lock." }, { - "EventCode": "4C010", + "EventCode": "0x4C010", "EventName": "PM_DISP_STALL_BR_MPRED_IC_L3MISS", "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from sources beyond the local L3 after suffering a mispredicted branch." }, { - "EventCode": "4D01E", + "EventCode": "0x4D01E", "EventName": "PM_DISP_STALL_BR_MPRED", "BriefDescription": "Cycles when dispatch was stalled for this thread due to a mispredicted branch." }, { - "EventCode": "4E010", + "EventCode": "0x4E010", "EventName": "PM_DISP_STALL_IC_L3MISS", "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from any source beyond the local L3." }, { - "EventCode": "4E01A", + "EventCode": "0x4E01A", "EventName": "PM_DISP_STALL_HELD_CYC", "BriefDescription": "Cycles in which the NTC instruction is held at dispatch for any reason." }, { - "EventCode": "44056", + "EventCode": "0x4003C", + "EventName": "PM_DISP_STALL_HELD_SYNC_CYC", + "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because of a synchronizing instruction that requires the ICT to be empty before dispatch." + }, + { + "EventCode": "0x44056", "EventName": "PM_VECTOR_ST_CMPL", "BriefDescription": "Vector store instructions completed." } diff --git a/tools/perf/pmu-events/arch/powerpc/power10/locks.json b/tools/perf/pmu-events/arch/powerpc/power10/locks.json index 016d8de0e14a..b5a0d6521963 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/locks.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/locks.json @@ -1,11 +1,11 @@ [ { - "EventCode": "1E058", + "EventCode": "0x1E058", "EventName": "PM_STCX_FAIL_FIN", "BriefDescription": "Conditional store instruction (STCX) failed. LARX and STCX are instructions used to acquire a lock." }, { - "EventCode": "4E050", + "EventCode": "0x4E050", "EventName": "PM_STCX_PASS_FIN", "BriefDescription": "Conditional store instruction (STCX) passed. LARX and STCX are instructions used to acquire a lock." } diff --git a/tools/perf/pmu-events/arch/powerpc/power10/marked.json b/tools/perf/pmu-events/arch/powerpc/power10/marked.json index 93a5a5910648..58b5dfe3a273 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/marked.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/marked.json @@ -1,146 +1,141 @@ [ { - "EventCode": "1002C", + "EventCode": "0x1002C", "EventName": "PM_LD_PREFETCH_CACHE_LINE_MISS", "BriefDescription": "The L1 cache was reloaded with a line that fulfills a prefetch request." }, { - "EventCode": "10132", + "EventCode": "0x10132", "EventName": "PM_MRK_INST_ISSUED", "BriefDescription": "Marked instruction issued. Note that stores always get issued twice, the address gets issued to the LSU and the data gets issued to the VSU. Also, issues can sometimes get killed/cancelled and cause multiple sequential issues for the same instruction." }, { - "EventCode": "101E0", + "EventCode": "0x101E0", "EventName": "PM_MRK_INST_DISP", "BriefDescription": "The thread has dispatched a randomly sampled marked instruction." }, { - "EventCode": "101E2", + "EventCode": "0x101E2", "EventName": "PM_MRK_BR_TAKEN_CMPL", "BriefDescription": "Marked Branch Taken instruction completed." }, { - "EventCode": "20112", + "EventCode": "0x20112", "EventName": "PM_MRK_NTF_FIN", "BriefDescription": "The marked instruction became the oldest in the pipeline before it finished. It excludes instructions that finish at dispatch." }, { - "EventCode": "2C01C", + "EventCode": "0x2C01C", "EventName": "PM_EXEC_STALL_DMISS_OFF_CHIP", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from a remote chip." }, { - "EventCode": "20138", + "EventCode": "0x20138", "EventName": "PM_MRK_ST_NEST", "BriefDescription": "A store has been sampled/marked and is at the point of execution where it has completed in the core and can no longer be flushed. At this point the store is sent to the L2." }, { - "EventCode": "2013A", + "EventCode": "0x2013A", "EventName": "PM_MRK_BRU_FIN", "BriefDescription": "Marked Branch instruction finished." }, { - "EventCode": "2C144", + "EventCode": "0x2C144", "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC2", "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[15:27]." }, { - "EventCode": "24156", + "EventCode": "0x24156", "EventName": "PM_MRK_STCX_FIN", "BriefDescription": "Marked conditional store instruction (STCX) finished. LARX and STCX are instructions used to acquire a lock." }, { - "EventCode": "24158", + "EventCode": "0x24158", "EventName": "PM_MRK_INST", "BriefDescription": "An instruction was marked. Includes both Random Instruction Sampling (RIS) at decode time and Random Event Sampling (RES) at the time the configured event happens." }, { - "EventCode": "2415C", + "EventCode": "0x2415C", "EventName": "PM_MRK_BR_CMPL", "BriefDescription": "A marked branch completed. All branches are included." }, { - "EventCode": "200FD", + "EventCode": "0x200FD", "EventName": "PM_L1_ICACHE_MISS", "BriefDescription": "Demand iCache Miss." }, { - "EventCode": "30130", + "EventCode": "0x30130", "EventName": "PM_MRK_INST_FIN", "BriefDescription": "marked instruction finished. Excludes instructions that finish at dispatch. Note that stores always finish twice since the address gets issued to the LSU and the data gets issued to the VSU." }, { - "EventCode": "34146", + "EventCode": "0x34146", "EventName": "PM_MRK_LD_CMPL", "BriefDescription": "Marked loads completed." }, { - "EventCode": "3E158", + "EventCode": "0x3E158", "EventName": "PM_MRK_STCX_FAIL", "BriefDescription": "Marked conditional store instruction (STCX) failed. LARX and STCX are instructions used to acquire a lock." }, { - "EventCode": "3E15A", + "EventCode": "0x3E15A", "EventName": "PM_MRK_ST_FIN", "BriefDescription": "The marked instruction was a store of any kind." }, { - "EventCode": "30068", + "EventCode": "0x30068", "EventName": "PM_L1_ICACHE_RELOADED_PREF", "BriefDescription": "Counts all Icache prefetch reloads ( includes demand turned into prefetch)." }, { - "EventCode": "301E4", + "EventCode": "0x301E4", "EventName": "PM_MRK_BR_MPRED_CMPL", "BriefDescription": "Marked Branch Mispredicted. Includes direction and target." }, { - "EventCode": "300F6", + "EventCode": "0x300F6", "EventName": "PM_LD_DEMAND_MISS_L1", "BriefDescription": "The L1 cache was reloaded with a line that fulfills a demand miss request. Counted at reload time, before finish." }, { - "EventCode": "300FE", + "EventCode": "0x300FE", "EventName": "PM_DATA_FROM_L3MISS", "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss." }, { - "EventCode": "40012", + "EventCode": "0x40012", "EventName": "PM_L1_ICACHE_RELOADED_ALL", "BriefDescription": "Counts all Icache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch." }, { - "EventCode": "40134", + "EventCode": "0x40134", "EventName": "PM_MRK_INST_TIMEO", "BriefDescription": "Marked instruction finish timeout (instruction was lost)." }, { - "EventCode": "4003C", - "EventName": "PM_DISP_STALL_HELD_SYNC_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because of a synchronizing instruction that requires the ICT to be empty before dispatch." - }, - { - "EventCode": "4505A", + "EventCode": "0x4505A", "EventName": "PM_SP_FLOP_CMPL", "BriefDescription": "Single Precision floating point instructions completed." }, { - "EventCode": "4D058", + "EventCode": "0x4D058", "EventName": "PM_VECTOR_FLOP_CMPL", "BriefDescription": "Vector floating point instructions completed." }, { - "EventCode": "4D05A", + "EventCode": "0x4D05A", "EventName": "PM_NON_MATH_FLOP_CMPL", "BriefDescription": "Non Math instructions completed." }, { - "EventCode": "401E0", + "EventCode": "0x401E0", "EventName": "PM_MRK_INST_CMPL", "BriefDescription": "marked instruction completed." }, { - "EventCode": "400FE", + "EventCode": "0x400FE", "EventName": "PM_DATA_FROM_MEMORY", "BriefDescription": "The processor's data cache was reloaded from local, remote, or distant memory due to a demand miss." } diff --git a/tools/perf/pmu-events/arch/powerpc/power10/memory.json b/tools/perf/pmu-events/arch/powerpc/power10/memory.json index b01141eeebee..843b51f531e9 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/memory.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/memory.json @@ -1,191 +1,186 @@ [ { - "EventCode": "1000A", + "EventCode": "0x1000A", "EventName": "PM_PMC3_REWIND", "BriefDescription": "The speculative event selected for PMC3 rewinds and the counter for PMC3 is not charged." }, { - "EventCode": "1C040", + "EventCode": "0x1C040", "EventName": "PM_XFER_FROM_SRC_PMC1", "BriefDescription": "The processor's L1 data cache was reloaded from the source specified in MMCR3[0:12]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." }, { - "EventCode": "1C142", + "EventCode": "0x1C142", "EventName": "PM_MRK_XFER_FROM_SRC_PMC1", "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[0:12]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." }, { - "EventCode": "1C144", + "EventCode": "0x1C144", "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC1", "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[0:12]." }, { - "EventCode": "1C056", + "EventCode": "0x1C056", "EventName": "PM_DERAT_MISS_4K", "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 4K. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "1C058", + "EventCode": "0x1C058", "EventName": "PM_DTLB_MISS_16G", "BriefDescription": "Data TLB reload (after a miss) page size 16G. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "1C05C", + "EventCode": "0x1C05C", "EventName": "PM_DTLB_MISS_2M", "BriefDescription": "Data TLB reload (after a miss) page size 2M. Implies radix translation was used. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "1E056", + "EventCode": "0x1E056", "EventName": "PM_EXEC_STALL_STORE_PIPE", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the store unit. This does not include cycles spent handling store misses, PTESYNC instructions or TLBIE instructions." }, { - "EventCode": "1F150", + "EventCode": "0x1F150", "EventName": "PM_MRK_ST_L2_CYC", "BriefDescription": "Cycles from L2 RC dispatch to L2 RC completion." }, { - "EventCode": "10062", + "EventCode": "0x10062", "EventName": "PM_LD_L3MISS_PEND_CYC", "BriefDescription": "Cycles L3 miss was pending for this thread." }, { - "EventCode": "20010", + "EventCode": "0x20010", "EventName": "PM_PMC1_OVERFLOW", "BriefDescription": "The event selected for PMC1 caused the event counter to overflow." }, { - "EventCode": "2001A", + "EventCode": "0x2001A", "EventName": "PM_ITLB_HIT", "BriefDescription": "The PTE required to translate the instruction address was resident in the TLB (instruction TLB access/IERAT reload). Applies to both HPT and RPT. When MMCR1[17]=0 this event counts only for demand misses. When MMCR1[17]=1 this event includes demand misses and prefetches." }, { - "EventCode": "2003E", + "EventCode": "0x2003E", "EventName": "PM_PTESYNC_FIN", "BriefDescription": "Ptesync instruction finished in the store unit. Only one ptesync can finish at a time." }, { - "EventCode": "2C040", + "EventCode": "0x2C040", "EventName": "PM_XFER_FROM_SRC_PMC2", "BriefDescription": "The processor's L1 data cache was reloaded from the source specified in MMCR3[15:27]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." }, { - "EventCode": "2C054", + "EventCode": "0x2C054", "EventName": "PM_DERAT_MISS_64K", "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 64K. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "2C056", + "EventCode": "0x2C056", "EventName": "PM_DTLB_MISS_4K", "BriefDescription": "Data TLB reload (after a miss) page size 4K. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "2D154", + "EventCode": "0x2D154", "EventName": "PM_MRK_DERAT_MISS_64K", "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 64K for a marked instruction. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "200F6", + "EventCode": "0x200F6", "EventName": "PM_DERAT_MISS", "BriefDescription": "DERAT Reloaded to satisfy a DERAT miss. All page sizes are counted by this event. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "3000A", - "EventName": "PM_DISP_STALL_ITLB_MISS", - "BriefDescription": "Cycles when dispatch was stalled while waiting to resolve an instruction TLB miss." - }, - { - "EventCode": "30016", + "EventCode": "0x30016", "EventName": "PM_EXEC_STALL_DERAT_DTLB_MISS", "BriefDescription": "Cycles in which the oldest instruction in the pipeline suffered a TLB miss and waited for it resolve." }, { - "EventCode": "3C040", + "EventCode": "0x3C040", "EventName": "PM_XFER_FROM_SRC_PMC3", "BriefDescription": "The processor's L1 data cache was reloaded from the source specified in MMCR3[30:42]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." }, { - "EventCode": "3C142", + "EventCode": "0x3C142", "EventName": "PM_MRK_XFER_FROM_SRC_PMC3", "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[30:42]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." }, { - "EventCode": "3C144", + "EventCode": "0x3C144", "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC3", "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[30:42]." }, { - "EventCode": "3C054", + "EventCode": "0x3C054", "EventName": "PM_DERAT_MISS_16M", "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 16M. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "3C056", + "EventCode": "0x3C056", "EventName": "PM_DTLB_MISS_64K", "BriefDescription": "Data TLB reload (after a miss) page size 64K. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "3C058", + "EventCode": "0x3C058", "EventName": "PM_LARX_FIN", "BriefDescription": "Load and reserve instruction (LARX) finished. LARX and STCX are instructions used to acquire a lock." }, { - "EventCode": "301E2", + "EventCode": "0x301E2", "EventName": "PM_MRK_ST_CMPL", "BriefDescription": "Marked store completed and sent to nest. Note that this count excludes cache-inhibited stores." }, { - "EventCode": "300FC", + "EventCode": "0x300FC", "EventName": "PM_DTLB_MISS", "BriefDescription": "The DPTEG required for the load/store instruction in execution was missing from the TLB. It includes pages of all sizes for demand and prefetch activity." }, { - "EventCode": "4D02C", + "EventCode": "0x4D02C", "EventName": "PM_PMC1_REWIND", "BriefDescription": "The speculative event selected for PMC1 rewinds and the counter for PMC1 is not charged." }, { - "EventCode": "4003E", + "EventCode": "0x4003E", "EventName": "PM_LD_CMPL", "BriefDescription": "Loads completed." }, { - "EventCode": "4C040", + "EventCode": "0x4C040", "EventName": "PM_XFER_FROM_SRC_PMC4", "BriefDescription": "The processor's L1 data cache was reloaded from the source specified in MMCR3[45:57]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." }, { - "EventCode": "4C142", + "EventCode": "0x4C142", "EventName": "PM_MRK_XFER_FROM_SRC_PMC4", "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[45:57]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." }, { - "EventCode": "4C144", + "EventCode": "0x4C144", "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC4", "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[45:57]." }, { - "EventCode": "4C056", + "EventCode": "0x4C056", "EventName": "PM_DTLB_MISS_16M", "BriefDescription": "Data TLB reload (after a miss) page size 16M. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "4C05A", + "EventCode": "0x4C05A", "EventName": "PM_DTLB_MISS_1G", "BriefDescription": "Data TLB reload (after a miss) page size 1G. Implies radix translation was used. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "4C15E", + "EventCode": "0x4C15E", "EventName": "PM_MRK_DTLB_MISS_64K", "BriefDescription": "Marked Data TLB reload (after a miss) page size 64K. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "4D056", + "EventCode": "0x4D056", "EventName": "PM_NON_FMA_FLOP_CMPL", "BriefDescription": "Non FMA instruction completed." }, { - "EventCode": "40164", + "EventCode": "0x40164", "EventName": "PM_MRK_DERAT_MISS_2M", "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 2M for a marked instruction. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." } diff --git a/tools/perf/pmu-events/arch/powerpc/power10/others.json b/tools/perf/pmu-events/arch/powerpc/power10/others.json index a119e56cbf1c..7d0de1a2860b 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/others.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/others.json @@ -1,296 +1,271 @@ [ { - "EventCode": "10016", + "EventCode": "0x10016", "EventName": "PM_VSU0_ISSUE", "BriefDescription": "VSU instructions issued to VSU pipe 0." }, { - "EventCode": "1001C", + "EventCode": "0x1001C", "EventName": "PM_ULTRAVISOR_INST_CMPL", "BriefDescription": "PowerPC instructions that completed while the thread was in ultravisor state." }, { - "EventCode": "100F0", + "EventCode": "0x100F0", "EventName": "PM_CYC", "BriefDescription": "Processor cycles." }, { - "EventCode": "10134", + "EventCode": "0x10134", "EventName": "PM_MRK_ST_DONE_L2", "BriefDescription": "Marked stores completed in L2 (RC machine done)." }, { - "EventCode": "1505E", + "EventCode": "0x1505E", "EventName": "PM_LD_HIT_L1", "BriefDescription": "Loads that finished without experiencing an L1 miss." }, { - "EventCode": "1D05E", - "EventName": "PM_DISP_STALL_HELD_HALT_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because of power management." - }, - { - "EventCode": "1E054", - "EventName": "PM_EXEC_STALL_DMISS_L21_L31", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from another core's L2 or L3 on the same chip." - }, - { - "EventCode": "1E05A", - "EventName": "PM_CMPL_STALL_LWSYNC", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a lwsync waiting to complete." - }, - { - "EventCode": "1F056", + "EventCode": "0x1F056", "EventName": "PM_DISP_SS0_2_INSTR_CYC", "BriefDescription": "Cycles in which Superslice 0 dispatches either 1 or 2 instructions." }, { - "EventCode": "1F15C", + "EventCode": "0x1F15C", "EventName": "PM_MRK_STCX_L2_CYC", "BriefDescription": "Cycles spent in the nest portion of a marked Stcx instruction. It starts counting when the operation starts to drain to the L2 and it stops counting when the instruction retires from the Instruction Completion Table (ICT) in the Instruction Sequencing Unit (ISU)." }, { - "EventCode": "10066", + "EventCode": "0x10066", "EventName": "PM_ADJUNCT_CYC", "BriefDescription": "Cycles in which the thread is in Adjunct state. MSR[S HV PR] bits = 011." }, { - "EventCode": "101E4", + "EventCode": "0x101E4", "EventName": "PM_MRK_L1_ICACHE_MISS", "BriefDescription": "Marked Instruction suffered an icache Miss." }, { - "EventCode": "101EA", + "EventCode": "0x101EA", "EventName": "PM_MRK_L1_RELOAD_VALID", "BriefDescription": "Marked demand reload." }, { - "EventCode": "100F4", + "EventCode": "0x100F4", "EventName": "PM_FLOP_CMPL", "BriefDescription": "Floating Point Operations Completed. Includes any type. It counts once for each 1, 2, 4 or 8 flop instruction. Use PM_1|2|4|8_FLOP_CMPL events to count flops." }, { - "EventCode": "100FA", + "EventCode": "0x100FA", "EventName": "PM_RUN_LATCH_ANY_THREAD_CYC", "BriefDescription": "Cycles when at least one thread has the run latch set." }, { - "EventCode": "100FC", + "EventCode": "0x100FC", "EventName": "PM_LD_REF_L1", "BriefDescription": "All L1 D cache load references counted at finish, gated by reject. In P9 and earlier this event counted only cacheable loads but in P10 both cacheable and non-cacheable loads are included." }, { - "EventCode": "20006", - "EventName": "PM_DISP_STALL_HELD_ISSQ_FULL_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch due to Issue queue full. Includes issue queue and branch queue." - }, - { - "EventCode": "2000C", + "EventCode": "0x2000C", "EventName": "PM_RUN_LATCH_ALL_THREADS_CYC", "BriefDescription": "Cycles when the run latch is set for all threads." }, { - "EventCode": "2E010", + "EventCode": "0x2E010", "EventName": "PM_ADJUNCT_INST_CMPL", "BriefDescription": "PowerPC instructions that completed while the thread is in Adjunct state." }, { - "EventCode": "2E014", + "EventCode": "0x2E014", "EventName": "PM_STCX_FIN", "BriefDescription": "Conditional store instruction (STCX) finished. LARX and STCX are instructions used to acquire a lock." }, { - "EventCode": "20130", + "EventCode": "0x20130", "EventName": "PM_MRK_INST_DECODED", "BriefDescription": "An instruction was marked at decode time. Random Instruction Sampling (RIS) only." }, { - "EventCode": "20132", + "EventCode": "0x20132", "EventName": "PM_MRK_DFU_ISSUE", "BriefDescription": "The marked instruction was a decimal floating point operation issued to the VSU. Measured at issue time." }, { - "EventCode": "20134", + "EventCode": "0x20134", "EventName": "PM_MRK_FXU_ISSUE", "BriefDescription": "The marked instruction was a fixed point operation issued to the VSU. Measured at issue time." }, { - "EventCode": "2505C", + "EventCode": "0x2505C", "EventName": "PM_VSU_ISSUE", "BriefDescription": "At least one VSU instruction was issued to one of the VSU pipes. Up to 4 per cycle. Includes fixed point operations." }, { - "EventCode": "2F054", + "EventCode": "0x2F054", "EventName": "PM_DISP_SS1_2_INSTR_CYC", "BriefDescription": "Cycles in which Superslice 1 dispatches either 1 or 2 instructions." }, { - "EventCode": "2F056", + "EventCode": "0x2F056", "EventName": "PM_DISP_SS1_4_INSTR_CYC", "BriefDescription": "Cycles in which Superslice 1 dispatches either 3 or 4 instructions." }, { - "EventCode": "2006C", + "EventCode": "0x2006C", "EventName": "PM_RUN_CYC_SMT4_MODE", "BriefDescription": "Cycles when this thread's run latch is set and the core is in SMT4 mode." }, { - "EventCode": "201E0", + "EventCode": "0x201E0", "EventName": "PM_MRK_DATA_FROM_MEMORY", "BriefDescription": "The processor's data cache was reloaded from local, remote, or distant memory due to a demand miss for a marked load." }, { - "EventCode": "201E4", + "EventCode": "0x201E4", "EventName": "PM_MRK_DATA_FROM_L3MISS", "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss for a marked load." }, { - "EventCode": "201E8", + "EventCode": "0x201E8", "EventName": "PM_THRESH_EXC_512", "BriefDescription": "Threshold counter exceeded a value of 512." }, { - "EventCode": "200F2", + "EventCode": "0x200F2", "EventName": "PM_INST_DISP", "BriefDescription": "PowerPC instructions dispatched." }, { - "EventCode": "30132", + "EventCode": "0x30132", "EventName": "PM_MRK_VSU_FIN", "BriefDescription": "VSU marked instructions finished. Excludes simple FX instructions issued to the Store Unit." }, { - "EventCode": "30038", + "EventCode": "0x30038", "EventName": "PM_EXEC_STALL_DMISS_LMEM", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local memory, local OpenCapp cache, or local OpenCapp memory." }, { - "EventCode": "3F04A", + "EventCode": "0x3F04A", "EventName": "PM_LSU_ST5_FIN", "BriefDescription": "LSU Finished an internal operation in ST2 port." }, { - "EventCode": "34054", - "EventName": "PM_EXEC_STALL_DMISS_L2L3_NOCONFLICT", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local L2 or local L3, without a dispatch conflict." - }, - { - "EventCode": "3405A", + "EventCode": "0x3405A", "EventName": "PM_PRIVILEGED_INST_CMPL", "BriefDescription": "PowerPC Instructions that completed while the thread is in Privileged state." }, { - "EventCode": "3F150", + "EventCode": "0x3F150", "EventName": "PM_MRK_ST_DRAIN_CYC", "BriefDescription": "cycles to drain st from core to L2." }, { - "EventCode": "3F054", + "EventCode": "0x3F054", "EventName": "PM_DISP_SS0_4_INSTR_CYC", "BriefDescription": "Cycles in which Superslice 0 dispatches either 3 or 4 instructions." }, { - "EventCode": "3F056", + "EventCode": "0x3F056", "EventName": "PM_DISP_SS0_8_INSTR_CYC", "BriefDescription": "Cycles in which Superslice 0 dispatches either 5, 6, 7 or 8 instructions." }, { - "EventCode": "30162", + "EventCode": "0x30162", "EventName": "PM_MRK_ISSUE_DEPENDENT_LOAD", "BriefDescription": "The marked instruction was dependent on a load. It is eligible for issue kill." }, { - "EventCode": "40114", + "EventCode": "0x40114", "EventName": "PM_MRK_START_PROBE_NOP_DISP", "BriefDescription": "Marked Start probe nop dispatched. Instruction AND R0,R0,R0." }, { - "EventCode": "4001C", + "EventCode": "0x4001C", "EventName": "PM_VSU_FIN", "BriefDescription": "VSU instructions finished." }, { - "EventCode": "4C01A", + "EventCode": "0x4C01A", "EventName": "PM_EXEC_STALL_DMISS_OFF_NODE", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from a distant chip." }, { - "EventCode": "4D012", + "EventCode": "0x4D012", "EventName": "PM_PMC3_SAVED", "BriefDescription": "The conditions for the speculative event selected for PMC3 are met and PMC3 is charged." }, { - "EventCode": "4D022", + "EventCode": "0x4D022", "EventName": "PM_HYPERVISOR_INST_CMPL", "BriefDescription": "PowerPC instructions that completed while the thread is in hypervisor state." }, { - "EventCode": "4D026", + "EventCode": "0x4D026", "EventName": "PM_ULTRAVISOR_CYC", "BriefDescription": "Cycles when the thread is in Ultravisor state. MSR[S HV PR]=110." }, { - "EventCode": "4D028", + "EventCode": "0x4D028", "EventName": "PM_PRIVILEGED_CYC", "BriefDescription": "Cycles when the thread is in Privileged state. MSR[S HV PR]=x00." }, { - "EventCode": "40030", + "EventCode": "0x40030", "EventName": "PM_INST_FIN", "BriefDescription": "Instructions finished." }, { - "EventCode": "44146", + "EventCode": "0x44146", "EventName": "PM_MRK_STCX_CORE_CYC", "BriefDescription": "Cycles spent in the core portion of a marked Stcx instruction. It starts counting when the instruction is decoded and stops counting when it drains into the L2." }, { - "EventCode": "44054", + "EventCode": "0x44054", "EventName": "PM_VECTOR_LD_CMPL", "BriefDescription": "Vector load instructions completed." }, { - "EventCode": "45054", + "EventCode": "0x45054", "EventName": "PM_FMA_CMPL", "BriefDescription": "Two floating point instructions completed (FMA class of instructions: fmadd, fnmadd, fmsub, fnmsub). Scalar instructions only." }, { - "EventCode": "45056", + "EventCode": "0x45056", "EventName": "PM_SCALAR_FLOP_CMPL", "BriefDescription": "Scalar floating point instructions completed." }, { - "EventCode": "4505C", + "EventCode": "0x4505C", "EventName": "PM_MATH_FLOP_CMPL", "BriefDescription": "Math floating point instructions completed." }, { - "EventCode": "4D05E", + "EventCode": "0x4D05E", "EventName": "PM_BR_CMPL", "BriefDescription": "A branch completed. All branches are included." }, { - "EventCode": "4E15E", + "EventCode": "0x4E15E", "EventName": "PM_MRK_INST_FLUSHED", "BriefDescription": "The marked instruction was flushed." }, { - "EventCode": "401E6", + "EventCode": "0x401E6", "EventName": "PM_MRK_INST_FROM_L3MISS", "BriefDescription": "The processor's instruction cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss for a marked instruction." }, { - "EventCode": "401E8", + "EventCode": "0x401E8", "EventName": "PM_MRK_DATA_FROM_L2MISS", "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1 or L2 due to a demand miss for a marked load." }, { - "EventCode": "400F0", + "EventCode": "0x400F0", "EventName": "PM_LD_DEMAND_MISS_L1_FIN", "BriefDescription": "Load Missed L1, counted at finish time." }, { - "EventCode": "400FA", + "EventCode": "0x400FA", "EventName": "PM_RUN_INST_CMPL", "BriefDescription": "Completed PowerPC instructions gated by the run latch." } diff --git a/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json b/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json index b61b5cc157ee..b8aded6045fa 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json @@ -1,296 +1,291 @@ [ { - "EventCode": "100FE", + "EventCode": "0x100FE", "EventName": "PM_INST_CMPL", "BriefDescription": "PowerPC instructions completed." }, { - "EventCode": "10006", - "EventName": "PM_DISP_STALL_HELD_OTHER_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch for any other reason." - }, - { - "EventCode": "1000C", + "EventCode": "0x1000C", "EventName": "PM_LSU_LD0_FIN", "BriefDescription": "LSU Finished an internal operation in LD0 port." }, { - "EventCode": "1000E", + "EventCode": "0x1000E", "EventName": "PM_MMA_ISSUED", "BriefDescription": "MMA instructions issued." }, { - "EventCode": "10012", + "EventCode": "0x10012", "EventName": "PM_LSU_ST0_FIN", "BriefDescription": "LSU Finished an internal operation in ST0 port." }, { - "EventCode": "10014", + "EventCode": "0x10014", "EventName": "PM_LSU_ST4_FIN", "BriefDescription": "LSU Finished an internal operation in ST4 port." }, { - "EventCode": "10018", + "EventCode": "0x10018", "EventName": "PM_IC_DEMAND_CYC", "BriefDescription": "Cycles in which an instruction reload is pending to satisfy a demand miss." }, { - "EventCode": "10022", + "EventCode": "0x10022", "EventName": "PM_PMC2_SAVED", "BriefDescription": "The conditions for the speculative event selected for PMC2 are met and PMC2 is charged." }, { - "EventCode": "10024", + "EventCode": "0x10024", "EventName": "PM_PMC5_OVERFLOW", "BriefDescription": "The event selected for PMC5 caused the event counter to overflow." }, { - "EventCode": "10058", + "EventCode": "0x10058", "EventName": "PM_EXEC_STALL_FIN_AT_DISP", "BriefDescription": "Cycles in which the oldest instruction in the pipeline finished at dispatch and did not require execution in the LSU, BRU or VSU." }, { - "EventCode": "1005A", + "EventCode": "0x1005A", "EventName": "PM_FLUSH_MPRED", "BriefDescription": "A flush occurred due to a mispredicted branch. Includes target and direction." }, { - "EventCode": "1C05A", + "EventCode": "0x1C05A", "EventName": "PM_DERAT_MISS_2M", "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 2M. Implies radix translation. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "10064", - "EventName": "PM_DISP_STALL_IC_L2", - "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L2." + "EventCode": "0x1E05A", + "EventName": "PM_CMPL_STALL_LWSYNC", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a lwsync waiting to complete." }, { - "EventCode": "10068", + "EventCode": "0x10068", "EventName": "PM_BR_FIN", "BriefDescription": "A branch instruction finished. Includes predicted/mispredicted/unconditional." }, { - "EventCode": "1006A", + "EventCode": "0x1006A", "EventName": "PM_FX_LSU_FIN", "BriefDescription": "Simple fixed point instruction issued to the store unit. Measured at finish time." }, { - "EventCode": "1006C", + "EventCode": "0x1006C", "EventName": "PM_RUN_CYC_ST_MODE", "BriefDescription": "Cycles when the run latch is set and the core is in ST mode." }, { - "EventCode": "20004", + "EventCode": "0x20004", "EventName": "PM_ISSUE_STALL", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was dispatched but not issued yet." }, { - "EventCode": "2000A", + "EventCode": "0x2000A", "EventName": "PM_HYPERVISOR_CYC", "BriefDescription": "Cycles when the thread is in Hypervisor state. MSR[S HV PR]=010." }, { - "EventCode": "2000E", + "EventCode": "0x2000E", "EventName": "PM_LSU_LD1_FIN", "BriefDescription": "LSU Finished an internal operation in LD1 port." }, { - "EventCode": "2C014", + "EventCode": "0x2C014", "EventName": "PM_CMPL_STALL_SPECIAL", "BriefDescription": "Cycles in which the oldest instruction in the pipeline required special handling before completing." }, { - "EventCode": "2C018", + "EventCode": "0x2C018", "EventName": "PM_EXEC_STALL_DMISS_L3MISS", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from a source beyond the local L2 or local L3." }, { - "EventCode": "2D010", + "EventCode": "0x2D010", "EventName": "PM_LSU_ST1_FIN", "BriefDescription": "LSU Finished an internal operation in ST1 port." }, { - "EventCode": "2D012", + "EventCode": "0x2D012", "EventName": "PM_VSU1_ISSUE", "BriefDescription": "VSU instructions issued to VSU pipe 1." }, { - "EventCode": "2D018", + "EventCode": "0x2D018", "EventName": "PM_EXEC_STALL_VSU", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the VSU (includes FXU, VSU, CRU)." }, { - "EventCode": "2E01E", + "EventCode": "0x2D01C", + "EventName": "PM_CMPL_STALL_STCX", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a stcx waiting for resolution from the nest before completing." + }, + { + "EventCode": "0x2E01E", "EventName": "PM_EXEC_STALL_NTC_FLUSH", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in any unit before it was flushed. Note that if the flush of the oldest instruction happens after finish, the cycles from dispatch to issue will be included in PM_DISP_STALL and the cycles from issue to finish will be included in PM_EXEC_STALL and its corresponding children." + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in any unit before it was flushed. Note that if the flush of the oldest instruction happens after finish, the cycles from dispatch to issue will be included in PM_DISP_STALL and the cycles from issue to finish will be included in PM_EXEC_STALL and its corresponding children. This event will also count cycles when the previous NTF instruction is still completing and the new NTF instruction is stalled at dispatch." }, { - "EventCode": "2013C", + "EventCode": "0x2013C", "EventName": "PM_MRK_FX_LSU_FIN", "BriefDescription": "The marked instruction was simple fixed point that was issued to the store unit. Measured at finish time." }, { - "EventCode": "2405A", + "EventCode": "0x2405A", "EventName": "PM_NTC_FIN", "BriefDescription": "Cycles in which the oldest instruction in the pipeline (NTC) finishes. Note that instructions can finish out of order, therefore not all the instructions that finish have a Next-to-complete status." }, { - "EventCode": "201E2", + "EventCode": "0x201E2", "EventName": "PM_MRK_LD_MISS_L1", "BriefDescription": "Marked DL1 Demand Miss counted at finish time." }, { - "EventCode": "200F4", + "EventCode": "0x200F4", "EventName": "PM_RUN_CYC", "BriefDescription": "Processor cycles gated by the run latch." }, { - "EventCode": "30004", - "EventName": "PM_DISP_STALL_FLUSH", - "BriefDescription": "Cycles when dispatch was stalled because of a flush that happened to an instruction(s) that was not yet NTC. PM_EXEC_STALL_NTC_FLUSH only includes instructions that were flushed after becoming NTC." - }, - { - "EventCode": "30008", + "EventCode": "0x30008", "EventName": "PM_EXEC_STALL", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting to finish in one of the execution units (BRU, LSU, VSU). Only cycles between issue and finish are counted in this category." }, { - "EventCode": "3001A", + "EventCode": "0x3001A", "EventName": "PM_LSU_ST2_FIN", "BriefDescription": "LSU Finished an internal operation in ST2 port." }, { - "EventCode": "30020", + "EventCode": "0x30020", "EventName": "PM_PMC2_REWIND", "BriefDescription": "The speculative event selected for PMC2 rewinds and the counter for PMC2 is not charged." }, { - "EventCode": "30022", + "EventCode": "0x30022", "EventName": "PM_PMC4_SAVED", "BriefDescription": "The conditions for the speculative event selected for PMC4 are met and PMC4 is charged." }, { - "EventCode": "30024", + "EventCode": "0x30024", "EventName": "PM_PMC6_OVERFLOW", "BriefDescription": "The event selected for PMC6 caused the event counter to overflow." }, { - "EventCode": "30028", + "EventCode": "0x30028", "EventName": "PM_CMPL_STALL_MEM_ECC", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for the non-speculative finish of either a stcx waiting for its result or a load waiting for non-critical sectors of data and ECC." }, { - "EventCode": "30036", + "EventCode": "0x30036", "EventName": "PM_EXEC_STALL_SIMPLE_FX", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a simple fixed point instruction executing in the Load Store Unit." }, { - "EventCode": "3003A", + "EventCode": "0x3003A", "EventName": "PM_CMPL_STALL_EXCEPTION", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was not allowed to complete because it was interrupted by ANY exception, which has to be serviced before the instruction can complete." }, { - "EventCode": "3F044", + "EventCode": "0x3F044", "EventName": "PM_VSU2_ISSUE", "BriefDescription": "VSU instructions issued to VSU pipe 2." }, { - "EventCode": "30058", + "EventCode": "0x30058", "EventName": "PM_TLBIE_FIN", "BriefDescription": "TLBIE instructions finished in the LSU. Two TLBIEs can finish each cycle. All will be counted." }, { - "EventCode": "3D058", + "EventCode": "0x3D058", "EventName": "PM_SCALAR_FSQRT_FDIV_ISSUE", "BriefDescription": "Scalar versions of four floating point operations: fdiv,fsqrt (xvdivdp, xvdivsp, xvsqrtdp, xvsqrtsp)." }, { - "EventCode": "30066", + "EventCode": "0x30066", "EventName": "PM_LSU_FIN", "BriefDescription": "LSU Finished an internal operation (up to 4 per cycle)." }, { - "EventCode": "40004", + "EventCode": "0x40004", "EventName": "PM_FXU_ISSUE", "BriefDescription": "A fixed point instruction was issued to the VSU." }, { - "EventCode": "40008", + "EventCode": "0x40008", "EventName": "PM_NTC_ALL_FIN", "BriefDescription": "Cycles in which both instructions in the ICT entry pair show as finished. These are the cycles between finish and completion for the oldest pair of instructions in the pipeline." }, { - "EventCode": "40010", + "EventCode": "0x40010", "EventName": "PM_PMC3_OVERFLOW", "BriefDescription": "The event selected for PMC3 caused the event counter to overflow." }, { - "EventCode": "4C012", + "EventCode": "0x4C012", "EventName": "PM_EXEC_STALL_DERAT_ONLY_MISS", "BriefDescription": "Cycles in which the oldest instruction in the pipeline suffered an ERAT miss and waited for it resolve." }, { - "EventCode": "4C018", + "EventCode": "0x4C018", "EventName": "PM_CMPL_STALL", "BriefDescription": "Cycles in which the oldest instruction in the pipeline cannot complete because the thread was blocked for any reason." }, { - "EventCode": "4C01E", + "EventCode": "0x4C01E", "EventName": "PM_LSU_ST3_FIN", "BriefDescription": "LSU Finished an internal operation in ST3 port." }, { - "EventCode": "4D018", + "EventCode": "0x4D018", "EventName": "PM_EXEC_STALL_BRU", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the Branch unit." }, { - "EventCode": "4D01A", + "EventCode": "0x4D01A", "EventName": "PM_CMPL_STALL_HWSYNC", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a hwsync waiting for response from L2 before completing." }, { - "EventCode": "4D01C", + "EventCode": "0x4D01C", "EventName": "PM_EXEC_STALL_TLBIEL", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a TLBIEL instruction executing in the Load Store Unit. TLBIEL instructions have lower overhead than TLBIE instructions because they don't get set to the nest." }, { - "EventCode": "4E012", + "EventCode": "0x4E012", "EventName": "PM_EXEC_STALL_UNKNOWN", "BriefDescription": "Cycles in which the oldest instruction in the pipeline completed without an ntf_type pulse. The ntf_pulse was missed by the ISU because the NTF finishes and completions came too close together." }, { - "EventCode": "4D020", + "EventCode": "0x4D020", "EventName": "PM_VSU3_ISSUE", "BriefDescription": "VSU instruction was issued to VSU pipe 3." }, { - "EventCode": "40132", + "EventCode": "0x40132", "EventName": "PM_MRK_LSU_FIN", "BriefDescription": "LSU marked instruction finish." }, { - "EventCode": "45058", + "EventCode": "0x45058", "EventName": "PM_IC_MISS_CMPL", "BriefDescription": "Non-speculative icache miss, counted at completion." }, { - "EventCode": "4D050", + "EventCode": "0x4D050", "EventName": "PM_VSU_NON_FLOP_CMPL", "BriefDescription": "Non-floating point VSU instructions completed." }, { - "EventCode": "4D052", + "EventCode": "0x4D052", "EventName": "PM_2FLOP_CMPL", "BriefDescription": "Double Precision vector version of fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg completed." }, { - "EventCode": "400F2", + "EventCode": "0x400F2", "EventName": "PM_1PLUS_PPC_DISP", "BriefDescription": "Cycles at least one Instr Dispatched." }, { - "EventCode": "400F8", + "EventCode": "0x400F8", "EventName": "PM_FLUSH", "BriefDescription": "Flush (any type)." } diff --git a/tools/perf/pmu-events/arch/powerpc/power10/pmc.json b/tools/perf/pmu-events/arch/powerpc/power10/pmc.json index ea122a91ceb0..b5d1bd39cfb2 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/pmc.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/pmc.json @@ -1,21 +1,21 @@ [ { - "EventCode": "301E8", + "EventCode": "0x301E8", "EventName": "PM_THRESH_EXC_64", "BriefDescription": "Threshold counter exceeded a value of 64." }, { - "EventCode": "45050", + "EventCode": "0x45050", "EventName": "PM_1FLOP_CMPL", "BriefDescription": "One floating point instruction completed (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg)." }, { - "EventCode": "45052", + "EventCode": "0x45052", "EventName": "PM_4FLOP_CMPL", "BriefDescription": "Four floating point instructions completed (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg)." }, { - "EventCode": "4D054", + "EventCode": "0x4D054", "EventName": "PM_8FLOP_CMPL", "BriefDescription": "Four Double Precision vector instructions completed." } diff --git a/tools/perf/pmu-events/arch/powerpc/power10/translation.json b/tools/perf/pmu-events/arch/powerpc/power10/translation.json index 5a714e3dd71a..db3766dca07c 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/translation.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/translation.json @@ -1,56 +1,56 @@ [ { - "EventCode": "1F15E", + "EventCode": "0x1F15E", "EventName": "PM_MRK_START_PROBE_NOP_CMPL", "BriefDescription": "Marked Start probe nop (AND R0,R0,R0) completed." }, { - "EventCode": "20016", + "EventCode": "0x20016", "EventName": "PM_ST_FIN", "BriefDescription": "Store finish count. Includes speculative activity." }, { - "EventCode": "20018", + "EventCode": "0x20018", "EventName": "PM_ST_FWD", "BriefDescription": "Store forwards that finished." }, { - "EventCode": "2011C", + "EventCode": "0x2011C", "EventName": "PM_MRK_NTF_CYC", "BriefDescription": "Cycles during which the marked instruction is the oldest in the pipeline (NTF or NTC)." }, { - "EventCode": "2E01C", + "EventCode": "0x2E01C", "EventName": "PM_EXEC_STALL_TLBIE", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a TLBIE instruction executing in the Load Store Unit." }, { - "EventCode": "201E6", + "EventCode": "0x201E6", "EventName": "PM_THRESH_EXC_32", "BriefDescription": "Threshold counter exceeded a value of 32." }, { - "EventCode": "200F0", + "EventCode": "0x200F0", "EventName": "PM_ST_CMPL", "BriefDescription": "Stores completed from S2Q (2nd-level store queue). This event includes regular stores, stcx and cache inhibited stores. The following operations are excluded (pteupdate, snoop tlbie complete, store atomics, miso, load atomic payloads, tlbie, tlbsync, slbieg, isync, msgsnd, slbiag, cpabort, copy, tcheck, tend, stsync, dcbst, icbi, dcbf, hwsync, lwsync, ptesync, eieio, msgsync)." }, { - "EventCode": "200FE", + "EventCode": "0x200FE", "EventName": "PM_DATA_FROM_L2MISS", "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1 or L2 due to a demand miss." }, { - "EventCode": "30010", + "EventCode": "0x30010", "EventName": "PM_PMC2_OVERFLOW", "BriefDescription": "The event selected for PMC2 caused the event counter to overflow." }, { - "EventCode": "4D010", + "EventCode": "0x4D010", "EventName": "PM_PMC1_SAVED", "BriefDescription": "The conditions for the speculative event selected for PMC1 are met and PMC1 is charged." }, { - "EventCode": "4D05C", + "EventCode": "0x4D05C", "EventName": "PM_DPP_FLOP_CMPL", "BriefDescription": "Double-Precision or Quad-Precision instructions completed." } diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index 7422b0ea8790..9604446f8360 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -960,7 +960,7 @@ static int get_maxfds(void) struct rlimit rlim; if (getrlimit(RLIMIT_NOFILE, &rlim) == 0) - return min((int)rlim.rlim_max / 2, 512); + return min(rlim.rlim_max / 2, (rlim_t)512); return 512; } diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py index 7daa8bb70a5a..711d4f9f5645 100755 --- a/tools/perf/scripts/python/exported-sql-viewer.py +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -91,6 +91,11 @@ from __future__ import print_function import sys +# Only change warnings if the python -W option was not used +if not sys.warnoptions: + import warnings + # PySide2 causes deprecation warnings, ignore them. + warnings.filterwarnings("ignore", category=DeprecationWarning) import argparse import weakref import threading @@ -125,8 +130,9 @@ if pyside_version_1: from PySide.QtGui import * from PySide.QtSql import * -from decimal import * -from ctypes import * +from decimal import Decimal, ROUND_HALF_UP +from ctypes import CDLL, Structure, create_string_buffer, addressof, sizeof, \ + c_void_p, c_bool, c_byte, c_char, c_int, c_uint, c_longlong, c_ulonglong from multiprocessing import Process, Array, Value, Event # xrange is range in Python3 @@ -3868,7 +3874,7 @@ def CopyTableCellsToClipboard(view, as_csv=False, with_hdr=False): if with_hdr: model = indexes[0].model() for col in range(min_col, max_col + 1): - val = model.headerData(col, Qt.Horizontal) + val = model.headerData(col, Qt.Horizontal, Qt.DisplayRole) if as_csv: text += sep + ToCSValue(val) sep = "," diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record index 4a7b8deef3fd..8c10955eff93 100644 --- a/tools/perf/tests/attr/base-record +++ b/tools/perf/tests/attr/base-record @@ -16,7 +16,7 @@ pinned=0 exclusive=0 exclude_user=0 exclude_kernel=0|1 -exclude_hv=0 +exclude_hv=0|1 exclude_idle=0 mmap=1 comm=1 diff --git a/tools/perf/tests/pfm.c b/tools/perf/tests/pfm.c index 76a53126efdf..d4b0ef74defc 100644 --- a/tools/perf/tests/pfm.c +++ b/tools/perf/tests/pfm.c @@ -131,8 +131,8 @@ static int test__pfm_group(void) }, { .events = "{},{instructions}", - .nr_events = 0, - .nr_groups = 0, + .nr_events = 1, + .nr_groups = 1, }, { .events = "{instructions},{instructions}", diff --git a/tools/perf/tests/shell/stat_bpf_counters.sh b/tools/perf/tests/shell/stat_bpf_counters.sh index 22eb31e48ca7..2f9948b3d943 100755 --- a/tools/perf/tests/shell/stat_bpf_counters.sh +++ b/tools/perf/tests/shell/stat_bpf_counters.sh @@ -11,9 +11,9 @@ compare_number() second_num=$2 # upper bound is first_num * 110% - upper=$(( $first_num + $first_num / 10 )) + upper=$(expr $first_num + $first_num / 10 ) # lower bound is first_num * 90% - lower=$(( $first_num - $first_num / 10 )) + lower=$(expr $first_num - $first_num / 10 ) if [ $second_num -gt $upper ] || [ $second_num -lt $lower ]; then echo "The difference between $first_num and $second_num are greater than 10%." diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h index b8fc5c53ba6f..0d8e3dcb7f88 100644 --- a/tools/perf/trace/beauty/include/linux/socket.h +++ b/tools/perf/trace/beauty/include/linux/socket.h @@ -438,6 +438,4 @@ extern int __sys_socketpair(int family, int type, int protocol, int __user *usockvec); extern int __sys_shutdown_sock(struct socket *sock, int how); extern int __sys_shutdown(int fd, int how); - -extern struct ns_common *get_net_ns(struct ns_common *ns); #endif /* _LINUX_SOCKET_H */ diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c index ddb52f748c8e..5ed674a2f55e 100644 --- a/tools/perf/util/bpf_counter.c +++ b/tools/perf/util/bpf_counter.c @@ -451,10 +451,10 @@ static int bperf_reload_leader_program(struct evsel *evsel, int attr_map_fd, goto out; } - err = -1; link = bpf_program__attach(skel->progs.on_switch); - if (!link) { + if (IS_ERR(link)) { pr_err("Failed to attach leader program\n"); + err = PTR_ERR(link); goto out; } @@ -521,9 +521,10 @@ static int bperf__load(struct evsel *evsel, struct target *target) evsel->bperf_leader_link_fd = bpf_link_get_fd_by_id(entry.link_id); if (evsel->bperf_leader_link_fd < 0 && - bperf_reload_leader_program(evsel, attr_map_fd, &entry)) + bperf_reload_leader_program(evsel, attr_map_fd, &entry)) { + err = -1; goto out; - + } /* * The bpf_link holds reference to the leader program, and the * leader program holds reference to the maps. Therefore, if @@ -550,6 +551,7 @@ static int bperf__load(struct evsel *evsel, struct target *target) /* Step 2: load the follower skeleton */ evsel->follower_skel = bperf_follower_bpf__open(); if (!evsel->follower_skel) { + err = -1; pr_err("Failed to open follower skeleton\n"); goto out; } diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index b2f4920e19a6..7d2ba8419b0c 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -975,9 +975,13 @@ static int __die_find_variable_cb(Dwarf_Die *die_mem, void *data) if ((tag == DW_TAG_formal_parameter || tag == DW_TAG_variable) && die_compare_name(die_mem, fvp->name) && - /* Does the DIE have location information or external instance? */ + /* + * Does the DIE have location information or const value + * or external instance? + */ (dwarf_attr(die_mem, DW_AT_external, &attr) || - dwarf_attr(die_mem, DW_AT_location, &attr))) + dwarf_attr(die_mem, DW_AT_location, &attr) || + dwarf_attr(die_mem, DW_AT_const_value, &attr))) return DIE_FIND_CB_END; if (dwarf_haspc(die_mem, fvp->addr)) return DIE_FIND_CB_CONTINUE; diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 9130f6fad8d5..bc5e4f294e9e 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -144,6 +144,7 @@ static void perf_env__purge_bpf(struct perf_env *env) node = rb_entry(next, struct bpf_prog_info_node, rb_node); next = rb_next(&node->rb_node); rb_erase(&node->rb_node, root); + free(node->info_linear); free(node); } diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 8a62fb39e365..19ad64f2bd83 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -100,7 +100,7 @@ enum { PERF_IP_FLAG_VMEXIT = 1ULL << 12, }; -#define PERF_IP_FLAG_CHARS "bcrosyiABEx" +#define PERF_IP_FLAG_CHARS "bcrosyiABExgh" #define PERF_BRANCH_MASK (\ PERF_IP_FLAG_BRANCH |\ diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 6e5c41528c7d..6ea3e677dc1e 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -425,9 +425,6 @@ static void __evlist__disable(struct evlist *evlist, char *evsel_name) if (affinity__setup(&affinity) < 0) return; - evlist__for_each_entry(evlist, pos) - bpf_counter__disable(pos); - /* Disable 'immediate' events last */ for (imm = 0; imm <= 1; imm++) { evlist__for_each_cpu(evlist, i, cpu) { diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 4a3cd1b5bb33..a8d8463f8ee5 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -428,6 +428,7 @@ struct evsel *evsel__clone(struct evsel *orig) evsel->auto_merge_stats = orig->auto_merge_stats; evsel->collect_stat = orig->collect_stat; evsel->weak_group = orig->weak_group; + evsel->use_config_name = orig->use_config_name; if (evsel__copy_config_terms(evsel, orig) < 0) goto out_err; diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 75cf5dbfe208..bdad52a06438 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -83,8 +83,10 @@ struct evsel { bool collect_stat; bool weak_group; bool bpf_counter; + bool use_config_name; int bpf_fd; struct bpf_object *bpf_obj; + struct list_head config_terms; }; /* @@ -116,10 +118,8 @@ struct evsel { bool merged_stat; bool reset_group; bool errored; - bool use_config_name; struct hashmap *per_pkg_mask; struct evsel *leader; - struct list_head config_terms; int err; int cpu_iter; struct { 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 8c59677bee13..20ad663978cc 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -1146,6 +1146,8 @@ static bool intel_pt_fup_event(struct intel_pt_decoder *decoder) decoder->set_fup_tx_flags = false; decoder->tx_flags = decoder->fup_tx_flags; decoder->state.type = INTEL_PT_TRANSACTION; + if (decoder->fup_tx_flags & INTEL_PT_ABORT_TX) + decoder->state.type |= INTEL_PT_BRANCH; decoder->state.from_ip = decoder->ip; decoder->state.to_ip = 0; decoder->state.flags = decoder->fup_tx_flags; @@ -1220,8 +1222,10 @@ static int intel_pt_walk_fup(struct intel_pt_decoder *decoder) return 0; if (err == -EAGAIN || intel_pt_fup_with_nlip(decoder, &intel_pt_insn, ip, err)) { + bool no_tip = decoder->pkt_state != INTEL_PT_STATE_FUP; + decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; - if (intel_pt_fup_event(decoder)) + if (intel_pt_fup_event(decoder) && no_tip) return 0; return -EAGAIN; } diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 8658d42ce57a..0dfec8761b9a 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -707,8 +707,10 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn, *ip += intel_pt_insn->length; - if (to_ip && *ip == to_ip) + if (to_ip && *ip == to_ip) { + intel_pt_insn->length = 0; goto out_no_cache; + } if (*ip >= al.map->end) break; @@ -1198,6 +1200,7 @@ static void intel_pt_set_pid_tid_cpu(struct intel_pt *pt, static void intel_pt_sample_flags(struct intel_pt_queue *ptq) { + ptq->insn_len = 0; if (ptq->state->flags & INTEL_PT_ABORT_TX) { ptq->flags = PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TX_ABORT; } else if (ptq->state->flags & INTEL_PT_ASYNC) { @@ -1211,7 +1214,6 @@ static void intel_pt_sample_flags(struct intel_pt_queue *ptq) ptq->flags = PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC | PERF_IP_FLAG_INTERRUPT; - ptq->insn_len = 0; } else { if (ptq->state->from_ip) ptq->flags = intel_pt_insn_type(ptq->state->insn_op); diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 3ff4936a15a4..da19be7da284 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -776,10 +776,10 @@ static int machine__process_ksymbol_register(struct machine *machine, if (dso) { dso->kernel = DSO_SPACE__KERNEL; map = map__new2(0, dso); + dso__put(dso); } if (!dso || !map) { - dso__put(dso); return -ENOMEM; } @@ -792,6 +792,7 @@ static int machine__process_ksymbol_register(struct machine *machine, map->start = event->ksymbol.addr; map->end = map->start + event->ksymbol.len; maps__insert(&machine->kmaps, map); + map__put(map); dso__set_loaded(dso); if (is_bpf_image(event->ksymbol.name)) { diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 8336dd8e8098..d3cf2dee36c8 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -162,10 +162,10 @@ static bool contains_event(struct evsel **metric_events, int num_events, return false; } -static bool evsel_same_pmu(struct evsel *ev1, struct evsel *ev2) +static bool evsel_same_pmu_or_none(struct evsel *ev1, struct evsel *ev2) { if (!ev1->pmu_name || !ev2->pmu_name) - return false; + return true; return !strcmp(ev1->pmu_name, ev2->pmu_name); } @@ -288,7 +288,7 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, */ if (!has_constraint && ev->leader != metric_events[i]->leader && - evsel_same_pmu(ev->leader, metric_events[i]->leader)) + evsel_same_pmu_or_none(ev->leader, metric_events[i]->leader)) break; if (!strcmp(metric_events[i]->name, ev->name)) { set_bit(ev->idx, evlist_used); @@ -1073,16 +1073,18 @@ static int metricgroup__add_metric_sys_event_iter(struct pmu_event *pe, ret = add_metric(d->metric_list, pe, d->metric_no_group, &m, NULL, d->ids); if (ret) - return ret; + goto out; ret = resolve_metric(d->metric_no_group, d->metric_list, NULL, d->ids); if (ret) - return ret; + goto out; *(d->has_match) = true; - return *d->ret; +out: + *(d->ret) = ret; + return ret; } static int metricgroup__add_metric(const char *metric, bool metric_no_group, diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 4dad14265b81..84108c17f48d 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -150,6 +150,10 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = { .symbol = "bpf-output", .alias = "", }, + [PERF_COUNT_SW_CGROUP_SWITCHES] = { + .symbol = "cgroup-switches", + .alias = "", + }, }; #define __PERF_EVENT_FIELD(config, name) \ @@ -2928,9 +2932,14 @@ restart: } for (i = 0; i < max; i++, syms++) { + /* + * New attr.config still not supported here, the latest + * example was PERF_COUNT_SW_CGROUP_SWITCHES + */ + if (syms->symbol == NULL) + continue; - if (event_glob != NULL && syms->symbol != NULL && - !(strglobmatch(syms->symbol, event_glob) || + if (event_glob != NULL && !(strglobmatch(syms->symbol, event_glob) || (syms->alias && strglobmatch(syms->alias, event_glob)))) continue; diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index fb8646cc3e83..923849024b15 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -347,6 +347,7 @@ emulation-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EM dummy { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); } duration_time { return tool(yyscanner, PERF_TOOL_DURATION_TIME); } bpf-output { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); } +cgroup-switches { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CGROUP_SWITCHES); } /* * We have to handle the kernel PMU event cycles-ct/cycles-t/mem-loads/mem-stores separately. diff --git a/tools/perf/util/perf_api_probe.c b/tools/perf/util/perf_api_probe.c index 829af17a0867..020411682a3c 100644 --- a/tools/perf/util/perf_api_probe.c +++ b/tools/perf/util/perf_api_probe.c @@ -103,6 +103,11 @@ static void perf_probe_build_id(struct evsel *evsel) evsel->core.attr.build_id = 1; } +static void perf_probe_cgroup(struct evsel *evsel) +{ + evsel->core.attr.cgroup = 1; +} + bool perf_can_sample_identifier(void) { return perf_probe_api(perf_probe_sample_identifier); @@ -182,3 +187,8 @@ bool perf_can_record_build_id(void) { return perf_probe_api(perf_probe_build_id); } + +bool perf_can_record_cgroup(void) +{ + return perf_probe_api(perf_probe_cgroup); +} diff --git a/tools/perf/util/perf_api_probe.h b/tools/perf/util/perf_api_probe.h index f12ca55f509a..b104168efb15 100644 --- a/tools/perf/util/perf_api_probe.h +++ b/tools/perf/util/perf_api_probe.h @@ -12,5 +12,6 @@ bool perf_can_record_switch_events(void); bool perf_can_record_text_poke_events(void); bool perf_can_sample_identifier(void); bool perf_can_record_build_id(void); +bool perf_can_record_cgroup(void); #endif // __PERF_API_PROBE_H diff --git a/tools/perf/util/pfm.c b/tools/perf/util/pfm.c index d735acb6c29c..6eef6dfeaa57 100644 --- a/tools/perf/util/pfm.c +++ b/tools/perf/util/pfm.c @@ -62,8 +62,16 @@ int parse_libpfm_events_option(const struct option *opt, const char *str, } /* no event */ - if (*q == '\0') + if (*q == '\0') { + if (*sep == '}') { + if (grp_evt < 0) { + ui__error("cannot close a non-existing event group\n"); + goto error; + } + grp_evt--; + } continue; + } memset(&attr, 0, sizeof(attr)); event_attr_init(&attr); @@ -107,6 +115,7 @@ int parse_libpfm_events_option(const struct option *opt, const char *str, grp_evt = -1; } } + free(p_orig); return 0; error: free(p_orig); diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 866f2d514d72..b029c29ce227 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -190,6 +190,9 @@ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr, immediate_value_is_supported()) { Dwarf_Sword snum; + if (!tvar) + return 0; + dwarf_formsdata(&attr, &snum); ret = asprintf(&tvar->value, "\\%ld", (long)snum); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 106b3d60881a..e59242c361ce 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1723,6 +1723,7 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset, if (event->header.size < hdr_sz || event->header.size > buf_sz) return -1; + buf += hdr_sz; rest = event->header.size - hdr_sz; if (readn(fd, buf, rest) != (ssize_t)rest) diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index a76fff5e7d83..ca326f98c7a2 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -541,7 +541,7 @@ static void uniquify_event_name(struct evsel *counter) char *config; int ret = 0; - if (counter->uniquified_name || + if (counter->uniquified_name || counter->use_config_name || !counter->pmu_name || !strncmp(counter->name, counter->pmu_name, strlen(counter->pmu_name))) return; @@ -555,10 +555,8 @@ static void uniquify_event_name(struct evsel *counter) } } else { if (perf_pmu__has_hybrid()) { - if (!counter->use_config_name) { - ret = asprintf(&new_name, "%s/%s/", - counter->pmu_name, counter->name); - } + ret = asprintf(&new_name, "%s/%s/", + counter->pmu_name, counter->name); } else { ret = asprintf(&new_name, "%s [%s]", counter->name, counter->pmu_name); diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 4c56aa837434..a73345730ba9 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -2412,6 +2412,7 @@ int cleanup_sdt_note_list(struct list_head *sdt_notes) list_for_each_entry_safe(pos, tmp, sdt_notes, note_list) { list_del_init(&pos->note_list); + zfree(&pos->args); zfree(&pos->name); zfree(&pos->provider); free(pos); diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index 12ee40284da0..2060bc122c53 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -40,7 +40,7 @@ struct ipv6_packet pkt_v6 = { .tcp.doff = 5, }; -static int settimeo(int fd, int timeout_ms) +int settimeo(int fd, int timeout_ms) { struct timeval timeout = { .tv_sec = 3 }; diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index 7205f8afdba1..5e0d51c07b63 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -33,6 +33,7 @@ struct ipv6_packet { } __packed; extern struct ipv6_packet pkt_v6; +int settimeo(int fd, int timeout_ms); int start_server(int family, int type, const char *addr, __u16 port, int timeout_ms); int connect_to_fd(int server_fd, int timeout_ms); diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c index de78617f6550..f9a8ae331963 100644 --- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c +++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c @@ -86,8 +86,9 @@ void test_ringbuf(void) const size_t rec_sz = BPF_RINGBUF_HDR_SZ + sizeof(struct sample); pthread_t thread; long bg_ret = -1; - int err, cnt; + int err, cnt, rb_fd; int page_size = getpagesize(); + void *mmap_ptr, *tmp_ptr; skel = test_ringbuf__open(); if (CHECK(!skel, "skel_open", "skeleton open failed\n")) @@ -101,6 +102,52 @@ void test_ringbuf(void) if (CHECK(err != 0, "skel_load", "skeleton load failed\n")) goto cleanup; + rb_fd = bpf_map__fd(skel->maps.ringbuf); + /* good read/write cons_pos */ + mmap_ptr = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED, rb_fd, 0); + ASSERT_OK_PTR(mmap_ptr, "rw_cons_pos"); + tmp_ptr = mremap(mmap_ptr, page_size, 2 * page_size, MREMAP_MAYMOVE); + if (!ASSERT_ERR_PTR(tmp_ptr, "rw_extend")) + goto cleanup; + ASSERT_ERR(mprotect(mmap_ptr, page_size, PROT_EXEC), "exec_cons_pos_protect"); + ASSERT_OK(munmap(mmap_ptr, page_size), "unmap_rw"); + + /* bad writeable prod_pos */ + mmap_ptr = mmap(NULL, page_size, PROT_WRITE, MAP_SHARED, rb_fd, page_size); + err = -errno; + ASSERT_ERR_PTR(mmap_ptr, "wr_prod_pos"); + ASSERT_EQ(err, -EPERM, "wr_prod_pos_err"); + + /* bad writeable data pages */ + mmap_ptr = mmap(NULL, page_size, PROT_WRITE, MAP_SHARED, rb_fd, 2 * page_size); + err = -errno; + ASSERT_ERR_PTR(mmap_ptr, "wr_data_page_one"); + ASSERT_EQ(err, -EPERM, "wr_data_page_one_err"); + mmap_ptr = mmap(NULL, page_size, PROT_WRITE, MAP_SHARED, rb_fd, 3 * page_size); + ASSERT_ERR_PTR(mmap_ptr, "wr_data_page_two"); + mmap_ptr = mmap(NULL, 2 * page_size, PROT_WRITE, MAP_SHARED, rb_fd, 2 * page_size); + ASSERT_ERR_PTR(mmap_ptr, "wr_data_page_all"); + + /* good read-only pages */ + mmap_ptr = mmap(NULL, 4 * page_size, PROT_READ, MAP_SHARED, rb_fd, 0); + if (!ASSERT_OK_PTR(mmap_ptr, "ro_prod_pos")) + goto cleanup; + + ASSERT_ERR(mprotect(mmap_ptr, 4 * page_size, PROT_WRITE), "write_protect"); + ASSERT_ERR(mprotect(mmap_ptr, 4 * page_size, PROT_EXEC), "exec_protect"); + ASSERT_ERR_PTR(mremap(mmap_ptr, 0, 4 * page_size, MREMAP_MAYMOVE), "ro_remap"); + ASSERT_OK(munmap(mmap_ptr, 4 * page_size), "unmap_ro"); + + /* good read-only pages with initial offset */ + mmap_ptr = mmap(NULL, page_size, PROT_READ, MAP_SHARED, rb_fd, page_size); + if (!ASSERT_OK_PTR(mmap_ptr, "ro_prod_pos")) + goto cleanup; + + ASSERT_ERR(mprotect(mmap_ptr, page_size, PROT_WRITE), "write_protect"); + ASSERT_ERR(mprotect(mmap_ptr, page_size, PROT_EXEC), "exec_protect"); + ASSERT_ERR_PTR(mremap(mmap_ptr, 0, 3 * page_size, MREMAP_MAYMOVE), "ro_remap"); + ASSERT_OK(munmap(mmap_ptr, page_size), "unmap_ro"); + /* only trigger BPF program for current process */ skel->bss->pid = getpid(); diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c new file mode 100644 index 000000000000..5703c918812b --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c @@ -0,0 +1,785 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause + +/* + * This test sets up 3 netns (src <-> fwd <-> dst). There is no direct veth link + * between src and dst. The netns fwd has veth links to each src and dst. The + * client is in src and server in dst. The test installs a TC BPF program to each + * host facing veth in fwd which calls into i) bpf_redirect_neigh() to perform the + * neigh addr population and redirect or ii) bpf_redirect_peer() for namespace + * switch from ingress side; it also installs a checker prog on the egress side + * to drop unexpected traffic. + */ + +#define _GNU_SOURCE + +#include <arpa/inet.h> +#include <linux/limits.h> +#include <linux/sysctl.h> +#include <linux/if_tun.h> +#include <linux/if.h> +#include <sched.h> +#include <stdbool.h> +#include <stdio.h> +#include <sys/stat.h> +#include <sys/mount.h> + +#include "test_progs.h" +#include "network_helpers.h" +#include "test_tc_neigh_fib.skel.h" +#include "test_tc_neigh.skel.h" +#include "test_tc_peer.skel.h" + +#define NS_SRC "ns_src" +#define NS_FWD "ns_fwd" +#define NS_DST "ns_dst" + +#define IP4_SRC "172.16.1.100" +#define IP4_DST "172.16.2.100" +#define IP4_TUN_SRC "172.17.1.100" +#define IP4_TUN_FWD "172.17.1.200" +#define IP4_PORT 9004 + +#define IP6_SRC "0::1:dead:beef:cafe" +#define IP6_DST "0::2:dead:beef:cafe" +#define IP6_TUN_SRC "1::1:dead:beef:cafe" +#define IP6_TUN_FWD "1::2:dead:beef:cafe" +#define IP6_PORT 9006 + +#define IP4_SLL "169.254.0.1" +#define IP4_DLL "169.254.0.2" +#define IP4_NET "169.254.0.0" + +#define MAC_DST_FWD "00:11:22:33:44:55" +#define MAC_DST "00:22:33:44:55:66" + +#define IFADDR_STR_LEN 18 +#define PING_ARGS "-i 0.2 -c 3 -w 10 -q" + +#define SRC_PROG_PIN_FILE "/sys/fs/bpf/test_tc_src" +#define DST_PROG_PIN_FILE "/sys/fs/bpf/test_tc_dst" +#define CHK_PROG_PIN_FILE "/sys/fs/bpf/test_tc_chk" + +#define TIMEOUT_MILLIS 10000 + +#define log_err(MSG, ...) \ + fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \ + __FILE__, __LINE__, strerror(errno), ##__VA_ARGS__) + +static const char * const namespaces[] = {NS_SRC, NS_FWD, NS_DST, NULL}; + +static int write_file(const char *path, const char *newval) +{ + FILE *f; + + f = fopen(path, "r+"); + if (!f) + return -1; + if (fwrite(newval, strlen(newval), 1, f) != 1) { + log_err("writing to %s failed", path); + fclose(f); + return -1; + } + fclose(f); + return 0; +} + +struct nstoken { + int orig_netns_fd; +}; + +static int setns_by_fd(int nsfd) +{ + int err; + + err = setns(nsfd, CLONE_NEWNET); + close(nsfd); + + if (!ASSERT_OK(err, "setns")) + return err; + + /* Switch /sys to the new namespace so that e.g. /sys/class/net + * reflects the devices in the new namespace. + */ + err = unshare(CLONE_NEWNS); + if (!ASSERT_OK(err, "unshare")) + return err; + + err = umount2("/sys", MNT_DETACH); + if (!ASSERT_OK(err, "umount2 /sys")) + return err; + + err = mount("sysfs", "/sys", "sysfs", 0, NULL); + if (!ASSERT_OK(err, "mount /sys")) + return err; + + err = mount("bpffs", "/sys/fs/bpf", "bpf", 0, NULL); + if (!ASSERT_OK(err, "mount /sys/fs/bpf")) + return err; + + return 0; +} + +/** + * open_netns() - Switch to specified network namespace by name. + * + * Returns token with which to restore the original namespace + * using close_netns(). + */ +static struct nstoken *open_netns(const char *name) +{ + int nsfd; + char nspath[PATH_MAX]; + int err; + struct nstoken *token; + + token = malloc(sizeof(struct nstoken)); + if (!ASSERT_OK_PTR(token, "malloc token")) + return NULL; + + token->orig_netns_fd = open("/proc/self/ns/net", O_RDONLY); + if (!ASSERT_GE(token->orig_netns_fd, 0, "open /proc/self/ns/net")) + goto fail; + + snprintf(nspath, sizeof(nspath), "%s/%s", "/var/run/netns", name); + nsfd = open(nspath, O_RDONLY | O_CLOEXEC); + if (!ASSERT_GE(nsfd, 0, "open netns fd")) + goto fail; + + err = setns_by_fd(nsfd); + if (!ASSERT_OK(err, "setns_by_fd")) + goto fail; + + return token; +fail: + free(token); + return NULL; +} + +static void close_netns(struct nstoken *token) +{ + ASSERT_OK(setns_by_fd(token->orig_netns_fd), "setns_by_fd"); + free(token); +} + +static int netns_setup_namespaces(const char *verb) +{ + const char * const *ns = namespaces; + char cmd[128]; + + while (*ns) { + snprintf(cmd, sizeof(cmd), "ip netns %s %s", verb, *ns); + if (!ASSERT_OK(system(cmd), cmd)) + return -1; + ns++; + } + return 0; +} + +struct netns_setup_result { + int ifindex_veth_src_fwd; + int ifindex_veth_dst_fwd; +}; + +static int get_ifaddr(const char *name, char *ifaddr) +{ + char path[PATH_MAX]; + FILE *f; + int ret; + + snprintf(path, PATH_MAX, "/sys/class/net/%s/address", name); + f = fopen(path, "r"); + if (!ASSERT_OK_PTR(f, path)) + return -1; + + ret = fread(ifaddr, 1, IFADDR_STR_LEN, f); + if (!ASSERT_EQ(ret, IFADDR_STR_LEN, "fread ifaddr")) { + fclose(f); + return -1; + } + fclose(f); + return 0; +} + +static int get_ifindex(const char *name) +{ + char path[PATH_MAX]; + char buf[32]; + FILE *f; + int ret; + + snprintf(path, PATH_MAX, "/sys/class/net/%s/ifindex", name); + f = fopen(path, "r"); + if (!ASSERT_OK_PTR(f, path)) + return -1; + + ret = fread(buf, 1, sizeof(buf), f); + if (!ASSERT_GT(ret, 0, "fread ifindex")) { + fclose(f); + return -1; + } + fclose(f); + return atoi(buf); +} + +#define SYS(fmt, ...) \ + ({ \ + char cmd[1024]; \ + snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__); \ + if (!ASSERT_OK(system(cmd), cmd)) \ + goto fail; \ + }) + +static int netns_setup_links_and_routes(struct netns_setup_result *result) +{ + struct nstoken *nstoken = NULL; + char veth_src_fwd_addr[IFADDR_STR_LEN+1] = {}; + + SYS("ip link add veth_src type veth peer name veth_src_fwd"); + SYS("ip link add veth_dst type veth peer name veth_dst_fwd"); + + SYS("ip link set veth_dst_fwd address " MAC_DST_FWD); + SYS("ip link set veth_dst address " MAC_DST); + + if (get_ifaddr("veth_src_fwd", veth_src_fwd_addr)) + goto fail; + + result->ifindex_veth_src_fwd = get_ifindex("veth_src_fwd"); + if (result->ifindex_veth_src_fwd < 0) + goto fail; + result->ifindex_veth_dst_fwd = get_ifindex("veth_dst_fwd"); + if (result->ifindex_veth_dst_fwd < 0) + goto fail; + + SYS("ip link set veth_src netns " NS_SRC); + SYS("ip link set veth_src_fwd netns " NS_FWD); + SYS("ip link set veth_dst_fwd netns " NS_FWD); + SYS("ip link set veth_dst netns " NS_DST); + + /** setup in 'src' namespace */ + nstoken = open_netns(NS_SRC); + if (!ASSERT_OK_PTR(nstoken, "setns src")) + goto fail; + + SYS("ip addr add " IP4_SRC "/32 dev veth_src"); + SYS("ip addr add " IP6_SRC "/128 dev veth_src nodad"); + SYS("ip link set dev veth_src up"); + + SYS("ip route add " IP4_DST "/32 dev veth_src scope global"); + SYS("ip route add " IP4_NET "/16 dev veth_src scope global"); + SYS("ip route add " IP6_DST "/128 dev veth_src scope global"); + + SYS("ip neigh add " IP4_DST " dev veth_src lladdr %s", + veth_src_fwd_addr); + SYS("ip neigh add " IP6_DST " dev veth_src lladdr %s", + veth_src_fwd_addr); + + close_netns(nstoken); + + /** setup in 'fwd' namespace */ + nstoken = open_netns(NS_FWD); + if (!ASSERT_OK_PTR(nstoken, "setns fwd")) + goto fail; + + /* The fwd netns automatically gets a v6 LL address / routes, but also + * needs v4 one in order to start ARP probing. IP4_NET route is added + * to the endpoints so that the ARP processing will reply. + */ + SYS("ip addr add " IP4_SLL "/32 dev veth_src_fwd"); + SYS("ip addr add " IP4_DLL "/32 dev veth_dst_fwd"); + SYS("ip link set dev veth_src_fwd up"); + SYS("ip link set dev veth_dst_fwd up"); + + SYS("ip route add " IP4_SRC "/32 dev veth_src_fwd scope global"); + SYS("ip route add " IP6_SRC "/128 dev veth_src_fwd scope global"); + SYS("ip route add " IP4_DST "/32 dev veth_dst_fwd scope global"); + SYS("ip route add " IP6_DST "/128 dev veth_dst_fwd scope global"); + + close_netns(nstoken); + + /** setup in 'dst' namespace */ + nstoken = open_netns(NS_DST); + if (!ASSERT_OK_PTR(nstoken, "setns dst")) + goto fail; + + SYS("ip addr add " IP4_DST "/32 dev veth_dst"); + SYS("ip addr add " IP6_DST "/128 dev veth_dst nodad"); + SYS("ip link set dev veth_dst up"); + + SYS("ip route add " IP4_SRC "/32 dev veth_dst scope global"); + SYS("ip route add " IP4_NET "/16 dev veth_dst scope global"); + SYS("ip route add " IP6_SRC "/128 dev veth_dst scope global"); + + SYS("ip neigh add " IP4_SRC " dev veth_dst lladdr " MAC_DST_FWD); + SYS("ip neigh add " IP6_SRC " dev veth_dst lladdr " MAC_DST_FWD); + + close_netns(nstoken); + + return 0; +fail: + if (nstoken) + close_netns(nstoken); + return -1; +} + +static int netns_load_bpf(void) +{ + SYS("tc qdisc add dev veth_src_fwd clsact"); + SYS("tc filter add dev veth_src_fwd ingress bpf da object-pinned " + SRC_PROG_PIN_FILE); + SYS("tc filter add dev veth_src_fwd egress bpf da object-pinned " + CHK_PROG_PIN_FILE); + + SYS("tc qdisc add dev veth_dst_fwd clsact"); + SYS("tc filter add dev veth_dst_fwd ingress bpf da object-pinned " + DST_PROG_PIN_FILE); + SYS("tc filter add dev veth_dst_fwd egress bpf da object-pinned " + CHK_PROG_PIN_FILE); + + return 0; +fail: + return -1; +} + +static void test_tcp(int family, const char *addr, __u16 port) +{ + int listen_fd = -1, accept_fd = -1, client_fd = -1; + char buf[] = "testing testing"; + int n; + struct nstoken *nstoken; + + nstoken = open_netns(NS_DST); + if (!ASSERT_OK_PTR(nstoken, "setns dst")) + return; + + listen_fd = start_server(family, SOCK_STREAM, addr, port, 0); + if (!ASSERT_GE(listen_fd, 0, "listen")) + goto done; + + close_netns(nstoken); + nstoken = open_netns(NS_SRC); + if (!ASSERT_OK_PTR(nstoken, "setns src")) + goto done; + + client_fd = connect_to_fd(listen_fd, TIMEOUT_MILLIS); + if (!ASSERT_GE(client_fd, 0, "connect_to_fd")) + goto done; + + accept_fd = accept(listen_fd, NULL, NULL); + if (!ASSERT_GE(accept_fd, 0, "accept")) + goto done; + + if (!ASSERT_OK(settimeo(accept_fd, TIMEOUT_MILLIS), "settimeo")) + goto done; + + n = write(client_fd, buf, sizeof(buf)); + if (!ASSERT_EQ(n, sizeof(buf), "send to server")) + goto done; + + n = read(accept_fd, buf, sizeof(buf)); + ASSERT_EQ(n, sizeof(buf), "recv from server"); + +done: + if (nstoken) + close_netns(nstoken); + if (listen_fd >= 0) + close(listen_fd); + if (accept_fd >= 0) + close(accept_fd); + if (client_fd >= 0) + close(client_fd); +} + +static int test_ping(int family, const char *addr) +{ + const char *ping = family == AF_INET6 ? "ping6" : "ping"; + + SYS("ip netns exec " NS_SRC " %s " PING_ARGS " %s > /dev/null", ping, addr); + return 0; +fail: + return -1; +} + +static void test_connectivity(void) +{ + test_tcp(AF_INET, IP4_DST, IP4_PORT); + test_ping(AF_INET, IP4_DST); + test_tcp(AF_INET6, IP6_DST, IP6_PORT); + test_ping(AF_INET6, IP6_DST); +} + +static int set_forwarding(bool enable) +{ + int err; + + err = write_file("/proc/sys/net/ipv4/ip_forward", enable ? "1" : "0"); + if (!ASSERT_OK(err, "set ipv4.ip_forward=0")) + return err; + + err = write_file("/proc/sys/net/ipv6/conf/all/forwarding", enable ? "1" : "0"); + if (!ASSERT_OK(err, "set ipv6.forwarding=0")) + return err; + + return 0; +} + +static void test_tc_redirect_neigh_fib(struct netns_setup_result *setup_result) +{ + struct nstoken *nstoken = NULL; + struct test_tc_neigh_fib *skel = NULL; + int err; + + nstoken = open_netns(NS_FWD); + if (!ASSERT_OK_PTR(nstoken, "setns fwd")) + return; + + skel = test_tc_neigh_fib__open(); + if (!ASSERT_OK_PTR(skel, "test_tc_neigh_fib__open")) + goto done; + + if (!ASSERT_OK(test_tc_neigh_fib__load(skel), "test_tc_neigh_fib__load")) + goto done; + + err = bpf_program__pin(skel->progs.tc_src, SRC_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " SRC_PROG_PIN_FILE)) + goto done; + + err = bpf_program__pin(skel->progs.tc_chk, CHK_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " CHK_PROG_PIN_FILE)) + goto done; + + err = bpf_program__pin(skel->progs.tc_dst, DST_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " DST_PROG_PIN_FILE)) + goto done; + + if (netns_load_bpf()) + goto done; + + /* bpf_fib_lookup() checks if forwarding is enabled */ + if (!ASSERT_OK(set_forwarding(true), "enable forwarding")) + goto done; + + test_connectivity(); + +done: + if (skel) + test_tc_neigh_fib__destroy(skel); + close_netns(nstoken); +} + +static void test_tc_redirect_neigh(struct netns_setup_result *setup_result) +{ + struct nstoken *nstoken = NULL; + struct test_tc_neigh *skel = NULL; + int err; + + nstoken = open_netns(NS_FWD); + if (!ASSERT_OK_PTR(nstoken, "setns fwd")) + return; + + skel = test_tc_neigh__open(); + if (!ASSERT_OK_PTR(skel, "test_tc_neigh__open")) + goto done; + + skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd; + skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd; + + err = test_tc_neigh__load(skel); + if (!ASSERT_OK(err, "test_tc_neigh__load")) + goto done; + + err = bpf_program__pin(skel->progs.tc_src, SRC_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " SRC_PROG_PIN_FILE)) + goto done; + + err = bpf_program__pin(skel->progs.tc_chk, CHK_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " CHK_PROG_PIN_FILE)) + goto done; + + err = bpf_program__pin(skel->progs.tc_dst, DST_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " DST_PROG_PIN_FILE)) + goto done; + + if (netns_load_bpf()) + goto done; + + if (!ASSERT_OK(set_forwarding(false), "disable forwarding")) + goto done; + + test_connectivity(); + +done: + if (skel) + test_tc_neigh__destroy(skel); + close_netns(nstoken); +} + +static void test_tc_redirect_peer(struct netns_setup_result *setup_result) +{ + struct nstoken *nstoken; + struct test_tc_peer *skel; + int err; + + nstoken = open_netns(NS_FWD); + if (!ASSERT_OK_PTR(nstoken, "setns fwd")) + return; + + skel = test_tc_peer__open(); + if (!ASSERT_OK_PTR(skel, "test_tc_peer__open")) + goto done; + + skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd; + skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd; + + err = test_tc_peer__load(skel); + if (!ASSERT_OK(err, "test_tc_peer__load")) + goto done; + + err = bpf_program__pin(skel->progs.tc_src, SRC_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " SRC_PROG_PIN_FILE)) + goto done; + + err = bpf_program__pin(skel->progs.tc_chk, CHK_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " CHK_PROG_PIN_FILE)) + goto done; + + err = bpf_program__pin(skel->progs.tc_dst, DST_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " DST_PROG_PIN_FILE)) + goto done; + + if (netns_load_bpf()) + goto done; + + if (!ASSERT_OK(set_forwarding(false), "disable forwarding")) + goto done; + + test_connectivity(); + +done: + if (skel) + test_tc_peer__destroy(skel); + close_netns(nstoken); +} + +static int tun_open(char *name) +{ + struct ifreq ifr; + int fd, err; + + fd = open("/dev/net/tun", O_RDWR); + if (!ASSERT_GE(fd, 0, "open /dev/net/tun")) + return -1; + + memset(&ifr, 0, sizeof(ifr)); + + ifr.ifr_flags = IFF_TUN | IFF_NO_PI; + if (*name) + strncpy(ifr.ifr_name, name, IFNAMSIZ); + + err = ioctl(fd, TUNSETIFF, &ifr); + if (!ASSERT_OK(err, "ioctl TUNSETIFF")) + goto fail; + + SYS("ip link set dev %s up", name); + + return fd; +fail: + close(fd); + return -1; +} + +#define MAX(a, b) ((a) > (b) ? (a) : (b)) +enum { + SRC_TO_TARGET = 0, + TARGET_TO_SRC = 1, +}; + +static int tun_relay_loop(int src_fd, int target_fd) +{ + fd_set rfds, wfds; + + FD_ZERO(&rfds); + FD_ZERO(&wfds); + + for (;;) { + char buf[1500]; + int direction, nread, nwrite; + + FD_SET(src_fd, &rfds); + FD_SET(target_fd, &rfds); + + if (select(1 + MAX(src_fd, target_fd), &rfds, NULL, NULL, NULL) < 0) { + log_err("select failed"); + return 1; + } + + direction = FD_ISSET(src_fd, &rfds) ? SRC_TO_TARGET : TARGET_TO_SRC; + + nread = read(direction == SRC_TO_TARGET ? src_fd : target_fd, buf, sizeof(buf)); + if (nread < 0) { + log_err("read failed"); + return 1; + } + + nwrite = write(direction == SRC_TO_TARGET ? target_fd : src_fd, buf, nread); + if (nwrite != nread) { + log_err("write failed"); + return 1; + } + } +} + +static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result) +{ + struct test_tc_peer *skel = NULL; + struct nstoken *nstoken = NULL; + int err; + int tunnel_pid = -1; + int src_fd, target_fd; + int ifindex; + + /* Start a L3 TUN/TAP tunnel between the src and dst namespaces. + * This test is using TUN/TAP instead of e.g. IPIP or GRE tunnel as those + * expose the L2 headers encapsulating the IP packet to BPF and hence + * don't have skb in suitable state for this test. Alternative to TUN/TAP + * would be e.g. Wireguard which would appear as a pure L3 device to BPF, + * but that requires much more complicated setup. + */ + nstoken = open_netns(NS_SRC); + if (!ASSERT_OK_PTR(nstoken, "setns " NS_SRC)) + return; + + src_fd = tun_open("tun_src"); + if (!ASSERT_GE(src_fd, 0, "tun_open tun_src")) + goto fail; + + close_netns(nstoken); + + nstoken = open_netns(NS_FWD); + if (!ASSERT_OK_PTR(nstoken, "setns " NS_FWD)) + goto fail; + + target_fd = tun_open("tun_fwd"); + if (!ASSERT_GE(target_fd, 0, "tun_open tun_fwd")) + goto fail; + + tunnel_pid = fork(); + if (!ASSERT_GE(tunnel_pid, 0, "fork tun_relay_loop")) + goto fail; + + if (tunnel_pid == 0) + exit(tun_relay_loop(src_fd, target_fd)); + + skel = test_tc_peer__open(); + if (!ASSERT_OK_PTR(skel, "test_tc_peer__open")) + goto fail; + + ifindex = get_ifindex("tun_fwd"); + if (!ASSERT_GE(ifindex, 0, "get_ifindex tun_fwd")) + goto fail; + + skel->rodata->IFINDEX_SRC = ifindex; + skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd; + + err = test_tc_peer__load(skel); + if (!ASSERT_OK(err, "test_tc_peer__load")) + goto fail; + + err = bpf_program__pin(skel->progs.tc_src_l3, SRC_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " SRC_PROG_PIN_FILE)) + goto fail; + + err = bpf_program__pin(skel->progs.tc_dst_l3, DST_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " DST_PROG_PIN_FILE)) + goto fail; + + err = bpf_program__pin(skel->progs.tc_chk, CHK_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " CHK_PROG_PIN_FILE)) + goto fail; + + /* Load "tc_src_l3" to the tun_fwd interface to redirect packets + * towards dst, and "tc_dst" to redirect packets + * and "tc_chk" on veth_dst_fwd to drop non-redirected packets. + */ + SYS("tc qdisc add dev tun_fwd clsact"); + SYS("tc filter add dev tun_fwd ingress bpf da object-pinned " + SRC_PROG_PIN_FILE); + + SYS("tc qdisc add dev veth_dst_fwd clsact"); + SYS("tc filter add dev veth_dst_fwd ingress bpf da object-pinned " + DST_PROG_PIN_FILE); + SYS("tc filter add dev veth_dst_fwd egress bpf da object-pinned " + CHK_PROG_PIN_FILE); + + /* Setup route and neigh tables */ + SYS("ip -netns " NS_SRC " addr add dev tun_src " IP4_TUN_SRC "/24"); + SYS("ip -netns " NS_FWD " addr add dev tun_fwd " IP4_TUN_FWD "/24"); + + SYS("ip -netns " NS_SRC " addr add dev tun_src " IP6_TUN_SRC "/64 nodad"); + SYS("ip -netns " NS_FWD " addr add dev tun_fwd " IP6_TUN_FWD "/64 nodad"); + + SYS("ip -netns " NS_SRC " route del " IP4_DST "/32 dev veth_src scope global"); + SYS("ip -netns " NS_SRC " route add " IP4_DST "/32 via " IP4_TUN_FWD + " dev tun_src scope global"); + SYS("ip -netns " NS_DST " route add " IP4_TUN_SRC "/32 dev veth_dst scope global"); + SYS("ip -netns " NS_SRC " route del " IP6_DST "/128 dev veth_src scope global"); + SYS("ip -netns " NS_SRC " route add " IP6_DST "/128 via " IP6_TUN_FWD + " dev tun_src scope global"); + SYS("ip -netns " NS_DST " route add " IP6_TUN_SRC "/128 dev veth_dst scope global"); + + SYS("ip -netns " NS_DST " neigh add " IP4_TUN_SRC " dev veth_dst lladdr " MAC_DST_FWD); + SYS("ip -netns " NS_DST " neigh add " IP6_TUN_SRC " dev veth_dst lladdr " MAC_DST_FWD); + + if (!ASSERT_OK(set_forwarding(false), "disable forwarding")) + goto fail; + + test_connectivity(); + +fail: + if (tunnel_pid > 0) { + kill(tunnel_pid, SIGTERM); + waitpid(tunnel_pid, NULL, 0); + } + if (src_fd >= 0) + close(src_fd); + if (target_fd >= 0) + close(target_fd); + if (skel) + test_tc_peer__destroy(skel); + if (nstoken) + close_netns(nstoken); +} + +#define RUN_TEST(name) \ + ({ \ + struct netns_setup_result setup_result; \ + if (test__start_subtest(#name)) \ + if (ASSERT_OK(netns_setup_namespaces("add"), "setup namespaces")) { \ + if (ASSERT_OK(netns_setup_links_and_routes(&setup_result), \ + "setup links and routes")) \ + test_ ## name(&setup_result); \ + netns_setup_namespaces("delete"); \ + } \ + }) + +static void *test_tc_redirect_run_tests(void *arg) +{ + RUN_TEST(tc_redirect_peer); + RUN_TEST(tc_redirect_peer_l3); + RUN_TEST(tc_redirect_neigh); + RUN_TEST(tc_redirect_neigh_fib); + return NULL; +} + +void test_tc_redirect(void) +{ + pthread_t test_thread; + int err; + + /* Run the tests in their own thread to isolate the namespace changes + * so they do not affect the environment of other tests. + * (specifically needed because of unshare(CLONE_NEWNS) in open_netns()) + */ + err = pthread_create(&test_thread, NULL, &test_tc_redirect_run_tests, NULL); + if (ASSERT_OK(err, "pthread_create")) + ASSERT_OK(pthread_join(test_thread, NULL), "pthread_join"); +} diff --git a/tools/testing/selftests/bpf/progs/test_tc_neigh.c b/tools/testing/selftests/bpf/progs/test_tc_neigh.c index b985ac4e7a81..0c93d326a663 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_neigh.c +++ b/tools/testing/selftests/bpf/progs/test_tc_neigh.c @@ -33,17 +33,8 @@ a.s6_addr32[3] == b.s6_addr32[3]) #endif -enum { - dev_src, - dev_dst, -}; - -struct bpf_map_def SEC("maps") ifindex_map = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(int), - .max_entries = 2, -}; +volatile const __u32 IFINDEX_SRC; +volatile const __u32 IFINDEX_DST; static __always_inline bool is_remote_ep_v4(struct __sk_buff *skb, __be32 addr) @@ -79,14 +70,8 @@ static __always_inline bool is_remote_ep_v6(struct __sk_buff *skb, return v6_equal(ip6h->daddr, addr); } -static __always_inline int get_dev_ifindex(int which) -{ - int *ifindex = bpf_map_lookup_elem(&ifindex_map, &which); - - return ifindex ? *ifindex : 0; -} - -SEC("chk_egress") int tc_chk(struct __sk_buff *skb) +SEC("classifier/chk_egress") +int tc_chk(struct __sk_buff *skb) { void *data_end = ctx_ptr(skb->data_end); void *data = ctx_ptr(skb->data); @@ -98,7 +83,8 @@ SEC("chk_egress") int tc_chk(struct __sk_buff *skb) return !raw[0] && !raw[1] && !raw[2] ? TC_ACT_SHOT : TC_ACT_OK; } -SEC("dst_ingress") int tc_dst(struct __sk_buff *skb) +SEC("classifier/dst_ingress") +int tc_dst(struct __sk_buff *skb) { __u8 zero[ETH_ALEN * 2]; bool redirect = false; @@ -119,10 +105,11 @@ SEC("dst_ingress") int tc_dst(struct __sk_buff *skb) if (bpf_skb_store_bytes(skb, 0, &zero, sizeof(zero), 0) < 0) return TC_ACT_SHOT; - return bpf_redirect_neigh(get_dev_ifindex(dev_src), NULL, 0, 0); + return bpf_redirect_neigh(IFINDEX_SRC, NULL, 0, 0); } -SEC("src_ingress") int tc_src(struct __sk_buff *skb) +SEC("classifier/src_ingress") +int tc_src(struct __sk_buff *skb) { __u8 zero[ETH_ALEN * 2]; bool redirect = false; @@ -143,7 +130,7 @@ SEC("src_ingress") int tc_src(struct __sk_buff *skb) if (bpf_skb_store_bytes(skb, 0, &zero, sizeof(zero), 0) < 0) return TC_ACT_SHOT; - return bpf_redirect_neigh(get_dev_ifindex(dev_dst), NULL, 0, 0); + return bpf_redirect_neigh(IFINDEX_DST, NULL, 0, 0); } char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c b/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c index d82ed3457030..f7ab69cf018e 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c +++ b/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c @@ -75,7 +75,8 @@ static __always_inline int fill_fib_params_v6(struct __sk_buff *skb, return 0; } -SEC("chk_egress") int tc_chk(struct __sk_buff *skb) +SEC("classifier/chk_egress") +int tc_chk(struct __sk_buff *skb) { void *data_end = ctx_ptr(skb->data_end); void *data = ctx_ptr(skb->data); @@ -142,12 +143,14 @@ static __always_inline int tc_redir(struct __sk_buff *skb) /* these are identical, but keep them separate for compatibility with the * section names expected by test_tc_redirect.sh */ -SEC("dst_ingress") int tc_dst(struct __sk_buff *skb) +SEC("classifier/dst_ingress") +int tc_dst(struct __sk_buff *skb) { return tc_redir(skb); } -SEC("src_ingress") int tc_src(struct __sk_buff *skb) +SEC("classifier/src_ingress") +int tc_src(struct __sk_buff *skb) { return tc_redir(skb); } diff --git a/tools/testing/selftests/bpf/progs/test_tc_peer.c b/tools/testing/selftests/bpf/progs/test_tc_peer.c index fc84a7685aa2..fe818cd5f010 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_peer.c +++ b/tools/testing/selftests/bpf/progs/test_tc_peer.c @@ -5,41 +5,59 @@ #include <linux/bpf.h> #include <linux/stddef.h> #include <linux/pkt_cls.h> +#include <linux/if_ether.h> +#include <linux/ip.h> #include <bpf/bpf_helpers.h> -enum { - dev_src, - dev_dst, -}; +volatile const __u32 IFINDEX_SRC; +volatile const __u32 IFINDEX_DST; -struct bpf_map_def SEC("maps") ifindex_map = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(int), - .max_entries = 2, -}; +static const __u8 src_mac[] = {0x00, 0x11, 0x22, 0x33, 0x44, 0x55}; +static const __u8 dst_mac[] = {0x00, 0x22, 0x33, 0x44, 0x55, 0x66}; -static __always_inline int get_dev_ifindex(int which) +SEC("classifier/chk_egress") +int tc_chk(struct __sk_buff *skb) { - int *ifindex = bpf_map_lookup_elem(&ifindex_map, &which); + return TC_ACT_SHOT; +} - return ifindex ? *ifindex : 0; +SEC("classifier/dst_ingress") +int tc_dst(struct __sk_buff *skb) +{ + return bpf_redirect_peer(IFINDEX_SRC, 0); } -SEC("chk_egress") int tc_chk(struct __sk_buff *skb) +SEC("classifier/src_ingress") +int tc_src(struct __sk_buff *skb) { - return TC_ACT_SHOT; + return bpf_redirect_peer(IFINDEX_DST, 0); } -SEC("dst_ingress") int tc_dst(struct __sk_buff *skb) +SEC("classifier/dst_ingress_l3") +int tc_dst_l3(struct __sk_buff *skb) { - return bpf_redirect_peer(get_dev_ifindex(dev_src), 0); + return bpf_redirect(IFINDEX_SRC, 0); } -SEC("src_ingress") int tc_src(struct __sk_buff *skb) +SEC("classifier/src_ingress_l3") +int tc_src_l3(struct __sk_buff *skb) { - return bpf_redirect_peer(get_dev_ifindex(dev_dst), 0); + __u16 proto = skb->protocol; + + if (bpf_skb_change_head(skb, ETH_HLEN, 0) != 0) + return TC_ACT_SHOT; + + if (bpf_skb_store_bytes(skb, 0, &src_mac, ETH_ALEN, 0) != 0) + return TC_ACT_SHOT; + + if (bpf_skb_store_bytes(skb, ETH_ALEN, &dst_mac, ETH_ALEN, 0) != 0) + return TC_ACT_SHOT; + + if (bpf_skb_store_bytes(skb, ETH_ALEN + ETH_ALEN, &proto, sizeof(__u16), 0) != 0) + return TC_ACT_SHOT; + + return bpf_redirect_peer(IFINDEX_DST, 0); } char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_tc_redirect.sh b/tools/testing/selftests/bpf/test_tc_redirect.sh deleted file mode 100755 index 8868aa1ca902..000000000000 --- a/tools/testing/selftests/bpf/test_tc_redirect.sh +++ /dev/null @@ -1,216 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 -# -# This test sets up 3 netns (src <-> fwd <-> dst). There is no direct veth link -# between src and dst. The netns fwd has veth links to each src and dst. The -# client is in src and server in dst. The test installs a TC BPF program to each -# host facing veth in fwd which calls into i) bpf_redirect_neigh() to perform the -# neigh addr population and redirect or ii) bpf_redirect_peer() for namespace -# switch from ingress side; it also installs a checker prog on the egress side -# to drop unexpected traffic. - -if [[ $EUID -ne 0 ]]; then - echo "This script must be run as root" - echo "FAIL" - exit 1 -fi - -# check that needed tools are present -command -v nc >/dev/null 2>&1 || \ - { echo >&2 "nc is not available"; exit 1; } -command -v dd >/dev/null 2>&1 || \ - { echo >&2 "dd is not available"; exit 1; } -command -v timeout >/dev/null 2>&1 || \ - { echo >&2 "timeout is not available"; exit 1; } -command -v ping >/dev/null 2>&1 || \ - { echo >&2 "ping is not available"; exit 1; } -if command -v ping6 >/dev/null 2>&1; then PING6=ping6; else PING6=ping; fi -command -v perl >/dev/null 2>&1 || \ - { echo >&2 "perl is not available"; exit 1; } -command -v jq >/dev/null 2>&1 || \ - { echo >&2 "jq is not available"; exit 1; } -command -v bpftool >/dev/null 2>&1 || \ - { echo >&2 "bpftool is not available"; exit 1; } - -readonly GREEN='\033[0;92m' -readonly RED='\033[0;31m' -readonly NC='\033[0m' # No Color - -readonly PING_ARG="-c 3 -w 10 -q" - -readonly TIMEOUT=10 - -readonly NS_SRC="ns-src-$(mktemp -u XXXXXX)" -readonly NS_FWD="ns-fwd-$(mktemp -u XXXXXX)" -readonly NS_DST="ns-dst-$(mktemp -u XXXXXX)" - -readonly IP4_SRC="172.16.1.100" -readonly IP4_DST="172.16.2.100" - -readonly IP6_SRC="::1:dead:beef:cafe" -readonly IP6_DST="::2:dead:beef:cafe" - -readonly IP4_SLL="169.254.0.1" -readonly IP4_DLL="169.254.0.2" -readonly IP4_NET="169.254.0.0" - -netns_cleanup() -{ - ip netns del ${NS_SRC} - ip netns del ${NS_FWD} - ip netns del ${NS_DST} -} - -netns_setup() -{ - ip netns add "${NS_SRC}" - ip netns add "${NS_FWD}" - ip netns add "${NS_DST}" - - ip link add veth_src type veth peer name veth_src_fwd - ip link add veth_dst type veth peer name veth_dst_fwd - - ip link set veth_src netns ${NS_SRC} - ip link set veth_src_fwd netns ${NS_FWD} - - ip link set veth_dst netns ${NS_DST} - ip link set veth_dst_fwd netns ${NS_FWD} - - ip -netns ${NS_SRC} addr add ${IP4_SRC}/32 dev veth_src - ip -netns ${NS_DST} addr add ${IP4_DST}/32 dev veth_dst - - # The fwd netns automatically get a v6 LL address / routes, but also - # needs v4 one in order to start ARP probing. IP4_NET route is added - # to the endpoints so that the ARP processing will reply. - - ip -netns ${NS_FWD} addr add ${IP4_SLL}/32 dev veth_src_fwd - ip -netns ${NS_FWD} addr add ${IP4_DLL}/32 dev veth_dst_fwd - - ip -netns ${NS_SRC} addr add ${IP6_SRC}/128 dev veth_src nodad - ip -netns ${NS_DST} addr add ${IP6_DST}/128 dev veth_dst nodad - - ip -netns ${NS_SRC} link set dev veth_src up - ip -netns ${NS_FWD} link set dev veth_src_fwd up - - ip -netns ${NS_DST} link set dev veth_dst up - ip -netns ${NS_FWD} link set dev veth_dst_fwd up - - ip -netns ${NS_SRC} route add ${IP4_DST}/32 dev veth_src scope global - ip -netns ${NS_SRC} route add ${IP4_NET}/16 dev veth_src scope global - ip -netns ${NS_FWD} route add ${IP4_SRC}/32 dev veth_src_fwd scope global - - ip -netns ${NS_SRC} route add ${IP6_DST}/128 dev veth_src scope global - ip -netns ${NS_FWD} route add ${IP6_SRC}/128 dev veth_src_fwd scope global - - ip -netns ${NS_DST} route add ${IP4_SRC}/32 dev veth_dst scope global - ip -netns ${NS_DST} route add ${IP4_NET}/16 dev veth_dst scope global - ip -netns ${NS_FWD} route add ${IP4_DST}/32 dev veth_dst_fwd scope global - - ip -netns ${NS_DST} route add ${IP6_SRC}/128 dev veth_dst scope global - ip -netns ${NS_FWD} route add ${IP6_DST}/128 dev veth_dst_fwd scope global - - fmac_src=$(ip netns exec ${NS_FWD} cat /sys/class/net/veth_src_fwd/address) - fmac_dst=$(ip netns exec ${NS_FWD} cat /sys/class/net/veth_dst_fwd/address) - - ip -netns ${NS_SRC} neigh add ${IP4_DST} dev veth_src lladdr $fmac_src - ip -netns ${NS_DST} neigh add ${IP4_SRC} dev veth_dst lladdr $fmac_dst - - ip -netns ${NS_SRC} neigh add ${IP6_DST} dev veth_src lladdr $fmac_src - ip -netns ${NS_DST} neigh add ${IP6_SRC} dev veth_dst lladdr $fmac_dst -} - -netns_test_connectivity() -{ - set +e - - ip netns exec ${NS_DST} bash -c "nc -4 -l -p 9004 &" - ip netns exec ${NS_DST} bash -c "nc -6 -l -p 9006 &" - - TEST="TCPv4 connectivity test" - ip netns exec ${NS_SRC} bash -c "timeout ${TIMEOUT} dd if=/dev/zero bs=1000 count=100 > /dev/tcp/${IP4_DST}/9004" - if [ $? -ne 0 ]; then - echo -e "${TEST}: ${RED}FAIL${NC}" - exit 1 - fi - echo -e "${TEST}: ${GREEN}PASS${NC}" - - TEST="TCPv6 connectivity test" - ip netns exec ${NS_SRC} bash -c "timeout ${TIMEOUT} dd if=/dev/zero bs=1000 count=100 > /dev/tcp/${IP6_DST}/9006" - if [ $? -ne 0 ]; then - echo -e "${TEST}: ${RED}FAIL${NC}" - exit 1 - fi - echo -e "${TEST}: ${GREEN}PASS${NC}" - - TEST="ICMPv4 connectivity test" - ip netns exec ${NS_SRC} ping $PING_ARG ${IP4_DST} - if [ $? -ne 0 ]; then - echo -e "${TEST}: ${RED}FAIL${NC}" - exit 1 - fi - echo -e "${TEST}: ${GREEN}PASS${NC}" - - TEST="ICMPv6 connectivity test" - ip netns exec ${NS_SRC} $PING6 $PING_ARG ${IP6_DST} - if [ $? -ne 0 ]; then - echo -e "${TEST}: ${RED}FAIL${NC}" - exit 1 - fi - echo -e "${TEST}: ${GREEN}PASS${NC}" - - set -e -} - -hex_mem_str() -{ - perl -e 'print join(" ", unpack("(H2)8", pack("L", @ARGV)))' $1 -} - -netns_setup_bpf() -{ - local obj=$1 - local use_forwarding=${2:-0} - - ip netns exec ${NS_FWD} tc qdisc add dev veth_src_fwd clsact - ip netns exec ${NS_FWD} tc filter add dev veth_src_fwd ingress bpf da obj $obj sec src_ingress - ip netns exec ${NS_FWD} tc filter add dev veth_src_fwd egress bpf da obj $obj sec chk_egress - - ip netns exec ${NS_FWD} tc qdisc add dev veth_dst_fwd clsact - ip netns exec ${NS_FWD} tc filter add dev veth_dst_fwd ingress bpf da obj $obj sec dst_ingress - ip netns exec ${NS_FWD} tc filter add dev veth_dst_fwd egress bpf da obj $obj sec chk_egress - - if [ "$use_forwarding" -eq "1" ]; then - # bpf_fib_lookup() checks if forwarding is enabled - ip netns exec ${NS_FWD} sysctl -w net.ipv4.ip_forward=1 - ip netns exec ${NS_FWD} sysctl -w net.ipv6.conf.veth_dst_fwd.forwarding=1 - ip netns exec ${NS_FWD} sysctl -w net.ipv6.conf.veth_src_fwd.forwarding=1 - return 0 - fi - - veth_src=$(ip netns exec ${NS_FWD} cat /sys/class/net/veth_src_fwd/ifindex) - veth_dst=$(ip netns exec ${NS_FWD} cat /sys/class/net/veth_dst_fwd/ifindex) - - progs=$(ip netns exec ${NS_FWD} bpftool net --json | jq -r '.[] | .tc | map(.id) | .[]') - for prog in $progs; do - map=$(bpftool prog show id $prog --json | jq -r '.map_ids | .? | .[]') - if [ ! -z "$map" ]; then - bpftool map update id $map key hex $(hex_mem_str 0) value hex $(hex_mem_str $veth_src) - bpftool map update id $map key hex $(hex_mem_str 1) value hex $(hex_mem_str $veth_dst) - fi - done -} - -trap netns_cleanup EXIT -set -e - -netns_setup -netns_setup_bpf test_tc_neigh.o -netns_test_connectivity -netns_cleanup -netns_setup -netns_setup_bpf test_tc_neigh_fib.o 1 -netns_test_connectivity -netns_cleanup -netns_setup -netns_setup_bpf test_tc_peer.o -netns_test_connectivity diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 1512092e1e68..3a9e332c5e36 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -1147,7 +1147,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv, } } - if (test->insn_processed) { + if (!unpriv && test->insn_processed) { uint32_t insn_processed; char *proc; diff --git a/tools/testing/selftests/bpf/verifier/and.c b/tools/testing/selftests/bpf/verifier/and.c index ca8fdb1b3f01..7d7ebee5cc7a 100644 --- a/tools/testing/selftests/bpf/verifier/and.c +++ b/tools/testing/selftests/bpf/verifier/and.c @@ -61,6 +61,8 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R1 !read_ok", + .result_unpriv = REJECT, .result = ACCEPT, .retval = 0 }, diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c index 8a1caf46ffbc..e061e8799ce2 100644 --- a/tools/testing/selftests/bpf/verifier/bounds.c +++ b/tools/testing/selftests/bpf/verifier/bounds.c @@ -508,6 +508,8 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, -1), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 invalid mem access 'inv'", + .result_unpriv = REJECT, .result = ACCEPT }, { @@ -528,6 +530,8 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, -1), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 invalid mem access 'inv'", + .result_unpriv = REJECT, .result = ACCEPT }, { @@ -569,6 +573,8 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 min value is outside of the allowed memory range", + .result_unpriv = REJECT, .fixup_map_hash_8b = { 3 }, .result = ACCEPT, }, @@ -589,6 +595,8 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 min value is outside of the allowed memory range", + .result_unpriv = REJECT, .fixup_map_hash_8b = { 3 }, .result = ACCEPT, }, @@ -609,6 +617,8 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 min value is outside of the allowed memory range", + .result_unpriv = REJECT, .fixup_map_hash_8b = { 3 }, .result = ACCEPT, }, @@ -674,6 +684,8 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 min value is outside of the allowed memory range", + .result_unpriv = REJECT, .fixup_map_hash_8b = { 3 }, .result = ACCEPT, }, @@ -695,6 +707,8 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 min value is outside of the allowed memory range", + .result_unpriv = REJECT, .fixup_map_hash_8b = { 3 }, .result = ACCEPT, }, diff --git a/tools/testing/selftests/bpf/verifier/dead_code.c b/tools/testing/selftests/bpf/verifier/dead_code.c index 17fe33a75034..2c8935b3e65d 100644 --- a/tools/testing/selftests/bpf/verifier/dead_code.c +++ b/tools/testing/selftests/bpf/verifier/dead_code.c @@ -8,6 +8,8 @@ BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 10, -4), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R9 !read_ok", + .result_unpriv = REJECT, .result = ACCEPT, .retval = 7, }, diff --git a/tools/testing/selftests/bpf/verifier/jmp32.c b/tools/testing/selftests/bpf/verifier/jmp32.c index bd5cae4a7f73..1c857b2fbdf0 100644 --- a/tools/testing/selftests/bpf/verifier/jmp32.c +++ b/tools/testing/selftests/bpf/verifier/jmp32.c @@ -87,6 +87,8 @@ BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R9 !read_ok", + .result_unpriv = REJECT, .result = ACCEPT, }, { @@ -150,6 +152,8 @@ BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R9 !read_ok", + .result_unpriv = REJECT, .result = ACCEPT, }, { @@ -213,6 +217,8 @@ BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R9 !read_ok", + .result_unpriv = REJECT, .result = ACCEPT, }, { @@ -280,6 +286,8 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 invalid mem access 'inv'", + .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, }, @@ -348,6 +356,8 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 invalid mem access 'inv'", + .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, }, @@ -416,6 +426,8 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 invalid mem access 'inv'", + .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, }, @@ -484,6 +496,8 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 invalid mem access 'inv'", + .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, }, @@ -552,6 +566,8 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 invalid mem access 'inv'", + .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, }, @@ -620,6 +636,8 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 invalid mem access 'inv'", + .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, }, @@ -688,6 +706,8 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 invalid mem access 'inv'", + .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, }, @@ -756,6 +776,8 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R0 invalid mem access 'inv'", + .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, }, diff --git a/tools/testing/selftests/bpf/verifier/jset.c b/tools/testing/selftests/bpf/verifier/jset.c index 8dcd4e0383d5..11fc68da735e 100644 --- a/tools/testing/selftests/bpf/verifier/jset.c +++ b/tools/testing/selftests/bpf/verifier/jset.c @@ -82,8 +82,8 @@ BPF_EXIT_INSN(), }, .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, - .retval_unpriv = 1, - .result_unpriv = ACCEPT, + .errstr_unpriv = "R9 !read_ok", + .result_unpriv = REJECT, .retval = 1, .result = ACCEPT, }, @@ -141,7 +141,8 @@ BPF_EXIT_INSN(), }, .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, - .result_unpriv = ACCEPT, + .errstr_unpriv = "R9 !read_ok", + .result_unpriv = REJECT, .result = ACCEPT, }, { @@ -162,6 +163,7 @@ BPF_EXIT_INSN(), }, .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, - .result_unpriv = ACCEPT, + .errstr_unpriv = "R9 !read_ok", + .result_unpriv = REJECT, .result = ACCEPT, }, diff --git a/tools/testing/selftests/bpf/verifier/stack_ptr.c b/tools/testing/selftests/bpf/verifier/stack_ptr.c index 07eaa04412ae..8ab94d65f3d5 100644 --- a/tools/testing/selftests/bpf/verifier/stack_ptr.c +++ b/tools/testing/selftests/bpf/verifier/stack_ptr.c @@ -295,8 +295,6 @@ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), BPF_EXIT_INSN(), }, - .result_unpriv = REJECT, - .errstr_unpriv = "invalid write to stack R1 off=0 size=1", .result = ACCEPT, .retval = 42, }, diff --git a/tools/testing/selftests/bpf/verifier/unpriv.c b/tools/testing/selftests/bpf/verifier/unpriv.c index bd436df5cc32..111801aea5e3 100644 --- a/tools/testing/selftests/bpf/verifier/unpriv.c +++ b/tools/testing/selftests/bpf/verifier/unpriv.c @@ -420,6 +420,8 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R7 invalid mem access 'inv'", + .result_unpriv = REJECT, .result = ACCEPT, .retval = 0, }, diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c index e5913fd3b903..a3e593ddfafc 100644 --- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c +++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c @@ -120,7 +120,7 @@ .fixup_map_array_48b = { 1 }, .result = ACCEPT, .result_unpriv = REJECT, - .errstr_unpriv = "R2 tried to add from different maps, paths or scalars", + .errstr_unpriv = "R2 pointer comparison prohibited", .retval = 0, }, { @@ -159,7 +159,8 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), // fake-dead code; targeted from branch A to - // prevent dead code sanitization + // prevent dead code sanitization, rejected + // via branch B however BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), @@ -167,7 +168,7 @@ .fixup_map_array_48b = { 1 }, .result = ACCEPT, .result_unpriv = REJECT, - .errstr_unpriv = "R2 tried to add from different maps, paths or scalars", + .errstr_unpriv = "R0 invalid mem access 'inv'", .retval = 0, }, { @@ -300,8 +301,6 @@ }, .fixup_map_array_48b = { 3 }, .result = ACCEPT, - .result_unpriv = REJECT, - .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .retval = 1, }, { @@ -371,8 +370,6 @@ }, .fixup_map_array_48b = { 3 }, .result = ACCEPT, - .result_unpriv = REJECT, - .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .retval = 1, }, { @@ -472,8 +469,6 @@ }, .fixup_map_array_48b = { 3 }, .result = ACCEPT, - .result_unpriv = REJECT, - .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .retval = 1, }, { @@ -766,8 +761,6 @@ }, .fixup_map_array_48b = { 3 }, .result = ACCEPT, - .result_unpriv = REJECT, - .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .retval = 1, }, { diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index bd83158e0e0b..524c857a049c 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -41,5 +41,6 @@ /kvm_create_max_vcpus /kvm_page_table_test /memslot_modification_stress_test +/memslot_perf_test /set_memory_region_test /steal_time diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index e439d027939d..daaee1888b12 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -33,7 +33,7 @@ ifeq ($(ARCH),s390) UNAME_M := s390x endif -LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c +LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/rbtree.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c @@ -74,6 +74,7 @@ TEST_GEN_PROGS_x86_64 += hardware_disable_test TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus TEST_GEN_PROGS_x86_64 += kvm_page_table_test TEST_GEN_PROGS_x86_64 += memslot_modification_stress_test +TEST_GEN_PROGS_x86_64 += memslot_perf_test TEST_GEN_PROGS_x86_64 += set_memory_region_test TEST_GEN_PROGS_x86_64 += steal_time diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c index 5f7a229c3af1..b74704305835 100644 --- a/tools/testing/selftests/kvm/demand_paging_test.c +++ b/tools/testing/selftests/kvm/demand_paging_test.c @@ -9,6 +9,7 @@ #define _GNU_SOURCE /* for pipe2 */ +#include <inttypes.h> #include <stdio.h> #include <stdlib.h> #include <time.h> @@ -38,6 +39,7 @@ static int nr_vcpus = 1; static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; +static size_t demand_paging_size; static char *guest_data_prototype; static void *vcpu_worker(void *data) @@ -71,36 +73,51 @@ static void *vcpu_worker(void *data) return NULL; } -static int handle_uffd_page_request(int uffd, uint64_t addr) +static int handle_uffd_page_request(int uffd_mode, int uffd, uint64_t addr) { - pid_t tid; + pid_t tid = syscall(__NR_gettid); struct timespec start; struct timespec ts_diff; - struct uffdio_copy copy; int r; - tid = syscall(__NR_gettid); + clock_gettime(CLOCK_MONOTONIC, &start); - copy.src = (uint64_t)guest_data_prototype; - copy.dst = addr; - copy.len = perf_test_args.host_page_size; - copy.mode = 0; + if (uffd_mode == UFFDIO_REGISTER_MODE_MISSING) { + struct uffdio_copy copy; - clock_gettime(CLOCK_MONOTONIC, &start); + copy.src = (uint64_t)guest_data_prototype; + copy.dst = addr; + copy.len = demand_paging_size; + copy.mode = 0; - r = ioctl(uffd, UFFDIO_COPY, ©); - if (r == -1) { - pr_info("Failed Paged in 0x%lx from thread %d with errno: %d\n", - addr, tid, errno); - return r; + r = ioctl(uffd, UFFDIO_COPY, ©); + if (r == -1) { + pr_info("Failed UFFDIO_COPY in 0x%lx from thread %d with errno: %d\n", + addr, tid, errno); + return r; + } + } else if (uffd_mode == UFFDIO_REGISTER_MODE_MINOR) { + struct uffdio_continue cont = {0}; + + cont.range.start = addr; + cont.range.len = demand_paging_size; + + r = ioctl(uffd, UFFDIO_CONTINUE, &cont); + if (r == -1) { + pr_info("Failed UFFDIO_CONTINUE in 0x%lx from thread %d with errno: %d\n", + addr, tid, errno); + return r; + } + } else { + TEST_FAIL("Invalid uffd mode %d", uffd_mode); } ts_diff = timespec_elapsed(start); - PER_PAGE_DEBUG("UFFDIO_COPY %d \t%ld ns\n", tid, + PER_PAGE_DEBUG("UFFD page-in %d \t%ld ns\n", tid, timespec_to_ns(ts_diff)); PER_PAGE_DEBUG("Paged in %ld bytes at 0x%lx from thread %d\n", - perf_test_args.host_page_size, addr, tid); + demand_paging_size, addr, tid); return 0; } @@ -108,6 +125,7 @@ static int handle_uffd_page_request(int uffd, uint64_t addr) bool quit_uffd_thread; struct uffd_handler_args { + int uffd_mode; int uffd; int pipefd; useconds_t delay; @@ -169,7 +187,7 @@ static void *uffd_handler_thread_fn(void *arg) if (r == -1) { if (errno == EAGAIN) continue; - pr_info("Read of uffd gor errno %d", errno); + pr_info("Read of uffd got errno %d\n", errno); return NULL; } @@ -184,7 +202,7 @@ static void *uffd_handler_thread_fn(void *arg) if (delay) usleep(delay); addr = msg.arg.pagefault.address; - r = handle_uffd_page_request(uffd, addr); + r = handle_uffd_page_request(uffd_args->uffd_mode, uffd, addr); if (r < 0) return NULL; pages++; @@ -198,43 +216,53 @@ static void *uffd_handler_thread_fn(void *arg) return NULL; } -static int setup_demand_paging(struct kvm_vm *vm, - pthread_t *uffd_handler_thread, int pipefd, - useconds_t uffd_delay, - struct uffd_handler_args *uffd_args, - void *hva, uint64_t len) +static void setup_demand_paging(struct kvm_vm *vm, + pthread_t *uffd_handler_thread, int pipefd, + int uffd_mode, useconds_t uffd_delay, + struct uffd_handler_args *uffd_args, + void *hva, void *alias, uint64_t len) { + bool is_minor = (uffd_mode == UFFDIO_REGISTER_MODE_MINOR); int uffd; struct uffdio_api uffdio_api; struct uffdio_register uffdio_register; + uint64_t expected_ioctls = ((uint64_t) 1) << _UFFDIO_COPY; - uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); - if (uffd == -1) { - pr_info("uffd creation failed\n"); - return -1; + PER_PAGE_DEBUG("Userfaultfd %s mode, faults resolved with %s\n", + is_minor ? "MINOR" : "MISSING", + is_minor ? "UFFDIO_CONINUE" : "UFFDIO_COPY"); + + /* In order to get minor faults, prefault via the alias. */ + if (is_minor) { + size_t p; + + expected_ioctls = ((uint64_t) 1) << _UFFDIO_CONTINUE; + + TEST_ASSERT(alias != NULL, "Alias required for minor faults"); + for (p = 0; p < (len / demand_paging_size); ++p) { + memcpy(alias + (p * demand_paging_size), + guest_data_prototype, demand_paging_size); + } } + uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); + TEST_ASSERT(uffd >= 0, "uffd creation failed, errno: %d", errno); + uffdio_api.api = UFFD_API; uffdio_api.features = 0; - if (ioctl(uffd, UFFDIO_API, &uffdio_api) == -1) { - pr_info("ioctl uffdio_api failed\n"); - return -1; - } + TEST_ASSERT(ioctl(uffd, UFFDIO_API, &uffdio_api) != -1, + "ioctl UFFDIO_API failed: %" PRIu64, + (uint64_t)uffdio_api.api); uffdio_register.range.start = (uint64_t)hva; uffdio_register.range.len = len; - uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) == -1) { - pr_info("ioctl uffdio_register failed\n"); - return -1; - } - - if ((uffdio_register.ioctls & UFFD_API_RANGE_IOCTLS) != - UFFD_API_RANGE_IOCTLS) { - pr_info("unexpected userfaultfd ioctl set\n"); - return -1; - } + uffdio_register.mode = uffd_mode; + TEST_ASSERT(ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) != -1, + "ioctl UFFDIO_REGISTER failed"); + TEST_ASSERT((uffdio_register.ioctls & expected_ioctls) == + expected_ioctls, "missing userfaultfd ioctls"); + uffd_args->uffd_mode = uffd_mode; uffd_args->uffd = uffd; uffd_args->pipefd = pipefd; uffd_args->delay = uffd_delay; @@ -243,13 +271,12 @@ static int setup_demand_paging(struct kvm_vm *vm, PER_VCPU_DEBUG("Created uffd thread for HVA range [%p, %p)\n", hva, hva + len); - - return 0; } struct test_params { - bool use_uffd; + int uffd_mode; useconds_t uffd_delay; + enum vm_mem_backing_src_type src_type; bool partition_vcpu_memory_access; }; @@ -267,14 +294,16 @@ static void run_test(enum vm_guest_mode mode, void *arg) int r; vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, - VM_MEM_SRC_ANONYMOUS); + p->src_type); perf_test_args.wr_fract = 1; - guest_data_prototype = malloc(perf_test_args.host_page_size); + demand_paging_size = get_backing_src_pagesz(p->src_type); + + guest_data_prototype = malloc(demand_paging_size); TEST_ASSERT(guest_data_prototype, "Failed to allocate buffer for guest data pattern"); - memset(guest_data_prototype, 0xAB, perf_test_args.host_page_size); + memset(guest_data_prototype, 0xAB, demand_paging_size); vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads)); TEST_ASSERT(vcpu_threads, "Memory allocation failed"); @@ -282,7 +311,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size, p->partition_vcpu_memory_access); - if (p->use_uffd) { + if (p->uffd_mode) { uffd_handler_threads = malloc(nr_vcpus * sizeof(*uffd_handler_threads)); TEST_ASSERT(uffd_handler_threads, "Memory allocation failed"); @@ -296,6 +325,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { vm_paddr_t vcpu_gpa; void *vcpu_hva; + void *vcpu_alias; uint64_t vcpu_mem_size; @@ -310,8 +340,9 @@ static void run_test(enum vm_guest_mode mode, void *arg) PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n", vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_mem_size); - /* Cache the HVA pointer of the region */ + /* Cache the host addresses of the region */ vcpu_hva = addr_gpa2hva(vm, vcpu_gpa); + vcpu_alias = addr_gpa2alias(vm, vcpu_gpa); /* * Set up user fault fd to handle demand paging @@ -321,13 +352,11 @@ static void run_test(enum vm_guest_mode mode, void *arg) O_CLOEXEC | O_NONBLOCK); TEST_ASSERT(!r, "Failed to set up pipefd"); - r = setup_demand_paging(vm, - &uffd_handler_threads[vcpu_id], - pipefds[vcpu_id * 2], - p->uffd_delay, &uffd_args[vcpu_id], - vcpu_hva, vcpu_mem_size); - if (r < 0) - exit(-r); + setup_demand_paging(vm, &uffd_handler_threads[vcpu_id], + pipefds[vcpu_id * 2], p->uffd_mode, + p->uffd_delay, &uffd_args[vcpu_id], + vcpu_hva, vcpu_alias, + vcpu_mem_size); } } @@ -355,7 +384,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) pr_info("All vCPU threads joined\n"); - if (p->use_uffd) { + if (p->uffd_mode) { char c; /* Tell the user fault fd handler threads to quit */ @@ -377,7 +406,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) free(guest_data_prototype); free(vcpu_threads); - if (p->use_uffd) { + if (p->uffd_mode) { free(uffd_handler_threads); free(uffd_args); free(pipefds); @@ -387,17 +416,19 @@ static void run_test(enum vm_guest_mode mode, void *arg) static void help(char *name) { puts(""); - printf("usage: %s [-h] [-m mode] [-u] [-d uffd_delay_usec]\n" - " [-b memory] [-v vcpus] [-o]\n", name); + printf("usage: %s [-h] [-m vm_mode] [-u uffd_mode] [-d uffd_delay_usec]\n" + " [-b memory] [-t type] [-v vcpus] [-o]\n", name); guest_modes_help(); - printf(" -u: use User Fault FD to handle vCPU page\n" - " faults.\n"); + printf(" -u: use userfaultfd to handle vCPU page faults. Mode is a\n" + " UFFD registration mode: 'MISSING' or 'MINOR'.\n"); printf(" -d: add a delay in usec to the User Fault\n" " FD handler to simulate demand paging\n" " overheads. Ignored without -u.\n"); printf(" -b: specify the size of the memory region which should be\n" " demand paged by each vCPU. e.g. 10M or 3G.\n" " Default: 1G\n"); + printf(" -t: The type of backing memory to use. Default: anonymous\n"); + backing_src_help(); printf(" -v: specify the number of vCPUs to run.\n"); printf(" -o: Overlap guest memory accesses instead of partitioning\n" " them into a separate region of memory for each vCPU.\n"); @@ -409,19 +440,24 @@ int main(int argc, char *argv[]) { int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS); struct test_params p = { + .src_type = VM_MEM_SRC_ANONYMOUS, .partition_vcpu_memory_access = true, }; int opt; guest_modes_append_default(); - while ((opt = getopt(argc, argv, "hm:ud:b:v:o")) != -1) { + while ((opt = getopt(argc, argv, "hm:u:d:b:t:v:o")) != -1) { switch (opt) { case 'm': guest_modes_cmdline(optarg); break; case 'u': - p.use_uffd = true; + if (!strcmp("MISSING", optarg)) + p.uffd_mode = UFFDIO_REGISTER_MODE_MISSING; + else if (!strcmp("MINOR", optarg)) + p.uffd_mode = UFFDIO_REGISTER_MODE_MINOR; + TEST_ASSERT(p.uffd_mode, "UFFD mode must be 'MISSING' or 'MINOR'."); break; case 'd': p.uffd_delay = strtoul(optarg, NULL, 0); @@ -430,6 +466,9 @@ int main(int argc, char *argv[]) case 'b': guest_percpu_mem_size = parse_size(optarg); break; + case 't': + p.src_type = parse_backing_src_type(optarg); + break; case 'v': nr_vcpus = atoi(optarg); TEST_ASSERT(nr_vcpus > 0 && nr_vcpus <= max_vcpus, @@ -445,6 +484,11 @@ int main(int argc, char *argv[]) } } + if (p.uffd_mode == UFFDIO_REGISTER_MODE_MINOR && + !backing_src_is_shared(p.src_type)) { + TEST_FAIL("userfaultfd MINOR mode requires shared memory; pick a different -t"); + } + for_each_guest_mode(run_test, &p); return 0; diff --git a/tools/testing/selftests/kvm/hardware_disable_test.c b/tools/testing/selftests/kvm/hardware_disable_test.c index 5aadf84c91c0..4b8db3bce610 100644 --- a/tools/testing/selftests/kvm/hardware_disable_test.c +++ b/tools/testing/selftests/kvm/hardware_disable_test.c @@ -132,6 +132,36 @@ static void run_test(uint32_t run) TEST_ASSERT(false, "%s: [%d] child escaped the ninja\n", __func__, run); } +void wait_for_child_setup(pid_t pid) +{ + /* + * Wait for the child to post to the semaphore, but wake up periodically + * to check if the child exited prematurely. + */ + for (;;) { + const struct timespec wait_period = { .tv_sec = 1 }; + int status; + + if (!sem_timedwait(sem, &wait_period)) + return; + + /* Child is still running, keep waiting. */ + if (pid != waitpid(pid, &status, WNOHANG)) + continue; + + /* + * Child is no longer running, which is not expected. + * + * If it exited with a non-zero status, we explicitly forward + * the child's status in case it exited with KSFT_SKIP. + */ + if (WIFEXITED(status)) + exit(WEXITSTATUS(status)); + else + TEST_ASSERT(false, "Child exited unexpectedly"); + } +} + int main(int argc, char **argv) { uint32_t i; @@ -148,7 +178,7 @@ int main(int argc, char **argv) run_test(i); /* This function always exits */ pr_debug("%s: [%d] waiting semaphore\n", __func__, i); - sem_wait(sem); + wait_for_child_setup(pid); r = (rand() % DELAY_US_MAX) + 1; pr_debug("%s: [%d] waiting %dus\n", __func__, i, r); usleep(r); diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index a8f022794ce3..35739567189e 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -43,6 +43,7 @@ enum vm_guest_mode { VM_MODE_P40V48_4K, VM_MODE_P40V48_64K, VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */ + VM_MODE_P47V64_4K, NUM_VM_MODES, }; @@ -60,7 +61,7 @@ enum vm_guest_mode { #elif defined(__s390x__) -#define VM_MODE_DEFAULT VM_MODE_P52V48_4K +#define VM_MODE_DEFAULT VM_MODE_P47V64_4K #define MIN_PAGE_SHIFT 12U #define ptes_per_page(page_size) ((page_size) / 16) @@ -77,6 +78,7 @@ struct vm_guest_mode_params { }; extern const struct vm_guest_mode_params vm_guest_mode_params[]; +int open_kvm_dev_path_or_exit(void); int kvm_check_cap(long cap); int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap); int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id, @@ -146,6 +148,7 @@ void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa); void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva); vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva); +void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa); /* * Address Guest Virtual to Guest Physical @@ -283,10 +286,11 @@ struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_me uint32_t num_percpu_pages, void *guest_code, uint32_t vcpuids[]); -/* Like vm_create_default_with_vcpus, but accepts mode as a parameter */ +/* Like vm_create_default_with_vcpus, but accepts mode and slot0 memory as a parameter */ struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, - uint64_t extra_mem_pages, uint32_t num_percpu_pages, - void *guest_code, uint32_t vcpuids[]); + uint64_t slot0_mem_pages, uint64_t extra_mem_pages, + uint32_t num_percpu_pages, void *guest_code, + uint32_t vcpuids[]); /* * Adds a vCPU with reasonable defaults (e.g. a stack) @@ -302,7 +306,7 @@ bool vm_is_unrestricted_guest(struct kvm_vm *vm); unsigned int vm_get_page_size(struct kvm_vm *vm); unsigned int vm_get_page_shift(struct kvm_vm *vm); -unsigned int vm_get_max_gfn(struct kvm_vm *vm); +uint64_t vm_get_max_gfn(struct kvm_vm *vm); int vm_get_fd(struct kvm_vm *vm); unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size); diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index fade3130eb01..d79be15dd3d2 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -17,6 +17,7 @@ #include <errno.h> #include <unistd.h> #include <fcntl.h> +#include <sys/mman.h> #include "kselftest.h" static inline int _no_printf(const char *format, ...) { return 0; } @@ -84,6 +85,8 @@ enum vm_mem_backing_src_type { VM_MEM_SRC_ANONYMOUS_HUGETLB_1GB, VM_MEM_SRC_ANONYMOUS_HUGETLB_2GB, VM_MEM_SRC_ANONYMOUS_HUGETLB_16GB, + VM_MEM_SRC_SHMEM, + VM_MEM_SRC_SHARED_HUGETLB, NUM_SRC_TYPES, }; @@ -100,4 +103,13 @@ size_t get_backing_src_pagesz(uint32_t i); void backing_src_help(void); enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name); +/* + * Whether or not the given source type is shared memory (as opposed to + * anonymous). + */ +static inline bool backing_src_is_shared(enum vm_mem_backing_src_type t) +{ + return vm_mem_backing_src_alias(t)->flag & MAP_SHARED; +} + #endif /* SELFTEST_KVM_TEST_UTIL_H */ diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c index 1c4753fff19e..82171f17c1d7 100644 --- a/tools/testing/selftests/kvm/kvm_page_table_test.c +++ b/tools/testing/selftests/kvm/kvm_page_table_test.c @@ -268,7 +268,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg) /* Create a VM with enough guest pages */ guest_num_pages = test_mem_size / guest_page_size; - vm = vm_create_with_vcpus(mode, nr_vcpus, + vm = vm_create_with_vcpus(mode, nr_vcpus, DEFAULT_GUEST_PHY_PAGES, guest_num_pages, 0, guest_code, NULL); /* Align down GPA of the testing memslot */ diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index fc83f6c5902d..a2b732cf96ea 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -32,6 +32,34 @@ static void *align(void *x, size_t size) } /* + * Open KVM_DEV_PATH if available, otherwise exit the entire program. + * + * Input Args: + * flags - The flags to pass when opening KVM_DEV_PATH. + * + * Return: + * The opened file descriptor of /dev/kvm. + */ +static int _open_kvm_dev_path_or_exit(int flags) +{ + int fd; + + fd = open(KVM_DEV_PATH, flags); + if (fd < 0) { + print_skip("%s not available, is KVM loaded? (errno: %d)", + KVM_DEV_PATH, errno); + exit(KSFT_SKIP); + } + + return fd; +} + +int open_kvm_dev_path_or_exit(void) +{ + return _open_kvm_dev_path_or_exit(O_RDONLY); +} + +/* * Capability * * Input Args: @@ -52,12 +80,9 @@ int kvm_check_cap(long cap) int ret; int kvm_fd; - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); - + kvm_fd = open_kvm_dev_path_or_exit(); ret = ioctl(kvm_fd, KVM_CHECK_EXTENSION, cap); - TEST_ASSERT(ret != -1, "KVM_CHECK_EXTENSION IOCTL failed,\n" + TEST_ASSERT(ret >= 0, "KVM_CHECK_EXTENSION IOCTL failed,\n" " rc: %i errno: %i", ret, errno); close(kvm_fd); @@ -128,9 +153,7 @@ void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size) static void vm_open(struct kvm_vm *vm, int perm) { - vm->kvm_fd = open(KVM_DEV_PATH, perm); - if (vm->kvm_fd < 0) - exit(KSFT_SKIP); + vm->kvm_fd = _open_kvm_dev_path_or_exit(perm); if (!kvm_check_cap(KVM_CAP_IMMEDIATE_EXIT)) { print_skip("immediate_exit not available"); @@ -152,6 +175,7 @@ const char *vm_guest_mode_string(uint32_t i) [VM_MODE_P40V48_4K] = "PA-bits:40, VA-bits:48, 4K pages", [VM_MODE_P40V48_64K] = "PA-bits:40, VA-bits:48, 64K pages", [VM_MODE_PXXV48_4K] = "PA-bits:ANY, VA-bits:48, 4K pages", + [VM_MODE_P47V64_4K] = "PA-bits:47, VA-bits:64, 4K pages", }; _Static_assert(sizeof(strings)/sizeof(char *) == NUM_VM_MODES, "Missing new mode strings?"); @@ -169,6 +193,7 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = { { 40, 48, 0x1000, 12 }, { 40, 48, 0x10000, 16 }, { 0, 0, 0x1000, 12 }, + { 47, 64, 0x1000, 12 }, }; _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES, "Missing new mode params?"); @@ -203,7 +228,9 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) TEST_ASSERT(vm != NULL, "Insufficient Memory"); INIT_LIST_HEAD(&vm->vcpus); - INIT_LIST_HEAD(&vm->userspace_mem_regions); + vm->regions.gpa_tree = RB_ROOT; + vm->regions.hva_tree = RB_ROOT; + hash_init(vm->regions.slot_hash); vm->mode = mode; vm->type = 0; @@ -252,6 +279,9 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) TEST_FAIL("VM_MODE_PXXV48_4K not supported on non-x86 platforms"); #endif break; + case VM_MODE_P47V64_4K: + vm->pgtable_levels = 5; + break; default: TEST_FAIL("Unknown guest mode, mode: 0x%x", mode); } @@ -283,21 +313,50 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) return vm; } +/* + * VM Create with customized parameters + * + * Input Args: + * mode - VM Mode (e.g. VM_MODE_P52V48_4K) + * nr_vcpus - VCPU count + * slot0_mem_pages - Slot0 physical memory size + * extra_mem_pages - Non-slot0 physical memory total size + * num_percpu_pages - Per-cpu physical memory pages + * guest_code - Guest entry point + * vcpuids - VCPU IDs + * + * Output Args: None + * + * Return: + * Pointer to opaque structure that describes the created VM. + * + * Creates a VM with the mode specified by mode (e.g. VM_MODE_P52V48_4K), + * with customized slot0 memory size, at least 512 pages currently. + * extra_mem_pages is only used to calculate the maximum page table size, + * no real memory allocation for non-slot0 memory in this function. + */ struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, - uint64_t extra_mem_pages, uint32_t num_percpu_pages, - void *guest_code, uint32_t vcpuids[]) + uint64_t slot0_mem_pages, uint64_t extra_mem_pages, + uint32_t num_percpu_pages, void *guest_code, + uint32_t vcpuids[]) { + uint64_t vcpu_pages, extra_pg_pages, pages; + struct kvm_vm *vm; + int i; + + /* Force slot0 memory size not small than DEFAULT_GUEST_PHY_PAGES */ + if (slot0_mem_pages < DEFAULT_GUEST_PHY_PAGES) + slot0_mem_pages = DEFAULT_GUEST_PHY_PAGES; + /* The maximum page table size for a memory region will be when the * smallest pages are used. Considering each page contains x page * table descriptors, the total extra size for page tables (for extra * N pages) will be: N/x+N/x^2+N/x^3+... which is definitely smaller * than N/x*2. */ - uint64_t vcpu_pages = (DEFAULT_STACK_PGS + num_percpu_pages) * nr_vcpus; - uint64_t extra_pg_pages = (extra_mem_pages + vcpu_pages) / PTES_PER_MIN_PAGE * 2; - uint64_t pages = DEFAULT_GUEST_PHY_PAGES + vcpu_pages + extra_pg_pages; - struct kvm_vm *vm; - int i; + vcpu_pages = (DEFAULT_STACK_PGS + num_percpu_pages) * nr_vcpus; + extra_pg_pages = (slot0_mem_pages + extra_mem_pages + vcpu_pages) / PTES_PER_MIN_PAGE * 2; + pages = slot0_mem_pages + vcpu_pages + extra_pg_pages; TEST_ASSERT(nr_vcpus <= kvm_check_cap(KVM_CAP_MAX_VCPUS), "nr_vcpus = %d too large for host, max-vcpus = %d", @@ -329,8 +388,8 @@ struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_me uint32_t num_percpu_pages, void *guest_code, uint32_t vcpuids[]) { - return vm_create_with_vcpus(VM_MODE_DEFAULT, nr_vcpus, extra_mem_pages, - num_percpu_pages, guest_code, vcpuids); + return vm_create_with_vcpus(VM_MODE_DEFAULT, nr_vcpus, DEFAULT_GUEST_PHY_PAGES, + extra_mem_pages, num_percpu_pages, guest_code, vcpuids); } struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, @@ -355,13 +414,14 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, */ void kvm_vm_restart(struct kvm_vm *vmp, int perm) { + int ctr; struct userspace_mem_region *region; vm_open(vmp, perm); if (vmp->has_irqchip) vm_create_irqchip(vmp); - list_for_each_entry(region, &vmp->userspace_mem_regions, list) { + hash_for_each(vmp->regions.slot_hash, ctr, region, slot_node) { int ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION, ®ion->region); TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n" " rc: %i errno: %i\n" @@ -424,14 +484,21 @@ uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm) static struct userspace_mem_region * userspace_mem_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end) { - struct userspace_mem_region *region; + struct rb_node *node; - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + for (node = vm->regions.gpa_tree.rb_node; node; ) { + struct userspace_mem_region *region = + container_of(node, struct userspace_mem_region, gpa_node); uint64_t existing_start = region->region.guest_phys_addr; uint64_t existing_end = region->region.guest_phys_addr + region->region.memory_size - 1; if (start <= existing_end && end >= existing_start) return region; + + if (start < existing_start) + node = node->rb_left; + else + node = node->rb_right; } return NULL; @@ -546,11 +613,16 @@ void kvm_vm_release(struct kvm_vm *vmp) } static void __vm_mem_region_delete(struct kvm_vm *vm, - struct userspace_mem_region *region) + struct userspace_mem_region *region, + bool unlink) { int ret; - list_del(®ion->list); + if (unlink) { + rb_erase(®ion->gpa_node, &vm->regions.gpa_tree); + rb_erase(®ion->hva_node, &vm->regions.hva_tree); + hash_del(®ion->slot_node); + } region->region.memory_size = 0; ret = ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, ®ion->region); @@ -569,14 +641,16 @@ static void __vm_mem_region_delete(struct kvm_vm *vm, */ void kvm_vm_free(struct kvm_vm *vmp) { - struct userspace_mem_region *region, *tmp; + int ctr; + struct hlist_node *node; + struct userspace_mem_region *region; if (vmp == NULL) return; /* Free userspace_mem_regions. */ - list_for_each_entry_safe(region, tmp, &vmp->userspace_mem_regions, list) - __vm_mem_region_delete(vmp, region); + hash_for_each_safe(vmp->regions.slot_hash, ctr, node, region, slot_node) + __vm_mem_region_delete(vmp, region, false); /* Free sparsebit arrays. */ sparsebit_free(&vmp->vpages_valid); @@ -658,13 +732,64 @@ int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, vm_vaddr_t gva, size_t len) return 0; } +static void vm_userspace_mem_region_gpa_insert(struct rb_root *gpa_tree, + struct userspace_mem_region *region) +{ + struct rb_node **cur, *parent; + + for (cur = &gpa_tree->rb_node, parent = NULL; *cur; ) { + struct userspace_mem_region *cregion; + + cregion = container_of(*cur, typeof(*cregion), gpa_node); + parent = *cur; + if (region->region.guest_phys_addr < + cregion->region.guest_phys_addr) + cur = &(*cur)->rb_left; + else { + TEST_ASSERT(region->region.guest_phys_addr != + cregion->region.guest_phys_addr, + "Duplicate GPA in region tree"); + + cur = &(*cur)->rb_right; + } + } + + rb_link_node(®ion->gpa_node, parent, cur); + rb_insert_color(®ion->gpa_node, gpa_tree); +} + +static void vm_userspace_mem_region_hva_insert(struct rb_root *hva_tree, + struct userspace_mem_region *region) +{ + struct rb_node **cur, *parent; + + for (cur = &hva_tree->rb_node, parent = NULL; *cur; ) { + struct userspace_mem_region *cregion; + + cregion = container_of(*cur, typeof(*cregion), hva_node); + parent = *cur; + if (region->host_mem < cregion->host_mem) + cur = &(*cur)->rb_left; + else { + TEST_ASSERT(region->host_mem != + cregion->host_mem, + "Duplicate HVA in region tree"); + + cur = &(*cur)->rb_right; + } + } + + rb_link_node(®ion->hva_node, parent, cur); + rb_insert_color(®ion->hva_node, hva_tree); +} + /* * VM Userspace Memory Region Add * * Input Args: * vm - Virtual Machine - * backing_src - Storage source for this region. - * NULL to use anonymous memory. + * src_type - Storage source for this region. + * NULL to use anonymous memory. * guest_paddr - Starting guest physical address * slot - KVM region slot * npages - Number of physical pages @@ -722,7 +847,8 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, (uint64_t) region->region.memory_size); /* Confirm no region with the requested slot already exists. */ - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + hash_for_each_possible(vm->regions.slot_hash, region, slot_node, + slot) { if (region->region.slot != slot) continue; @@ -755,11 +881,30 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, if (alignment > 1) region->mmap_size += alignment; + region->fd = -1; + if (backing_src_is_shared(src_type)) { + int memfd_flags = MFD_CLOEXEC; + + if (src_type == VM_MEM_SRC_SHARED_HUGETLB) + memfd_flags |= MFD_HUGETLB; + + region->fd = memfd_create("kvm_selftest", memfd_flags); + TEST_ASSERT(region->fd != -1, + "memfd_create failed, errno: %i", errno); + + ret = ftruncate(region->fd, region->mmap_size); + TEST_ASSERT(ret == 0, "ftruncate failed, errno: %i", errno); + + ret = fallocate(region->fd, + FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, + region->mmap_size); + TEST_ASSERT(ret == 0, "fallocate failed, errno: %i", errno); + } + region->mmap_start = mmap(NULL, region->mmap_size, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS - | vm_mem_backing_src_alias(src_type)->flag, - -1, 0); + vm_mem_backing_src_alias(src_type)->flag, + region->fd, 0); TEST_ASSERT(region->mmap_start != MAP_FAILED, "test_malloc failed, mmap_start: %p errno: %i", region->mmap_start, errno); @@ -793,8 +938,23 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, ret, errno, slot, flags, guest_paddr, (uint64_t) region->region.memory_size); - /* Add to linked-list of memory regions. */ - list_add(®ion->list, &vm->userspace_mem_regions); + /* Add to quick lookup data structures */ + vm_userspace_mem_region_gpa_insert(&vm->regions.gpa_tree, region); + vm_userspace_mem_region_hva_insert(&vm->regions.hva_tree, region); + hash_add(vm->regions.slot_hash, ®ion->slot_node, slot); + + /* If shared memory, create an alias. */ + if (region->fd >= 0) { + region->mmap_alias = mmap(NULL, region->mmap_size, + PROT_READ | PROT_WRITE, + vm_mem_backing_src_alias(src_type)->flag, + region->fd, 0); + TEST_ASSERT(region->mmap_alias != MAP_FAILED, + "mmap of alias failed, errno: %i", errno); + + /* Align host alias address */ + region->host_alias = align(region->mmap_alias, alignment); + } } /* @@ -817,10 +977,10 @@ memslot2region(struct kvm_vm *vm, uint32_t memslot) { struct userspace_mem_region *region; - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + hash_for_each_possible(vm->regions.slot_hash, region, slot_node, + memslot) if (region->region.slot == memslot) return region; - } fprintf(stderr, "No mem region with the requested slot found,\n" " requested slot: %u\n", memslot); @@ -905,7 +1065,7 @@ void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa) */ void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot) { - __vm_mem_region_delete(vm, memslot2region(vm, slot)); + __vm_mem_region_delete(vm, memslot2region(vm, slot), true); } /* @@ -925,9 +1085,7 @@ static int vcpu_mmap_sz(void) { int dev_fd, ret; - dev_fd = open(KVM_DEV_PATH, O_RDONLY); - if (dev_fd < 0) - exit(KSFT_SKIP); + dev_fd = open_kvm_dev_path_or_exit(); ret = ioctl(dev_fd, KVM_GET_VCPU_MMAP_SIZE, NULL); TEST_ASSERT(ret >= sizeof(struct kvm_run), @@ -1099,6 +1257,9 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, uint64_t pages = (sz >> vm->page_shift) + ((sz % vm->page_size) != 0); virt_pgd_alloc(vm, pgd_memslot); + vm_paddr_t paddr = vm_phy_pages_alloc(vm, pages, + KVM_UTIL_MIN_PFN * vm->page_size, + data_memslot); /* * Find an unused range of virtual page addresses of at least @@ -1108,11 +1269,7 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, /* Map the virtual pages. */ for (vm_vaddr_t vaddr = vaddr_start; pages > 0; - pages--, vaddr += vm->page_size) { - vm_paddr_t paddr; - - paddr = vm_phy_page_alloc(vm, - KVM_UTIL_MIN_PFN * vm->page_size, data_memslot); + pages--, vaddr += vm->page_size, paddr += vm->page_size) { virt_pg_map(vm, vaddr, paddr, pgd_memslot); @@ -1177,16 +1334,14 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa) { struct userspace_mem_region *region; - list_for_each_entry(region, &vm->userspace_mem_regions, list) { - if ((gpa >= region->region.guest_phys_addr) - && (gpa <= (region->region.guest_phys_addr - + region->region.memory_size - 1))) - return (void *) ((uintptr_t) region->host_mem - + (gpa - region->region.guest_phys_addr)); + region = userspace_mem_region_find(vm, gpa, gpa); + if (!region) { + TEST_FAIL("No vm physical memory at 0x%lx", gpa); + return NULL; } - TEST_FAIL("No vm physical memory at 0x%lx", gpa); - return NULL; + return (void *)((uintptr_t)region->host_mem + + (gpa - region->region.guest_phys_addr)); } /* @@ -1208,15 +1363,22 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa) */ vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva) { - struct userspace_mem_region *region; + struct rb_node *node; - list_for_each_entry(region, &vm->userspace_mem_regions, list) { - if ((hva >= region->host_mem) - && (hva <= (region->host_mem - + region->region.memory_size - 1))) - return (vm_paddr_t) ((uintptr_t) - region->region.guest_phys_addr - + (hva - (uintptr_t) region->host_mem)); + for (node = vm->regions.hva_tree.rb_node; node; ) { + struct userspace_mem_region *region = + container_of(node, struct userspace_mem_region, hva_node); + + if (hva >= region->host_mem) { + if (hva <= (region->host_mem + + region->region.memory_size - 1)) + return (vm_paddr_t)((uintptr_t) + region->region.guest_phys_addr + + (hva - (uintptr_t)region->host_mem)); + + node = node->rb_right; + } else + node = node->rb_left; } TEST_FAIL("No mapping to a guest physical address, hva: %p", hva); @@ -1224,6 +1386,42 @@ vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva) } /* + * Address VM physical to Host Virtual *alias*. + * + * Input Args: + * vm - Virtual Machine + * gpa - VM physical address + * + * Output Args: None + * + * Return: + * Equivalent address within the host virtual *alias* area, or NULL + * (without failing the test) if the guest memory is not shared (so + * no alias exists). + * + * When vm_create() and related functions are called with a shared memory + * src_type, we also create a writable, shared alias mapping of the + * underlying guest memory. This allows the host to manipulate guest memory + * without mapping that memory in the guest's address space. And, for + * userfaultfd-based demand paging, we can do so without triggering userfaults. + */ +void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa) +{ + struct userspace_mem_region *region; + uintptr_t offset; + + region = userspace_mem_region_find(vm, gpa, gpa); + if (!region) + return NULL; + + if (!region->host_alias) + return NULL; + + offset = gpa - region->region.guest_phys_addr; + return (void *) ((uintptr_t) region->host_alias + offset); +} + +/* * VM Create IRQ Chip * * Input Args: @@ -1822,6 +2020,7 @@ int kvm_device_access(int dev_fd, uint32_t group, uint64_t attr, */ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) { + int ctr; struct userspace_mem_region *region; struct vcpu *vcpu; @@ -1829,7 +2028,7 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) fprintf(stream, "%*sfd: %i\n", indent, "", vm->fd); fprintf(stream, "%*spage_size: 0x%x\n", indent, "", vm->page_size); fprintf(stream, "%*sMem Regions:\n", indent, ""); - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + hash_for_each(vm->regions.slot_hash, ctr, region, slot_node) { fprintf(stream, "%*sguest_phys: 0x%lx size: 0x%lx " "host_virt: %p\n", indent + 2, "", (uint64_t) region->region.guest_phys_addr, @@ -2015,10 +2214,7 @@ bool vm_is_unrestricted_guest(struct kvm_vm *vm) if (vm == NULL) { /* Ensure that the KVM vendor-specific module is loaded. */ - f = fopen(KVM_DEV_PATH, "r"); - TEST_ASSERT(f != NULL, "Error in opening KVM dev file: %d", - errno); - fclose(f); + close(open_kvm_dev_path_or_exit()); } f = fopen("/sys/module/kvm_intel/parameters/unrestricted_guest", "r"); @@ -2041,7 +2237,7 @@ unsigned int vm_get_page_shift(struct kvm_vm *vm) return vm->page_shift; } -unsigned int vm_get_max_gfn(struct kvm_vm *vm) +uint64_t vm_get_max_gfn(struct kvm_vm *vm) { return vm->max_gfn; } diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h index 91ce1b5d480b..a03febc24ba6 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h +++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h @@ -8,6 +8,9 @@ #ifndef SELFTEST_KVM_UTIL_INTERNAL_H #define SELFTEST_KVM_UTIL_INTERNAL_H +#include "linux/hashtable.h" +#include "linux/rbtree.h" + #include "sparsebit.h" struct userspace_mem_region { @@ -16,9 +19,13 @@ struct userspace_mem_region { int fd; off_t offset; void *host_mem; + void *host_alias; void *mmap_start; + void *mmap_alias; size_t mmap_size; - struct list_head list; + struct rb_node gpa_node; + struct rb_node hva_node; + struct hlist_node slot_node; }; struct vcpu { @@ -31,6 +38,12 @@ struct vcpu { uint32_t dirty_gfns_count; }; +struct userspace_mem_regions { + struct rb_root gpa_tree; + struct rb_root hva_tree; + DECLARE_HASHTABLE(slot_hash, 9); +}; + struct kvm_vm { int mode; unsigned long type; @@ -43,7 +56,7 @@ struct kvm_vm { unsigned int va_bits; uint64_t max_gfn; struct list_head vcpus; - struct list_head userspace_mem_regions; + struct userspace_mem_regions regions; struct sparsebit *vpages_valid; struct sparsebit *vpages_mapped; bool has_irqchip; diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c index 81490b9b4e32..7397ca299835 100644 --- a/tools/testing/selftests/kvm/lib/perf_test_util.c +++ b/tools/testing/selftests/kvm/lib/perf_test_util.c @@ -2,6 +2,7 @@ /* * Copyright (C) 2020, Google LLC. */ +#include <inttypes.h> #include "kvm_util.h" #include "perf_test_util.h" @@ -68,7 +69,7 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus, TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0, "Guest memory size is not guest page size aligned."); - vm = vm_create_with_vcpus(mode, vcpus, + vm = vm_create_with_vcpus(mode, vcpus, DEFAULT_GUEST_PHY_PAGES, (vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size, 0, guest_code, NULL); @@ -80,7 +81,8 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus, */ TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm), "Requested more guest memory than address space allows.\n" - " guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n", + " guest pages: %" PRIx64 " max gfn: %" PRIx64 + " vcpus: %d wss: %" PRIx64 "]\n", guest_num_pages, vm_get_max_gfn(vm), vcpus, vcpu_memory_bytes); diff --git a/tools/testing/selftests/kvm/lib/rbtree.c b/tools/testing/selftests/kvm/lib/rbtree.c new file mode 100644 index 000000000000..a703f0194ea3 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/rbtree.c @@ -0,0 +1 @@ +#include "../../../../lib/rbtree.c" diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index 63d2bc7d757b..af1031fed97f 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -166,72 +166,89 @@ size_t get_def_hugetlb_pagesz(void) return 0; } +#define ANON_FLAGS (MAP_PRIVATE | MAP_ANONYMOUS) +#define ANON_HUGE_FLAGS (ANON_FLAGS | MAP_HUGETLB) + const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i) { static const struct vm_mem_backing_src_alias aliases[] = { [VM_MEM_SRC_ANONYMOUS] = { .name = "anonymous", - .flag = 0, + .flag = ANON_FLAGS, }, [VM_MEM_SRC_ANONYMOUS_THP] = { .name = "anonymous_thp", - .flag = 0, + .flag = ANON_FLAGS, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB] = { .name = "anonymous_hugetlb", - .flag = MAP_HUGETLB, + .flag = ANON_HUGE_FLAGS, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_16KB] = { .name = "anonymous_hugetlb_16kb", - .flag = MAP_HUGETLB | MAP_HUGE_16KB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_16KB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_64KB] = { .name = "anonymous_hugetlb_64kb", - .flag = MAP_HUGETLB | MAP_HUGE_64KB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_64KB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_512KB] = { .name = "anonymous_hugetlb_512kb", - .flag = MAP_HUGETLB | MAP_HUGE_512KB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_512KB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_1MB] = { .name = "anonymous_hugetlb_1mb", - .flag = MAP_HUGETLB | MAP_HUGE_1MB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_1MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_2MB] = { .name = "anonymous_hugetlb_2mb", - .flag = MAP_HUGETLB | MAP_HUGE_2MB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_2MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_8MB] = { .name = "anonymous_hugetlb_8mb", - .flag = MAP_HUGETLB | MAP_HUGE_8MB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_8MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_16MB] = { .name = "anonymous_hugetlb_16mb", - .flag = MAP_HUGETLB | MAP_HUGE_16MB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_16MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_32MB] = { .name = "anonymous_hugetlb_32mb", - .flag = MAP_HUGETLB | MAP_HUGE_32MB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_32MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_256MB] = { .name = "anonymous_hugetlb_256mb", - .flag = MAP_HUGETLB | MAP_HUGE_256MB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_256MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_512MB] = { .name = "anonymous_hugetlb_512mb", - .flag = MAP_HUGETLB | MAP_HUGE_512MB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_512MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_1GB] = { .name = "anonymous_hugetlb_1gb", - .flag = MAP_HUGETLB | MAP_HUGE_1GB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_1GB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_2GB] = { .name = "anonymous_hugetlb_2gb", - .flag = MAP_HUGETLB | MAP_HUGE_2GB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_2GB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_16GB] = { .name = "anonymous_hugetlb_16gb", - .flag = MAP_HUGETLB | MAP_HUGE_16GB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_16GB, + }, + [VM_MEM_SRC_SHMEM] = { + .name = "shmem", + .flag = MAP_SHARED, + }, + [VM_MEM_SRC_SHARED_HUGETLB] = { + .name = "shared_hugetlb", + /* + * No MAP_HUGETLB, we use MFD_HUGETLB instead. Since + * we're using "file backed" memory, we need to specify + * this when the FD is created, not when the area is + * mapped. + */ + .flag = MAP_SHARED, }, }; _Static_assert(ARRAY_SIZE(aliases) == NUM_SRC_TYPES, @@ -250,10 +267,12 @@ size_t get_backing_src_pagesz(uint32_t i) switch (i) { case VM_MEM_SRC_ANONYMOUS: + case VM_MEM_SRC_SHMEM: return getpagesize(); case VM_MEM_SRC_ANONYMOUS_THP: return get_trans_hugepagesz(); case VM_MEM_SRC_ANONYMOUS_HUGETLB: + case VM_MEM_SRC_SHARED_HUGETLB: return get_def_hugetlb_pagesz(); default: return MAP_HUGE_PAGE_SIZE(flag); diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index a8906e60a108..efe235044421 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -657,9 +657,7 @@ struct kvm_cpuid2 *kvm_get_supported_cpuid(void) return cpuid; cpuid = allocate_kvm_cpuid2(); - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID, cpuid); TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_CPUID failed %d %d\n", @@ -691,9 +689,7 @@ uint64_t kvm_get_feature_msr(uint64_t msr_index) buffer.header.nmsrs = 1; buffer.entry.index = msr_index; - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); r = ioctl(kvm_fd, KVM_GET_MSRS, &buffer.header); TEST_ASSERT(r == 1, "KVM_GET_MSRS IOCTL failed,\n" @@ -986,9 +982,7 @@ struct kvm_msr_list *kvm_get_msr_index_list(void) struct kvm_msr_list *list; int nmsrs, r, kvm_fd; - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); nmsrs = kvm_get_num_msrs_fd(kvm_fd); list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0])); @@ -1312,9 +1306,7 @@ struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void) return cpuid; cpuid = allocate_kvm_cpuid2(); - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_HV_CPUID, cpuid); TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_HV_CPUID failed %d %d\n", diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c index 6096bf0a5b34..98351ba0933c 100644 --- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c +++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c @@ -71,14 +71,22 @@ struct memslot_antagonist_args { }; static void add_remove_memslot(struct kvm_vm *vm, useconds_t delay, - uint64_t nr_modifications, uint64_t gpa) + uint64_t nr_modifications) { + const uint64_t pages = 1; + uint64_t gpa; int i; + /* + * Add the dummy memslot just below the perf_test_util memslot, which is + * at the top of the guest physical address space. + */ + gpa = guest_test_phys_mem - pages * vm_get_page_size(vm); + for (i = 0; i < nr_modifications; i++) { usleep(delay); vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, gpa, - DUMMY_MEMSLOT_INDEX, 1, 0); + DUMMY_MEMSLOT_INDEX, pages, 0); vm_mem_region_delete(vm, DUMMY_MEMSLOT_INDEX); } @@ -120,11 +128,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) pr_info("Started all vCPUs\n"); add_remove_memslot(vm, p->memslot_modification_delay, - p->nr_memslot_modifications, - guest_test_phys_mem + - (guest_percpu_mem_size * nr_vcpus) + - perf_test_args.host_page_size + - perf_test_args.guest_page_size); + p->nr_memslot_modifications); run_vcpus = false; diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c new file mode 100644 index 000000000000..11239652d805 --- /dev/null +++ b/tools/testing/selftests/kvm/memslot_perf_test.c @@ -0,0 +1,1037 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * A memslot-related performance benchmark. + * + * Copyright (C) 2021 Oracle and/or its affiliates. + * + * Basic guest setup / host vCPU thread code lifted from set_memory_region_test. + */ +#include <pthread.h> +#include <sched.h> +#include <semaphore.h> +#include <stdatomic.h> +#include <stdbool.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> +#include <time.h> +#include <unistd.h> + +#include <linux/compiler.h> + +#include <test_util.h> +#include <kvm_util.h> +#include <processor.h> + +#define VCPU_ID 0 + +#define MEM_SIZE ((512U << 20) + 4096) +#define MEM_SIZE_PAGES (MEM_SIZE / 4096) +#define MEM_GPA 0x10000000UL +#define MEM_AUX_GPA MEM_GPA +#define MEM_SYNC_GPA MEM_AUX_GPA +#define MEM_TEST_GPA (MEM_AUX_GPA + 4096) +#define MEM_TEST_SIZE (MEM_SIZE - 4096) +static_assert(MEM_SIZE % 4096 == 0, "invalid mem size"); +static_assert(MEM_TEST_SIZE % 4096 == 0, "invalid mem test size"); + +/* + * 32 MiB is max size that gets well over 100 iterations on 509 slots. + * Considering that each slot needs to have at least one page up to + * 8194 slots in use can then be tested (although with slightly + * limited resolution). + */ +#define MEM_SIZE_MAP ((32U << 20) + 4096) +#define MEM_SIZE_MAP_PAGES (MEM_SIZE_MAP / 4096) +#define MEM_TEST_MAP_SIZE (MEM_SIZE_MAP - 4096) +#define MEM_TEST_MAP_SIZE_PAGES (MEM_TEST_MAP_SIZE / 4096) +static_assert(MEM_SIZE_MAP % 4096 == 0, "invalid map test region size"); +static_assert(MEM_TEST_MAP_SIZE % 4096 == 0, "invalid map test region size"); +static_assert(MEM_TEST_MAP_SIZE_PAGES % 2 == 0, "invalid map test region size"); +static_assert(MEM_TEST_MAP_SIZE_PAGES > 2, "invalid map test region size"); + +/* + * 128 MiB is min size that fills 32k slots with at least one page in each + * while at the same time gets 100+ iterations in such test + */ +#define MEM_TEST_UNMAP_SIZE (128U << 20) +#define MEM_TEST_UNMAP_SIZE_PAGES (MEM_TEST_UNMAP_SIZE / 4096) +/* 2 MiB chunk size like a typical huge page */ +#define MEM_TEST_UNMAP_CHUNK_PAGES (2U << (20 - 12)) +static_assert(MEM_TEST_UNMAP_SIZE <= MEM_TEST_SIZE, + "invalid unmap test region size"); +static_assert(MEM_TEST_UNMAP_SIZE % 4096 == 0, + "invalid unmap test region size"); +static_assert(MEM_TEST_UNMAP_SIZE_PAGES % + (2 * MEM_TEST_UNMAP_CHUNK_PAGES) == 0, + "invalid unmap test region size"); + +/* + * For the move active test the middle of the test area is placed on + * a memslot boundary: half lies in the memslot being moved, half in + * other memslot(s). + * + * When running this test with 32k memslots (32764, really) each memslot + * contains 4 pages. + * The last one additionally contains the remaining 21 pages of memory, + * for the total size of 25 pages. + * Hence, the maximum size here is 50 pages. + */ +#define MEM_TEST_MOVE_SIZE_PAGES (50) +#define MEM_TEST_MOVE_SIZE (MEM_TEST_MOVE_SIZE_PAGES * 4096) +#define MEM_TEST_MOVE_GPA_DEST (MEM_GPA + MEM_SIZE) +static_assert(MEM_TEST_MOVE_SIZE <= MEM_TEST_SIZE, + "invalid move test region size"); + +#define MEM_TEST_VAL_1 0x1122334455667788 +#define MEM_TEST_VAL_2 0x99AABBCCDDEEFF00 + +struct vm_data { + struct kvm_vm *vm; + pthread_t vcpu_thread; + uint32_t nslots; + uint64_t npages; + uint64_t pages_per_slot; + void **hva_slots; + bool mmio_ok; + uint64_t mmio_gpa_min; + uint64_t mmio_gpa_max; +}; + +struct sync_area { + atomic_bool start_flag; + atomic_bool exit_flag; + atomic_bool sync_flag; + void *move_area_ptr; +}; + +/* + * Technically, we need also for the atomic bool to be address-free, which + * is recommended, but not strictly required, by C11 for lockless + * implementations. + * However, in practice both GCC and Clang fulfill this requirement on + * all KVM-supported platforms. + */ +static_assert(ATOMIC_BOOL_LOCK_FREE == 2, "atomic bool is not lockless"); + +static sem_t vcpu_ready; + +static bool map_unmap_verify; + +static bool verbose; +#define pr_info_v(...) \ + do { \ + if (verbose) \ + pr_info(__VA_ARGS__); \ + } while (0) + +static void *vcpu_worker(void *data) +{ + struct vm_data *vm = data; + struct kvm_run *run; + struct ucall uc; + uint64_t cmd; + + run = vcpu_state(vm->vm, VCPU_ID); + while (1) { + vcpu_run(vm->vm, VCPU_ID); + + if (run->exit_reason == KVM_EXIT_IO) { + cmd = get_ucall(vm->vm, VCPU_ID, &uc); + if (cmd != UCALL_SYNC) + break; + + sem_post(&vcpu_ready); + continue; + } + + if (run->exit_reason != KVM_EXIT_MMIO) + break; + + TEST_ASSERT(vm->mmio_ok, "Unexpected mmio exit"); + TEST_ASSERT(run->mmio.is_write, "Unexpected mmio read"); + TEST_ASSERT(run->mmio.len == 8, + "Unexpected exit mmio size = %u", run->mmio.len); + TEST_ASSERT(run->mmio.phys_addr >= vm->mmio_gpa_min && + run->mmio.phys_addr <= vm->mmio_gpa_max, + "Unexpected exit mmio address = 0x%llx", + run->mmio.phys_addr); + } + + if (run->exit_reason == KVM_EXIT_IO && cmd == UCALL_ABORT) + TEST_FAIL("%s at %s:%ld, val = %lu", (const char *)uc.args[0], + __FILE__, uc.args[1], uc.args[2]); + + return NULL; +} + +static void wait_for_vcpu(void) +{ + struct timespec ts; + + TEST_ASSERT(!clock_gettime(CLOCK_REALTIME, &ts), + "clock_gettime() failed: %d\n", errno); + + ts.tv_sec += 2; + TEST_ASSERT(!sem_timedwait(&vcpu_ready, &ts), + "sem_timedwait() failed: %d\n", errno); +} + +static void *vm_gpa2hva(struct vm_data *data, uint64_t gpa, uint64_t *rempages) +{ + uint64_t gpage, pgoffs; + uint32_t slot, slotoffs; + void *base; + + TEST_ASSERT(gpa >= MEM_GPA, "Too low gpa to translate"); + TEST_ASSERT(gpa < MEM_GPA + data->npages * 4096, + "Too high gpa to translate"); + gpa -= MEM_GPA; + + gpage = gpa / 4096; + pgoffs = gpa % 4096; + slot = min(gpage / data->pages_per_slot, (uint64_t)data->nslots - 1); + slotoffs = gpage - (slot * data->pages_per_slot); + + if (rempages) { + uint64_t slotpages; + + if (slot == data->nslots - 1) + slotpages = data->npages - slot * data->pages_per_slot; + else + slotpages = data->pages_per_slot; + + TEST_ASSERT(!pgoffs, + "Asking for remaining pages in slot but gpa not page aligned"); + *rempages = slotpages - slotoffs; + } + + base = data->hva_slots[slot]; + return (uint8_t *)base + slotoffs * 4096 + pgoffs; +} + +static uint64_t vm_slot2gpa(struct vm_data *data, uint32_t slot) +{ + TEST_ASSERT(slot < data->nslots, "Too high slot number"); + + return MEM_GPA + slot * data->pages_per_slot * 4096; +} + +static struct vm_data *alloc_vm(void) +{ + struct vm_data *data; + + data = malloc(sizeof(*data)); + TEST_ASSERT(data, "malloc(vmdata) failed"); + + data->vm = NULL; + data->hva_slots = NULL; + + return data; +} + +static bool prepare_vm(struct vm_data *data, int nslots, uint64_t *maxslots, + void *guest_code, uint64_t mempages, + struct timespec *slot_runtime) +{ + uint32_t max_mem_slots; + uint64_t rempages; + uint64_t guest_addr; + uint32_t slot; + struct timespec tstart; + struct sync_area *sync; + + max_mem_slots = kvm_check_cap(KVM_CAP_NR_MEMSLOTS); + TEST_ASSERT(max_mem_slots > 1, + "KVM_CAP_NR_MEMSLOTS should be greater than 1"); + TEST_ASSERT(nslots > 1 || nslots == -1, + "Slot count cap should be greater than 1"); + if (nslots != -1) + max_mem_slots = min(max_mem_slots, (uint32_t)nslots); + pr_info_v("Allowed number of memory slots: %"PRIu32"\n", max_mem_slots); + + TEST_ASSERT(mempages > 1, + "Can't test without any memory"); + + data->npages = mempages; + data->nslots = max_mem_slots - 1; + data->pages_per_slot = mempages / data->nslots; + if (!data->pages_per_slot) { + *maxslots = mempages + 1; + return false; + } + + rempages = mempages % data->nslots; + data->hva_slots = malloc(sizeof(*data->hva_slots) * data->nslots); + TEST_ASSERT(data->hva_slots, "malloc() fail"); + + data->vm = vm_create_default(VCPU_ID, mempages, guest_code); + + pr_info_v("Adding slots 1..%i, each slot with %"PRIu64" pages + %"PRIu64" extra pages last\n", + max_mem_slots - 1, data->pages_per_slot, rempages); + + clock_gettime(CLOCK_MONOTONIC, &tstart); + for (slot = 1, guest_addr = MEM_GPA; slot < max_mem_slots; slot++) { + uint64_t npages; + + npages = data->pages_per_slot; + if (slot == max_mem_slots - 1) + npages += rempages; + + vm_userspace_mem_region_add(data->vm, VM_MEM_SRC_ANONYMOUS, + guest_addr, slot, npages, + 0); + guest_addr += npages * 4096; + } + *slot_runtime = timespec_elapsed(tstart); + + for (slot = 0, guest_addr = MEM_GPA; slot < max_mem_slots - 1; slot++) { + uint64_t npages; + uint64_t gpa; + + npages = data->pages_per_slot; + if (slot == max_mem_slots - 2) + npages += rempages; + + gpa = vm_phy_pages_alloc(data->vm, npages, guest_addr, + slot + 1); + TEST_ASSERT(gpa == guest_addr, + "vm_phy_pages_alloc() failed\n"); + + data->hva_slots[slot] = addr_gpa2hva(data->vm, guest_addr); + memset(data->hva_slots[slot], 0, npages * 4096); + + guest_addr += npages * 4096; + } + + virt_map(data->vm, MEM_GPA, MEM_GPA, mempages, 0); + + sync = (typeof(sync))vm_gpa2hva(data, MEM_SYNC_GPA, NULL); + atomic_init(&sync->start_flag, false); + atomic_init(&sync->exit_flag, false); + atomic_init(&sync->sync_flag, false); + + data->mmio_ok = false; + + return true; +} + +static void launch_vm(struct vm_data *data) +{ + pr_info_v("Launching the test VM\n"); + + pthread_create(&data->vcpu_thread, NULL, vcpu_worker, data); + + /* Ensure the guest thread is spun up. */ + wait_for_vcpu(); +} + +static void free_vm(struct vm_data *data) +{ + kvm_vm_free(data->vm); + free(data->hva_slots); + free(data); +} + +static void wait_guest_exit(struct vm_data *data) +{ + pthread_join(data->vcpu_thread, NULL); +} + +static void let_guest_run(struct sync_area *sync) +{ + atomic_store_explicit(&sync->start_flag, true, memory_order_release); +} + +static void guest_spin_until_start(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + + while (!atomic_load_explicit(&sync->start_flag, memory_order_acquire)) + ; +} + +static void make_guest_exit(struct sync_area *sync) +{ + atomic_store_explicit(&sync->exit_flag, true, memory_order_release); +} + +static bool _guest_should_exit(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + + return atomic_load_explicit(&sync->exit_flag, memory_order_acquire); +} + +#define guest_should_exit() unlikely(_guest_should_exit()) + +/* + * noinline so we can easily see how much time the host spends waiting + * for the guest. + * For the same reason use alarm() instead of polling clock_gettime() + * to implement a wait timeout. + */ +static noinline void host_perform_sync(struct sync_area *sync) +{ + alarm(2); + + atomic_store_explicit(&sync->sync_flag, true, memory_order_release); + while (atomic_load_explicit(&sync->sync_flag, memory_order_acquire)) + ; + + alarm(0); +} + +static bool guest_perform_sync(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + bool expected; + + do { + if (guest_should_exit()) + return false; + + expected = true; + } while (!atomic_compare_exchange_weak_explicit(&sync->sync_flag, + &expected, false, + memory_order_acq_rel, + memory_order_relaxed)); + + return true; +} + +static void guest_code_test_memslot_move(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + uintptr_t base = (typeof(base))READ_ONCE(sync->move_area_ptr); + + GUEST_SYNC(0); + + guest_spin_until_start(); + + while (!guest_should_exit()) { + uintptr_t ptr; + + for (ptr = base; ptr < base + MEM_TEST_MOVE_SIZE; + ptr += 4096) + *(uint64_t *)ptr = MEM_TEST_VAL_1; + + /* + * No host sync here since the MMIO exits are so expensive + * that the host would spend most of its time waiting for + * the guest and so instead of measuring memslot move + * performance we would measure the performance and + * likelihood of MMIO exits + */ + } + + GUEST_DONE(); +} + +static void guest_code_test_memslot_map(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + + GUEST_SYNC(0); + + guest_spin_until_start(); + + while (1) { + uintptr_t ptr; + + for (ptr = MEM_TEST_GPA; + ptr < MEM_TEST_GPA + MEM_TEST_MAP_SIZE / 2; ptr += 4096) + *(uint64_t *)ptr = MEM_TEST_VAL_1; + + if (!guest_perform_sync()) + break; + + for (ptr = MEM_TEST_GPA + MEM_TEST_MAP_SIZE / 2; + ptr < MEM_TEST_GPA + MEM_TEST_MAP_SIZE; ptr += 4096) + *(uint64_t *)ptr = MEM_TEST_VAL_2; + + if (!guest_perform_sync()) + break; + } + + GUEST_DONE(); +} + +static void guest_code_test_memslot_unmap(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + + GUEST_SYNC(0); + + guest_spin_until_start(); + + while (1) { + uintptr_t ptr = MEM_TEST_GPA; + + /* + * We can afford to access (map) just a small number of pages + * per host sync as otherwise the host will spend + * a significant amount of its time waiting for the guest + * (instead of doing unmap operations), so this will + * effectively turn this test into a map performance test. + * + * Just access a single page to be on the safe side. + */ + *(uint64_t *)ptr = MEM_TEST_VAL_1; + + if (!guest_perform_sync()) + break; + + ptr += MEM_TEST_UNMAP_SIZE / 2; + *(uint64_t *)ptr = MEM_TEST_VAL_2; + + if (!guest_perform_sync()) + break; + } + + GUEST_DONE(); +} + +static void guest_code_test_memslot_rw(void) +{ + GUEST_SYNC(0); + + guest_spin_until_start(); + + while (1) { + uintptr_t ptr; + + for (ptr = MEM_TEST_GPA; + ptr < MEM_TEST_GPA + MEM_TEST_SIZE; ptr += 4096) + *(uint64_t *)ptr = MEM_TEST_VAL_1; + + if (!guest_perform_sync()) + break; + + for (ptr = MEM_TEST_GPA + 4096 / 2; + ptr < MEM_TEST_GPA + MEM_TEST_SIZE; ptr += 4096) { + uint64_t val = *(uint64_t *)ptr; + + GUEST_ASSERT_1(val == MEM_TEST_VAL_2, val); + *(uint64_t *)ptr = 0; + } + + if (!guest_perform_sync()) + break; + } + + GUEST_DONE(); +} + +static bool test_memslot_move_prepare(struct vm_data *data, + struct sync_area *sync, + uint64_t *maxslots, bool isactive) +{ + uint64_t movesrcgpa, movetestgpa; + + movesrcgpa = vm_slot2gpa(data, data->nslots - 1); + + if (isactive) { + uint64_t lastpages; + + vm_gpa2hva(data, movesrcgpa, &lastpages); + if (lastpages < MEM_TEST_MOVE_SIZE_PAGES / 2) { + *maxslots = 0; + return false; + } + } + + movetestgpa = movesrcgpa - (MEM_TEST_MOVE_SIZE / (isactive ? 2 : 1)); + sync->move_area_ptr = (void *)movetestgpa; + + if (isactive) { + data->mmio_ok = true; + data->mmio_gpa_min = movesrcgpa; + data->mmio_gpa_max = movesrcgpa + MEM_TEST_MOVE_SIZE / 2 - 1; + } + + return true; +} + +static bool test_memslot_move_prepare_active(struct vm_data *data, + struct sync_area *sync, + uint64_t *maxslots) +{ + return test_memslot_move_prepare(data, sync, maxslots, true); +} + +static bool test_memslot_move_prepare_inactive(struct vm_data *data, + struct sync_area *sync, + uint64_t *maxslots) +{ + return test_memslot_move_prepare(data, sync, maxslots, false); +} + +static void test_memslot_move_loop(struct vm_data *data, struct sync_area *sync) +{ + uint64_t movesrcgpa; + + movesrcgpa = vm_slot2gpa(data, data->nslots - 1); + vm_mem_region_move(data->vm, data->nslots - 1 + 1, + MEM_TEST_MOVE_GPA_DEST); + vm_mem_region_move(data->vm, data->nslots - 1 + 1, movesrcgpa); +} + +static void test_memslot_do_unmap(struct vm_data *data, + uint64_t offsp, uint64_t count) +{ + uint64_t gpa, ctr; + + for (gpa = MEM_TEST_GPA + offsp * 4096, ctr = 0; ctr < count; ) { + uint64_t npages; + void *hva; + int ret; + + hva = vm_gpa2hva(data, gpa, &npages); + TEST_ASSERT(npages, "Empty memory slot at gptr 0x%"PRIx64, gpa); + npages = min(npages, count - ctr); + ret = madvise(hva, npages * 4096, MADV_DONTNEED); + TEST_ASSERT(!ret, + "madvise(%p, MADV_DONTNEED) on VM memory should not fail for gptr 0x%"PRIx64, + hva, gpa); + ctr += npages; + gpa += npages * 4096; + } + TEST_ASSERT(ctr == count, + "madvise(MADV_DONTNEED) should exactly cover all of the requested area"); +} + +static void test_memslot_map_unmap_check(struct vm_data *data, + uint64_t offsp, uint64_t valexp) +{ + uint64_t gpa; + uint64_t *val; + + if (!map_unmap_verify) + return; + + gpa = MEM_TEST_GPA + offsp * 4096; + val = (typeof(val))vm_gpa2hva(data, gpa, NULL); + TEST_ASSERT(*val == valexp, + "Guest written values should read back correctly before unmap (%"PRIu64" vs %"PRIu64" @ %"PRIx64")", + *val, valexp, gpa); + *val = 0; +} + +static void test_memslot_map_loop(struct vm_data *data, struct sync_area *sync) +{ + /* + * Unmap the second half of the test area while guest writes to (maps) + * the first half. + */ + test_memslot_do_unmap(data, MEM_TEST_MAP_SIZE_PAGES / 2, + MEM_TEST_MAP_SIZE_PAGES / 2); + + /* + * Wait for the guest to finish writing the first half of the test + * area, verify the written value on the first and the last page of + * this area and then unmap it. + * Meanwhile, the guest is writing to (mapping) the second half of + * the test area. + */ + host_perform_sync(sync); + test_memslot_map_unmap_check(data, 0, MEM_TEST_VAL_1); + test_memslot_map_unmap_check(data, + MEM_TEST_MAP_SIZE_PAGES / 2 - 1, + MEM_TEST_VAL_1); + test_memslot_do_unmap(data, 0, MEM_TEST_MAP_SIZE_PAGES / 2); + + + /* + * Wait for the guest to finish writing the second half of the test + * area and verify the written value on the first and the last page + * of this area. + * The area will be unmapped at the beginning of the next loop + * iteration. + * Meanwhile, the guest is writing to (mapping) the first half of + * the test area. + */ + host_perform_sync(sync); + test_memslot_map_unmap_check(data, MEM_TEST_MAP_SIZE_PAGES / 2, + MEM_TEST_VAL_2); + test_memslot_map_unmap_check(data, MEM_TEST_MAP_SIZE_PAGES - 1, + MEM_TEST_VAL_2); +} + +static void test_memslot_unmap_loop_common(struct vm_data *data, + struct sync_area *sync, + uint64_t chunk) +{ + uint64_t ctr; + + /* + * Wait for the guest to finish mapping page(s) in the first half + * of the test area, verify the written value and then perform unmap + * of this area. + * Meanwhile, the guest is writing to (mapping) page(s) in the second + * half of the test area. + */ + host_perform_sync(sync); + test_memslot_map_unmap_check(data, 0, MEM_TEST_VAL_1); + for (ctr = 0; ctr < MEM_TEST_UNMAP_SIZE_PAGES / 2; ctr += chunk) + test_memslot_do_unmap(data, ctr, chunk); + + /* Likewise, but for the opposite host / guest areas */ + host_perform_sync(sync); + test_memslot_map_unmap_check(data, MEM_TEST_UNMAP_SIZE_PAGES / 2, + MEM_TEST_VAL_2); + for (ctr = MEM_TEST_UNMAP_SIZE_PAGES / 2; + ctr < MEM_TEST_UNMAP_SIZE_PAGES; ctr += chunk) + test_memslot_do_unmap(data, ctr, chunk); +} + +static void test_memslot_unmap_loop(struct vm_data *data, + struct sync_area *sync) +{ + test_memslot_unmap_loop_common(data, sync, 1); +} + +static void test_memslot_unmap_loop_chunked(struct vm_data *data, + struct sync_area *sync) +{ + test_memslot_unmap_loop_common(data, sync, MEM_TEST_UNMAP_CHUNK_PAGES); +} + +static void test_memslot_rw_loop(struct vm_data *data, struct sync_area *sync) +{ + uint64_t gptr; + + for (gptr = MEM_TEST_GPA + 4096 / 2; + gptr < MEM_TEST_GPA + MEM_TEST_SIZE; gptr += 4096) + *(uint64_t *)vm_gpa2hva(data, gptr, NULL) = MEM_TEST_VAL_2; + + host_perform_sync(sync); + + for (gptr = MEM_TEST_GPA; + gptr < MEM_TEST_GPA + MEM_TEST_SIZE; gptr += 4096) { + uint64_t *vptr = (typeof(vptr))vm_gpa2hva(data, gptr, NULL); + uint64_t val = *vptr; + + TEST_ASSERT(val == MEM_TEST_VAL_1, + "Guest written values should read back correctly (is %"PRIu64" @ %"PRIx64")", + val, gptr); + *vptr = 0; + } + + host_perform_sync(sync); +} + +struct test_data { + const char *name; + uint64_t mem_size; + void (*guest_code)(void); + bool (*prepare)(struct vm_data *data, struct sync_area *sync, + uint64_t *maxslots); + void (*loop)(struct vm_data *data, struct sync_area *sync); +}; + +static bool test_execute(int nslots, uint64_t *maxslots, + unsigned int maxtime, + const struct test_data *tdata, + uint64_t *nloops, + struct timespec *slot_runtime, + struct timespec *guest_runtime) +{ + uint64_t mem_size = tdata->mem_size ? : MEM_SIZE_PAGES; + struct vm_data *data; + struct sync_area *sync; + struct timespec tstart; + bool ret = true; + + data = alloc_vm(); + if (!prepare_vm(data, nslots, maxslots, tdata->guest_code, + mem_size, slot_runtime)) { + ret = false; + goto exit_free; + } + + sync = (typeof(sync))vm_gpa2hva(data, MEM_SYNC_GPA, NULL); + + if (tdata->prepare && + !tdata->prepare(data, sync, maxslots)) { + ret = false; + goto exit_free; + } + + launch_vm(data); + + clock_gettime(CLOCK_MONOTONIC, &tstart); + let_guest_run(sync); + + while (1) { + *guest_runtime = timespec_elapsed(tstart); + if (guest_runtime->tv_sec >= maxtime) + break; + + tdata->loop(data, sync); + + (*nloops)++; + } + + make_guest_exit(sync); + wait_guest_exit(data); + +exit_free: + free_vm(data); + + return ret; +} + +static const struct test_data tests[] = { + { + .name = "map", + .mem_size = MEM_SIZE_MAP_PAGES, + .guest_code = guest_code_test_memslot_map, + .loop = test_memslot_map_loop, + }, + { + .name = "unmap", + .mem_size = MEM_TEST_UNMAP_SIZE_PAGES + 1, + .guest_code = guest_code_test_memslot_unmap, + .loop = test_memslot_unmap_loop, + }, + { + .name = "unmap chunked", + .mem_size = MEM_TEST_UNMAP_SIZE_PAGES + 1, + .guest_code = guest_code_test_memslot_unmap, + .loop = test_memslot_unmap_loop_chunked, + }, + { + .name = "move active area", + .guest_code = guest_code_test_memslot_move, + .prepare = test_memslot_move_prepare_active, + .loop = test_memslot_move_loop, + }, + { + .name = "move inactive area", + .guest_code = guest_code_test_memslot_move, + .prepare = test_memslot_move_prepare_inactive, + .loop = test_memslot_move_loop, + }, + { + .name = "RW", + .guest_code = guest_code_test_memslot_rw, + .loop = test_memslot_rw_loop + }, +}; + +#define NTESTS ARRAY_SIZE(tests) + +struct test_args { + int tfirst; + int tlast; + int nslots; + int seconds; + int runs; +}; + +static void help(char *name, struct test_args *targs) +{ + int ctr; + + pr_info("usage: %s [-h] [-v] [-d] [-s slots] [-f first_test] [-e last_test] [-l test_length] [-r run_count]\n", + name); + pr_info(" -h: print this help screen.\n"); + pr_info(" -v: enable verbose mode (not for benchmarking).\n"); + pr_info(" -d: enable extra debug checks.\n"); + pr_info(" -s: specify memslot count cap (-1 means no cap; currently: %i)\n", + targs->nslots); + pr_info(" -f: specify the first test to run (currently: %i; max %zu)\n", + targs->tfirst, NTESTS - 1); + pr_info(" -e: specify the last test to run (currently: %i; max %zu)\n", + targs->tlast, NTESTS - 1); + pr_info(" -l: specify the test length in seconds (currently: %i)\n", + targs->seconds); + pr_info(" -r: specify the number of runs per test (currently: %i)\n", + targs->runs); + + pr_info("\nAvailable tests:\n"); + for (ctr = 0; ctr < NTESTS; ctr++) + pr_info("%d: %s\n", ctr, tests[ctr].name); +} + +static bool parse_args(int argc, char *argv[], + struct test_args *targs) +{ + int opt; + + while ((opt = getopt(argc, argv, "hvds:f:e:l:r:")) != -1) { + switch (opt) { + case 'h': + default: + help(argv[0], targs); + return false; + case 'v': + verbose = true; + break; + case 'd': + map_unmap_verify = true; + break; + case 's': + targs->nslots = atoi(optarg); + if (targs->nslots <= 0 && targs->nslots != -1) { + pr_info("Slot count cap has to be positive or -1 for no cap\n"); + return false; + } + break; + case 'f': + targs->tfirst = atoi(optarg); + if (targs->tfirst < 0) { + pr_info("First test to run has to be non-negative\n"); + return false; + } + break; + case 'e': + targs->tlast = atoi(optarg); + if (targs->tlast < 0 || targs->tlast >= NTESTS) { + pr_info("Last test to run has to be non-negative and less than %zu\n", + NTESTS); + return false; + } + break; + case 'l': + targs->seconds = atoi(optarg); + if (targs->seconds < 0) { + pr_info("Test length in seconds has to be non-negative\n"); + return false; + } + break; + case 'r': + targs->runs = atoi(optarg); + if (targs->runs <= 0) { + pr_info("Runs per test has to be positive\n"); + return false; + } + break; + } + } + + if (optind < argc) { + help(argv[0], targs); + return false; + } + + if (targs->tfirst > targs->tlast) { + pr_info("First test to run cannot be greater than the last test to run\n"); + return false; + } + + return true; +} + +struct test_result { + struct timespec slot_runtime, guest_runtime, iter_runtime; + int64_t slottimens, runtimens; + uint64_t nloops; +}; + +static bool test_loop(const struct test_data *data, + const struct test_args *targs, + struct test_result *rbestslottime, + struct test_result *rbestruntime) +{ + uint64_t maxslots; + struct test_result result; + + result.nloops = 0; + if (!test_execute(targs->nslots, &maxslots, targs->seconds, data, + &result.nloops, + &result.slot_runtime, &result.guest_runtime)) { + if (maxslots) + pr_info("Memslot count too high for this test, decrease the cap (max is %"PRIu64")\n", + maxslots); + else + pr_info("Memslot count may be too high for this test, try adjusting the cap\n"); + + return false; + } + + pr_info("Test took %ld.%.9lds for slot setup + %ld.%.9lds all iterations\n", + result.slot_runtime.tv_sec, result.slot_runtime.tv_nsec, + result.guest_runtime.tv_sec, result.guest_runtime.tv_nsec); + if (!result.nloops) { + pr_info("No full loops done - too short test time or system too loaded?\n"); + return true; + } + + result.iter_runtime = timespec_div(result.guest_runtime, + result.nloops); + pr_info("Done %"PRIu64" iterations, avg %ld.%.9lds each\n", + result.nloops, + result.iter_runtime.tv_sec, + result.iter_runtime.tv_nsec); + result.slottimens = timespec_to_ns(result.slot_runtime); + result.runtimens = timespec_to_ns(result.iter_runtime); + + /* + * Only rank the slot setup time for tests using the whole test memory + * area so they are comparable + */ + if (!data->mem_size && + (!rbestslottime->slottimens || + result.slottimens < rbestslottime->slottimens)) + *rbestslottime = result; + if (!rbestruntime->runtimens || + result.runtimens < rbestruntime->runtimens) + *rbestruntime = result; + + return true; +} + +int main(int argc, char *argv[]) +{ + struct test_args targs = { + .tfirst = 0, + .tlast = NTESTS - 1, + .nslots = -1, + .seconds = 5, + .runs = 1, + }; + struct test_result rbestslottime; + int tctr; + + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + if (!parse_args(argc, argv, &targs)) + return -1; + + rbestslottime.slottimens = 0; + for (tctr = targs.tfirst; tctr <= targs.tlast; tctr++) { + const struct test_data *data = &tests[tctr]; + unsigned int runctr; + struct test_result rbestruntime; + + if (tctr > targs.tfirst) + pr_info("\n"); + + pr_info("Testing %s performance with %i runs, %d seconds each\n", + data->name, targs.runs, targs.seconds); + + rbestruntime.runtimens = 0; + for (runctr = 0; runctr < targs.runs; runctr++) + if (!test_loop(data, &targs, + &rbestslottime, &rbestruntime)) + break; + + if (rbestruntime.runtimens) + pr_info("Best runtime result was %ld.%.9lds per iteration (with %"PRIu64" iterations)\n", + rbestruntime.iter_runtime.tv_sec, + rbestruntime.iter_runtime.tv_nsec, + rbestruntime.nloops); + } + + if (rbestslottime.slottimens) + pr_info("Best slot setup time for the whole test area was %ld.%.9lds\n", + rbestslottime.slot_runtime.tv_sec, + rbestslottime.slot_runtime.tv_nsec); + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c b/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c index 9b78e8889638..8c77537af5a1 100644 --- a/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c +++ b/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c @@ -19,7 +19,12 @@ struct { u32 function; u32 index; } mangled_cpuids[] = { + /* + * These entries depend on the vCPU's XCR0 register and IA32_XSS MSR, + * which are not controlled for by this test. + */ {.function = 0xd, .index = 0}, + {.function = 0xd, .index = 1}, }; static void test_guest_cpuids(struct kvm_cpuid2 *guest_cpuid) diff --git a/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c b/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c index cb953df4d7d0..8aed0db1331d 100644 --- a/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c +++ b/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c @@ -37,9 +37,7 @@ static void test_get_msr_index(void) int old_res, res, kvm_fd, r; struct kvm_msr_list *list; - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); old_res = kvm_num_index_msrs(kvm_fd, 0); TEST_ASSERT(old_res != 0, "Expecting nmsrs to be > 0"); @@ -101,9 +99,7 @@ static void test_get_msr_feature(void) int res, old_res, i, kvm_fd; struct kvm_msr_list *feature_list; - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); old_res = kvm_num_feature_msrs(kvm_fd, 0); TEST_ASSERT(old_res != 0, "Expecting nmsrs to be > 0"); diff --git a/tools/testing/selftests/nci/.gitignore b/tools/testing/selftests/nci/.gitignore new file mode 100644 index 000000000000..448eeb4590fc --- /dev/null +++ b/tools/testing/selftests/nci/.gitignore @@ -0,0 +1 @@ +/nci_dev diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 76d9487fb03c..5abe92d55b69 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -1384,12 +1384,37 @@ ipv4_rt_replace() ipv4_rt_replace_mpath } +# checks that cached input route on VRF port is deleted +# when VRF is deleted +ipv4_local_rt_cache() +{ + run_cmd "ip addr add 10.0.0.1/32 dev lo" + run_cmd "ip netns add test-ns" + run_cmd "ip link add veth-outside type veth peer name veth-inside" + run_cmd "ip link add vrf-100 type vrf table 1100" + run_cmd "ip link set veth-outside master vrf-100" + run_cmd "ip link set veth-inside netns test-ns" + run_cmd "ip link set veth-outside up" + run_cmd "ip link set vrf-100 up" + run_cmd "ip route add 10.1.1.1/32 dev veth-outside table 1100" + run_cmd "ip netns exec test-ns ip link set veth-inside up" + run_cmd "ip netns exec test-ns ip addr add 10.1.1.1/32 dev veth-inside" + run_cmd "ip netns exec test-ns ip route add 10.0.0.1/32 dev veth-inside" + run_cmd "ip netns exec test-ns ip route add default via 10.0.0.1" + run_cmd "ip netns exec test-ns ping 10.0.0.1 -c 1 -i 1" + run_cmd "ip link delete vrf-100" + + # if we do not hang test is a success + log_test $? 0 "Cached route removed from VRF port device" +} + ipv4_route_test() { route_setup ipv4_rt_add ipv4_rt_replace + ipv4_local_rt_cache route_cleanup } diff --git a/tools/testing/selftests/net/icmp.sh b/tools/testing/selftests/net/icmp.sh new file mode 100755 index 000000000000..e4b04cd1644a --- /dev/null +++ b/tools/testing/selftests/net/icmp.sh @@ -0,0 +1,74 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test for checking ICMP response with dummy address instead of 0.0.0.0. +# Sets up two namespaces like: +# +----------------------+ +--------------------+ +# | ns1 | v4-via-v6 routes: | ns2 | +# | | ' | | +# | +--------+ -> 172.16.1.0/24 -> +--------+ | +# | | veth0 +--------------------------+ veth0 | | +# | +--------+ <- 172.16.0.0/24 <- +--------+ | +# | 172.16.0.1 | | 2001:db8:1::2/64 | +# | 2001:db8:1::2/64 | | | +# +----------------------+ +--------------------+ +# +# And then tries to ping 172.16.1.1 from ns1. This results in a "net +# unreachable" message being sent from ns2, but there is no IPv4 address set in +# that address space, so the kernel should substitute the dummy address +# 192.0.0.8 defined in RFC7600. + +NS1=ns1 +NS2=ns2 +H1_IP=172.16.0.1/32 +H1_IP6=2001:db8:1::1 +RT1=172.16.1.0/24 +PINGADDR=172.16.1.1 +RT2=172.16.0.0/24 +H2_IP6=2001:db8:1::2 + +TMPFILE=$(mktemp) + +cleanup() +{ + rm -f "$TMPFILE" + ip netns del $NS1 + ip netns del $NS2 +} + +trap cleanup EXIT + +# Namespaces +ip netns add $NS1 +ip netns add $NS2 + +# Connectivity +ip -netns $NS1 link add veth0 type veth peer name veth0 netns $NS2 +ip -netns $NS1 link set dev veth0 up +ip -netns $NS2 link set dev veth0 up +ip -netns $NS1 addr add $H1_IP dev veth0 +ip -netns $NS1 addr add $H1_IP6/64 dev veth0 nodad +ip -netns $NS2 addr add $H2_IP6/64 dev veth0 nodad +ip -netns $NS1 route add $RT1 via inet6 $H2_IP6 +ip -netns $NS2 route add $RT2 via inet6 $H1_IP6 + +# Make sure ns2 will respond with ICMP unreachable +ip netns exec $NS2 sysctl -qw net.ipv4.icmp_ratelimit=0 net.ipv4.ip_forward=1 + +# Run the test - a ping runs in the background, and we capture ICMP responses +# with tcpdump; -c 1 means it should exit on the first ping, but add a timeout +# in case something goes wrong +ip netns exec $NS1 ping -w 3 -i 0.5 $PINGADDR >/dev/null & +ip netns exec $NS1 timeout 10 tcpdump -tpni veth0 -c 1 'icmp and icmp[icmptype] != icmp-echo' > $TMPFILE 2>/dev/null + +# Parse response and check for dummy address +# tcpdump output looks like: +# IP 192.0.0.8 > 172.16.0.1: ICMP net 172.16.1.1 unreachable, length 92 +RESP_IP=$(awk '{print $2}' < $TMPFILE) +if [[ "$RESP_IP" != "192.0.0.8" ]]; then + echo "FAIL - got ICMP response from $RESP_IP, should be 192.0.0.8" + exit 1 +else + echo "OK" + exit 0 +fi diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index 3c4cb72ed8a4..2b495dc8d78e 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -197,9 +197,6 @@ ip -net "$ns4" link set ns4eth3 up ip -net "$ns4" route add default via 10.0.3.2 ip -net "$ns4" route add default via dead:beef:3::2 -# use TCP syn cookies, even if no flooding was detected. -ip netns exec "$ns2" sysctl -q net.ipv4.tcp_syncookies=2 - set_ethtool_flags() { local ns="$1" local dev="$2" @@ -501,6 +498,7 @@ do_transfer() local stat_ackrx_now_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") local stat_cookietx_now=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesSent") local stat_cookierx_now=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesRecv") + local stat_ooo_now=$(get_mib_counter "${listener_ns}" "TcpExtTCPOFOQueue") expect_synrx=$((stat_synrx_last_l)) expect_ackrx=$((stat_ackrx_last_l)) @@ -518,10 +516,14 @@ do_transfer() "${stat_synrx_now_l}" "${expect_synrx}" 1>&2 retc=1 fi - if [ ${stat_ackrx_now_l} -lt ${expect_ackrx} ]; then - printf "[ FAIL ] lower MPC ACK rx (%d) than expected (%d)\n" \ - "${stat_ackrx_now_l}" "${expect_ackrx}" 1>&2 - rets=1 + if [ ${stat_ackrx_now_l} -lt ${expect_ackrx} -a ${stat_ooo_now} -eq 0 ]; then + if [ ${stat_ooo_now} -eq 0 ]; then + printf "[ FAIL ] lower MPC ACK rx (%d) than expected (%d)\n" \ + "${stat_ackrx_now_l}" "${expect_ackrx}" 1>&2 + rets=1 + else + printf "[ Note ] fallback due to TCP OoO" + fi fi if [ $retc -eq 0 ] && [ $rets -eq 0 ]; then @@ -732,6 +734,14 @@ for sender in $ns1 $ns2 $ns3 $ns4;do exit $ret fi + # ns1<->ns2 is not subject to reordering/tc delays. Use it to test + # mptcp syncookie support. + if [ $sender = $ns1 ]; then + ip netns exec "$ns2" sysctl -q net.ipv4.tcp_syncookies=2 + else + ip netns exec "$ns2" sysctl -q net.ipv4.tcp_syncookies=1 + fi + run_tests "$ns2" $sender 10.0.1.2 run_tests "$ns2" $sender dead:beef:1::2 run_tests "$ns2" $sender 10.0.2.1 diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh index a8fa64136282..7f26591f236b 100755 --- a/tools/testing/selftests/net/udpgro_fwd.sh +++ b/tools/testing/selftests/net/udpgro_fwd.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 readonly BASE="ns-$(mktemp -u XXXXXX)" diff --git a/tools/testing/selftests/net/veth.sh b/tools/testing/selftests/net/veth.sh index 2fedc0781ce8..11d7cdb898c0 100755 --- a/tools/testing/selftests/net/veth.sh +++ b/tools/testing/selftests/net/veth.sh @@ -18,7 +18,8 @@ ret=0 cleanup() { local ns - local -r jobs="$(jobs -p)" + local jobs + readonly jobs="$(jobs -p)" [ -n "${jobs}" ] && kill -1 ${jobs} 2>/dev/null rm -f $STATS @@ -108,7 +109,7 @@ chk_gro() { if [ ! -f ../bpf/xdp_dummy.o ]; then echo "Missing xdp_dummy helper. Build bpf selftest first" - exit -1 + exit 1 fi create_ns diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index 3171069a6b46..cd6430b39982 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for netfilter selftests -TEST_PROGS := nft_trans_stress.sh nft_nat.sh bridge_brouter.sh \ +TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \ conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \ nft_concat_range.sh nft_conntrack_helper.sh \ nft_queue.sh nft_meta.sh nf_nat_edemux.sh \ diff --git a/tools/testing/selftests/netfilter/nft_fib.sh b/tools/testing/selftests/netfilter/nft_fib.sh new file mode 100755 index 000000000000..6caf6ac8c285 --- /dev/null +++ b/tools/testing/selftests/netfilter/nft_fib.sh @@ -0,0 +1,221 @@ +#!/bin/bash +# +# This tests the fib expression. +# +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 +ret=0 + +sfx=$(mktemp -u "XXXXXXXX") +ns1="ns1-$sfx" +ns2="ns2-$sfx" +nsrouter="nsrouter-$sfx" +timeout=4 + +log_netns=$(sysctl -n net.netfilter.nf_log_all_netns) + +cleanup() +{ + ip netns del ${ns1} + ip netns del ${ns2} + ip netns del ${nsrouter} + + [ $log_netns -eq 0 ] && sysctl -q net.netfilter.nf_log_all_netns=$log_netns +} + +nft --version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without nft tool" + exit $ksft_skip +fi + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +ip netns add ${nsrouter} +if [ $? -ne 0 ];then + echo "SKIP: Could not create net namespace" + exit $ksft_skip +fi + +trap cleanup EXIT + +dmesg | grep -q ' nft_rpfilter: ' +if [ $? -eq 0 ]; then + dmesg -c | grep ' nft_rpfilter: ' + echo "WARN: a previous test run has failed" 1>&2 +fi + +sysctl -q net.netfilter.nf_log_all_netns=1 +ip netns add ${ns1} +ip netns add ${ns2} + +load_ruleset() { + local netns=$1 + +ip netns exec ${netns} nft -f /dev/stdin <<EOF +table inet filter { + chain prerouting { + type filter hook prerouting priority 0; policy accept; + fib saddr . iif oif missing counter log prefix "$netns nft_rpfilter: " drop + } +} +EOF +} + +load_ruleset_count() { + local netns=$1 + +ip netns exec ${netns} nft -f /dev/stdin <<EOF +table inet filter { + chain prerouting { + type filter hook prerouting priority 0; policy accept; + ip daddr 1.1.1.1 fib saddr . iif oif missing counter drop + ip6 daddr 1c3::c01d fib saddr . iif oif missing counter drop + } +} +EOF +} + +check_drops() { + dmesg | grep -q ' nft_rpfilter: ' + if [ $? -eq 0 ]; then + dmesg | grep ' nft_rpfilter: ' + echo "FAIL: rpfilter did drop packets" + return 1 + fi + + return 0 +} + +check_fib_counter() { + local want=$1 + local ns=$2 + local address=$3 + + line=$(ip netns exec ${ns} nft list table inet filter | grep 'fib saddr . iif' | grep $address | grep "packets $want" ) + ret=$? + + if [ $ret -ne 0 ];then + echo "Netns $ns fib counter doesn't match expected packet count of $want for $address" 1>&2 + ip netns exec ${ns} nft list table inet filter + return 1 + fi + + if [ $want -gt 0 ]; then + echo "PASS: fib expression did drop packets for $address" + fi + + return 0 +} + +load_ruleset ${nsrouter} +load_ruleset ${ns1} +load_ruleset ${ns2} + +ip link add veth0 netns ${nsrouter} type veth peer name eth0 netns ${ns1} > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: No virtual ethernet pair device support in kernel" + exit $ksft_skip +fi +ip link add veth1 netns ${nsrouter} type veth peer name eth0 netns ${ns2} + +ip -net ${nsrouter} link set lo up +ip -net ${nsrouter} link set veth0 up +ip -net ${nsrouter} addr add 10.0.1.1/24 dev veth0 +ip -net ${nsrouter} addr add dead:1::1/64 dev veth0 + +ip -net ${nsrouter} link set veth1 up +ip -net ${nsrouter} addr add 10.0.2.1/24 dev veth1 +ip -net ${nsrouter} addr add dead:2::1/64 dev veth1 + +ip -net ${ns1} link set lo up +ip -net ${ns1} link set eth0 up + +ip -net ${ns2} link set lo up +ip -net ${ns2} link set eth0 up + +ip -net ${ns1} addr add 10.0.1.99/24 dev eth0 +ip -net ${ns1} addr add dead:1::99/64 dev eth0 +ip -net ${ns1} route add default via 10.0.1.1 +ip -net ${ns1} route add default via dead:1::1 + +ip -net ${ns2} addr add 10.0.2.99/24 dev eth0 +ip -net ${ns2} addr add dead:2::99/64 dev eth0 +ip -net ${ns2} route add default via 10.0.2.1 +ip -net ${ns2} route add default via dead:2::1 + +test_ping() { + local daddr4=$1 + local daddr6=$2 + + ip netns exec ${ns1} ping -c 1 -q $daddr4 > /dev/null + ret=$? + if [ $ret -ne 0 ];then + check_drops + echo "FAIL: ${ns1} cannot reach $daddr4, ret $ret" 1>&2 + return 1 + fi + + ip netns exec ${ns1} ping -c 3 -q $daddr6 > /dev/null + ret=$? + if [ $ret -ne 0 ];then + check_drops + echo "FAIL: ${ns1} cannot reach $daddr6, ret $ret" 1>&2 + return 1 + fi + + return 0 +} + +ip netns exec ${nsrouter} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null +ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null +ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null + +sleep 3 + +test_ping 10.0.2.1 dead:2::1 || exit 1 +check_drops || exit 1 + +test_ping 10.0.2.99 dead:2::99 || exit 1 +check_drops || exit 1 + +echo "PASS: fib expression did not cause unwanted packet drops" + +ip netns exec ${nsrouter} nft flush table inet filter + +ip -net ${ns1} route del default +ip -net ${ns1} -6 route del default + +ip -net ${ns1} addr del 10.0.1.99/24 dev eth0 +ip -net ${ns1} addr del dead:1::99/64 dev eth0 + +ip -net ${ns1} addr add 10.0.2.99/24 dev eth0 +ip -net ${ns1} addr add dead:2::99/64 dev eth0 + +ip -net ${ns1} route add default via 10.0.2.1 +ip -net ${ns1} -6 route add default via dead:2::1 + +ip -net ${nsrouter} addr add dead:2::1/64 dev veth0 + +# switch to ruleset that doesn't log, this time +# its expected that this does drop the packets. +load_ruleset_count ${nsrouter} + +# ns1 has a default route, but nsrouter does not. +# must not check return value, ping to 1.1.1.1 will +# fail. +check_fib_counter 0 ${nsrouter} 1.1.1.1 || exit 1 +check_fib_counter 0 ${nsrouter} 1c3::c01d || exit 1 + +ip netns exec ${ns1} ping -c 1 -W 1 -q 1.1.1.1 > /dev/null +check_fib_counter 1 ${nsrouter} 1.1.1.1 || exit 1 + +sleep 2 +ip netns exec ${ns1} ping -c 3 -q 1c3::c01d > /dev/null +check_fib_counter 3 ${nsrouter} 1c3::c01d || exit 1 + +exit 0 diff --git a/tools/testing/selftests/proc/.gitignore b/tools/testing/selftests/proc/.gitignore index bed4b5318a86..8f3e72e626fa 100644 --- a/tools/testing/selftests/proc/.gitignore +++ b/tools/testing/selftests/proc/.gitignore @@ -10,6 +10,7 @@ /proc-self-map-files-002 /proc-self-syscall /proc-self-wchan +/proc-subset-pid /proc-uptime-001 /proc-uptime-002 /read diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json index 1cda2e11b3ad..773c5027553d 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json @@ -9,11 +9,11 @@ "setup": [ "$IP link add dev $DUMMY type dummy || /bin/true" ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY root fq_pie flows 65536", - "expExitCode": "2", + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq_pie flows 65536", + "expExitCode": "0", "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc", - "matchCount": "0", + "matchPattern": "qdisc fq_pie 1: root refcnt 2 limit 10240p flows 65536", + "matchCount": "1", "teardown": [ "$IP link del dev $DUMMY" ] diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index 7ed7cd95e58f..ebc4ee0fe179 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -363,6 +363,7 @@ ip1 -6 rule add table main suppress_prefixlength 0 ip1 -4 route add default dev wg0 table 51820 ip1 -4 rule add not fwmark 51820 table 51820 ip1 -4 rule add table main suppress_prefixlength 0 +n1 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/vethc/rp_filter' # Flood the pings instead of sending just one, to trigger routing table reference counting bugs. n1 ping -W 1 -c 100 -f 192.168.99.7 n1 ping -W 1 -c 100 -f abab::1111 diff --git a/tools/testing/selftests/wireguard/qemu/kernel.config b/tools/testing/selftests/wireguard/qemu/kernel.config index 4eecb432a66c..74db83a0aedd 100644 --- a/tools/testing/selftests/wireguard/qemu/kernel.config +++ b/tools/testing/selftests/wireguard/qemu/kernel.config @@ -19,7 +19,6 @@ CONFIG_NETFILTER_XTABLES=y CONFIG_NETFILTER_XT_NAT=y CONFIG_NETFILTER_XT_MATCH_LENGTH=y CONFIG_NETFILTER_XT_MARK=y -CONFIG_NF_CONNTRACK_IPV4=y CONFIG_NF_NAT_IPV4=y CONFIG_IP_NF_IPTABLES=y CONFIG_IP_NF_FILTER=y |