diff options
Diffstat (limited to 'tools')
345 files changed, 35867 insertions, 3301 deletions
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 578793e..fb00a2f 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -198,7 +198,6 @@ #define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */ #define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */ #define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */ - #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ #define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ @@ -207,13 +206,19 @@ #define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */ - +#define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */ +#define X86_FEATURE_SSBD ( 7*32+17) /* Speculative Store Bypass Disable */ #define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ #define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */ #define X86_FEATURE_SEV ( 7*32+20) /* AMD Secure Encrypted Virtualization */ - #define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ #define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */ +#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* "" Disable Speculative Store Bypass. */ +#define X86_FEATURE_LS_CFG_SSBD ( 7*32+24) /* "" AMD SSBD implementation via LS_CFG MSR */ +#define X86_FEATURE_IBRS ( 7*32+25) /* Indirect Branch Restricted Speculation */ +#define X86_FEATURE_IBPB ( 7*32+26) /* Indirect Branch Prediction Barrier */ +#define X86_FEATURE_STIBP ( 7*32+27) /* Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_ZEN ( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ @@ -274,9 +279,10 @@ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ #define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */ #define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */ -#define X86_FEATURE_IBPB (13*32+12) /* Indirect Branch Prediction Barrier */ -#define X86_FEATURE_IBRS (13*32+14) /* Indirect Branch Restricted Speculation */ -#define X86_FEATURE_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_AMD_IBPB (13*32+12) /* "" Indirect Branch Prediction Barrier */ +#define X86_FEATURE_AMD_IBRS (13*32+14) /* "" Indirect Branch Restricted Speculation */ +#define X86_FEATURE_AMD_STIBP (13*32+15) /* "" Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ #define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ @@ -334,6 +340,7 @@ #define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ #define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ #define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */ +#define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* "" Speculative Store Bypass Disable */ /* * BUG word(s) @@ -363,5 +370,6 @@ #define X86_BUG_CPU_MELTDOWN X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */ #define X86_BUG_SPECTRE_V1 X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */ #define X86_BUG_SPECTRE_V2 X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */ +#define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* CPU is affected by speculative store bypass attack */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/bpf/bpf_exp.l b/tools/bpf/bpf_exp.l index bd83149..4da8d05 100644 --- a/tools/bpf/bpf_exp.l +++ b/tools/bpf/bpf_exp.l @@ -175,7 +175,7 @@ extern void yyerror(const char *str); yylval.number = strtol(yytext, NULL, 10); return number; } -([0][0-9]+) { +([0][0-7]+) { yylval.number = strtol(yytext + 1, NULL, 8); return number; } diff --git a/tools/bpf/bpftool/.gitignore b/tools/bpf/bpftool/.gitignore new file mode 100644 index 0000000..d7e678c --- /dev/null +++ b/tools/bpf/bpftool/.gitignore @@ -0,0 +1,3 @@ +*.d +bpftool +FEATURE-DUMP.bpftool diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst index 0e4e923..7b0e6d4 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst @@ -26,7 +26,9 @@ MAP COMMANDS | **bpftool** **cgroup help** | | *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } -| *ATTACH_TYPE* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** } +| *ATTACH_TYPE* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** | +| **bind4** | **bind6** | **post_bind4** | **post_bind6** | **connect4** | **connect6** | +| **sendmsg4** | **sendmsg6** } | *ATTACH_FLAGS* := { **multi** | **override** } DESCRIPTION @@ -63,7 +65,17 @@ DESCRIPTION **egress** egress path of the inet socket (since 4.10); **sock_create** opening of an inet socket (since 4.10); **sock_ops** various socket operations (since 4.12); - **device** device access (since 4.15). + **device** device access (since 4.15); + **bind4** call to bind(2) for an inet4 socket (since 4.17); + **bind6** call to bind(2) for an inet6 socket (since 4.17); + **post_bind4** return from bind(2) for an inet4 socket (since 4.17); + **post_bind6** return from bind(2) for an inet6 socket (since 4.17); + **connect4** call to connect(2) for an inet4 socket (since 4.17); + **connect6** call to connect(2) for an inet6 socket (since 4.17); + **sendmsg4** call to sendto(2), sendmsg(2), sendmmsg(2) for an + unconnected udp4 socket (since 4.18); + **sendmsg6** call to sendto(2), sendmsg(2), sendmmsg(2) for an + unconnected udp6 socket (since 4.18). **bpftool cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG* Detach *PROG* from the cgroup *CGROUP* and attach type diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 457e868..a6258bc 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -22,17 +22,19 @@ MAP COMMANDS ============= | **bpftool** **map { show | list }** [*MAP*] -| **bpftool** **map dump** *MAP* -| **bpftool** **map update** *MAP* **key** *BYTES* **value** *VALUE* [*UPDATE_FLAGS*] -| **bpftool** **map lookup** *MAP* **key** *BYTES* -| **bpftool** **map getnext** *MAP* [**key** *BYTES*] -| **bpftool** **map delete** *MAP* **key** *BYTES* -| **bpftool** **map pin** *MAP* *FILE* +| **bpftool** **map dump** *MAP* +| **bpftool** **map update** *MAP* **key** *DATA* **value** *VALUE* [*UPDATE_FLAGS*] +| **bpftool** **map lookup** *MAP* **key** *DATA* +| **bpftool** **map getnext** *MAP* [**key** *DATA*] +| **bpftool** **map delete** *MAP* **key** *DATA* +| **bpftool** **map pin** *MAP* *FILE* +| **bpftool** **map event_pipe** *MAP* [**cpu** *N* **index** *M*] | **bpftool** **map help** | | *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } +| *DATA* := { [**hex**] *BYTES* } | *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } -| *VALUE* := { *BYTES* | *MAP* | *PROG* } +| *VALUE* := { *DATA* | *MAP* | *PROG* } | *UPDATE_FLAGS* := { **any** | **exist** | **noexist** } DESCRIPTION @@ -48,20 +50,26 @@ DESCRIPTION **bpftool map dump** *MAP* Dump all entries in a given *MAP*. - **bpftool map update** *MAP* **key** *BYTES* **value** *VALUE* [*UPDATE_FLAGS*] + **bpftool map update** *MAP* **key** *DATA* **value** *VALUE* [*UPDATE_FLAGS*] Update map entry for a given *KEY*. *UPDATE_FLAGS* can be one of: **any** update existing entry or add if doesn't exit; **exist** update only if entry already exists; **noexist** update only if entry doesn't exist. - **bpftool map lookup** *MAP* **key** *BYTES* + If the **hex** keyword is provided in front of the bytes + sequence, the bytes are parsed as hexadeximal values, even if + no "0x" prefix is added. If the keyword is not provided, then + the bytes are parsed as decimal values, unless a "0x" prefix + (for hexadecimal) or a "0" prefix (for octal) is provided. + + **bpftool map lookup** *MAP* **key** *DATA* Lookup **key** in the map. - **bpftool map getnext** *MAP* [**key** *BYTES*] + **bpftool map getnext** *MAP* [**key** *DATA*] Get next key. If *key* is not specified, get first key. - **bpftool map delete** *MAP* **key** *BYTES* + **bpftool map delete** *MAP* **key** *DATA* Remove entry from the map. **bpftool map pin** *MAP* *FILE* @@ -69,6 +77,22 @@ DESCRIPTION Note: *FILE* must be located in *bpffs* mount. + **bpftool** **map event_pipe** *MAP* [**cpu** *N* **index** *M*] + Read events from a BPF_MAP_TYPE_PERF_EVENT_ARRAY map. + + Install perf rings into a perf event array map and dump + output of any bpf_perf_event_output() call in the kernel. + By default read the number of CPUs on the system and + install perf ring for each CPU in the corresponding index + in the array. + + If **cpu** and **index** are specified, install perf ring + for given **cpu** at **index** in the array (single ring). + + Note that installing a perf ring into an array will silently + replace any existing ring. Any other application will stop + receiving events if it installed its rings earlier. + **bpftool map help** Print short help message. @@ -98,7 +122,12 @@ EXAMPLES 10: hash name some_map flags 0x0 key 4B value 8B max_entries 2048 memlock 167936B -**# bpftool map update id 10 key 13 00 07 00 value 02 00 00 00 01 02 03 04** +The following three commands are equivalent: + +| +| **# bpftool map update id 10 key hex 20 c4 b7 00 value hex 0f ff ff ab 01 02 03 4c** +| **# bpftool map update id 10 key 0x20 0xc4 0xb7 0x00 value 0x0f 0xff 0xff 0xab 0x01 0x02 0x03 0x4c** +| **# bpftool map update id 10 key 32 196 183 0 value 15 255 255 171 1 2 3 76** **# bpftool map lookup id 10 key 0 1 2 3** diff --git a/tools/bpf/bpftool/Documentation/bpftool-perf.rst b/tools/bpf/bpftool/Documentation/bpftool-perf.rst new file mode 100644 index 0000000..e3eb0ea --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-perf.rst @@ -0,0 +1,81 @@ +================ +bpftool-perf +================ +------------------------------------------------------------------------------- +tool for inspection of perf related bpf prog attachments +------------------------------------------------------------------------------- + +:Manual section: 8 + +SYNOPSIS +======== + + **bpftool** [*OPTIONS*] **perf** *COMMAND* + + *OPTIONS* := { [{ **-j** | **--json** }] [{ **-p** | **--pretty** }] } + + *COMMANDS* := + { **show** | **list** | **help** } + +PERF COMMANDS +============= + +| **bpftool** **perf { show | list }** +| **bpftool** **perf help** + +DESCRIPTION +=========== + **bpftool perf { show | list }** + List all raw_tracepoint, tracepoint, kprobe attachment in the system. + + Output will start with process id and file descriptor in that process, + followed by bpf program id, attachment information, and attachment point. + The attachment point for raw_tracepoint/tracepoint is the trace probe name. + The attachment point for k[ret]probe is either symbol name and offset, + or a kernel virtual address. + The attachment point for u[ret]probe is the file name and the file offset. + + **bpftool perf help** + Print short help message. + +OPTIONS +======= + -h, --help + Print short generic help message (similar to **bpftool help**). + + -v, --version + Print version number (similar to **bpftool version**). + + -j, --json + Generate JSON output. For commands that cannot produce JSON, this + option has no effect. + + -p, --pretty + Generate human-readable JSON output. Implies **-j**. + +EXAMPLES +======== + +| **# bpftool perf** + +:: + + pid 21711 fd 5: prog_id 5 kprobe func __x64_sys_write offset 0 + pid 21765 fd 5: prog_id 7 kretprobe func __x64_sys_nanosleep offset 0 + pid 21767 fd 5: prog_id 8 tracepoint sys_enter_nanosleep + pid 21800 fd 5: prog_id 9 uprobe filename /home/yhs/a.out offset 1159 + +| +| **# bpftool -j perf** + +:: + + [{"pid":21711,"fd":5,"prog_id":5,"fd_type":"kprobe","func":"__x64_sys_write","offset":0}, \ + {"pid":21765,"fd":5,"prog_id":7,"fd_type":"kretprobe","func":"__x64_sys_nanosleep","offset":0}, \ + {"pid":21767,"fd":5,"prog_id":8,"fd_type":"tracepoint","tracepoint":"sys_enter_nanosleep"}, \ + {"pid":21800,"fd":5,"prog_id":9,"fd_type":"uprobe","filename":"/home/yhs/a.out","offset":1159}] + + +SEE ALSO +======== + **bpftool**\ (8), **bpftool-prog**\ (8), **bpftool-map**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 67ca6c6..43d34a5 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -95,7 +95,7 @@ EXAMPLES **# bpftool prog show** :: - 10: xdp name some_prog tag 005a3d2123620c8b + 10: xdp name some_prog tag 005a3d2123620c8b gpl loaded_at Sep 29/20:11 uid 0 xlated 528B jited 370B memlock 4096B map_ids 10 @@ -108,6 +108,7 @@ EXAMPLES "id": 10, "type": "xdp", "tag": "005a3d2123620c8b", + "gpl_compatible": true, "loaded_at": "Sep 29/20:11", "uid": 0, "bytes_xlated": 528, diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst index 20689a3..b6f5d56 100644 --- a/tools/bpf/bpftool/Documentation/bpftool.rst +++ b/tools/bpf/bpftool/Documentation/bpftool.rst @@ -16,20 +16,22 @@ SYNOPSIS **bpftool** **version** - *OBJECT* := { **map** | **program** | **cgroup** } + *OBJECT* := { **map** | **program** | **cgroup** | **perf** } *OPTIONS* := { { **-V** | **--version** } | { **-h** | **--help** } | { **-j** | **--json** } [{ **-p** | **--pretty** }] } *MAP-COMMANDS* := { **show** | **list** | **dump** | **update** | **lookup** | **getnext** | **delete** - | **pin** | **help** } + | **pin** | **event_pipe** | **help** } *PROG-COMMANDS* := { **show** | **list** | **dump jited** | **dump xlated** | **pin** | **load** | **help** } *CGROUP-COMMANDS* := { **show** | **list** | **attach** | **detach** | **help** } + *PERF-COMMANDS* := { **show** | **list** | **help** } + DESCRIPTION =========== *bpftool* allows for inspection and simple modification of BPF objects @@ -56,3 +58,4 @@ OPTIONS SEE ALSO ======== **bpftool-map**\ (8), **bpftool-prog**\ (8), **bpftool-cgroup**\ (8) + **bpftool-perf**\ (8) diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index 4e69782..892dbf0 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -39,7 +39,12 @@ CC = gcc CFLAGS += -O2 CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wshadow -Wno-missing-field-initializers -CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ -I$(srctree)/tools/include/uapi -I$(srctree)/tools/include -I$(srctree)/tools/lib/bpf -I$(srctree)/kernel/bpf/ +CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \ + -I$(srctree)/kernel/bpf/ \ + -I$(srctree)/tools/include \ + -I$(srctree)/tools/include/uapi \ + -I$(srctree)/tools/lib/bpf \ + -I$(srctree)/tools/perf CFLAGS += -DBPFTOOL_VERSION='"$(BPFTOOL_VERSION)"' LIBS = -lelf -lbfd -lopcodes $(LIBBPF) diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 490811b..1e10833 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -1,6 +1,6 @@ # bpftool(8) bash completion -*- shell-script -*- # -# Copyright (C) 2017 Netronome Systems, Inc. +# Copyright (C) 2017-2018 Netronome Systems, Inc. # # This software is dual licensed under the GNU General License # Version 2, June 1991 as shown in the file COPYING in the top-level @@ -79,6 +79,14 @@ _bpftool_get_map_ids() command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) } +_bpftool_get_perf_map_ids() +{ + COMPREPLY+=( $( compgen -W "$( bpftool -jp map 2>&1 | \ + command grep -C2 perf_event_array | \ + command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) +} + + _bpftool_get_prog_ids() { COMPREPLY+=( $( compgen -W "$( bpftool -jp prog 2>&1 | \ @@ -147,7 +155,7 @@ _bpftool() # Deal with simplest keywords case $prev in - help|key|opcodes|visual) + help|hex|opcodes|visual) return 0 ;; tag) @@ -283,7 +291,7 @@ _bpftool() return 0 ;; key) - return 0 + COMPREPLY+=( $( compgen -W 'hex' -- "$cur" ) ) ;; *) _bpftool_once_attr 'key' @@ -302,7 +310,7 @@ _bpftool() return 0 ;; key) - return 0 + COMPREPLY+=( $( compgen -W 'hex' -- "$cur" ) ) ;; value) # We can have bytes, or references to a prog or a @@ -321,6 +329,8 @@ _bpftool() return 0 ;; *) + COMPREPLY+=( $( compgen -W 'hex' \ + -- "$cur" ) ) return 0 ;; esac @@ -357,10 +367,34 @@ _bpftool() fi return 0 ;; + event_pipe) + case $prev in + $command) + COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) + return 0 + ;; + id) + _bpftool_get_perf_map_ids + return 0 + ;; + cpu) + return 0 + ;; + index) + return 0 + ;; + *) + _bpftool_once_attr 'cpu' + _bpftool_once_attr 'index' + return 0 + ;; + esac + ;; *) [[ $prev == $object ]] && \ COMPREPLY=( $( compgen -W 'delete dump getnext help \ - lookup pin show list update' -- "$cur" ) ) + lookup pin event_pipe show list update' -- \ + "$cur" ) ) ;; esac ;; @@ -372,7 +406,8 @@ _bpftool() ;; attach|detach) local ATTACH_TYPES='ingress egress sock_create sock_ops \ - device' + device bind4 bind6 post_bind4 post_bind6 connect4 \ + connect6 sendmsg4 sendmsg6' local ATTACH_FLAGS='multi override' local PROG_TYPE='id pinned tag' case $prev in @@ -380,7 +415,9 @@ _bpftool() _filedir return 0 ;; - ingress|egress|sock_create|sock_ops|device) + ingress|egress|sock_create|sock_ops|device|bind4|bind6|\ + post_bind4|post_bind6|connect4|connect6|sendmsg4|\ + sendmsg6) COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \ "$cur" ) ) return 0 @@ -412,6 +449,15 @@ _bpftool() ;; esac ;; + perf) + case $command in + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'help \ + show list' -- "$cur" ) ) + ;; + esac + ;; esac } && complete -F _bpftool bpftool diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index cae32a6..16bee01 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -16,8 +16,11 @@ #define HELP_SPEC_ATTACH_FLAGS \ "ATTACH_FLAGS := { multi | override }" -#define HELP_SPEC_ATTACH_TYPES \ - "ATTACH_TYPE := { ingress | egress | sock_create | sock_ops | device }" +#define HELP_SPEC_ATTACH_TYPES \ + " ATTACH_TYPE := { ingress | egress | sock_create |\n" \ + " sock_ops | device | bind4 | bind6 |\n" \ + " post_bind4 | post_bind6 | connect4 |\n" \ + " connect6 | sendmsg4 | sendmsg6 }" static const char * const attach_type_strings[] = { [BPF_CGROUP_INET_INGRESS] = "ingress", @@ -25,6 +28,14 @@ static const char * const attach_type_strings[] = { [BPF_CGROUP_INET_SOCK_CREATE] = "sock_create", [BPF_CGROUP_SOCK_OPS] = "sock_ops", [BPF_CGROUP_DEVICE] = "device", + [BPF_CGROUP_INET4_BIND] = "bind4", + [BPF_CGROUP_INET6_BIND] = "bind6", + [BPF_CGROUP_INET4_CONNECT] = "connect4", + [BPF_CGROUP_INET6_CONNECT] = "connect6", + [BPF_CGROUP_INET4_POST_BIND] = "post_bind4", + [BPF_CGROUP_INET6_POST_BIND] = "post_bind6", + [BPF_CGROUP_UDP4_SENDMSG] = "sendmsg4", + [BPF_CGROUP_UDP6_SENDMSG] = "sendmsg6", [__MAX_BPF_ATTACH_TYPE] = NULL, }; @@ -282,7 +293,7 @@ static int do_help(int argc, char **argv) " %s %s detach CGROUP ATTACH_TYPE PROG\n" " %s %s help\n" "\n" - " " HELP_SPEC_ATTACH_TYPES "\n" + HELP_SPEC_ATTACH_TYPES "\n" " " HELP_SPEC_ATTACH_FLAGS "\n" " " HELP_SPEC_PROGRAM "\n" " " HELP_SPEC_OPTIONS "\n" diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 4659952..32f9e39 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2017 Netronome Systems, Inc. + * Copyright (C) 2017-2018 Netronome Systems, Inc. * * This software is dual licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this @@ -33,6 +33,7 @@ /* Author: Jakub Kicinski <kubakici@wp.pl> */ +#include <ctype.h> #include <errno.h> #include <fcntl.h> #include <fts.h> @@ -330,6 +331,16 @@ char *get_fdinfo(int fd, const char *key) return NULL; } +void print_data_json(uint8_t *data, size_t len) +{ + unsigned int i; + + jsonw_start_array(json_wtr); + for (i = 0; i < len; i++) + jsonw_printf(json_wtr, "%d", data[i]); + jsonw_end_array(json_wtr); +} + void print_hex_data_json(uint8_t *data, size_t len) { unsigned int i; @@ -420,6 +431,70 @@ void delete_pinned_obj_table(struct pinned_obj_table *tab) } } +unsigned int get_page_size(void) +{ + static int result; + + if (!result) + result = getpagesize(); + return result; +} + +unsigned int get_possible_cpus(void) +{ + static unsigned int result; + char buf[128]; + long int n; + char *ptr; + int fd; + + if (result) + return result; + + fd = open("/sys/devices/system/cpu/possible", O_RDONLY); + if (fd < 0) { + p_err("can't open sysfs possible cpus"); + exit(-1); + } + + n = read(fd, buf, sizeof(buf)); + if (n < 2) { + p_err("can't read sysfs possible cpus"); + exit(-1); + } + close(fd); + + if (n == sizeof(buf)) { + p_err("read sysfs possible cpus overflow"); + exit(-1); + } + + ptr = buf; + n = 0; + while (*ptr && *ptr != '\n') { + unsigned int a, b; + + if (sscanf(ptr, "%u-%u", &a, &b) == 2) { + n += b - a + 1; + + ptr = strchr(ptr, '-') + 1; + } else if (sscanf(ptr, "%u", &a) == 1) { + n++; + } else { + assert(0); + } + + while (isdigit(*ptr)) + ptr++; + if (*ptr == ',') + ptr++; + } + + result = n; + + return result; +} + static char * ifindex_to_name_ns(__u32 ifindex, __u32 ns_dev, __u32 ns_ino, char *buf) { diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index 1ec852d..eea7f14 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -87,7 +87,7 @@ static int do_help(int argc, char **argv) " %s batch file FILE\n" " %s version\n" "\n" - " OBJECT := { prog | map | cgroup }\n" + " OBJECT := { prog | map | cgroup | perf }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, bin_name, bin_name); @@ -216,6 +216,7 @@ static const struct cmd cmds[] = { { "prog", do_prog }, { "map", do_map }, { "cgroup", do_cgroup }, + { "perf", do_perf }, { "version", do_version }, { 0 } }; diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index b8e9584..63fdb31 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2017 Netronome Systems, Inc. + * Copyright (C) 2017-2018 Netronome Systems, Inc. * * This software is dual licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this @@ -117,14 +117,20 @@ int do_pin_fd(int fd, const char *name); int do_prog(int argc, char **arg); int do_map(int argc, char **arg); +int do_event_pipe(int argc, char **argv); int do_cgroup(int argc, char **arg); +int do_perf(int argc, char **arg); int prog_parse_fd(int *argc, char ***argv); +int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len); void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, const char *arch); +void print_data_json(uint8_t *data, size_t len); void print_hex_data_json(uint8_t *data, size_t len); +unsigned int get_page_size(void); +unsigned int get_possible_cpus(void); const char *ifindex_to_bfd_name_ns(__u32 ifindex, __u64 ns_dev, __u64 ns_ino); #endif diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index f509c86..097b1a5 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2017 Netronome Systems, Inc. + * Copyright (C) 2017-2018 Netronome Systems, Inc. * * This software is dual licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this @@ -34,7 +34,6 @@ /* Author: Jakub Kicinski <kubakici@wp.pl> */ #include <assert.h> -#include <ctype.h> #include <errno.h> #include <fcntl.h> #include <stdbool.h> @@ -67,63 +66,9 @@ static const char * const map_type_name[] = { [BPF_MAP_TYPE_DEVMAP] = "devmap", [BPF_MAP_TYPE_SOCKMAP] = "sockmap", [BPF_MAP_TYPE_CPUMAP] = "cpumap", + [BPF_MAP_TYPE_SOCKHASH] = "sockhash", }; -static unsigned int get_possible_cpus(void) -{ - static unsigned int result; - char buf[128]; - long int n; - char *ptr; - int fd; - - if (result) - return result; - - fd = open("/sys/devices/system/cpu/possible", O_RDONLY); - if (fd < 0) { - p_err("can't open sysfs possible cpus"); - exit(-1); - } - - n = read(fd, buf, sizeof(buf)); - if (n < 2) { - p_err("can't read sysfs possible cpus"); - exit(-1); - } - close(fd); - - if (n == sizeof(buf)) { - p_err("read sysfs possible cpus overflow"); - exit(-1); - } - - ptr = buf; - n = 0; - while (*ptr && *ptr != '\n') { - unsigned int a, b; - - if (sscanf(ptr, "%u-%u", &a, &b) == 2) { - n += b - a + 1; - - ptr = strchr(ptr, '-') + 1; - } else if (sscanf(ptr, "%u", &a) == 1) { - n++; - } else { - assert(0); - } - - while (isdigit(*ptr)) - ptr++; - if (*ptr == ',') - ptr++; - } - - result = n; - - return result; -} - static bool map_is_per_cpu(__u32 type) { return type == BPF_MAP_TYPE_PERCPU_HASH || @@ -186,8 +131,7 @@ static int map_parse_fd(int *argc, char ***argv) return -1; } -static int -map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len) +int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len) { int err; int fd; @@ -283,11 +227,16 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, static char **parse_bytes(char **argv, const char *name, unsigned char *val, unsigned int n) { - unsigned int i = 0; + unsigned int i = 0, base = 0; char *endptr; + if (is_prefix(*argv, "hex")) { + base = 16; + argv++; + } + while (i < n && argv[i]) { - val[i] = strtoul(argv[i], &endptr, 0); + val[i] = strtoul(argv[i], &endptr, base); if (*endptr) { p_err("error parsing byte: %s", argv[i]); return NULL; @@ -868,23 +817,25 @@ static int do_help(int argc, char **argv) fprintf(stderr, "Usage: %s %s { show | list } [MAP]\n" - " %s %s dump MAP\n" - " %s %s update MAP key BYTES value VALUE [UPDATE_FLAGS]\n" - " %s %s lookup MAP key BYTES\n" - " %s %s getnext MAP [key BYTES]\n" - " %s %s delete MAP key BYTES\n" - " %s %s pin MAP FILE\n" + " %s %s dump MAP\n" + " %s %s update MAP key DATA value VALUE [UPDATE_FLAGS]\n" + " %s %s lookup MAP key DATA\n" + " %s %s getnext MAP [key DATA]\n" + " %s %s delete MAP key DATA\n" + " %s %s pin MAP FILE\n" + " %s %s event_pipe MAP [cpu N index M]\n" " %s %s help\n" "\n" " MAP := { id MAP_ID | pinned FILE }\n" + " DATA := { [hex] BYTES }\n" " " HELP_SPEC_PROGRAM "\n" - " VALUE := { BYTES | MAP | PROG }\n" + " VALUE := { DATA | MAP | PROG }\n" " UPDATE_FLAGS := { any | exist | noexist }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], - bin_name, argv[-2], bin_name, argv[-2]); + bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2]); return 0; } @@ -899,6 +850,7 @@ static const struct cmd cmds[] = { { "getnext", do_getnext }, { "delete", do_delete }, { "pin", do_pin }, + { "event_pipe", do_event_pipe }, { 0 } }; diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c new file mode 100644 index 0000000..1832100 --- /dev/null +++ b/tools/bpf/bpftool/map_perf_ring.c @@ -0,0 +1,306 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2018 Netronome Systems, Inc. */ +/* This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <errno.h> +#include <fcntl.h> +#include <libbpf.h> +#include <poll.h> +#include <signal.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <time.h> +#include <unistd.h> +#include <linux/bpf.h> +#include <linux/perf_event.h> +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <sys/syscall.h> + +#include <bpf.h> +#include <perf-sys.h> + +#include "main.h" + +#define MMAP_PAGE_CNT 16 + +static bool stop; + +struct event_ring_info { + int fd; + int key; + unsigned int cpu; + void *mem; +}; + +struct perf_event_sample { + struct perf_event_header header; + u64 time; + __u32 size; + unsigned char data[]; +}; + +static void int_exit(int signo) +{ + fprintf(stderr, "Stopping...\n"); + stop = true; +} + +static enum bpf_perf_event_ret print_bpf_output(void *event, void *priv) +{ + struct event_ring_info *ring = priv; + struct perf_event_sample *e = event; + struct { + struct perf_event_header header; + __u64 id; + __u64 lost; + } *lost = event; + + if (json_output) { + jsonw_start_object(json_wtr); + jsonw_name(json_wtr, "type"); + jsonw_uint(json_wtr, e->header.type); + jsonw_name(json_wtr, "cpu"); + jsonw_uint(json_wtr, ring->cpu); + jsonw_name(json_wtr, "index"); + jsonw_uint(json_wtr, ring->key); + if (e->header.type == PERF_RECORD_SAMPLE) { + jsonw_name(json_wtr, "timestamp"); + jsonw_uint(json_wtr, e->time); + jsonw_name(json_wtr, "data"); + print_data_json(e->data, e->size); + } else if (e->header.type == PERF_RECORD_LOST) { + jsonw_name(json_wtr, "lost"); + jsonw_start_object(json_wtr); + jsonw_name(json_wtr, "id"); + jsonw_uint(json_wtr, lost->id); + jsonw_name(json_wtr, "count"); + jsonw_uint(json_wtr, lost->lost); + jsonw_end_object(json_wtr); + } + jsonw_end_object(json_wtr); + } else { + if (e->header.type == PERF_RECORD_SAMPLE) { + printf("== @%lld.%09lld CPU: %d index: %d =====\n", + e->time / 1000000000ULL, e->time % 1000000000ULL, + ring->cpu, ring->key); + fprint_hex(stdout, e->data, e->size, " "); + printf("\n"); + } else if (e->header.type == PERF_RECORD_LOST) { + printf("lost %lld events\n", lost->lost); + } else { + printf("unknown event type=%d size=%d\n", + e->header.type, e->header.size); + } + } + + return LIBBPF_PERF_EVENT_CONT; +} + +static void +perf_event_read(struct event_ring_info *ring, void **buf, size_t *buf_len) +{ + enum bpf_perf_event_ret ret; + + ret = bpf_perf_event_read_simple(ring->mem, + MMAP_PAGE_CNT * get_page_size(), + get_page_size(), buf, buf_len, + print_bpf_output, ring); + if (ret != LIBBPF_PERF_EVENT_CONT) { + fprintf(stderr, "perf read loop failed with %d\n", ret); + stop = true; + } +} + +static int perf_mmap_size(void) +{ + return get_page_size() * (MMAP_PAGE_CNT + 1); +} + +static void *perf_event_mmap(int fd) +{ + int mmap_size = perf_mmap_size(); + void *base; + + base = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + if (base == MAP_FAILED) { + p_err("event mmap failed: %s\n", strerror(errno)); + return NULL; + } + + return base; +} + +static void perf_event_unmap(void *mem) +{ + if (munmap(mem, perf_mmap_size())) + fprintf(stderr, "Can't unmap ring memory!\n"); +} + +static int bpf_perf_event_open(int map_fd, int key, int cpu) +{ + struct perf_event_attr attr = { + .sample_type = PERF_SAMPLE_RAW | PERF_SAMPLE_TIME, + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_BPF_OUTPUT, + }; + int pmu_fd; + + pmu_fd = sys_perf_event_open(&attr, -1, cpu, -1, 0); + if (pmu_fd < 0) { + p_err("failed to open perf event %d for CPU %d", key, cpu); + return -1; + } + + if (bpf_map_update_elem(map_fd, &key, &pmu_fd, BPF_ANY)) { + p_err("failed to update map for event %d for CPU %d", key, cpu); + goto err_close; + } + if (ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) { + p_err("failed to enable event %d for CPU %d", key, cpu); + goto err_close; + } + + return pmu_fd; + +err_close: + close(pmu_fd); + return -1; +} + +int do_event_pipe(int argc, char **argv) +{ + int i, nfds, map_fd, index = -1, cpu = -1; + struct bpf_map_info map_info = {}; + struct event_ring_info *rings; + size_t tmp_buf_sz = 0; + void *tmp_buf = NULL; + struct pollfd *pfds; + __u32 map_info_len; + bool do_all = true; + + map_info_len = sizeof(map_info); + map_fd = map_parse_fd_and_info(&argc, &argv, &map_info, &map_info_len); + if (map_fd < 0) + return -1; + + if (map_info.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) { + p_err("map is not a perf event array"); + goto err_close_map; + } + + while (argc) { + if (argc < 2) + BAD_ARG(); + + if (is_prefix(*argv, "cpu")) { + char *endptr; + + NEXT_ARG(); + cpu = strtoul(*argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as CPU ID", **argv); + goto err_close_map; + } + + NEXT_ARG(); + } else if (is_prefix(*argv, "index")) { + char *endptr; + + NEXT_ARG(); + index = strtoul(*argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as index", **argv); + goto err_close_map; + } + + NEXT_ARG(); + } else { + BAD_ARG(); + } + + do_all = false; + } + + if (!do_all) { + if (index == -1 || cpu == -1) { + p_err("cpu and index must be specified together"); + goto err_close_map; + } + + nfds = 1; + } else { + nfds = min(get_possible_cpus(), map_info.max_entries); + cpu = 0; + index = 0; + } + + rings = calloc(nfds, sizeof(rings[0])); + if (!rings) + goto err_close_map; + + pfds = calloc(nfds, sizeof(pfds[0])); + if (!pfds) + goto err_free_rings; + + for (i = 0; i < nfds; i++) { + rings[i].cpu = cpu + i; + rings[i].key = index + i; + + rings[i].fd = bpf_perf_event_open(map_fd, rings[i].key, + rings[i].cpu); + if (rings[i].fd < 0) + goto err_close_fds_prev; + + rings[i].mem = perf_event_mmap(rings[i].fd); + if (!rings[i].mem) + goto err_close_fds_current; + + pfds[i].fd = rings[i].fd; + pfds[i].events = POLLIN; + } + + signal(SIGINT, int_exit); + signal(SIGHUP, int_exit); + signal(SIGTERM, int_exit); + + if (json_output) + jsonw_start_array(json_wtr); + + while (!stop) { + poll(pfds, nfds, 200); + for (i = 0; i < nfds; i++) + perf_event_read(&rings[i], &tmp_buf, &tmp_buf_sz); + } + free(tmp_buf); + + if (json_output) + jsonw_end_array(json_wtr); + + for (i = 0; i < nfds; i++) { + perf_event_unmap(rings[i].mem); + close(rings[i].fd); + } + free(pfds); + free(rings); + close(map_fd); + + return 0; + +err_close_fds_prev: + while (i--) { + perf_event_unmap(rings[i].mem); +err_close_fds_current: + close(rings[i].fd); + } + free(pfds); +err_free_rings: + free(rings); +err_close_map: + close(map_fd); + return -1; +} diff --git a/tools/bpf/bpftool/perf.c b/tools/bpf/bpftool/perf.c new file mode 100644 index 0000000..ac6b1a1 --- /dev/null +++ b/tools/bpf/bpftool/perf.c @@ -0,0 +1,246 @@ +// SPDX-License-Identifier: GPL-2.0+ +// Copyright (C) 2018 Facebook +// Author: Yonghong Song <yhs@fb.com> + +#define _GNU_SOURCE +#include <ctype.h> +#include <errno.h> +#include <fcntl.h> +#include <stdlib.h> +#include <string.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <unistd.h> +#include <ftw.h> + +#include <bpf.h> + +#include "main.h" + +/* 0: undecided, 1: supported, 2: not supported */ +static int perf_query_supported; +static bool has_perf_query_support(void) +{ + __u64 probe_offset, probe_addr; + __u32 len, prog_id, fd_type; + char buf[256]; + int fd; + + if (perf_query_supported) + goto out; + + fd = open(bin_name, O_RDONLY); + if (fd < 0) { + p_err("perf_query_support: %s", strerror(errno)); + goto out; + } + + /* the following query will fail as no bpf attachment, + * the expected errno is ENOTSUPP + */ + errno = 0; + len = sizeof(buf); + bpf_task_fd_query(getpid(), fd, 0, buf, &len, &prog_id, + &fd_type, &probe_offset, &probe_addr); + + if (errno == 524 /* ENOTSUPP */) { + perf_query_supported = 1; + goto close_fd; + } + + perf_query_supported = 2; + p_err("perf_query_support: %s", strerror(errno)); + fprintf(stderr, + "HINT: non root or kernel doesn't support TASK_FD_QUERY\n"); + +close_fd: + close(fd); +out: + return perf_query_supported == 1; +} + +static void print_perf_json(int pid, int fd, __u32 prog_id, __u32 fd_type, + char *buf, __u64 probe_offset, __u64 probe_addr) +{ + jsonw_start_object(json_wtr); + jsonw_int_field(json_wtr, "pid", pid); + jsonw_int_field(json_wtr, "fd", fd); + jsonw_uint_field(json_wtr, "prog_id", prog_id); + switch (fd_type) { + case BPF_FD_TYPE_RAW_TRACEPOINT: + jsonw_string_field(json_wtr, "fd_type", "raw_tracepoint"); + jsonw_string_field(json_wtr, "tracepoint", buf); + break; + case BPF_FD_TYPE_TRACEPOINT: + jsonw_string_field(json_wtr, "fd_type", "tracepoint"); + jsonw_string_field(json_wtr, "tracepoint", buf); + break; + case BPF_FD_TYPE_KPROBE: + jsonw_string_field(json_wtr, "fd_type", "kprobe"); + if (buf[0] != '\0') { + jsonw_string_field(json_wtr, "func", buf); + jsonw_lluint_field(json_wtr, "offset", probe_offset); + } else { + jsonw_lluint_field(json_wtr, "addr", probe_addr); + } + break; + case BPF_FD_TYPE_KRETPROBE: + jsonw_string_field(json_wtr, "fd_type", "kretprobe"); + if (buf[0] != '\0') { + jsonw_string_field(json_wtr, "func", buf); + jsonw_lluint_field(json_wtr, "offset", probe_offset); + } else { + jsonw_lluint_field(json_wtr, "addr", probe_addr); + } + break; + case BPF_FD_TYPE_UPROBE: + jsonw_string_field(json_wtr, "fd_type", "uprobe"); + jsonw_string_field(json_wtr, "filename", buf); + jsonw_lluint_field(json_wtr, "offset", probe_offset); + break; + case BPF_FD_TYPE_URETPROBE: + jsonw_string_field(json_wtr, "fd_type", "uretprobe"); + jsonw_string_field(json_wtr, "filename", buf); + jsonw_lluint_field(json_wtr, "offset", probe_offset); + break; + } + jsonw_end_object(json_wtr); +} + +static void print_perf_plain(int pid, int fd, __u32 prog_id, __u32 fd_type, + char *buf, __u64 probe_offset, __u64 probe_addr) +{ + printf("pid %d fd %d: prog_id %u ", pid, fd, prog_id); + switch (fd_type) { + case BPF_FD_TYPE_RAW_TRACEPOINT: + printf("raw_tracepoint %s\n", buf); + break; + case BPF_FD_TYPE_TRACEPOINT: + printf("tracepoint %s\n", buf); + break; + case BPF_FD_TYPE_KPROBE: + if (buf[0] != '\0') + printf("kprobe func %s offset %llu\n", buf, + probe_offset); + else + printf("kprobe addr %llu\n", probe_addr); + break; + case BPF_FD_TYPE_KRETPROBE: + if (buf[0] != '\0') + printf("kretprobe func %s offset %llu\n", buf, + probe_offset); + else + printf("kretprobe addr %llu\n", probe_addr); + break; + case BPF_FD_TYPE_UPROBE: + printf("uprobe filename %s offset %llu\n", buf, probe_offset); + break; + case BPF_FD_TYPE_URETPROBE: + printf("uretprobe filename %s offset %llu\n", buf, + probe_offset); + break; + } +} + +static int show_proc(const char *fpath, const struct stat *sb, + int tflag, struct FTW *ftwbuf) +{ + __u64 probe_offset, probe_addr; + __u32 len, prog_id, fd_type; + int err, pid = 0, fd = 0; + const char *pch; + char buf[4096]; + + /* prefix always /proc */ + pch = fpath + 5; + if (*pch == '\0') + return 0; + + /* pid should be all numbers */ + pch++; + while (isdigit(*pch)) { + pid = pid * 10 + *pch - '0'; + pch++; + } + if (*pch == '\0') + return 0; + if (*pch != '/') + return FTW_SKIP_SUBTREE; + + /* check /proc/<pid>/fd directory */ + pch++; + if (strncmp(pch, "fd", 2)) + return FTW_SKIP_SUBTREE; + pch += 2; + if (*pch == '\0') + return 0; + if (*pch != '/') + return FTW_SKIP_SUBTREE; + + /* check /proc/<pid>/fd/<fd_num> */ + pch++; + while (isdigit(*pch)) { + fd = fd * 10 + *pch - '0'; + pch++; + } + if (*pch != '\0') + return FTW_SKIP_SUBTREE; + + /* query (pid, fd) for potential perf events */ + len = sizeof(buf); + err = bpf_task_fd_query(pid, fd, 0, buf, &len, &prog_id, &fd_type, + &probe_offset, &probe_addr); + if (err < 0) + return 0; + + if (json_output) + print_perf_json(pid, fd, prog_id, fd_type, buf, probe_offset, + probe_addr); + else + print_perf_plain(pid, fd, prog_id, fd_type, buf, probe_offset, + probe_addr); + + return 0; +} + +static int do_show(int argc, char **argv) +{ + int flags = FTW_ACTIONRETVAL | FTW_PHYS; + int err = 0, nopenfd = 16; + + if (!has_perf_query_support()) + return -1; + + if (json_output) + jsonw_start_array(json_wtr); + if (nftw("/proc", show_proc, nopenfd, flags) == -1) { + p_err("%s", strerror(errno)); + err = -1; + } + if (json_output) + jsonw_end_array(json_wtr); + + return err; +} + +static int do_help(int argc, char **argv) +{ + fprintf(stderr, + "Usage: %s %s { show | list | help }\n" + "", + bin_name, argv[-2]); + + return 0; +} + +static const struct cmd cmds[] = { + { "show", do_show }, + { "list", do_show }, + { "help", do_help }, + { 0 } +}; + +int do_perf(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index f7a8108..a4f4352 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -68,6 +68,10 @@ static const char * const prog_type_name[] = { [BPF_PROG_TYPE_SOCK_OPS] = "sock_ops", [BPF_PROG_TYPE_SK_SKB] = "sk_skb", [BPF_PROG_TYPE_CGROUP_DEVICE] = "cgroup_device", + [BPF_PROG_TYPE_SK_MSG] = "sk_msg", + [BPF_PROG_TYPE_RAW_TRACEPOINT] = "raw_tracepoint", + [BPF_PROG_TYPE_CGROUP_SOCK_ADDR] = "cgroup_sock_addr", + [BPF_PROG_TYPE_LIRC_MODE2] = "lirc_mode2", }; static void print_boot_time(__u64 nsecs, char *buf, unsigned int size) @@ -93,7 +97,10 @@ static void print_boot_time(__u64 nsecs, char *buf, unsigned int size) return; } - strftime(buf, size, "%b %d/%H:%M", &load_tm); + if (json_output) + strftime(buf, size, "%s", &load_tm); + else + strftime(buf, size, "%FT%T%z", &load_tm); } static int prog_fd_by_tag(unsigned char *tag) @@ -232,6 +239,8 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) info->tag[0], info->tag[1], info->tag[2], info->tag[3], info->tag[4], info->tag[5], info->tag[6], info->tag[7]); + jsonw_bool_field(json_wtr, "gpl_compatible", info->gpl_compatible); + print_dev_json(info->ifindex, info->netns_dev, info->netns_ino); if (info->load_time) { @@ -240,7 +249,8 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) print_boot_time(info->load_time, buf, sizeof(buf)); /* Piggy back on load_time, since 0 uid is a valid one */ - jsonw_string_field(json_wtr, "loaded_at", buf); + jsonw_name(json_wtr, "loaded_at"); + jsonw_printf(json_wtr, "%s", buf); jsonw_uint_field(json_wtr, "uid", info->created_by_uid); } @@ -292,6 +302,7 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd) printf("tag "); fprint_hex(stdout, info->tag, BPF_TAG_SIZE, ""); print_dev_plain(info->ifindex, info->netns_dev, info->netns_ino); + printf("%s", info->gpl_compatible ? " gpl" : ""); printf("\n"); if (info->load_time) { @@ -410,7 +421,11 @@ static int do_show(int argc, char **argv) static int do_dump(int argc, char **argv) { + unsigned long *func_ksyms = NULL; struct bpf_prog_info info = {}; + unsigned int *func_lens = NULL; + unsigned int nr_func_ksyms; + unsigned int nr_func_lens; struct dump_data dd = {}; __u32 len = sizeof(info); unsigned int buf_size; @@ -486,10 +501,34 @@ static int do_dump(int argc, char **argv) return -1; } + nr_func_ksyms = info.nr_jited_ksyms; + if (nr_func_ksyms) { + func_ksyms = malloc(nr_func_ksyms * sizeof(__u64)); + if (!func_ksyms) { + p_err("mem alloc failed"); + close(fd); + goto err_free; + } + } + + nr_func_lens = info.nr_jited_func_lens; + if (nr_func_lens) { + func_lens = malloc(nr_func_lens * sizeof(__u32)); + if (!func_lens) { + p_err("mem alloc failed"); + close(fd); + goto err_free; + } + } + memset(&info, 0, sizeof(info)); *member_ptr = ptr_to_u64(buf); *member_len = buf_size; + info.jited_ksyms = ptr_to_u64(func_ksyms); + info.nr_jited_ksyms = nr_func_ksyms; + info.jited_func_lens = ptr_to_u64(func_lens); + info.nr_jited_func_lens = nr_func_lens; err = bpf_obj_get_info_by_fd(fd, &info, &len); close(fd); @@ -503,6 +542,16 @@ static int do_dump(int argc, char **argv) goto err_free; } + if (info.nr_jited_ksyms > nr_func_ksyms) { + p_err("too many addresses returned"); + goto err_free; + } + + if (info.nr_jited_func_lens > nr_func_lens) { + p_err("too many values returned"); + goto err_free; + } + if ((member_len == &info.jited_prog_len && info.jited_prog_insns == 0) || (member_len == &info.xlated_prog_len && @@ -540,7 +589,57 @@ static int do_dump(int argc, char **argv) goto err_free; } - disasm_print_insn(buf, *member_len, opcodes, name); + if (info.nr_jited_func_lens && info.jited_func_lens) { + struct kernel_sym *sym = NULL; + char sym_name[SYM_MAX_NAME]; + unsigned char *img = buf; + __u64 *ksyms = NULL; + __u32 *lens; + __u32 i; + + if (info.nr_jited_ksyms) { + kernel_syms_load(&dd); + ksyms = (__u64 *) info.jited_ksyms; + } + + if (json_output) + jsonw_start_array(json_wtr); + + lens = (__u32 *) info.jited_func_lens; + for (i = 0; i < info.nr_jited_func_lens; i++) { + if (ksyms) { + sym = kernel_syms_search(&dd, ksyms[i]); + if (sym) + sprintf(sym_name, "%s", sym->name); + else + sprintf(sym_name, "0x%016llx", ksyms[i]); + } else { + strcpy(sym_name, "unknown"); + } + + if (json_output) { + jsonw_start_object(json_wtr); + jsonw_name(json_wtr, "name"); + jsonw_string(json_wtr, sym_name); + jsonw_name(json_wtr, "insns"); + } else { + printf("%s:\n", sym_name); + } + + disasm_print_insn(img, lens[i], opcodes, name); + img += lens[i]; + + if (json_output) + jsonw_end_object(json_wtr); + else + printf("\n"); + } + + if (json_output) + jsonw_end_array(json_wtr); + } else { + disasm_print_insn(buf, *member_len, opcodes, name); + } } else if (visual) { if (json_output) jsonw_null(json_wtr); @@ -548,6 +647,9 @@ static int do_dump(int argc, char **argv) dump_xlated_cfg(buf, *member_len); } else { kernel_syms_load(&dd); + dd.nr_jited_ksyms = info.nr_jited_ksyms; + dd.jited_ksyms = (__u64 *) info.jited_ksyms; + if (json_output) dump_xlated_json(&dd, buf, *member_len, opcodes); else @@ -556,10 +658,14 @@ static int do_dump(int argc, char **argv) } free(buf); + free(func_ksyms); + free(func_lens); return 0; err_free: free(buf); + free(func_ksyms); + free(func_lens); return -1; } diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c index 7a3173b..b97f1da 100644 --- a/tools/bpf/bpftool/xlated_dumper.c +++ b/tools/bpf/bpftool/xlated_dumper.c @@ -102,8 +102,8 @@ void kernel_syms_destroy(struct dump_data *dd) free(dd->sym_mapping); } -static struct kernel_sym *kernel_syms_search(struct dump_data *dd, - unsigned long key) +struct kernel_sym *kernel_syms_search(struct dump_data *dd, + unsigned long key) { struct kernel_sym sym = { .address = key, @@ -174,7 +174,11 @@ static const char *print_call_pcrel(struct dump_data *dd, unsigned long address, const struct bpf_insn *insn) { - if (sym) + if (!dd->nr_jited_ksyms) + /* Do not show address for interpreted programs */ + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "%+d", insn->off); + else if (sym) snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), "%+d#%s", insn->off, sym->name); else @@ -203,6 +207,10 @@ static const char *print_call(void *private_data, unsigned long address = dd->address_call_base + insn->imm; struct kernel_sym *sym; + if (insn->src_reg == BPF_PSEUDO_CALL && + (__u32) insn->imm < dd->nr_jited_ksyms) + address = dd->jited_ksyms[insn->imm]; + sym = kernel_syms_search(dd, address); if (insn->src_reg == BPF_PSEUDO_CALL) return print_call_pcrel(dd, sym, address, insn); diff --git a/tools/bpf/bpftool/xlated_dumper.h b/tools/bpf/bpftool/xlated_dumper.h index b34affa..33d86e2 100644 --- a/tools/bpf/bpftool/xlated_dumper.h +++ b/tools/bpf/bpftool/xlated_dumper.h @@ -49,11 +49,14 @@ struct dump_data { unsigned long address_call_base; struct kernel_sym *sym_mapping; __u32 sym_count; + __u64 *jited_ksyms; + __u32 nr_jited_ksyms; char scratch_buff[SYM_MAX_NAME + 8]; }; void kernel_syms_load(struct dump_data *dd); void kernel_syms_destroy(struct dump_data *dd); +struct kernel_sym *kernel_syms_search(struct dump_data *dd, unsigned long key); void dump_xlated_json(struct dump_data *dd, void *buf, unsigned int len, bool opcodes); void dump_xlated_plain(struct dump_data *dd, void *buf, unsigned int len, diff --git a/tools/iio/iio_generic_buffer.c b/tools/iio/iio_generic_buffer.c index f0c6f54..3040830 100644 --- a/tools/iio/iio_generic_buffer.c +++ b/tools/iio/iio_generic_buffer.c @@ -248,7 +248,7 @@ void print_usage(void) "Capture, convert and output data from IIO device buffer\n" " -a Auto-activate all available channels\n" " -A Force-activate ALL channels\n" - " -c <n> Do n conversions\n" + " -c <n> Do n conversions, or loop forever if n < 0\n" " -e Disable wait for event (new data)\n" " -g Use trigger-less mode\n" " -l <n> Set buffer length to n samples\n" @@ -330,11 +330,14 @@ static const struct option longopts[] = { int main(int argc, char **argv) { - unsigned long num_loops = 2; + unsigned long long num_loops = 2; unsigned long timedelay = 1000000; unsigned long buf_len = 128; - int ret, c, i, j, toread; + ssize_t i; + unsigned long long j; + unsigned long toread; + int ret, c; int fp = -1; int num_channels = 0; @@ -366,7 +369,7 @@ int main(int argc, char **argv) break; case 'c': errno = 0; - num_loops = strtoul(optarg, &dummy, 10); + num_loops = strtoll(optarg, &dummy, 10); if (errno) { ret = -errno; goto error; @@ -634,7 +637,7 @@ int main(int argc, char **argv) goto error; } - for (j = 0; j < num_loops; j++) { + for (j = 0; j < num_loops || num_loops < 0; j++) { if (!noevents) { struct pollfd pfd = { .fd = fp, diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h index a3a4427..70fe612 100644 --- a/tools/include/linux/compiler-gcc.h +++ b/tools/include/linux/compiler-gcc.h @@ -21,6 +21,9 @@ /* &a[0] degrades to a pointer: a different type from an array */ #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) +#ifndef __pure +#define __pure __attribute__((pure)) +#endif #define noinline __attribute__((noinline)) #ifndef __packed #define __packed __attribute__((packed)) diff --git a/tools/include/linux/filter.h b/tools/include/linux/filter.h index c5e512d..af55acf 100644 --- a/tools/include/linux/filter.h +++ b/tools/include/linux/filter.h @@ -263,6 +263,16 @@ #define BPF_LD_MAP_FD(DST, MAP_FD) \ BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD) +/* Relative call */ + +#define BPF_CALL_REL(TGT) \ + ((struct bpf_insn) { \ + .code = BPF_JMP | BPF_CALL, \ + .dst_reg = 0, \ + .src_reg = BPF_PSEUDO_CALL, \ + .off = 0, \ + .imm = TGT }) + /* Program exit */ #define BPF_EXIT_INSN() \ diff --git a/tools/include/uapi/asm/bitsperlong.h b/tools/include/uapi/asm/bitsperlong.h new file mode 100644 index 0000000..8dd6aef --- /dev/null +++ b/tools/include/uapi/asm/bitsperlong.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#if defined(__i386__) || defined(__x86_64__) +#include "../../arch/x86/include/uapi/asm/bitsperlong.h" +#elif defined(__aarch64__) +#include "../../arch/arm64/include/uapi/asm/bitsperlong.h" +#elif defined(__powerpc__) +#include "../../arch/powerpc/include/uapi/asm/bitsperlong.h" +#elif defined(__s390__) +#include "../../arch/s390/include/uapi/asm/bitsperlong.h" +#elif defined(__sparc__) +#include "../../arch/sparc/include/uapi/asm/bitsperlong.h" +#elif defined(__mips__) +#include "../../arch/mips/include/uapi/asm/bitsperlong.h" +#elif defined(__ia64__) +#include "../../arch/ia64/include/uapi/asm/bitsperlong.h" +#else +#include <asm-generic/bitsperlong.h> +#endif diff --git a/tools/include/uapi/asm/errno.h b/tools/include/uapi/asm/errno.h new file mode 100644 index 0000000..ce3c594 --- /dev/null +++ b/tools/include/uapi/asm/errno.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#if defined(__i386__) || defined(__x86_64__) +#include "../../arch/x86/include/uapi/asm/errno.h" +#elif defined(__powerpc__) +#include "../../arch/powerpc/include/uapi/asm/errno.h" +#elif defined(__sparc__) +#include "../../arch/sparc/include/uapi/asm/errno.h" +#elif defined(__alpha__) +#include "../../arch/alpha/include/uapi/asm/errno.h" +#elif defined(__mips__) +#include "../../arch/mips/include/uapi/asm/errno.h" +#elif defined(__ia64__) +#include "../../arch/ia64/include/uapi/asm/errno.h" +#elif defined(__xtensa__) +#include "../../arch/xtensa/include/uapi/asm/errno.h" +#else +#include <asm-generic/errno.h> +#endif diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index c5ec897..e0b0678 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -95,6 +95,9 @@ enum bpf_cmd { BPF_OBJ_GET_INFO_BY_FD, BPF_PROG_QUERY, BPF_RAW_TRACEPOINT_OPEN, + BPF_BTF_LOAD, + BPF_BTF_GET_FD_BY_ID, + BPF_TASK_FD_QUERY, }; enum bpf_map_type { @@ -115,6 +118,8 @@ enum bpf_map_type { BPF_MAP_TYPE_DEVMAP, BPF_MAP_TYPE_SOCKMAP, BPF_MAP_TYPE_CPUMAP, + BPF_MAP_TYPE_XSKMAP, + BPF_MAP_TYPE_SOCKHASH, }; enum bpf_prog_type { @@ -137,6 +142,8 @@ enum bpf_prog_type { BPF_PROG_TYPE_SK_MSG, BPF_PROG_TYPE_RAW_TRACEPOINT, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + BPF_PROG_TYPE_LWT_SEG6LOCAL, + BPF_PROG_TYPE_LIRC_MODE2, }; enum bpf_attach_type { @@ -154,6 +161,9 @@ enum bpf_attach_type { BPF_CGROUP_INET6_CONNECT, BPF_CGROUP_INET4_POST_BIND, BPF_CGROUP_INET6_POST_BIND, + BPF_CGROUP_UDP4_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + BPF_LIRC_MODE2, __MAX_BPF_ATTACH_TYPE }; @@ -279,6 +289,9 @@ union bpf_attr { */ char map_name[BPF_OBJ_NAME_LEN]; __u32 map_ifindex; /* ifindex of netdev to create on */ + __u32 btf_fd; /* fd pointing to a BTF type data */ + __u32 btf_key_type_id; /* BTF type_id of the key */ + __u32 btf_value_type_id; /* BTF type_id of the value */ }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -339,6 +352,7 @@ union bpf_attr { __u32 start_id; __u32 prog_id; __u32 map_id; + __u32 btf_id; }; __u32 next_id; __u32 open_flags; @@ -363,398 +377,1704 @@ union bpf_attr { __u64 name; __u32 prog_fd; } raw_tracepoint; + + struct { /* anonymous struct for BPF_BTF_LOAD */ + __aligned_u64 btf; + __aligned_u64 btf_log_buf; + __u32 btf_size; + __u32 btf_log_size; + __u32 btf_log_level; + }; + + struct { + __u32 pid; /* input: pid */ + __u32 fd; /* input: fd */ + __u32 flags; /* input: flags */ + __u32 buf_len; /* input/output: buf len */ + __aligned_u64 buf; /* input/output: + * tp_name for tracepoint + * symbol for kprobe + * filename for uprobe + */ + __u32 prog_id; /* output: prod_id */ + __u32 fd_type; /* output: BPF_FD_TYPE_* */ + __u64 probe_offset; /* output: probe_offset */ + __u64 probe_addr; /* output: probe_addr */ + } task_fd_query; } __attribute__((aligned(8))); -/* BPF helper function descriptions: - * - * void *bpf_map_lookup_elem(&map, &key) - * Return: Map value or NULL - * - * int bpf_map_update_elem(&map, &key, &value, flags) - * Return: 0 on success or negative error - * - * int bpf_map_delete_elem(&map, &key) - * Return: 0 on success or negative error - * - * int bpf_probe_read(void *dst, int size, void *src) - * Return: 0 on success or negative error +/* The description below is an attempt at providing documentation to eBPF + * developers about the multiple available eBPF helper functions. It can be + * parsed and used to produce a manual page. The workflow is the following, + * and requires the rst2man utility: + * + * $ ./scripts/bpf_helpers_doc.py \ + * --filename include/uapi/linux/bpf.h > /tmp/bpf-helpers.rst + * $ rst2man /tmp/bpf-helpers.rst > /tmp/bpf-helpers.7 + * $ man /tmp/bpf-helpers.7 + * + * Note that in order to produce this external documentation, some RST + * formatting is used in the descriptions to get "bold" and "italics" in + * manual pages. Also note that the few trailing white spaces are + * intentional, removing them would break paragraphs for rst2man. + * + * Start of BPF helper function descriptions: + * + * void *bpf_map_lookup_elem(struct bpf_map *map, const void *key) + * Description + * Perform a lookup in *map* for an entry associated to *key*. + * Return + * Map value associated to *key*, or **NULL** if no entry was + * found. + * + * int bpf_map_update_elem(struct bpf_map *map, const void *key, const void *value, u64 flags) + * Description + * Add or update the value of the entry associated to *key* in + * *map* with *value*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * Flag value **BPF_NOEXIST** cannot be used for maps of types + * **BPF_MAP_TYPE_ARRAY** or **BPF_MAP_TYPE_PERCPU_ARRAY** (all + * elements always exist), the helper would return an error. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_delete_elem(struct bpf_map *map, const void *key) + * Description + * Delete entry with *key* from *map*. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_probe_read(void *dst, u32 size, const void *src) + * Description + * For tracing programs, safely attempt to read *size* bytes from + * address *src* and store the data in *dst*. + * Return + * 0 on success, or a negative error in case of failure. * * u64 bpf_ktime_get_ns(void) - * Return: current ktime - * - * int bpf_trace_printk(const char *fmt, int fmt_size, ...) - * Return: length of buffer written or negative error - * - * u32 bpf_prandom_u32(void) - * Return: random value - * - * u32 bpf_raw_smp_processor_id(void) - * Return: SMP processor ID - * - * int bpf_skb_store_bytes(skb, offset, from, len, flags) - * store bytes into packet - * @skb: pointer to skb - * @offset: offset within packet from skb->mac_header - * @from: pointer where to copy bytes from - * @len: number of bytes to store into packet - * @flags: bit 0 - if true, recompute skb->csum - * other bits - reserved - * Return: 0 on success or negative error - * - * int bpf_l3_csum_replace(skb, offset, from, to, flags) - * recompute IP checksum - * @skb: pointer to skb - * @offset: offset within packet where IP checksum is located - * @from: old value of header field - * @to: new value of header field - * @flags: bits 0-3 - size of header field - * other bits - reserved - * Return: 0 on success or negative error - * - * int bpf_l4_csum_replace(skb, offset, from, to, flags) - * recompute TCP/UDP checksum - * @skb: pointer to skb - * @offset: offset within packet where TCP/UDP checksum is located - * @from: old value of header field - * @to: new value of header field - * @flags: bits 0-3 - size of header field - * bit 4 - is pseudo header - * other bits - reserved - * Return: 0 on success or negative error - * - * int bpf_tail_call(ctx, prog_array_map, index) - * jump into another BPF program - * @ctx: context pointer passed to next program - * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY - * @index: 32-bit index inside array that selects specific program to run - * Return: 0 on success or negative error - * - * int bpf_clone_redirect(skb, ifindex, flags) - * redirect to another netdev - * @skb: pointer to skb - * @ifindex: ifindex of the net device - * @flags: bit 0 - if set, redirect to ingress instead of egress - * other bits - reserved - * Return: 0 on success or negative error + * Description + * Return the time elapsed since system boot, in nanoseconds. + * Return + * Current *ktime*. + * + * int bpf_trace_printk(const char *fmt, u32 fmt_size, ...) + * Description + * This helper is a "printk()-like" facility for debugging. It + * prints a message defined by format *fmt* (of size *fmt_size*) + * to file *\/sys/kernel/debug/tracing/trace* from DebugFS, if + * available. It can take up to three additional **u64** + * arguments (as an eBPF helpers, the total number of arguments is + * limited to five). + * + * Each time the helper is called, it appends a line to the trace. + * The format of the trace is customizable, and the exact output + * one will get depends on the options set in + * *\/sys/kernel/debug/tracing/trace_options* (see also the + * *README* file under the same directory). However, it usually + * defaults to something like: + * + * :: + * + * telnet-470 [001] .N.. 419421.045894: 0x00000001: <formatted msg> + * + * In the above: + * + * * ``telnet`` is the name of the current task. + * * ``470`` is the PID of the current task. + * * ``001`` is the CPU number on which the task is + * running. + * * In ``.N..``, each character refers to a set of + * options (whether irqs are enabled, scheduling + * options, whether hard/softirqs are running, level of + * preempt_disabled respectively). **N** means that + * **TIF_NEED_RESCHED** and **PREEMPT_NEED_RESCHED** + * are set. + * * ``419421.045894`` is a timestamp. + * * ``0x00000001`` is a fake value used by BPF for the + * instruction pointer register. + * * ``<formatted msg>`` is the message formatted with + * *fmt*. + * + * The conversion specifiers supported by *fmt* are similar, but + * more limited than for printk(). They are **%d**, **%i**, + * **%u**, **%x**, **%ld**, **%li**, **%lu**, **%lx**, **%lld**, + * **%lli**, **%llu**, **%llx**, **%p**, **%s**. No modifier (size + * of field, padding with zeroes, etc.) is available, and the + * helper will return **-EINVAL** (but print nothing) if it + * encounters an unknown specifier. + * + * Also, note that **bpf_trace_printk**\ () is slow, and should + * only be used for debugging purposes. For this reason, a notice + * bloc (spanning several lines) is printed to kernel logs and + * states that the helper should not be used "for production use" + * the first time this helper is used (or more precisely, when + * **trace_printk**\ () buffers are allocated). For passing values + * to user space, perf events should be preferred. + * Return + * The number of bytes written to the buffer, or a negative error + * in case of failure. + * + * u32 bpf_get_prandom_u32(void) + * Description + * Get a pseudo-random number. + * + * From a security point of view, this helper uses its own + * pseudo-random internal state, and cannot be used to infer the + * seed of other random functions in the kernel. However, it is + * essential to note that the generator used by the helper is not + * cryptographically secure. + * Return + * A random 32-bit unsigned value. + * + * u32 bpf_get_smp_processor_id(void) + * Description + * Get the SMP (symmetric multiprocessing) processor id. Note that + * all programs run with preemption disabled, which means that the + * SMP processor id is stable during all the execution of the + * program. + * Return + * The SMP id of the processor running the program. + * + * int bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) + * Description + * Store *len* bytes from address *from* into the packet + * associated to *skb*, at *offset*. *flags* are a combination of + * **BPF_F_RECOMPUTE_CSUM** (automatically recompute the + * checksum for the packet after storing the bytes) and + * **BPF_F_INVALIDATE_HASH** (set *skb*\ **->hash**, *skb*\ + * **->swhash** and *skb*\ **->l4hash** to 0). + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_l3_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 size) + * Description + * Recompute the layer 3 (e.g. IP) checksum for the packet + * associated to *skb*. Computation is incremental, so the helper + * must know the former value of the header field that was + * modified (*from*), the new value of this field (*to*), and the + * number of bytes (2 or 4) for this field, stored in *size*. + * Alternatively, it is possible to store the difference between + * the previous and the new values of the header field in *to*, by + * setting *from* and *size* to 0. For both methods, *offset* + * indicates the location of the IP checksum within the packet. + * + * This helper works in combination with **bpf_csum_diff**\ (), + * which does not update the checksum in-place, but offers more + * flexibility and can handle sizes larger than 2 or 4 for the + * checksum to update. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_l4_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 flags) + * Description + * Recompute the layer 4 (e.g. TCP, UDP or ICMP) checksum for the + * packet associated to *skb*. Computation is incremental, so the + * helper must know the former value of the header field that was + * modified (*from*), the new value of this field (*to*), and the + * number of bytes (2 or 4) for this field, stored on the lowest + * four bits of *flags*. Alternatively, it is possible to store + * the difference between the previous and the new values of the + * header field in *to*, by setting *from* and the four lowest + * bits of *flags* to 0. For both methods, *offset* indicates the + * location of the IP checksum within the packet. In addition to + * the size of the field, *flags* can be added (bitwise OR) actual + * flags. With **BPF_F_MARK_MANGLED_0**, a null checksum is left + * untouched (unless **BPF_F_MARK_ENFORCE** is added as well), and + * for updates resulting in a null checksum the value is set to + * **CSUM_MANGLED_0** instead. Flag **BPF_F_PSEUDO_HDR** indicates + * the checksum is to be computed against a pseudo-header. + * + * This helper works in combination with **bpf_csum_diff**\ (), + * which does not update the checksum in-place, but offers more + * flexibility and can handle sizes larger than 2 or 4 for the + * checksum to update. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_tail_call(void *ctx, struct bpf_map *prog_array_map, u32 index) + * Description + * This special helper is used to trigger a "tail call", or in + * other words, to jump into another eBPF program. The same stack + * frame is used (but values on stack and in registers for the + * caller are not accessible to the callee). This mechanism allows + * for program chaining, either for raising the maximum number of + * available eBPF instructions, or to execute given programs in + * conditional blocks. For security reasons, there is an upper + * limit to the number of successive tail calls that can be + * performed. + * + * Upon call of this helper, the program attempts to jump into a + * program referenced at index *index* in *prog_array_map*, a + * special map of type **BPF_MAP_TYPE_PROG_ARRAY**, and passes + * *ctx*, a pointer to the context. + * + * If the call succeeds, the kernel immediately runs the first + * instruction of the new program. This is not a function call, + * and it never returns to the previous program. If the call + * fails, then the helper has no effect, and the caller continues + * to run its subsequent instructions. A call can fail if the + * destination program for the jump does not exist (i.e. *index* + * is superior to the number of entries in *prog_array_map*), or + * if the maximum number of tail calls has been reached for this + * chain of programs. This limit is defined in the kernel by the + * macro **MAX_TAIL_CALL_CNT** (not accessible to user space), + * which is currently set to 32. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_clone_redirect(struct sk_buff *skb, u32 ifindex, u64 flags) + * Description + * Clone and redirect the packet associated to *skb* to another + * net device of index *ifindex*. Both ingress and egress + * interfaces can be used for redirection. The **BPF_F_INGRESS** + * value in *flags* is used to make the distinction (ingress path + * is selected if the flag is present, egress path otherwise). + * This is the only flag supported for now. + * + * In comparison with **bpf_redirect**\ () helper, + * **bpf_clone_redirect**\ () has the associated cost of + * duplicating the packet buffer, but this can be executed out of + * the eBPF program. Conversely, **bpf_redirect**\ () is more + * efficient, but it is handled through an action code where the + * redirection happens only after the eBPF program has returned. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. * * u64 bpf_get_current_pid_tgid(void) - * Return: current->tgid << 32 | current->pid + * Return + * A 64-bit integer containing the current tgid and pid, and + * created as such: + * *current_task*\ **->tgid << 32 \|** + * *current_task*\ **->pid**. * * u64 bpf_get_current_uid_gid(void) - * Return: current_gid << 32 | current_uid - * - * int bpf_get_current_comm(char *buf, int size_of_buf) - * stores current->comm into buf - * Return: 0 on success or negative error - * - * u32 bpf_get_cgroup_classid(skb) - * retrieve a proc's classid - * @skb: pointer to skb - * Return: classid if != 0 - * - * int bpf_skb_vlan_push(skb, vlan_proto, vlan_tci) - * Return: 0 on success or negative error - * - * int bpf_skb_vlan_pop(skb) - * Return: 0 on success or negative error - * - * int bpf_skb_get_tunnel_key(skb, key, size, flags) - * int bpf_skb_set_tunnel_key(skb, key, size, flags) - * retrieve or populate tunnel metadata - * @skb: pointer to skb - * @key: pointer to 'struct bpf_tunnel_key' - * @size: size of 'struct bpf_tunnel_key' - * @flags: room for future extensions - * Return: 0 on success or negative error - * - * u64 bpf_perf_event_read(map, flags) - * read perf event counter value - * @map: pointer to perf_event_array map - * @flags: index of event in the map or bitmask flags - * Return: value of perf event counter read or error code - * - * int bpf_redirect(ifindex, flags) - * redirect to another netdev - * @ifindex: ifindex of the net device - * @flags: - * cls_bpf: - * bit 0 - if set, redirect to ingress instead of egress - * other bits - reserved - * xdp_bpf: - * all bits - reserved - * Return: cls_bpf: TC_ACT_REDIRECT on success or TC_ACT_SHOT on error - * xdp_bfp: XDP_REDIRECT on success or XDP_ABORT on error - * int bpf_redirect_map(map, key, flags) - * redirect to endpoint in map - * @map: pointer to dev map - * @key: index in map to lookup - * @flags: -- - * Return: XDP_REDIRECT on success or XDP_ABORT on error - * - * u32 bpf_get_route_realm(skb) - * retrieve a dst's tclassid - * @skb: pointer to skb - * Return: realm if != 0 - * - * int bpf_perf_event_output(ctx, map, flags, data, size) - * output perf raw sample - * @ctx: struct pt_regs* - * @map: pointer to perf_event_array map - * @flags: index of event in the map or bitmask flags - * @data: data on stack to be output as raw data - * @size: size of data - * Return: 0 on success or negative error - * - * int bpf_get_stackid(ctx, map, flags) - * walk user or kernel stack and return id - * @ctx: struct pt_regs* - * @map: pointer to stack_trace map - * @flags: bits 0-7 - numer of stack frames to skip - * bit 8 - collect user stack instead of kernel - * bit 9 - compare stacks by hash only - * bit 10 - if two different stacks hash into the same stackid - * discard old - * other bits - reserved - * Return: >= 0 stackid on success or negative error - * - * s64 bpf_csum_diff(from, from_size, to, to_size, seed) - * calculate csum diff - * @from: raw from buffer - * @from_size: length of from buffer - * @to: raw to buffer - * @to_size: length of to buffer - * @seed: optional seed - * Return: csum result or negative error code - * - * int bpf_skb_get_tunnel_opt(skb, opt, size) - * retrieve tunnel options metadata - * @skb: pointer to skb - * @opt: pointer to raw tunnel option data - * @size: size of @opt - * Return: option size - * - * int bpf_skb_set_tunnel_opt(skb, opt, size) - * populate tunnel options metadata - * @skb: pointer to skb - * @opt: pointer to raw tunnel option data - * @size: size of @opt - * Return: 0 on success or negative error - * - * int bpf_skb_change_proto(skb, proto, flags) - * Change protocol of the skb. Currently supported is v4 -> v6, - * v6 -> v4 transitions. The helper will also resize the skb. eBPF - * program is expected to fill the new headers via skb_store_bytes - * and lX_csum_replace. - * @skb: pointer to skb - * @proto: new skb->protocol type - * @flags: reserved - * Return: 0 on success or negative error - * - * int bpf_skb_change_type(skb, type) - * Change packet type of skb. - * @skb: pointer to skb - * @type: new skb->pkt_type type - * Return: 0 on success or negative error - * - * int bpf_skb_under_cgroup(skb, map, index) - * Check cgroup2 membership of skb - * @skb: pointer to skb - * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type - * @index: index of the cgroup in the bpf_map - * Return: - * == 0 skb failed the cgroup2 descendant test - * == 1 skb succeeded the cgroup2 descendant test - * < 0 error - * - * u32 bpf_get_hash_recalc(skb) - * Retrieve and possibly recalculate skb->hash. - * @skb: pointer to skb - * Return: hash + * Return + * A 64-bit integer containing the current GID and UID, and + * created as such: *current_gid* **<< 32 \|** *current_uid*. + * + * int bpf_get_current_comm(char *buf, u32 size_of_buf) + * Description + * Copy the **comm** attribute of the current task into *buf* of + * *size_of_buf*. The **comm** attribute contains the name of + * the executable (excluding the path) for the current task. The + * *size_of_buf* must be strictly positive. On success, the + * helper makes sure that the *buf* is NUL-terminated. On failure, + * it is filled with zeroes. + * Return + * 0 on success, or a negative error in case of failure. + * + * u32 bpf_get_cgroup_classid(struct sk_buff *skb) + * Description + * Retrieve the classid for the current task, i.e. for the net_cls + * cgroup to which *skb* belongs. + * + * This helper can be used on TC egress path, but not on ingress. + * + * The net_cls cgroup provides an interface to tag network packets + * based on a user-provided identifier for all traffic coming from + * the tasks belonging to the related cgroup. See also the related + * kernel documentation, available from the Linux sources in file + * *Documentation/cgroup-v1/net_cls.txt*. + * + * The Linux kernel has two versions for cgroups: there are + * cgroups v1 and cgroups v2. Both are available to users, who can + * use a mixture of them, but note that the net_cls cgroup is for + * cgroup v1 only. This makes it incompatible with BPF programs + * run on cgroups, which is a cgroup-v2-only feature (a socket can + * only hold data for one version of cgroups at a time). + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_CGROUP_NET_CLASSID** configuration option set to + * "**y**" or to "**m**". + * Return + * The classid, or 0 for the default unconfigured classid. + * + * int bpf_skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) + * Description + * Push a *vlan_tci* (VLAN tag control information) of protocol + * *vlan_proto* to the packet associated to *skb*, then update + * the checksum. Note that if *vlan_proto* is different from + * **ETH_P_8021Q** and **ETH_P_8021AD**, it is considered to + * be **ETH_P_8021Q**. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_vlan_pop(struct sk_buff *skb) + * Description + * Pop a VLAN header from the packet associated to *skb*. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_get_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags) + * Description + * Get tunnel metadata. This helper takes a pointer *key* to an + * empty **struct bpf_tunnel_key** of **size**, that will be + * filled with tunnel metadata for the packet associated to *skb*. + * The *flags* can be set to **BPF_F_TUNINFO_IPV6**, which + * indicates that the tunnel is based on IPv6 protocol instead of + * IPv4. + * + * The **struct bpf_tunnel_key** is an object that generalizes the + * principal parameters used by various tunneling protocols into a + * single struct. This way, it can be used to easily make a + * decision based on the contents of the encapsulation header, + * "summarized" in this struct. In particular, it holds the IP + * address of the remote end (IPv4 or IPv6, depending on the case) + * in *key*\ **->remote_ipv4** or *key*\ **->remote_ipv6**. Also, + * this struct exposes the *key*\ **->tunnel_id**, which is + * generally mapped to a VNI (Virtual Network Identifier), making + * it programmable together with the **bpf_skb_set_tunnel_key**\ + * () helper. + * + * Let's imagine that the following code is part of a program + * attached to the TC ingress interface, on one end of a GRE + * tunnel, and is supposed to filter out all messages coming from + * remote ends with IPv4 address other than 10.0.0.1: + * + * :: + * + * int ret; + * struct bpf_tunnel_key key = {}; + * + * ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + * if (ret < 0) + * return TC_ACT_SHOT; // drop packet + * + * if (key.remote_ipv4 != 0x0a000001) + * return TC_ACT_SHOT; // drop packet + * + * return TC_ACT_OK; // accept packet + * + * This interface can also be used with all encapsulation devices + * that can operate in "collect metadata" mode: instead of having + * one network device per specific configuration, the "collect + * metadata" mode only requires a single device where the + * configuration can be extracted from this helper. + * + * This can be used together with various tunnels such as VXLan, + * Geneve, GRE or IP in IP (IPIP). + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_set_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags) + * Description + * Populate tunnel metadata for packet associated to *skb.* The + * tunnel metadata is set to the contents of *key*, of *size*. The + * *flags* can be set to a combination of the following values: + * + * **BPF_F_TUNINFO_IPV6** + * Indicate that the tunnel is based on IPv6 protocol + * instead of IPv4. + * **BPF_F_ZERO_CSUM_TX** + * For IPv4 packets, add a flag to tunnel metadata + * indicating that checksum computation should be skipped + * and checksum set to zeroes. + * **BPF_F_DONT_FRAGMENT** + * Add a flag to tunnel metadata indicating that the + * packet should not be fragmented. + * **BPF_F_SEQ_NUMBER** + * Add a flag to tunnel metadata indicating that a + * sequence number should be added to tunnel header before + * sending the packet. This flag was added for GRE + * encapsulation, but might be used with other protocols + * as well in the future. + * + * Here is a typical usage on the transmit path: + * + * :: + * + * struct bpf_tunnel_key key; + * populate key ... + * bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0); + * bpf_clone_redirect(skb, vxlan_dev_ifindex, 0); + * + * See also the description of the **bpf_skb_get_tunnel_key**\ () + * helper for additional information. + * Return + * 0 on success, or a negative error in case of failure. + * + * u64 bpf_perf_event_read(struct bpf_map *map, u64 flags) + * Description + * Read the value of a perf event counter. This helper relies on a + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of + * the perf event counter is selected when *map* is updated with + * perf event file descriptors. The *map* is an array whose size + * is the number of available CPUs, and each cell contains a value + * relative to one CPU. The value to retrieve is indicated by + * *flags*, that contains the index of the CPU to look up, masked + * with **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to + * **BPF_F_CURRENT_CPU** to indicate that the value for the + * current CPU should be retrieved. + * + * Note that before Linux 4.13, only hardware perf event can be + * retrieved. + * + * Also, be aware that the newer helper + * **bpf_perf_event_read_value**\ () is recommended over + * **bpf_perf_event_read**\ () in general. The latter has some ABI + * quirks where error and counter value are used as a return code + * (which is wrong to do since ranges may overlap). This issue is + * fixed with **bpf_perf_event_read_value**\ (), which at the same + * time provides more features over the **bpf_perf_event_read**\ + * () interface. Please refer to the description of + * **bpf_perf_event_read_value**\ () for details. + * Return + * The value of the perf event counter read from the map, or a + * negative error code in case of failure. + * + * int bpf_redirect(u32 ifindex, u64 flags) + * Description + * Redirect the packet to another net device of index *ifindex*. + * This helper is somewhat similar to **bpf_clone_redirect**\ + * (), except that the packet is not cloned, which provides + * increased performance. + * + * Except for XDP, both ingress and egress interfaces can be used + * for redirection. The **BPF_F_INGRESS** value in *flags* is used + * to make the distinction (ingress path is selected if the flag + * is present, egress path otherwise). Currently, XDP only + * supports redirection to the egress interface, and accepts no + * flag at all. + * + * The same effect can be attained with the more generic + * **bpf_redirect_map**\ (), which requires specific maps to be + * used but offers better performance. + * Return + * For XDP, the helper returns **XDP_REDIRECT** on success or + * **XDP_ABORTED** on error. For other program types, the values + * are **TC_ACT_REDIRECT** on success or **TC_ACT_SHOT** on + * error. + * + * u32 bpf_get_route_realm(struct sk_buff *skb) + * Description + * Retrieve the realm or the route, that is to say the + * **tclassid** field of the destination for the *skb*. The + * indentifier retrieved is a user-provided tag, similar to the + * one used with the net_cls cgroup (see description for + * **bpf_get_cgroup_classid**\ () helper), but here this tag is + * held by a route (a destination entry), not by a task. + * + * Retrieving this identifier works with the clsact TC egress hook + * (see also **tc-bpf(8)**), or alternatively on conventional + * classful egress qdiscs, but not on TC ingress path. In case of + * clsact TC egress hook, this has the advantage that, internally, + * the destination entry has not been dropped yet in the transmit + * path. Therefore, the destination entry does not need to be + * artificially held via **netif_keep_dst**\ () for a classful + * qdisc until the *skb* is freed. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_IP_ROUTE_CLASSID** configuration option. + * Return + * The realm of the route for the packet associated to *skb*, or 0 + * if none was found. + * + * int bpf_perf_event_output(struct pt_reg *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) + * Description + * Write raw *data* blob into a special BPF perf event held by + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf + * event must have the following attributes: **PERF_SAMPLE_RAW** + * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and + * **PERF_COUNT_SW_BPF_OUTPUT** as **config**. + * + * The *flags* are used to indicate the index in *map* for which + * the value must be put, masked with **BPF_F_INDEX_MASK**. + * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU** + * to indicate that the index of the current CPU core should be + * used. + * + * The value to write, of *size*, is passed through eBPF stack and + * pointed by *data*. + * + * The context of the program *ctx* needs also be passed to the + * helper. + * + * On user space, a program willing to read the values needs to + * call **perf_event_open**\ () on the perf event (either for + * one or for all CPUs) and to store the file descriptor into the + * *map*. This must be done before the eBPF program can send data + * into it. An example is available in file + * *samples/bpf/trace_output_user.c* in the Linux kernel source + * tree (the eBPF program counterpart is in + * *samples/bpf/trace_output_kern.c*). + * + * **bpf_perf_event_output**\ () achieves better performance + * than **bpf_trace_printk**\ () for sharing data with user + * space, and is much better suitable for streaming data from eBPF + * programs. + * + * Note that this helper is not restricted to tracing use cases + * and can be used with programs attached to TC or XDP as well, + * where it allows for passing data to user space listeners. Data + * can be: + * + * * Only custom structs, + * * Only the packet payload, or + * * A combination of both. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len) + * Description + * This helper was provided as an easy way to load data from a + * packet. It can be used to load *len* bytes from *offset* from + * the packet associated to *skb*, into the buffer pointed by + * *to*. + * + * Since Linux 4.7, usage of this helper has mostly been replaced + * by "direct packet access", enabling packet data to be + * manipulated with *skb*\ **->data** and *skb*\ **->data_end** + * pointing respectively to the first byte of packet data and to + * the byte after the last byte of packet data. However, it + * remains useful if one wishes to read large quantities of data + * at once from a packet into the eBPF stack. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_get_stackid(struct pt_reg *ctx, struct bpf_map *map, u64 flags) + * Description + * Walk a user or a kernel stack and return its id. To achieve + * this, the helper needs *ctx*, which is a pointer to the context + * on which the tracing program is executed, and a pointer to a + * *map* of type **BPF_MAP_TYPE_STACK_TRACE**. + * + * The last argument, *flags*, holds the number of stack frames to + * skip (from 0 to 255), masked with + * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set + * a combination of the following flags: + * + * **BPF_F_USER_STACK** + * Collect a user space stack instead of a kernel stack. + * **BPF_F_FAST_STACK_CMP** + * Compare stacks by hash only. + * **BPF_F_REUSE_STACKID** + * If two different stacks hash into the same *stackid*, + * discard the old one. + * + * The stack id retrieved is a 32 bit long integer handle which + * can be further combined with other data (including other stack + * ids) and used as a key into maps. This can be useful for + * generating a variety of graphs (such as flame graphs or off-cpu + * graphs). + * + * For walking a stack, this helper is an improvement over + * **bpf_probe_read**\ (), which can be used with unrolled loops + * but is not efficient and consumes a lot of eBPF instructions. + * Instead, **bpf_get_stackid**\ () can collect up to + * **PERF_MAX_STACK_DEPTH** both kernel and user frames. Note that + * this limit can be controlled with the **sysctl** program, and + * that it should be manually increased in order to profile long + * user stacks (such as stacks for Java programs). To do so, use: + * + * :: + * + * # sysctl kernel.perf_event_max_stack=<new value> + * Return + * The positive or null stack id on success, or a negative error + * in case of failure. + * + * s64 bpf_csum_diff(__be32 *from, u32 from_size, __be32 *to, u32 to_size, __wsum seed) + * Description + * Compute a checksum difference, from the raw buffer pointed by + * *from*, of length *from_size* (that must be a multiple of 4), + * towards the raw buffer pointed by *to*, of size *to_size* + * (same remark). An optional *seed* can be added to the value + * (this can be cascaded, the seed may come from a previous call + * to the helper). + * + * This is flexible enough to be used in several ways: + * + * * With *from_size* == 0, *to_size* > 0 and *seed* set to + * checksum, it can be used when pushing new data. + * * With *from_size* > 0, *to_size* == 0 and *seed* set to + * checksum, it can be used when removing data from a packet. + * * With *from_size* > 0, *to_size* > 0 and *seed* set to 0, it + * can be used to compute a diff. Note that *from_size* and + * *to_size* do not need to be equal. + * + * This helper can be used in combination with + * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\ (), to + * which one can feed in the difference computed with + * **bpf_csum_diff**\ (). + * Return + * The checksum result, or a negative error code in case of + * failure. + * + * int bpf_skb_get_tunnel_opt(struct sk_buff *skb, u8 *opt, u32 size) + * Description + * Retrieve tunnel options metadata for the packet associated to + * *skb*, and store the raw tunnel option data to the buffer *opt* + * of *size*. + * + * This helper can be used with encapsulation devices that can + * operate in "collect metadata" mode (please refer to the related + * note in the description of **bpf_skb_get_tunnel_key**\ () for + * more details). A particular example where this can be used is + * in combination with the Geneve encapsulation protocol, where it + * allows for pushing (with **bpf_skb_get_tunnel_opt**\ () helper) + * and retrieving arbitrary TLVs (Type-Length-Value headers) from + * the eBPF program. This allows for full customization of these + * headers. + * Return + * The size of the option data retrieved. + * + * int bpf_skb_set_tunnel_opt(struct sk_buff *skb, u8 *opt, u32 size) + * Description + * Set tunnel options metadata for the packet associated to *skb* + * to the option data contained in the raw buffer *opt* of *size*. + * + * See also the description of the **bpf_skb_get_tunnel_opt**\ () + * helper for additional information. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_change_proto(struct sk_buff *skb, __be16 proto, u64 flags) + * Description + * Change the protocol of the *skb* to *proto*. Currently + * supported are transition from IPv4 to IPv6, and from IPv6 to + * IPv4. The helper takes care of the groundwork for the + * transition, including resizing the socket buffer. The eBPF + * program is expected to fill the new headers, if any, via + * **skb_store_bytes**\ () and to recompute the checksums with + * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\ + * (). The main case for this helper is to perform NAT64 + * operations out of an eBPF program. + * + * Internally, the GSO type is marked as dodgy so that headers are + * checked and segments are recalculated by the GSO/GRO engine. + * The size for GSO target is adapted as well. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_change_type(struct sk_buff *skb, u32 type) + * Description + * Change the packet type for the packet associated to *skb*. This + * comes down to setting *skb*\ **->pkt_type** to *type*, except + * the eBPF program does not have a write access to *skb*\ + * **->pkt_type** beside this helper. Using a helper here allows + * for graceful handling of errors. + * + * The major use case is to change incoming *skb*s to + * **PACKET_HOST** in a programmatic way instead of having to + * recirculate via **redirect**\ (..., **BPF_F_INGRESS**), for + * example. + * + * Note that *type* only allows certain values. At this time, they + * are: + * + * **PACKET_HOST** + * Packet is for us. + * **PACKET_BROADCAST** + * Send packet to all. + * **PACKET_MULTICAST** + * Send packet to group. + * **PACKET_OTHERHOST** + * Send packet to someone else. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_under_cgroup(struct sk_buff *skb, struct bpf_map *map, u32 index) + * Description + * Check whether *skb* is a descendant of the cgroup2 held by + * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*. + * Return + * The return value depends on the result of the test, and can be: + * + * * 0, if the *skb* failed the cgroup2 descendant test. + * * 1, if the *skb* succeeded the cgroup2 descendant test. + * * A negative error code, if an error occurred. + * + * u32 bpf_get_hash_recalc(struct sk_buff *skb) + * Description + * Retrieve the hash of the packet, *skb*\ **->hash**. If it is + * not set, in particular if the hash was cleared due to mangling, + * recompute this hash. Later accesses to the hash can be done + * directly with *skb*\ **->hash**. + * + * Calling **bpf_set_hash_invalid**\ (), changing a packet + * prototype with **bpf_skb_change_proto**\ (), or calling + * **bpf_skb_store_bytes**\ () with the + * **BPF_F_INVALIDATE_HASH** are actions susceptible to clear + * the hash and to trigger a new computation for the next call to + * **bpf_get_hash_recalc**\ (). + * Return + * The 32-bit hash. * * u64 bpf_get_current_task(void) - * Returns current task_struct - * Return: current - * - * int bpf_probe_write_user(void *dst, void *src, int len) - * safely attempt to write to a location - * @dst: destination address in userspace - * @src: source address on stack - * @len: number of bytes to copy - * Return: 0 on success or negative error - * - * int bpf_current_task_under_cgroup(map, index) - * Check cgroup2 membership of current task - * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type - * @index: index of the cgroup in the bpf_map - * Return: - * == 0 current failed the cgroup2 descendant test - * == 1 current succeeded the cgroup2 descendant test - * < 0 error - * - * int bpf_skb_change_tail(skb, len, flags) - * The helper will resize the skb to the given new size, to be used f.e. - * with control messages. - * @skb: pointer to skb - * @len: new skb length - * @flags: reserved - * Return: 0 on success or negative error - * - * int bpf_skb_pull_data(skb, len) - * The helper will pull in non-linear data in case the skb is non-linear - * and not all of len are part of the linear section. Only needed for - * read/write with direct packet access. - * @skb: pointer to skb - * @len: len to make read/writeable - * Return: 0 on success or negative error - * - * s64 bpf_csum_update(skb, csum) - * Adds csum into skb->csum in case of CHECKSUM_COMPLETE. - * @skb: pointer to skb - * @csum: csum to add - * Return: csum on success or negative error - * - * void bpf_set_hash_invalid(skb) - * Invalidate current skb->hash. - * @skb: pointer to skb - * - * int bpf_get_numa_node_id() - * Return: Id of current NUMA node. - * - * int bpf_skb_change_head() - * Grows headroom of skb and adjusts MAC header offset accordingly. - * Will extends/reallocae as required automatically. - * May change skb data pointer and will thus invalidate any check - * performed for direct packet access. - * @skb: pointer to skb - * @len: length of header to be pushed in front - * @flags: Flags (unused for now) - * Return: 0 on success or negative error - * - * int bpf_xdp_adjust_head(xdp_md, delta) - * Adjust the xdp_md.data by delta - * @xdp_md: pointer to xdp_md - * @delta: An positive/negative integer to be added to xdp_md.data - * Return: 0 on success or negative on error + * Return + * A pointer to the current task struct. + * + * int bpf_probe_write_user(void *dst, const void *src, u32 len) + * Description + * Attempt in a safe way to write *len* bytes from the buffer + * *src* to *dst* in memory. It only works for threads that are in + * user context, and *dst* must be a valid user space address. + * + * This helper should not be used to implement any kind of + * security mechanism because of TOC-TOU attacks, but rather to + * debug, divert, and manipulate execution of semi-cooperative + * processes. + * + * Keep in mind that this feature is meant for experiments, and it + * has a risk of crashing the system and running programs. + * Therefore, when an eBPF program using this helper is attached, + * a warning including PID and process name is printed to kernel + * logs. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_current_task_under_cgroup(struct bpf_map *map, u32 index) + * Description + * Check whether the probe is being run is the context of a given + * subset of the cgroup2 hierarchy. The cgroup2 to test is held by + * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*. + * Return + * The return value depends on the result of the test, and can be: + * + * * 0, if the *skb* task belongs to the cgroup2. + * * 1, if the *skb* task does not belong to the cgroup2. + * * A negative error code, if an error occurred. + * + * int bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags) + * Description + * Resize (trim or grow) the packet associated to *skb* to the + * new *len*. The *flags* are reserved for future usage, and must + * be left at zero. + * + * The basic idea is that the helper performs the needed work to + * change the size of the packet, then the eBPF program rewrites + * the rest via helpers like **bpf_skb_store_bytes**\ (), + * **bpf_l3_csum_replace**\ (), **bpf_l3_csum_replace**\ () + * and others. This helper is a slow path utility intended for + * replies with control messages. And because it is targeted for + * slow path, the helper itself can afford to be slow: it + * implicitly linearizes, unclones and drops offloads from the + * *skb*. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_pull_data(struct sk_buff *skb, u32 len) + * Description + * Pull in non-linear data in case the *skb* is non-linear and not + * all of *len* are part of the linear section. Make *len* bytes + * from *skb* readable and writable. If a zero value is passed for + * *len*, then the whole length of the *skb* is pulled. + * + * This helper is only needed for reading and writing with direct + * packet access. + * + * For direct packet access, testing that offsets to access + * are within packet boundaries (test on *skb*\ **->data_end**) is + * susceptible to fail if offsets are invalid, or if the requested + * data is in non-linear parts of the *skb*. On failure the + * program can just bail out, or in the case of a non-linear + * buffer, use a helper to make the data available. The + * **bpf_skb_load_bytes**\ () helper is a first solution to access + * the data. Another one consists in using **bpf_skb_pull_data** + * to pull in once the non-linear parts, then retesting and + * eventually access the data. + * + * At the same time, this also makes sure the *skb* is uncloned, + * which is a necessary condition for direct write. As this needs + * to be an invariant for the write part only, the verifier + * detects writes and adds a prologue that is calling + * **bpf_skb_pull_data()** to effectively unclone the *skb* from + * the very beginning in case it is indeed cloned. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * s64 bpf_csum_update(struct sk_buff *skb, __wsum csum) + * Description + * Add the checksum *csum* into *skb*\ **->csum** in case the + * driver has supplied a checksum for the entire packet into that + * field. Return an error otherwise. This helper is intended to be + * used in combination with **bpf_csum_diff**\ (), in particular + * when the checksum needs to be updated after data has been + * written into the packet through direct packet access. + * Return + * The checksum on success, or a negative error code in case of + * failure. + * + * void bpf_set_hash_invalid(struct sk_buff *skb) + * Description + * Invalidate the current *skb*\ **->hash**. It can be used after + * mangling on headers through direct packet access, in order to + * indicate that the hash is outdated and to trigger a + * recalculation the next time the kernel tries to access this + * hash or when the **bpf_get_hash_recalc**\ () helper is called. + * + * int bpf_get_numa_node_id(void) + * Description + * Return the id of the current NUMA node. The primary use case + * for this helper is the selection of sockets for the local NUMA + * node, when the program is attached to sockets using the + * **SO_ATTACH_REUSEPORT_EBPF** option (see also **socket(7)**), + * but the helper is also available to other eBPF program types, + * similarly to **bpf_get_smp_processor_id**\ (). + * Return + * The id of current NUMA node. + * + * int bpf_skb_change_head(struct sk_buff *skb, u32 len, u64 flags) + * Description + * Grows headroom of packet associated to *skb* and adjusts the + * offset of the MAC header accordingly, adding *len* bytes of + * space. It automatically extends and reallocates memory as + * required. + * + * This helper can be used on a layer 3 *skb* to push a MAC header + * for redirection into a layer 2 device. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_xdp_adjust_head(struct xdp_buff *xdp_md, int delta) + * Description + * Adjust (move) *xdp_md*\ **->data** by *delta* bytes. Note that + * it is possible to use a negative value for *delta*. This helper + * can be used to prepare the packet for pushing or popping + * headers. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. * * int bpf_probe_read_str(void *dst, int size, const void *unsafe_ptr) - * Copy a NUL terminated string from unsafe address. In case the string - * length is smaller than size, the target is not padded with further NUL - * bytes. In case the string length is larger than size, just count-1 - * bytes are copied and the last byte is set to NUL. - * @dst: destination address - * @size: maximum number of bytes to copy, including the trailing NUL - * @unsafe_ptr: unsafe address - * Return: - * > 0 length of the string including the trailing NUL on success - * < 0 error - * - * u64 bpf_get_socket_cookie(skb) - * Get the cookie for the socket stored inside sk_buff. - * @skb: pointer to skb - * Return: 8 Bytes non-decreasing number on success or 0 if the socket - * field is missing inside sk_buff - * - * u32 bpf_get_socket_uid(skb) - * Get the owner uid of the socket stored inside sk_buff. - * @skb: pointer to skb - * Return: uid of the socket owner on success or overflowuid if failed. - * - * u32 bpf_set_hash(skb, hash) - * Set full skb->hash. - * @skb: pointer to skb - * @hash: hash to set - * - * int bpf_setsockopt(bpf_socket, level, optname, optval, optlen) - * Calls setsockopt. Not all opts are available, only those with - * integer optvals plus TCP_CONGESTION. - * Supported levels: SOL_SOCKET and IPPROTO_TCP - * @bpf_socket: pointer to bpf_socket - * @level: SOL_SOCKET or IPPROTO_TCP - * @optname: option name - * @optval: pointer to option value - * @optlen: length of optval in bytes - * Return: 0 or negative error - * - * int bpf_getsockopt(bpf_socket, level, optname, optval, optlen) - * Calls getsockopt. Not all opts are available. - * Supported levels: IPPROTO_TCP - * @bpf_socket: pointer to bpf_socket - * @level: IPPROTO_TCP - * @optname: option name - * @optval: pointer to option value - * @optlen: length of optval in bytes - * Return: 0 or negative error - * - * int bpf_sock_ops_cb_flags_set(bpf_sock_ops, flags) - * Set callback flags for sock_ops - * @bpf_sock_ops: pointer to bpf_sock_ops_kern struct - * @flags: flags value - * Return: 0 for no error - * -EINVAL if there is no full tcp socket - * bits in flags that are not supported by current kernel - * - * int bpf_skb_adjust_room(skb, len_diff, mode, flags) - * Grow or shrink room in sk_buff. - * @skb: pointer to skb - * @len_diff: (signed) amount of room to grow/shrink - * @mode: operation mode (enum bpf_adj_room_mode) - * @flags: reserved for future use - * Return: 0 on success or negative error code - * - * int bpf_sk_redirect_map(map, key, flags) - * Redirect skb to a sock in map using key as a lookup key for the - * sock in map. - * @map: pointer to sockmap - * @key: key to lookup sock in map - * @flags: reserved for future use - * Return: SK_PASS - * - * int bpf_sock_map_update(skops, map, key, flags) - * @skops: pointer to bpf_sock_ops - * @map: pointer to sockmap to update - * @key: key to insert/update sock in map - * @flags: same flags as map update elem - * - * int bpf_xdp_adjust_meta(xdp_md, delta) - * Adjust the xdp_md.data_meta by delta - * @xdp_md: pointer to xdp_md - * @delta: An positive/negative integer to be added to xdp_md.data_meta - * Return: 0 on success or negative on error - * - * int bpf_perf_event_read_value(map, flags, buf, buf_size) - * read perf event counter value and perf event enabled/running time - * @map: pointer to perf_event_array map - * @flags: index of event in the map or bitmask flags - * @buf: buf to fill - * @buf_size: size of the buf - * Return: 0 on success or negative error code - * - * int bpf_perf_prog_read_value(ctx, buf, buf_size) - * read perf prog attached perf event counter and enabled/running time - * @ctx: pointer to ctx - * @buf: buf to fill - * @buf_size: size of the buf - * Return : 0 on success or negative error code - * - * int bpf_override_return(pt_regs, rc) - * @pt_regs: pointer to struct pt_regs - * @rc: the return value to set - * - * int bpf_msg_redirect_map(map, key, flags) - * Redirect msg to a sock in map using key as a lookup key for the - * sock in map. - * @map: pointer to sockmap - * @key: key to lookup sock in map - * @flags: reserved for future use - * Return: SK_PASS - * - * int bpf_bind(ctx, addr, addr_len) - * Bind socket to address. Only binding to IP is supported, no port can be - * set in addr. - * @ctx: pointer to context of type bpf_sock_addr - * @addr: pointer to struct sockaddr to bind socket to - * @addr_len: length of sockaddr structure - * Return: 0 on success or negative error code + * Description + * Copy a NUL terminated string from an unsafe address + * *unsafe_ptr* to *dst*. The *size* should include the + * terminating NUL byte. In case the string length is smaller than + * *size*, the target is not padded with further NUL bytes. If the + * string length is larger than *size*, just *size*-1 bytes are + * copied and the last byte is set to NUL. + * + * On success, the length of the copied string is returned. This + * makes this helper useful in tracing programs for reading + * strings, and more importantly to get its length at runtime. See + * the following snippet: + * + * :: + * + * SEC("kprobe/sys_open") + * void bpf_sys_open(struct pt_regs *ctx) + * { + * char buf[PATHLEN]; // PATHLEN is defined to 256 + * int res = bpf_probe_read_str(buf, sizeof(buf), + * ctx->di); + * + * // Consume buf, for example push it to + * // userspace via bpf_perf_event_output(); we + * // can use res (the string length) as event + * // size, after checking its boundaries. + * } + * + * In comparison, using **bpf_probe_read()** helper here instead + * to read the string would require to estimate the length at + * compile time, and would often result in copying more memory + * than necessary. + * + * Another useful use case is when parsing individual process + * arguments or individual environment variables navigating + * *current*\ **->mm->arg_start** and *current*\ + * **->mm->env_start**: using this helper and the return value, + * one can quickly iterate at the right offset of the memory area. + * Return + * On success, the strictly positive length of the string, + * including the trailing NUL character. On error, a negative + * value. + * + * u64 bpf_get_socket_cookie(struct sk_buff *skb) + * Description + * If the **struct sk_buff** pointed by *skb* has a known socket, + * retrieve the cookie (generated by the kernel) of this socket. + * If no cookie has been set yet, generate a new cookie. Once + * generated, the socket cookie remains stable for the life of the + * socket. This helper can be useful for monitoring per socket + * networking traffic statistics as it provides a unique socket + * identifier per namespace. + * Return + * A 8-byte long non-decreasing number on success, or 0 if the + * socket field is missing inside *skb*. + * + * u32 bpf_get_socket_uid(struct sk_buff *skb) + * Return + * The owner UID of the socket associated to *skb*. If the socket + * is **NULL**, or if it is not a full socket (i.e. if it is a + * time-wait or a request socket instead), **overflowuid** value + * is returned (note that **overflowuid** might also be the actual + * UID value for the socket). + * + * u32 bpf_set_hash(struct sk_buff *skb, u32 hash) + * Description + * Set the full hash for *skb* (set the field *skb*\ **->hash**) + * to value *hash*. + * Return + * 0 + * + * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *optval, int optlen) + * Description + * Emulate a call to **setsockopt()** on the socket associated to + * *bpf_socket*, which must be a full socket. The *level* at + * which the option resides and the name *optname* of the option + * must be specified, see **setsockopt(2)** for more information. + * The option value of length *optlen* is pointed by *optval*. + * + * This helper actually implements a subset of **setsockopt()**. + * It supports the following *level*\ s: + * + * * **SOL_SOCKET**, which supports the following *optname*\ s: + * **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**, + * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**. + * * **IPPROTO_TCP**, which supports the following *optname*\ s: + * **TCP_CONGESTION**, **TCP_BPF_IW**, + * **TCP_BPF_SNDCWND_CLAMP**. + * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. + * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_adjust_room(struct sk_buff *skb, u32 len_diff, u32 mode, u64 flags) + * Description + * Grow or shrink the room for data in the packet associated to + * *skb* by *len_diff*, and according to the selected *mode*. + * + * There is a single supported mode at this time: + * + * * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer + * (room space is added or removed below the layer 3 header). + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_redirect_map(struct bpf_map *map, u32 key, u64 flags) + * Description + * Redirect the packet to the endpoint referenced by *map* at + * index *key*. Depending on its type, this *map* can contain + * references to net devices (for forwarding packets through other + * ports), or to CPUs (for redirecting XDP frames to another CPU; + * but this is only implemented for native XDP (with driver + * support) as of this writing). + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * When used to redirect packets to net devices, this helper + * provides a high performance increase over **bpf_redirect**\ (). + * This is due to various implementation details of the underlying + * mechanisms, one of which is the fact that **bpf_redirect_map**\ + * () tries to send packet as a "bulk" to the device. + * Return + * **XDP_REDIRECT** on success, or **XDP_ABORTED** on error. + * + * int bpf_sk_redirect_map(struct bpf_map *map, u32 key, u64 flags) + * Description + * Redirect the packet to the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * int bpf_sock_map_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags) + * Description + * Add an entry to, or update a *map* referencing sockets. The + * *skops* is used as a new value for the entry associated to + * *key*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * If the *map* has eBPF programs (parser and verdict), those will + * be inherited by the socket being added. If the socket is + * already attached to eBPF programs, this results in an error. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_xdp_adjust_meta(struct xdp_buff *xdp_md, int delta) + * Description + * Adjust the address pointed by *xdp_md*\ **->data_meta** by + * *delta* (which can be positive or negative). Note that this + * operation modifies the address stored in *xdp_md*\ **->data**, + * so the latter must be loaded only after the helper has been + * called. + * + * The use of *xdp_md*\ **->data_meta** is optional and programs + * are not required to use it. The rationale is that when the + * packet is processed with XDP (e.g. as DoS filter), it is + * possible to push further meta data along with it before passing + * to the stack, and to give the guarantee that an ingress eBPF + * program attached as a TC classifier on the same device can pick + * this up for further post-processing. Since TC works with socket + * buffers, it remains possible to set from XDP the **mark** or + * **priority** pointers, or other pointers for the socket buffer. + * Having this scratch space generic and programmable allows for + * more flexibility as the user is free to store whatever meta + * data they need. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_perf_event_read_value(struct bpf_map *map, u64 flags, struct bpf_perf_event_value *buf, u32 buf_size) + * Description + * Read the value of a perf event counter, and store it into *buf* + * of size *buf_size*. This helper relies on a *map* of type + * **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of the perf event + * counter is selected when *map* is updated with perf event file + * descriptors. The *map* is an array whose size is the number of + * available CPUs, and each cell contains a value relative to one + * CPU. The value to retrieve is indicated by *flags*, that + * contains the index of the CPU to look up, masked with + * **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to + * **BPF_F_CURRENT_CPU** to indicate that the value for the + * current CPU should be retrieved. + * + * This helper behaves in a way close to + * **bpf_perf_event_read**\ () helper, save that instead of + * just returning the value observed, it fills the *buf* + * structure. This allows for additional data to be retrieved: in + * particular, the enabled and running times (in *buf*\ + * **->enabled** and *buf*\ **->running**, respectively) are + * copied. In general, **bpf_perf_event_read_value**\ () is + * recommended over **bpf_perf_event_read**\ (), which has some + * ABI issues and provides fewer functionalities. + * + * These values are interesting, because hardware PMU (Performance + * Monitoring Unit) counters are limited resources. When there are + * more PMU based perf events opened than available counters, + * kernel will multiplex these events so each event gets certain + * percentage (but not all) of the PMU time. In case that + * multiplexing happens, the number of samples or counter value + * will not reflect the case compared to when no multiplexing + * occurs. This makes comparison between different runs difficult. + * Typically, the counter value should be normalized before + * comparing to other experiments. The usual normalization is done + * as follows. + * + * :: + * + * normalized_counter = counter * t_enabled / t_running + * + * Where t_enabled is the time enabled for event and t_running is + * the time running for event since last normalization. The + * enabled and running times are accumulated since the perf event + * open. To achieve scaling factor between two invocations of an + * eBPF program, users can can use CPU id as the key (which is + * typical for perf array usage model) to remember the previous + * value and do the calculation inside the eBPF program. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size) + * Description + * For en eBPF program attached to a perf event, retrieve the + * value of the event counter associated to *ctx* and store it in + * the structure pointed by *buf* and of size *buf_size*. Enabled + * and running times are also stored in the structure (see + * description of helper **bpf_perf_event_read_value**\ () for + * more details). + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *optval, int optlen) + * Description + * Emulate a call to **getsockopt()** on the socket associated to + * *bpf_socket*, which must be a full socket. The *level* at + * which the option resides and the name *optname* of the option + * must be specified, see **getsockopt(2)** for more information. + * The retrieved value is stored in the structure pointed by + * *opval* and of length *optlen*. + * + * This helper actually implements a subset of **getsockopt()**. + * It supports the following *level*\ s: + * + * * **IPPROTO_TCP**, which supports *optname* + * **TCP_CONGESTION**. + * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. + * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_override_return(struct pt_reg *regs, u64 rc) + * Description + * Used for error injection, this helper uses kprobes to override + * the return value of the probed function, and to set it to *rc*. + * The first argument is the context *regs* on which the kprobe + * works. + * + * This helper works by setting setting the PC (program counter) + * to an override function which is run in place of the original + * probed function. This means the probed function is not run at + * all. The replacement function just returns with the required + * value. + * + * This helper has security implications, and thus is subject to + * restrictions. It is only available if the kernel was compiled + * with the **CONFIG_BPF_KPROBE_OVERRIDE** configuration + * option, and in this case it only works on functions tagged with + * **ALLOW_ERROR_INJECTION** in the kernel code. + * + * Also, the helper is only available for the architectures having + * the CONFIG_FUNCTION_ERROR_INJECTION option. As of this writing, + * x86 architecture is the only one to support this feature. + * Return + * 0 + * + * int bpf_sock_ops_cb_flags_set(struct bpf_sock_ops *bpf_sock, int argval) + * Description + * Attempt to set the value of the **bpf_sock_ops_cb_flags** field + * for the full TCP socket associated to *bpf_sock_ops* to + * *argval*. + * + * The primary use of this field is to determine if there should + * be calls to eBPF programs of type + * **BPF_PROG_TYPE_SOCK_OPS** at various points in the TCP + * code. A program of the same type can change its value, per + * connection and as necessary, when the connection is + * established. This field is directly accessible for reading, but + * this helper must be used for updates in order to return an + * error if an eBPF program tries to set a callback that is not + * supported in the current kernel. + * + * The supported callback values that *argval* can combine are: + * + * * **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out) + * * **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission) + * * **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change) + * + * Here are some examples of where one could call such eBPF + * program: + * + * * When RTO fires. + * * When a packet is retransmitted. + * * When the connection terminates. + * * When a packet is sent. + * * When a packet is received. + * Return + * Code **-EINVAL** if the socket is not a full TCP socket; + * otherwise, a positive number containing the bits that could not + * be set is returned (which comes down to 0 if all bits were set + * as required). + * + * int bpf_msg_redirect_map(struct sk_msg_buff *msg, struct bpf_map *map, u32 key, u64 flags) + * Description + * This helper is used in programs implementing policies at the + * socket level. If the message *msg* is allowed to pass (i.e. if + * the verdict eBPF program returns **SK_PASS**), redirect it to + * the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * int bpf_msg_apply_bytes(struct sk_msg_buff *msg, u32 bytes) + * Description + * For socket policies, apply the verdict of the eBPF program to + * the next *bytes* (number of bytes) of message *msg*. + * + * For example, this helper can be used in the following cases: + * + * * A single **sendmsg**\ () or **sendfile**\ () system call + * contains multiple logical messages that the eBPF program is + * supposed to read and for which it should apply a verdict. + * * An eBPF program only cares to read the first *bytes* of a + * *msg*. If the message has a large payload, then setting up + * and calling the eBPF program repeatedly for all bytes, even + * though the verdict is already known, would create unnecessary + * overhead. + * + * When called from within an eBPF program, the helper sets a + * counter internal to the BPF infrastructure, that is used to + * apply the last verdict to the next *bytes*. If *bytes* is + * smaller than the current data being processed from a + * **sendmsg**\ () or **sendfile**\ () system call, the first + * *bytes* will be sent and the eBPF program will be re-run with + * the pointer for start of data pointing to byte number *bytes* + * **+ 1**. If *bytes* is larger than the current data being + * processed, then the eBPF verdict will be applied to multiple + * **sendmsg**\ () or **sendfile**\ () calls until *bytes* are + * consumed. + * + * Note that if a socket closes with the internal counter holding + * a non-zero value, this is not a problem because data is not + * being buffered for *bytes* and is sent as it is received. + * Return + * 0 + * + * int bpf_msg_cork_bytes(struct sk_msg_buff *msg, u32 bytes) + * Description + * For socket policies, prevent the execution of the verdict eBPF + * program for message *msg* until *bytes* (byte number) have been + * accumulated. + * + * This can be used when one needs a specific number of bytes + * before a verdict can be assigned, even if the data spans + * multiple **sendmsg**\ () or **sendfile**\ () calls. The extreme + * case would be a user calling **sendmsg**\ () repeatedly with + * 1-byte long message segments. Obviously, this is bad for + * performance, but it is still valid. If the eBPF program needs + * *bytes* bytes to validate a header, this helper can be used to + * prevent the eBPF program to be called again until *bytes* have + * been accumulated. + * Return + * 0 + * + * int bpf_msg_pull_data(struct sk_msg_buff *msg, u32 start, u32 end, u64 flags) + * Description + * For socket policies, pull in non-linear data from user space + * for *msg* and set pointers *msg*\ **->data** and *msg*\ + * **->data_end** to *start* and *end* bytes offsets into *msg*, + * respectively. + * + * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a + * *msg* it can only parse data that the (**data**, **data_end**) + * pointers have already consumed. For **sendmsg**\ () hooks this + * is likely the first scatterlist element. But for calls relying + * on the **sendpage** handler (e.g. **sendfile**\ ()) this will + * be the range (**0**, **0**) because the data is shared with + * user space and by default the objective is to avoid allowing + * user space to modify data while (or after) eBPF verdict is + * being decided. This helper can be used to pull in data and to + * set the start and end pointer to given values. Data will be + * copied if necessary (i.e. if data was not linear and if start + * and end pointers do not point to the same chunk). + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_bind(struct bpf_sock_addr *ctx, struct sockaddr *addr, int addr_len) + * Description + * Bind the socket associated to *ctx* to the address pointed by + * *addr*, of length *addr_len*. This allows for making outgoing + * connection from the desired IP address, which can be useful for + * example when all processes inside a cgroup should use one + * single IP address on a host that has multiple IP configured. + * + * This helper works for IPv4 and IPv6, TCP and UDP sockets. The + * domain (*addr*\ **->sa_family**) must be **AF_INET** (or + * **AF_INET6**). Looking for a free port to bind to can be + * expensive, therefore binding to port is not permitted by the + * helper: *addr*\ **->sin_port** (or **sin6_port**, respectively) + * must be set to zero. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_xdp_adjust_tail(struct xdp_buff *xdp_md, int delta) + * Description + * Adjust (move) *xdp_md*\ **->data_end** by *delta* bytes. It is + * only possible to shrink the packet as of this writing, + * therefore *delta* must be a negative integer. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_get_xfrm_state(struct sk_buff *skb, u32 index, struct bpf_xfrm_state *xfrm_state, u32 size, u64 flags) + * Description + * Retrieve the XFRM state (IP transform framework, see also + * **ip-xfrm(8)**) at *index* in XFRM "security path" for *skb*. + * + * The retrieved value is stored in the **struct bpf_xfrm_state** + * pointed by *xfrm_state* and of length *size*. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_XFRM** configuration option. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_get_stack(struct pt_regs *regs, void *buf, u32 size, u64 flags) + * Description + * Return a user or a kernel stack in bpf program provided buffer. + * To achieve this, the helper needs *ctx*, which is a pointer + * to the context on which the tracing program is executed. + * To store the stacktrace, the bpf program provides *buf* with + * a nonnegative *size*. + * + * The last argument, *flags*, holds the number of stack frames to + * skip (from 0 to 255), masked with + * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set + * the following flags: + * + * **BPF_F_USER_STACK** + * Collect a user space stack instead of a kernel stack. + * **BPF_F_USER_BUILD_ID** + * Collect buildid+offset instead of ips for user stack, + * only valid if **BPF_F_USER_STACK** is also specified. + * + * **bpf_get_stack**\ () can collect up to + * **PERF_MAX_STACK_DEPTH** both kernel and user frames, subject + * to sufficient large buffer size. Note that + * this limit can be controlled with the **sysctl** program, and + * that it should be manually increased in order to profile long + * user stacks (such as stacks for Java programs). To do so, use: + * + * :: + * + * # sysctl kernel.perf_event_max_stack=<new value> + * Return + * A non-negative value equal to or less than *size* on success, + * or a negative error in case of failure. + * + * int skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header) + * Description + * This helper is similar to **bpf_skb_load_bytes**\ () in that + * it provides an easy way to load *len* bytes from *offset* + * from the packet associated to *skb*, into the buffer pointed + * by *to*. The difference to **bpf_skb_load_bytes**\ () is that + * a fifth argument *start_header* exists in order to select a + * base offset to start from. *start_header* can be one of: + * + * **BPF_HDR_START_MAC** + * Base offset to load data from is *skb*'s mac header. + * **BPF_HDR_START_NET** + * Base offset to load data from is *skb*'s network header. + * + * In general, "direct packet access" is the preferred method to + * access packet data, however, this helper is in particular useful + * in socket filters where *skb*\ **->data** does not always point + * to the start of the mac header and where "direct packet access" + * is not available. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_fib_lookup(void *ctx, struct bpf_fib_lookup *params, int plen, u32 flags) + * Description + * Do FIB lookup in kernel tables using parameters in *params*. + * If lookup is successful and result shows packet is to be + * forwarded, the neighbor tables are searched for the nexthop. + * If successful (ie., FIB lookup shows forwarding and nexthop + * is resolved), the nexthop address is returned in ipv4_dst + * or ipv6_dst based on family, smac is set to mac address of + * egress device, dmac is set to nexthop mac address, rt_metric + * is set to metric from route (IPv4/IPv6 only). + * + * *plen* argument is the size of the passed in struct. + * *flags* argument can be a combination of one or more of the + * following values: + * + * **BPF_FIB_LOOKUP_DIRECT** + * Do a direct table lookup vs full lookup using FIB + * rules. + * **BPF_FIB_LOOKUP_OUTPUT** + * Perform lookup from an egress perspective (default is + * ingress). + * + * *ctx* is either **struct xdp_md** for XDP programs or + * **struct sk_buff** tc cls_act programs. + * Return + * Egress device index on success, 0 if packet needs to continue + * up the stack for further processing or a negative error in case + * of failure. + * + * int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags) + * Description + * Add an entry to, or update a sockhash *map* referencing sockets. + * The *skops* is used as a new value for the entry associated to + * *key*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * If the *map* has eBPF programs (parser and verdict), those will + * be inherited by the socket being added. If the socket is + * already attached to eBPF programs, this results in an error. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_msg_redirect_hash(struct sk_msg_buff *msg, struct bpf_map *map, void *key, u64 flags) + * Description + * This helper is used in programs implementing policies at the + * socket level. If the message *msg* is allowed to pass (i.e. if + * the verdict eBPF program returns **SK_PASS**), redirect it to + * the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * int bpf_sk_redirect_hash(struct sk_buff *skb, struct bpf_map *map, void *key, u64 flags) + * Description + * This helper is used in programs implementing policies at the + * skb socket level. If the sk_buff *skb* is allowed to pass (i.e. + * if the verdeict eBPF program returns **SK_PASS**), redirect it + * to the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * int bpf_lwt_push_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len) + * Description + * Encapsulate the packet associated to *skb* within a Layer 3 + * protocol header. This header is provided in the buffer at + * address *hdr*, with *len* its size in bytes. *type* indicates + * the protocol of the header and can be one of: + * + * **BPF_LWT_ENCAP_SEG6** + * IPv6 encapsulation with Segment Routing Header + * (**struct ipv6_sr_hdr**). *hdr* only contains the SRH, + * the IPv6 header is computed by the kernel. + * **BPF_LWT_ENCAP_SEG6_INLINE** + * Only works if *skb* contains an IPv6 packet. Insert a + * Segment Routing Header (**struct ipv6_sr_hdr**) inside + * the IPv6 header. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_lwt_seg6_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len) + * Description + * Store *len* bytes from address *from* into the packet + * associated to *skb*, at *offset*. Only the flags, tag and TLVs + * inside the outermost IPv6 Segment Routing Header can be + * modified through this helper. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_lwt_seg6_adjust_srh(struct sk_buff *skb, u32 offset, s32 delta) + * Description + * Adjust the size allocated to TLVs in the outermost IPv6 + * Segment Routing Header contained in the packet associated to + * *skb*, at position *offset* by *delta* bytes. Only offsets + * after the segments are accepted. *delta* can be as well + * positive (growing) as negative (shrinking). + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_lwt_seg6_action(struct sk_buff *skb, u32 action, void *param, u32 param_len) + * Description + * Apply an IPv6 Segment Routing action of type *action* to the + * packet associated to *skb*. Each action takes a parameter + * contained at address *param*, and of length *param_len* bytes. + * *action* can be one of: + * + * **SEG6_LOCAL_ACTION_END_X** + * End.X action: Endpoint with Layer-3 cross-connect. + * Type of *param*: **struct in6_addr**. + * **SEG6_LOCAL_ACTION_END_T** + * End.T action: Endpoint with specific IPv6 table lookup. + * Type of *param*: **int**. + * **SEG6_LOCAL_ACTION_END_B6** + * End.B6 action: Endpoint bound to an SRv6 policy. + * Type of param: **struct ipv6_sr_hdr**. + * **SEG6_LOCAL_ACTION_END_B6_ENCAP** + * End.B6.Encap action: Endpoint bound to an SRv6 + * encapsulation policy. + * Type of param: **struct ipv6_sr_hdr**. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle) + * Description + * This helper is used in programs implementing IR decoding, to + * report a successfully decoded key press with *scancode*, + * *toggle* value in the given *protocol*. The scancode will be + * translated to a keycode using the rc keymap, and reported as + * an input key down event. After a period a key up event is + * generated. This period can be extended by calling either + * **bpf_rc_keydown** () again with the same values, or calling + * **bpf_rc_repeat** (). + * + * Some protocols include a toggle bit, in case the button was + * released and pressed again between consecutive scancodes. + * + * The *ctx* should point to the lirc sample as passed into + * the program. + * + * The *protocol* is the decoded protocol number (see + * **enum rc_proto** for some predefined values). + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_BPF_LIRC_MODE2** configuration option set to + * "**y**". + * + * Return + * 0 + * + * int bpf_rc_repeat(void *ctx) + * Description + * This helper is used in programs implementing IR decoding, to + * report a successfully decoded repeat key message. This delays + * the generation of a key up event for previously generated + * key down event. + * + * Some IR protocols like NEC have a special IR message for + * repeating last button, for when a button is held down. + * + * The *ctx* should point to the lirc sample as passed into + * the program. + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_BPF_LIRC_MODE2** configuration option set to + * "**y**". + * + * Return + * 0 + * + * uint64_t bpf_skb_cgroup_id(struct sk_buff *skb) + * Description + * Return the cgroup v2 id of the socket associated with the *skb*. + * This is roughly similar to the **bpf_get_cgroup_classid**\ () + * helper for cgroup v1 by providing a tag resp. identifier that + * can be matched on or used for map lookups e.g. to implement + * policy. The cgroup v2 id of a given path in the hierarchy is + * exposed in user space through the f_handle API in order to get + * to the same 64-bit id. + * + * This helper can be used on TC egress path, but not on ingress, + * and is available only if the kernel was compiled with the + * **CONFIG_SOCK_CGROUP_DATA** configuration option. + * Return + * The id is returned or 0 in case the id could not be retrieved. + * + * u64 bpf_get_current_cgroup_id(void) + * Return + * A 64-bit integer containing the current cgroup id based + * on the cgroup within which the current task is running. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -821,7 +2141,23 @@ union bpf_attr { FN(msg_apply_bytes), \ FN(msg_cork_bytes), \ FN(msg_pull_data), \ - FN(bind), + FN(bind), \ + FN(xdp_adjust_tail), \ + FN(skb_get_xfrm_state), \ + FN(get_stack), \ + FN(skb_load_bytes_relative), \ + FN(fib_lookup), \ + FN(sock_hash_update), \ + FN(msg_redirect_hash), \ + FN(sk_redirect_hash), \ + FN(lwt_push_encap), \ + FN(lwt_seg6_store_bytes), \ + FN(lwt_seg6_adjust_srh), \ + FN(lwt_seg6_action), \ + FN(rc_repeat), \ + FN(rc_keydown), \ + FN(skb_cgroup_id), \ + FN(get_current_cgroup_id), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -855,11 +2191,14 @@ enum bpf_func_id { /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ #define BPF_F_TUNINFO_IPV6 (1ULL << 0) -/* BPF_FUNC_get_stackid flags. */ +/* flags for both BPF_FUNC_get_stackid and BPF_FUNC_get_stack. */ #define BPF_F_SKIP_FIELD_MASK 0xffULL #define BPF_F_USER_STACK (1ULL << 8) +/* flags used by BPF_FUNC_get_stackid only. */ #define BPF_F_FAST_STACK_CMP (1ULL << 9) #define BPF_F_REUSE_STACKID (1ULL << 10) +/* flags used by BPF_FUNC_get_stack only. */ +#define BPF_F_USER_BUILD_ID (1ULL << 11) /* BPF_FUNC_skb_set_tunnel_key flags. */ #define BPF_F_ZERO_CSUM_TX (1ULL << 1) @@ -879,6 +2218,18 @@ enum bpf_adj_room_mode { BPF_ADJ_ROOM_NET, }; +/* Mode for BPF_FUNC_skb_load_bytes_relative helper. */ +enum bpf_hdr_start_off { + BPF_HDR_START_MAC, + BPF_HDR_START_NET, +}; + +/* Encapsulation type for BPF_FUNC_lwt_push_encap helper. */ +enum bpf_lwt_encap_mode { + BPF_LWT_ENCAP_SEG6, + BPF_LWT_ENCAP_SEG6_INLINE +}; + /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure */ @@ -923,10 +2274,24 @@ struct bpf_tunnel_key { }; __u8 tunnel_tos; __u8 tunnel_ttl; - __u16 tunnel_ext; + __u16 tunnel_ext; /* Padding, future use. */ __u32 tunnel_label; }; +/* user accessible mirror of in-kernel xfrm_state. + * new fields can only be added to the end of this structure + */ +struct bpf_xfrm_state { + __u32 reqid; + __u32 spi; /* Stored in network byte order */ + __u16 family; + __u16 ext; /* Padding, future use. */ + union { + __u32 remote_ipv4; /* Stored in network byte order */ + __u32 remote_ipv6[4]; /* Stored in network byte order */ + }; +}; + /* Generic BPF return codes which all BPF program types may support. * The values are binary compatible with their TC_ACT_* counter-part to * provide backwards compatibility with existing SCHED_CLS and SCHED_ACT @@ -999,6 +2364,14 @@ enum sk_action { struct sk_msg_md { void *data; void *data_end; + + __u32 family; + __u32 remote_ip4; /* Stored in network byte order */ + __u32 local_ip4; /* Stored in network byte order */ + __u32 remote_ip6[4]; /* Stored in network byte order */ + __u32 local_ip6[4]; /* Stored in network byte order */ + __u32 remote_port; /* Stored in network byte order */ + __u32 local_port; /* stored in host byte order */ }; #define BPF_TAG_SIZE 8 @@ -1017,8 +2390,13 @@ struct bpf_prog_info { __aligned_u64 map_ids; char name[BPF_OBJ_NAME_LEN]; __u32 ifindex; + __u32 gpl_compatible:1; __u64 netns_dev; __u64 netns_ino; + __u32 nr_jited_ksyms; + __u32 nr_jited_func_lens; + __aligned_u64 jited_ksyms; + __aligned_u64 jited_func_lens; } __attribute__((aligned(8))); struct bpf_map_info { @@ -1030,8 +2408,18 @@ struct bpf_map_info { __u32 map_flags; char name[BPF_OBJ_NAME_LEN]; __u32 ifindex; + __u32 :32; __u64 netns_dev; __u64 netns_ino; + __u32 btf_id; + __u32 btf_key_type_id; + __u32 btf_value_type_id; +} __attribute__((aligned(8))); + +struct bpf_btf_info { + __aligned_u64 btf; + __u32 btf_size; + __u32 id; } __attribute__((aligned(8))); /* User bpf_sock_addr struct to access socket fields and sockaddr struct passed @@ -1052,6 +2440,12 @@ struct bpf_sock_addr { __u32 family; /* Allows 4-byte read, but no write */ __u32 type; /* Allows 4-byte read, but no write */ __u32 protocol; /* Allows 4-byte read, but no write */ + __u32 msg_src_ip4; /* Allows 1,2,4-byte read an 4-byte write. + * Stored in network byte order. + */ + __u32 msg_src_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write. + * Stored in network byte order. + */ }; /* User bpf_sock_ops struct to access socket values and specify request ops @@ -1212,4 +2606,64 @@ struct bpf_raw_tracepoint_args { __u64 args[0]; }; +/* DIRECT: Skip the FIB rules and go to FIB table associated with device + * OUTPUT: Do lookup from egress perspective; default is ingress + */ +#define BPF_FIB_LOOKUP_DIRECT BIT(0) +#define BPF_FIB_LOOKUP_OUTPUT BIT(1) + +struct bpf_fib_lookup { + /* input: network family for lookup (AF_INET, AF_INET6) + * output: network family of egress nexthop + */ + __u8 family; + + /* set if lookup is to consider L4 data - e.g., FIB rules */ + __u8 l4_protocol; + __be16 sport; + __be16 dport; + + /* total length of packet from network header - used for MTU check */ + __u16 tot_len; + __u32 ifindex; /* L3 device index for lookup */ + + union { + /* inputs to lookup */ + __u8 tos; /* AF_INET */ + __be32 flowlabel; /* AF_INET6 */ + + /* output: metric of fib result (IPv4/IPv6 only) */ + __u32 rt_metric; + }; + + union { + __be32 ipv4_src; + __u32 ipv6_src[4]; /* in6_addr; network order */ + }; + + /* input to bpf_fib_lookup, ipv{4,6}_dst is destination address in + * network header. output: bpf_fib_lookup sets to gateway address + * if FIB lookup returns gateway route + */ + union { + __be32 ipv4_dst; + __u32 ipv6_dst[4]; /* in6_addr; network order */ + }; + + /* output */ + __be16 h_vlan_proto; + __be16 h_vlan_TCI; + __u8 smac[6]; /* ETH_ALEN */ + __u8 dmac[6]; /* ETH_ALEN */ +}; + +enum bpf_task_fd_type { + BPF_FD_TYPE_RAW_TRACEPOINT, /* tp name */ + BPF_FD_TYPE_TRACEPOINT, /* tp name */ + BPF_FD_TYPE_KPROBE, /* (symbol + offset) or addr */ + BPF_FD_TYPE_KRETPROBE, /* (symbol + offset) or addr */ + BPF_FD_TYPE_UPROBE, /* filename + offset */ + BPF_FD_TYPE_URETPROBE, /* filename + offset */ +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h new file mode 100644 index 0000000..0b5ddbe --- /dev/null +++ b/tools/include/uapi/linux/btf.h @@ -0,0 +1,113 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* Copyright (c) 2018 Facebook */ +#ifndef _UAPI__LINUX_BTF_H__ +#define _UAPI__LINUX_BTF_H__ + +#include <linux/types.h> + +#define BTF_MAGIC 0xeB9F +#define BTF_VERSION 1 + +struct btf_header { + __u16 magic; + __u8 version; + __u8 flags; + __u32 hdr_len; + + /* All offsets are in bytes relative to the end of this header */ + __u32 type_off; /* offset of type section */ + __u32 type_len; /* length of type section */ + __u32 str_off; /* offset of string section */ + __u32 str_len; /* length of string section */ +}; + +/* Max # of type identifier */ +#define BTF_MAX_TYPE 0x0000ffff +/* Max offset into the string section */ +#define BTF_MAX_NAME_OFFSET 0x0000ffff +/* Max # of struct/union/enum members or func args */ +#define BTF_MAX_VLEN 0xffff + +struct btf_type { + __u32 name_off; + /* "info" bits arrangement + * bits 0-15: vlen (e.g. # of struct's members) + * bits 16-23: unused + * bits 24-27: kind (e.g. int, ptr, array...etc) + * bits 28-31: unused + */ + __u32 info; + /* "size" is used by INT, ENUM, STRUCT and UNION. + * "size" tells the size of the type it is describing. + * + * "type" is used by PTR, TYPEDEF, VOLATILE, CONST and RESTRICT. + * "type" is a type_id referring to another type. + */ + union { + __u32 size; + __u32 type; + }; +}; + +#define BTF_INFO_KIND(info) (((info) >> 24) & 0x0f) +#define BTF_INFO_VLEN(info) ((info) & 0xffff) + +#define BTF_KIND_UNKN 0 /* Unknown */ +#define BTF_KIND_INT 1 /* Integer */ +#define BTF_KIND_PTR 2 /* Pointer */ +#define BTF_KIND_ARRAY 3 /* Array */ +#define BTF_KIND_STRUCT 4 /* Struct */ +#define BTF_KIND_UNION 5 /* Union */ +#define BTF_KIND_ENUM 6 /* Enumeration */ +#define BTF_KIND_FWD 7 /* Forward */ +#define BTF_KIND_TYPEDEF 8 /* Typedef */ +#define BTF_KIND_VOLATILE 9 /* Volatile */ +#define BTF_KIND_CONST 10 /* Const */ +#define BTF_KIND_RESTRICT 11 /* Restrict */ +#define BTF_KIND_MAX 11 +#define NR_BTF_KINDS 12 + +/* For some specific BTF_KIND, "struct btf_type" is immediately + * followed by extra data. + */ + +/* BTF_KIND_INT is followed by a u32 and the following + * is the 32 bits arrangement: + */ +#define BTF_INT_ENCODING(VAL) (((VAL) & 0x0f000000) >> 24) +#define BTF_INT_OFFSET(VAL) (((VAL & 0x00ff0000)) >> 16) +#define BTF_INT_BITS(VAL) ((VAL) & 0x0000ffff) + +/* Attributes stored in the BTF_INT_ENCODING */ +#define BTF_INT_SIGNED (1 << 0) +#define BTF_INT_CHAR (1 << 1) +#define BTF_INT_BOOL (1 << 2) + +/* BTF_KIND_ENUM is followed by multiple "struct btf_enum". + * The exact number of btf_enum is stored in the vlen (of the + * info in "struct btf_type"). + */ +struct btf_enum { + __u32 name_off; + __s32 val; +}; + +/* BTF_KIND_ARRAY is followed by one "struct btf_array" */ +struct btf_array { + __u32 type; + __u32 index_type; + __u32 nelems; +}; + +/* BTF_KIND_STRUCT and BTF_KIND_UNION are followed + * by multiple "struct btf_member". The exact number + * of btf_member is stored in the vlen (of the info in + * "struct btf_type"). + */ +struct btf_member { + __u32 name_off; + __u32 type; + __u32 offset; /* offset in bits */ +}; + +#endif /* _UAPI__LINUX_BTF_H__ */ diff --git a/tools/include/uapi/linux/erspan.h b/tools/include/uapi/linux/erspan.h new file mode 100644 index 0000000..8415730 --- /dev/null +++ b/tools/include/uapi/linux/erspan.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * ERSPAN Tunnel Metadata + * + * Copyright (c) 2018 VMware + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * Userspace API for metadata mode ERSPAN tunnel + */ +#ifndef _UAPI_ERSPAN_H +#define _UAPI_ERSPAN_H + +#include <linux/types.h> /* For __beXX in userspace */ +#include <asm/byteorder.h> + +/* ERSPAN version 2 metadata header */ +struct erspan_md2 { + __be32 timestamp; + __be16 sgt; /* security group tag */ +#if defined(__LITTLE_ENDIAN_BITFIELD) + __u8 hwid_upper:2, + ft:5, + p:1; + __u8 o:1, + gra:2, + dir:1, + hwid:4; +#elif defined(__BIG_ENDIAN_BITFIELD) + __u8 p:1, + ft:5, + hwid_upper:2; + __u8 hwid:4, + dir:1, + gra:2, + o:1; +#else +#error "Please fix <asm/byteorder.h>" +#endif +}; + +struct erspan_metadata { + int version; + union { + __be32 index; /* Version 1 (type II)*/ + struct erspan_md2 md2; /* Version 2 (type III) */ + } u; +}; + +#endif /* _UAPI_ERSPAN_H */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index b02c41e..39e364c 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -677,10 +677,10 @@ struct kvm_ioeventfd { }; #define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0) -#define KVM_X86_DISABLE_EXITS_HTL (1 << 1) +#define KVM_X86_DISABLE_EXITS_HLT (1 << 1) #define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2) #define KVM_X86_DISABLE_VALID_EXITS (KVM_X86_DISABLE_EXITS_MWAIT | \ - KVM_X86_DISABLE_EXITS_HTL | \ + KVM_X86_DISABLE_EXITS_HLT | \ KVM_X86_DISABLE_EXITS_PAUSE) /* for KVM_ENABLE_CAP */ diff --git a/tools/include/uapi/linux/lirc.h b/tools/include/uapi/linux/lirc.h new file mode 100644 index 0000000..f189931 --- /dev/null +++ b/tools/include/uapi/linux/lirc.h @@ -0,0 +1,217 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * lirc.h - linux infrared remote control header file + * last modified 2010/07/13 by Jarod Wilson + */ + +#ifndef _LINUX_LIRC_H +#define _LINUX_LIRC_H + +#include <linux/types.h> +#include <linux/ioctl.h> + +#define PULSE_BIT 0x01000000 +#define PULSE_MASK 0x00FFFFFF + +#define LIRC_MODE2_SPACE 0x00000000 +#define LIRC_MODE2_PULSE 0x01000000 +#define LIRC_MODE2_FREQUENCY 0x02000000 +#define LIRC_MODE2_TIMEOUT 0x03000000 + +#define LIRC_VALUE_MASK 0x00FFFFFF +#define LIRC_MODE2_MASK 0xFF000000 + +#define LIRC_SPACE(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_SPACE) +#define LIRC_PULSE(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_PULSE) +#define LIRC_FREQUENCY(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_FREQUENCY) +#define LIRC_TIMEOUT(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_TIMEOUT) + +#define LIRC_VALUE(val) ((val)&LIRC_VALUE_MASK) +#define LIRC_MODE2(val) ((val)&LIRC_MODE2_MASK) + +#define LIRC_IS_SPACE(val) (LIRC_MODE2(val) == LIRC_MODE2_SPACE) +#define LIRC_IS_PULSE(val) (LIRC_MODE2(val) == LIRC_MODE2_PULSE) +#define LIRC_IS_FREQUENCY(val) (LIRC_MODE2(val) == LIRC_MODE2_FREQUENCY) +#define LIRC_IS_TIMEOUT(val) (LIRC_MODE2(val) == LIRC_MODE2_TIMEOUT) + +/* used heavily by lirc userspace */ +#define lirc_t int + +/*** lirc compatible hardware features ***/ + +#define LIRC_MODE2SEND(x) (x) +#define LIRC_SEND2MODE(x) (x) +#define LIRC_MODE2REC(x) ((x) << 16) +#define LIRC_REC2MODE(x) ((x) >> 16) + +#define LIRC_MODE_RAW 0x00000001 +#define LIRC_MODE_PULSE 0x00000002 +#define LIRC_MODE_MODE2 0x00000004 +#define LIRC_MODE_SCANCODE 0x00000008 +#define LIRC_MODE_LIRCCODE 0x00000010 + + +#define LIRC_CAN_SEND_RAW LIRC_MODE2SEND(LIRC_MODE_RAW) +#define LIRC_CAN_SEND_PULSE LIRC_MODE2SEND(LIRC_MODE_PULSE) +#define LIRC_CAN_SEND_MODE2 LIRC_MODE2SEND(LIRC_MODE_MODE2) +#define LIRC_CAN_SEND_LIRCCODE LIRC_MODE2SEND(LIRC_MODE_LIRCCODE) + +#define LIRC_CAN_SEND_MASK 0x0000003f + +#define LIRC_CAN_SET_SEND_CARRIER 0x00000100 +#define LIRC_CAN_SET_SEND_DUTY_CYCLE 0x00000200 +#define LIRC_CAN_SET_TRANSMITTER_MASK 0x00000400 + +#define LIRC_CAN_REC_RAW LIRC_MODE2REC(LIRC_MODE_RAW) +#define LIRC_CAN_REC_PULSE LIRC_MODE2REC(LIRC_MODE_PULSE) +#define LIRC_CAN_REC_MODE2 LIRC_MODE2REC(LIRC_MODE_MODE2) +#define LIRC_CAN_REC_SCANCODE LIRC_MODE2REC(LIRC_MODE_SCANCODE) +#define LIRC_CAN_REC_LIRCCODE LIRC_MODE2REC(LIRC_MODE_LIRCCODE) + +#define LIRC_CAN_REC_MASK LIRC_MODE2REC(LIRC_CAN_SEND_MASK) + +#define LIRC_CAN_SET_REC_CARRIER (LIRC_CAN_SET_SEND_CARRIER << 16) +#define LIRC_CAN_SET_REC_DUTY_CYCLE (LIRC_CAN_SET_SEND_DUTY_CYCLE << 16) + +#define LIRC_CAN_SET_REC_DUTY_CYCLE_RANGE 0x40000000 +#define LIRC_CAN_SET_REC_CARRIER_RANGE 0x80000000 +#define LIRC_CAN_GET_REC_RESOLUTION 0x20000000 +#define LIRC_CAN_SET_REC_TIMEOUT 0x10000000 +#define LIRC_CAN_SET_REC_FILTER 0x08000000 + +#define LIRC_CAN_MEASURE_CARRIER 0x02000000 +#define LIRC_CAN_USE_WIDEBAND_RECEIVER 0x04000000 + +#define LIRC_CAN_SEND(x) ((x)&LIRC_CAN_SEND_MASK) +#define LIRC_CAN_REC(x) ((x)&LIRC_CAN_REC_MASK) + +#define LIRC_CAN_NOTIFY_DECODE 0x01000000 + +/*** IOCTL commands for lirc driver ***/ + +#define LIRC_GET_FEATURES _IOR('i', 0x00000000, __u32) + +#define LIRC_GET_SEND_MODE _IOR('i', 0x00000001, __u32) +#define LIRC_GET_REC_MODE _IOR('i', 0x00000002, __u32) +#define LIRC_GET_REC_RESOLUTION _IOR('i', 0x00000007, __u32) + +#define LIRC_GET_MIN_TIMEOUT _IOR('i', 0x00000008, __u32) +#define LIRC_GET_MAX_TIMEOUT _IOR('i', 0x00000009, __u32) + +/* code length in bits, currently only for LIRC_MODE_LIRCCODE */ +#define LIRC_GET_LENGTH _IOR('i', 0x0000000f, __u32) + +#define LIRC_SET_SEND_MODE _IOW('i', 0x00000011, __u32) +#define LIRC_SET_REC_MODE _IOW('i', 0x00000012, __u32) +/* Note: these can reset the according pulse_width */ +#define LIRC_SET_SEND_CARRIER _IOW('i', 0x00000013, __u32) +#define LIRC_SET_REC_CARRIER _IOW('i', 0x00000014, __u32) +#define LIRC_SET_SEND_DUTY_CYCLE _IOW('i', 0x00000015, __u32) +#define LIRC_SET_TRANSMITTER_MASK _IOW('i', 0x00000017, __u32) + +/* + * when a timeout != 0 is set the driver will send a + * LIRC_MODE2_TIMEOUT data packet, otherwise LIRC_MODE2_TIMEOUT is + * never sent, timeout is disabled by default + */ +#define LIRC_SET_REC_TIMEOUT _IOW('i', 0x00000018, __u32) + +/* 1 enables, 0 disables timeout reports in MODE2 */ +#define LIRC_SET_REC_TIMEOUT_REPORTS _IOW('i', 0x00000019, __u32) + +/* + * if enabled from the next key press on the driver will send + * LIRC_MODE2_FREQUENCY packets + */ +#define LIRC_SET_MEASURE_CARRIER_MODE _IOW('i', 0x0000001d, __u32) + +/* + * to set a range use LIRC_SET_REC_CARRIER_RANGE with the + * lower bound first and later LIRC_SET_REC_CARRIER with the upper bound + */ +#define LIRC_SET_REC_CARRIER_RANGE _IOW('i', 0x0000001f, __u32) + +#define LIRC_SET_WIDEBAND_RECEIVER _IOW('i', 0x00000023, __u32) + +/* + * struct lirc_scancode - decoded scancode with protocol for use with + * LIRC_MODE_SCANCODE + * + * @timestamp: Timestamp in nanoseconds using CLOCK_MONOTONIC when IR + * was decoded. + * @flags: should be 0 for transmit. When receiving scancodes, + * LIRC_SCANCODE_FLAG_TOGGLE or LIRC_SCANCODE_FLAG_REPEAT can be set + * depending on the protocol + * @rc_proto: see enum rc_proto + * @keycode: the translated keycode. Set to 0 for transmit. + * @scancode: the scancode received or to be sent + */ +struct lirc_scancode { + __u64 timestamp; + __u16 flags; + __u16 rc_proto; + __u32 keycode; + __u64 scancode; +}; + +/* Set if the toggle bit of rc-5 or rc-6 is enabled */ +#define LIRC_SCANCODE_FLAG_TOGGLE 1 +/* Set if this is a nec or sanyo repeat */ +#define LIRC_SCANCODE_FLAG_REPEAT 2 + +/** + * enum rc_proto - the Remote Controller protocol + * + * @RC_PROTO_UNKNOWN: Protocol not known + * @RC_PROTO_OTHER: Protocol known but proprietary + * @RC_PROTO_RC5: Philips RC5 protocol + * @RC_PROTO_RC5X_20: Philips RC5x 20 bit protocol + * @RC_PROTO_RC5_SZ: StreamZap variant of RC5 + * @RC_PROTO_JVC: JVC protocol + * @RC_PROTO_SONY12: Sony 12 bit protocol + * @RC_PROTO_SONY15: Sony 15 bit protocol + * @RC_PROTO_SONY20: Sony 20 bit protocol + * @RC_PROTO_NEC: NEC protocol + * @RC_PROTO_NECX: Extended NEC protocol + * @RC_PROTO_NEC32: NEC 32 bit protocol + * @RC_PROTO_SANYO: Sanyo protocol + * @RC_PROTO_MCIR2_KBD: RC6-ish MCE keyboard + * @RC_PROTO_MCIR2_MSE: RC6-ish MCE mouse + * @RC_PROTO_RC6_0: Philips RC6-0-16 protocol + * @RC_PROTO_RC6_6A_20: Philips RC6-6A-20 protocol + * @RC_PROTO_RC6_6A_24: Philips RC6-6A-24 protocol + * @RC_PROTO_RC6_6A_32: Philips RC6-6A-32 protocol + * @RC_PROTO_RC6_MCE: MCE (Philips RC6-6A-32 subtype) protocol + * @RC_PROTO_SHARP: Sharp protocol + * @RC_PROTO_XMP: XMP protocol + * @RC_PROTO_CEC: CEC protocol + * @RC_PROTO_IMON: iMon Pad protocol + */ +enum rc_proto { + RC_PROTO_UNKNOWN = 0, + RC_PROTO_OTHER = 1, + RC_PROTO_RC5 = 2, + RC_PROTO_RC5X_20 = 3, + RC_PROTO_RC5_SZ = 4, + RC_PROTO_JVC = 5, + RC_PROTO_SONY12 = 6, + RC_PROTO_SONY15 = 7, + RC_PROTO_SONY20 = 8, + RC_PROTO_NEC = 9, + RC_PROTO_NECX = 10, + RC_PROTO_NEC32 = 11, + RC_PROTO_SANYO = 12, + RC_PROTO_MCIR2_KBD = 13, + RC_PROTO_MCIR2_MSE = 14, + RC_PROTO_RC6_0 = 15, + RC_PROTO_RC6_6A_20 = 16, + RC_PROTO_RC6_6A_24 = 17, + RC_PROTO_RC6_6A_32 = 18, + RC_PROTO_RC6_MCE = 19, + RC_PROTO_SHARP = 20, + RC_PROTO_XMP = 21, + RC_PROTO_CEC = 22, + RC_PROTO_IMON = 23, +}; + +#endif diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index af5f8c2..db9f15f 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -207,4 +207,16 @@ struct prctl_mm_map { # define PR_SVE_VL_LEN_MASK 0xffff # define PR_SVE_VL_INHERIT (1 << 17) /* inherit across exec */ +/* Per task speculation control */ +#define PR_GET_SPECULATION_CTRL 52 +#define PR_SET_SPECULATION_CTRL 53 +/* Speculation control variants */ +# define PR_SPEC_STORE_BYPASS 0 +/* Return and control values for PR_SET/GET_SPECULATION_CTRL */ +# define PR_SPEC_NOT_AFFECTED 0 +# define PR_SPEC_PRCTL (1UL << 0) +# define PR_SPEC_ENABLE (1UL << 1) +# define PR_SPEC_DISABLE (1UL << 2) +# define PR_SPEC_FORCE_DISABLE (1UL << 3) + #endif /* _LINUX_PRCTL_H */ diff --git a/tools/include/uapi/linux/seg6.h b/tools/include/uapi/linux/seg6.h new file mode 100644 index 0000000..286e8d6 --- /dev/null +++ b/tools/include/uapi/linux/seg6.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * SR-IPv6 implementation + * + * Author: + * David Lebrun <david.lebrun@uclouvain.be> + * + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _UAPI_LINUX_SEG6_H +#define _UAPI_LINUX_SEG6_H + +#include <linux/types.h> +#include <linux/in6.h> /* For struct in6_addr. */ + +/* + * SRH + */ +struct ipv6_sr_hdr { + __u8 nexthdr; + __u8 hdrlen; + __u8 type; + __u8 segments_left; + __u8 first_segment; /* Represents the last_entry field of SRH */ + __u8 flags; + __u16 tag; + + struct in6_addr segments[0]; +}; + +#define SR6_FLAG1_PROTECTED (1 << 6) +#define SR6_FLAG1_OAM (1 << 5) +#define SR6_FLAG1_ALERT (1 << 4) +#define SR6_FLAG1_HMAC (1 << 3) + +#define SR6_TLV_INGRESS 1 +#define SR6_TLV_EGRESS 2 +#define SR6_TLV_OPAQUE 3 +#define SR6_TLV_PADDING 4 +#define SR6_TLV_HMAC 5 + +#define sr_has_hmac(srh) ((srh)->flags & SR6_FLAG1_HMAC) + +struct sr6_tlv { + __u8 type; + __u8 len; + __u8 data[0]; +}; + +#endif diff --git a/tools/include/uapi/linux/seg6_local.h b/tools/include/uapi/linux/seg6_local.h new file mode 100644 index 0000000..edc138b --- /dev/null +++ b/tools/include/uapi/linux/seg6_local.h @@ -0,0 +1,80 @@ +/* + * SR-IPv6 implementation + * + * Author: + * David Lebrun <david.lebrun@uclouvain.be> + * + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _UAPI_LINUX_SEG6_LOCAL_H +#define _UAPI_LINUX_SEG6_LOCAL_H + +#include <linux/seg6.h> + +enum { + SEG6_LOCAL_UNSPEC, + SEG6_LOCAL_ACTION, + SEG6_LOCAL_SRH, + SEG6_LOCAL_TABLE, + SEG6_LOCAL_NH4, + SEG6_LOCAL_NH6, + SEG6_LOCAL_IIF, + SEG6_LOCAL_OIF, + SEG6_LOCAL_BPF, + __SEG6_LOCAL_MAX, +}; +#define SEG6_LOCAL_MAX (__SEG6_LOCAL_MAX - 1) + +enum { + SEG6_LOCAL_ACTION_UNSPEC = 0, + /* node segment */ + SEG6_LOCAL_ACTION_END = 1, + /* adjacency segment (IPv6 cross-connect) */ + SEG6_LOCAL_ACTION_END_X = 2, + /* lookup of next seg NH in table */ + SEG6_LOCAL_ACTION_END_T = 3, + /* decap and L2 cross-connect */ + SEG6_LOCAL_ACTION_END_DX2 = 4, + /* decap and IPv6 cross-connect */ + SEG6_LOCAL_ACTION_END_DX6 = 5, + /* decap and IPv4 cross-connect */ + SEG6_LOCAL_ACTION_END_DX4 = 6, + /* decap and lookup of DA in v6 table */ + SEG6_LOCAL_ACTION_END_DT6 = 7, + /* decap and lookup of DA in v4 table */ + SEG6_LOCAL_ACTION_END_DT4 = 8, + /* binding segment with insertion */ + SEG6_LOCAL_ACTION_END_B6 = 9, + /* binding segment with encapsulation */ + SEG6_LOCAL_ACTION_END_B6_ENCAP = 10, + /* binding segment with MPLS encap */ + SEG6_LOCAL_ACTION_END_BM = 11, + /* lookup last seg in table */ + SEG6_LOCAL_ACTION_END_S = 12, + /* forward to SR-unaware VNF with static proxy */ + SEG6_LOCAL_ACTION_END_AS = 13, + /* forward to SR-unaware VNF with masquerading */ + SEG6_LOCAL_ACTION_END_AM = 14, + /* custom BPF action */ + SEG6_LOCAL_ACTION_END_BPF = 15, + + __SEG6_LOCAL_ACTION_MAX, +}; + +#define SEG6_LOCAL_ACTION_MAX (__SEG6_LOCAL_ACTION_MAX - 1) + +enum { + SEG6_LOCAL_BPF_PROG_UNSPEC, + SEG6_LOCAL_BPF_PROG, + SEG6_LOCAL_BPF_PROG_NAME, + __SEG6_LOCAL_BPF_PROG_MAX, +}; + +#define SEG6_LOCAL_BPF_PROG_MAX (__SEG6_LOCAL_BPF_PROG_MAX - 1) + +#endif diff --git a/tools/lib/api/fs/tracing_path.c b/tools/lib/api/fs/tracing_path.c index 7b7fd0b..1200374 100644 --- a/tools/lib/api/fs/tracing_path.c +++ b/tools/lib/api/fs/tracing_path.c @@ -13,11 +13,9 @@ #include "tracing_path.h" - -char tracing_mnt[PATH_MAX] = "/sys/kernel/debug"; -char tracing_path[PATH_MAX] = "/sys/kernel/debug/tracing"; -char tracing_events_path[PATH_MAX] = "/sys/kernel/debug/tracing/events"; - +static char tracing_mnt[PATH_MAX] = "/sys/kernel/debug"; +static char tracing_path[PATH_MAX] = "/sys/kernel/debug/tracing"; +static char tracing_events_path[PATH_MAX] = "/sys/kernel/debug/tracing/events"; static void __tracing_path_set(const char *tracing, const char *mountpoint) { @@ -76,7 +74,7 @@ char *get_tracing_file(const char *name) { char *file; - if (asprintf(&file, "%s/%s", tracing_path, name) < 0) + if (asprintf(&file, "%s/%s", tracing_path_mount(), name) < 0) return NULL; return file; @@ -87,6 +85,34 @@ void put_tracing_file(char *file) free(file); } +char *get_events_file(const char *name) +{ + char *file; + + if (asprintf(&file, "%s/events/%s", tracing_path_mount(), name) < 0) + return NULL; + + return file; +} + +void put_events_file(char *file) +{ + free(file); +} + +DIR *tracing_events__opendir(void) +{ + DIR *dir = NULL; + char *path = get_tracing_file("events"); + + if (path) { + dir = opendir(path); + put_events_file(path); + } + + return dir; +} + int tracing_path__strerror_open_tp(int err, char *buf, size_t size, const char *sys, const char *name) { @@ -129,7 +155,7 @@ int tracing_path__strerror_open_tp(int err, char *buf, size_t size, snprintf(buf, size, "Error:\tNo permissions to read %s/%s\n" "Hint:\tTry 'sudo mount -o remount,mode=755 %s'\n", - tracing_events_path, filename, tracing_mnt); + tracing_events_path, filename, tracing_path_mount()); } break; default: diff --git a/tools/lib/api/fs/tracing_path.h b/tools/lib/api/fs/tracing_path.h index 0066f06..a19136b 100644 --- a/tools/lib/api/fs/tracing_path.h +++ b/tools/lib/api/fs/tracing_path.h @@ -3,9 +3,9 @@ #define __API_FS_TRACING_PATH_H #include <linux/types.h> +#include <dirent.h> -extern char tracing_path[]; -extern char tracing_events_path[]; +DIR *tracing_events__opendir(void); void tracing_path_set(const char *mountpoint); const char *tracing_path_mount(void); @@ -13,5 +13,10 @@ const char *tracing_path_mount(void); char *get_tracing_file(const char *name); void put_tracing_file(char *file); +char *get_events_file(const char *name); +void put_events_file(char *file); + +#define zput_events_file(ptr) ({ free(*ptr); *ptr = NULL; }) + int tracing_path__strerror_open_tp(int err, char *buf, size_t size, const char *sys, const char *name); #endif /* __API_FS_TRACING_PATH_H */ diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build index 64c679d..6070e65 100644 --- a/tools/lib/bpf/Build +++ b/tools/lib/bpf/Build @@ -1 +1 @@ -libbpf-y := libbpf.o bpf.o nlattr.o +libbpf-y := libbpf.o bpf.o nlattr.o btf.o diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index e6d5f8d..5390e77 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -69,7 +69,7 @@ FEATURE_USER = .libbpf FEATURE_TESTS = libelf libelf-getphdrnum libelf-mmap bpf FEATURE_DISPLAY = libelf bpf -INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi +INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi -I$(srctree)/tools/perf FEATURE_CHECK_CFLAGS-bpf = $(INCLUDES) check_feat := 1 @@ -189,6 +189,7 @@ install_headers: $(call QUIET_INSTALL, headers) \ $(call do_install,bpf.h,$(prefix)/include/bpf,644); \ $(call do_install,libbpf.h,$(prefix)/include/bpf,644); + $(call do_install,btf.h,$(prefix)/include/bpf,644); install: install_lib diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index acbb3f8..9ddc89d 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -73,43 +73,77 @@ static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr, return syscall(__NR_bpf, cmd, attr, size); } -int bpf_create_map_node(enum bpf_map_type map_type, const char *name, - int key_size, int value_size, int max_entries, - __u32 map_flags, int node) +int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr) { - __u32 name_len = name ? strlen(name) : 0; + __u32 name_len = create_attr->name ? strlen(create_attr->name) : 0; union bpf_attr attr; memset(&attr, '\0', sizeof(attr)); - attr.map_type = map_type; - attr.key_size = key_size; - attr.value_size = value_size; - attr.max_entries = max_entries; - attr.map_flags = map_flags; - memcpy(attr.map_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1)); + attr.map_type = create_attr->map_type; + attr.key_size = create_attr->key_size; + attr.value_size = create_attr->value_size; + attr.max_entries = create_attr->max_entries; + attr.map_flags = create_attr->map_flags; + memcpy(attr.map_name, create_attr->name, + min(name_len, BPF_OBJ_NAME_LEN - 1)); + attr.numa_node = create_attr->numa_node; + attr.btf_fd = create_attr->btf_fd; + attr.btf_key_type_id = create_attr->btf_key_type_id; + attr.btf_value_type_id = create_attr->btf_value_type_id; + attr.map_ifindex = create_attr->map_ifindex; + + return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); +} +int bpf_create_map_node(enum bpf_map_type map_type, const char *name, + int key_size, int value_size, int max_entries, + __u32 map_flags, int node) +{ + struct bpf_create_map_attr map_attr = {}; + + map_attr.name = name; + map_attr.map_type = map_type; + map_attr.map_flags = map_flags; + map_attr.key_size = key_size; + map_attr.value_size = value_size; + map_attr.max_entries = max_entries; if (node >= 0) { - attr.map_flags |= BPF_F_NUMA_NODE; - attr.numa_node = node; + map_attr.numa_node = node; + map_attr.map_flags |= BPF_F_NUMA_NODE; } - return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); + return bpf_create_map_xattr(&map_attr); } int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size, int max_entries, __u32 map_flags) { - return bpf_create_map_node(map_type, NULL, key_size, value_size, - max_entries, map_flags, -1); + struct bpf_create_map_attr map_attr = {}; + + map_attr.map_type = map_type; + map_attr.map_flags = map_flags; + map_attr.key_size = key_size; + map_attr.value_size = value_size; + map_attr.max_entries = max_entries; + + return bpf_create_map_xattr(&map_attr); } int bpf_create_map_name(enum bpf_map_type map_type, const char *name, int key_size, int value_size, int max_entries, __u32 map_flags) { - return bpf_create_map_node(map_type, name, key_size, value_size, - max_entries, map_flags, -1); + struct bpf_create_map_attr map_attr = {}; + + map_attr.name = name; + map_attr.map_type = map_type; + map_attr.map_flags = map_flags; + map_attr.key_size = key_size; + map_attr.value_size = value_size; + map_attr.max_entries = max_entries; + + return bpf_create_map_xattr(&map_attr); } int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name, @@ -168,6 +202,7 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, attr.log_size = 0; attr.log_level = 0; attr.kern_version = load_attr->kern_version; + attr.prog_ifindex = load_attr->prog_ifindex; memcpy(attr.prog_name, load_attr->name, min(name_len, BPF_OBJ_NAME_LEN - 1)); @@ -425,6 +460,16 @@ int bpf_map_get_fd_by_id(__u32 id) return sys_bpf(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr)); } +int bpf_btf_get_fd_by_id(__u32 id) +{ + union bpf_attr attr; + + bzero(&attr, sizeof(attr)); + attr.btf_id = id; + + return sys_bpf(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr)); +} + int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len) { union bpf_attr attr; @@ -573,3 +618,51 @@ cleanup: close(sock); return ret; } + +int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size, + bool do_log) +{ + union bpf_attr attr = {}; + int fd; + + attr.btf = ptr_to_u64(btf); + attr.btf_size = btf_size; + +retry: + if (do_log && log_buf && log_buf_size) { + attr.btf_log_level = 1; + attr.btf_log_size = log_buf_size; + attr.btf_log_buf = ptr_to_u64(log_buf); + } + + fd = sys_bpf(BPF_BTF_LOAD, &attr, sizeof(attr)); + if (fd == -1 && !do_log && log_buf && log_buf_size) { + do_log = true; + goto retry; + } + + return fd; +} + +int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len, + __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset, + __u64 *probe_addr) +{ + union bpf_attr attr = {}; + int err; + + attr.task_fd_query.pid = pid; + attr.task_fd_query.fd = fd; + attr.task_fd_query.flags = flags; + attr.task_fd_query.buf = ptr_to_u64(buf); + attr.task_fd_query.buf_len = *buf_len; + + err = sys_bpf(BPF_TASK_FD_QUERY, &attr, sizeof(attr)); + *buf_len = attr.task_fd_query.buf_len; + *prog_id = attr.task_fd_query.prog_id; + *fd_type = attr.task_fd_query.fd_type; + *probe_offset = attr.task_fd_query.probe_offset; + *probe_addr = attr.task_fd_query.probe_addr; + + return err; +} diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 39f6a0d..0639a30 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -24,8 +24,24 @@ #define __BPF_BPF_H #include <linux/bpf.h> +#include <stdbool.h> #include <stddef.h> +struct bpf_create_map_attr { + const char *name; + enum bpf_map_type map_type; + __u32 map_flags; + __u32 key_size; + __u32 value_size; + __u32 max_entries; + __u32 numa_node; + __u32 btf_fd; + __u32 btf_key_type_id; + __u32 btf_value_type_id; + __u32 map_ifindex; +}; + +int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr); int bpf_create_map_node(enum bpf_map_type map_type, const char *name, int key_size, int value_size, int max_entries, __u32 map_flags, int node); @@ -49,6 +65,7 @@ struct bpf_load_program_attr { size_t insns_cnt; const char *license; __u32 kern_version; + __u32 prog_ifindex; }; /* Recommend log buffer size */ @@ -83,8 +100,14 @@ int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id); int bpf_map_get_next_id(__u32 start_id, __u32 *next_id); int bpf_prog_get_fd_by_id(__u32 id); int bpf_map_get_fd_by_id(__u32 id); +int bpf_btf_get_fd_by_id(__u32 id); int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len); int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt); int bpf_raw_tracepoint_open(const char *name, int prog_fd); +int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size, + bool do_log); +int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len, + __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset, + __u64 *probe_addr); #endif diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c new file mode 100644 index 0000000..8c54a4b --- /dev/null +++ b/tools/lib/bpf/btf.c @@ -0,0 +1,373 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018 Facebook */ + +#include <stdlib.h> +#include <stdint.h> +#include <string.h> +#include <unistd.h> +#include <errno.h> +#include <linux/err.h> +#include <linux/btf.h> +#include "btf.h" +#include "bpf.h" + +#define elog(fmt, ...) { if (err_log) err_log(fmt, ##__VA_ARGS__); } +#define max(a, b) ((a) > (b) ? (a) : (b)) +#define min(a, b) ((a) < (b) ? (a) : (b)) + +#define BTF_MAX_NR_TYPES 65535 + +static struct btf_type btf_void; + +struct btf { + union { + struct btf_header *hdr; + void *data; + }; + struct btf_type **types; + const char *strings; + void *nohdr_data; + uint32_t nr_types; + uint32_t types_size; + uint32_t data_size; + int fd; +}; + +static const char *btf_name_by_offset(const struct btf *btf, uint32_t offset) +{ + if (offset < btf->hdr->str_len) + return &btf->strings[offset]; + else + return NULL; +} + +static int btf_add_type(struct btf *btf, struct btf_type *t) +{ + if (btf->types_size - btf->nr_types < 2) { + struct btf_type **new_types; + u32 expand_by, new_size; + + if (btf->types_size == BTF_MAX_NR_TYPES) + return -E2BIG; + + expand_by = max(btf->types_size >> 2, 16); + new_size = min(BTF_MAX_NR_TYPES, btf->types_size + expand_by); + + new_types = realloc(btf->types, sizeof(*new_types) * new_size); + if (!new_types) + return -ENOMEM; + + if (btf->nr_types == 0) + new_types[0] = &btf_void; + + btf->types = new_types; + btf->types_size = new_size; + } + + btf->types[++(btf->nr_types)] = t; + + return 0; +} + +static int btf_parse_hdr(struct btf *btf, btf_print_fn_t err_log) +{ + const struct btf_header *hdr = btf->hdr; + u32 meta_left; + + if (btf->data_size < sizeof(struct btf_header)) { + elog("BTF header not found\n"); + return -EINVAL; + } + + if (hdr->magic != BTF_MAGIC) { + elog("Invalid BTF magic:%x\n", hdr->magic); + return -EINVAL; + } + + if (hdr->version != BTF_VERSION) { + elog("Unsupported BTF version:%u\n", hdr->version); + return -ENOTSUP; + } + + if (hdr->flags) { + elog("Unsupported BTF flags:%x\n", hdr->flags); + return -ENOTSUP; + } + + meta_left = btf->data_size - sizeof(*hdr); + if (!meta_left) { + elog("BTF has no data\n"); + return -EINVAL; + } + + if (meta_left < hdr->type_off) { + elog("Invalid BTF type section offset:%u\n", hdr->type_off); + return -EINVAL; + } + + if (meta_left < hdr->str_off) { + elog("Invalid BTF string section offset:%u\n", hdr->str_off); + return -EINVAL; + } + + if (hdr->type_off >= hdr->str_off) { + elog("BTF type section offset >= string section offset. No type?\n"); + return -EINVAL; + } + + if (hdr->type_off & 0x02) { + elog("BTF type section is not aligned to 4 bytes\n"); + return -EINVAL; + } + + btf->nohdr_data = btf->hdr + 1; + + return 0; +} + +static int btf_parse_str_sec(struct btf *btf, btf_print_fn_t err_log) +{ + const struct btf_header *hdr = btf->hdr; + const char *start = btf->nohdr_data + hdr->str_off; + const char *end = start + btf->hdr->str_len; + + if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_NAME_OFFSET || + start[0] || end[-1]) { + elog("Invalid BTF string section\n"); + return -EINVAL; + } + + btf->strings = start; + + return 0; +} + +static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log) +{ + struct btf_header *hdr = btf->hdr; + void *nohdr_data = btf->nohdr_data; + void *next_type = nohdr_data + hdr->type_off; + void *end_type = nohdr_data + hdr->str_off; + + while (next_type < end_type) { + struct btf_type *t = next_type; + uint16_t vlen = BTF_INFO_VLEN(t->info); + int err; + + next_type += sizeof(*t); + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_INT: + next_type += sizeof(int); + break; + case BTF_KIND_ARRAY: + next_type += sizeof(struct btf_array); + break; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + next_type += vlen * sizeof(struct btf_member); + break; + case BTF_KIND_ENUM: + next_type += vlen * sizeof(struct btf_enum); + break; + case BTF_KIND_TYPEDEF: + case BTF_KIND_PTR: + case BTF_KIND_FWD: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + break; + default: + elog("Unsupported BTF_KIND:%u\n", + BTF_INFO_KIND(t->info)); + return -EINVAL; + } + + err = btf_add_type(btf, t); + if (err) + return err; + } + + return 0; +} + +static const struct btf_type *btf_type_by_id(const struct btf *btf, + uint32_t type_id) +{ + if (type_id > btf->nr_types) + return NULL; + + return btf->types[type_id]; +} + +static bool btf_type_is_void(const struct btf_type *t) +{ + return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD; +} + +static bool btf_type_is_void_or_null(const struct btf_type *t) +{ + return !t || btf_type_is_void(t); +} + +static int64_t btf_type_size(const struct btf_type *t) +{ + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_INT: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + case BTF_KIND_ENUM: + return t->size; + case BTF_KIND_PTR: + return sizeof(void *); + default: + return -EINVAL; + } +} + +#define MAX_RESOLVE_DEPTH 32 + +int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id) +{ + const struct btf_array *array; + const struct btf_type *t; + uint32_t nelems = 1; + int64_t size = -1; + int i; + + t = btf_type_by_id(btf, type_id); + for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t); + i++) { + size = btf_type_size(t); + if (size >= 0) + break; + + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_TYPEDEF: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + type_id = t->type; + break; + case BTF_KIND_ARRAY: + array = (const struct btf_array *)(t + 1); + if (nelems && array->nelems > UINT32_MAX / nelems) + return -E2BIG; + nelems *= array->nelems; + type_id = array->type; + break; + default: + return -EINVAL; + } + + t = btf_type_by_id(btf, type_id); + } + + if (size < 0) + return -EINVAL; + + if (nelems && size > UINT32_MAX / nelems) + return -E2BIG; + + return nelems * size; +} + +int32_t btf__find_by_name(const struct btf *btf, const char *type_name) +{ + uint32_t i; + + if (!strcmp(type_name, "void")) + return 0; + + for (i = 1; i <= btf->nr_types; i++) { + const struct btf_type *t = btf->types[i]; + const char *name = btf_name_by_offset(btf, t->name_off); + + if (name && !strcmp(type_name, name)) + return i; + } + + return -ENOENT; +} + +void btf__free(struct btf *btf) +{ + if (!btf) + return; + + if (btf->fd != -1) + close(btf->fd); + + free(btf->data); + free(btf->types); + free(btf); +} + +struct btf *btf__new(uint8_t *data, uint32_t size, + btf_print_fn_t err_log) +{ + uint32_t log_buf_size = 0; + char *log_buf = NULL; + struct btf *btf; + int err; + + btf = calloc(1, sizeof(struct btf)); + if (!btf) + return ERR_PTR(-ENOMEM); + + btf->fd = -1; + + if (err_log) { + log_buf = malloc(BPF_LOG_BUF_SIZE); + if (!log_buf) { + err = -ENOMEM; + goto done; + } + *log_buf = 0; + log_buf_size = BPF_LOG_BUF_SIZE; + } + + btf->data = malloc(size); + if (!btf->data) { + err = -ENOMEM; + goto done; + } + + memcpy(btf->data, data, size); + btf->data_size = size; + + btf->fd = bpf_load_btf(btf->data, btf->data_size, + log_buf, log_buf_size, false); + + if (btf->fd == -1) { + err = -errno; + elog("Error loading BTF: %s(%d)\n", strerror(errno), errno); + if (log_buf && *log_buf) + elog("%s\n", log_buf); + goto done; + } + + err = btf_parse_hdr(btf, err_log); + if (err) + goto done; + + err = btf_parse_str_sec(btf, err_log); + if (err) + goto done; + + err = btf_parse_type_sec(btf, err_log); + +done: + free(log_buf); + + if (err) { + btf__free(btf); + return ERR_PTR(err); + } + + return btf; +} + +int btf__fd(const struct btf *btf) +{ + return btf->fd; +} diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h new file mode 100644 index 0000000..74bb344 --- /dev/null +++ b/tools/lib/bpf/btf.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018 Facebook */ + +#ifndef __BPF_BTF_H +#define __BPF_BTF_H + +#include <stdint.h> + +#define BTF_ELF_SEC ".BTF" + +struct btf; + +typedef int (*btf_print_fn_t)(const char *, ...) + __attribute__((format(printf, 1, 2))); + +void btf__free(struct btf *btf); +struct btf *btf__new(uint8_t *data, uint32_t size, btf_print_fn_t err_log); +int32_t btf__find_by_name(const struct btf *btf, const char *type_name); +int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id); +int btf__fd(const struct btf *btf); + +#endif diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 0f9f06d..a1e96b5 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -31,6 +31,7 @@ #include <unistd.h> #include <fcntl.h> #include <errno.h> +#include <perf-sys.h> #include <asm/unistd.h> #include <linux/err.h> #include <linux/kernel.h> @@ -45,6 +46,7 @@ #include "libbpf.h" #include "bpf.h" +#include "btf.h" #ifndef EM_BPF #define EM_BPF 247 @@ -176,6 +178,7 @@ struct bpf_program { /* Index in elf obj file, for relocation use. */ int idx; char *name; + int prog_ifindex; char *section_name; struct bpf_insn *insns; size_t insns_cnt, main_prog_cnt; @@ -211,7 +214,10 @@ struct bpf_map { int fd; char *name; size_t offset; + int map_ifindex; struct bpf_map_def def; + uint32_t btf_key_type_id; + uint32_t btf_value_type_id; void *priv; bpf_map_clear_priv_t clear_priv; }; @@ -256,6 +262,8 @@ struct bpf_object { */ struct list_head list; + struct btf *btf; + void *priv; bpf_object_clear_priv_t clear_priv; @@ -819,7 +827,15 @@ static int bpf_object__elf_collect(struct bpf_object *obj) data->d_size); else if (strcmp(name, "maps") == 0) obj->efile.maps_shndx = idx; - else if (sh.sh_type == SHT_SYMTAB) { + else if (strcmp(name, BTF_ELF_SEC) == 0) { + obj->btf = btf__new(data->d_buf, data->d_size, + __pr_debug); + if (IS_ERR(obj->btf)) { + pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n", + BTF_ELF_SEC, PTR_ERR(obj->btf)); + obj->btf = NULL; + } + } else if (sh.sh_type == SHT_SYMTAB) { if (obj->efile.symbols) { pr_warning("bpf: multiple SYMTAB in %s\n", obj->path); @@ -996,33 +1012,127 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, return 0; } +static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf) +{ + struct bpf_map_def *def = &map->def; + const size_t max_name = 256; + int64_t key_size, value_size; + int32_t key_id, value_id; + char name[max_name]; + + /* Find key type by name from BTF */ + if (snprintf(name, max_name, "%s_key", map->name) == max_name) { + pr_warning("map:%s length of BTF key_type:%s_key is too long\n", + map->name, map->name); + return -EINVAL; + } + + key_id = btf__find_by_name(btf, name); + if (key_id < 0) { + pr_debug("map:%s key_type:%s cannot be found in BTF\n", + map->name, name); + return key_id; + } + + key_size = btf__resolve_size(btf, key_id); + if (key_size < 0) { + pr_warning("map:%s key_type:%s cannot get the BTF type_size\n", + map->name, name); + return key_size; + } + + if (def->key_size != key_size) { + pr_warning("map:%s key_type:%s has BTF type_size:%u != key_size:%u\n", + map->name, name, (unsigned int)key_size, def->key_size); + return -EINVAL; + } + + /* Find value type from BTF */ + if (snprintf(name, max_name, "%s_value", map->name) == max_name) { + pr_warning("map:%s length of BTF value_type:%s_value is too long\n", + map->name, map->name); + return -EINVAL; + } + + value_id = btf__find_by_name(btf, name); + if (value_id < 0) { + pr_debug("map:%s value_type:%s cannot be found in BTF\n", + map->name, name); + return value_id; + } + + value_size = btf__resolve_size(btf, value_id); + if (value_size < 0) { + pr_warning("map:%s value_type:%s cannot get the BTF type_size\n", + map->name, name); + return value_size; + } + + if (def->value_size != value_size) { + pr_warning("map:%s value_type:%s has BTF type_size:%u != value_size:%u\n", + map->name, name, (unsigned int)value_size, def->value_size); + return -EINVAL; + } + + map->btf_key_type_id = key_id; + map->btf_value_type_id = value_id; + + return 0; +} + static int bpf_object__create_maps(struct bpf_object *obj) { + struct bpf_create_map_attr create_attr = {}; unsigned int i; + int err; for (i = 0; i < obj->nr_maps; i++) { - struct bpf_map_def *def = &obj->maps[i].def; - int *pfd = &obj->maps[i].fd; - - *pfd = bpf_create_map_name(def->type, - obj->maps[i].name, - def->key_size, - def->value_size, - def->max_entries, - def->map_flags); + struct bpf_map *map = &obj->maps[i]; + struct bpf_map_def *def = &map->def; + int *pfd = &map->fd; + + create_attr.name = map->name; + create_attr.map_ifindex = map->map_ifindex; + create_attr.map_type = def->type; + create_attr.map_flags = def->map_flags; + create_attr.key_size = def->key_size; + create_attr.value_size = def->value_size; + create_attr.max_entries = def->max_entries; + create_attr.btf_fd = 0; + create_attr.btf_key_type_id = 0; + create_attr.btf_value_type_id = 0; + + if (obj->btf && !bpf_map_find_btf_info(map, obj->btf)) { + create_attr.btf_fd = btf__fd(obj->btf); + create_attr.btf_key_type_id = map->btf_key_type_id; + create_attr.btf_value_type_id = map->btf_value_type_id; + } + + *pfd = bpf_create_map_xattr(&create_attr); + if (*pfd < 0 && create_attr.btf_key_type_id) { + pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n", + map->name, strerror(errno), errno); + create_attr.btf_fd = 0; + create_attr.btf_key_type_id = 0; + create_attr.btf_value_type_id = 0; + map->btf_key_type_id = 0; + map->btf_value_type_id = 0; + *pfd = bpf_create_map_xattr(&create_attr); + } + if (*pfd < 0) { size_t j; - int err = *pfd; + err = *pfd; pr_warning("failed to create map (name: '%s'): %s\n", - obj->maps[i].name, + map->name, strerror(errno)); for (j = 0; j < i; j++) zclose(obj->maps[j].fd); return err; } - pr_debug("create map %s: fd=%d\n", obj->maps[i].name, *pfd); + pr_debug("create map %s: fd=%d\n", map->name, *pfd); } return 0; @@ -1166,7 +1276,7 @@ static int bpf_object__collect_reloc(struct bpf_object *obj) static int load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type, const char *name, struct bpf_insn *insns, int insns_cnt, - char *license, u32 kern_version, int *pfd) + char *license, u32 kern_version, int *pfd, int prog_ifindex) { struct bpf_load_program_attr load_attr; char *log_buf; @@ -1180,6 +1290,7 @@ load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type, load_attr.insns_cnt = insns_cnt; load_attr.license = license; load_attr.kern_version = kern_version; + load_attr.prog_ifindex = prog_ifindex; if (!load_attr.insns || !load_attr.insns_cnt) return -EINVAL; @@ -1261,7 +1372,8 @@ bpf_program__load(struct bpf_program *prog, } err = load_program(prog->type, prog->expected_attach_type, prog->name, prog->insns, prog->insns_cnt, - license, kern_version, &fd); + license, kern_version, &fd, + prog->prog_ifindex); if (!err) prog->instances.fds[0] = fd; goto out; @@ -1292,7 +1404,8 @@ bpf_program__load(struct bpf_program *prog, err = load_program(prog->type, prog->expected_attach_type, prog->name, result.new_insn_ptr, result.new_insn_cnt, - license, kern_version, &fd); + license, kern_version, &fd, + prog->prog_ifindex); if (err) { pr_warning("Loading the %dth instance of program '%s' failed\n", @@ -1331,9 +1444,39 @@ bpf_object__load_progs(struct bpf_object *obj) return 0; } -static int bpf_object__validate(struct bpf_object *obj) +static bool bpf_prog_type__needs_kver(enum bpf_prog_type type) +{ + switch (type) { + case BPF_PROG_TYPE_SOCKET_FILTER: + case BPF_PROG_TYPE_SCHED_CLS: + case BPF_PROG_TYPE_SCHED_ACT: + case BPF_PROG_TYPE_XDP: + case BPF_PROG_TYPE_CGROUP_SKB: + case BPF_PROG_TYPE_CGROUP_SOCK: + case BPF_PROG_TYPE_LWT_IN: + case BPF_PROG_TYPE_LWT_OUT: + case BPF_PROG_TYPE_LWT_XMIT: + case BPF_PROG_TYPE_LWT_SEG6LOCAL: + case BPF_PROG_TYPE_SOCK_OPS: + case BPF_PROG_TYPE_SK_SKB: + case BPF_PROG_TYPE_CGROUP_DEVICE: + case BPF_PROG_TYPE_SK_MSG: + case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: + case BPF_PROG_TYPE_LIRC_MODE2: + return false; + case BPF_PROG_TYPE_UNSPEC: + case BPF_PROG_TYPE_KPROBE: + case BPF_PROG_TYPE_TRACEPOINT: + case BPF_PROG_TYPE_PERF_EVENT: + case BPF_PROG_TYPE_RAW_TRACEPOINT: + default: + return true; + } +} + +static int bpf_object__validate(struct bpf_object *obj, bool needs_kver) { - if (obj->kern_version == 0) { + if (needs_kver && obj->kern_version == 0) { pr_warning("%s doesn't provide kernel version\n", obj->path); return -LIBBPF_ERRNO__KVERSION; @@ -1342,7 +1485,8 @@ static int bpf_object__validate(struct bpf_object *obj) } static struct bpf_object * -__bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz) +__bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz, + bool needs_kver) { struct bpf_object *obj; int err; @@ -1360,7 +1504,7 @@ __bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz) CHECK_ERR(bpf_object__check_endianness(obj), err, out); CHECK_ERR(bpf_object__elf_collect(obj), err, out); CHECK_ERR(bpf_object__collect_reloc(obj), err, out); - CHECK_ERR(bpf_object__validate(obj), err, out); + CHECK_ERR(bpf_object__validate(obj, needs_kver), err, out); bpf_object__elf_finish(obj); return obj; @@ -1377,7 +1521,7 @@ struct bpf_object *bpf_object__open(const char *path) pr_debug("loading %s\n", path); - return __bpf_object__open(path, NULL, 0); + return __bpf_object__open(path, NULL, 0, true); } struct bpf_object *bpf_object__open_buffer(void *obj_buf, @@ -1400,7 +1544,7 @@ struct bpf_object *bpf_object__open_buffer(void *obj_buf, pr_debug("loading object '%s' from buffer\n", name); - return __bpf_object__open(name, obj_buf, obj_buf_sz); + return __bpf_object__open(name, obj_buf, obj_buf_sz, true); } int bpf_object__unload(struct bpf_object *obj) @@ -1641,6 +1785,7 @@ void bpf_object__close(struct bpf_object *obj) bpf_object__elf_finish(obj); bpf_object__unload(obj); + btf__free(obj->btf); for (i = 0; i < obj->nr_maps; i++) { zfree(&obj->maps[i].name); @@ -1692,6 +1837,11 @@ unsigned int bpf_object__kversion(struct bpf_object *obj) return obj ? obj->kern_version : 0; } +int bpf_object__btf_fd(const struct bpf_object *obj) +{ + return obj->btf ? btf__fd(obj->btf) : -1; +} + int bpf_object__set_priv(struct bpf_object *obj, void *priv, bpf_object_clear_priv_t clear_priv) { @@ -1845,11 +1995,12 @@ BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE); BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS); BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT); BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT); +BPF_PROG_TYPE_FNS(raw_tracepoint, BPF_PROG_TYPE_RAW_TRACEPOINT); BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP); BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT); -static void bpf_program__set_expected_attach_type(struct bpf_program *prog, - enum bpf_attach_type type) +void bpf_program__set_expected_attach_type(struct bpf_program *prog, + enum bpf_attach_type type) { prog->expected_attach_type = type; } @@ -1859,6 +2010,9 @@ static void bpf_program__set_expected_attach_type(struct bpf_program *prog, #define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_FULL(string, ptype, 0) +#define BPF_S_PROG_SEC(string, ptype) \ + BPF_PROG_SEC_FULL(string, BPF_PROG_TYPE_CGROUP_SOCK, ptype) + #define BPF_SA_PROG_SEC(string, ptype) \ BPF_PROG_SEC_FULL(string, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, ptype) @@ -1874,6 +2028,7 @@ static const struct { BPF_PROG_SEC("classifier", BPF_PROG_TYPE_SCHED_CLS), BPF_PROG_SEC("action", BPF_PROG_TYPE_SCHED_ACT), BPF_PROG_SEC("tracepoint/", BPF_PROG_TYPE_TRACEPOINT), + BPF_PROG_SEC("raw_tracepoint/", BPF_PROG_TYPE_RAW_TRACEPOINT), BPF_PROG_SEC("xdp", BPF_PROG_TYPE_XDP), BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT), BPF_PROG_SEC("cgroup/skb", BPF_PROG_TYPE_CGROUP_SKB), @@ -1889,10 +2044,15 @@ static const struct { BPF_SA_PROG_SEC("cgroup/bind6", BPF_CGROUP_INET6_BIND), BPF_SA_PROG_SEC("cgroup/connect4", BPF_CGROUP_INET4_CONNECT), BPF_SA_PROG_SEC("cgroup/connect6", BPF_CGROUP_INET6_CONNECT), + BPF_SA_PROG_SEC("cgroup/sendmsg4", BPF_CGROUP_UDP4_SENDMSG), + BPF_SA_PROG_SEC("cgroup/sendmsg6", BPF_CGROUP_UDP6_SENDMSG), + BPF_S_PROG_SEC("cgroup/post_bind4", BPF_CGROUP_INET4_POST_BIND), + BPF_S_PROG_SEC("cgroup/post_bind6", BPF_CGROUP_INET6_POST_BIND), }; #undef BPF_PROG_SEC #undef BPF_PROG_SEC_FULL +#undef BPF_S_PROG_SEC #undef BPF_SA_PROG_SEC static int bpf_program__identify_section(struct bpf_program *prog) @@ -1929,6 +2089,16 @@ const char *bpf_map__name(struct bpf_map *map) return map ? map->name : NULL; } +uint32_t bpf_map__btf_key_type_id(const struct bpf_map *map) +{ + return map ? map->btf_key_type_id : 0; +} + +uint32_t bpf_map__btf_value_type_id(const struct bpf_map *map) +{ + return map ? map->btf_value_type_id : 0; +} + int bpf_map__set_priv(struct bpf_map *map, void *priv, bpf_map_clear_priv_t clear_priv) { @@ -2028,13 +2198,17 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, enum bpf_attach_type expected_attach_type; enum bpf_prog_type prog_type; struct bpf_object *obj; + struct bpf_map *map; int section_idx; int err; if (!attr) return -EINVAL; + if (!attr->file) + return -EINVAL; - obj = bpf_object__open(attr->file); + obj = __bpf_object__open(attr->file, NULL, 0, + bpf_prog_type__needs_kver(attr->prog_type)); if (IS_ERR_OR_NULL(obj)) return -ENOENT; @@ -2044,6 +2218,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, * section name. */ prog_type = attr->prog_type; + prog->prog_ifindex = attr->ifindex; expected_attach_type = attr->expected_attach_type; if (prog_type == BPF_PROG_TYPE_UNSPEC) { section_idx = bpf_program__identify_section(prog); @@ -2064,6 +2239,10 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, first_prog = prog; } + bpf_map__for_each(map, obj) { + map->map_ifindex = attr->ifindex; + } + if (!first_prog) { pr_warning("object file doesn't contain bpf program\n"); bpf_object__close(obj); @@ -2080,3 +2259,63 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, *prog_fd = bpf_program__fd(first_prog); return 0; } + +enum bpf_perf_event_ret +bpf_perf_event_read_simple(void *mem, unsigned long size, + unsigned long page_size, void **buf, size_t *buf_len, + bpf_perf_event_print_t fn, void *priv) +{ + volatile struct perf_event_mmap_page *header = mem; + __u64 data_tail = header->data_tail; + __u64 data_head = header->data_head; + void *base, *begin, *end; + int ret; + + asm volatile("" ::: "memory"); /* in real code it should be smp_rmb() */ + if (data_head == data_tail) + return LIBBPF_PERF_EVENT_CONT; + + base = ((char *)header) + page_size; + + begin = base + data_tail % size; + end = base + data_head % size; + + while (begin != end) { + struct perf_event_header *ehdr; + + ehdr = begin; + if (begin + ehdr->size > base + size) { + long len = base + size - begin; + + if (*buf_len < ehdr->size) { + free(*buf); + *buf = malloc(ehdr->size); + if (!*buf) { + ret = LIBBPF_PERF_EVENT_ERROR; + break; + } + *buf_len = ehdr->size; + } + + memcpy(*buf, begin, len); + memcpy(*buf + len, base, ehdr->size - len); + ehdr = (void *)*buf; + begin = base + ehdr->size - len; + } else if (begin + ehdr->size == base + size) { + begin = base; + } else { + begin += ehdr->size; + } + + ret = fn(ehdr, priv); + if (ret != LIBBPF_PERF_EVENT_CONT) + break; + + data_tail += ehdr->size; + } + + __sync_synchronize(); /* smp_mb() */ + header->data_tail = data_tail; + + return ret; +} diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index a3a62a5..0997653 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -52,8 +52,8 @@ enum libbpf_errno { int libbpf_strerror(int err, char *buf, size_t size); /* - * In include/linux/compiler-gcc.h, __printf is defined. However - * it should be better if libbpf.h doesn't depend on Linux header file. + * __printf is defined in include/linux/compiler-gcc.h. However, + * it would be better if libbpf.h didn't depend on Linux header files. * So instead of __printf, here we use gcc attribute directly. */ typedef int (*libbpf_print_fn_t)(const char *, ...) @@ -78,6 +78,7 @@ int bpf_object__load(struct bpf_object *obj); int bpf_object__unload(struct bpf_object *obj); const char *bpf_object__name(struct bpf_object *obj); unsigned int bpf_object__kversion(struct bpf_object *obj); +int bpf_object__btf_fd(const struct bpf_object *obj); struct bpf_object *bpf_object__next(struct bpf_object *prev); #define bpf_object__for_each_safe(pos, tmp) \ @@ -91,7 +92,7 @@ int bpf_object__set_priv(struct bpf_object *obj, void *priv, bpf_object_clear_priv_t clear_priv); void *bpf_object__priv(struct bpf_object *prog); -/* Accessors of bpf_program. */ +/* Accessors of bpf_program */ struct bpf_program; struct bpf_program *bpf_program__next(struct bpf_program *prog, struct bpf_object *obj); @@ -120,28 +121,28 @@ struct bpf_insn; /* * Libbpf allows callers to adjust BPF programs before being loaded - * into kernel. One program in an object file can be transform into - * multiple variants to be attached to different code. + * into kernel. One program in an object file can be transformed into + * multiple variants to be attached to different hooks. * * bpf_program_prep_t, bpf_program__set_prep and bpf_program__nth_fd - * are APIs for this propose. + * form an API for this purpose. * * - bpf_program_prep_t: - * It defines 'preprocessor', which is a caller defined function + * Defines a 'preprocessor', which is a caller defined function * passed to libbpf through bpf_program__set_prep(), and will be * called before program is loaded. The processor should adjust - * the program one time for each instances according to the number + * the program one time for each instance according to the instance id * passed to it. * * - bpf_program__set_prep: - * Attachs a preprocessor to a BPF program. The number of instances - * whould be created is also passed through this function. + * Attaches a preprocessor to a BPF program. The number of instances + * that should be created is also passed through this function. * * - bpf_program__nth_fd: - * After the program is loaded, get resuling fds from bpf program for - * each instances. + * After the program is loaded, get resulting FD of a given instance + * of the BPF program. * - * If bpf_program__set_prep() is not used, the program whould be loaded + * If bpf_program__set_prep() is not used, the program would be loaded * without adjustment during bpf_object__load(). The program has only * one instance. In this case bpf_program__fd(prog) is equal to * bpf_program__nth_fd(prog, 0). @@ -155,7 +156,7 @@ struct bpf_prog_prep_result { struct bpf_insn *new_insn_ptr; int new_insn_cnt; - /* If not NULL, result fd is set to it */ + /* If not NULL, result FD is written to it. */ int *pfd; }; @@ -168,8 +169,8 @@ struct bpf_prog_prep_result { * - res: Output parameter, result of transformation. * * Return value: - * - Zero: pre-processing success. - * - Non-zero: pre-processing, stop loading. + * - Zero: pre-processing success. + * - Non-zero: pre-processing error, stop loading. */ typedef int (*bpf_program_prep_t)(struct bpf_program *prog, int n, struct bpf_insn *insns, int insns_cnt, @@ -181,19 +182,23 @@ int bpf_program__set_prep(struct bpf_program *prog, int nr_instance, int bpf_program__nth_fd(struct bpf_program *prog, int n); /* - * Adjust type of bpf program. Default is kprobe. + * Adjust type of BPF program. Default is kprobe. */ int bpf_program__set_socket_filter(struct bpf_program *prog); int bpf_program__set_tracepoint(struct bpf_program *prog); +int bpf_program__set_raw_tracepoint(struct bpf_program *prog); int bpf_program__set_kprobe(struct bpf_program *prog); int bpf_program__set_sched_cls(struct bpf_program *prog); int bpf_program__set_sched_act(struct bpf_program *prog); int bpf_program__set_xdp(struct bpf_program *prog); int bpf_program__set_perf_event(struct bpf_program *prog); void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type); +void bpf_program__set_expected_attach_type(struct bpf_program *prog, + enum bpf_attach_type type); bool bpf_program__is_socket_filter(struct bpf_program *prog); bool bpf_program__is_tracepoint(struct bpf_program *prog); +bool bpf_program__is_raw_tracepoint(struct bpf_program *prog); bool bpf_program__is_kprobe(struct bpf_program *prog); bool bpf_program__is_sched_cls(struct bpf_program *prog); bool bpf_program__is_sched_act(struct bpf_program *prog); @@ -201,10 +206,10 @@ bool bpf_program__is_xdp(struct bpf_program *prog); bool bpf_program__is_perf_event(struct bpf_program *prog); /* - * We don't need __attribute__((packed)) now since it is - * unnecessary for 'bpf_map_def' because they are all aligned. - * In addition, using it will trigger -Wpacked warning message, - * and will be treated as an error due to -Werror. + * No need for __attribute__((packed)), all members of 'bpf_map_def' + * are all aligned. In addition, using __attribute__((packed)) + * would trigger a -Wpacked warning message, and lead to an error + * if -Werror is set. */ struct bpf_map_def { unsigned int type; @@ -215,8 +220,8 @@ struct bpf_map_def { }; /* - * There is another 'struct bpf_map' in include/linux/map.h. However, - * it is not a uapi header so no need to consider name clash. + * The 'struct bpf_map' in include/linux/bpf.h is internal to the kernel, + * so no need to worry about a name clash. */ struct bpf_map; struct bpf_map * @@ -224,7 +229,7 @@ bpf_object__find_map_by_name(struct bpf_object *obj, const char *name); /* * Get bpf_map through the offset of corresponding struct bpf_map_def - * in the bpf object file. + * in the BPF object file. */ struct bpf_map * bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset); @@ -239,6 +244,8 @@ bpf_map__next(struct bpf_map *map, struct bpf_object *obj); int bpf_map__fd(struct bpf_map *map); const struct bpf_map_def *bpf_map__def(struct bpf_map *map); const char *bpf_map__name(struct bpf_map *map); +uint32_t bpf_map__btf_key_type_id(const struct bpf_map *map); +uint32_t bpf_map__btf_value_type_id(const struct bpf_map *map); typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *); int bpf_map__set_priv(struct bpf_map *map, void *priv, @@ -252,6 +259,7 @@ struct bpf_prog_load_attr { const char *file; enum bpf_prog_type prog_type; enum bpf_attach_type expected_attach_type; + int ifindex; }; int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, @@ -260,4 +268,17 @@ int bpf_prog_load(const char *file, enum bpf_prog_type type, struct bpf_object **pobj, int *prog_fd); int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags); + +enum bpf_perf_event_ret { + LIBBPF_PERF_EVENT_DONE = 0, + LIBBPF_PERF_EVENT_ERROR = -1, + LIBBPF_PERF_EVENT_CONT = -2, +}; + +typedef enum bpf_perf_event_ret (*bpf_perf_event_print_t)(void *event, + void *priv); +int bpf_perf_event_read_simple(void *mem, unsigned long size, + unsigned long page_size, + void **buf, size_t *buf_len, + bpf_perf_event_print_t fn, void *priv); #endif diff --git a/tools/lib/symbol/kallsyms.c b/tools/lib/symbol/kallsyms.c index 689b6a1..96d8305 100644 --- a/tools/lib/symbol/kallsyms.c +++ b/tools/lib/symbol/kallsyms.c @@ -10,6 +10,12 @@ u8 kallsyms2elf_type(char type) return (type == 't' || type == 'w') ? STT_FUNC : STT_OBJECT; } +bool kallsyms__is_function(char symbol_type) +{ + symbol_type = toupper(symbol_type); + return symbol_type == 'T' || symbol_type == 'W'; +} + int kallsyms__parse(const char *filename, void *arg, int (*process_symbol)(void *arg, const char *name, char type, u64 start)) diff --git a/tools/lib/symbol/kallsyms.h b/tools/lib/symbol/kallsyms.h index bc40101..72ab987 100644 --- a/tools/lib/symbol/kallsyms.h +++ b/tools/lib/symbol/kallsyms.h @@ -20,6 +20,8 @@ static inline u8 kallsyms2elf_binding(char type) u8 kallsyms2elf_type(char type); +bool kallsyms__is_function(char symbol_type); + int kallsyms__parse(const char *filename, void *arg, int (*process_symbol)(void *arg, const char *name, char type, u64 start)); diff --git a/tools/memory-model/Documentation/cheatsheet.txt b/tools/memory-model/Documentation/cheatsheet.txt index 956b1ae4..33ba98d 100644 --- a/tools/memory-model/Documentation/cheatsheet.txt +++ b/tools/memory-model/Documentation/cheatsheet.txt @@ -1,6 +1,6 @@ Prior Operation Subsequent Operation --------------- --------------------------- - C Self R W RWM Self R W DR DW RMW SV + C Self R W RMW Self R W DR DW RMW SV -- ---- - - --- ---- - - -- -- --- -- Store, e.g., WRITE_ONCE() Y Y @@ -14,7 +14,7 @@ smp_wmb() Y W Y Y W smp_mb() & synchronize_rcu() CP Y Y Y Y Y Y Y Y Successful full non-void RMW CP Y Y Y Y Y Y Y Y Y Y Y smp_mb__before_atomic() CP Y Y Y a a a a Y -smp_mb__after_atomic() CP a a Y Y Y Y Y +smp_mb__after_atomic() CP a a Y Y Y Y Y Y Key: C: Ordering is cumulative @@ -26,4 +26,5 @@ Key: C: Ordering is cumulative DR: Dependent read (address dependency) DW: Dependent write (address, data, or control dependency) RMW: Atomic read-modify-write operation - SV Same-variable access + SELF: Orders self, as opposed to accesses before and/or after + SV: Orders later accesses to the same variable diff --git a/tools/memory-model/Documentation/explanation.txt b/tools/memory-model/Documentation/explanation.txt index a727c82..1b09f31 100644 --- a/tools/memory-model/Documentation/explanation.txt +++ b/tools/memory-model/Documentation/explanation.txt @@ -27,7 +27,7 @@ Explanation of the Linux-Kernel Memory Consistency Model 19. AND THEN THERE WAS ALPHA 20. THE HAPPENS-BEFORE RELATION: hb 21. THE PROPAGATES-BEFORE RELATION: pb - 22. RCU RELATIONS: link, gp-link, rscs-link, and rcu-path + 22. RCU RELATIONS: rcu-link, gp, rscs, rcu-fence, and rb 23. ODDS AND ENDS @@ -1451,8 +1451,8 @@ they execute means that it cannot have cycles. This requirement is the content of the LKMM's "propagation" axiom. -RCU RELATIONS: link, gp-link, rscs-link, and rcu-path ------------------------------------------------------ +RCU RELATIONS: rcu-link, gp, rscs, rcu-fence, and rb +---------------------------------------------------- RCU (Read-Copy-Update) is a powerful synchronization mechanism. It rests on two concepts: grace periods and read-side critical sections. @@ -1509,8 +1509,8 @@ y, which occurs before the end of the critical section, did not propagate to P1 before the end of the grace period, violating the Guarantee. -In the kernel's implementations of RCU, the business about stores -propagating to every CPU is realized by placing strong fences at +In the kernel's implementations of RCU, the requirements for stores +to propagate to every CPU are fulfilled by placing strong fences at suitable places in the RCU-related code. Thus, if a critical section starts before a grace period does then the critical section's CPU will execute an smp_mb() fence after the end of the critical section and @@ -1523,72 +1523,124 @@ executes. What exactly do we mean by saying that a critical section "starts before" or "ends after" a grace period? Some aspects of the meaning are pretty obvious, as in the example above, but the details aren't -entirely clear. The LKMM formalizes this notion by means of a -relation with the unfortunately generic name "link". It is a very -general relation; among other things, X ->link Z includes cases where -X happens-before or is equal to some event Y which is equal to or -comes before Z in the coherence order. Taking Y = Z, this says that -X ->rfe Z implies X ->link Z, and taking Y = X, it says that X ->fr Z -and X ->co Z each imply X ->link Z. - -The formal definition of the link relation is more than a little +entirely clear. The LKMM formalizes this notion by means of the +rcu-link relation. rcu-link encompasses a very general notion of +"before": Among other things, X ->rcu-link Z includes cases where X +happens-before or is equal to some event Y which is equal to or comes +before Z in the coherence order. When Y = Z this says that X ->rfe Z +implies X ->rcu-link Z. In addition, when Y = X it says that X ->fr Z +and X ->co Z each imply X ->rcu-link Z. + +The formal definition of the rcu-link relation is more than a little obscure, and we won't give it here. It is closely related to the pb relation, and the details don't matter unless you want to comb through a somewhat lengthy formal proof. Pretty much all you need to know -about link is the information in the preceding paragraph. - -The LKMM goes on to define the gp-link and rscs-link relations. They -bring grace periods and read-side critical sections into the picture, -in the following way: - - E ->gp-link F means there is a synchronize_rcu() fence event S - and an event X such that E ->po S, either S ->po X or S = X, - and X ->link F. In other words, E and F are connected by a - grace period followed by an instance of link. - - E ->rscs-link F means there is a critical section delimited by - an rcu_read_lock() fence L and an rcu_read_unlock() fence U, - and an event X such that E ->po U, either L ->po X or L = X, - and X ->link F. Roughly speaking, this says that some event - in the same critical section as E is connected by link to F. - -If we think of the link relation as standing for an extended "before", -then E ->gp-link F says that E executes before a grace period which -ends before F executes. (In fact it says more than this, because it -includes cases where E executes before a grace period and some store -propagates to F's CPU before F executes and doesn't propagate to some -other CPU until after the grace period ends.) Similarly, -E ->rscs-link F says that E is part of (or before the start of) a -critical section which starts before F executes. +about rcu-link is the information in the preceding paragraph. + +The LKMM also defines the gp and rscs relations. They bring grace +periods and read-side critical sections into the picture, in the +following way: + + E ->gp F means there is a synchronize_rcu() fence event S such + that E ->po S and either S ->po F or S = F. In simple terms, + there is a grace period po-between E and F. + + E ->rscs F means there is a critical section delimited by an + rcu_read_lock() fence L and an rcu_read_unlock() fence U, such + that E ->po U and either L ->po F or L = F. You can think of + this as saying that E and F are in the same critical section + (in fact, it also allows E to be po-before the start of the + critical section and F to be po-after the end). + +If we think of the rcu-link relation as standing for an extended +"before", then X ->gp Y ->rcu-link Z says that X executes before a +grace period which ends before Z executes. (In fact it covers more +than this, because it also includes cases where X executes before a +grace period and some store propagates to Z's CPU before Z executes +but doesn't propagate to some other CPU until after the grace period +ends.) Similarly, X ->rscs Y ->rcu-link Z says that X is part of (or +before the start of) a critical section which starts before Z +executes. + +The LKMM goes on to define the rcu-fence relation as a sequence of gp +and rscs links separated by rcu-link links, in which the number of gp +links is >= the number of rscs links. For example: + + X ->gp Y ->rcu-link Z ->rscs T ->rcu-link U ->gp V + +would imply that X ->rcu-fence V, because this sequence contains two +gp links and only one rscs link. (It also implies that X ->rcu-fence T +and Z ->rcu-fence V.) On the other hand: + + X ->rscs Y ->rcu-link Z ->rscs T ->rcu-link U ->gp V + +does not imply X ->rcu-fence V, because the sequence contains only +one gp link but two rscs links. + +The rcu-fence relation is important because the Grace Period Guarantee +means that rcu-fence acts kind of like a strong fence. In particular, +if W is a write and we have W ->rcu-fence Z, the Guarantee says that W +will propagate to every CPU before Z executes. + +To prove this in full generality requires some intellectual effort. +We'll consider just a very simple case: + + W ->gp X ->rcu-link Y ->rscs Z. + +This formula means that there is a grace period G and a critical +section C such that: + + 1. W is po-before G; + + 2. X is equal to or po-after G; + + 3. X comes "before" Y in some sense; + + 4. Y is po-before the end of C; + + 5. Z is equal to or po-after the start of C. + +From 2 - 4 we deduce that the grace period G ends before the critical +section C. Then the second part of the Grace Period Guarantee says +not only that G starts before C does, but also that W (which executes +on G's CPU before G starts) must propagate to every CPU before C +starts. In particular, W propagates to every CPU before Z executes +(or finishes executing, in the case where Z is equal to the +rcu_read_lock() fence event which starts C.) This sort of reasoning +can be expanded to handle all the situations covered by rcu-fence. + +Finally, the LKMM defines the RCU-before (rb) relation in terms of +rcu-fence. This is done in essentially the same way as the pb +relation was defined in terms of strong-fence. We will omit the +details; the end result is that E ->rb F implies E must execute before +F, just as E ->pb F does (and for much the same reasons). Putting this all together, the LKMM expresses the Grace Period -Guarantee by requiring that there are no cycles consisting of gp-link -and rscs-link connections in which the number of gp-link instances is ->= the number of rscs-link instances. It does this by defining the -rcu-path relation to link events E and F whenever it is possible to -pass from E to F by a sequence of gp-link and rscs-link connections -with at least as many of the former as the latter. The LKMM's "rcu" -axiom then says that there are no events E such that E ->rcu-path E. - -Justifying this axiom takes some intellectual effort, but it is in -fact a valid formalization of the Grace Period Guarantee. We won't -attempt to go through the detailed argument, but the following -analysis gives a taste of what is involved. Suppose we have a -violation of the first part of the Guarantee: A critical section -starts before a grace period, and some store propagates to the -critical section's CPU before the end of the critical section but -doesn't propagate to some other CPU until after the end of the grace -period. +Guarantee by requiring that the rb relation does not contain a cycle. +Equivalently, this "rcu" axiom requires that there are no events E and +F with E ->rcu-link F ->rcu-fence E. Or to put it a third way, the +axiom requires that there are no cycles consisting of gp and rscs +alternating with rcu-link, where the number of gp links is >= the +number of rscs links. + +Justifying the axiom isn't easy, but it is in fact a valid +formalization of the Grace Period Guarantee. We won't attempt to go +through the detailed argument, but the following analysis gives a +taste of what is involved. Suppose we have a violation of the first +part of the Guarantee: A critical section starts before a grace +period, and some store propagates to the critical section's CPU before +the end of the critical section but doesn't propagate to some other +CPU until after the end of the grace period. Putting symbols to these ideas, let L and U be the rcu_read_lock() and rcu_read_unlock() fence events delimiting the critical section in question, and let S be the synchronize_rcu() fence event for the grace period. Saying that the critical section starts before S means there are events E and F where E is po-after L (which marks the start of the -critical section), E is "before" F in the sense of the link relation, -and F is po-before the grace period S: +critical section), E is "before" F in the sense of the rcu-link +relation, and F is po-before the grace period S: - L ->po E ->link F ->po S. + L ->po E ->rcu-link F ->po S. Let W be the store mentioned above, let Z come before the end of the critical section and witness that W propagates to the critical @@ -1600,16 +1652,19 @@ some event X which is po-after S. Symbolically, this amounts to: The fr link from Y to W indicates that W has not propagated to Y's CPU at the time that Y executes. From this, it can be shown (see the -discussion of the link relation earlier) that X and Z are connected by -link, yielding: +discussion of the rcu-link relation earlier) that X and Z are related +by rcu-link, yielding: + + S ->po X ->rcu-link Z ->po U. + +The formulas say that S is po-between F and X, hence F ->gp X. They +also say that Z comes before the end of the critical section and E +comes after its start, hence Z ->rscs E. From all this we obtain: - S ->po X ->link Z ->po U. + F ->gp X ->rcu-link Z ->rscs E ->rcu-link F, -These formulas say that S is po-between F and X, hence F ->gp-link Z -via X. They also say that Z comes before the end of the critical -section and E comes after its start, hence Z ->rscs-link F via E. But -now we have a forbidden cycle: F ->gp-link Z ->rscs-link F. Thus the -"rcu" axiom rules out this violation of the Grace Period Guarantee. +a forbidden cycle. Thus the "rcu" axiom rules out this violation of +the Grace Period Guarantee. For something a little more down-to-earth, let's see how the axiom works out in practice. Consider the RCU code example from above, this @@ -1635,18 +1690,18 @@ time with statement labels added to the memory access instructions: } -If r2 = 0 at the end then P0's store at X overwrites the value -that P1's load at Z reads from, so we have Z ->fre X and thus -Z ->link X. In addition, there is a synchronize_rcu() between Y and -Z, so therefore we have Y ->gp-link X. +If r2 = 0 at the end then P0's store at X overwrites the value that +P1's load at Z reads from, so we have Z ->fre X and thus Z ->rcu-link X. +In addition, there is a synchronize_rcu() between Y and Z, so therefore +we have Y ->gp Z. If r1 = 1 at the end then P1's load at Y reads from P0's store at W, -so we have W ->link Y. In addition, W and X are in the same critical -section, so therefore we have X ->rscs-link Y. +so we have W ->rcu-link Y. In addition, W and X are in the same critical +section, so therefore we have X ->rscs W. -This gives us a cycle, Y ->gp-link X ->rscs-link Y, with one gp-link -and one rscs-link, violating the "rcu" axiom. Hence the outcome is -not allowed by the LKMM, as we would expect. +Then X ->rscs W ->rcu-link Y ->gp Z ->rcu-link X is a forbidden cycle, +violating the "rcu" axiom. Hence the outcome is not allowed by the +LKMM, as we would expect. For contrast, let's see what can happen in a more complicated example: @@ -1682,15 +1737,11 @@ For contrast, let's see what can happen in a more complicated example: } If r0 = r1 = r2 = 1 at the end, then similar reasoning to before shows -that W ->rscs-link Y via X, Y ->gp-link U via Z, and U ->rscs-link W -via V. And just as before, this gives a cycle: - - W ->rscs-link Y ->gp-link U ->rscs-link W. - -However, this cycle has fewer gp-link instances than rscs-link -instances, and consequently the outcome is not forbidden by the LKMM. -The following instruction timing diagram shows how it might actually -occur: +that W ->rscs X ->rcu-link Y ->gp Z ->rcu-link U ->rscs V ->rcu-link W. +However this cycle is not forbidden, because the sequence of relations +contains fewer instances of gp (one) than of rscs (two). Consequently +the outcome is allowed by the LKMM. The following instruction timing +diagram shows how it might actually occur: P0 P1 P2 -------------------- -------------------- -------------------- diff --git a/tools/memory-model/Documentation/references.txt b/tools/memory-model/Documentation/references.txt index ba2e34c..b177f3e 100644 --- a/tools/memory-model/Documentation/references.txt +++ b/tools/memory-model/Documentation/references.txt @@ -63,15 +63,22 @@ o Shaked Flur, Susmit Sarkar, Christopher Pulte, Kyndylan Nienhuis, Principles of Programming Languages (POPL 2017). ACM, New York, NY, USA, 429–442. +o Christopher Pulte, Shaked Flur, Will Deacon, Jon French, + Susmit Sarkar, and Peter Sewell. 2018. "Simplifying ARM concurrency: + multicopy-atomic axiomatic and operational models for ARMv8". In + Proceedings of the ACM on Programming Languages, Volume 2, Issue + POPL, Article No. 19. ACM, New York, NY, USA. + Linux-kernel memory model ========================= -o Andrea Parri, Alan Stern, Luc Maranget, Paul E. McKenney, - and Jade Alglave. 2017. "A formal model of - Linux-kernel memory ordering - companion webpage". - http://moscova.inria.fr/∼maranget/cats7/linux/. (2017). [Online; - accessed 30-January-2017]. +o Jade Alglave, Luc Maranget, Paul E. McKenney, Andrea Parri, and + Alan Stern. 2018. "Frightening small children and disconcerting + grown-ups: Concurrency in the Linux kernel". In Proceedings of + the 23rd International Conference on Architectural Support for + Programming Languages and Operating Systems (ASPLOS 2018). ACM, + New York, NY, USA, 405-418. Webpage: http://diy.inria.fr/linux/. o Jade Alglave, Luc Maranget, Paul E. McKenney, Andrea Parri, and Alan Stern. 2017. "A formal kernel memory-ordering model (part 1)" diff --git a/tools/memory-model/README b/tools/memory-model/README index 0b3a5f3..734f7fe 100644 --- a/tools/memory-model/README +++ b/tools/memory-model/README @@ -20,7 +20,7 @@ that litmus test to be exercised within the Linux kernel. REQUIREMENTS ============ -Version 7.48 of the "herd7" and "klitmus7" tools must be downloaded +Version 7.49 of the "herd7" and "klitmus7" tools must be downloaded separately: https://github.com/herd/herdtools7 diff --git a/tools/memory-model/linux-kernel.bell b/tools/memory-model/linux-kernel.bell index 432c7cf..64f5740 100644 --- a/tools/memory-model/linux-kernel.bell +++ b/tools/memory-model/linux-kernel.bell @@ -5,10 +5,10 @@ * Copyright (C) 2017 Alan Stern <stern@rowland.harvard.edu>, * Andrea Parri <parri.andrea@gmail.com> * - * An earlier version of this file appears in the companion webpage for + * An earlier version of this file appeared in the companion webpage for * "Frightening small children and disconcerting grown-ups: Concurrency * in the Linux kernel" by Alglave, Maranget, McKenney, Parri, and Stern, - * which is to appear in ASPLOS 2018. + * which appeared in ASPLOS 2018. *) "Linux-kernel memory consistency model" diff --git a/tools/memory-model/linux-kernel.cat b/tools/memory-model/linux-kernel.cat index df97db0..59b5cbe 100644 --- a/tools/memory-model/linux-kernel.cat +++ b/tools/memory-model/linux-kernel.cat @@ -5,10 +5,10 @@ * Copyright (C) 2017 Alan Stern <stern@rowland.harvard.edu>, * Andrea Parri <parri.andrea@gmail.com> * - * An earlier version of this file appears in the companion webpage for + * An earlier version of this file appeared in the companion webpage for * "Frightening small children and disconcerting grown-ups: Concurrency * in the Linux kernel" by Alglave, Maranget, McKenney, Parri, and Stern, - * which is to appear in ASPLOS 2018. + * which appeared in ASPLOS 2018. *) "Linux-kernel memory consistency model" @@ -100,22 +100,29 @@ let rscs = po ; crit^-1 ; po? * one but two non-rf relations, but only in conjunction with an RCU * read-side critical section. *) -let link = hb* ; pb* ; prop +let rcu-link = hb* ; pb* ; prop -(* Chains that affect the RCU grace-period guarantee *) -let gp-link = gp ; link -let rscs-link = rscs ; link +(* + * Any sequence containing at least as many grace periods as RCU read-side + * critical sections (joined by rcu-link) acts as a generalized strong fence. + *) +let rec rcu-fence = gp | + (gp ; rcu-link ; rscs) | + (rscs ; rcu-link ; gp) | + (gp ; rcu-link ; rcu-fence ; rcu-link ; rscs) | + (rscs ; rcu-link ; rcu-fence ; rcu-link ; gp) | + (rcu-fence ; rcu-link ; rcu-fence) + +(* rb orders instructions just as pb does *) +let rb = prop ; rcu-fence ; hb* ; pb* + +irreflexive rb as rcu (* - * A cycle containing at least as many grace periods as RCU read-side - * critical sections is forbidden. + * The happens-before, propagation, and rcu constraints are all + * expressions of temporal ordering. They could be replaced by + * a single constraint on an "executes-before" relation, xb: + * + * let xb = hb | pb | rb + * acyclic xb as executes-before *) -let rec rcu-path = - gp-link | - (gp-link ; rscs-link) | - (rscs-link ; gp-link) | - (rcu-path ; rcu-path) | - (gp-link ; rcu-path ; rscs-link) | - (rscs-link ; rcu-path ; gp-link) - -irreflexive rcu-path as rcu diff --git a/tools/memory-model/linux-kernel.def b/tools/memory-model/linux-kernel.def index 397e4e6..6fa3eb2 100644 --- a/tools/memory-model/linux-kernel.def +++ b/tools/memory-model/linux-kernel.def @@ -1,9 +1,9 @@ // SPDX-License-Identifier: GPL-2.0+ // -// An earlier version of this file appears in the companion webpage for +// An earlier version of this file appeared in the companion webpage for // "Frightening small children and disconcerting grown-ups: Concurrency // in the Linux kernel" by Alglave, Maranget, McKenney, Parri, and Stern, -// which is to appear in ASPLOS 2018. +// which appeared in ASPLOS 2018. // ONCE READ_ONCE(X) __load{once}(X) @@ -14,14 +14,15 @@ smp_store_release(X,V) { __store{release}(*X,V); } smp_load_acquire(X) __load{acquire}(*X) rcu_assign_pointer(X,V) { __store{release}(X,V); } rcu_dereference(X) __load{once}(X) +smp_store_mb(X,V) { __store{once}(X,V); __fence{mb}; } // Fences -smp_mb() { __fence{mb} ; } -smp_rmb() { __fence{rmb} ; } -smp_wmb() { __fence{wmb} ; } -smp_mb__before_atomic() { __fence{before-atomic} ; } -smp_mb__after_atomic() { __fence{after-atomic} ; } -smp_mb__after_spinlock() { __fence{after-spinlock} ; } +smp_mb() { __fence{mb}; } +smp_rmb() { __fence{rmb}; } +smp_wmb() { __fence{wmb}; } +smp_mb__before_atomic() { __fence{before-atomic}; } +smp_mb__after_atomic() { __fence{after-atomic}; } +smp_mb__after_spinlock() { __fence{after-spinlock}; } // Exchange xchg(X,V) __xchg{mb}(X,V) @@ -34,26 +35,27 @@ cmpxchg_acquire(X,V,W) __cmpxchg{acquire}(X,V,W) cmpxchg_release(X,V,W) __cmpxchg{release}(X,V,W) // Spinlocks -spin_lock(X) { __lock(X) ; } -spin_unlock(X) { __unlock(X) ; } +spin_lock(X) { __lock(X); } +spin_unlock(X) { __unlock(X); } spin_trylock(X) __trylock(X) +spin_is_locked(X) __islocked(X) // RCU rcu_read_lock() { __fence{rcu-lock}; } -rcu_read_unlock() { __fence{rcu-unlock};} +rcu_read_unlock() { __fence{rcu-unlock}; } synchronize_rcu() { __fence{sync-rcu}; } synchronize_rcu_expedited() { __fence{sync-rcu}; } // Atomic atomic_read(X) READ_ONCE(*X) -atomic_set(X,V) { WRITE_ONCE(*X,V) ; } +atomic_set(X,V) { WRITE_ONCE(*X,V); } atomic_read_acquire(X) smp_load_acquire(X) atomic_set_release(X,V) { smp_store_release(X,V); } -atomic_add(V,X) { __atomic_op(X,+,V) ; } -atomic_sub(V,X) { __atomic_op(X,-,V) ; } -atomic_inc(X) { __atomic_op(X,+,1) ; } -atomic_dec(X) { __atomic_op(X,-,1) ; } +atomic_add(V,X) { __atomic_op(X,+,V); } +atomic_sub(V,X) { __atomic_op(X,-,V); } +atomic_inc(X) { __atomic_op(X,+,1); } +atomic_dec(X) { __atomic_op(X,-,1); } atomic_add_return(V,X) __atomic_op_return{mb}(X,+,V) atomic_add_return_relaxed(V,X) __atomic_op_return{once}(X,+,V) diff --git a/tools/memory-model/litmus-tests/.gitignore b/tools/memory-model/litmus-tests/.gitignore new file mode 100644 index 0000000..6e2ddc54 --- /dev/null +++ b/tools/memory-model/litmus-tests/.gitignore @@ -0,0 +1 @@ +*.litmus.out diff --git a/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus b/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus index 50d5db9..98a3716 100644 --- a/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus +++ b/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus @@ -7,7 +7,7 @@ C IRIW+mbonceonces+OnceOnce * between each pairs of reads. In other words, is smp_mb() sufficient to * cause two different reading processes to agree on the order of a pair * of writes, where each write is to a different variable by a different - * process? + * process? This litmus test exercises LKMM's "propagation" rule. *) {} diff --git a/tools/memory-model/litmus-tests/MP+polockmbonce+poacquiresilsil.litmus b/tools/memory-model/litmus-tests/MP+polockmbonce+poacquiresilsil.litmus new file mode 100644 index 0000000..50f4d62 --- /dev/null +++ b/tools/memory-model/litmus-tests/MP+polockmbonce+poacquiresilsil.litmus @@ -0,0 +1,35 @@ +C MP+polockmbonce+poacquiresilsil + +(* + * Result: Never + * + * Do spinlocks combined with smp_mb__after_spinlock() provide order + * to outside observers using spin_is_locked() to sense the lock-held + * state, ordered by acquire? Note that when the first spin_is_locked() + * returns false and the second true, we know that the smp_load_acquire() + * executed before the lock was acquired (loosely speaking). + *) + +{ +} + +P0(spinlock_t *lo, int *x) +{ + spin_lock(lo); + smp_mb__after_spinlock(); + WRITE_ONCE(*x, 1); + spin_unlock(lo); +} + +P1(spinlock_t *lo, int *x) +{ + int r1; + int r2; + int r3; + + r1 = smp_load_acquire(x); + r2 = spin_is_locked(lo); + r3 = spin_is_locked(lo); +} + +exists (1:r1=1 /\ 1:r2=0 /\ 1:r3=1) diff --git a/tools/memory-model/litmus-tests/MP+polockonce+poacquiresilsil.litmus b/tools/memory-model/litmus-tests/MP+polockonce+poacquiresilsil.litmus new file mode 100644 index 0000000..abf81e7 --- /dev/null +++ b/tools/memory-model/litmus-tests/MP+polockonce+poacquiresilsil.litmus @@ -0,0 +1,34 @@ +C MP+polockonce+poacquiresilsil + +(* + * Result: Sometimes + * + * Do spinlocks provide order to outside observers using spin_is_locked() + * to sense the lock-held state, ordered by acquire? Note that when the + * first spin_is_locked() returns false and the second true, we know that + * the smp_load_acquire() executed before the lock was acquired (loosely + * speaking). + *) + +{ +} + +P0(spinlock_t *lo, int *x) +{ + spin_lock(lo); + WRITE_ONCE(*x, 1); + spin_unlock(lo); +} + +P1(spinlock_t *lo, int *x) +{ + int r1; + int r2; + int r3; + + r1 = smp_load_acquire(x); + r2 = spin_is_locked(lo); + r3 = spin_is_locked(lo); +} + +exists (1:r1=1 /\ 1:r2=0 /\ 1:r3=1) diff --git a/tools/memory-model/litmus-tests/README b/tools/memory-model/litmus-tests/README index 04096fb..17eb9a8 100644 --- a/tools/memory-model/litmus-tests/README +++ b/tools/memory-model/litmus-tests/README @@ -23,7 +23,8 @@ IRIW+mbonceonces+OnceOnce.litmus between each pairs of reads. In other words, is smp_mb() sufficient to cause two different reading processes to agree on the order of a pair of writes, where each write is to a different - variable by a different process? + variable by a different process? This litmus test is forbidden + by LKMM's propagation rule. IRIW+poonceonces+OnceOnce.litmus Test of independent reads from independent writes with nothing @@ -63,6 +64,16 @@ LB+poonceonces.litmus MP+onceassign+derefonce.litmus As below, but with rcu_assign_pointer() and an rcu_dereference(). +MP+polockmbonce+poacquiresilsil.litmus + Protect the access with a lock and an smp_mb__after_spinlock() + in one process, and use an acquire load followed by a pair of + spin_is_locked() calls in the other process. + +MP+polockonce+poacquiresilsil.litmus + Protect the access with a lock in one process, and use an + acquire load followed by a pair of spin_is_locked() calls + in the other process. + MP+polocks.litmus As below, but with the second access of the writer process and the first access of reader process protected by a lock. @@ -109,8 +120,10 @@ S+wmbonceonce+poacquireonce.litmus WRC+poonceonces+Once.litmus WRC+pooncerelease+rmbonceonce+Once.litmus - These two are members of an extension of the MP litmus-test class - in which the first write is moved to a separate process. + These two are members of an extension of the MP litmus-test + class in which the first write is moved to a separate process. + The second is forbidden because smp_store_release() is + A-cumulative in LKMM. Z6.0+pooncelock+pooncelock+pombonce.litmus Is the ordering provided by a spin_unlock() and a subsequent diff --git a/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus b/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus index 97fcbff..ad3448b 100644 --- a/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus +++ b/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus @@ -5,7 +5,9 @@ C WRC+pooncerelease+rmbonceonce+Once * * This litmus test is an extension of the message-passing pattern, where * the first write is moved to a separate process. Because it features - * a release and a read memory barrier, it should be forbidden. + * a release and a read memory barrier, it should be forbidden. More + * specifically, this litmus test is forbidden because smp_store_release() + * is A-cumulative in LKMM. *) {} diff --git a/tools/memory-model/lock.cat b/tools/memory-model/lock.cat index ba4a4ec..305ded1 100644 --- a/tools/memory-model/lock.cat +++ b/tools/memory-model/lock.cat @@ -4,46 +4,72 @@ * Copyright (C) 2017 Alan Stern <stern@rowland.harvard.edu> *) -(* Generate coherence orders and handle lock operations *) +(* + * Generate coherence orders and handle lock operations + * + * Warning: spin_is_locked() crashes herd7 versions strictly before 7.48. + * spin_is_locked() is functional from herd7 version 7.49. + *) include "cross.cat" -(* From lock reads to their partner lock writes *) -let lk-rmw = ([LKR] ; po-loc ; [LKW]) \ (po ; po) -let rmw = rmw | lk-rmw - (* - * A paired LKR must always see an unlocked value; spin_lock() calls nested - * inside a critical section (for the same lock) always deadlock. + * The lock-related events generated by herd are as follows: + * + * LKR Lock-Read: the read part of a spin_lock() or successful + * spin_trylock() read-modify-write event pair + * LKW Lock-Write: the write part of a spin_lock() or successful + * spin_trylock() RMW event pair + * UL Unlock: a spin_unlock() event + * LF Lock-Fail: a failed spin_trylock() event + * RL Read-Locked: a spin_is_locked() event which returns True + * RU Read-Unlocked: a spin_is_locked() event which returns False + * + * LKR and LKW events always come paired, like all RMW event sequences. + * + * LKR, LF, RL, and RU are read events; LKR has Acquire ordering. + * LKW and UL are write events; UL has Release ordering. + * LKW, LF, RL, and RU have no ordering properties. *) -empty ([LKW] ; po-loc ; [domain(lk-rmw)]) \ (po-loc ; [UL] ; po-loc) - as lock-nest -(* The litmus test is invalid if an LKW event is not part of an RMW pair *) -flag ~empty LKW \ range(lk-rmw) as unpaired-LKW +(* Backward compatibility *) +let RL = try RL with emptyset +let RU = try RU with emptyset -(* This will be allowed if we implement spin_is_locked() *) -flag ~empty LKR \ domain(lk-rmw) as unpaired-LKR +(* Treat RL as a kind of LF: a read with no ordering properties *) +let LF = LF | RL -(* There should be no R or W accesses to spinlocks *) -let ALL-LOCKS = LKR | LKW | UL | LF +(* There should be no ordinary R or W accesses to spinlocks *) +let ALL-LOCKS = LKR | LKW | UL | LF | RU flag ~empty [M \ IW] ; loc ; [ALL-LOCKS] as mixed-lock-accesses +(* Link Lock-Reads to their RMW-partner Lock-Writes *) +let lk-rmw = ([LKR] ; po-loc ; [LKW]) \ (po ; po) +let rmw = rmw | lk-rmw + +(* The litmus test is invalid if an LKR/LKW event is not part of an RMW pair *) +flag ~empty LKW \ range(lk-rmw) as unpaired-LKW +flag ~empty LKR \ domain(lk-rmw) as unpaired-LKR + +(* + * An LKR must always see an unlocked value; spin_lock() calls nested + * inside a critical section (for the same lock) always deadlock. + *) +empty ([LKW] ; po-loc ; [LKR]) \ (po-loc ; [UL] ; po-loc) as lock-nest + (* The final value of a spinlock should not be tested *) flag ~empty [FW] ; loc ; [ALL-LOCKS] as lock-final - (* * Put lock operations in their appropriate classes, but leave UL out of W * until after the co relation has been generated. *) -let R = R | LKR | LF +let R = R | LKR | LF | RU let W = W | LKW let Release = Release | UL let Acquire = Acquire | LKR - (* Match LKW events to their corresponding UL events *) let critical = ([LKW] ; po-loc ; [UL]) \ (po-loc ; [LKW | UL] ; po-loc) @@ -53,27 +79,48 @@ flag ~empty UL \ range(critical) as unmatched-unlock let UNMATCHED-LKW = LKW \ domain(critical) empty ([UNMATCHED-LKW] ; loc ; [UNMATCHED-LKW]) \ id as unmatched-locks - (* rfi for LF events: link each LKW to the LF events in its critical section *) let rfi-lf = ([LKW] ; po-loc ; [LF]) \ ([LKW] ; po-loc ; [UL] ; po-loc) (* rfe for LF events *) let all-possible-rfe-lf = - (* - * Given an LF event r, compute the possible rfe edges for that event - * (all those starting from LKW events in other threads), - * and then convert that relation to a set of single-edge relations. - *) - let possible-rfe-lf r = - let pair-to-relation p = p ++ 0 - in map pair-to-relation ((LKW * {r}) & loc & ext) - (* Do this for each LF event r that isn't in rfi-lf *) - in map possible-rfe-lf (LF \ range(rfi-lf)) + (* + * Given an LF event r, compute the possible rfe edges for that event + * (all those starting from LKW events in other threads), + * and then convert that relation to a set of single-edge relations. + *) + let possible-rfe-lf r = + let pair-to-relation p = p ++ 0 + in map pair-to-relation ((LKW * {r}) & loc & ext) + (* Do this for each LF event r that isn't in rfi-lf *) + in map possible-rfe-lf (LF \ range(rfi-lf)) (* Generate all rf relations for LF events *) with rfe-lf from cross(all-possible-rfe-lf) -let rf = rf | rfi-lf | rfe-lf +let rf-lf = rfe-lf | rfi-lf + +(* + * RU, i.e., spin_is_locked() returning False, is slightly different. + * We rely on the memory model to rule out cases where spin_is_locked() + * within one of the lock's critical sections returns False. + *) + +(* rfi for RU events: an RU may read from the last po-previous UL *) +let rfi-ru = ([UL] ; po-loc ; [RU]) \ ([UL] ; po-loc ; [LKW] ; po-loc) + +(* rfe for RU events: an RU may read from an external UL or the initial write *) +let all-possible-rfe-ru = + let possible-rfe-ru r = + let pair-to-relation p = p ++ 0 + in map pair-to-relation (((UL | IW) * {r}) & loc & ext) + in map possible-rfe-ru RU + +(* Generate all rf relations for RU events *) +with rfe-ru from cross(all-possible-rfe-ru) +let rf-ru = rfe-ru | rfi-ru +(* Final rf relation *) +let rf = rf | rf-lf | rf-ru (* Generate all co relations, including LKW events but not UL *) let co0 = co0 | ([IW] ; loc ; [LKW]) | diff --git a/tools/memory-model/scripts/checkalllitmus.sh b/tools/memory-model/scripts/checkalllitmus.sh new file mode 100644 index 0000000..af0aa15 --- /dev/null +++ b/tools/memory-model/scripts/checkalllitmus.sh @@ -0,0 +1,73 @@ +#!/bin/sh +# +# Run herd tests on all .litmus files in the specified directory (which +# defaults to litmus-tests) and check each file's result against a "Result:" +# comment within that litmus test. If the verification result does not +# match that specified in the litmus test, this script prints an error +# message prefixed with "^^^". It also outputs verification results to +# a file whose name is that of the specified litmus test, but with ".out" +# appended. +# +# Usage: +# sh checkalllitmus.sh [ directory ] +# +# The LINUX_HERD_OPTIONS environment variable may be used to specify +# arguments to herd, whose default is defined by the checklitmus.sh script. +# Thus, one would normally run this in the directory containing the memory +# model, specifying the pathname of the litmus test to check. +# +# This script makes no attempt to run the litmus tests concurrently. +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, you can access it online at +# http://www.gnu.org/licenses/gpl-2.0.html. +# +# Copyright IBM Corporation, 2018 +# +# Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com> + +litmusdir=${1-litmus-tests} +if test -d "$litmusdir" -a -r "$litmusdir" -a -x "$litmusdir" +then + : +else + echo ' --- ' error: $litmusdir is not an accessible directory + exit 255 +fi + +# Find the checklitmus script. If it is not where we expect it, then +# assume that the caller has the PATH environment variable set +# appropriately. +if test -x scripts/checklitmus.sh +then + clscript=scripts/checklitmus.sh +else + clscript=checklitmus.sh +fi + +# Run the script on all the litmus tests in the specified directory +ret=0 +for i in litmus-tests/*.litmus +do + if ! $clscript $i + then + ret=1 + fi +done +if test "$ret" -ne 0 +then + echo " ^^^ VERIFICATION MISMATCHES" +else + echo All litmus tests verified as was expected. +fi +exit $ret diff --git a/tools/memory-model/scripts/checklitmus.sh b/tools/memory-model/scripts/checklitmus.sh new file mode 100644 index 0000000..e2e4774 --- /dev/null +++ b/tools/memory-model/scripts/checklitmus.sh @@ -0,0 +1,86 @@ +#!/bin/sh +# +# Run a herd test and check the result against a "Result:" comment within +# the litmus test. If the verification result does not match that specified +# in the litmus test, this script prints an error message prefixed with +# "^^^" and exits with a non-zero status. It also outputs verification +# results to a file whose name is that of the specified litmus test, but +# with ".out" appended. +# +# Usage: +# sh checklitmus.sh file.litmus +# +# The LINUX_HERD_OPTIONS environment variable may be used to specify +# arguments to herd, which default to "-conf linux-kernel.cfg". Thus, +# one would normally run this in the directory containing the memory model, +# specifying the pathname of the litmus test to check. +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, you can access it online at +# http://www.gnu.org/licenses/gpl-2.0.html. +# +# Copyright IBM Corporation, 2018 +# +# Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com> + +litmus=$1 +herdoptions=${LINUX_HERD_OPTIONS--conf linux-kernel.cfg} + +if test -f "$litmus" -a -r "$litmus" +then + : +else + echo ' --- ' error: \"$litmus\" is not a readable file + exit 255 +fi +if grep -q '^ \* Result: ' $litmus +then + outcome=`grep -m 1 '^ \* Result: ' $litmus | awk '{ print $3 }'` +else + outcome=specified +fi + +echo Herd options: $herdoptions > $litmus.out +/usr/bin/time herd7 -o ~/tmp $herdoptions $litmus >> $litmus.out 2>&1 +grep "Herd options:" $litmus.out +grep '^Observation' $litmus.out +if grep -q '^Observation' $litmus.out +then + : +else + cat $litmus.out + echo ' ^^^ Verification error' + echo ' ^^^ Verification error' >> $litmus.out 2>&1 + exit 255 +fi +if test "$outcome" = DEADLOCK +then + echo grep 3 and 4 + if grep '^Observation' $litmus.out | grep -q 'Never 0 0$' + then + ret=0 + else + echo " ^^^ Unexpected non-$outcome verification" + echo " ^^^ Unexpected non-$outcome verification" >> $litmus.out 2>&1 + ret=1 + fi +elif grep '^Observation' $litmus.out | grep -q $outcome || test "$outcome" = Maybe +then + ret=0 +else + echo " ^^^ Unexpected non-$outcome verification" + echo " ^^^ Unexpected non-$outcome verification" >> $litmus.out 2>&1 + ret=1 +fi +tail -2 $litmus.out | head -1 +exit $ret diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 3a31b23..38047c6 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -543,6 +543,28 @@ static int add_jump_destinations(struct objtool_file *file) dest_off); return -1; } + + /* + * For GCC 8+, create parent/child links for any cold + * subfunctions. This is _mostly_ redundant with a similar + * initialization in read_symbols(). + * + * If a function has aliases, we want the *first* such function + * in the symbol table to be the subfunction's parent. In that + * case we overwrite the initialization done in read_symbols(). + * + * However this code can't completely replace the + * read_symbols() code because this doesn't detect the case + * where the parent function's only reference to a subfunction + * is through a switch table. + */ + if (insn->func && insn->jump_dest->func && + insn->func != insn->jump_dest->func && + !strstr(insn->func->name, ".cold.") && + strstr(insn->jump_dest->func->name, ".cold.")) { + insn->func->cfunc = insn->jump_dest->func; + insn->jump_dest->func->pfunc = insn->func; + } } return 0; diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile index db11478..42261a9 100644 --- a/tools/perf/Documentation/Makefile +++ b/tools/perf/Documentation/Makefile @@ -47,7 +47,8 @@ man5dir=$(mandir)/man5 man7dir=$(mandir)/man7 ASCIIDOC=asciidoc -ASCIIDOC_EXTRA = --unsafe +ASCIIDOC_EXTRA = --unsafe -f asciidoc.conf +ASCIIDOC_HTML = xhtml11 MANPAGE_XSL = manpage-normal.xsl XMLTO_EXTRA = INSTALL?=install @@ -55,6 +56,14 @@ RM ?= rm -f DOC_REF = origin/man HTML_REF = origin/html +ifdef USE_ASCIIDOCTOR +ASCIIDOC = asciidoctor +ASCIIDOC_EXTRA = -a compat-mode +ASCIIDOC_EXTRA += -I. -rasciidoctor-extensions +ASCIIDOC_EXTRA += -a mansource="perf" -a manmanual="perf Manual" +ASCIIDOC_HTML = xhtml5 +endif + infodir?=$(prefix)/share/info MAKEINFO=makeinfo INSTALL_INFO=install-info @@ -73,10 +82,12 @@ ifeq ($(_tmp_tool_path),) missing_tools = $(ASCIIDOC) endif +ifndef USE_ASCIIDOCTOR _tmp_tool_path := $(call get-executable,$(XMLTO)) ifeq ($(_tmp_tool_path),) missing_tools += $(XMLTO) endif +endif # # For asciidoc ... @@ -264,9 +275,17 @@ clean: $(MAN_HTML): $(OUTPUT)%.html : %.txt $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \ - $(ASCIIDOC) -b xhtml11 -d manpage -f asciidoc.conf \ + $(ASCIIDOC) -b $(ASCIIDOC_HTML) -d manpage \ + $(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \ + mv $@+ $@ + +ifdef USE_ASCIIDOCTOR +$(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.txt + $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \ + $(ASCIIDOC) -b manpage -d manpage \ $(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \ mv $@+ $@ +endif $(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.xml $(QUIET_XMLTO)$(RM) $@ && \ @@ -274,7 +293,7 @@ $(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.xml $(OUTPUT)%.xml : %.txt $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \ - $(ASCIIDOC) -b docbook -d manpage -f asciidoc.conf \ + $(ASCIIDOC) -b docbook -d manpage \ $(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \ mv $@+ $@ @@ -321,13 +340,13 @@ howto-index.txt: howto-index.sh $(wildcard howto/*.txt) mv $@+ $@ $(patsubst %,%.html,$(ARTICLES)) : %.html : %.txt - $(QUIET_ASCIIDOC)$(ASCIIDOC) -b xhtml11 $*.txt + $(QUIET_ASCIIDOC)$(ASCIIDOC) -b $(ASCIIDOC_HTML) $*.txt WEBDOC_DEST = /pub/software/tools/perf/docs $(patsubst %.txt,%.html,$(wildcard howto/*.txt)): %.html : %.txt $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \ - sed -e '1,/^$$/d' $< | $(ASCIIDOC) -b xhtml11 - >$@+ && \ + sed -e '1,/^$$/d' $< | $(ASCIIDOC) -b $(ASCIIDOC_HTML) - >$@+ && \ mv $@+ $@ # UNIMPLEMENTED diff --git a/tools/perf/Documentation/asciidoctor-extensions.rb b/tools/perf/Documentation/asciidoctor-extensions.rb new file mode 100644 index 0000000..d148fe9 --- /dev/null +++ b/tools/perf/Documentation/asciidoctor-extensions.rb @@ -0,0 +1,29 @@ +require 'asciidoctor' +require 'asciidoctor/extensions' + +module Perf + module Documentation + class LinkPerfProcessor < Asciidoctor::Extensions::InlineMacroProcessor + use_dsl + + named :chrome + + def process(parent, target, attrs) + if parent.document.basebackend? 'html' + %(<a href="#{target}.html">#{target}(#{attrs[1]})</a>\n) + elsif parent.document.basebackend? 'manpage' + "#{target}(#{attrs[1]})" + elsif parent.document.basebackend? 'docbook' + "<citerefentry>\n" \ + "<refentrytitle>#{target}</refentrytitle>" \ + "<manvolnum>#{attrs[1]}</manvolnum>\n" \ + "</citerefentry>\n" + end + end + end + end +end + +Asciidoctor::Extensions.register do + inline_macro Perf::Documentation::LinkPerfProcessor, :linkperf +end diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt index 73c2650..f6de095 100644 --- a/tools/perf/Documentation/perf-buildid-cache.txt +++ b/tools/perf/Documentation/perf-buildid-cache.txt @@ -48,6 +48,9 @@ OPTIONS --purge=:: Purge all cached binaries including older caches which have specified path from the cache. +-P:: +--purge-all:: + Purge all cached binaries. This will flush out entire cache. -M:: --missing=:: List missing build ids in the cache for the specified file. @@ -59,7 +62,9 @@ OPTIONS exactly same build-id, that is replaced by new one. It can be used to update kallsyms and kernel dso to vmlinux in order to support annotation. - +-l:: +--list:: + List all valid binaries from cache. -v:: --verbose:: Be more verbose. diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index 2549c34..11300db 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -124,7 +124,11 @@ The available PMUs and their raw parameters can be listed with For example the raw event "LSD.UOPS" core pmu event above could be specified as - perf stat -e cpu/event=0xa8,umask=0x1,name=LSD.UOPS_CYCLES,cmask=1/ ... + perf stat -e cpu/event=0xa8,umask=0x1,name=LSD.UOPS_CYCLES,cmask=0x1/ ... + + or using extended name syntax + + perf stat -e cpu/event=0xa8,umask=0x1,cmask=0x1,name=\'LSD.UOPS_CYCLES:cmask=0x1\'/ ... PER SOCKET PMUS --------------- diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index cc37b3a..04168da 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -57,6 +57,9 @@ OPTIONS FP mode, "dwarf" for DWARF mode, "lbr" for LBR mode and "no" for disable callgraph. - 'stack-size': user stack size for dwarf mode + - 'name' : User defined event name. Single quotes (') may be used to + escape symbols in the name from parsing by shell and tool + like this: name=\'CPU_CLK_UNHALTED.THREAD:cmask=0x1\'. See the linkperf:perf-list[1] man page for more parameters. diff --git a/tools/perf/Documentation/perf-script-python.txt b/tools/perf/Documentation/perf-script-python.txt index 51ec2d2..0fb9eda 100644 --- a/tools/perf/Documentation/perf-script-python.txt +++ b/tools/perf/Documentation/perf-script-python.txt @@ -610,6 +610,32 @@ Various utility functions for use with perf script: nsecs_str(nsecs) - returns printable string in the form secs.nsecs avg(total, n) - returns average given a sum and a total number of values +SUPPORTED FIELDS +---------------- + +Currently supported fields: + +ev_name, comm, pid, tid, cpu, ip, time, period, phys_addr, addr, +symbol, dso, time_enabled, time_running, values, callchain, +brstack, brstacksym, datasrc, datasrc_decode, iregs, uregs, +weight, transaction, raw_buf, attr. + +Some fields have sub items: + +brstack: + from, to, from_dsoname, to_dsoname, mispred, + predicted, in_tx, abort, cycles. + +brstacksym: + items: from, to, pred, in_tx, abort (converted string) + +For example, +We can use this code to print brstack "from", "to", "cycles". + +if 'brstack' in dict: + for entry in dict['brstack']: + print "from %s, to %s, cycles %s" % (entry["from"], entry["to"], entry["cycles"]) + SEE ALSO -------- linkperf:perf-script[1] diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index e6c3b4e..5dfe102 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -116,6 +116,22 @@ Do not aggregate counts across all monitored CPUs. print counts using a CSV-style output to make it easy to import directly into spreadsheets. Columns are separated by the string specified in SEP. +--table:: Display time for each run (-r option), in a table format, e.g.: + + $ perf stat --null -r 5 --table perf bench sched pipe + + Performance counter stats for 'perf bench sched pipe' (5 runs): + + # Table of individual measurements: + 5.189 (-0.293) # + 5.189 (-0.294) # + 5.186 (-0.296) # + 5.663 (+0.181) ## + 6.186 (+0.703) #### + + # Final result: + 5.483 +- 0.198 seconds time elapsed ( +- 3.62% ) + -G name:: --cgroup name:: monitor only in the container (cgroup) called "name". This option is available only @@ -294,20 +310,38 @@ Users who wants to get the actual value can apply --no-metric-only. EXAMPLES -------- -$ perf stat -- make -j +$ perf stat -- make + + Performance counter stats for 'make': + + 83723.452481 task-clock:u (msec) # 1.004 CPUs utilized + 0 context-switches:u # 0.000 K/sec + 0 cpu-migrations:u # 0.000 K/sec + 3,228,188 page-faults:u # 0.039 M/sec + 229,570,665,834 cycles:u # 2.742 GHz + 313,163,853,778 instructions:u # 1.36 insn per cycle + 69,704,684,856 branches:u # 832.559 M/sec + 2,078,861,393 branch-misses:u # 2.98% of all branches + + 83.409183620 seconds time elapsed + + 74.684747000 seconds user + 8.739217000 seconds sys + +TIMINGS +------- +As displayed in the example above we can display 3 types of timings. +We always display the time the counters were enabled/alive: + + 83.409183620 seconds time elapsed - Performance counter stats for 'make -j': +For workload sessions we also display time the workloads spent in +user/system lands: - 8117.370256 task clock ticks # 11.281 CPU utilization factor - 678 context switches # 0.000 M/sec - 133 CPU migrations # 0.000 M/sec - 235724 pagefaults # 0.029 M/sec - 24821162526 CPU cycles # 3057.784 M/sec - 18687303457 instructions # 2302.138 M/sec - 172158895 cache references # 21.209 M/sec - 27075259 cache misses # 3.335 M/sec + 74.684747000 seconds user + 8.739217000 seconds sys - Wall-clock time elapsed: 719.554352 msecs +Those times are the very same as displayed by the 'time' tool. CSV FORMAT ---------- diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt index d00f0d5..dfb218f 100644 --- a/tools/perf/Documentation/perf.data-file-format.txt +++ b/tools/perf/Documentation/perf.data-file-format.txt @@ -111,8 +111,8 @@ A perf_header_string with the CPU architecture (uname -m) A structure defining the number of CPUs. struct nr_cpus { - uint32_t nr_cpus_online; uint32_t nr_cpus_available; /* CPUs not yet onlined */ + uint32_t nr_cpus_online; }; HEADER_CPUDESC = 8, @@ -153,10 +153,18 @@ struct { HEADER_CPU_TOPOLOGY = 13, String lists defining the core and CPU threads topology. +The string lists are followed by a variable length array +which contains core_id and socket_id of each cpu. +The number of entries can be determined by the size of the +section minus the sizes of both string lists. struct { struct perf_header_string_list cores; /* Variable length */ struct perf_header_string_list threads; /* Variable length */ + struct { + uint32_t core_id; + uint32_t socket_id; + } cpus[nr]; /* Variable length records */ }; Example: diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index ae7dc46..b5ac356 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -885,6 +885,8 @@ endif # Among the variables below, these: # perfexecdir +# perf_include_dir +# perf_examples_dir # template_dir # mandir # infodir @@ -904,6 +906,8 @@ bindir = $(abspath $(prefix)/$(bindir_relative)) mandir = share/man infodir = share/info perfexecdir = libexec/perf-core +perf_include_dir = lib/include/perf +perf_examples_dir = lib/examples/perf sharedir = $(prefix)/share template_dir = share/perf-core/templates STRACE_GROUPS_DIR = share/perf-core/strace/groups @@ -934,6 +938,8 @@ bindir_SQ = $(subst ','\'',$(bindir)) mandir_SQ = $(subst ','\'',$(mandir)) infodir_SQ = $(subst ','\'',$(infodir)) perfexecdir_SQ = $(subst ','\'',$(perfexecdir)) +perf_include_dir_SQ = $(subst ','\'',$(perf_include_dir)) +perf_examples_dir_SQ = $(subst ','\'',$(perf_examples_dir)) template_dir_SQ = $(subst ','\'',$(template_dir)) htmldir_SQ = $(subst ','\'',$(htmldir)) tipdir_SQ = $(subst ','\'',$(tipdir)) @@ -944,14 +950,20 @@ srcdir_SQ = $(subst ','\'',$(srcdir)) ifneq ($(filter /%,$(firstword $(perfexecdir))),) perfexec_instdir = $(perfexecdir) +perf_include_instdir = $(perf_include_dir) +perf_examples_instdir = $(perf_examples_dir) STRACE_GROUPS_INSTDIR = $(STRACE_GROUPS_DIR) tip_instdir = $(tipdir) else perfexec_instdir = $(prefix)/$(perfexecdir) +perf_include_instdir = $(prefix)/$(perf_include_dir) +perf_examples_instdir = $(prefix)/$(perf_examples_dir) STRACE_GROUPS_INSTDIR = $(prefix)/$(STRACE_GROUPS_DIR) tip_instdir = $(prefix)/$(tipdir) endif perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir)) +perf_include_instdir_SQ = $(subst ','\'',$(perf_include_instdir)) +perf_examples_instdir_SQ = $(subst ','\'',$(perf_examples_instdir)) STRACE_GROUPS_INSTDIR_SQ = $(subst ','\'',$(STRACE_GROUPS_INSTDIR)) tip_instdir_SQ = $(subst ','\'',$(tip_instdir)) @@ -999,6 +1011,8 @@ $(call detected_var,ETC_PERFCONFIG_SQ) $(call detected_var,STRACE_GROUPS_DIR_SQ) $(call detected_var,prefix_SQ) $(call detected_var,perfexecdir_SQ) +$(call detected_var,perf_include_dir_SQ) +$(call detected_var,perf_examples_dir_SQ) $(call detected_var,tipdir_SQ) $(call detected_var,srcdir_SQ) $(call detected_var,LIBDIR) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 83e453d..ecc9fc9 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -767,6 +767,16 @@ ifndef NO_JVMTI endif $(call QUIET_INSTALL, libexec) \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' +ifndef NO_LIBBPF + $(call QUIET_INSTALL, lib) \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf' + $(call QUIET_INSTALL, include/bpf) \ + $(INSTALL) include/bpf/*.h '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf' + $(call QUIET_INSTALL, lib) \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf' + $(call QUIET_INSTALL, examples/bpf) \ + $(INSTALL) examples/bpf/*.c '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf' +endif $(call QUIET_INSTALL, perf-archive) \ $(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' $(call QUIET_INSTALL, perf-with-kcore) \ diff --git a/tools/perf/arch/arm/tests/dwarf-unwind.c b/tools/perf/arch/arm/tests/dwarf-unwind.c index 8cb3477..9a0242e 100644 --- a/tools/perf/arch/arm/tests/dwarf-unwind.c +++ b/tools/perf/arch/arm/tests/dwarf-unwind.c @@ -25,7 +25,7 @@ static int sample_ustack(struct perf_sample *sample, sp = (unsigned long) regs[PERF_REG_ARM_SP]; - map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp); + map = map_groups__find(thread->mg, (u64)sp); if (!map) { pr_debug("failed to get stack map\n"); free(buf); diff --git a/tools/perf/arch/arm64/tests/dwarf-unwind.c b/tools/perf/arch/arm64/tests/dwarf-unwind.c index e907f0f..5522ce3 100644 --- a/tools/perf/arch/arm64/tests/dwarf-unwind.c +++ b/tools/perf/arch/arm64/tests/dwarf-unwind.c @@ -25,7 +25,7 @@ static int sample_ustack(struct perf_sample *sample, sp = (unsigned long) regs[PERF_REG_ARM64_SP]; - map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp); + map = map_groups__find(thread->mg, (u64)sp); if (!map) { pr_debug("failed to get stack map\n"); free(buf); diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c index c6f3735..82657c0 100644 --- a/tools/perf/arch/common.c +++ b/tools/perf/arch/common.c @@ -189,7 +189,7 @@ out_error: return -1; } -int perf_env__lookup_objdump(struct perf_env *env) +int perf_env__lookup_objdump(struct perf_env *env, const char **path) { /* * For live mode, env->arch will be NULL and we can use @@ -198,5 +198,5 @@ int perf_env__lookup_objdump(struct perf_env *env) if (env->arch == NULL) return 0; - return perf_env__lookup_binutils_path(env, "objdump", &objdump_path); + return perf_env__lookup_binutils_path(env, "objdump", path); } diff --git a/tools/perf/arch/common.h b/tools/perf/arch/common.h index 2d875baa..2167001 100644 --- a/tools/perf/arch/common.h +++ b/tools/perf/arch/common.h @@ -4,8 +4,6 @@ #include "../util/env.h" -extern const char *objdump_path; - -int perf_env__lookup_objdump(struct perf_env *env); +int perf_env__lookup_objdump(struct perf_env *env, const char **path); #endif /* ARCH_PERF_COMMON_H */ diff --git a/tools/perf/arch/powerpc/tests/dwarf-unwind.c b/tools/perf/arch/powerpc/tests/dwarf-unwind.c index 30cbbd6..5f39efe 100644 --- a/tools/perf/arch/powerpc/tests/dwarf-unwind.c +++ b/tools/perf/arch/powerpc/tests/dwarf-unwind.c @@ -26,7 +26,7 @@ static int sample_ustack(struct perf_sample *sample, sp = (unsigned long) regs[PERF_REG_POWERPC_R1]; - map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp); + map = map_groups__find(thread->mg, (u64)sp); if (!map) { pr_debug("failed to get stack map\n"); free(buf); diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c index 0c370f8..3598b8b 100644 --- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c +++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c @@ -248,8 +248,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain) ip = chain->ips[2]; - thread__find_addr_location(thread, PERF_RECORD_MISC_USER, - MAP__FUNCTION, ip, &al); + thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al); if (al.map) dso = al.map->dso; diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c index 95036c7..7879df3 100644 --- a/tools/perf/arch/x86/tests/dwarf-unwind.c +++ b/tools/perf/arch/x86/tests/dwarf-unwind.c @@ -26,7 +26,7 @@ static int sample_ustack(struct perf_sample *sample, sp = (unsigned long) regs[PERF_REG_X86_SP]; - map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp); + map = map_groups__find(thread->mg, (u64)sp); if (!map) { pr_debug("failed to get stack map\n"); free(buf); diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build index f95e6f4..844b8f3 100644 --- a/tools/perf/arch/x86/util/Build +++ b/tools/perf/arch/x86/util/Build @@ -4,6 +4,8 @@ libperf-y += pmu.o libperf-y += kvm-stat.o libperf-y += perf_regs.o libperf-y += group.o +libperf-y += machine.o +libperf-y += event.o libperf-$(CONFIG_DWARF) += dwarf-regs.o libperf-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.o diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c new file mode 100644 index 0000000..675a021 --- /dev/null +++ b/tools/perf/arch/x86/util/event.c @@ -0,0 +1,76 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/types.h> +#include <linux/string.h> + +#include "../../util/machine.h" +#include "../../util/tool.h" +#include "../../util/map.h" +#include "../../util/util.h" +#include "../../util/debug.h" + +#if defined(__x86_64__) + +int perf_event__synthesize_extra_kmaps(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine) +{ + int rc = 0; + struct map *pos; + struct map_groups *kmaps = &machine->kmaps; + struct maps *maps = &kmaps->maps; + union perf_event *event = zalloc(sizeof(event->mmap) + + machine->id_hdr_size); + + if (!event) { + pr_debug("Not enough memory synthesizing mmap event " + "for extra kernel maps\n"); + return -1; + } + + for (pos = maps__first(maps); pos; pos = map__next(pos)) { + struct kmap *kmap; + size_t size; + + if (!__map__is_extra_kernel_map(pos)) + continue; + + kmap = map__kmap(pos); + + size = sizeof(event->mmap) - sizeof(event->mmap.filename) + + PERF_ALIGN(strlen(kmap->name) + 1, sizeof(u64)) + + machine->id_hdr_size; + + memset(event, 0, size); + + event->mmap.header.type = PERF_RECORD_MMAP; + + /* + * kernel uses 0 for user space maps, see kernel/perf_event.c + * __perf_event_mmap + */ + if (machine__is_host(machine)) + event->header.misc = PERF_RECORD_MISC_KERNEL; + else + event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL; + + event->mmap.header.size = size; + + event->mmap.start = pos->start; + event->mmap.len = pos->end - pos->start; + event->mmap.pgoff = pos->pgoff; + event->mmap.pid = machine->pid; + + strlcpy(event->mmap.filename, kmap->name, PATH_MAX); + + if (perf_tool__process_synth_event(tool, event, machine, + process) != 0) { + rc = -1; + break; + } + } + + free(event); + return rc; +} + +#endif diff --git a/tools/perf/arch/x86/util/machine.c b/tools/perf/arch/x86/util/machine.c new file mode 100644 index 0000000..4520ac5 --- /dev/null +++ b/tools/perf/arch/x86/util/machine.c @@ -0,0 +1,103 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/types.h> +#include <linux/string.h> +#include <stdlib.h> + +#include "../../util/machine.h" +#include "../../util/map.h" +#include "../../util/symbol.h" +#include "../../util/sane_ctype.h" + +#include <symbol/kallsyms.h> + +#if defined(__x86_64__) + +struct extra_kernel_map_info { + int cnt; + int max_cnt; + struct extra_kernel_map *maps; + bool get_entry_trampolines; + u64 entry_trampoline; +}; + +static int add_extra_kernel_map(struct extra_kernel_map_info *mi, u64 start, + u64 end, u64 pgoff, const char *name) +{ + if (mi->cnt >= mi->max_cnt) { + void *buf; + size_t sz; + + mi->max_cnt = mi->max_cnt ? mi->max_cnt * 2 : 32; + sz = sizeof(struct extra_kernel_map) * mi->max_cnt; + buf = realloc(mi->maps, sz); + if (!buf) + return -1; + mi->maps = buf; + } + + mi->maps[mi->cnt].start = start; + mi->maps[mi->cnt].end = end; + mi->maps[mi->cnt].pgoff = pgoff; + strlcpy(mi->maps[mi->cnt].name, name, KMAP_NAME_LEN); + + mi->cnt += 1; + + return 0; +} + +static int find_extra_kernel_maps(void *arg, const char *name, char type, + u64 start) +{ + struct extra_kernel_map_info *mi = arg; + + if (!mi->entry_trampoline && kallsyms2elf_binding(type) == STB_GLOBAL && + !strcmp(name, "_entry_trampoline")) { + mi->entry_trampoline = start; + return 0; + } + + if (is_entry_trampoline(name)) { + u64 end = start + page_size; + + return add_extra_kernel_map(mi, start, end, 0, name); + } + + return 0; +} + +int machine__create_extra_kernel_maps(struct machine *machine, + struct dso *kernel) +{ + struct extra_kernel_map_info mi = { .cnt = 0, }; + char filename[PATH_MAX]; + int ret; + int i; + + machine__get_kallsyms_filename(machine, filename, PATH_MAX); + + if (symbol__restricted_filename(filename, "/proc/kallsyms")) + return 0; + + ret = kallsyms__parse(filename, &mi, find_extra_kernel_maps); + if (ret) + goto out_free; + + if (!mi.entry_trampoline) + goto out_free; + + for (i = 0; i < mi.cnt; i++) { + struct extra_kernel_map *xm = &mi.maps[i]; + + xm->pgoff = mi.entry_trampoline; + ret = machine__create_extra_kernel_map(machine, kernel, xm); + if (ret) + goto out_free; + } + + machine->trampolines_mapped = mi.cnt; +out_free: + free(mi.maps); + return ret; +} + +#endif diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 51709a9..5eb22cc 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -40,11 +40,11 @@ struct perf_annotate { struct perf_tool tool; struct perf_session *session; + struct annotation_options opts; bool use_tui, use_stdio, use_stdio2, use_gtk; - bool full_paths; - bool print_line; bool skip_missing; bool has_br_stack; + bool group_set; const char *sym_hist_filter; const char *cpu_list; DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); @@ -161,12 +161,12 @@ static int hist_iter__branch_callback(struct hist_entry_iter *iter, hist__account_cycles(sample->branch_stack, al, sample, false); bi = he->branch_info; - err = addr_map_symbol__inc_samples(&bi->from, sample, evsel->idx); + err = addr_map_symbol__inc_samples(&bi->from, sample, evsel); if (err) goto out; - err = addr_map_symbol__inc_samples(&bi->to, sample, evsel->idx); + err = addr_map_symbol__inc_samples(&bi->to, sample, evsel); out: return err; @@ -228,7 +228,7 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel, */ if (al->sym != NULL) { rb_erase(&al->sym->rb_node, - &al->map->dso->symbols[al->map->type]); + &al->map->dso->symbols); symbol__delete(al->sym); dso__reset_find_symbol_cache(al->map->dso); } @@ -248,7 +248,7 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel, if (he == NULL) return -ENOMEM; - ret = hist_entry__inc_addr_samples(he, sample, evsel->idx, al->addr); + ret = hist_entry__inc_addr_samples(he, sample, evsel, al->addr); hists__inc_nr_samples(hists, true); return ret; } @@ -288,10 +288,9 @@ static int hist_entry__tty_annotate(struct hist_entry *he, struct perf_annotate *ann) { if (!ann->use_stdio2) - return symbol__tty_annotate(he->ms.sym, he->ms.map, evsel, - ann->print_line, ann->full_paths, 0, 0); - return symbol__tty_annotate2(he->ms.sym, he->ms.map, evsel, - ann->print_line, ann->full_paths); + return symbol__tty_annotate(he->ms.sym, he->ms.map, evsel, &ann->opts); + + return symbol__tty_annotate2(he->ms.sym, he->ms.map, evsel, &ann->opts); } static void hists__find_annotations(struct hists *hists, @@ -342,7 +341,7 @@ find_next: /* skip missing symbols */ nd = rb_next(nd); } else if (use_browser == 1) { - key = hist_entry__tui_annotate(he, evsel, NULL); + key = hist_entry__tui_annotate(he, evsel, NULL, &ann->opts); switch (key) { case -1: @@ -389,8 +388,9 @@ static int __cmd_annotate(struct perf_annotate *ann) goto out; } - if (!objdump_path) { - ret = perf_env__lookup_objdump(&session->header.env); + if (!ann->opts.objdump_path) { + ret = perf_env__lookup_objdump(&session->header.env, + &ann->opts.objdump_path); if (ret) goto out; } @@ -475,6 +475,7 @@ int cmd_annotate(int argc, const char **argv) .ordered_events = true, .ordering_requires_timestamps = true, }, + .opts = annotation__default_options, }; struct perf_data data = { .mode = PERF_DATA_MODE_READ, @@ -502,23 +503,26 @@ int cmd_annotate(int argc, const char **argv) "file", "vmlinux pathname"), OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules, "load module symbols - WARNING: use only with -k and LIVE kernel"), - OPT_BOOLEAN('l', "print-line", &annotate.print_line, + OPT_BOOLEAN('l', "print-line", &annotate.opts.print_lines, "print matching source lines (may be slow)"), - OPT_BOOLEAN('P', "full-paths", &annotate.full_paths, + OPT_BOOLEAN('P', "full-paths", &annotate.opts.full_path, "Don't shorten the displayed pathnames"), OPT_BOOLEAN(0, "skip-missing", &annotate.skip_missing, "Skip symbols that cannot be annotated"), + OPT_BOOLEAN_SET(0, "group", &symbol_conf.event_group, + &annotate.group_set, + "Show event group information together"), OPT_STRING('C', "cpu", &annotate.cpu_list, "cpu", "list of cpus to profile"), OPT_CALLBACK(0, "symfs", NULL, "directory", "Look for files with symbols relative to this directory", symbol__config_symfs), - OPT_BOOLEAN(0, "source", &symbol_conf.annotate_src, + OPT_BOOLEAN(0, "source", &annotate.opts.annotate_src, "Interleave source code with assembly code (default)"), - OPT_BOOLEAN(0, "asm-raw", &symbol_conf.annotate_asm_raw, + OPT_BOOLEAN(0, "asm-raw", &annotate.opts.show_asm_raw, "Display raw encoding of assembly instructions (default)"), - OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style", + OPT_STRING('M', "disassembler-style", &annotate.opts.disassembler_style, "disassembler style", "Specify disassembler style (e.g. -M intel for intel syntax)"), - OPT_STRING(0, "objdump", &objdump_path, "path", + OPT_STRING(0, "objdump", &annotate.opts.objdump_path, "path", "objdump binary to use for disassembly and annotations"), OPT_BOOLEAN(0, "group", &symbol_conf.event_group, "Show event group information together"), @@ -570,6 +574,9 @@ int cmd_annotate(int argc, const char **argv) annotate.has_br_stack = perf_header__has_feat(&annotate.session->header, HEADER_BRANCH_STACK); + if (annotate.group_set) + perf_evlist__force_leader(annotate.session->evlist); + ret = symbol__annotation_init(); if (ret < 0) goto out_delete; diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index 41db2cb..115110a 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -25,6 +25,7 @@ #include "util/session.h" #include "util/symbol.h" #include "util/time-utils.h" +#include "util/probe-file.h" static int build_id_cache__kcore_buildid(const char *proc_dir, char *sbuildid) { @@ -239,6 +240,34 @@ out: return err; } +static int build_id_cache__purge_all(void) +{ + struct strlist *list; + struct str_node *pos; + int err = 0; + char *buf; + + list = build_id_cache__list_all(false); + if (!list) { + pr_debug("Failed to get buildids: -%d\n", errno); + return -EINVAL; + } + + strlist__for_each_entry(pos, list) { + buf = build_id_cache__origname(pos->s); + err = build_id_cache__remove_s(pos->s); + pr_debug("Removing %s (%s): %s\n", buf, pos->s, + err ? "FAIL" : "Ok"); + free(buf); + if (err) + break; + } + strlist__delete(list); + + pr_debug("Purged all: %s\n", err ? "FAIL" : "Ok"); + return err; +} + static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused) { char filename[PATH_MAX]; @@ -297,6 +326,26 @@ static int build_id_cache__update_file(const char *filename, struct nsinfo *nsi) return err; } +static int build_id_cache__show_all(void) +{ + struct strlist *bidlist; + struct str_node *nd; + char *buf; + + bidlist = build_id_cache__list_all(true); + if (!bidlist) { + pr_debug("Failed to get buildids: -%d\n", errno); + return -1; + } + strlist__for_each_entry(nd, bidlist) { + buf = build_id_cache__origname(nd->s); + fprintf(stdout, "%s %s\n", nd->s, buf); + free(buf); + } + strlist__delete(bidlist); + return 0; +} + int cmd_buildid_cache(int argc, const char **argv) { struct strlist *list; @@ -304,6 +353,9 @@ int cmd_buildid_cache(int argc, const char **argv) int ret = 0; int ns_id = -1; bool force = false; + bool list_files = false; + bool opts_flag = false; + bool purge_all = false; char const *add_name_list_str = NULL, *remove_name_list_str = NULL, *purge_name_list_str = NULL, @@ -327,6 +379,8 @@ int cmd_buildid_cache(int argc, const char **argv) "file(s) to remove"), OPT_STRING('p', "purge", &purge_name_list_str, "file list", "file(s) to remove (remove old caches too)"), + OPT_BOOLEAN('P', "purge-all", &purge_all, "purge all cached files"), + OPT_BOOLEAN('l', "list", &list_files, "list all cached files"), OPT_STRING('M', "missing", &missing_filename, "file", "to find missing build ids in the cache"), OPT_BOOLEAN('f', "force", &force, "don't complain, do it"), @@ -344,11 +398,20 @@ int cmd_buildid_cache(int argc, const char **argv) argc = parse_options(argc, argv, buildid_cache_options, buildid_cache_usage, 0); - if (argc || (!add_name_list_str && !kcore_filename && - !remove_name_list_str && !purge_name_list_str && - !missing_filename && !update_name_list_str)) + opts_flag = add_name_list_str || kcore_filename || + remove_name_list_str || purge_name_list_str || + missing_filename || update_name_list_str || + purge_all; + + if (argc || !(list_files || opts_flag)) usage_with_options(buildid_cache_usage, buildid_cache_options); + /* -l is exclusive. It can not be used with other options. */ + if (list_files && opts_flag) { + usage_with_options_msg(buildid_cache_usage, + buildid_cache_options, "-l is exclusive.\n"); + } + if (ns_id > 0) nsi = nsinfo__new(ns_id); @@ -366,6 +429,11 @@ int cmd_buildid_cache(int argc, const char **argv) setup_pager(); + if (list_files) { + ret = build_id_cache__show_all(); + goto out; + } + if (add_name_list_str) { list = strlist__new(add_name_list_str, NULL); if (list) { @@ -420,6 +488,13 @@ int cmd_buildid_cache(int argc, const char **argv) } } + if (purge_all) { + if (build_id_cache__purge_all()) { + pr_warning("Couldn't remove some caches. Error: %s.\n", + str_error_r(errno, sbuf, sizeof(sbuf))); + } + } + if (missing_filename) ret = build_id_cache__fprintf_missing(session, stdout); diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index 2126bfb..307b359 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -1976,7 +1976,7 @@ static int filter_cb(struct hist_entry *he) c2c_he = container_of(he, struct c2c_hist_entry, he); if (c2c.show_src && !he->srcline) - he->srcline = hist_entry__get_srcline(he); + he->srcline = hist_entry__srcline(he); calc_width(c2c_he); diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 40fe919..a3b3463 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -440,9 +440,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool, goto repipe; } - thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->ip, &al); - - if (al.map != NULL) { + if (thread__find_map(thread, sample->cpumode, sample->ip, &al)) { if (!al.map->dso->hit) { al.map->dso->hit = 1; if (map__load(al.map) >= 0) { diff --git a/tools/perf/builtin-kallsyms.c b/tools/perf/builtin-kallsyms.c index bcfb363..90d1a23 100644 --- a/tools/perf/builtin-kallsyms.c +++ b/tools/perf/builtin-kallsyms.c @@ -27,7 +27,7 @@ static int __cmd_kallsyms(int argc, const char **argv) for (i = 0; i < argc; ++i) { struct map *map; - struct symbol *symbol = machine__find_kernel_function_by_name(machine, argv[i], &map); + struct symbol *symbol = machine__find_kernel_symbol_by_name(machine, argv[i], &map); if (symbol == NULL) { printf("%s: not found\n", argv[i]); diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index ae11e4c..54d3f21 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -1004,7 +1004,7 @@ static void __print_slab_result(struct rb_root *root, if (is_caller) { addr = data->call_site; if (!raw_ip) - sym = machine__find_kernel_function(machine, addr, &map); + sym = machine__find_kernel_symbol(machine, addr, &map); } else addr = data->ptr; @@ -1068,7 +1068,7 @@ static void __print_page_alloc_result(struct perf_session *session, int n_lines) char *caller = buf; data = rb_entry(next, struct page_stat, node); - sym = machine__find_kernel_function(machine, data->callsite, &map); + sym = machine__find_kernel_symbol(machine, data->callsite, &map); if (sym) caller = sym->name; else @@ -1110,7 +1110,7 @@ static void __print_page_caller_result(struct perf_session *session, int n_lines char *caller = buf; data = rb_entry(next, struct page_stat, node); - sym = machine__find_kernel_function(machine, data->callsite, &map); + sym = machine__find_kernel_symbol(machine, data->callsite, &map); if (sym) caller = sym->name; else diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 72e2ca0..2b1ef70 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -1438,8 +1438,6 @@ static int kvm_events_live(struct perf_kvm_stat *kvm, goto out; } - symbol_conf.nr_events = kvm->evlist->nr_entries; - if (perf_evlist__create_maps(kvm->evlist, &kvm->opts.target) < 0) usage_with_options(live_usage, live_options); diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index c006592..99de916 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -81,8 +81,7 @@ static int parse_probe_event(const char *str) params.target_used = true; } - if (params.nsi) - pev->nsi = nsinfo__get(params.nsi); + pev->nsi = nsinfo__get(params.nsi); /* Parse a perf-probe command into event */ ret = parse_perf_probe_command(str, pev); diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 0f198f6..cdb5b69 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -71,6 +71,7 @@ struct report { bool group_set; int max_stack; struct perf_read_values show_threads_values; + struct annotation_options annotation_opts; const char *pretty_printing_style; const char *cpu_list; const char *symbol_filter_str; @@ -136,26 +137,25 @@ static int hist_iter__report_callback(struct hist_entry_iter *iter, if (sort__mode == SORT_MODE__BRANCH) { bi = he->branch_info; - err = addr_map_symbol__inc_samples(&bi->from, sample, evsel->idx); + err = addr_map_symbol__inc_samples(&bi->from, sample, evsel); if (err) goto out; - err = addr_map_symbol__inc_samples(&bi->to, sample, evsel->idx); + err = addr_map_symbol__inc_samples(&bi->to, sample, evsel); } else if (rep->mem_mode) { mi = he->mem_info; - err = addr_map_symbol__inc_samples(&mi->daddr, sample, evsel->idx); + err = addr_map_symbol__inc_samples(&mi->daddr, sample, evsel); if (err) goto out; - err = hist_entry__inc_addr_samples(he, sample, evsel->idx, al->addr); + err = hist_entry__inc_addr_samples(he, sample, evsel, al->addr); } else if (symbol_conf.cumulate_callchain) { if (single) - err = hist_entry__inc_addr_samples(he, sample, evsel->idx, - al->addr); + err = hist_entry__inc_addr_samples(he, sample, evsel, al->addr); } else { - err = hist_entry__inc_addr_samples(he, sample, evsel->idx, al->addr); + err = hist_entry__inc_addr_samples(he, sample, evsel, al->addr); } out: @@ -181,11 +181,11 @@ static int hist_iter__branch_callback(struct hist_entry_iter *iter, rep->nonany_branch_mode); bi = he->branch_info; - err = addr_map_symbol__inc_samples(&bi->from, sample, evsel->idx); + err = addr_map_symbol__inc_samples(&bi->from, sample, evsel); if (err) goto out; - err = addr_map_symbol__inc_samples(&bi->to, sample, evsel->idx); + err = addr_map_symbol__inc_samples(&bi->to, sample, evsel); branch_type_count(&rep->brtype_stat, &bi->flags, bi->from.addr, bi->to.addr); @@ -194,20 +194,11 @@ out: return err; } -/* - * Events in data file are not collect in groups, but we still want - * the group display. Set the artificial group and set the leader's - * forced_leader flag to notify the display code. - */ static void setup_forced_leader(struct report *report, struct perf_evlist *evlist) { - if (report->group_set && !evlist->nr_groups) { - struct perf_evsel *leader = perf_evlist__first(evlist); - - perf_evlist__set_leader(evlist); - leader->forced_leader = true; - } + if (report->group_set) + perf_evlist__force_leader(evlist); } static int process_feature_event(struct perf_tool *tool, @@ -523,12 +514,9 @@ static void report__warn_kptr_restrict(const struct report *rep) "As no suitable kallsyms nor vmlinux was found, kernel samples\n" "can't be resolved."; - if (kernel_map) { - const struct dso *kdso = kernel_map->dso; - if (!RB_EMPTY_ROOT(&kdso->symbols[MAP__FUNCTION])) { - desc = "If some relocation was applied (e.g. " - "kexec) symbols may be misresolved."; - } + if (kernel_map && map__has_symbols(kernel_map)) { + desc = "If some relocation was applied (e.g. " + "kexec) symbols may be misresolved."; } ui__warning( @@ -573,7 +561,7 @@ static int report__browse_hists(struct report *rep) ret = perf_evlist__tui_browse_hists(evlist, help, NULL, rep->min_percent, &session->header.env, - true); + true, &rep->annotation_opts); /* * Usually "ret" is the last pressed key, and we only * care if the key notifies us to switch data file. @@ -718,10 +706,7 @@ static size_t maps__fprintf_task(struct maps *maps, int indent, FILE *fp) static int map_groups__fprintf_task(struct map_groups *mg, int indent, FILE *fp) { - int printed = 0, i; - for (i = 0; i < MAP__NR_TYPES; ++i) - printed += maps__fprintf_task(&mg->maps[i], indent, fp); - return printed; + return maps__fprintf_task(&mg->maps, indent, fp); } static void task__print_level(struct task *task, FILE *fp, int level) @@ -961,12 +946,6 @@ parse_percent_limit(const struct option *opt, const char *str, return 0; } -#define CALLCHAIN_DEFAULT_OPT "graph,0.5,caller,function,percent" - -const char report_callchain_help[] = "Display call graph (stack chain/backtrace):\n\n" - CALLCHAIN_REPORT_HELP - "\n\t\t\t\tDefault: " CALLCHAIN_DEFAULT_OPT; - int cmd_report(int argc, const char **argv) { struct perf_session *session; @@ -975,6 +954,10 @@ int cmd_report(int argc, const char **argv) bool has_br_stack = false; int branch_mode = -1; bool branch_call_mode = false; +#define CALLCHAIN_DEFAULT_OPT "graph,0.5,caller,function,percent" + const char report_callchain_help[] = "Display call graph (stack chain/backtrace):\n\n" + CALLCHAIN_REPORT_HELP + "\n\t\t\t\tDefault: " CALLCHAIN_DEFAULT_OPT; char callchain_default_opt[] = CALLCHAIN_DEFAULT_OPT; const char * const report_usage[] = { "perf report [<options>]", @@ -1004,6 +987,7 @@ int cmd_report(int argc, const char **argv) .max_stack = PERF_MAX_STACK_DEPTH, .pretty_printing_style = "normal", .socket_filter = -1, + .annotation_opts = annotation__default_options, }; const struct option options[] = { OPT_STRING('i', "input", &input_name, "file", @@ -1093,11 +1077,11 @@ int cmd_report(int argc, const char **argv) "list of cpus to profile"), OPT_BOOLEAN('I', "show-info", &report.show_full_info, "Display extended information about perf.data file"), - OPT_BOOLEAN(0, "source", &symbol_conf.annotate_src, + OPT_BOOLEAN(0, "source", &report.annotation_opts.annotate_src, "Interleave source code with assembly code (default)"), - OPT_BOOLEAN(0, "asm-raw", &symbol_conf.annotate_asm_raw, + OPT_BOOLEAN(0, "asm-raw", &report.annotation_opts.show_asm_raw, "Display raw encoding of assembly instructions (default)"), - OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style", + OPT_STRING('M', "disassembler-style", &report.annotation_opts.disassembler_style, "disassembler style", "Specify disassembler style (e.g. -M intel for intel syntax)"), OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period, "Show a column with the sum of periods"), @@ -1108,7 +1092,7 @@ int cmd_report(int argc, const char **argv) parse_branch_mode), OPT_BOOLEAN(0, "branch-history", &branch_call_mode, "add last branch records to call history"), - OPT_STRING(0, "objdump", &objdump_path, "path", + OPT_STRING(0, "objdump", &report.annotation_opts.objdump_path, "path", "objdump binary to use for disassembly and annotations"), OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle, "Disable symbol demangling"), diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 4dfdee6..cbf39da 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -2143,7 +2143,7 @@ static void save_task_callchain(struct perf_sched *sched, return; } - if (!symbol_conf.use_callchain || sample->callchain == NULL) + if (!sched->show_callchain || sample->callchain == NULL) return; if (thread__resolve_callchain(thread, cursor, evsel, sample, @@ -2271,10 +2271,11 @@ static struct thread *get_idle_thread(int cpu) return idle_threads[cpu]; } -static void save_idle_callchain(struct idle_thread_runtime *itr, +static void save_idle_callchain(struct perf_sched *sched, + struct idle_thread_runtime *itr, struct perf_sample *sample) { - if (!symbol_conf.use_callchain || sample->callchain == NULL) + if (!sched->show_callchain || sample->callchain == NULL) return; callchain_cursor__copy(&itr->cursor, &callchain_cursor); @@ -2320,7 +2321,7 @@ static struct thread *timehist_get_thread(struct perf_sched *sched, /* copy task callchain when entering to idle */ if (perf_evsel__intval(evsel, sample, "next_pid") == 0) - save_idle_callchain(itr, sample); + save_idle_callchain(sched, itr, sample); } } @@ -2849,7 +2850,7 @@ static void timehist_print_summary(struct perf_sched *sched, printf(" CPU %2d idle entire time window\n", i); } - if (sched->idle_hist && symbol_conf.use_callchain) { + if (sched->idle_hist && sched->show_callchain) { callchain_param.mode = CHAIN_FOLDED; callchain_param.value = CCVAL_PERIOD; @@ -2933,8 +2934,7 @@ static int timehist_check_attr(struct perf_sched *sched, return -1; } - if (sched->show_callchain && - !(evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN)) { + if (sched->show_callchain && !evsel__has_callchain(evsel)) { pr_info("Samples do not have callchains.\n"); sched->show_callchain = 0; symbol_conf.use_callchain = 0; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index e0a9845..b3bf355 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -153,8 +153,8 @@ static struct { .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | - PERF_OUTPUT_SYM | PERF_OUTPUT_DSO | - PERF_OUTPUT_PERIOD, + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD, .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, @@ -165,8 +165,9 @@ static struct { .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | - PERF_OUTPUT_SYM | PERF_OUTPUT_DSO | - PERF_OUTPUT_PERIOD | PERF_OUTPUT_BPF_OUTPUT, + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD | + PERF_OUTPUT_BPF_OUTPUT, .invalid_fields = PERF_OUTPUT_TRACE, }, @@ -185,10 +186,10 @@ static struct { .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | - PERF_OUTPUT_SYM | PERF_OUTPUT_DSO | - PERF_OUTPUT_PERIOD | PERF_OUTPUT_ADDR | - PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT | - PERF_OUTPUT_PHYS_ADDR, + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD | + PERF_OUTPUT_ADDR | PERF_OUTPUT_DATA_SRC | + PERF_OUTPUT_WEIGHT | PERF_OUTPUT_PHYS_ADDR, .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, @@ -199,8 +200,8 @@ static struct { .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | - PERF_OUTPUT_SYM | PERF_OUTPUT_DSO | - PERF_OUTPUT_PERIOD, + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD, .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, @@ -211,8 +212,8 @@ static struct { .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | - PERF_OUTPUT_SYM | PERF_OUTPUT_DSO | - PERF_OUTPUT_SYNTH, + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_SYNTH, .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, @@ -516,7 +517,7 @@ static int perf_session__check_output_opt(struct perf_session *session) evlist__for_each_entry(session->evlist, evsel) { not_pipe = true; - if (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) { + if (evsel__has_callchain(evsel)) { use_callchain = true; break; } @@ -531,21 +532,18 @@ static int perf_session__check_output_opt(struct perf_session *session) */ if (symbol_conf.use_callchain && !output[PERF_TYPE_TRACEPOINT].user_set) { - struct perf_event_attr *attr; - j = PERF_TYPE_TRACEPOINT; evlist__for_each_entry(session->evlist, evsel) { if (evsel->attr.type != j) continue; - attr = &evsel->attr; - - if (attr->sample_type & PERF_SAMPLE_CALLCHAIN) { + if (evsel__has_callchain(evsel)) { output[j].fields |= PERF_OUTPUT_IP; output[j].fields |= PERF_OUTPUT_SYM; + output[j].fields |= PERF_OUTPUT_SYMOFFSET; output[j].fields |= PERF_OUTPUT_DSO; - set_print_ip_opts(attr); + set_print_ip_opts(&evsel->attr); goto out; } } @@ -608,7 +606,7 @@ static int perf_sample__fprintf_start(struct perf_sample *sample, if (PRINT_FIELD(COMM)) { if (latency_format) printed += fprintf(fp, "%8.8s ", thread__comm_str(thread)); - else if (PRINT_FIELD(IP) && symbol_conf.use_callchain) + else if (PRINT_FIELD(IP) && evsel__has_callchain(evsel) && symbol_conf.use_callchain) printed += fprintf(fp, "%s ", thread__comm_str(thread)); else printed += fprintf(fp, "%16s ", thread__comm_str(thread)); @@ -717,8 +715,8 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample, if (PRINT_FIELD(DSO)) { memset(&alf, 0, sizeof(alf)); memset(&alt, 0, sizeof(alt)); - thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf); - thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt); + thread__find_map(thread, sample->cpumode, from, &alf); + thread__find_map(thread, sample->cpumode, to, &alt); } printed += fprintf(fp, " 0x%"PRIx64, from); @@ -764,13 +762,8 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample, from = br->entries[i].from; to = br->entries[i].to; - thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf); - if (alf.map) - alf.sym = map__find_symbol(alf.map, alf.addr); - - thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt); - if (alt.map) - alt.sym = map__find_symbol(alt.map, alt.addr); + thread__find_symbol(thread, sample->cpumode, from, &alf); + thread__find_symbol(thread, sample->cpumode, to, &alt); printed += symbol__fprintf_symname_offs(alf.sym, &alf, fp); if (PRINT_FIELD(DSO)) { @@ -814,12 +807,12 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample, from = br->entries[i].from; to = br->entries[i].to; - thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf); - if (alf.map && !alf.map->dso->adjust_symbols) + if (thread__find_map(thread, sample->cpumode, from, &alf) && + !alf.map->dso->adjust_symbols) from = map__map_ip(alf.map, from); - thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt); - if (alt.map && !alt.map->dso->adjust_symbols) + if (thread__find_map(thread, sample->cpumode, to, &alt) && + !alt.map->dso->adjust_symbols) to = map__map_ip(alt.map, to); printed += fprintf(fp, " 0x%"PRIx64, from); @@ -882,8 +875,7 @@ static int grab_bb(u8 *buffer, u64 start, u64 end, return 0; } - thread__find_addr_map(thread, *cpumode, MAP__FUNCTION, start, &al); - if (!al.map || !al.map->dso) { + if (!thread__find_map(thread, *cpumode, start, &al) || !al.map->dso) { pr_debug("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end); return 0; } @@ -933,10 +925,8 @@ static int ip__fprintf_sym(uint64_t addr, struct thread *thread, memset(&al, 0, sizeof(al)); - thread__find_addr_map(thread, cpumode, MAP__FUNCTION, addr, &al); - if (!al.map) - thread__find_addr_map(thread, cpumode, MAP__VARIABLE, - addr, &al); + thread__find_map(thread, cpumode, addr, &al); + if ((*lastsym) && al.addr >= (*lastsym)->start && al.addr < (*lastsym)->end) return 0; diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index f17dc60..096ccb2 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -80,6 +80,9 @@ #include <sys/stat.h> #include <sys/wait.h> #include <unistd.h> +#include <sys/time.h> +#include <sys/resource.h> +#include <sys/wait.h> #include "sane_ctype.h" @@ -164,6 +167,7 @@ static bool forever = false; static bool metric_only = false; static bool force_metric_only = false; static bool no_merge = false; +static bool walltime_run_table = false; static struct timespec ref_time; static struct cpu_map *aggr_map; static aggr_get_id_t aggr_get_id; @@ -173,6 +177,9 @@ static const char *output_name; static int output_fd; static int print_free_counters_hint; static int print_mixed_hw_group_error; +static u64 *walltime_run; +static bool ru_display = false; +static struct rusage ru_data; struct perf_stat { bool record; @@ -569,7 +576,7 @@ static struct perf_evsel *perf_evsel__reset_weak_group(struct perf_evsel *evsel) return leader; } -static int __run_perf_stat(int argc, const char **argv) +static int __run_perf_stat(int argc, const char **argv, int run_idx) { int interval = stat_config.interval; int times = stat_config.times; @@ -724,7 +731,7 @@ try_again: break; } } - waitpid(child_pid, &status, 0); + wait4(child_pid, &status, 0, &ru_data); if (workload_exec_errno) { const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg)); @@ -752,6 +759,9 @@ try_again: t1 = rdclock(); + if (walltime_run_table) + walltime_run[run_idx] = t1 - t0; + update_stats(&walltime_nsecs_stats, t1 - t0); /* @@ -766,7 +776,7 @@ try_again: return WEXITSTATUS(status); } -static int run_perf_stat(int argc, const char **argv) +static int run_perf_stat(int argc, const char **argv, int run_idx) { int ret; @@ -779,7 +789,7 @@ static int run_perf_stat(int argc, const char **argv) if (sync_run) sync(); - ret = __run_perf_stat(argc, argv); + ret = __run_perf_stat(argc, argv, run_idx); if (ret) return ret; @@ -1764,19 +1774,81 @@ static void print_header(int argc, const char **argv) } } +static int get_precision(double num) +{ + if (num > 1) + return 0; + + return lround(ceil(-log10(num))); +} + +static void print_table(FILE *output, int precision, double avg) +{ + char tmp[64]; + int idx, indent = 0; + + scnprintf(tmp, 64, " %17.*f", precision, avg); + while (tmp[indent] == ' ') + indent++; + + fprintf(output, "%*s# Table of individual measurements:\n", indent, ""); + + for (idx = 0; idx < run_count; idx++) { + double run = (double) walltime_run[idx] / NSEC_PER_SEC; + int h, n = 1 + abs((int) (100.0 * (run - avg)/run) / 5); + + fprintf(output, " %17.*f (%+.*f) ", + precision, run, precision, run - avg); + + for (h = 0; h < n; h++) + fprintf(output, "#"); + + fprintf(output, "\n"); + } + + fprintf(output, "\n%*s# Final result:\n", indent, ""); +} + +static double timeval2double(struct timeval *t) +{ + return t->tv_sec + (double) t->tv_usec/USEC_PER_SEC; +} + static void print_footer(void) { + double avg = avg_stats(&walltime_nsecs_stats) / NSEC_PER_SEC; FILE *output = stat_config.output; int n; if (!null_run) fprintf(output, "\n"); - fprintf(output, " %17.9f seconds time elapsed", - avg_stats(&walltime_nsecs_stats) / NSEC_PER_SEC); - if (run_count > 1) { - fprintf(output, " "); - print_noise_pct(stddev_stats(&walltime_nsecs_stats), - avg_stats(&walltime_nsecs_stats)); + + if (run_count == 1) { + fprintf(output, " %17.9f seconds time elapsed", avg); + + if (ru_display) { + double ru_utime = timeval2double(&ru_data.ru_utime); + double ru_stime = timeval2double(&ru_data.ru_stime); + + fprintf(output, "\n\n"); + fprintf(output, " %17.9f seconds user\n", ru_utime); + fprintf(output, " %17.9f seconds sys\n", ru_stime); + } + } else { + double sd = stddev_stats(&walltime_nsecs_stats) / NSEC_PER_SEC; + /* + * Display at most 2 more significant + * digits than the stddev inaccuracy. + */ + int precision = get_precision(sd) + 2; + + if (walltime_run_table) + print_table(output, precision, avg); + + fprintf(output, " %17.*f +- %.*f seconds time elapsed", + precision, avg, precision, sd); + + print_noise_pct(sd, avg); } fprintf(output, "\n\n"); @@ -1952,6 +2024,8 @@ static const struct option stat_options[] = { "be more verbose (show counter open errors, etc)"), OPT_INTEGER('r', "repeat", &run_count, "repeat command and print average + stddev (max: 100, forever: 0)"), + OPT_BOOLEAN(0, "table", &walltime_run_table, + "display details about each run (only with -r option)"), OPT_BOOLEAN('n', "null", &null_run, "null run - dont start any counters"), OPT_INCR('d', "detailed", &detailed_run, @@ -2843,6 +2917,13 @@ int cmd_stat(int argc, const char **argv) goto out; } + if (walltime_run_table && run_count <= 1) { + fprintf(stderr, "--table is only supported with -r\n"); + parse_options_usage(stat_usage, stat_options, "r", 1); + parse_options_usage(NULL, stat_options, "table", 0); + goto out; + } + if (output_fd < 0) { fprintf(stderr, "argument to --log-fd must be a > 0\n"); parse_options_usage(stat_usage, stat_options, "log-fd", 0); @@ -2888,6 +2969,13 @@ int cmd_stat(int argc, const char **argv) setup_system_wide(argc); + /* + * Display user/system times only for single + * run and when there's specified tracee. + */ + if ((run_count == 1) && target__none(&target)) + ru_display = true; + if (run_count < 0) { pr_err("Run count must be a positive number\n"); parse_options_usage(stat_usage, stat_options, "r", 1); @@ -2897,6 +2985,14 @@ int cmd_stat(int argc, const char **argv) run_count = 1; } + if (walltime_run_table) { + walltime_run = zalloc(run_count * sizeof(walltime_run[0])); + if (!walltime_run) { + pr_err("failed to setup -r option"); + goto out; + } + } + if ((stat_config.aggr_mode == AGGR_THREAD) && !target__has_task(&target)) { if (!target.system_wide || target.cpu_list) { @@ -3012,7 +3108,7 @@ int cmd_stat(int argc, const char **argv) fprintf(output, "[ perf stat: executing run #%d ... ]\n", run_idx + 1); - status = run_perf_stat(argc, argv); + status = run_perf_stat(argc, argv, run_idx); if (forever && status != -1) { print_counters(NULL, argc, argv); perf_stat__reset_stats(); @@ -3060,6 +3156,8 @@ int cmd_stat(int argc, const char **argv) perf_stat__exit_aggr_mode(); perf_evlist__free_stats(evsel_list); out: + free(walltime_run); + if (smi_cost && smi_reset) sysfs__write_int(FREEZE_ON_SMI_PATH, 0); diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index 813698a..a827919 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -533,12 +533,8 @@ static const char *cat_backtrace(union perf_event *event, } tal.filtered = 0; - thread__find_addr_location(al.thread, cpumode, - MAP__FUNCTION, ip, &tal); - - if (tal.sym) - fprintf(f, "..... %016" PRIx64 " %s\n", ip, - tal.sym->name); + if (thread__find_symbol(al.thread, cpumode, ip, &tal)) + fprintf(f, "..... %016" PRIx64 " %s\n", ip, tal.sym->name); else fprintf(f, "..... %016" PRIx64 "\n", ip); } diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index f39bd60..ffdc276 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -123,14 +123,9 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he) } notes = symbol__annotation(sym); - if (notes->src != NULL) { - pthread_mutex_lock(¬es->lock); - goto out_assign; - } - pthread_mutex_lock(¬es->lock); - if (symbol__alloc_hist(sym) < 0) { + if (!symbol__hists(sym, top->evlist->nr_entries)) { pthread_mutex_unlock(¬es->lock); pr_err("Not enough memory for annotating '%s' symbol!\n", sym->name); @@ -138,9 +133,8 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he) return err; } - err = symbol__annotate(sym, map, evsel, 0, NULL); + err = symbol__annotate(sym, map, evsel, 0, &top->annotation_opts, NULL); if (err == 0) { -out_assign: top->sym_filter_entry = he; } else { char msg[BUFSIZ]; @@ -188,7 +182,7 @@ static void ui__warn_map_erange(struct map *map, struct symbol *sym, u64 ip) static void perf_top__record_precise_ip(struct perf_top *top, struct hist_entry *he, struct perf_sample *sample, - int counter, u64 ip) + struct perf_evsel *evsel, u64 ip) { struct annotation *notes; struct symbol *sym = he->ms.sym; @@ -204,7 +198,7 @@ static void perf_top__record_precise_ip(struct perf_top *top, if (pthread_mutex_trylock(¬es->lock)) return; - err = hist_entry__inc_addr_samples(he, sample, counter, ip); + err = hist_entry__inc_addr_samples(he, sample, evsel, ip); pthread_mutex_unlock(¬es->lock); @@ -249,10 +243,9 @@ static void perf_top__show_details(struct perf_top *top) goto out_unlock; printf("Showing %s for %s\n", perf_evsel__name(top->sym_evsel), symbol->name); - printf(" Events Pcnt (>=%d%%)\n", top->sym_pcnt_filter); + printf(" Events Pcnt (>=%d%%)\n", top->annotation_opts.min_pcnt); - more = symbol__annotate_printf(symbol, he->ms.map, top->sym_evsel, - 0, top->sym_pcnt_filter, top->print_entries, 4); + more = symbol__annotate_printf(symbol, he->ms.map, top->sym_evsel, &top->annotation_opts); if (top->evlist->enabled) { if (top->zero) @@ -412,7 +405,7 @@ static void perf_top__print_mapped_keys(struct perf_top *top) fprintf(stdout, "\t[f] profile display filter (count). \t(%d)\n", top->count_filter); - fprintf(stdout, "\t[F] annotate display filter (percent). \t(%d%%)\n", top->sym_pcnt_filter); + fprintf(stdout, "\t[F] annotate display filter (percent). \t(%d%%)\n", top->annotation_opts.min_pcnt); fprintf(stdout, "\t[s] annotate symbol. \t(%s)\n", name?: "NULL"); fprintf(stdout, "\t[S] stop annotation.\n"); @@ -515,7 +508,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c) prompt_integer(&top->count_filter, "Enter display event count filter"); break; case 'F': - prompt_percent(&top->sym_pcnt_filter, + prompt_percent(&top->annotation_opts.min_pcnt, "Enter details display event filter (percent)"); break; case 'K': @@ -613,7 +606,8 @@ static void *display_thread_tui(void *arg) perf_evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent, &top->session->header.env, - !top->record_opts.overwrite); + !top->record_opts.overwrite, + &top->annotation_opts); done = 1; return NULL; @@ -691,7 +685,7 @@ static int hist_iter__top_callback(struct hist_entry_iter *iter, struct perf_evsel *evsel = iter->evsel; if (perf_hpp_list.sym && single) - perf_top__record_precise_ip(top, he, iter->sample, evsel->idx, al->addr); + perf_top__record_precise_ip(top, he, iter->sample, evsel, al->addr); hist__account_cycles(iter->sample->branch_stack, al, iter->sample, !(top->record_opts.branch_stack & PERF_SAMPLE_BRANCH_ANY)); @@ -742,7 +736,7 @@ static void perf_event__process_sample(struct perf_tool *tool, "Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n" "Check /proc/sys/kernel/kptr_restrict.\n\n" "Kernel%s samples will not be resolved.\n", - al.map && !RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION]) ? + al.map && map__has_symbols(al.map) ? " modules" : ""); if (use_browser <= 0) sleep(5); @@ -750,7 +744,7 @@ static void perf_event__process_sample(struct perf_tool *tool, machine->kptr_restrict_warned = true; } - if (al.sym == NULL) { + if (al.sym == NULL && al.map != NULL) { const char *msg = "Kernel samples will not be resolved.\n"; /* * As we do lazy loading of symtabs we only will know if the @@ -764,8 +758,7 @@ static void perf_event__process_sample(struct perf_tool *tool, * invalid --vmlinux ;-) */ if (!machine->kptr_restrict_warned && !top->vmlinux_warned && - al.map == machine->vmlinux_maps[MAP__FUNCTION] && - RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION])) { + __map__is_kernel(al.map) && map__has_symbols(al.map)) { if (symbol_conf.vmlinux_name) { char serr[256]; dso__strerror_load(al.map->dso, serr, sizeof(serr)); @@ -1084,8 +1077,9 @@ static int __cmd_top(struct perf_top *top) if (top->session == NULL) return -1; - if (!objdump_path) { - ret = perf_env__lookup_objdump(&top->session->header.env); + if (!top->annotation_opts.objdump_path) { + ret = perf_env__lookup_objdump(&top->session->header.env, + &top->annotation_opts.objdump_path); if (ret) goto out_delete; } @@ -1265,8 +1259,8 @@ int cmd_top(int argc, const char **argv) .proc_map_timeout = 500, .overwrite = 1, }, - .max_stack = sysctl_perf_event_max_stack, - .sym_pcnt_filter = 5, + .max_stack = sysctl__max_stack(), + .annotation_opts = annotation__default_options, .nr_threads_synthesize = UINT_MAX, }; struct record_opts *opts = &top.record_opts; @@ -1348,15 +1342,15 @@ int cmd_top(int argc, const char **argv) "only consider symbols in these comms"), OPT_STRING(0, "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]", "only consider these symbols"), - OPT_BOOLEAN(0, "source", &symbol_conf.annotate_src, + OPT_BOOLEAN(0, "source", &top.annotation_opts.annotate_src, "Interleave source code with assembly code (default)"), - OPT_BOOLEAN(0, "asm-raw", &symbol_conf.annotate_asm_raw, + OPT_BOOLEAN(0, "asm-raw", &top.annotation_opts.show_asm_raw, "Display raw encoding of assembly instructions (default)"), OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel, "Enable kernel symbol demangling"), - OPT_STRING(0, "objdump", &objdump_path, "path", + OPT_STRING(0, "objdump", &top.annotation_opts.objdump_path, "path", "objdump binary to use for disassembly and annotations"), - OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style", + OPT_STRING('M', "disassembler-style", &top.annotation_opts.disassembler_style, "disassembler style", "Specify disassembler style (e.g. -M intel for intel syntax)"), OPT_STRING('u', "uid", &target->uid_str, "user", "user to profile"), OPT_CALLBACK(0, "percent-limit", &top, "percent", @@ -1392,6 +1386,9 @@ int cmd_top(int argc, const char **argv) if (status < 0) return status; + top.annotation_opts.min_pcnt = 5; + top.annotation_opts.context = 4; + top.evlist = perf_evlist__new(); if (top.evlist == NULL) return -ENOMEM; @@ -1469,8 +1466,6 @@ int cmd_top(int argc, const char **argv) goto out_delete_evlist; } - symbol_conf.nr_events = top.evlist->nr_entries; - if (top.delay_secs < 1) top.delay_secs = 1; diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 3ad17ee..6a748ec 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -2024,8 +2024,7 @@ static int trace__pgfault(struct trace *trace, if (trace->summary_only) goto out; - thread__find_addr_location(thread, sample->cpumode, MAP__FUNCTION, - sample->ip, &al); + thread__find_symbol(thread, sample->cpumode, sample->ip, &al); trace__fprintf_entry_head(trace, thread, 0, true, sample->time, trace->output); @@ -2037,12 +2036,10 @@ static int trace__pgfault(struct trace *trace, fprintf(trace->output, "] => "); - thread__find_addr_location(thread, sample->cpumode, MAP__VARIABLE, - sample->addr, &al); + thread__find_symbol(thread, sample->cpumode, sample->addr, &al); if (!al.map) { - thread__find_addr_location(thread, sample->cpumode, - MAP__FUNCTION, sample->addr, &al); + thread__find_symbol(thread, sample->cpumode, sample->addr, &al); if (al.map) map_type = 'x'; @@ -2494,7 +2491,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv) * to override an explicitely set --max-stack global setting. */ evlist__for_each_entry(evlist, evsel) { - if ((evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) && + if (evsel__has_callchain(evsel) && evsel->attr.sample_max_stack == 0) evsel->attr.sample_max_stack = trace->max_stack; } @@ -3165,7 +3162,7 @@ int cmd_trace(int argc, const char **argv) mmap_pages_user_set = false; if (trace.max_stack == UINT_MAX) { - trace.max_stack = input_name ? PERF_MAX_STACK_DEPTH : sysctl_perf_event_max_stack; + trace.max_stack = input_name ? PERF_MAX_STACK_DEPTH : sysctl__max_stack(); max_stack_user_set = false; } diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 9aff89b..10f333e 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -55,22 +55,26 @@ include/uapi/asm-generic/ioctls.h include/uapi/asm-generic/mman-common.h ' -check () { - file=$1 +check_2 () { + file1=$1 + file2=$2 shift - opts= - while [ -n "$*" ]; do - opts="$opts \"$1\"" - shift - done + shift - cmd="diff $opts ../$file ../../$file > /dev/null" + cmd="diff $* $file1 $file2 > /dev/null" - test -f ../../$file && + test -f $file2 && eval $cmd || echo "Warning: Kernel ABI header at 'tools/$file' differs from latest version at '$file'" >&2 } +check () { + file=$1 + + shift + + check_2 ../$file ../../$file $* +} # Check if we have the kernel headers (tools/perf/../../include), else # we're probably on a detached tarball, so no point in trying to check @@ -83,7 +87,7 @@ for i in $HEADERS; do done # diff with extra ignore lines -check arch/x86/lib/memcpy_64.S -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -check arch/x86/lib/memset_64.S -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -check include/uapi/asm-generic/mman.h -I "^#include <\(uapi/\)*asm-generic/mman-common.h>" -check include/uapi/linux/mman.h -I "^#include <\(uapi/\)*asm/mman.h>" +check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"' +check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"' +check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common.h>"' +check include/uapi/linux/mman.h '-I "^#include <\(uapi/\)*asm/mman.h>"' diff --git a/tools/perf/examples/bpf/5sec.c b/tools/perf/examples/bpf/5sec.c new file mode 100644 index 0000000..b9c20321 --- /dev/null +++ b/tools/perf/examples/bpf/5sec.c @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + Description: + + . Disable strace like syscall tracing (--no-syscalls), or try tracing + just some (-e *sleep). + + . Attach a filter function to a kernel function, returning when it should + be considered, i.e. appear on the output. + + . Run it system wide, so that any sleep of >= 5 seconds and < than 6 + seconds gets caught. + + . Ask for callgraphs using DWARF info, so that userspace can be unwound + + . While this is running, run something like "sleep 5s". + + . If we decide to add tv_nsec as well, then it becomes: + + int probe(hrtimer_nanosleep, rqtp->tv_sec rqtp->tv_nsec)(void *ctx, int err, long sec, long nsec) + + I.e. add where it comes from (rqtp->tv_nsec) and where it will be + accessible in the function body (nsec) + + # perf trace --no-syscalls -e tools/perf/examples/bpf/5sec.c/call-graph=dwarf/ + 0.000 perf_bpf_probe:func:(ffffffff9811b5f0) tv_sec=5 + hrtimer_nanosleep ([kernel.kallsyms]) + __x64_sys_nanosleep ([kernel.kallsyms]) + do_syscall_64 ([kernel.kallsyms]) + entry_SYSCALL_64 ([kernel.kallsyms]) + __GI___nanosleep (/usr/lib64/libc-2.26.so) + rpl_nanosleep (/usr/bin/sleep) + xnanosleep (/usr/bin/sleep) + main (/usr/bin/sleep) + __libc_start_main (/usr/lib64/libc-2.26.so) + _start (/usr/bin/sleep) + ^C# + + Copyright (C) 2018 Red Hat, Inc., Arnaldo Carvalho de Melo <acme@redhat.com> +*/ + +#include <bpf.h> + +int probe(hrtimer_nanosleep, rqtp->tv_sec)(void *ctx, int err, long sec) +{ + return sec == 5; +} + +license(GPL); diff --git a/tools/perf/examples/bpf/empty.c b/tools/perf/examples/bpf/empty.c new file mode 100644 index 0000000..3776d26 --- /dev/null +++ b/tools/perf/examples/bpf/empty.c @@ -0,0 +1,3 @@ +#include <bpf.h> + +license(GPL); diff --git a/tools/perf/include/bpf/bpf.h b/tools/perf/include/bpf/bpf.h new file mode 100644 index 0000000..dd764ad --- /dev/null +++ b/tools/perf/include/bpf/bpf.h @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef _PERF_BPF_H +#define _PERF_BPF_H +#define SEC(NAME) __attribute__((section(NAME), used)) + +#define probe(function, vars) \ + SEC(#function "=" #function " " #vars) function + +#define license(name) \ +char _license[] SEC("license") = #name; \ +int _version SEC("version") = LINUX_VERSION_CODE; + +#endif /* _PERF_BPF_H */ diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 20a08cb..a11cb00 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -12,7 +12,6 @@ #include "util/env.h" #include <subcmd/exec-cmd.h> #include "util/config.h" -#include "util/quote.h" #include <subcmd/run-command.h> #include "util/parse-events.h" #include <subcmd/parse-options.h> @@ -238,7 +237,7 @@ static int handle_options(const char ***argv, int *argc, int *envchanged) (*argc)--; } else if (strstarts(cmd, CMD_DEBUGFS_DIR)) { tracing_path_set(cmd + strlen(CMD_DEBUGFS_DIR)); - fprintf(stderr, "dir: %s\n", tracing_path); + fprintf(stderr, "dir: %s\n", tracing_path_mount()); if (envchanged) *envchanged = 1; } else if (!strcmp(cmd, "--list-cmds")) { @@ -421,22 +420,11 @@ void pthread__unblock_sigwinch(void) pthread_sigmask(SIG_UNBLOCK, &set, NULL); } -#ifdef _SC_LEVEL1_DCACHE_LINESIZE -#define cache_line_size(cacheline_sizep) *cacheline_sizep = sysconf(_SC_LEVEL1_DCACHE_LINESIZE) -#else -static void cache_line_size(int *cacheline_sizep) -{ - if (sysfs__read_int("devices/system/cpu/cpu0/cache/index0/coherency_line_size", cacheline_sizep)) - pr_debug("cannot determine cache line size"); -} -#endif - int main(int argc, const char **argv) { int err; const char *cmd; char sbuf[STRERR_BUFSIZE]; - int value; /* libsubcmd init */ exec_cmd_init("perf", PREFIX, PERF_EXEC_PATH, EXEC_PATH_ENVIRONMENT); @@ -444,13 +432,6 @@ int main(int argc, const char **argv) /* The page_size is placed in util object. */ page_size = sysconf(_SC_PAGE_SIZE); - cache_line_size(&cacheline_size); - - if (sysctl__read_int("kernel/perf_event_max_stack", &value) == 0) - sysctl_perf_event_max_stack = value; - - if (sysctl__read_int("kernel/perf_event_max_contexts_per_stack", &value) == 0) - sysctl_perf_event_max_contexts_per_stack = value; cmd = extract_argv0_path(argv[0]); if (!cmd) @@ -458,15 +439,11 @@ int main(int argc, const char **argv) srandom(time(NULL)); - perf_config__init(); err = perf_config(perf_default_config, NULL); if (err) return err; set_buildid_dir(NULL); - /* get debugfs/tracefs mount point from /proc/mounts */ - tracing_path_mount(); - /* * "perf-xxxx" is the same as "perf xxxx", but we obviously: * diff --git a/tools/perf/scripts/python/bin/powerpc-hcalls-record b/tools/perf/scripts/python/bin/powerpc-hcalls-record new file mode 100644 index 0000000..b7402aa --- /dev/null +++ b/tools/perf/scripts/python/bin/powerpc-hcalls-record @@ -0,0 +1,2 @@ +#!/bin/bash +perf record -e "{powerpc:hcall_entry,powerpc:hcall_exit}" $@ diff --git a/tools/perf/scripts/python/bin/powerpc-hcalls-report b/tools/perf/scripts/python/bin/powerpc-hcalls-report new file mode 100644 index 0000000..dd32ad7 --- /dev/null +++ b/tools/perf/scripts/python/bin/powerpc-hcalls-report @@ -0,0 +1,2 @@ +#!/bin/bash +perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/powerpc-hcalls.py diff --git a/tools/perf/scripts/python/powerpc-hcalls.py b/tools/perf/scripts/python/powerpc-hcalls.py new file mode 100644 index 0000000..00e0e74 --- /dev/null +++ b/tools/perf/scripts/python/powerpc-hcalls.py @@ -0,0 +1,200 @@ +# SPDX-License-Identifier: GPL-2.0+ +# +# Copyright (C) 2018 Ravi Bangoria, IBM Corporation +# +# Hypervisor call statisics + +import os +import sys + +sys.path.append(os.environ['PERF_EXEC_PATH'] + \ + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') + +from perf_trace_context import * +from Core import * +from Util import * + +# output: { +# opcode: { +# 'min': minimum time nsec +# 'max': maximum time nsec +# 'time': average time nsec +# 'cnt': counter +# } ... +# } +output = {} + +# d_enter: { +# cpu: { +# opcode: nsec +# } ... +# } +d_enter = {} + +hcall_table = { + 4: 'H_REMOVE', + 8: 'H_ENTER', + 12: 'H_READ', + 16: 'H_CLEAR_MOD', + 20: 'H_CLEAR_REF', + 24: 'H_PROTECT', + 28: 'H_GET_TCE', + 32: 'H_PUT_TCE', + 36: 'H_SET_SPRG0', + 40: 'H_SET_DABR', + 44: 'H_PAGE_INIT', + 48: 'H_SET_ASR', + 52: 'H_ASR_ON', + 56: 'H_ASR_OFF', + 60: 'H_LOGICAL_CI_LOAD', + 64: 'H_LOGICAL_CI_STORE', + 68: 'H_LOGICAL_CACHE_LOAD', + 72: 'H_LOGICAL_CACHE_STORE', + 76: 'H_LOGICAL_ICBI', + 80: 'H_LOGICAL_DCBF', + 84: 'H_GET_TERM_CHAR', + 88: 'H_PUT_TERM_CHAR', + 92: 'H_REAL_TO_LOGICAL', + 96: 'H_HYPERVISOR_DATA', + 100: 'H_EOI', + 104: 'H_CPPR', + 108: 'H_IPI', + 112: 'H_IPOLL', + 116: 'H_XIRR', + 120: 'H_MIGRATE_DMA', + 124: 'H_PERFMON', + 220: 'H_REGISTER_VPA', + 224: 'H_CEDE', + 228: 'H_CONFER', + 232: 'H_PROD', + 236: 'H_GET_PPP', + 240: 'H_SET_PPP', + 244: 'H_PURR', + 248: 'H_PIC', + 252: 'H_REG_CRQ', + 256: 'H_FREE_CRQ', + 260: 'H_VIO_SIGNAL', + 264: 'H_SEND_CRQ', + 272: 'H_COPY_RDMA', + 276: 'H_REGISTER_LOGICAL_LAN', + 280: 'H_FREE_LOGICAL_LAN', + 284: 'H_ADD_LOGICAL_LAN_BUFFER', + 288: 'H_SEND_LOGICAL_LAN', + 292: 'H_BULK_REMOVE', + 304: 'H_MULTICAST_CTRL', + 308: 'H_SET_XDABR', + 312: 'H_STUFF_TCE', + 316: 'H_PUT_TCE_INDIRECT', + 332: 'H_CHANGE_LOGICAL_LAN_MAC', + 336: 'H_VTERM_PARTNER_INFO', + 340: 'H_REGISTER_VTERM', + 344: 'H_FREE_VTERM', + 348: 'H_RESET_EVENTS', + 352: 'H_ALLOC_RESOURCE', + 356: 'H_FREE_RESOURCE', + 360: 'H_MODIFY_QP', + 364: 'H_QUERY_QP', + 368: 'H_REREGISTER_PMR', + 372: 'H_REGISTER_SMR', + 376: 'H_QUERY_MR', + 380: 'H_QUERY_MW', + 384: 'H_QUERY_HCA', + 388: 'H_QUERY_PORT', + 392: 'H_MODIFY_PORT', + 396: 'H_DEFINE_AQP1', + 400: 'H_GET_TRACE_BUFFER', + 404: 'H_DEFINE_AQP0', + 408: 'H_RESIZE_MR', + 412: 'H_ATTACH_MCQP', + 416: 'H_DETACH_MCQP', + 420: 'H_CREATE_RPT', + 424: 'H_REMOVE_RPT', + 428: 'H_REGISTER_RPAGES', + 432: 'H_DISABLE_AND_GETC', + 436: 'H_ERROR_DATA', + 440: 'H_GET_HCA_INFO', + 444: 'H_GET_PERF_COUNT', + 448: 'H_MANAGE_TRACE', + 468: 'H_FREE_LOGICAL_LAN_BUFFER', + 472: 'H_POLL_PENDING', + 484: 'H_QUERY_INT_STATE', + 580: 'H_ILLAN_ATTRIBUTES', + 592: 'H_MODIFY_HEA_QP', + 596: 'H_QUERY_HEA_QP', + 600: 'H_QUERY_HEA', + 604: 'H_QUERY_HEA_PORT', + 608: 'H_MODIFY_HEA_PORT', + 612: 'H_REG_BCMC', + 616: 'H_DEREG_BCMC', + 620: 'H_REGISTER_HEA_RPAGES', + 624: 'H_DISABLE_AND_GET_HEA', + 628: 'H_GET_HEA_INFO', + 632: 'H_ALLOC_HEA_RESOURCE', + 644: 'H_ADD_CONN', + 648: 'H_DEL_CONN', + 664: 'H_JOIN', + 676: 'H_VASI_STATE', + 688: 'H_ENABLE_CRQ', + 696: 'H_GET_EM_PARMS', + 720: 'H_SET_MPP', + 724: 'H_GET_MPP', + 748: 'H_HOME_NODE_ASSOCIATIVITY', + 756: 'H_BEST_ENERGY', + 764: 'H_XIRR_X', + 768: 'H_RANDOM', + 772: 'H_COP', + 788: 'H_GET_MPP_X', + 796: 'H_SET_MODE', + 61440: 'H_RTAS', +} + +def hcall_table_lookup(opcode): + if (hcall_table.has_key(opcode)): + return hcall_table[opcode] + else: + return opcode + +print_ptrn = '%-28s%10s%10s%10s%10s' + +def trace_end(): + print print_ptrn % ('hcall', 'count', 'min(ns)', 'max(ns)', 'avg(ns)') + print '-' * 68 + for opcode in output: + h_name = hcall_table_lookup(opcode) + time = output[opcode]['time'] + cnt = output[opcode]['cnt'] + min_t = output[opcode]['min'] + max_t = output[opcode]['max'] + + print print_ptrn % (h_name, cnt, min_t, max_t, time/cnt) + +def powerpc__hcall_exit(name, context, cpu, sec, nsec, pid, comm, callchain, + opcode, retval): + if (d_enter.has_key(cpu) and d_enter[cpu].has_key(opcode)): + diff = nsecs(sec, nsec) - d_enter[cpu][opcode] + + if (output.has_key(opcode)): + output[opcode]['time'] += diff + output[opcode]['cnt'] += 1 + if (output[opcode]['min'] > diff): + output[opcode]['min'] = diff + if (output[opcode]['max'] < diff): + output[opcode]['max'] = diff + else: + output[opcode] = { + 'time': diff, + 'cnt': 1, + 'min': diff, + 'max': diff, + } + + del d_enter[cpu][opcode] +# else: +# print "Can't find matching hcall_enter event. Ignoring sample" + +def powerpc__hcall_entry(event_name, context, cpu, sec, nsec, pid, comm, + callchain, opcode): + if (d_enter.has_key(cpu)): + d_enter[cpu][opcode] = nsecs(sec, nsec) + else: + d_enter[cpu] = {opcode: nsecs(sec, nsec)} diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index cac8f88..2bde505 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -654,6 +654,15 @@ static int perf_test__list(int argc, const char **argv) continue; pr_info("%2d: %s\n", i, t->desc); + + if (t->subtest.get_nr) { + int subn = t->subtest.get_nr(); + int subi; + + for (subi = 0; subi < subn; subi++) + pr_info("%2d:%1d: %s\n", i, subi + 1, + t->subtest.get_desc(subi)); + } } perf_test__list_shell(argc, argv, i); diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 9993635..4892bd2 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -236,14 +236,13 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr); - thread__find_addr_map(thread, cpumode, MAP__FUNCTION, addr, &al); - if (!al.map || !al.map->dso) { + if (!thread__find_map(thread, cpumode, addr, &al) || !al.map->dso) { if (cpumode == PERF_RECORD_MISC_HYPERVISOR) { pr_debug("Hypervisor address can not be resolved - skipping\n"); return 0; } - pr_debug("thread__find_addr_map failed\n"); + pr_debug("thread__find_map failed\n"); return -1; } @@ -561,6 +560,7 @@ static int do_test_code_reading(bool try_kcore) pid = getpid(); machine = machine__new_host(); + machine->env = &perf_env; ret = machine__create_kernel_maps(machine); if (ret < 0) { diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c index f7c5b61..b889a28f 100644 --- a/tools/perf/tests/hists_common.c +++ b/tools/perf/tests/hists_common.c @@ -131,20 +131,20 @@ struct machine *setup_fake_machine(struct machines *machines) goto out; /* emulate dso__load() */ - dso__set_loaded(dso, MAP__FUNCTION); + dso__set_loaded(dso); for (k = 0; k < fake_symbols[i].nr_syms; k++) { struct symbol *sym; struct fake_sym *fsym = &fake_symbols[i].syms[k]; sym = symbol__new(fsym->start, fsym->length, - STB_GLOBAL, fsym->name); + STB_GLOBAL, STT_FUNC, fsym->name); if (sym == NULL) { dso__put(dso); goto out; } - symbols__insert(&dso->symbols[MAP__FUNCTION], sym); + symbols__insert(&dso->symbols, sym); } dso__put(dso); diff --git a/tools/perf/tests/kmod-path.c b/tools/perf/tests/kmod-path.c index 8e57d46..148dd31 100644 --- a/tools/perf/tests/kmod-path.c +++ b/tools/perf/tests/kmod-path.c @@ -127,6 +127,22 @@ int test__kmod_path__parse(struct test *t __maybe_unused, int subtest __maybe_un M("[vdso]", PERF_RECORD_MISC_KERNEL, false); M("[vdso]", PERF_RECORD_MISC_USER, false); + T("[vdso32]", true , true , false, false, "[vdso32]", NULL); + T("[vdso32]", false , true , false, false, NULL , NULL); + T("[vdso32]", true , false , false, false, "[vdso32]", NULL); + T("[vdso32]", false , false , false, false, NULL , NULL); + M("[vdso32]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false); + M("[vdso32]", PERF_RECORD_MISC_KERNEL, false); + M("[vdso32]", PERF_RECORD_MISC_USER, false); + + T("[vdsox32]", true , true , false, false, "[vdsox32]", NULL); + T("[vdsox32]", false , true , false, false, NULL , NULL); + T("[vdsox32]", true , false , false, false, "[vdsox32]", NULL); + T("[vdsox32]", false , false , false, false, NULL , NULL); + M("[vdsox32]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false); + M("[vdsox32]", PERF_RECORD_MISC_KERNEL, false); + M("[vdsox32]", PERF_RECORD_MISC_USER, false); + /* path alloc_name alloc_ext kmod comp name ext */ T("[vsyscall]", true , true , false, false, "[vsyscall]", NULL); T("[vsyscall]", false , true , false, false, NULL , NULL); diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c index 868d82b5..b1af249 100644 --- a/tools/perf/tests/mmap-thread-lookup.c +++ b/tools/perf/tests/mmap-thread-lookup.c @@ -188,9 +188,8 @@ static int mmap_events(synth_cb synth) pr_debug("looking for map %p\n", td->map); - thread__find_addr_map(thread, - PERF_RECORD_MISC_USER, MAP__FUNCTION, - (unsigned long) (td->map + 1), &al); + thread__find_map(thread, PERF_RECORD_MISC_USER, + (unsigned long) (td->map + 1), &al); thread__put(thread); @@ -218,7 +217,7 @@ static int mmap_events(synth_cb synth) * perf_event__synthesize_threads (global) * * We test we can find all memory maps via: - * thread__find_addr_map + * thread__find_map * * by using all thread objects. */ diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 18b0644..7d40770 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -499,7 +499,7 @@ static int test__checkevent_pmu_partial_time_callgraph(struct perf_evlist *evlis * while this test executes only parse events method. */ TEST_ASSERT_VAL("wrong period", 0 == evsel->attr.sample_period); - TEST_ASSERT_VAL("wrong callgraph", !(PERF_SAMPLE_CALLCHAIN & evsel->attr.sample_type)); + TEST_ASSERT_VAL("wrong callgraph", !evsel__has_callchain(evsel)); TEST_ASSERT_VAL("wrong time", !(PERF_SAMPLE_TIME & evsel->attr.sample_type)); /* cpu/config=2,call-graph=no,time=0,period=2000/ */ @@ -512,7 +512,7 @@ static int test__checkevent_pmu_partial_time_callgraph(struct perf_evlist *evlis * while this test executes only parse events method. */ TEST_ASSERT_VAL("wrong period", 0 == evsel->attr.sample_period); - TEST_ASSERT_VAL("wrong callgraph", !(PERF_SAMPLE_CALLCHAIN & evsel->attr.sample_type)); + TEST_ASSERT_VAL("wrong callgraph", !evsel__has_callchain(evsel)); TEST_ASSERT_VAL("wrong time", !(PERF_SAMPLE_TIME & evsel->attr.sample_type)); return 0; @@ -1309,18 +1309,26 @@ static int test__checkevent_config_cache(struct perf_evlist *evlist) return 0; } +static int test__intel_pt(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__first(evlist); + + TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "intel_pt//u") == 0); + return 0; +} + static int count_tracepoints(void) { struct dirent *events_ent; DIR *events_dir; int cnt = 0; - events_dir = opendir(tracing_events_path); + events_dir = tracing_events__opendir(); TEST_ASSERT_VAL("Can't open events dir", events_dir); while ((events_ent = readdir(events_dir))) { - char sys_path[PATH_MAX]; + char *sys_path; struct dirent *sys_ent; DIR *sys_dir; @@ -1331,8 +1339,8 @@ static int count_tracepoints(void) || !strcmp(events_ent->d_name, "header_page")) continue; - scnprintf(sys_path, PATH_MAX, "%s/%s", - tracing_events_path, events_ent->d_name); + sys_path = get_events_file(events_ent->d_name); + TEST_ASSERT_VAL("Can't get sys path", sys_path); sys_dir = opendir(sys_path); TEST_ASSERT_VAL("Can't open sys dir", sys_dir); @@ -1348,6 +1356,7 @@ static int count_tracepoints(void) } closedir(sys_dir); + put_events_file(sys_path); } closedir(events_dir); @@ -1637,6 +1646,11 @@ static struct evlist_test test__events[] = { .check = test__checkevent_config_cache, .id = 51, }, + { + .name = "intel_pt//u", + .check = test__intel_pt, + .id = 52, + }, }; static struct evlist_test test__events_pmu[] = { diff --git a/tools/perf/tests/python-use.c b/tools/perf/tests/python-use.c index 5d2df65..40ab721 100644 --- a/tools/perf/tests/python-use.c +++ b/tools/perf/tests/python-use.c @@ -7,8 +7,7 @@ #include <stdlib.h> #include <linux/compiler.h> #include "tests.h" - -extern int verbose; +#include "util/debug.h" int test__python_use(struct test *test __maybe_unused, int subtest __maybe_unused) { diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh index ee86473..2630570 100755 --- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh +++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh @@ -11,23 +11,23 @@ . $(dirname $0)/lib/probe.sh libc=$(grep -w libc /proc/self/maps | head -1 | sed -r 's/.*[[:space:]](\/.*)/\1/g') -nm -g $libc 2>/dev/null | fgrep -q inet_pton || exit 254 +nm -Dg $libc 2>/dev/null | fgrep -q inet_pton || exit 254 trace_libc_inet_pton_backtrace() { idx=0 expected[0]="ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)" - expected[1]=".*inet_pton[[:space:]]\($libc|inlined\)$" + expected[1]=".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" case "$(uname -m)" in s390x) eventattr='call-graph=dwarf,max-stack=4' - expected[2]="gaih_inet.*[[:space:]]\($libc|inlined\)$" - expected[3]="(__GI_)?getaddrinfo[[:space:]]\($libc|inlined\)$" - expected[4]="main[[:space:]]\(.*/bin/ping.*\)$" + expected[2]="gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" + expected[3]="(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" + expected[4]="main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" ;; *) eventattr='max-stack=3' - expected[2]="getaddrinfo[[:space:]]\($libc\)$" - expected[3]=".*\(.*/bin/ping.*\)$" + expected[2]="getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" + expected[3]=".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" ;; esac diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c index 17cb1bb..40e30a2 100644 --- a/tools/perf/tests/topology.c +++ b/tools/perf/tests/topology.c @@ -70,6 +70,27 @@ static int check_cpu_topology(char *path, struct cpu_map *map) session = perf_session__new(&data, false, NULL); TEST_ASSERT_VAL("can't get session", session); + /* On platforms with large numbers of CPUs process_cpu_topology() + * might issue an error while reading the perf.data file section + * HEADER_CPU_TOPOLOGY and the cpu_topology_map pointed to by member + * cpu is a NULL pointer. + * Example: On s390 + * CPU 0 is on core_id 0 and physical_package_id 6 + * CPU 1 is on core_id 1 and physical_package_id 3 + * + * Core_id and physical_package_id are platform and architecture + * dependend and might have higher numbers than the CPU id. + * This actually depends on the configuration. + * + * In this case process_cpu_topology() prints error message: + * "socket_id number is too big. You may need to upgrade the + * perf tool." + * + * This is the reason why this test might be skipped. + */ + if (!session->header.env.cpu) + return TEST_SKIP; + for (i = 0; i < session->header.env.nr_cpus_avail; i++) { if (!cpu_map__has(map, i)) continue; @@ -95,7 +116,7 @@ int test__session_topology(struct test *test __maybe_unused, int subtest __maybe { char path[PATH_MAX]; struct cpu_map *map; - int ret = -1; + int ret = TEST_FAIL; TEST_ASSERT_VAL("can't get templ file", !get_temp(path)); @@ -110,12 +131,9 @@ int test__session_topology(struct test *test __maybe_unused, int subtest __maybe goto free_path; } - if (check_cpu_topology(path, map)) - goto free_map; - ret = 0; - -free_map: + ret = check_cpu_topology(path, map); cpu_map__put(map); + free_path: unlink(path); return ret; diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index 1e5adb6..7691980 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -19,8 +19,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest struct symbol *sym; struct map *kallsyms_map, *vmlinux_map, *map; struct machine kallsyms, vmlinux; - enum map_type type = MAP__FUNCTION; - struct maps *maps = &vmlinux.kmaps.maps[type]; + struct maps *maps = machine__kernel_maps(&vmlinux); u64 mem_start, mem_end; bool header_printed; @@ -56,7 +55,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest * be compacted against the list of modules found in the "vmlinux" * code and with the one got from /proc/modules from the "kallsyms" code. */ - if (machine__load_kallsyms(&kallsyms, "/proc/kallsyms", type) <= 0) { + if (machine__load_kallsyms(&kallsyms, "/proc/kallsyms") <= 0) { pr_debug("dso__load_kallsyms "); goto out; } @@ -94,7 +93,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest * maps__reloc_vmlinux will notice and set proper ->[un]map_ip routines * to fixup the symbols. */ - if (machine__load_vmlinux_path(&vmlinux, type) <= 0) { + if (machine__load_vmlinux_path(&vmlinux) <= 0) { pr_debug("Couldn't find a vmlinux that matches the kernel running on this machine, skipping test\n"); err = TEST_SKIP; goto out; @@ -108,7 +107,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest * in the kallsyms dso. For the ones that are in both, check its names and * end addresses too. */ - for (nd = rb_first(&vmlinux_map->dso->symbols[type]); nd; nd = rb_next(nd)) { + map__for_each_symbol(vmlinux_map, sym, nd) { struct symbol *pair, *first_pair; sym = rb_entry(nd, struct symbol, rb_node); @@ -119,8 +118,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest mem_start = vmlinux_map->unmap_ip(vmlinux_map, sym->start); mem_end = vmlinux_map->unmap_ip(vmlinux_map, sym->end); - first_pair = machine__find_kernel_symbol(&kallsyms, type, - mem_start, NULL); + first_pair = machine__find_kernel_symbol(&kallsyms, mem_start, NULL); pair = first_pair; if (pair && UM(pair->start) == mem_start) { @@ -149,7 +147,7 @@ next_pair: */ continue; } else { - pair = machine__find_kernel_symbol_by_name(&kallsyms, type, sym->name, NULL); + pair = machine__find_kernel_symbol_by_name(&kallsyms, sym->name, NULL); if (pair) { if (UM(pair->start) == mem_start) goto next_pair; @@ -183,7 +181,7 @@ next_pair: * so use the short name, less descriptive but the same ("[kernel]" in * both cases. */ - pair = map_groups__find_by_name(&kallsyms.kmaps, type, + pair = map_groups__find_by_name(&kallsyms.kmaps, (map->dso->kernel ? map->dso->short_name : map->dso->name)); @@ -206,7 +204,7 @@ next_pair: mem_start = vmlinux_map->unmap_ip(vmlinux_map, map->start); mem_end = vmlinux_map->unmap_ip(vmlinux_map, map->end); - pair = map_groups__find(&kallsyms.kmaps, type, mem_start); + pair = map_groups__find(&kallsyms.kmaps, mem_start); if (pair == NULL || pair->priv) continue; @@ -228,7 +226,7 @@ next_pair: header_printed = false; - maps = &kallsyms.kmaps.maps[type]; + maps = machine__kernel_maps(&kallsyms); for (map = maps__first(maps); map; map = map__next(map)) { if (!map->priv) { diff --git a/tools/perf/trace/beauty/prctl_option.sh b/tools/perf/trace/beauty/prctl_option.sh index 0be4138..f247221 100755 --- a/tools/perf/trace/beauty/prctl_option.sh +++ b/tools/perf/trace/beauty/prctl_option.sh @@ -1,6 +1,6 @@ #!/bin/sh -header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ printf "static const char *prctl_options[] = {\n" regex='^#define[[:space:]]+PR_([GS]ET\w+)[[:space:]]*([[:xdigit:]]+).*' diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index 3781d74..3b4f1c1 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -29,6 +29,7 @@ struct annotate_browser { struct rb_node *curr_hot; struct annotation_line *selection; struct arch *arch; + struct annotation_options *opts; bool searching_backwards; char search_bf[128]; }; @@ -410,7 +411,7 @@ static bool annotate_browser__callq(struct annotate_browser *browser, notes = symbol__annotation(dl->ops.target.sym); pthread_mutex_lock(¬es->lock); - if (notes->src == NULL && symbol__alloc_hist(dl->ops.target.sym) < 0) { + if (!symbol__hists(dl->ops.target.sym, evsel->evlist->nr_entries)) { pthread_mutex_unlock(¬es->lock); ui__warning("Not enough memory for annotating '%s' symbol!\n", dl->ops.target.sym->name); @@ -418,7 +419,7 @@ static bool annotate_browser__callq(struct annotate_browser *browser, } pthread_mutex_unlock(¬es->lock); - symbol__tui_annotate(dl->ops.target.sym, ms->map, evsel, hbt); + symbol__tui_annotate(dl->ops.target.sym, ms->map, evsel, hbt, browser->opts); sym_title(ms->sym, ms->map, title, sizeof(title)); ui_browser__show_title(&browser->b, title); return true; @@ -695,6 +696,7 @@ static int annotate_browser__run(struct annotate_browser *browser, "O Bump offset level (jump targets -> +call -> all -> cycle thru)\n" "s Toggle source code view\n" "t Circulate percent, total period, samples view\n" + "c Show min/max cycle\n" "/ Search string\n" "k Toggle line numbers\n" "P Print to [symbol_name].annotation file.\n" @@ -791,6 +793,13 @@ show_sup_ins: notes->options->show_total_period = true; annotation__update_column_widths(notes); continue; + case 'c': + if (notes->options->show_minmax_cycle) + notes->options->show_minmax_cycle = false; + else + notes->options->show_minmax_cycle = true; + annotation__update_column_widths(notes); + continue; case K_LEFT: case K_ESC: case 'q': @@ -809,24 +818,27 @@ out: } int map_symbol__tui_annotate(struct map_symbol *ms, struct perf_evsel *evsel, - struct hist_browser_timer *hbt) + struct hist_browser_timer *hbt, + struct annotation_options *opts) { - return symbol__tui_annotate(ms->sym, ms->map, evsel, hbt); + return symbol__tui_annotate(ms->sym, ms->map, evsel, hbt, opts); } int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel, - struct hist_browser_timer *hbt) + struct hist_browser_timer *hbt, + struct annotation_options *opts) { /* reset abort key so that it can get Ctrl-C as a key */ SLang_reset_tty(); SLang_init_tty(0, 0, 0); - return map_symbol__tui_annotate(&he->ms, evsel, hbt); + return map_symbol__tui_annotate(&he->ms, evsel, hbt, opts); } int symbol__tui_annotate(struct symbol *sym, struct map *map, struct perf_evsel *evsel, - struct hist_browser_timer *hbt) + struct hist_browser_timer *hbt, + struct annotation_options *opts) { struct annotation *notes = symbol__annotation(sym); struct map_symbol ms = { @@ -843,6 +855,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, .priv = &ms, .use_navkeypressed = true, }, + .opts = opts, }; int ret = -1, err; @@ -852,7 +865,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, if (map->dso->annotate_warned) return -1; - err = symbol__annotate2(sym, map, evsel, &annotation__default_options, &browser.arch); + err = symbol__annotate2(sym, map, evsel, opts, &browser.arch); if (err) { char msg[BUFSIZ]; symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg)); diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index e5f2472..a96f62c 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -1231,6 +1231,7 @@ static int hist_browser__show_entry(struct hist_browser *browser, int width = browser->b.width; char folded_sign = ' '; bool current_entry = ui_browser__is_current_entry(&browser->b, row); + bool use_callchain = hist_entry__has_callchains(entry) && symbol_conf.use_callchain; off_t row_offset = entry->row_offset; bool first = true; struct perf_hpp_fmt *fmt; @@ -1240,7 +1241,7 @@ static int hist_browser__show_entry(struct hist_browser *browser, browser->selection = &entry->ms; } - if (symbol_conf.use_callchain) { + if (use_callchain) { hist_entry__init_have_children(entry); folded_sign = hist_entry__folded(entry); } @@ -1276,7 +1277,7 @@ static int hist_browser__show_entry(struct hist_browser *browser, } if (first) { - if (symbol_conf.use_callchain) { + if (use_callchain) { ui_browser__printf(&browser->b, "%c ", folded_sign); width -= 2; } @@ -1583,7 +1584,7 @@ hists_browser__scnprintf_headers(struct hist_browser *browser, char *buf, int column = 0; int span = 0; - if (symbol_conf.use_callchain) { + if (hists__has_callchains(hists) && symbol_conf.use_callchain) { ret = scnprintf(buf, size, " "); if (advance_hpp_check(&dummy_hpp, ret)) return ret; @@ -1987,7 +1988,7 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser, bool first = true; int ret; - if (symbol_conf.use_callchain) { + if (hist_entry__has_callchains(he) && symbol_conf.use_callchain) { folded_sign = hist_entry__folded(he); printed += fprintf(fp, "%c ", folded_sign); } @@ -2175,7 +2176,8 @@ struct hist_browser *hist_browser__new(struct hists *hists) static struct hist_browser * perf_evsel_browser__new(struct perf_evsel *evsel, struct hist_browser_timer *hbt, - struct perf_env *env) + struct perf_env *env, + struct annotation_options *annotation_opts) { struct hist_browser *browser = hist_browser__new(evsel__hists(evsel)); @@ -2183,6 +2185,7 @@ perf_evsel_browser__new(struct perf_evsel *evsel, browser->hbt = hbt; browser->env = env; browser->title = hists_browser__scnprintf_title; + browser->annotation_opts = annotation_opts; } return browser; } @@ -2336,7 +2339,8 @@ do_annotate(struct hist_browser *browser, struct popup_action *act) struct hist_entry *he; int err; - if (!objdump_path && perf_env__lookup_objdump(browser->env)) + if (!browser->annotation_opts->objdump_path && + perf_env__lookup_objdump(browser->env, &browser->annotation_opts->objdump_path)) return 0; notes = symbol__annotation(act->ms.sym); @@ -2344,7 +2348,8 @@ do_annotate(struct hist_browser *browser, struct popup_action *act) return 0; evsel = hists_to_evsel(browser->hists); - err = map_symbol__tui_annotate(&act->ms, evsel, browser->hbt); + err = map_symbol__tui_annotate(&act->ms, evsel, browser->hbt, + browser->annotation_opts); he = hist_browser__selected_entry(browser); /* * offer option to annotate the other branch source or target @@ -2667,7 +2672,7 @@ static void hist_browser__update_percent_limit(struct hist_browser *hb, he->nr_rows = 0; } - if (!he->leaf || !symbol_conf.use_callchain) + if (!he->leaf || !hist_entry__has_callchains(he) || !symbol_conf.use_callchain) goto next; if (callchain_param.mode == CHAIN_GRAPH_REL) { @@ -2697,10 +2702,11 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, struct hist_browser_timer *hbt, float min_pcnt, struct perf_env *env, - bool warn_lost_event) + bool warn_lost_event, + struct annotation_options *annotation_opts) { struct hists *hists = evsel__hists(evsel); - struct hist_browser *browser = perf_evsel_browser__new(evsel, hbt, env); + struct hist_browser *browser = perf_evsel_browser__new(evsel, hbt, env, annotation_opts); struct branch_info *bi; #define MAX_OPTIONS 16 char *options[MAX_OPTIONS]; @@ -3062,6 +3068,7 @@ out: struct perf_evsel_menu { struct ui_browser b; struct perf_evsel *selection; + struct annotation_options *annotation_opts; bool lost_events, lost_events_warned; float min_pcnt; struct perf_env *env; @@ -3163,7 +3170,8 @@ browse_hists: true, hbt, menu->min_pcnt, menu->env, - warn_lost_event); + warn_lost_event, + menu->annotation_opts); ui_browser__show_title(&menu->b, title); switch (key) { case K_TAB: @@ -3222,7 +3230,8 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist, struct hist_browser_timer *hbt, float min_pcnt, struct perf_env *env, - bool warn_lost_event) + bool warn_lost_event, + struct annotation_options *annotation_opts) { struct perf_evsel *pos; struct perf_evsel_menu menu = { @@ -3237,6 +3246,7 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist, }, .min_pcnt = min_pcnt, .env = env, + .annotation_opts = annotation_opts, }; ui_helpline__push("Press ESC to exit"); @@ -3257,7 +3267,8 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, struct hist_browser_timer *hbt, float min_pcnt, struct perf_env *env, - bool warn_lost_event) + bool warn_lost_event, + struct annotation_options *annotation_opts) { int nr_entries = evlist->nr_entries; @@ -3267,7 +3278,8 @@ single_entry: return perf_evsel__hists_browse(first, nr_entries, help, false, hbt, min_pcnt, - env, warn_lost_event); + env, warn_lost_event, + annotation_opts); } if (symbol_conf.event_group) { @@ -3285,5 +3297,6 @@ single_entry: return __perf_evlist__tui_browse_hists(evlist, nr_entries, help, hbt, min_pcnt, env, - warn_lost_event); + warn_lost_event, + annotation_opts); } diff --git a/tools/perf/ui/browsers/hists.h b/tools/perf/ui/browsers/hists.h index 9428bee..91d3e18 100644 --- a/tools/perf/ui/browsers/hists.h +++ b/tools/perf/ui/browsers/hists.h @@ -4,6 +4,8 @@ #include "ui/browser.h" +struct annotation_options; + struct hist_browser { struct ui_browser b; struct hists *hists; @@ -12,6 +14,7 @@ struct hist_browser { struct hist_browser_timer *hbt; struct pstack *pstack; struct perf_env *env; + struct annotation_options *annotation_opts; int print_seq; bool show_dso; bool show_headers; diff --git a/tools/perf/ui/browsers/map.c b/tools/perf/ui/browsers/map.c index e03fa75..5b8b8c6 100644 --- a/tools/perf/ui/browsers/map.c +++ b/tools/perf/ui/browsers/map.c @@ -104,7 +104,7 @@ int map__browse(struct map *map) { struct map_browser mb = { .b = { - .entries = &map->dso->symbols[map->type], + .entries = &map->dso->symbols, .refresh = ui_browser__rb_tree_refresh, .seek = ui_browser__rb_tree_seek, .write = map_browser__write, diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c index aeeaf15..48428c9 100644 --- a/tools/perf/ui/gtk/annotate.c +++ b/tools/perf/ui/gtk/annotate.c @@ -169,7 +169,7 @@ static int symbol__gtk_annotate(struct symbol *sym, struct map *map, if (map->dso->annotate_warned) return -1; - err = symbol__annotate(sym, map, evsel, 0, NULL); + err = symbol__annotate(sym, map, evsel, 0, &annotation__default_options, NULL); if (err) { char msg[BUFSIZ]; symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg)); diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c index 24e1ec2..b085f1b 100644 --- a/tools/perf/ui/gtk/hists.c +++ b/tools/perf/ui/gtk/hists.c @@ -382,7 +382,8 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, gtk_tree_store_set(store, &iter, col_idx++, s, -1); } - if (symbol_conf.use_callchain && hists__has(hists, sym)) { + if (hists__has_callchains(hists) && + symbol_conf.use_callchain && hists__has(hists, sym)) { if (callchain_param.mode == CHAIN_GRAPH_REL) total = symbol_conf.cumulate_callchain ? h->stat_acc->period : h->stat.period; @@ -479,7 +480,7 @@ static void perf_gtk__add_hierarchy_entries(struct hists *hists, } } - if (symbol_conf.use_callchain && he->leaf) { + if (he->leaf && hist_entry__has_callchains(he) && symbol_conf.use_callchain) { if (callchain_param.mode == CHAIN_GRAPH_REL) total = symbol_conf.cumulate_callchain ? he->stat_acc->period : he->stat.period; diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index 706f6f1..fe3dfaa 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -207,7 +207,7 @@ static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b, if (ret) return ret; - if (a->thread != b->thread || !symbol_conf.use_callchain) + if (a->thread != b->thread || !hist_entry__has_callchains(a) || !symbol_conf.use_callchain) return 0; ret = b->callchain->max_depth - a->callchain->max_depth; diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index 6832fcb..69b7a28 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -516,7 +516,7 @@ static int hist_entry__hierarchy_fprintf(struct hist_entry *he, } printed += putc('\n', fp); - if (symbol_conf.use_callchain && he->leaf) { + if (he->leaf && hist_entry__has_callchains(he) && symbol_conf.use_callchain) { u64 total = hists__total_period(hists); printed += hist_entry_callchain__fprintf(he, total, 0, fp); @@ -550,7 +550,7 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size, ret = fprintf(fp, "%s\n", bf); - if (use_callchain) + if (hist_entry__has_callchains(he) && use_callchain) callchain_ret = hist_entry_callchain__fprintf(he, total_period, 0, fp); @@ -819,8 +819,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, } if (h->ms.map == NULL && verbose > 1) { - __map_groups__fprintf_maps(h->thread->mg, - MAP__FUNCTION, fp); + map_groups__fprintf(h->thread->mg, fp); fprintf(fp, "%.10s end\n", graph_dotted_line); } } diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 8052373..b604ef3 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -24,7 +24,6 @@ libperf-y += libstring.o libperf-y += bitmap.o libperf-y += hweight.o libperf-y += smt.o -libperf-y += quote.o libperf-y += strbuf.o libperf-y += string.o libperf-y += strlist.o @@ -152,6 +151,8 @@ libperf-y += perf-hooks.o libperf-$(CONFIG_CXX) += c++/ CFLAGS_config.o += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" +CFLAGS_llvm-utils.o += -DPERF_INCLUDE_DIR="BUILD_STR($(perf_include_dir_SQ))" + # avoid compiler warnings in 32-bit mode CFLAGS_genelf_debug.o += -Wno-packed diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 5d74a30..f91775b 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -21,6 +21,7 @@ #include "debug.h" #include "annotate.h" #include "evsel.h" +#include "evlist.h" #include "block-range.h" #include "string2.h" #include "arch/common.h" @@ -46,11 +47,10 @@ struct annotation_options annotation__default_options = { .use_offset = true, .jump_arrows = true, + .annotate_src = true, .offset_level = ANNOTATION__OFFSET_JUMP_TARGETS, }; -const char *disassembler_style; -const char *objdump_path; static regex_t file_lineno; static struct ins_ops *ins__find(struct arch *arch, const char *name); @@ -678,10 +678,28 @@ static struct arch *arch__find(const char *name) return bsearch(name, architectures, nmemb, sizeof(struct arch), arch__key_cmp); } -int symbol__alloc_hist(struct symbol *sym) +static struct annotated_source *annotated_source__new(void) +{ + struct annotated_source *src = zalloc(sizeof(*src)); + + if (src != NULL) + INIT_LIST_HEAD(&src->source); + + return src; +} + +static __maybe_unused void annotated_source__delete(struct annotated_source *src) +{ + if (src == NULL) + return; + zfree(&src->histograms); + zfree(&src->cycles_hist); + free(src); +} + +static int annotated_source__alloc_histograms(struct annotated_source *src, + size_t size, int nr_hists) { - struct annotation *notes = symbol__annotation(sym); - size_t size = symbol__size(sym); size_t sizeof_sym_hist; /* @@ -701,17 +719,13 @@ int symbol__alloc_hist(struct symbol *sym) sizeof_sym_hist = (sizeof(struct sym_hist) + size * sizeof(struct sym_hist_entry)); /* Check for overflow in zalloc argument */ - if (sizeof_sym_hist > (SIZE_MAX - sizeof(*notes->src)) - / symbol_conf.nr_events) + if (sizeof_sym_hist > SIZE_MAX / nr_hists) return -1; - notes->src = zalloc(sizeof(*notes->src) + symbol_conf.nr_events * sizeof_sym_hist); - if (notes->src == NULL) - return -1; - notes->src->sizeof_sym_hist = sizeof_sym_hist; - notes->src->nr_histograms = symbol_conf.nr_events; - INIT_LIST_HEAD(¬es->src->source); - return 0; + src->sizeof_sym_hist = sizeof_sym_hist; + src->nr_histograms = nr_hists; + src->histograms = calloc(nr_hists, sizeof_sym_hist) ; + return src->histograms ? 0 : -1; } /* The cycles histogram is lazily allocated. */ @@ -741,14 +755,11 @@ void symbol__annotate_zero_histograms(struct symbol *sym) pthread_mutex_unlock(¬es->lock); } -static int __symbol__account_cycles(struct annotation *notes, +static int __symbol__account_cycles(struct cyc_hist *ch, u64 start, unsigned offset, unsigned cycles, unsigned have_start) { - struct cyc_hist *ch; - - ch = notes->src->cycles_hist; /* * For now we can only account one basic block per * final jump. But multiple could be overlapping. @@ -760,6 +771,15 @@ static int __symbol__account_cycles(struct annotation *notes, ch[offset].num_aggr++; ch[offset].cycles_aggr += cycles; + if (cycles > ch[offset].cycles_max) + ch[offset].cycles_max = cycles; + + if (ch[offset].cycles_min) { + if (cycles && cycles < ch[offset].cycles_min) + ch[offset].cycles_min = cycles; + } else + ch[offset].cycles_min = cycles; + if (!have_start && ch[offset].have_start) return 0; if (ch[offset].num) { @@ -782,7 +802,7 @@ static int __symbol__account_cycles(struct annotation *notes, } static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map, - struct annotation *notes, int evidx, u64 addr, + struct annotated_source *src, int evidx, u64 addr, struct perf_sample *sample) { unsigned offset; @@ -798,7 +818,12 @@ static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map, } offset = addr - sym->start; - h = annotation__histogram(notes, evidx); + h = annotated_source__histogram(src, evidx); + if (h == NULL) { + pr_debug("%s(%d): ENOMEM! sym->name=%s, start=%#" PRIx64 ", addr=%#" PRIx64 ", end=%#" PRIx64 ", func: %d\n", + __func__, __LINE__, sym->name, sym->start, addr, sym->end, sym->type == STT_FUNC); + return -ENOMEM; + } h->nr_samples++; h->addr[offset].nr_samples++; h->period += sample->period; @@ -811,45 +836,69 @@ static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map, return 0; } -static struct annotation *symbol__get_annotation(struct symbol *sym, bool cycles) +static struct cyc_hist *symbol__cycles_hist(struct symbol *sym) { struct annotation *notes = symbol__annotation(sym); if (notes->src == NULL) { - if (symbol__alloc_hist(sym) < 0) + notes->src = annotated_source__new(); + if (notes->src == NULL) return NULL; + goto alloc_cycles_hist; } - if (!notes->src->cycles_hist && cycles) { - if (symbol__alloc_hist_cycles(sym) < 0) + + if (!notes->src->cycles_hist) { +alloc_cycles_hist: + symbol__alloc_hist_cycles(sym); + } + + return notes->src->cycles_hist; +} + +struct annotated_source *symbol__hists(struct symbol *sym, int nr_hists) +{ + struct annotation *notes = symbol__annotation(sym); + + if (notes->src == NULL) { + notes->src = annotated_source__new(); + if (notes->src == NULL) return NULL; + goto alloc_histograms; + } + + if (notes->src->histograms == NULL) { +alloc_histograms: + annotated_source__alloc_histograms(notes->src, symbol__size(sym), + nr_hists); } - return notes; + + return notes->src; } static int symbol__inc_addr_samples(struct symbol *sym, struct map *map, - int evidx, u64 addr, + struct perf_evsel *evsel, u64 addr, struct perf_sample *sample) { - struct annotation *notes; + struct annotated_source *src; if (sym == NULL) return 0; - notes = symbol__get_annotation(sym, false); - if (notes == NULL) + src = symbol__hists(sym, evsel->evlist->nr_entries); + if (src == NULL) return -ENOMEM; - return __symbol__inc_addr_samples(sym, map, notes, evidx, addr, sample); + return __symbol__inc_addr_samples(sym, map, src, evsel->idx, addr, sample); } static int symbol__account_cycles(u64 addr, u64 start, struct symbol *sym, unsigned cycles) { - struct annotation *notes; + struct cyc_hist *cycles_hist; unsigned offset; if (sym == NULL) return 0; - notes = symbol__get_annotation(sym, true); - if (notes == NULL) + cycles_hist = symbol__cycles_hist(sym); + if (cycles_hist == NULL) return -ENOMEM; if (addr < sym->start || addr >= sym->end) return -ERANGE; @@ -861,7 +910,7 @@ static int symbol__account_cycles(u64 addr, u64 start, start = 0; } offset = addr - sym->start; - return __symbol__account_cycles(notes, + return __symbol__account_cycles(cycles_hist, start ? start - sym->start : 0, offset, cycles, !!start); @@ -953,8 +1002,11 @@ void annotation__compute_ipc(struct annotation *notes, size_t size) if (ch->have_start) annotation__count_and_fill(notes, ch->start, offset, ch); al = notes->offsets[offset]; - if (al && ch->num_aggr) + if (al && ch->num_aggr) { al->cycles = ch->cycles_aggr / ch->num_aggr; + al->cycles_max = ch->cycles_max; + al->cycles_min = ch->cycles_min; + } notes->have_cycles = true; } } @@ -962,15 +1014,15 @@ void annotation__compute_ipc(struct annotation *notes, size_t size) } int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample, - int evidx) + struct perf_evsel *evsel) { - return symbol__inc_addr_samples(ams->sym, ams->map, evidx, ams->al_addr, sample); + return symbol__inc_addr_samples(ams->sym, ams->map, evsel, ams->al_addr, sample); } int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *sample, - int evidx, u64 ip) + struct perf_evsel *evsel, u64 ip) { - return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip, sample); + return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evsel, ip, sample); } static void disasm_line__init_ins(struct disasm_line *dl, struct arch *arch, struct map_symbol *ms) @@ -1019,6 +1071,7 @@ struct annotate_args { struct arch *arch; struct map_symbol ms; struct perf_evsel *evsel; + struct annotation_options *options; s64 offset; char *line; int line_nr; @@ -1560,6 +1613,7 @@ fallback: static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) { + struct annotation_options *opts = args->options; struct map *map = args->ms.map; struct dso *dso = map->dso; char *command; @@ -1607,13 +1661,13 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) "%s %s%s --start-address=0x%016" PRIx64 " --stop-address=0x%016" PRIx64 " -l -d %s %s -C \"%s\" 2>/dev/null|grep -v \"%s:\"|expand", - objdump_path ? objdump_path : "objdump", - disassembler_style ? "-M " : "", - disassembler_style ? disassembler_style : "", + opts->objdump_path ?: "objdump", + opts->disassembler_style ? "-M " : "", + opts->disassembler_style ?: "", map__rip_2objdump(map, sym->start), map__rip_2objdump(map, sym->end), - symbol_conf.annotate_asm_raw ? "" : "--no-show-raw", - symbol_conf.annotate_src ? "-S" : "", + opts->show_asm_raw ? "" : "--no-show-raw", + opts->annotate_src ? "-S" : "", symfs_filename, symfs_filename); if (err < 0) { @@ -1755,11 +1809,13 @@ void symbol__calc_percent(struct symbol *sym, struct perf_evsel *evsel) int symbol__annotate(struct symbol *sym, struct map *map, struct perf_evsel *evsel, size_t privsize, + struct annotation_options *options, struct arch **parch) { struct annotate_args args = { .privsize = privsize, .evsel = evsel, + .options = options, }; struct perf_env *env = perf_evsel__env(evsel); const char *arch_name = perf_env__arch(env); @@ -1937,8 +1993,8 @@ static int annotated_source__addr_fmt_width(struct list_head *lines, u64 start) } int symbol__annotate_printf(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, bool full_paths, - int min_pcnt, int max_lines, int context) + struct perf_evsel *evsel, + struct annotation_options *opts) { struct dso *dso = map->dso; char *filename; @@ -1950,23 +2006,28 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, u64 start = map__rip_2objdump(map, sym->start); int printed = 2, queue_len = 0, addr_fmt_width; int more = 0; + bool context = opts->context; u64 len; int width = symbol_conf.show_total_period ? 12 : 8; int graph_dotted_len; + char buf[512]; filename = strdup(dso->long_name); if (!filename) return -ENOMEM; - if (full_paths) + if (opts->full_path) d_filename = filename; else d_filename = basename(filename); len = symbol__size(sym); - if (perf_evsel__is_group_event(evsel)) + if (perf_evsel__is_group_event(evsel)) { width *= evsel->nr_members; + perf_evsel__group_desc(evsel, buf, sizeof(buf)); + evsel_name = buf; + } graph_dotted_len = printf(" %-*.*s| Source code & Disassembly of %s for %s (%" PRIu64 " samples)\n", width, width, symbol_conf.show_total_period ? "Period" : @@ -1990,7 +2051,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, } err = annotation_line__print(pos, sym, start, evsel, len, - min_pcnt, printed, max_lines, + opts->min_pcnt, printed, opts->max_lines, queue, addr_fmt_width); switch (err) { @@ -2323,20 +2384,19 @@ static void symbol__calc_lines(struct symbol *sym, struct map *map, } int symbol__tty_annotate2(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, bool print_lines, - bool full_paths) + struct perf_evsel *evsel, + struct annotation_options *opts) { struct dso *dso = map->dso; struct rb_root source_line = RB_ROOT; - struct annotation_options opts = annotation__default_options; struct annotation *notes = symbol__annotation(sym); char buf[1024]; - if (symbol__annotate2(sym, map, evsel, &opts, NULL) < 0) + if (symbol__annotate2(sym, map, evsel, opts, NULL) < 0) return -1; - if (print_lines) { - srcline_full_filename = full_paths; + if (opts->print_lines) { + srcline_full_filename = opts->full_path; symbol__calc_lines(sym, map, &source_line); print_summary(&source_line, dso->long_name); } @@ -2351,25 +2411,24 @@ int symbol__tty_annotate2(struct symbol *sym, struct map *map, } int symbol__tty_annotate(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, bool print_lines, - bool full_paths, int min_pcnt, int max_lines) + struct perf_evsel *evsel, + struct annotation_options *opts) { struct dso *dso = map->dso; struct rb_root source_line = RB_ROOT; - if (symbol__annotate(sym, map, evsel, 0, NULL) < 0) + if (symbol__annotate(sym, map, evsel, 0, opts, NULL) < 0) return -1; symbol__calc_percent(sym, evsel); - if (print_lines) { - srcline_full_filename = full_paths; + if (opts->print_lines) { + srcline_full_filename = opts->full_path; symbol__calc_lines(sym, map, &source_line); print_summary(&source_line, dso->long_name); } - symbol__annotate_printf(sym, map, evsel, full_paths, - min_pcnt, max_lines, 0); + symbol__annotate_printf(sym, map, evsel, opts); annotated_source__purge(symbol__annotation(sym)->src); @@ -2486,13 +2545,38 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati else obj__printf(obj, "%*s ", ANNOTATION__IPC_WIDTH - 1, "IPC"); - if (al->cycles) - obj__printf(obj, "%*" PRIu64 " ", + if (!notes->options->show_minmax_cycle) { + if (al->cycles) + obj__printf(obj, "%*" PRIu64 " ", ANNOTATION__CYCLES_WIDTH - 1, al->cycles); - else if (!show_title) - obj__printf(obj, "%*s", ANNOTATION__CYCLES_WIDTH, " "); - else - obj__printf(obj, "%*s ", ANNOTATION__CYCLES_WIDTH - 1, "Cycle"); + else if (!show_title) + obj__printf(obj, "%*s", + ANNOTATION__CYCLES_WIDTH, " "); + else + obj__printf(obj, "%*s ", + ANNOTATION__CYCLES_WIDTH - 1, + "Cycle"); + } else { + if (al->cycles) { + char str[32]; + + scnprintf(str, sizeof(str), + "%" PRIu64 "(%" PRIu64 "/%" PRIu64 ")", + al->cycles, al->cycles_min, + al->cycles_max); + + obj__printf(obj, "%*s ", + ANNOTATION__MINMAX_CYCLES_WIDTH - 1, + str); + } else if (!show_title) + obj__printf(obj, "%*s", + ANNOTATION__MINMAX_CYCLES_WIDTH, + " "); + else + obj__printf(obj, "%*s ", + ANNOTATION__MINMAX_CYCLES_WIDTH - 1, + "Cycle(min/max)"); + } } obj__printf(obj, " "); @@ -2579,7 +2663,7 @@ int symbol__annotate2(struct symbol *sym, struct map *map, struct perf_evsel *ev if (perf_evsel__is_group_event(evsel)) nr_pcnt = evsel->nr_members; - err = symbol__annotate(sym, map, evsel, 0, parch); + err = symbol__annotate(sym, map, evsel, 0, options, parch); if (err) goto out_free_offsets; diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index f28a9e4..a4c0d91 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -61,16 +61,27 @@ bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2); #define ANNOTATION__IPC_WIDTH 6 #define ANNOTATION__CYCLES_WIDTH 6 +#define ANNOTATION__MINMAX_CYCLES_WIDTH 19 struct annotation_options { bool hide_src_code, use_offset, jump_arrows, + print_lines, + full_path, show_linenr, show_nr_jumps, show_nr_samples, - show_total_period; + show_total_period, + show_minmax_cycle, + show_asm_raw, + annotate_src; u8 offset_level; + int min_pcnt; + int max_lines; + int context; + const char *objdump_path; + const char *disassembler_style; }; enum { @@ -105,6 +116,8 @@ struct annotation_line { int jump_sources; float ipc; u64 cycles; + u64 cycles_max; + u64 cycles_min; size_t privsize; char *path; u32 idx; @@ -186,6 +199,8 @@ struct cyc_hist { u64 start; u64 cycles; u64 cycles_aggr; + u64 cycles_max; + u64 cycles_min; u32 num; u32 num_aggr; u8 have_start; @@ -195,7 +210,11 @@ struct cyc_hist { /** struct annotated_source - symbols with hits have this attached as in sannotation * - * @histogram: Array of addr hit histograms per event being monitored + * @histograms: Array of addr hit histograms per event being monitored + * nr_histograms: This may not be the same as evsel->evlist->nr_entries if + * we have more than a group in a evlist, where we will want + * to see each group separately, that is why symbol__annotate2() + * sets src->nr_histograms to evsel->nr_members. * @lines: If 'print_lines' is specified, per source code line percentages * @source: source parsed from a disassembler like objdump -dS * @cyc_hist: Average cycles per basic block @@ -211,7 +230,7 @@ struct annotated_source { int nr_histograms; size_t sizeof_sym_hist; struct cyc_hist *cycles_hist; - struct sym_hist histograms[0]; + struct sym_hist *histograms; }; struct annotation { @@ -239,6 +258,9 @@ struct annotation { static inline int annotation__cycles_width(struct annotation *notes) { + if (notes->have_cycles && notes->options->show_minmax_cycle) + return ANNOTATION__IPC_WIDTH + ANNOTATION__MINMAX_CYCLES_WIDTH; + return notes->have_cycles ? ANNOTATION__IPC_WIDTH + ANNOTATION__CYCLES_WIDTH : 0; } @@ -258,10 +280,14 @@ void annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym) void annotation__update_column_widths(struct annotation *notes); void annotation__init_column_widths(struct annotation *notes, struct symbol *sym); +static inline struct sym_hist *annotated_source__histogram(struct annotated_source *src, int idx) +{ + return ((void *)src->histograms) + (src->sizeof_sym_hist * idx); +} + static inline struct sym_hist *annotation__histogram(struct annotation *notes, int idx) { - return (((void *)¬es->src->histograms) + - (notes->src->sizeof_sym_hist * idx)); + return annotated_source__histogram(notes->src, idx); } static inline struct annotation *symbol__annotation(struct symbol *sym) @@ -270,20 +296,21 @@ static inline struct annotation *symbol__annotation(struct symbol *sym) } int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample, - int evidx); + struct perf_evsel *evsel); int addr_map_symbol__account_cycles(struct addr_map_symbol *ams, struct addr_map_symbol *start, unsigned cycles); int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *sample, - int evidx, u64 addr); + struct perf_evsel *evsel, u64 addr); -int symbol__alloc_hist(struct symbol *sym); +struct annotated_source *symbol__hists(struct symbol *sym, int nr_hists); void symbol__annotate_zero_histograms(struct symbol *sym); int symbol__annotate(struct symbol *sym, struct map *map, struct perf_evsel *evsel, size_t privsize, + struct annotation_options *options, struct arch **parch); int symbol__annotate2(struct symbol *sym, struct map *map, struct perf_evsel *evsel, @@ -311,8 +338,8 @@ int symbol__strerror_disassemble(struct symbol *sym, struct map *map, int errnum, char *buf, size_t buflen); int symbol__annotate_printf(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, bool full_paths, - int min_pcnt, int max_lines, int context); + struct perf_evsel *evsel, + struct annotation_options *options); int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp); void symbol__annotate_zero_histogram(struct symbol *sym, int evidx); void symbol__annotate_decay_histogram(struct symbol *sym, int evidx); @@ -323,30 +350,27 @@ int map_symbol__annotation_dump(struct map_symbol *ms, struct perf_evsel *evsel) bool ui__has_annotation(void); int symbol__tty_annotate(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, bool print_lines, - bool full_paths, int min_pcnt, int max_lines); + struct perf_evsel *evsel, struct annotation_options *opts); int symbol__tty_annotate2(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, bool print_lines, - bool full_paths); + struct perf_evsel *evsel, struct annotation_options *opts); #ifdef HAVE_SLANG_SUPPORT int symbol__tui_annotate(struct symbol *sym, struct map *map, struct perf_evsel *evsel, - struct hist_browser_timer *hbt); + struct hist_browser_timer *hbt, + struct annotation_options *opts); #else static inline int symbol__tui_annotate(struct symbol *sym __maybe_unused, struct map *map __maybe_unused, struct perf_evsel *evsel __maybe_unused, - struct hist_browser_timer *hbt - __maybe_unused) + struct hist_browser_timer *hbt __maybe_unused, + struct annotation_options *opts __maybe_unused) { return 0; } #endif -extern const char *disassembler_style; - void annotation_config__init(void); #endif /* __PERF_ANNOTATE_H */ diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 857de69..d056447 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -1679,7 +1679,7 @@ struct sym_args { static bool kern_sym_match(struct sym_args *args, const char *name, char type) { /* A function with the same name, and global or the n'th found or any */ - return symbol_type__is_a(type, MAP__FUNCTION) && + return kallsyms__is_function(type) && !strcmp(name, args->name) && ((args->global && isupper(type)) || (args->selected && ++(args->cnt) == args->idx) || @@ -1784,7 +1784,7 @@ static int find_entire_kern_cb(void *arg, const char *name __maybe_unused, { struct sym_args *args = arg; - if (!symbol_type__is_a(type, MAP__FUNCTION)) + if (!kallsyms__is_function(type)) return 0; if (!args->started) { @@ -1915,7 +1915,7 @@ static void print_duplicate_syms(struct dso *dso, const char *sym_name) pr_err("Multiple symbols with name '%s'\n", sym_name); - sym = dso__first_symbol(dso, MAP__FUNCTION); + sym = dso__first_symbol(dso); while (sym) { if (dso_sym_match(sym, sym_name, &cnt, -1)) { pr_err("#%d\t0x%"PRIx64"\t%c\t%s\n", @@ -1945,7 +1945,7 @@ static int find_dso_sym(struct dso *dso, const char *sym_name, u64 *start, *start = 0; *size = 0; - sym = dso__first_symbol(dso, MAP__FUNCTION); + sym = dso__first_symbol(dso); while (sym) { if (*start) { if (!*size) @@ -1972,8 +1972,8 @@ static int find_dso_sym(struct dso *dso, const char *sym_name, u64 *start, static int addr_filter__entire_dso(struct addr_filter *filt, struct dso *dso) { - struct symbol *first_sym = dso__first_symbol(dso, MAP__FUNCTION); - struct symbol *last_sym = dso__last_symbol(dso, MAP__FUNCTION); + struct symbol *first_sym = dso__first_symbol(dso); + struct symbol *last_sym = dso__last_symbol(dso); if (!first_sym || !last_sym) { pr_err("Failed to determine filter for %s\nNo symbols found.\n", diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index af7ad81..cee6587 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -66,7 +66,7 @@ bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz, const char *name) } obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, name); - if (IS_ERR(obj)) { + if (IS_ERR_OR_NULL(obj)) { pr_debug("bpf: failed to load buffer\n"); return ERR_PTR(-EINVAL); } @@ -102,14 +102,14 @@ struct bpf_object *bpf__prepare_load(const char *filename, bool source) pr_debug("bpf: successfull builtin compilation\n"); obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, filename); - if (!IS_ERR(obj) && llvm_param.dump_obj) + if (!IS_ERR_OR_NULL(obj) && llvm_param.dump_obj) llvm__dump_obj(filename, obj_buf, obj_buf_sz); free(obj_buf); } else obj = bpf_object__open(filename); - if (IS_ERR(obj)) { + if (IS_ERR_OR_NULL(obj)) { pr_debug("bpf: failed to load %s\n", filename); return obj; } diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 537eadd..04b1d53 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -47,9 +47,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused, return -1; } - thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->ip, &al); - - if (al.map != NULL) + if (thread__find_map(thread, sample->cpumode, sample->ip, &al)) al.map->dso->hit = 1; thread__put(thread); diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c index decb91f9..ccd0263 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -93,20 +93,17 @@ static int open_cgroup(const char *name) static struct cgroup *evlist__find_cgroup(struct perf_evlist *evlist, const char *str) { struct perf_evsel *counter; - struct cgroup *cgrp = NULL; /* * check if cgrp is already defined, if so we reuse it */ evlist__for_each_entry(evlist, counter) { if (!counter->cgrp) continue; - if (!strcmp(counter->cgrp->name, str)) { - cgrp = cgroup__get(counter->cgrp); - break; - } + if (!strcmp(counter->cgrp->name, str)) + return cgroup__get(counter->cgrp); } - return cgrp; + return NULL; } static struct cgroup *cgroup__new(const char *name) diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 84eb939..5ac1570 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -707,6 +707,14 @@ struct perf_config_set *perf_config_set__new(void) return set; } +static int perf_config__init(void) +{ + if (config_set == NULL) + config_set = perf_config_set__new(); + + return config_set == NULL; +} + int perf_config(config_fn_t fn, void *data) { int ret = 0; @@ -714,7 +722,7 @@ int perf_config(config_fn_t fn, void *data) struct perf_config_section *section; struct perf_config_item *item; - if (config_set == NULL) + if (config_set == NULL && perf_config__init()) return -1; perf_config_set__for_each_entry(config_set, section, item) { @@ -735,12 +743,6 @@ int perf_config(config_fn_t fn, void *data) return ret; } -void perf_config__init(void) -{ - if (config_set == NULL) - config_set = perf_config_set__new(); -} - void perf_config__exit(void) { perf_config_set__delete(config_set); diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h index baf82bf..bd0a589 100644 --- a/tools/perf/util/config.h +++ b/tools/perf/util/config.h @@ -38,7 +38,6 @@ struct perf_config_set *perf_config_set__new(void); void perf_config_set__delete(struct perf_config_set *set); int perf_config_set__collect(struct perf_config_set *set, const char *file_name, const char *var, const char *value); -void perf_config__init(void); void perf_config__exit(void); void perf_config__refresh(void); diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c index c8b98fa..4d5fc37 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -96,11 +96,19 @@ int cs_etm_decoder__get_packet(struct cs_etm_decoder *decoder, /* Nothing to do, might as well just return */ if (decoder->packet_count == 0) return 0; + /* + * The queueing process in function cs_etm_decoder__buffer_packet() + * increments the tail *before* using it. This is somewhat counter + * intuitive but it has the advantage of centralizing tail management + * at a single location. Because of that we need to follow the same + * heuristic with the head, i.e we increment it before using its + * value. Otherwise the first element of the packet queue is not + * used. + */ + decoder->head = (decoder->head + 1) & (MAX_BUFFER - 1); *packet = decoder->packet_buffer[decoder->head]; - decoder->head = (decoder->head + 1) & (MAX_BUFFER - 1); - decoder->packet_count--; return 1; diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index bf16dc9..822ba91 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -270,9 +270,7 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address, thread = etmq->etm->unknown_thread; } - thread__find_addr_map(thread, cpumode, MAP__FUNCTION, address, &al); - - if (!al.map || !al.map->dso) + if (!thread__find_map(thread, cpumode, address, &al) || !al.map->dso) return 0; if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR && diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c index b0c2b5c..7123746 100644 --- a/tools/perf/util/db-export.c +++ b/tools/perf/util/db-export.c @@ -247,9 +247,9 @@ static int db_ids_from_al(struct db_export *dbe, struct addr_location *al, *dso_db_id = dso->db_id; if (!al->sym) { - al->sym = symbol__new(al->addr, 0, 0, "unknown"); + al->sym = symbol__new(al->addr, 0, 0, 0, "unknown"); if (al->sym) - dso__insert_symbol(dso, al->map->type, al->sym); + dso__insert_symbol(dso, al->sym); } if (al->sym) { @@ -315,8 +315,7 @@ static struct call_path *call_path_from_sample(struct db_export *dbe, al.addr = node->ip; if (al.map && !al.sym) - al.sym = dso__find_symbol(al.map->dso, MAP__FUNCTION, - al.addr); + al.sym = dso__find_symbol(al.map->dso, al.addr); db_ids_from_al(dbe, &al, &dso_db_id, &sym_db_id, &offset); diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 36ef45b..51cf82c 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -354,6 +354,8 @@ int __kmod_path__parse(struct kmod_path *m, const char *path, if ((strncmp(name, "[kernel.kallsyms]", 17) == 0) || (strncmp(name, "[guest.kernel.kallsyms", 22) == 0) || (strncmp(name, "[vdso]", 6) == 0) || + (strncmp(name, "[vdso32]", 8) == 0) || + (strncmp(name, "[vdsox32]", 9) == 0) || (strncmp(name, "[vsyscall]", 10) == 0)) { m->kmod = false; @@ -1014,7 +1016,7 @@ struct map *dso__new_map(const char *name) struct dso *dso = dso__new(name); if (dso) - map = map__new2(0, dso, MAP__FUNCTION); + map = map__new2(0, dso); return map; } @@ -1176,19 +1178,19 @@ int dso__name_len(const struct dso *dso) return dso->short_name_len; } -bool dso__loaded(const struct dso *dso, enum map_type type) +bool dso__loaded(const struct dso *dso) { - return dso->loaded & (1 << type); + return dso->loaded; } -bool dso__sorted_by_name(const struct dso *dso, enum map_type type) +bool dso__sorted_by_name(const struct dso *dso) { - return dso->sorted_by_name & (1 << type); + return dso->sorted_by_name; } -void dso__set_sorted_by_name(struct dso *dso, enum map_type type) +void dso__set_sorted_by_name(struct dso *dso) { - dso->sorted_by_name |= (1 << type); + dso->sorted_by_name = true; } struct dso *dso__new(const char *name) @@ -1196,12 +1198,10 @@ struct dso *dso__new(const char *name) struct dso *dso = calloc(1, sizeof(*dso) + strlen(name) + 1); if (dso != NULL) { - int i; strcpy(dso->name, name); dso__set_long_name(dso, dso->name, false); dso__set_short_name(dso, dso->name, false); - for (i = 0; i < MAP__NR_TYPES; ++i) - dso->symbols[i] = dso->symbol_names[i] = RB_ROOT; + dso->symbols = dso->symbol_names = RB_ROOT; dso->data.cache = RB_ROOT; dso->inlined_nodes = RB_ROOT; dso->srclines = RB_ROOT; @@ -1231,8 +1231,6 @@ struct dso *dso__new(const char *name) void dso__delete(struct dso *dso) { - int i; - if (!RB_EMPTY_NODE(&dso->rb_node)) pr_err("DSO %s is still in rbtree when being deleted!\n", dso->long_name); @@ -1240,8 +1238,7 @@ void dso__delete(struct dso *dso) /* free inlines first, as they reference symbols */ inlines__tree_delete(&dso->inlined_nodes); srcline__tree_delete(&dso->srclines); - for (i = 0; i < MAP__NR_TYPES; ++i) - symbols__delete(&dso->symbols[i]); + symbols__delete(&dso->symbols); if (dso->short_name_allocated) { zfree((char **)&dso->short_name); @@ -1451,9 +1448,7 @@ size_t __dsos__fprintf(struct list_head *head, FILE *fp) size_t ret = 0; list_for_each_entry(pos, head, node) { - int i; - for (i = 0; i < MAP__NR_TYPES; ++i) - ret += dso__fprintf(pos, i, fp); + ret += dso__fprintf(pos, fp); } return ret; @@ -1467,18 +1462,17 @@ size_t dso__fprintf_buildid(struct dso *dso, FILE *fp) return fprintf(fp, "%s", sbuild_id); } -size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp) +size_t dso__fprintf(struct dso *dso, FILE *fp) { struct rb_node *nd; size_t ret = fprintf(fp, "dso: %s (", dso->short_name); if (dso->short_name != dso->long_name) ret += fprintf(fp, "%s, ", dso->long_name); - ret += fprintf(fp, "%s, %sloaded, ", map_type__name[type], - dso__loaded(dso, type) ? "" : "NOT "); + ret += fprintf(fp, "%sloaded, ", dso__loaded(dso) ? "" : "NOT "); ret += dso__fprintf_buildid(dso, fp); ret += fprintf(fp, ")\n"); - for (nd = rb_first(&dso->symbols[type]); nd; nd = rb_next(nd)) { + for (nd = rb_first(&dso->symbols); nd; nd = rb_next(nd)) { struct symbol *pos = rb_entry(nd, struct symbol, rb_node); ret += symbol__fprintf(pos, fp); } diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index c229dbe..ef69de2 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -140,14 +140,14 @@ struct dso { struct list_head node; struct rb_node rb_node; /* rbtree node sorted by long name */ struct rb_root *root; /* root of rbtree that rb_node is in */ - struct rb_root symbols[MAP__NR_TYPES]; - struct rb_root symbol_names[MAP__NR_TYPES]; + struct rb_root symbols; + struct rb_root symbol_names; struct rb_root inlined_nodes; struct rb_root srclines; struct { u64 addr; struct symbol *symbol; - } last_find_result[MAP__NR_TYPES]; + } last_find_result; void *a2l; char *symsrc_filename; unsigned int a2l_fails; @@ -164,8 +164,8 @@ struct dso { u8 short_name_allocated:1; u8 long_name_allocated:1; u8 is_64_bit:1; - u8 sorted_by_name; - u8 loaded; + bool sorted_by_name; + bool loaded; u8 rel; u8 build_id[BUILD_ID_SIZE]; u64 text_offset; @@ -202,14 +202,13 @@ struct dso { * @dso: the 'struct dso *' in which symbols itereated * @pos: the 'struct symbol *' to use as a loop cursor * @n: the 'struct rb_node *' to use as a temporary storage - * @type: the 'enum map_type' type of symbols */ -#define dso__for_each_symbol(dso, pos, n, type) \ - symbols__for_each_entry(&(dso)->symbols[(type)], pos, n) +#define dso__for_each_symbol(dso, pos, n) \ + symbols__for_each_entry(&(dso)->symbols, pos, n) -static inline void dso__set_loaded(struct dso *dso, enum map_type type) +static inline void dso__set_loaded(struct dso *dso) { - dso->loaded |= (1 << type); + dso->loaded = true; } struct dso *dso__new(const char *name); @@ -231,11 +230,16 @@ static inline void __dso__zput(struct dso **dso) #define dso__zput(dso) __dso__zput(&dso) -bool dso__loaded(const struct dso *dso, enum map_type type); +bool dso__loaded(const struct dso *dso); -bool dso__sorted_by_name(const struct dso *dso, enum map_type type); -void dso__set_sorted_by_name(struct dso *dso, enum map_type type); -void dso__sort_by_name(struct dso *dso, enum map_type type); +static inline bool dso__has_symbols(const struct dso *dso) +{ + return !RB_EMPTY_ROOT(&dso->symbols); +} + +bool dso__sorted_by_name(const struct dso *dso); +void dso__set_sorted_by_name(struct dso *dso); +void dso__sort_by_name(struct dso *dso); void dso__set_build_id(struct dso *dso, void *build_id); bool dso__build_id_equal(const struct dso *dso, u8 *build_id); @@ -349,9 +353,8 @@ size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp, size_t __dsos__fprintf(struct list_head *head, FILE *fp); size_t dso__fprintf_buildid(struct dso *dso, FILE *fp); -size_t dso__fprintf_symbols_by_name(struct dso *dso, - enum map_type type, FILE *fp); -size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp); +size_t dso__fprintf_symbols_by_name(struct dso *dso, FILE *fp); +size_t dso__fprintf(struct dso *dso, FILE *fp); static inline bool dso__is_vmlinux(struct dso *dso) { diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 4c84276..59f38c7 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -93,6 +93,37 @@ int perf_env__read_cpu_topology_map(struct perf_env *env) return 0; } +static int perf_env__read_arch(struct perf_env *env) +{ + struct utsname uts; + + if (env->arch) + return 0; + + if (!uname(&uts)) + env->arch = strdup(uts.machine); + + return env->arch ? 0 : -ENOMEM; +} + +static int perf_env__read_nr_cpus_avail(struct perf_env *env) +{ + if (env->nr_cpus_avail == 0) + env->nr_cpus_avail = cpu__max_present_cpu(); + + return env->nr_cpus_avail ? 0 : -ENOENT; +} + +const char *perf_env__raw_arch(struct perf_env *env) +{ + return env && !perf_env__read_arch(env) ? env->arch : "unknown"; +} + +int perf_env__nr_cpus_avail(struct perf_env *env) +{ + return env && !perf_env__read_nr_cpus_avail(env) ? env->nr_cpus_avail : 0; +} + void cpu_cache_level__free(struct cpu_cache_level *cache) { free(cache->type); diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index c4ef2e5..1f3ccc36 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -76,4 +76,7 @@ int perf_env__read_cpu_topology_map(struct perf_env *env); void cpu_cache_level__free(struct cpu_cache_level *cache); const char *perf_env__arch(struct perf_env *env); +const char *perf_env__raw_arch(struct perf_env *env); +int perf_env__nr_cpus_avail(struct perf_env *env); + #endif /* __PERF_ENV_H */ diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 98ff3a6..0c8ecf0 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -88,10 +88,10 @@ static const char *perf_ns__name(unsigned int id) return perf_ns__names[id]; } -static int perf_tool__process_synth_event(struct perf_tool *tool, - union perf_event *event, - struct machine *machine, - perf_event__handler_t process) +int perf_tool__process_synth_event(struct perf_tool *tool, + union perf_event *event, + struct machine *machine, + perf_event__handler_t process) { struct perf_sample synth_sample = { .pid = -1, @@ -464,8 +464,7 @@ int perf_event__synthesize_modules(struct perf_tool *tool, { int rc = 0; struct map *pos; - struct map_groups *kmaps = &machine->kmaps; - struct maps *maps = &kmaps->maps[MAP__FUNCTION]; + struct maps *maps = machine__kernel_maps(machine); union perf_event *event = zalloc((sizeof(event->mmap) + machine->id_hdr_size)); if (event == NULL) { @@ -488,7 +487,7 @@ int perf_event__synthesize_modules(struct perf_tool *tool, for (pos = maps__first(maps); pos; pos = map__next(pos)) { size_t size; - if (__map__is_kernel(pos)) + if (!__map__is_kmodule(pos)) continue; size = PERF_ALIGN(pos->dso->long_name_len + 1, sizeof(u64)); @@ -869,7 +868,7 @@ static int find_symbol_cb(void *arg, const char *name, char type, * Must be a function or at least an alias, as in PARISC64, where "_text" is * an 'A' to the same address as "_stext". */ - if (!(symbol_type__is_a(type, MAP__FUNCTION) || + if (!(kallsyms__is_function(type) || type == 'A') || strcmp(name, args->name)) return 0; @@ -889,9 +888,16 @@ int kallsyms__get_function_start(const char *kallsyms_filename, return 0; } -int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine) +int __weak perf_event__synthesize_extra_kmaps(struct perf_tool *tool __maybe_unused, + perf_event__handler_t process __maybe_unused, + struct machine *machine __maybe_unused) +{ + return 0; +} + +static int __perf_event__synthesize_kernel_mmap(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine) { size_t size; struct map *map = machine__kernel_map(machine); @@ -944,6 +950,19 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, return err; } +int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine) +{ + int err; + + err = __perf_event__synthesize_kernel_mmap(tool, process, machine); + if (err < 0) + return err; + + return perf_event__synthesize_extra_kmaps(tool, process, machine); +} + int perf_event__synthesize_thread_map2(struct perf_tool *tool, struct thread_map *threads, perf_event__handler_t process, @@ -1489,9 +1508,8 @@ int perf_event__process(struct perf_tool *tool __maybe_unused, return machine__process_event(machine, event, sample); } -void thread__find_addr_map(struct thread *thread, u8 cpumode, - enum map_type type, u64 addr, - struct addr_location *al) +struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, + struct addr_location *al) { struct map_groups *mg = thread->mg; struct machine *machine = mg->machine; @@ -1505,7 +1523,7 @@ void thread__find_addr_map(struct thread *thread, u8 cpumode, if (machine == NULL) { al->map = NULL; - return; + return NULL; } if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) { @@ -1533,10 +1551,10 @@ void thread__find_addr_map(struct thread *thread, u8 cpumode, !perf_host) al->filtered |= (1 << HIST_FILTER__HOST); - return; + return NULL; } try_again: - al->map = map_groups__find(mg, type, al->addr); + al->map = map_groups__find(mg, al->addr); if (al->map == NULL) { /* * If this is outside of all known maps, and is a negative @@ -1563,17 +1581,17 @@ try_again: map__load(al->map); al->addr = al->map->map_ip(al->map, al->addr); } + + return al->map; } -void thread__find_addr_location(struct thread *thread, - u8 cpumode, enum map_type type, u64 addr, - struct addr_location *al) +struct symbol *thread__find_symbol(struct thread *thread, u8 cpumode, + u64 addr, struct addr_location *al) { - thread__find_addr_map(thread, cpumode, type, addr, al); - if (al->map != NULL) + al->sym = NULL; + if (thread__find_map(thread, cpumode, addr, al)) al->sym = map__find_symbol(al->map, al->addr); - else - al->sym = NULL; + return al->sym; } /* @@ -1590,7 +1608,7 @@ int machine__resolve(struct machine *machine, struct addr_location *al, return -1; dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid); - thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->ip, al); + thread__find_map(thread, sample->cpumode, sample->ip, al); dump_printf(" ...... dso: %s\n", al->map ? al->map->dso->long_name : al->level == 'H' ? "[hypervisor]" : "<not found>"); @@ -1669,10 +1687,7 @@ bool sample_addr_correlates_sym(struct perf_event_attr *attr) void thread__resolve(struct thread *thread, struct addr_location *al, struct perf_sample *sample) { - thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->addr, al); - if (!al->map) - thread__find_addr_map(thread, sample->cpumode, MAP__VARIABLE, - sample->addr, al); + thread__find_map(thread, sample->cpumode, sample->addr, al); al->cpu = sample->cpu; al->sym = NULL; diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 0f79474..bfa60bc 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -750,6 +750,10 @@ int perf_event__process_exit(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine); +int perf_tool__process_synth_event(struct perf_tool *tool, + union perf_event *event, + struct machine *machine, + perf_event__handler_t process); int perf_event__process(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -796,6 +800,10 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool, bool mmap_data, unsigned int proc_map_timeout); +int perf_event__synthesize_extra_kmaps(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine); + size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp); size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp); size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp); diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index a59281d..e7a4b31 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1795,3 +1795,18 @@ bool perf_evlist__exclude_kernel(struct perf_evlist *evlist) return true; } + +/* + * Events in data file are not collect in groups, but we still want + * the group display. Set the artificial group and set the leader's + * forced_leader flag to notify the display code. + */ +void perf_evlist__force_leader(struct perf_evlist *evlist) +{ + if (!evlist->nr_groups) { + struct perf_evsel *leader = perf_evlist__first(evlist); + + perf_evlist__set_leader(evlist); + leader->forced_leader = true; + } +} diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 6c41b2f..dc66436 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -309,4 +309,7 @@ struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist, union perf_event *event); bool perf_evlist__exclude_kernel(struct perf_evlist *evlist); + +void perf_evlist__force_leader(struct perf_evlist *evlist); + #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 4cd2cf9..94fce4f 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -2197,7 +2197,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, } } - if (type & PERF_SAMPLE_CALLCHAIN) { + if (evsel__has_callchain(evsel)) { const u64 max_callchain_nr = UINT64_MAX / sizeof(u64); OVERFLOW_CHECK_u64(array); @@ -2857,12 +2857,12 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, "Hint: Try again after reducing the number of events.\n" "Hint: Try increasing the limit with 'ulimit -n <limit>'"); case ENOMEM: - if ((evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) != 0 && + if (evsel__has_callchain(evsel) && access("/proc/sys/kernel/perf_event_max_stack", F_OK) == 0) return scnprintf(msg, size, "Not enough memory to setup event with callchain.\n" "Hint: Try tweaking /proc/sys/kernel/perf_event_max_stack\n" - "Hint: Current value: %d", sysctl_perf_event_max_stack); + "Hint: Current value: %d", sysctl__max_stack()); break; case ENODEV: if (target->cpu_list) diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 92ec009..d277930 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -127,6 +127,7 @@ struct perf_evsel { bool precise_max; bool ignore_missing_thread; bool forced_leader; + bool use_uncore_alias; /* parse modifier helper */ int exclude_GH; int nr_members; @@ -458,6 +459,11 @@ static inline bool perf_evsel__has_branch_callstack(const struct perf_evsel *evs return evsel->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK; } +static inline bool evsel__has_callchain(const struct perf_evsel *evsel) +{ + return (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) != 0; +} + typedef int (*attr__fprintf_f)(FILE *, const char *, const char *, void *); int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c index c540d47..aafbe54 100644 --- a/tools/perf/util/genelf.c +++ b/tools/perf/util/genelf.c @@ -114,7 +114,7 @@ gen_build_id(struct buildid_note *note, fd = open("/dev/urandom", O_RDONLY); if (fd == -1) - err(1, "cannot access /dev/urandom for builid"); + err(1, "cannot access /dev/urandom for buildid"); sret = read(fd, note->build_id, sz); diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index a8bff21..540cd2d 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1459,8 +1459,24 @@ static void print_cmdline(struct feat_fd *ff, FILE *fp) fprintf(fp, "# cmdline : "); - for (i = 0; i < nr; i++) - fprintf(fp, "%s ", ff->ph->env.cmdline_argv[i]); + for (i = 0; i < nr; i++) { + char *argv_i = strdup(ff->ph->env.cmdline_argv[i]); + if (!argv_i) { + fprintf(fp, "%s ", ff->ph->env.cmdline_argv[i]); + } else { + char *mem = argv_i; + do { + char *quote = strchr(argv_i, '\''); + if (!quote) + break; + *quote++ = '\0'; + fprintf(fp, "%s\\\'", argv_i); + argv_i = quote; + } while (1); + fprintf(fp, "%s ", argv_i); + free(mem); + } + } fputc('\n', fp); } @@ -3312,8 +3328,6 @@ int perf_session__read_header(struct perf_session *session) lseek(fd, tmp, SEEK_SET); } - symbol_conf.nr_events = nr_attrs; - perf_header__process_sections(header, fd, &session->tevent, perf_file_section__process); @@ -3739,8 +3753,6 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused, perf_evlist__id_add(evlist, evsel, 0, i, event->attr.id[i]); } - symbol_conf.nr_events = evlist->nr_entries; - return 0; } diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 4d602fb..52e8fda 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -410,7 +410,7 @@ static int hist_entry__init(struct hist_entry *he, map__get(he->mem_info->daddr.map); } - if (symbol_conf.use_callchain) + if (hist_entry__has_callchains(he) && symbol_conf.use_callchain) callchain_init(he->callchain); if (he->raw_data) { @@ -492,7 +492,7 @@ static u8 symbol__parent_filter(const struct symbol *parent) static void hist_entry__add_callchain_period(struct hist_entry *he, u64 period) { - if (!symbol_conf.use_callchain) + if (!hist_entry__has_callchains(he) || !symbol_conf.use_callchain) return; he->hists->callchain_period += period; @@ -986,7 +986,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter, iter->he = he; he_cache[iter->curr++] = he; - if (symbol_conf.use_callchain) + if (hist_entry__has_callchains(he) && symbol_conf.use_callchain) callchain_append(he->callchain, &cursor, sample->period); return 0; } @@ -1039,7 +1039,7 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, int err, err2; struct map *alm = NULL; - if (al && al->map) + if (al) alm = map__get(al->map); err = sample__resolve_callchain(iter->sample, &callchain_cursor, &iter->parent, @@ -1373,7 +1373,8 @@ static int hists__hierarchy_insert_entry(struct hists *hists, if (new_he) { new_he->leaf = true; - if (symbol_conf.use_callchain) { + if (hist_entry__has_callchains(new_he) && + symbol_conf.use_callchain) { callchain_cursor_reset(&callchain_cursor); if (callchain_merge(&callchain_cursor, new_he->callchain, @@ -1414,7 +1415,7 @@ static int hists__collapse_insert_entry(struct hists *hists, if (symbol_conf.cumulate_callchain) he_stat__add_stat(iter->stat_acc, he->stat_acc); - if (symbol_conf.use_callchain) { + if (hist_entry__has_callchains(he) && symbol_conf.use_callchain) { callchain_cursor_reset(&callchain_cursor); if (callchain_merge(&callchain_cursor, iter->callchain, @@ -1757,7 +1758,7 @@ void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *pro bool use_callchain; if (evsel && symbol_conf.use_callchain && !symbol_conf.show_ref_callgraph) - use_callchain = evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN; + use_callchain = evsel__has_callchain(evsel); else use_callchain = symbol_conf.use_callchain; diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index fbabfd8..06607c4 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -220,6 +220,12 @@ static inline struct hists *evsel__hists(struct perf_evsel *evsel) return &hevsel->hists; } +static __pure inline bool hists__has_callchains(struct hists *hists) +{ + const struct perf_evsel *evsel = hists_to_evsel(hists); + return evsel__has_callchain(evsel); +} + int hists__init(void); int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list); @@ -419,19 +425,24 @@ struct hist_browser_timer { int refresh; }; +struct annotation_options; + #ifdef HAVE_SLANG_SUPPORT #include "../ui/keysyms.h" int map_symbol__tui_annotate(struct map_symbol *ms, struct perf_evsel *evsel, - struct hist_browser_timer *hbt); + struct hist_browser_timer *hbt, + struct annotation_options *annotation_opts); int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel, - struct hist_browser_timer *hbt); + struct hist_browser_timer *hbt, + struct annotation_options *annotation_opts); int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, struct hist_browser_timer *hbt, float min_pcnt, struct perf_env *env, - bool warn_lost_event); + bool warn_lost_event, + struct annotation_options *annotation_options); int script_browse(const char *script_opt); #else static inline @@ -440,20 +451,23 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused, struct hist_browser_timer *hbt __maybe_unused, float min_pcnt __maybe_unused, struct perf_env *env __maybe_unused, - bool warn_lost_event __maybe_unused) + bool warn_lost_event __maybe_unused, + struct annotation_options *annotation_options __maybe_unused) { return 0; } static inline int map_symbol__tui_annotate(struct map_symbol *ms __maybe_unused, struct perf_evsel *evsel __maybe_unused, - struct hist_browser_timer *hbt __maybe_unused) + struct hist_browser_timer *hbt __maybe_unused, + struct annotation_options *annotation_options __maybe_unused) { return 0; } static inline int hist_entry__tui_annotate(struct hist_entry *he __maybe_unused, struct perf_evsel *evsel __maybe_unused, - struct hist_browser_timer *hbt __maybe_unused) + struct hist_browser_timer *hbt __maybe_unused, + struct annotation_options *annotation_opts __maybe_unused) { return 0; } diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c index 72db274..7f0c83b 100644 --- a/tools/perf/util/intel-bts.c +++ b/tools/perf/util/intel-bts.c @@ -335,8 +335,7 @@ static int intel_bts_get_next_insn(struct intel_bts_queue *btsq, u64 ip) if (!thread) return -1; - thread__find_addr_map(thread, cpumode, MAP__FUNCTION, ip, &al); - if (!al.map || !al.map->dso) + if (!thread__find_map(thread, cpumode, ip, &al) || !al.map->dso) goto out_put; len = dso__data_read_addr(al.map->dso, al.map, machine, ip, buf, diff --git a/tools/perf/util/intel-pt-decoder/insn.h b/tools/perf/util/intel-pt-decoder/insn.h index e23578c..2669c9f 100644 --- a/tools/perf/util/intel-pt-decoder/insn.h +++ b/tools/perf/util/intel-pt-decoder/insn.h @@ -208,4 +208,22 @@ static inline int insn_offset_immediate(struct insn *insn) return insn_offset_displacement(insn) + insn->displacement.nbytes; } +#define POP_SS_OPCODE 0x1f +#define MOV_SREG_OPCODE 0x8e + +/* + * Intel SDM Vol.3A 6.8.3 states; + * "Any single-step trap that would be delivered following the MOV to SS + * instruction or POP to SS instruction (because EFLAGS.TF is 1) is + * suppressed." + * This function returns true if @insn is MOV SS or POP SS. On these + * instructions, single stepping is suppressed. + */ +static inline int insn_masking_exception(struct insn *insn) +{ + return insn->opcode.bytes[0] == POP_SS_OPCODE || + (insn->opcode.bytes[0] == MOV_SREG_OPCODE && + X86_MODRM_REG(insn->modrm.bytes[0]) == 2); +} + #endif /* _ASM_X86_INSN_H */ 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 f9157ae..d404bed 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -113,6 +113,7 @@ struct intel_pt_decoder { bool have_cyc; bool fixup_last_mtc; bool have_last_ip; + enum intel_pt_param_flags flags; uint64_t pos; uint64_t last_ip; uint64_t ip; @@ -226,6 +227,8 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params) decoder->return_compression = params->return_compression; decoder->branch_enable = params->branch_enable; + decoder->flags = params->flags; + decoder->period = params->period; decoder->period_type = params->period_type; @@ -1097,6 +1100,15 @@ static bool intel_pt_fup_event(struct intel_pt_decoder *decoder) return ret; } +static inline bool intel_pt_fup_with_nlip(struct intel_pt_decoder *decoder, + struct intel_pt_insn *intel_pt_insn, + uint64_t ip, int err) +{ + return decoder->flags & INTEL_PT_FUP_WITH_NLIP && !err && + intel_pt_insn->branch == INTEL_PT_BR_INDIRECT && + ip == decoder->ip + intel_pt_insn->length; +} + static int intel_pt_walk_fup(struct intel_pt_decoder *decoder) { struct intel_pt_insn intel_pt_insn; @@ -1109,10 +1121,11 @@ static int intel_pt_walk_fup(struct intel_pt_decoder *decoder) err = intel_pt_walk_insn(decoder, &intel_pt_insn, ip); if (err == INTEL_PT_RETURN) return 0; - if (err == -EAGAIN) { + if (err == -EAGAIN || + intel_pt_fup_with_nlip(decoder, &intel_pt_insn, ip, err)) { if (intel_pt_fup_event(decoder)) return 0; - return err; + return -EAGAIN; } decoder->set_fup_tx_flags = false; if (err) @@ -1376,7 +1389,6 @@ static int intel_pt_overflow(struct intel_pt_decoder *decoder) { intel_pt_log("ERROR: Buffer overflow\n"); intel_pt_clear_tx_flags(decoder); - decoder->have_tma = false; decoder->cbr = 0; decoder->timestamp_insn_cnt = 0; decoder->pkt_state = INTEL_PT_STATE_ERR_RESYNC; @@ -1604,7 +1616,6 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder) case INTEL_PT_PSB: case INTEL_PT_TSC: case INTEL_PT_TMA: - case INTEL_PT_CBR: case INTEL_PT_MODE_TSX: case INTEL_PT_BAD: case INTEL_PT_PSBEND: @@ -1620,6 +1631,10 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder) decoder->pkt_step = 0; return -ENOENT; + case INTEL_PT_CBR: + intel_pt_calc_cbr(decoder); + break; + case INTEL_PT_OVF: return intel_pt_overflow(decoder); diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h index fc1752d..51c18d6 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h @@ -60,6 +60,14 @@ enum { INTEL_PT_ERR_MAX, }; +enum intel_pt_param_flags { + /* + * FUP packet can contain next linear instruction pointer instead of + * current linear instruction pointer. + */ + INTEL_PT_FUP_WITH_NLIP = 1 << 0, +}; + struct intel_pt_state { enum intel_pt_sample_type type; int err; @@ -106,6 +114,7 @@ struct intel_pt_params { unsigned int mtc_period; uint32_t tsc_ctc_ratio_n; uint32_t tsc_ctc_ratio_d; + enum intel_pt_param_flags flags; }; struct intel_pt_decoder; diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 0effaff..aec6890 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -442,8 +442,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn, } while (1) { - thread__find_addr_map(thread, cpumode, MAP__FUNCTION, *ip, &al); - if (!al.map || !al.map->dso) + if (!thread__find_map(thread, cpumode, *ip, &al) || !al.map->dso) return -EINVAL; if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR && @@ -596,8 +595,7 @@ static int __intel_pt_pgd_ip(uint64_t ip, void *data) if (!thread) return -EINVAL; - thread__find_addr_map(thread, cpumode, MAP__FUNCTION, ip, &al); - if (!al.map || !al.map->dso) + if (!thread__find_map(thread, cpumode, ip, &al) || !al.map->dso) return -EINVAL; offset = al.map->map_ip(al.map, ip); @@ -751,6 +749,7 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt, unsigned int queue_nr) { struct intel_pt_params params = { .get_trace = 0, }; + struct perf_env *env = pt->machine->env; struct intel_pt_queue *ptq; ptq = zalloc(sizeof(struct intel_pt_queue)); @@ -832,6 +831,9 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt, } } + if (env->cpuid && !strncmp(env->cpuid, "GenuineIntel,6,92,", 18)) + params.flags |= INTEL_PT_FUP_WITH_NLIP; + ptq->decoder = intel_pt_decoder_new(¶ms); if (!ptq->decoder) goto out_free; @@ -1523,6 +1525,7 @@ static int intel_pt_sample(struct intel_pt_queue *ptq) if (intel_pt_is_switch_ip(ptq, state->to_ip)) { switch (ptq->switch_state) { + case INTEL_PT_SS_NOT_TRACING: case INTEL_PT_SS_UNKNOWN: case INTEL_PT_SS_EXPECTING_SWITCH_IP: err = intel_pt_next_tid(pt, ptq); @@ -1565,7 +1568,7 @@ static u64 intel_pt_switch_ip(struct intel_pt *pt, u64 *ptss_ip) if (map__load(map)) return 0; - start = dso__first_symbol(map->dso, MAP__FUNCTION); + start = dso__first_symbol(map->dso); for (sym = start; sym; sym = dso__next_symbol(sym)) { if (sym->binding == STB_GLOBAL && diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c index 1cca0a2..976e658 100644 --- a/tools/perf/util/llvm-utils.c +++ b/tools/perf/util/llvm-utils.c @@ -14,11 +14,12 @@ #include "config.h" #include "util.h" #include <sys/wait.h> +#include <subcmd/exec-cmd.h> #define CLANG_BPF_CMD_DEFAULT_TEMPLATE \ "$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\ "-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE " \ - "$CLANG_OPTIONS $KERNEL_INC_OPTIONS " \ + "$CLANG_OPTIONS $KERNEL_INC_OPTIONS $PERF_BPF_INC_OPTIONS " \ "-Wno-unused-value -Wno-pointer-sign " \ "-working-directory $WORKING_DIR " \ "-c \"$CLANG_SOURCE\" -target bpf -O2 -o -" @@ -212,7 +213,7 @@ version_notice(void) " \t\thttp://llvm.org/apt\n\n" " \tIf you are using old version of clang, change 'clang-bpf-cmd-template'\n" " \toption in [llvm] section of ~/.perfconfig to:\n\n" -" \t \"$CLANG_EXEC $CLANG_OPTIONS $KERNEL_INC_OPTIONS \\\n" +" \t \"$CLANG_EXEC $CLANG_OPTIONS $KERNEL_INC_OPTIONS $PERF_BPF_INC_OPTIONS \\\n" " \t -working-directory $WORKING_DIR -c $CLANG_SOURCE \\\n" " \t -emit-llvm -o - | /path/to/llc -march=bpf -filetype=obj -o -\"\n" " \t(Replace /path/to/llc with path to your llc)\n\n" @@ -431,9 +432,11 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf, const char *clang_opt = llvm_param.clang_opt; char clang_path[PATH_MAX], abspath[PATH_MAX], nr_cpus_avail_str[64]; char serr[STRERR_BUFSIZE]; - char *kbuild_dir = NULL, *kbuild_include_opts = NULL; + char *kbuild_dir = NULL, *kbuild_include_opts = NULL, + *perf_bpf_include_opts = NULL; const char *template = llvm_param.clang_bpf_cmd_template; - char *command_echo, *command_out; + char *command_echo = NULL, *command_out; + char *perf_include_dir = system_path(PERF_INCLUDE_DIR); if (path[0] != '-' && realpath(path, abspath) == NULL) { err = errno; @@ -471,12 +474,14 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf, snprintf(linux_version_code_str, sizeof(linux_version_code_str), "0x%x", kernel_version); - + if (asprintf(&perf_bpf_include_opts, "-I%s/bpf", perf_include_dir) < 0) + goto errout; force_set_env("NR_CPUS", nr_cpus_avail_str); force_set_env("LINUX_VERSION_CODE", linux_version_code_str); force_set_env("CLANG_EXEC", clang_path); force_set_env("CLANG_OPTIONS", clang_opt); force_set_env("KERNEL_INC_OPTIONS", kbuild_include_opts); + force_set_env("PERF_BPF_INC_OPTIONS", perf_bpf_include_opts); force_set_env("WORKING_DIR", kbuild_dir ? : "."); /* @@ -512,6 +517,8 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf, free(command_out); free(kbuild_dir); free(kbuild_include_opts); + free(perf_bpf_include_opts); + free(perf_include_dir); if (!p_obj_buf) free(obj_buf); @@ -526,6 +533,8 @@ errout: free(kbuild_dir); free(kbuild_include_opts); free(obj_buf); + free(perf_bpf_include_opts); + free(perf_include_dir); if (p_obj_buf) *p_obj_buf = NULL; if (p_obj_buf_sz) diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 32d5049..e7b4a8b 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -24,6 +24,7 @@ #include "sane_ctype.h" #include <symbol/kallsyms.h> +#include <linux/mman.h> static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock); @@ -81,8 +82,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid) machine->kptr_restrict_warned = false; machine->comm_exec = false; machine->kernel_start = 0; - - memset(machine->vmlinux_maps, 0, sizeof(machine->vmlinux_maps)); + machine->vmlinux_map = NULL; machine->root_dir = strdup(root_dir); if (machine->root_dir == NULL) @@ -137,13 +137,11 @@ struct machine *machine__new_kallsyms(void) struct machine *machine = machine__new_host(); /* * FIXME: - * 1) MAP__FUNCTION will go away when we stop loading separate maps for - * functions and data objects. - * 2) We should switch to machine__load_kallsyms(), i.e. not explicitely + * 1) We should switch to machine__load_kallsyms(), i.e. not explicitely * ask for not using the kcore parsing code, once this one is fixed * to create a map per module. */ - if (machine && machine__load_kallsyms(machine, "/proc/kallsyms", MAP__FUNCTION) <= 0) { + if (machine && machine__load_kallsyms(machine, "/proc/kallsyms") <= 0) { machine__delete(machine); machine = NULL; } @@ -673,8 +671,7 @@ struct map *machine__findnew_module_map(struct machine *machine, u64 start, if (kmod_path__parse_name(&m, filename)) return NULL; - map = map_groups__find_by_name(&machine->kmaps, MAP__FUNCTION, - m.name); + map = map_groups__find_by_name(&machine->kmaps, m.name); if (map) { /* * If the map's dso is an offline module, give dso__load() @@ -689,7 +686,7 @@ struct map *machine__findnew_module_map(struct machine *machine, u64 start, if (dso == NULL) goto out; - map = map__new2(start, dso, MAP__FUNCTION); + map = map__new2(start, dso); if (map == NULL) goto out; @@ -810,8 +807,8 @@ struct process_args { u64 start; }; -static void machine__get_kallsyms_filename(struct machine *machine, char *buf, - size_t bufsz) +void machine__get_kallsyms_filename(struct machine *machine, char *buf, + size_t bufsz) { if (machine__is_default_guest(machine)) scnprintf(buf, bufsz, "%s", symbol_conf.default_guest_kallsyms); @@ -854,65 +851,171 @@ static int machine__get_running_kernel_start(struct machine *machine, return 0; } +int machine__create_extra_kernel_map(struct machine *machine, + struct dso *kernel, + struct extra_kernel_map *xm) +{ + struct kmap *kmap; + struct map *map; + + map = map__new2(xm->start, kernel); + if (!map) + return -1; + + map->end = xm->end; + map->pgoff = xm->pgoff; + + kmap = map__kmap(map); + + kmap->kmaps = &machine->kmaps; + strlcpy(kmap->name, xm->name, KMAP_NAME_LEN); + + map_groups__insert(&machine->kmaps, map); + + pr_debug2("Added extra kernel map %s %" PRIx64 "-%" PRIx64 "\n", + kmap->name, map->start, map->end); + + map__put(map); + + return 0; +} + +static u64 find_entry_trampoline(struct dso *dso) +{ + /* Duplicates are removed so lookup all aliases */ + const char *syms[] = { + "_entry_trampoline", + "__entry_trampoline_start", + "entry_SYSCALL_64_trampoline", + }; + struct symbol *sym = dso__first_symbol(dso); + unsigned int i; + + for (; sym; sym = dso__next_symbol(sym)) { + if (sym->binding != STB_GLOBAL) + continue; + for (i = 0; i < ARRAY_SIZE(syms); i++) { + if (!strcmp(sym->name, syms[i])) + return sym->start; + } + } + + return 0; +} + +/* + * These values can be used for kernels that do not have symbols for the entry + * trampolines in kallsyms. + */ +#define X86_64_CPU_ENTRY_AREA_PER_CPU 0xfffffe0000000000ULL +#define X86_64_CPU_ENTRY_AREA_SIZE 0x2c000 +#define X86_64_ENTRY_TRAMPOLINE 0x6000 + +/* Map x86_64 PTI entry trampolines */ +int machine__map_x86_64_entry_trampolines(struct machine *machine, + struct dso *kernel) +{ + struct map_groups *kmaps = &machine->kmaps; + struct maps *maps = &kmaps->maps; + int nr_cpus_avail, cpu; + bool found = false; + struct map *map; + u64 pgoff; + + /* + * In the vmlinux case, pgoff is a virtual address which must now be + * mapped to a vmlinux offset. + */ + for (map = maps__first(maps); map; map = map__next(map)) { + struct kmap *kmap = __map__kmap(map); + struct map *dest_map; + + if (!kmap || !is_entry_trampoline(kmap->name)) + continue; + + dest_map = map_groups__find(kmaps, map->pgoff); + if (dest_map != map) + map->pgoff = dest_map->map_ip(dest_map, map->pgoff); + found = true; + } + if (found || machine->trampolines_mapped) + return 0; + + pgoff = find_entry_trampoline(kernel); + if (!pgoff) + return 0; + + nr_cpus_avail = machine__nr_cpus_avail(machine); + + /* Add a 1 page map for each CPU's entry trampoline */ + for (cpu = 0; cpu < nr_cpus_avail; cpu++) { + u64 va = X86_64_CPU_ENTRY_AREA_PER_CPU + + cpu * X86_64_CPU_ENTRY_AREA_SIZE + + X86_64_ENTRY_TRAMPOLINE; + struct extra_kernel_map xm = { + .start = va, + .end = va + page_size, + .pgoff = pgoff, + }; + + strlcpy(xm.name, ENTRY_TRAMPOLINE_NAME, KMAP_NAME_LEN); + + if (machine__create_extra_kernel_map(machine, kernel, &xm) < 0) + return -1; + } + + machine->trampolines_mapped = nr_cpus_avail; + + return 0; +} + +int __weak machine__create_extra_kernel_maps(struct machine *machine __maybe_unused, + struct dso *kernel __maybe_unused) +{ + return 0; +} + static int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) { - int type; + struct kmap *kmap; + struct map *map; /* In case of renewal the kernel map, destroy previous one */ machine__destroy_kernel_maps(machine); - for (type = 0; type < MAP__NR_TYPES; ++type) { - struct kmap *kmap; - struct map *map; - - machine->vmlinux_maps[type] = map__new2(0, kernel, type); - if (machine->vmlinux_maps[type] == NULL) - return -1; + machine->vmlinux_map = map__new2(0, kernel); + if (machine->vmlinux_map == NULL) + return -1; - machine->vmlinux_maps[type]->map_ip = - machine->vmlinux_maps[type]->unmap_ip = - identity__map_ip; - map = __machine__kernel_map(machine, type); - kmap = map__kmap(map); - if (!kmap) - return -1; + machine->vmlinux_map->map_ip = machine->vmlinux_map->unmap_ip = identity__map_ip; + map = machine__kernel_map(machine); + kmap = map__kmap(map); + if (!kmap) + return -1; - kmap->kmaps = &machine->kmaps; - map_groups__insert(&machine->kmaps, map); - } + kmap->kmaps = &machine->kmaps; + map_groups__insert(&machine->kmaps, map); return 0; } void machine__destroy_kernel_maps(struct machine *machine) { - int type; - - for (type = 0; type < MAP__NR_TYPES; ++type) { - struct kmap *kmap; - struct map *map = __machine__kernel_map(machine, type); - - if (map == NULL) - continue; + struct kmap *kmap; + struct map *map = machine__kernel_map(machine); - kmap = map__kmap(map); - map_groups__remove(&machine->kmaps, map); - if (kmap && kmap->ref_reloc_sym) { - /* - * ref_reloc_sym is shared among all maps, so free just - * on one of them. - */ - if (type == MAP__FUNCTION) { - zfree((char **)&kmap->ref_reloc_sym->name); - zfree(&kmap->ref_reloc_sym); - } else - kmap->ref_reloc_sym = NULL; - } + if (map == NULL) + return; - map__put(machine->vmlinux_maps[type]); - machine->vmlinux_maps[type] = NULL; + kmap = map__kmap(map); + map_groups__remove(&machine->kmaps, map); + if (kmap && kmap->ref_reloc_sym) { + zfree((char **)&kmap->ref_reloc_sym->name); + zfree(&kmap->ref_reloc_sym); } + + map__zput(machine->vmlinux_map); } int machines__create_guest_kernel_maps(struct machines *machines) @@ -989,32 +1092,31 @@ int machines__create_kernel_maps(struct machines *machines, pid_t pid) return machine__create_kernel_maps(machine); } -int machine__load_kallsyms(struct machine *machine, const char *filename, - enum map_type type) +int machine__load_kallsyms(struct machine *machine, const char *filename) { struct map *map = machine__kernel_map(machine); int ret = __dso__load_kallsyms(map->dso, filename, map, true); if (ret > 0) { - dso__set_loaded(map->dso, type); + dso__set_loaded(map->dso); /* * Since /proc/kallsyms will have multiple sessions for the * kernel, with modules between them, fixup the end of all * sections. */ - __map_groups__fixup_end(&machine->kmaps, type); + map_groups__fixup_end(&machine->kmaps); } return ret; } -int machine__load_vmlinux_path(struct machine *machine, enum map_type type) +int machine__load_vmlinux_path(struct machine *machine) { struct map *map = machine__kernel_map(machine); int ret = dso__load_vmlinux_path(map->dso, map); if (ret > 0) - dso__set_loaded(map->dso, type); + dso__set_loaded(map->dso); return ret; } @@ -1055,10 +1157,9 @@ static bool is_kmod_dso(struct dso *dso) static int map_groups__set_module_path(struct map_groups *mg, const char *path, struct kmod_path *m) { - struct map *map; char *long_name; + struct map *map = map_groups__find_by_name(mg, m->name); - map = map_groups__find_by_name(mg, MAP__FUNCTION, m->name); if (map == NULL) return 0; @@ -1207,19 +1308,14 @@ static int machine__create_modules(struct machine *machine) static void machine__set_kernel_mmap(struct machine *machine, u64 start, u64 end) { - int i; - - for (i = 0; i < MAP__NR_TYPES; i++) { - machine->vmlinux_maps[i]->start = start; - machine->vmlinux_maps[i]->end = end; - - /* - * Be a bit paranoid here, some perf.data file came with - * a zero sized synthesized MMAP event for the kernel. - */ - if (start == 0 && end == 0) - machine->vmlinux_maps[i]->end = ~0ULL; - } + machine->vmlinux_map->start = start; + machine->vmlinux_map->end = end; + /* + * Be a bit paranoid here, some perf.data file came with + * a zero sized synthesized MMAP event for the kernel. + */ + if (start == 0 && end == 0) + machine->vmlinux_map->end = ~0ULL; } int machine__create_kernel_maps(struct machine *machine) @@ -1234,9 +1330,8 @@ int machine__create_kernel_maps(struct machine *machine) return -1; ret = __machine__create_kernel_maps(machine, kernel); - dso__put(kernel); if (ret < 0) - return -1; + goto out_put; if (symbol_conf.use_modules && machine__create_modules(machine) < 0) { if (machine__is_host(machine)) @@ -1249,9 +1344,10 @@ int machine__create_kernel_maps(struct machine *machine) if (!machine__get_running_kernel_start(machine, &name, &addr)) { if (name && - maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name, addr)) { + map__set_kallsyms_ref_reloc_sym(machine->vmlinux_map, name, addr)) { machine__destroy_kernel_maps(machine); - return -1; + ret = -1; + goto out_put; } /* we have a real start address now, so re-order the kmaps */ @@ -1267,12 +1363,16 @@ int machine__create_kernel_maps(struct machine *machine) map__put(map); } + if (machine__create_extra_kernel_maps(machine, kernel)) + pr_debug("Problems creating extra kernel maps, continuing anyway...\n"); + /* update end address of the kernel map using adjacent module address */ map = map__next(machine__kernel_map(machine)); if (map) machine__set_kernel_mmap(machine, addr, map->start); - - return 0; +out_put: + dso__put(kernel); + return ret; } static bool machine__uses_kcore(struct machine *machine) @@ -1287,6 +1387,32 @@ static bool machine__uses_kcore(struct machine *machine) return false; } +static bool perf_event__is_extra_kernel_mmap(struct machine *machine, + union perf_event *event) +{ + return machine__is(machine, "x86_64") && + is_entry_trampoline(event->mmap.filename); +} + +static int machine__process_extra_kernel_map(struct machine *machine, + union perf_event *event) +{ + struct map *kernel_map = machine__kernel_map(machine); + struct dso *kernel = kernel_map ? kernel_map->dso : NULL; + struct extra_kernel_map xm = { + .start = event->mmap.start, + .end = event->mmap.start + event->mmap.len, + .pgoff = event->mmap.pgoff, + }; + + if (kernel == NULL) + return -1; + + strlcpy(xm.name, event->mmap.filename, KMAP_NAME_LEN); + + return machine__create_extra_kernel_map(machine, kernel, &xm); +} + static int machine__process_kernel_mmap_event(struct machine *machine, union perf_event *event) { @@ -1379,9 +1505,9 @@ static int machine__process_kernel_mmap_event(struct machine *machine, * time /proc/sys/kernel/kptr_restrict was non zero. */ if (event->mmap.pgoff != 0) { - maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, - symbol_name, - event->mmap.pgoff); + map__set_kallsyms_ref_reloc_sym(machine->vmlinux_map, + symbol_name, + event->mmap.pgoff); } if (machine__is_default_guest(machine)) { @@ -1390,6 +1516,8 @@ static int machine__process_kernel_mmap_event(struct machine *machine, */ dso__load(kernel, machine__kernel_map(machine)); } + } else if (perf_event__is_extra_kernel_mmap(machine, event)) { + return machine__process_extra_kernel_map(machine, event); } return 0; out_problem: @@ -1402,7 +1530,6 @@ int machine__process_mmap2_event(struct machine *machine, { struct thread *thread; struct map *map; - enum map_type type; int ret = 0; if (dump_trace) @@ -1421,11 +1548,6 @@ int machine__process_mmap2_event(struct machine *machine, if (thread == NULL) goto out_problem; - if (event->header.misc & PERF_RECORD_MISC_MMAP_DATA) - type = MAP__VARIABLE; - else - type = MAP__FUNCTION; - map = map__new(machine, event->mmap2.start, event->mmap2.len, event->mmap2.pgoff, event->mmap2.maj, @@ -1433,7 +1555,7 @@ int machine__process_mmap2_event(struct machine *machine, event->mmap2.ino_generation, event->mmap2.prot, event->mmap2.flags, - event->mmap2.filename, type, thread); + event->mmap2.filename, thread); if (map == NULL) goto out_problem_map; @@ -1460,7 +1582,7 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event { struct thread *thread; struct map *map; - enum map_type type; + u32 prot = 0; int ret = 0; if (dump_trace) @@ -1479,16 +1601,14 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event if (thread == NULL) goto out_problem; - if (event->header.misc & PERF_RECORD_MISC_MMAP_DATA) - type = MAP__VARIABLE; - else - type = MAP__FUNCTION; + if (!(event->header.misc & PERF_RECORD_MISC_MMAP_DATA)) + prot = PROT_EXEC; map = map__new(machine, event->mmap.start, event->mmap.len, event->mmap.pgoff, - 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, prot, 0, event->mmap.filename, - type, thread); + thread); if (map == NULL) goto out_problem_map; @@ -1664,7 +1784,7 @@ static void ip__resolve_ams(struct thread *thread, * Thus, we have to try consecutively until we find a match * or else, the symbol is unknown */ - thread__find_cpumode_addr_location(thread, MAP__FUNCTION, ip, &al); + thread__find_cpumode_addr_location(thread, ip, &al); ams->addr = ip; ams->al_addr = al.addr; @@ -1681,15 +1801,7 @@ static void ip__resolve_data(struct thread *thread, memset(&al, 0, sizeof(al)); - thread__find_addr_location(thread, m, MAP__VARIABLE, addr, &al); - if (al.map == NULL) { - /* - * some shared data regions have execute bit set which puts - * their mapping in the MAP__FUNCTION type array. - * Check there as a fallback option before dropping the sample. - */ - thread__find_addr_location(thread, m, MAP__FUNCTION, addr, &al); - } + thread__find_symbol(thread, m, addr, &al); ams->addr = addr; ams->al_addr = al.addr; @@ -1758,8 +1870,7 @@ static int add_callchain_ip(struct thread *thread, al.filtered = 0; al.sym = NULL; if (!cpumode) { - thread__find_cpumode_addr_location(thread, MAP__FUNCTION, - ip, &al); + thread__find_cpumode_addr_location(thread, ip, &al); } else { if (ip >= PERF_CONTEXT_MAX) { switch (ip) { @@ -1784,8 +1895,7 @@ static int add_callchain_ip(struct thread *thread, } return 0; } - thread__find_addr_location(thread, *cpumode, MAP__FUNCTION, - ip, &al); + thread__find_symbol(thread, *cpumode, ip, &al); } if (al.sym != NULL) { @@ -1810,7 +1920,7 @@ static int add_callchain_ip(struct thread *thread, } srcline = callchain_srcline(al.map, al.sym, al.addr); - return callchain_cursor_append(cursor, al.addr, al.map, al.sym, + return callchain_cursor_append(cursor, ip, al.map, al.sym, branch, flags, nr_loop_iter, iter_cycles, branch_from, srcline); } @@ -2342,6 +2452,20 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid, return 0; } +/* + * Compares the raw arch string. N.B. see instead perf_env__arch() if a + * normalized arch is needed. + */ +bool machine__is(struct machine *machine, const char *arch) +{ + return machine && !strcmp(perf_env__raw_arch(machine->env), arch); +} + +int machine__nr_cpus_avail(struct machine *machine) +{ + return machine ? perf_env__nr_cpus_avail(machine->env) : 0; +} + int machine__get_kernel_start(struct machine *machine) { struct map *map = machine__kernel_map(machine); @@ -2358,7 +2482,12 @@ int machine__get_kernel_start(struct machine *machine) machine->kernel_start = 1ULL << 63; if (map) { err = map__load(map); - if (!err) + /* + * On x86_64, PTI entry trampolines are less than the + * start of kernel text, but still above 2^63. So leave + * kernel_start = 1ULL << 63 for x86_64. + */ + if (!err && !machine__is(machine, "x86_64")) machine->kernel_start = map->start; } return err; @@ -2373,7 +2502,7 @@ char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, ch { struct machine *machine = vmachine; struct map *map; - struct symbol *sym = map_groups__find_symbol(&machine->kmaps, MAP__FUNCTION, *addrp, &map); + struct symbol *sym = machine__find_kernel_symbol(machine, *addrp, &map); if (sym == NULL) return NULL; diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 66cc200..1de7660 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -49,13 +49,14 @@ struct machine { struct perf_env *env; struct dsos dsos; struct map_groups kmaps; - struct map *vmlinux_maps[MAP__NR_TYPES]; + struct map *vmlinux_map; u64 kernel_start; pid_t *current_tid; union { /* Tool specific area */ void *priv; u64 db_id; }; + bool trampolines_mapped; }; static inline struct threads *machine__threads(struct machine *machine, pid_t tid) @@ -64,16 +65,22 @@ static inline struct threads *machine__threads(struct machine *machine, pid_t ti return &machine->threads[(unsigned int)tid % THREADS__TABLE_SIZE]; } +/* + * The main kernel (vmlinux) map + */ static inline -struct map *__machine__kernel_map(struct machine *machine, enum map_type type) +struct map *machine__kernel_map(struct machine *machine) { - return machine->vmlinux_maps[type]; + return machine->vmlinux_map; } +/* + * kernel (the one returned by machine__kernel_map()) plus kernel modules maps + */ static inline -struct map *machine__kernel_map(struct machine *machine) +struct maps *machine__kernel_maps(struct machine *machine) { - return __machine__kernel_map(machine, MAP__FUNCTION); + return &machine->kmaps.maps; } int machine__get_kernel_start(struct machine *machine); @@ -182,6 +189,9 @@ static inline bool machine__is_host(struct machine *machine) return machine ? machine->pid == HOST_KERNEL_ID : false; } +bool machine__is(struct machine *machine, const char *arch); +int machine__nr_cpus_avail(struct machine *machine); + struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid); struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid); @@ -190,44 +200,27 @@ struct dso *machine__findnew_dso(struct machine *machine, const char *filename); size_t machine__fprintf(struct machine *machine, FILE *fp); static inline -struct symbol *machine__find_kernel_symbol(struct machine *machine, - enum map_type type, u64 addr, +struct symbol *machine__find_kernel_symbol(struct machine *machine, u64 addr, struct map **mapp) { - return map_groups__find_symbol(&machine->kmaps, type, addr, mapp); + return map_groups__find_symbol(&machine->kmaps, addr, mapp); } static inline struct symbol *machine__find_kernel_symbol_by_name(struct machine *machine, - enum map_type type, const char *name, + const char *name, struct map **mapp) { - return map_groups__find_symbol_by_name(&machine->kmaps, type, name, mapp); -} - -static inline -struct symbol *machine__find_kernel_function(struct machine *machine, u64 addr, - struct map **mapp) -{ - return machine__find_kernel_symbol(machine, MAP__FUNCTION, addr, - mapp); -} - -static inline -struct symbol *machine__find_kernel_function_by_name(struct machine *machine, - const char *name, - struct map **mapp) -{ - return map_groups__find_function_by_name(&machine->kmaps, name, mapp); + return map_groups__find_symbol_by_name(&machine->kmaps, name, mapp); } struct map *machine__findnew_module_map(struct machine *machine, u64 start, const char *filename); int arch__fix_module_text_start(u64 *start, const char *name); -int machine__load_kallsyms(struct machine *machine, const char *filename, - enum map_type type); -int machine__load_vmlinux_path(struct machine *machine, enum map_type type); +int machine__load_kallsyms(struct machine *machine, const char *filename); + +int machine__load_vmlinux_path(struct machine *machine); size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp, bool (skip)(struct dso *dso, int parm), int parm); @@ -276,4 +269,25 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid, */ char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, char **modp); +void machine__get_kallsyms_filename(struct machine *machine, char *buf, + size_t bufsz); + +int machine__create_extra_kernel_maps(struct machine *machine, + struct dso *kernel); + +/* Kernel-space maps for symbols that are outside the main kernel map and module maps */ +struct extra_kernel_map { + u64 start; + u64 end; + u64 pgoff; + char name[KMAP_NAME_LEN]; +}; + +int machine__create_extra_kernel_map(struct machine *machine, + struct dso *kernel, + struct extra_kernel_map *xm); + +int machine__map_x86_64_entry_trampolines(struct machine *machine, + struct dso *kernel); + #endif /* __PERF_MACHINE_H */ diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 8fe5703..89ac5b5 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -22,11 +22,6 @@ static void __maps__insert(struct maps *maps, struct map *map); -const char *map_type__name[MAP__NR_TYPES] = { - [MAP__FUNCTION] = "Functions", - [MAP__VARIABLE] = "Variables", -}; - static inline int is_anon_memory(const char *filename, u32 flags) { return flags & MAP_HUGETLB || @@ -129,10 +124,8 @@ static inline bool replace_android_lib(const char *filename, char *newfilename) return false; } -void map__init(struct map *map, enum map_type type, - u64 start, u64 end, u64 pgoff, struct dso *dso) +void map__init(struct map *map, u64 start, u64 end, u64 pgoff, struct dso *dso) { - map->type = type; map->start = start; map->end = end; map->pgoff = pgoff; @@ -149,7 +142,7 @@ void map__init(struct map *map, enum map_type type, struct map *map__new(struct machine *machine, u64 start, u64 len, u64 pgoff, u32 d_maj, u32 d_min, u64 ino, u64 ino_gen, u32 prot, u32 flags, char *filename, - enum map_type type, struct thread *thread) + struct thread *thread) { struct map *map = malloc(sizeof(*map)); struct nsinfo *nsi = NULL; @@ -173,7 +166,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, map->flags = flags; nsi = nsinfo__get(thread->nsinfo); - if ((anon || no_dso) && nsi && type == MAP__FUNCTION) { + if ((anon || no_dso) && nsi && (prot & PROT_EXEC)) { snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", nsi->pid); filename = newfilename; @@ -203,7 +196,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, if (dso == NULL) goto out_delete; - map__init(map, type, start, start + len, pgoff, dso); + map__init(map, start, start + len, pgoff, dso); if (anon || no_dso) { map->map_ip = map->unmap_ip = identity__map_ip; @@ -213,8 +206,8 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, * functions still return NULL, and we avoid the * unnecessary map__load warning. */ - if (type != MAP__FUNCTION) - dso__set_loaded(dso, map->type); + if (!(prot & PROT_EXEC)) + dso__set_loaded(dso); } dso->nsinfo = nsi; dso__put(dso); @@ -231,7 +224,7 @@ out_delete: * they are loaded) and for vmlinux, where only after we load all the * symbols we'll know where it starts and ends. */ -struct map *map__new2(u64 start, struct dso *dso, enum map_type type) +struct map *map__new2(u64 start, struct dso *dso) { struct map *map = calloc(1, (sizeof(*map) + (dso->kernel ? sizeof(struct kmap) : 0))); @@ -239,7 +232,7 @@ struct map *map__new2(u64 start, struct dso *dso, enum map_type type) /* * ->end will be filled after we load all the symbols */ - map__init(map, type, start, 0, 0, dso); + map__init(map, start, 0, 0, dso); } return map; @@ -256,7 +249,19 @@ struct map *map__new2(u64 start, struct dso *dso, enum map_type type) */ bool __map__is_kernel(const struct map *map) { - return __machine__kernel_map(map->groups->machine, map->type) == map; + return machine__kernel_map(map->groups->machine) == map; +} + +bool __map__is_extra_kernel_map(const struct map *map) +{ + struct kmap *kmap = __map__kmap((struct map *)map); + + return kmap && kmap->name[0]; +} + +bool map__has_symbols(const struct map *map) +{ + return dso__has_symbols(map->dso); } static void map__exit(struct map *map) @@ -279,7 +284,7 @@ void map__put(struct map *map) void map__fixup_start(struct map *map) { - struct rb_root *symbols = &map->dso->symbols[map->type]; + struct rb_root *symbols = &map->dso->symbols; struct rb_node *nd = rb_first(symbols); if (nd != NULL) { struct symbol *sym = rb_entry(nd, struct symbol, rb_node); @@ -289,7 +294,7 @@ void map__fixup_start(struct map *map) void map__fixup_end(struct map *map) { - struct rb_root *symbols = &map->dso->symbols[map->type]; + struct rb_root *symbols = &map->dso->symbols; struct rb_node *nd = rb_last(symbols); if (nd != NULL) { struct symbol *sym = rb_entry(nd, struct symbol, rb_node); @@ -304,7 +309,7 @@ int map__load(struct map *map) const char *name = map->dso->long_name; int nr; - if (dso__loaded(map->dso, map->type)) + if (dso__loaded(map->dso)) return 0; nr = dso__load(map->dso, map); @@ -348,7 +353,7 @@ struct symbol *map__find_symbol(struct map *map, u64 addr) if (map__load(map) < 0) return NULL; - return dso__find_symbol(map->dso, map->type, addr); + return dso__find_symbol(map->dso, addr); } struct symbol *map__find_symbol_by_name(struct map *map, const char *name) @@ -356,10 +361,10 @@ struct symbol *map__find_symbol_by_name(struct map *map, const char *name) if (map__load(map) < 0) return NULL; - if (!dso__sorted_by_name(map->dso, map->type)) - dso__sort_by_name(map->dso, map->type); + if (!dso__sorted_by_name(map->dso)) + dso__sort_by_name(map->dso); - return dso__find_symbol_by_name(map->dso, map->type, name); + return dso__find_symbol_by_name(map->dso, name); } struct map *map__clone(struct map *from) @@ -410,16 +415,20 @@ size_t map__fprintf_dsoname(struct map *map, FILE *fp) return fprintf(fp, "%s", dsoname); } +char *map__srcline(struct map *map, u64 addr, struct symbol *sym) +{ + if (map == NULL) + return SRCLINE_UNKNOWN; + return get_srcline(map->dso, map__rip_2objdump(map, addr), sym, true, true, addr); +} + int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix, FILE *fp) { - char *srcline; int ret = 0; if (map && map->dso) { - srcline = get_srcline(map->dso, - map__rip_2objdump(map, addr), NULL, - true, true, addr); + char *srcline = map__srcline(map, addr, NULL); if (srcline != SRCLINE_UNKNOWN) ret = fprintf(fp, "%s%s", prefix, srcline); free_srcline(srcline); @@ -440,6 +449,20 @@ int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix, */ u64 map__rip_2objdump(struct map *map, u64 rip) { + struct kmap *kmap = __map__kmap(map); + + /* + * vmlinux does not have program headers for PTI entry trampolines and + * kcore may not either. However the trampoline object code is on the + * main kernel map, so just use that instead. + */ + if (kmap && is_entry_trampoline(kmap->name) && kmap->kmaps && kmap->kmaps->machine) { + struct map *kernel_map = machine__kernel_map(kmap->kmaps->machine); + + if (kernel_map) + map = kernel_map; + } + if (!map->dso->adjust_symbols) return rip; @@ -494,10 +517,7 @@ static void maps__init(struct maps *maps) void map_groups__init(struct map_groups *mg, struct machine *machine) { - int i; - for (i = 0; i < MAP__NR_TYPES; ++i) { - maps__init(&mg->maps[i]); - } + maps__init(&mg->maps); mg->machine = machine; refcount_set(&mg->refcnt, 1); } @@ -525,22 +545,12 @@ static void maps__exit(struct maps *maps) void map_groups__exit(struct map_groups *mg) { - int i; - - for (i = 0; i < MAP__NR_TYPES; ++i) - maps__exit(&mg->maps[i]); + maps__exit(&mg->maps); } bool map_groups__empty(struct map_groups *mg) { - int i; - - for (i = 0; i < MAP__NR_TYPES; ++i) { - if (maps__first(&mg->maps[i])) - return false; - } - - return true; + return !maps__first(&mg->maps); } struct map_groups *map_groups__new(struct machine *machine) @@ -566,10 +576,9 @@ void map_groups__put(struct map_groups *mg) } struct symbol *map_groups__find_symbol(struct map_groups *mg, - enum map_type type, u64 addr, - struct map **mapp) + u64 addr, struct map **mapp) { - struct map *map = map_groups__find(mg, type, addr); + struct map *map = map_groups__find(mg, addr); /* Ensure map is loaded before using map->map_ip */ if (map != NULL && map__load(map) >= 0) { @@ -608,13 +617,10 @@ out: } struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg, - enum map_type type, const char *name, struct map **mapp) { - struct symbol *sym = maps__find_symbol_by_name(&mg->maps[type], name, mapp); - - return sym; + return maps__find_symbol_by_name(&mg->maps, name, mapp); } int map_groups__find_ams(struct addr_map_symbol *ams) @@ -622,8 +628,7 @@ int map_groups__find_ams(struct addr_map_symbol *ams) if (ams->addr < ams->map->start || ams->addr >= ams->map->end) { if (ams->map->groups == NULL) return -1; - ams->map = map_groups__find(ams->map->groups, ams->map->type, - ams->addr); + ams->map = map_groups__find(ams->map->groups, ams->addr); if (ams->map == NULL) return -1; } @@ -646,7 +651,7 @@ static size_t maps__fprintf(struct maps *maps, FILE *fp) printed += fprintf(fp, "Map:"); printed += map__fprintf(pos, fp); if (verbose > 2) { - printed += dso__fprintf(pos->dso, pos->type, fp); + printed += dso__fprintf(pos->dso, fp); printed += fprintf(fp, "--\n"); } } @@ -656,24 +661,14 @@ static size_t maps__fprintf(struct maps *maps, FILE *fp) return printed; } -size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type, - FILE *fp) -{ - size_t printed = fprintf(fp, "%s:\n", map_type__name[type]); - return printed += maps__fprintf(&mg->maps[type], fp); -} - size_t map_groups__fprintf(struct map_groups *mg, FILE *fp) { - size_t printed = 0, i; - for (i = 0; i < MAP__NR_TYPES; ++i) - printed += __map_groups__fprintf_maps(mg, i, fp); - return printed; + return maps__fprintf(&mg->maps, fp); } static void __map_groups__insert(struct map_groups *mg, struct map *map) { - __maps__insert(&mg->maps[map->type], map); + __maps__insert(&mg->maps, map); map->groups = mg; } @@ -758,19 +753,18 @@ out: int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, FILE *fp) { - return maps__fixup_overlappings(&mg->maps[map->type], map, fp); + return maps__fixup_overlappings(&mg->maps, map, fp); } /* * XXX This should not really _copy_ te maps, but refcount them. */ -int map_groups__clone(struct thread *thread, - struct map_groups *parent, enum map_type type) +int map_groups__clone(struct thread *thread, struct map_groups *parent) { struct map_groups *mg = thread->mg; int err = -ENOMEM; struct map *map; - struct maps *maps = &parent->maps[type]; + struct maps *maps = &parent->maps; down_read(&maps->lock); @@ -877,15 +871,22 @@ struct map *map__next(struct map *map) return NULL; } -struct kmap *map__kmap(struct map *map) +struct kmap *__map__kmap(struct map *map) { - if (!map->dso || !map->dso->kernel) { - pr_err("Internal error: map__kmap with a non-kernel map\n"); + if (!map->dso || !map->dso->kernel) return NULL; - } return (struct kmap *)(map + 1); } +struct kmap *map__kmap(struct map *map) +{ + struct kmap *kmap = __map__kmap(map); + + if (!kmap) + pr_err("Internal error: map__kmap with a non-kernel map\n"); + return kmap; +} + struct map_groups *map__kmaps(struct map *map) { struct kmap *kmap = map__kmap(map); diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 0e9bbe0..4cb90f2 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -8,19 +8,11 @@ #include <linux/rbtree.h> #include <pthread.h> #include <stdio.h> +#include <string.h> #include <stdbool.h> #include <linux/types.h> #include "rwsem.h" -enum map_type { - MAP__FUNCTION = 0, - MAP__VARIABLE, -}; - -#define MAP__NR_TYPES (MAP__VARIABLE + 1) - -extern const char *map_type__name[MAP__NR_TYPES]; - struct dso; struct ip_callchain; struct ref_reloc_sym; @@ -35,7 +27,6 @@ struct map { }; u64 start; u64 end; - u8 /* enum map_type */ type; bool erange_warned; u32 priv; u32 prot; @@ -56,9 +47,12 @@ struct map { refcount_t refcnt; }; +#define KMAP_NAME_LEN 256 + struct kmap { struct ref_reloc_sym *ref_reloc_sym; struct map_groups *kmaps; + char name[KMAP_NAME_LEN]; }; struct maps { @@ -67,7 +61,7 @@ struct maps { }; struct map_groups { - struct maps maps[MAP__NR_TYPES]; + struct maps maps; struct machine *machine; refcount_t refcnt; }; @@ -85,6 +79,7 @@ static inline struct map_groups *map_groups__get(struct map_groups *mg) void map_groups__put(struct map_groups *mg); +struct kmap *__map__kmap(struct map *map); struct kmap *map__kmap(struct map *map); struct map_groups *map__kmaps(struct map *map); @@ -125,7 +120,7 @@ struct thread; * Note: caller must ensure map->dso is not NULL (map is loaded). */ #define map__for_each_symbol(map, pos, n) \ - dso__for_each_symbol(map->dso, pos, n, map->type) + dso__for_each_symbol(map->dso, pos, n) /* map__for_each_symbol_with_name - iterate over the symbols in the given map * that have the given name @@ -144,13 +139,13 @@ struct thread; #define map__for_each_symbol_by_name(map, sym_name, pos) \ __map__for_each_symbol_by_name(map, sym_name, (pos)) -void map__init(struct map *map, enum map_type type, +void map__init(struct map *map, u64 start, u64 end, u64 pgoff, struct dso *dso); struct map *map__new(struct machine *machine, u64 start, u64 len, u64 pgoff, u32 d_maj, u32 d_min, u64 ino, u64 ino_gen, u32 prot, u32 flags, - char *filename, enum map_type type, struct thread *thread); -struct map *map__new2(u64 start, struct dso *dso, enum map_type type); + char *filename, struct thread *thread); +struct map *map__new2(u64 start, struct dso *dso); void map__delete(struct map *map); struct map *map__clone(struct map *map); @@ -174,6 +169,7 @@ static inline void __map__zput(struct map **map) int map__overlap(struct map *l, struct map *r); size_t map__fprintf(struct map *map, FILE *fp); size_t map__fprintf_dsoname(struct map *map, FILE *fp); +char *map__srcline(struct map *map, u64 addr, struct symbol *sym); int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix, FILE *fp); @@ -185,8 +181,6 @@ void map__fixup_end(struct map *map); void map__reloc_vmlinux(struct map *map); -size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type, - FILE *fp); void maps__insert(struct maps *maps, struct map *map); void maps__remove(struct maps *maps, struct map *map); struct map *maps__find(struct maps *maps, u64 addr); @@ -197,34 +191,29 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, void map_groups__init(struct map_groups *mg, struct machine *machine); void map_groups__exit(struct map_groups *mg); int map_groups__clone(struct thread *thread, - struct map_groups *parent, enum map_type type); + struct map_groups *parent); size_t map_groups__fprintf(struct map_groups *mg, FILE *fp); -int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name, - u64 addr); +int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name, + u64 addr); static inline void map_groups__insert(struct map_groups *mg, struct map *map) { - maps__insert(&mg->maps[map->type], map); + maps__insert(&mg->maps, map); map->groups = mg; } static inline void map_groups__remove(struct map_groups *mg, struct map *map) { - maps__remove(&mg->maps[map->type], map); + maps__remove(&mg->maps, map); } -static inline struct map *map_groups__find(struct map_groups *mg, - enum map_type type, u64 addr) +static inline struct map *map_groups__find(struct map_groups *mg, u64 addr) { - return maps__find(&mg->maps[type], addr); + return maps__find(&mg->maps, addr); } -static inline struct map *map_groups__first(struct map_groups *mg, - enum map_type type) -{ - return maps__first(&mg->maps[type]); -} +struct map *map_groups__first(struct map_groups *mg); static inline struct map *map_groups__next(struct map *map) { @@ -232,11 +221,9 @@ static inline struct map *map_groups__next(struct map *map) } struct symbol *map_groups__find_symbol(struct map_groups *mg, - enum map_type type, u64 addr, - struct map **mapp); + u64 addr, struct map **mapp); struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg, - enum map_type type, const char *name, struct map **mapp); @@ -244,24 +231,26 @@ struct addr_map_symbol; int map_groups__find_ams(struct addr_map_symbol *ams); -static inline -struct symbol *map_groups__find_function_by_name(struct map_groups *mg, - const char *name, struct map **mapp) -{ - return map_groups__find_symbol_by_name(mg, MAP__FUNCTION, name, mapp); -} - int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, FILE *fp); -struct map *map_groups__find_by_name(struct map_groups *mg, - enum map_type type, const char *name); +struct map *map_groups__find_by_name(struct map_groups *mg, const char *name); bool __map__is_kernel(const struct map *map); +bool __map__is_extra_kernel_map(const struct map *map); static inline bool __map__is_kmodule(const struct map *map) { - return !__map__is_kernel(map); + return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map); +} + +bool map__has_symbols(const struct map *map); + +#define ENTRY_TRAMPOLINE_NAME "__entry_SYSCALL_64_trampoline" + +static inline bool is_entry_trampoline(const char *name) +{ + return !strcmp(name, ENTRY_TRAMPOLINE_NAME); } #endif /* __PERF_MAP_H */ diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index b8b8a95..15eec49 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -156,13 +156,12 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = { (strcmp(sys_dirent->d_name, ".")) && \ (strcmp(sys_dirent->d_name, ".."))) -static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir) +static int tp_event_has_id(const char *dir_path, struct dirent *evt_dir) { char evt_path[MAXPATHLEN]; int fd; - snprintf(evt_path, MAXPATHLEN, "%s/%s/%s/id", tracing_events_path, - sys_dir->d_name, evt_dir->d_name); + snprintf(evt_path, MAXPATHLEN, "%s/%s/id", dir_path, evt_dir->d_name); fd = open(evt_path, O_RDONLY); if (fd < 0) return -EINVAL; @@ -171,12 +170,12 @@ static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir) return 0; } -#define for_each_event(sys_dirent, evt_dir, evt_dirent) \ +#define for_each_event(dir_path, evt_dir, evt_dirent) \ while ((evt_dirent = readdir(evt_dir)) != NULL) \ if (evt_dirent->d_type == DT_DIR && \ (strcmp(evt_dirent->d_name, ".")) && \ (strcmp(evt_dirent->d_name, "..")) && \ - (!tp_event_has_id(sys_dirent, evt_dirent))) + (!tp_event_has_id(dir_path, evt_dirent))) #define MAX_EVENT_LENGTH 512 @@ -190,21 +189,21 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) int fd; u64 id; char evt_path[MAXPATHLEN]; - char dir_path[MAXPATHLEN]; + char *dir_path; - sys_dir = opendir(tracing_events_path); + sys_dir = tracing_events__opendir(); if (!sys_dir) return NULL; for_each_subsystem(sys_dir, sys_dirent) { - - snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path, - sys_dirent->d_name); + dir_path = get_events_file(sys_dirent->d_name); + if (!dir_path) + continue; evt_dir = opendir(dir_path); if (!evt_dir) - continue; + goto next; - for_each_event(sys_dirent, evt_dir, evt_dirent) { + for_each_event(dir_path, evt_dir, evt_dirent) { scnprintf(evt_path, MAXPATHLEN, "%s/%s/id", dir_path, evt_dirent->d_name); @@ -218,6 +217,7 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) close(fd); id = atoll(id_buf); if (id == config) { + put_events_file(dir_path); closedir(evt_dir); closedir(sys_dir); path = zalloc(sizeof(*path)); @@ -242,6 +242,8 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) } } closedir(evt_dir); +next: + put_events_file(dir_path); } closedir(sys_dir); @@ -512,14 +514,19 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx, struct parse_events_error *err, struct list_head *head_config) { - char evt_path[MAXPATHLEN]; + char *evt_path; struct dirent *evt_ent; DIR *evt_dir; int ret = 0, found = 0; - snprintf(evt_path, MAXPATHLEN, "%s/%s", tracing_events_path, sys_name); + evt_path = get_events_file(sys_name); + if (!evt_path) { + tracepoint_error(err, errno, sys_name, evt_name); + return -1; + } evt_dir = opendir(evt_path); if (!evt_dir) { + put_events_file(evt_path); tracepoint_error(err, errno, sys_name, evt_name); return -1; } @@ -545,6 +552,7 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx, ret = -1; } + put_events_file(evt_path); closedir(evt_dir); return ret; } @@ -570,7 +578,7 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx, DIR *events_dir; int ret = 0; - events_dir = opendir(tracing_events_path); + events_dir = tracing_events__opendir(); if (!events_dir) { tracepoint_error(err, errno, sys_name, evt_name); return -1; @@ -1219,13 +1227,16 @@ int parse_events_add_numeric(struct parse_events_state *parse_state, int parse_events_add_pmu(struct parse_events_state *parse_state, struct list_head *list, char *name, - struct list_head *head_config, bool auto_merge_stats) + struct list_head *head_config, + bool auto_merge_stats, + bool use_alias) { struct perf_event_attr attr; struct perf_pmu_info info; struct perf_pmu *pmu; struct perf_evsel *evsel; struct parse_events_error *err = parse_state->error; + bool use_uncore_alias; LIST_HEAD(config_terms); pmu = perf_pmu__find(name); @@ -1244,11 +1255,14 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, memset(&attr, 0, sizeof(attr)); } + use_uncore_alias = (pmu->is_uncore && use_alias); + if (!head_config) { attr.type = pmu->type; evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats); if (evsel) { evsel->pmu_name = name; + evsel->use_uncore_alias = use_uncore_alias; return 0; } else { return -ENOMEM; @@ -1282,6 +1296,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, evsel->metric_expr = info.metric_expr; evsel->metric_name = info.metric_name; evsel->pmu_name = name; + evsel->use_uncore_alias = use_uncore_alias; } return evsel ? 0 : -ENOMEM; @@ -1317,7 +1332,8 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, list_add_tail(&term->list, head); if (!parse_events_add_pmu(parse_state, list, - pmu->name, head, true)) { + pmu->name, head, + true, true)) { pr_debug("%s -> %s/%s/\n", str, pmu->name, alias->str); ok++; @@ -1339,7 +1355,120 @@ int parse_events__modifier_group(struct list_head *list, return parse_events__modifier_event(list, event_mod, true); } -void parse_events__set_leader(char *name, struct list_head *list) +/* + * Check if the two uncore PMUs are from the same uncore block + * The format of the uncore PMU name is uncore_#blockname_#pmuidx + */ +static bool is_same_uncore_block(const char *pmu_name_a, const char *pmu_name_b) +{ + char *end_a, *end_b; + + end_a = strrchr(pmu_name_a, '_'); + end_b = strrchr(pmu_name_b, '_'); + + if (!end_a || !end_b) + return false; + + if ((end_a - pmu_name_a) != (end_b - pmu_name_b)) + return false; + + return (strncmp(pmu_name_a, pmu_name_b, end_a - pmu_name_a) == 0); +} + +static int +parse_events__set_leader_for_uncore_aliase(char *name, struct list_head *list, + struct parse_events_state *parse_state) +{ + struct perf_evsel *evsel, *leader; + uintptr_t *leaders; + bool is_leader = true; + int i, nr_pmu = 0, total_members, ret = 0; + + leader = list_first_entry(list, struct perf_evsel, node); + evsel = list_last_entry(list, struct perf_evsel, node); + total_members = evsel->idx - leader->idx + 1; + + leaders = calloc(total_members, sizeof(uintptr_t)); + if (WARN_ON(!leaders)) + return 0; + + /* + * Going through the whole group and doing sanity check. + * All members must use alias, and be from the same uncore block. + * Also, storing the leader events in an array. + */ + __evlist__for_each_entry(list, evsel) { + + /* Only split the uncore group which members use alias */ + if (!evsel->use_uncore_alias) + goto out; + + /* The events must be from the same uncore block */ + if (!is_same_uncore_block(leader->pmu_name, evsel->pmu_name)) + goto out; + + if (!is_leader) + continue; + /* + * If the event's PMU name starts to repeat, it must be a new + * event. That can be used to distinguish the leader from + * other members, even they have the same event name. + */ + if ((leader != evsel) && (leader->pmu_name == evsel->pmu_name)) { + is_leader = false; + continue; + } + /* The name is always alias name */ + WARN_ON(strcmp(leader->name, evsel->name)); + + /* Store the leader event for each PMU */ + leaders[nr_pmu++] = (uintptr_t) evsel; + } + + /* only one event alias */ + if (nr_pmu == total_members) { + parse_state->nr_groups--; + goto handled; + } + + /* + * An uncore event alias is a joint name which means the same event + * runs on all PMUs of a block. + * Perf doesn't support mixed events from different PMUs in the same + * group. The big group has to be split into multiple small groups + * which only include the events from the same PMU. + * + * Here the uncore event aliases must be from the same uncore block. + * The number of PMUs must be same for each alias. The number of new + * small groups equals to the number of PMUs. + * Setting the leader event for corresponding members in each group. + */ + i = 0; + __evlist__for_each_entry(list, evsel) { + if (i >= nr_pmu) + i = 0; + evsel->leader = (struct perf_evsel *) leaders[i++]; + } + + /* The number of members and group name are same for each group */ + for (i = 0; i < nr_pmu; i++) { + evsel = (struct perf_evsel *) leaders[i]; + evsel->nr_members = total_members / nr_pmu; + evsel->group_name = name ? strdup(name) : NULL; + } + + /* Take the new small groups into account */ + parse_state->nr_groups += nr_pmu - 1; + +handled: + ret = 1; +out: + free(leaders); + return ret; +} + +void parse_events__set_leader(char *name, struct list_head *list, + struct parse_events_state *parse_state) { struct perf_evsel *leader; @@ -1348,6 +1477,9 @@ void parse_events__set_leader(char *name, struct list_head *list) return; } + if (parse_events__set_leader_for_uncore_aliase(name, list, parse_state)) + return; + __perf_evlist__set_leader(list); leader = list_entry(list->next, struct perf_evsel, node); leader->group_name = name ? strdup(name) : NULL; @@ -1968,13 +2100,13 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob, DIR *sys_dir, *evt_dir; struct dirent *sys_dirent, *evt_dirent; char evt_path[MAXPATHLEN]; - char dir_path[MAXPATHLEN]; + char *dir_path; char **evt_list = NULL; unsigned int evt_i = 0, evt_num = 0; bool evt_num_known = false; restart: - sys_dir = opendir(tracing_events_path); + sys_dir = tracing_events__opendir(); if (!sys_dir) return; @@ -1989,13 +2121,14 @@ restart: !strglobmatch(sys_dirent->d_name, subsys_glob)) continue; - snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path, - sys_dirent->d_name); + dir_path = get_events_file(sys_dirent->d_name); + if (!dir_path) + continue; evt_dir = opendir(dir_path); if (!evt_dir) - continue; + goto next; - for_each_event(sys_dirent, evt_dir, evt_dirent) { + for_each_event(dir_path, evt_dir, evt_dirent) { if (event_glob != NULL && !strglobmatch(evt_dirent->d_name, event_glob)) continue; @@ -2009,11 +2142,15 @@ restart: sys_dirent->d_name, evt_dirent->d_name); evt_list[evt_i] = strdup(evt_path); - if (evt_list[evt_i] == NULL) + if (evt_list[evt_i] == NULL) { + put_events_file(dir_path); goto out_close_evt_dir; + } evt_i++; } closedir(evt_dir); +next: + put_events_file(dir_path); } closedir(sys_dir); @@ -2061,21 +2198,21 @@ int is_valid_tracepoint(const char *event_string) DIR *sys_dir, *evt_dir; struct dirent *sys_dirent, *evt_dirent; char evt_path[MAXPATHLEN]; - char dir_path[MAXPATHLEN]; + char *dir_path; - sys_dir = opendir(tracing_events_path); + sys_dir = tracing_events__opendir(); if (!sys_dir) return 0; for_each_subsystem(sys_dir, sys_dirent) { - - snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path, - sys_dirent->d_name); + dir_path = get_events_file(sys_dirent->d_name); + if (!dir_path) + continue; evt_dir = opendir(dir_path); if (!evt_dir) - continue; + goto next; - for_each_event(sys_dirent, evt_dir, evt_dirent) { + for_each_event(dir_path, evt_dir, evt_dirent) { snprintf(evt_path, MAXPATHLEN, "%s:%s", sys_dirent->d_name, evt_dirent->d_name); if (!strcmp(evt_path, event_string)) { @@ -2085,6 +2222,8 @@ int is_valid_tracepoint(const char *event_string) } } closedir(evt_dir); +next: + put_events_file(dir_path); } closedir(sys_dir); return 0; diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 5015cfd..4473dac 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -167,7 +167,9 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx, void *ptr, char *type, u64 len); int parse_events_add_pmu(struct parse_events_state *parse_state, struct list_head *list, char *name, - struct list_head *head_config, bool auto_merge_stats); + struct list_head *head_config, + bool auto_merge_stats, + bool use_alias); int parse_events_multi_pmu_add(struct parse_events_state *parse_state, char *str, @@ -178,7 +180,8 @@ int parse_events_copy_term_list(struct list_head *old, enum perf_pmu_event_symbol_type perf_pmu__parse_check(const char *name); -void parse_events__set_leader(char *name, struct list_head *list); +void parse_events__set_leader(char *name, struct list_head *list, + struct parse_events_state *parse_state); void parse_events_update_lists(struct list_head *list_event, struct list_head *list_all); void parse_events_evlist_error(struct parse_events_state *parse_state, diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index a1a01b1..5f761f3 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -53,7 +53,21 @@ static int str(yyscan_t scanner, int token) YYSTYPE *yylval = parse_events_get_lval(scanner); char *text = parse_events_get_text(scanner); - yylval->str = strdup(text); + if (text[0] != '\'') { + yylval->str = strdup(text); + } else { + /* + * If a text tag specified on the command line + * contains opening single quite ' then it is + * expected that the tag ends with single quote + * as well, like this: + * name=\'CPU_CLK_UNHALTED.THREAD:cmask=1\' + * quotes need to be escaped to bypass shell + * processing. + */ + yylval->str = strndup(&text[1], strlen(text) - 2); + } + return token; } @@ -176,6 +190,7 @@ num_dec [0-9]+ num_hex 0x[a-fA-F0-9]+ num_raw_hex [a-fA-F0-9]+ name [a-zA-Z_*?\[\]][a-zA-Z0-9_*?.\[\]]* +name_tag [\'][a-zA-Z_*?\[\]][a-zA-Z0-9_*?\-,\.\[\]:=]*[\'] name_minus [a-zA-Z_*?][a-zA-Z0-9\-_*?.:]* drv_cfg_term [a-zA-Z0-9_\.]+(=[a-zA-Z0-9_*?\.:]+)? /* If you add a modifier you need to update check_modifier() */ @@ -344,6 +359,7 @@ r{num_raw_hex} { return raw(yyscanner); } {bpf_object} { if (!isbpf(yyscanner)) { USER_REJECT }; return str(yyscanner, PE_BPF_OBJECT); } {bpf_source} { if (!isbpf(yyscanner)) { USER_REJECT }; return str(yyscanner, PE_BPF_SOURCE); } {name} { return pmu_str_check(yyscanner); } +{name_tag} { return str(yyscanner, PE_NAME); } "/" { BEGIN(config); return '/'; } - { return '-'; } , { BEGIN(event); return ','; } diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 7afeb80..155d257 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -73,6 +73,7 @@ static void inc_group_count(struct list_head *list, %type <num> value_sym %type <head> event_config %type <head> opt_event_config +%type <head> opt_pmu_config %type <term> event_term %type <head> event_pmu %type <head> event_legacy_symbol @@ -161,7 +162,7 @@ PE_NAME '{' events '}' struct list_head *list = $3; inc_group_count(list, _parse_state); - parse_events__set_leader($1, list); + parse_events__set_leader($1, list, _parse_state); $$ = list; } | @@ -170,7 +171,7 @@ PE_NAME '{' events '}' struct list_head *list = $2; inc_group_count(list, _parse_state); - parse_events__set_leader(NULL, list); + parse_events__set_leader(NULL, list, _parse_state); $$ = list; } @@ -224,7 +225,7 @@ event_def: event_pmu | event_bpf_file event_pmu: -PE_NAME opt_event_config +PE_NAME opt_pmu_config { struct list_head *list, *orig_terms, *terms; @@ -232,7 +233,7 @@ PE_NAME opt_event_config YYABORT; ALLOC_LIST(list); - if (parse_events_add_pmu(_parse_state, list, $1, $2, false)) { + if (parse_events_add_pmu(_parse_state, list, $1, $2, false, false)) { struct perf_pmu *pmu = NULL; int ok = 0; char *pattern; @@ -251,7 +252,7 @@ PE_NAME opt_event_config free(pattern); YYABORT; } - if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms, true)) + if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms, true, false)) ok++; parse_events_terms__delete(terms); } @@ -496,6 +497,17 @@ opt_event_config: $$ = NULL; } +opt_pmu_config: +'/' event_config '/' +{ + $$ = $2; +} +| +'/' '/' +{ + $$ = NULL; +} + start_terms: event_config { struct parse_events_state *parse_state = _parse_state; diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index e1dbc98..f119eb6 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -111,17 +111,6 @@ void exit_probe_symbol_maps(void) symbol__exit(); } -static struct symbol *__find_kernel_function_by_name(const char *name, - struct map **mapp) -{ - return machine__find_kernel_function_by_name(host_machine, name, mapp); -} - -static struct symbol *__find_kernel_function(u64 addr, struct map **mapp) -{ - return machine__find_kernel_function(host_machine, addr, mapp); -} - static struct ref_reloc_sym *kernel_get_ref_reloc_sym(void) { /* kmap->ref_reloc_sym should be set if host_machine is initialized */ @@ -149,7 +138,7 @@ static int kernel_get_symbol_address_by_name(const char *name, u64 *addr, if (reloc_sym && strcmp(name, reloc_sym->name) == 0) *addr = (reloc) ? reloc_sym->addr : reloc_sym->unrelocated_addr; else { - sym = __find_kernel_function_by_name(name, &map); + sym = machine__find_kernel_symbol_by_name(host_machine, name, &map); if (!sym) return -ENOENT; *addr = map->unmap_ip(map, sym->start) - @@ -161,8 +150,7 @@ static int kernel_get_symbol_address_by_name(const char *name, u64 *addr, static struct map *kernel_get_module_map(const char *module) { - struct map_groups *grp = &host_machine->kmaps; - struct maps *maps = &grp->maps[MAP__FUNCTION]; + struct maps *maps = machine__kernel_maps(host_machine); struct map *pos; /* A file path -- this is an offline module */ @@ -177,8 +165,7 @@ static struct map *kernel_get_module_map(const char *module) if (strncmp(pos->dso->short_name + 1, module, pos->dso->short_name_len - 2) == 0 && module[pos->dso->short_name_len - 2] == '\0') { - map__get(pos); - return pos; + return map__get(pos); } } return NULL; @@ -341,7 +328,7 @@ static int kernel_get_module_dso(const char *module, struct dso **pdso) char module_name[128]; snprintf(module_name, sizeof(module_name), "[%s]", module); - map = map_groups__find_by_name(&host_machine->kmaps, MAP__FUNCTION, module_name); + map = map_groups__find_by_name(&host_machine->kmaps, module_name); if (map) { dso = map->dso; goto found; @@ -2098,7 +2085,7 @@ static int find_perf_probe_point_from_map(struct probe_trace_point *tp, } if (addr) { addr += tp->offset; - sym = __find_kernel_function(addr, &map); + sym = machine__find_kernel_symbol(host_machine, addr, &map); } } @@ -3504,19 +3491,18 @@ int show_available_funcs(const char *target, struct nsinfo *nsi, (target) ? : "kernel"); goto end; } - if (!dso__sorted_by_name(map->dso, map->type)) - dso__sort_by_name(map->dso, map->type); + if (!dso__sorted_by_name(map->dso)) + dso__sort_by_name(map->dso); /* Show all (filtered) symbols */ setup_pager(); - for (nd = rb_first(&map->dso->symbol_names[map->type]); nd; nd = rb_next(nd)) { + for (nd = rb_first(&map->dso->symbol_names); nd; nd = rb_next(nd)) { struct symbol_name_rb_node *pos = rb_entry(nd, struct symbol_name_rb_node, rb_node); if (strfilter__compare(_filter, pos->sym.name)) printf("%s\n", pos->sym.name); - } - + } end: map__put(map); exit_probe_symbol_maps(); diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index 4ae1123..b76088f 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -84,8 +84,7 @@ int open_trace_file(const char *trace_file, bool readwrite) char buf[PATH_MAX]; int ret; - ret = e_snprintf(buf, PATH_MAX, "%s/%s", - tracing_path, trace_file); + ret = e_snprintf(buf, PATH_MAX, "%s/%s", tracing_path_mount(), trace_file); if (ret >= 0) { pr_debug("Opening %s write=%d\n", buf, readwrite); if (readwrite && !probe_event_dry_run) diff --git a/tools/perf/util/quote.c b/tools/perf/util/quote.c deleted file mode 100644 index 22eaa20..0000000 --- a/tools/perf/util/quote.c +++ /dev/null @@ -1,62 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <errno.h> -#include <stdlib.h> -#include "strbuf.h" -#include "quote.h" -#include "util.h" - -/* Help to copy the thing properly quoted for the shell safety. - * any single quote is replaced with '\'', any exclamation point - * is replaced with '\!', and the whole thing is enclosed in a - * - * E.g. - * original sq_quote result - * name ==> name ==> 'name' - * a b ==> a b ==> 'a b' - * a'b ==> a'\''b ==> 'a'\''b' - * a!b ==> a'\!'b ==> 'a'\!'b' - */ -static inline int need_bs_quote(char c) -{ - return (c == '\'' || c == '!'); -} - -static int sq_quote_buf(struct strbuf *dst, const char *src) -{ - char *to_free = NULL; - int ret; - - if (dst->buf == src) - to_free = strbuf_detach(dst, NULL); - - ret = strbuf_addch(dst, '\''); - while (!ret && *src) { - size_t len = strcspn(src, "'!"); - ret = strbuf_add(dst, src, len); - src += len; - while (!ret && need_bs_quote(*src)) - ret = strbuf_addf(dst, "'\\%c\'", *src++); - } - if (!ret) - ret = strbuf_addch(dst, '\''); - free(to_free); - - return ret; -} - -int sq_quote_argv(struct strbuf *dst, const char** argv, size_t maxlen) -{ - int i, ret; - - /* Copy into destination buffer. */ - ret = strbuf_grow(dst, 255); - for (i = 0; !ret && argv[i]; ++i) { - ret = strbuf_addch(dst, ' '); - if (ret) - break; - ret = sq_quote_buf(dst, argv[i]); - if (maxlen && dst->len > maxlen) - return -ENOSPC; - } - return ret; -} diff --git a/tools/perf/util/quote.h b/tools/perf/util/quote.h deleted file mode 100644 index 274bf26..0000000 --- a/tools/perf/util/quote.h +++ /dev/null @@ -1,31 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __PERF_QUOTE_H -#define __PERF_QUOTE_H - -#include <stddef.h> - -/* Help to copy the thing properly quoted for the shell safety. - * any single quote is replaced with '\'', any exclamation point - * is replaced with '\!', and the whole thing is enclosed in a - * single quote pair. - * - * For example, if you are passing the result to system() as an - * argument: - * - * sprintf(cmd, "foobar %s %s", sq_quote(arg0), sq_quote(arg1)) - * - * would be appropriate. If the system() is going to call ssh to - * run the command on the other side: - * - * sprintf(cmd, "git-diff-tree %s %s", sq_quote(arg0), sq_quote(arg1)); - * sprintf(rcmd, "ssh %s %s", sq_util/quote.host), sq_quote(cmd)); - * - * Note that the above examples leak memory! Remember to free result from - * sq_quote() in a real application. - */ - -struct strbuf; - -int sq_quote_argv(struct strbuf *, const char **argv, size_t maxlen); - -#endif /* __PERF_QUOTE_H */ diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 10dd5fc..46e9e19 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -48,6 +48,7 @@ #include "cpumap.h" #include "print_binary.h" #include "stat.h" +#include "mem-events.h" #if PY_MAJOR_VERSION < 3 #define _PyUnicode_FromString(arg) \ @@ -372,6 +373,19 @@ static PyObject *get_field_numeric_entry(struct event_format *event, return obj; } +static const char *get_dsoname(struct map *map) +{ + const char *dsoname = "[unknown]"; + + if (map && map->dso) { + if (symbol_conf.show_kernel_path && map->dso->long_name) + dsoname = map->dso->long_name; + else + dsoname = map->dso->name; + } + + return dsoname; +} static PyObject *python_process_callchain(struct perf_sample *sample, struct perf_evsel *evsel, @@ -427,14 +441,8 @@ static PyObject *python_process_callchain(struct perf_sample *sample, } if (node->map) { - struct map *map = node->map; - const char *dsoname = "[unknown]"; - if (map && map->dso) { - if (symbol_conf.show_kernel_path && map->dso->long_name) - dsoname = map->dso->long_name; - else - dsoname = map->dso->name; - } + const char *dsoname = get_dsoname(node->map); + pydict_set_item_string_decref(pyelem, "dso", _PyUnicode_FromString(dsoname)); } @@ -448,6 +456,166 @@ exit: return pylist; } +static PyObject *python_process_brstack(struct perf_sample *sample, + struct thread *thread) +{ + struct branch_stack *br = sample->branch_stack; + PyObject *pylist; + u64 i; + + pylist = PyList_New(0); + if (!pylist) + Py_FatalError("couldn't create Python list"); + + if (!(br && br->nr)) + goto exit; + + for (i = 0; i < br->nr; i++) { + PyObject *pyelem; + struct addr_location al; + const char *dsoname; + + pyelem = PyDict_New(); + if (!pyelem) + Py_FatalError("couldn't create Python dictionary"); + + pydict_set_item_string_decref(pyelem, "from", + PyLong_FromUnsignedLongLong(br->entries[i].from)); + pydict_set_item_string_decref(pyelem, "to", + PyLong_FromUnsignedLongLong(br->entries[i].to)); + pydict_set_item_string_decref(pyelem, "mispred", + PyBool_FromLong(br->entries[i].flags.mispred)); + pydict_set_item_string_decref(pyelem, "predicted", + PyBool_FromLong(br->entries[i].flags.predicted)); + pydict_set_item_string_decref(pyelem, "in_tx", + PyBool_FromLong(br->entries[i].flags.in_tx)); + pydict_set_item_string_decref(pyelem, "abort", + PyBool_FromLong(br->entries[i].flags.abort)); + pydict_set_item_string_decref(pyelem, "cycles", + PyLong_FromUnsignedLongLong(br->entries[i].flags.cycles)); + + thread__find_map(thread, sample->cpumode, + br->entries[i].from, &al); + dsoname = get_dsoname(al.map); + pydict_set_item_string_decref(pyelem, "from_dsoname", + _PyUnicode_FromString(dsoname)); + + thread__find_map(thread, sample->cpumode, + br->entries[i].to, &al); + dsoname = get_dsoname(al.map); + pydict_set_item_string_decref(pyelem, "to_dsoname", + _PyUnicode_FromString(dsoname)); + + PyList_Append(pylist, pyelem); + Py_DECREF(pyelem); + } + +exit: + return pylist; +} + +static unsigned long get_offset(struct symbol *sym, struct addr_location *al) +{ + unsigned long offset; + + if (al->addr < sym->end) + offset = al->addr - sym->start; + else + offset = al->addr - al->map->start - sym->start; + + return offset; +} + +static int get_symoff(struct symbol *sym, struct addr_location *al, + bool print_off, char *bf, int size) +{ + unsigned long offset; + + if (!sym || !sym->name[0]) + return scnprintf(bf, size, "%s", "[unknown]"); + + if (!print_off) + return scnprintf(bf, size, "%s", sym->name); + + offset = get_offset(sym, al); + + return scnprintf(bf, size, "%s+0x%x", sym->name, offset); +} + +static int get_br_mspred(struct branch_flags *flags, char *bf, int size) +{ + if (!flags->mispred && !flags->predicted) + return scnprintf(bf, size, "%s", "-"); + + if (flags->mispred) + return scnprintf(bf, size, "%s", "M"); + + return scnprintf(bf, size, "%s", "P"); +} + +static PyObject *python_process_brstacksym(struct perf_sample *sample, + struct thread *thread) +{ + struct branch_stack *br = sample->branch_stack; + PyObject *pylist; + u64 i; + char bf[512]; + struct addr_location al; + + pylist = PyList_New(0); + if (!pylist) + Py_FatalError("couldn't create Python list"); + + if (!(br && br->nr)) + goto exit; + + for (i = 0; i < br->nr; i++) { + PyObject *pyelem; + + pyelem = PyDict_New(); + if (!pyelem) + Py_FatalError("couldn't create Python dictionary"); + + thread__find_symbol(thread, sample->cpumode, + br->entries[i].from, &al); + get_symoff(al.sym, &al, true, bf, sizeof(bf)); + pydict_set_item_string_decref(pyelem, "from", + _PyUnicode_FromString(bf)); + + thread__find_symbol(thread, sample->cpumode, + br->entries[i].to, &al); + get_symoff(al.sym, &al, true, bf, sizeof(bf)); + pydict_set_item_string_decref(pyelem, "to", + _PyUnicode_FromString(bf)); + + get_br_mspred(&br->entries[i].flags, bf, sizeof(bf)); + pydict_set_item_string_decref(pyelem, "pred", + _PyUnicode_FromString(bf)); + + if (br->entries[i].flags.in_tx) { + pydict_set_item_string_decref(pyelem, "in_tx", + _PyUnicode_FromString("X")); + } else { + pydict_set_item_string_decref(pyelem, "in_tx", + _PyUnicode_FromString("-")); + } + + if (br->entries[i].flags.abort) { + pydict_set_item_string_decref(pyelem, "abort", + _PyUnicode_FromString("A")); + } else { + pydict_set_item_string_decref(pyelem, "abort", + _PyUnicode_FromString("-")); + } + + PyList_Append(pylist, pyelem); + Py_DECREF(pyelem); + } + +exit: + return pylist; +} + static PyObject *get_sample_value_as_tuple(struct sample_read_value *value) { PyObject *t; @@ -498,12 +666,63 @@ static void set_sample_read_in_dict(PyObject *dict_sample, pydict_set_item_string_decref(dict_sample, "values", values); } +static void set_sample_datasrc_in_dict(PyObject *dict, + struct perf_sample *sample) +{ + struct mem_info mi = { .data_src.val = sample->data_src }; + char decode[100]; + + pydict_set_item_string_decref(dict, "datasrc", + PyLong_FromUnsignedLongLong(sample->data_src)); + + perf_script__meminfo_scnprintf(decode, 100, &mi); + + pydict_set_item_string_decref(dict, "datasrc_decode", + _PyUnicode_FromString(decode)); +} + +static int regs_map(struct regs_dump *regs, uint64_t mask, char *bf, int size) +{ + unsigned int i = 0, r; + int printed = 0; + + bf[0] = 0; + + for_each_set_bit(r, (unsigned long *) &mask, sizeof(mask) * 8) { + u64 val = regs->regs[i++]; + + printed += scnprintf(bf + printed, size - printed, + "%5s:0x%" PRIx64 " ", + perf_reg_name(r), val); + } + + return printed; +} + +static void set_regs_in_dict(PyObject *dict, + struct perf_sample *sample, + struct perf_evsel *evsel) +{ + struct perf_event_attr *attr = &evsel->attr; + char bf[512]; + + regs_map(&sample->intr_regs, attr->sample_regs_intr, bf, sizeof(bf)); + + pydict_set_item_string_decref(dict, "iregs", + _PyUnicode_FromString(bf)); + + regs_map(&sample->user_regs, attr->sample_regs_user, bf, sizeof(bf)); + + pydict_set_item_string_decref(dict, "uregs", + _PyUnicode_FromString(bf)); +} + static PyObject *get_perf_sample_dict(struct perf_sample *sample, struct perf_evsel *evsel, struct addr_location *al, PyObject *callchain) { - PyObject *dict, *dict_sample; + PyObject *dict, *dict_sample, *brstack, *brstacksym; dict = PyDict_New(); if (!dict) @@ -531,7 +750,14 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample, PyLong_FromUnsignedLongLong(sample->period)); pydict_set_item_string_decref(dict_sample, "phys_addr", PyLong_FromUnsignedLongLong(sample->phys_addr)); + pydict_set_item_string_decref(dict_sample, "addr", + PyLong_FromUnsignedLongLong(sample->addr)); set_sample_read_in_dict(dict_sample, sample, evsel); + pydict_set_item_string_decref(dict_sample, "weight", + PyLong_FromUnsignedLongLong(sample->weight)); + pydict_set_item_string_decref(dict_sample, "transaction", + PyLong_FromUnsignedLongLong(sample->transaction)); + set_sample_datasrc_in_dict(dict_sample, sample); pydict_set_item_string_decref(dict, "sample", dict_sample); pydict_set_item_string_decref(dict, "raw_buf", _PyBytes_FromStringAndSize( @@ -549,6 +775,14 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample, pydict_set_item_string_decref(dict, "callchain", callchain); + brstack = python_process_brstack(sample, al->thread); + pydict_set_item_string_decref(dict, "brstack", brstack); + + brstacksym = python_process_brstacksym(sample, al->thread); + pydict_set_item_string_decref(dict, "brstacksym", brstacksym); + + set_regs_in_dict(dict, sample, evsel); + return dict; } diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index f4a7a43..8b93693 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1094,7 +1094,7 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, sample_type = evsel->attr.sample_type; - if (sample_type & PERF_SAMPLE_CALLCHAIN) + if (evsel__has_callchain(evsel)) callchain__printf(evsel, sample); if ((sample_type & PERF_SAMPLE_BRANCH_STACK) && !perf_evsel__has_branch_callstack(evsel)) @@ -1973,12 +1973,11 @@ bool perf_session__has_traces(struct perf_session *session, const char *msg) return false; } -int maps__set_kallsyms_ref_reloc_sym(struct map **maps, - const char *symbol_name, u64 addr) +int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name, u64 addr) { char *bracket; - int i; struct ref_reloc_sym *ref; + struct kmap *kmap; ref = zalloc(sizeof(struct ref_reloc_sym)); if (ref == NULL) @@ -1996,13 +1995,9 @@ int maps__set_kallsyms_ref_reloc_sym(struct map **maps, ref->addr = addr; - for (i = 0; i < MAP__NR_TYPES; ++i) { - struct kmap *kmap = map__kmap(maps[i]); - - if (!kmap) - continue; + kmap = map__kmap(map); + if (kmap) kmap->ref_reloc_sym = ref; - } return 0; } diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 26a68df..fed2952 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -2,7 +2,7 @@ #include <errno.h> #include <inttypes.h> #include <regex.h> -#include <sys/mman.h> +#include <linux/mman.h> #include "sort.h" #include "hist.h" #include "comm.h" @@ -282,7 +282,7 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym, ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", level); if (sym && map) { - if (map->type == MAP__VARIABLE) { + if (sym->type == STT_OBJECT) { ret += repsep_snprintf(bf + ret, size - ret, "%s", sym->name); ret += repsep_snprintf(bf + ret, size - ret, "+0x%llx", ip - map->unmap_ip(map, sym->start)); @@ -331,24 +331,18 @@ struct sort_entry sort_sym = { /* --sort srcline */ -char *hist_entry__get_srcline(struct hist_entry *he) +char *hist_entry__srcline(struct hist_entry *he) { - struct map *map = he->ms.map; - - if (!map) - return SRCLINE_UNKNOWN; - - return get_srcline(map->dso, map__rip_2objdump(map, he->ip), - he->ms.sym, true, true, he->ip); + return map__srcline(he->ms.map, he->ip, he->ms.sym); } static int64_t sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right) { if (!left->srcline) - left->srcline = hist_entry__get_srcline(left); + left->srcline = hist_entry__srcline(left); if (!right->srcline) - right->srcline = hist_entry__get_srcline(right); + right->srcline = hist_entry__srcline(right); return strcmp(right->srcline, left->srcline); } @@ -357,7 +351,7 @@ static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { if (!he->srcline) - he->srcline = hist_entry__get_srcline(he); + he->srcline = hist_entry__srcline(he); return repsep_snprintf(bf, size, "%-.*s", width, he->srcline); } @@ -371,33 +365,20 @@ struct sort_entry sort_srcline = { /* --sort srcline_from */ +static char *addr_map_symbol__srcline(struct addr_map_symbol *ams) +{ + return map__srcline(ams->map, ams->al_addr, ams->sym); +} + static int64_t sort__srcline_from_cmp(struct hist_entry *left, struct hist_entry *right) { - if (!left->branch_info->srcline_from) { - struct map *map = left->branch_info->from.map; - if (!map) - left->branch_info->srcline_from = SRCLINE_UNKNOWN; - else - left->branch_info->srcline_from = get_srcline(map->dso, - map__rip_2objdump(map, - left->branch_info->from.al_addr), - left->branch_info->from.sym, - true, true, - left->branch_info->from.al_addr); - } - if (!right->branch_info->srcline_from) { - struct map *map = right->branch_info->from.map; - if (!map) - right->branch_info->srcline_from = SRCLINE_UNKNOWN; - else - right->branch_info->srcline_from = get_srcline(map->dso, - map__rip_2objdump(map, - right->branch_info->from.al_addr), - right->branch_info->from.sym, - true, true, - right->branch_info->from.al_addr); - } + if (!left->branch_info->srcline_from) + left->branch_info->srcline_from = addr_map_symbol__srcline(&left->branch_info->from); + + if (!right->branch_info->srcline_from) + right->branch_info->srcline_from = addr_map_symbol__srcline(&right->branch_info->from); + return strcmp(right->branch_info->srcline_from, left->branch_info->srcline_from); } @@ -419,30 +400,12 @@ struct sort_entry sort_srcline_from = { static int64_t sort__srcline_to_cmp(struct hist_entry *left, struct hist_entry *right) { - if (!left->branch_info->srcline_to) { - struct map *map = left->branch_info->to.map; - if (!map) - left->branch_info->srcline_to = SRCLINE_UNKNOWN; - else - left->branch_info->srcline_to = get_srcline(map->dso, - map__rip_2objdump(map, - left->branch_info->to.al_addr), - left->branch_info->from.sym, - true, true, - left->branch_info->to.al_addr); - } - if (!right->branch_info->srcline_to) { - struct map *map = right->branch_info->to.map; - if (!map) - right->branch_info->srcline_to = SRCLINE_UNKNOWN; - else - right->branch_info->srcline_to = get_srcline(map->dso, - map__rip_2objdump(map, - right->branch_info->to.al_addr), - right->branch_info->to.sym, - true, true, - right->branch_info->to.al_addr); - } + if (!left->branch_info->srcline_to) + left->branch_info->srcline_to = addr_map_symbol__srcline(&left->branch_info->to); + + if (!right->branch_info->srcline_to) + right->branch_info->srcline_to = addr_map_symbol__srcline(&right->branch_info->to); + return strcmp(right->branch_info->srcline_to, left->branch_info->srcline_to); } @@ -1211,7 +1174,7 @@ static int hist_entry__dcacheline_snprintf(struct hist_entry *he, char *bf, /* print [s] for shared data mmaps */ if ((he->cpumode != PERF_RECORD_MISC_KERNEL) && - map && (map->type == MAP__VARIABLE) && + map && !(map->prot & PROT_EXEC) && (map->flags & MAP_SHARED) && (map->maj || map->min || map->ino || map->ino_generation)) @@ -2582,7 +2545,7 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok, if (sort__mode != SORT_MODE__MEMORY) return -EINVAL; - if (sd->entry == &sort_mem_dcacheline && cacheline_size == 0) + if (sd->entry == &sort_mem_dcacheline && cacheline_size() == 0) return -EINVAL; if (sd->entry == &sort_mem_daddr_sym) @@ -2628,7 +2591,7 @@ static int setup_sort_list(struct perf_hpp_list *list, char *str, if (*tok) { ret = sort_dimension__add(list, tok, evlist, level); if (ret == -EINVAL) { - if (!cacheline_size && !strncasecmp(tok, "dcacheline", strlen(tok))) + if (!cacheline_size() && !strncasecmp(tok, "dcacheline", strlen(tok))) pr_err("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system"); else pr_err("Invalid --sort key: `%s'", tok); diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 035b62e..7cf2d5c 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -151,6 +151,11 @@ struct hist_entry { struct callchain_root callchain[0]; /* must be last member */ }; +static __pure inline bool hist_entry__has_callchains(struct hist_entry *he) +{ + return hists__has_callchains(he->hists); +} + static inline bool hist_entry__has_pairs(struct hist_entry *he) { return !list_empty(&he->pairs.node); @@ -186,13 +191,13 @@ static inline float hist_entry__get_percent_limit(struct hist_entry *he) static inline u64 cl_address(u64 address) { /* return the cacheline of the address */ - return (address & ~(cacheline_size - 1)); + return (address & ~(cacheline_size() - 1)); } static inline u64 cl_offset(u64 address) { /* return the cacheline of the address */ - return (address & (cacheline_size - 1)); + return (address & (cacheline_size() - 1)); } enum sort_mode { @@ -292,5 +297,5 @@ int64_t sort__daddr_cmp(struct hist_entry *left, struct hist_entry *right); int64_t sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right); -char *hist_entry__get_srcline(struct hist_entry *he); +char *hist_entry__srcline(struct hist_entry *he); #endif /* __PERF_SORT_H */ diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index 3c21fd0..09d6746 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -103,6 +103,7 @@ static struct symbol *new_inline_sym(struct dso *dso, inline_sym = symbol__new(base_sym ? base_sym->start : 0, base_sym ? base_sym->end : 0, base_sym ? base_sym->binding : 0, + base_sym ? base_sym->type : 0, funcname); if (inline_sym) inline_sym->inlined = 1; diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 8f56ba4..36efb98 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -7,8 +7,7 @@ #include "xyarray.h" #include "rblist.h" -struct stats -{ +struct stats { double n, mean, M2; u64 max, min; }; diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 2de7705..29770ea 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -114,16 +114,9 @@ static inline int elf_sym__is_label(const GElf_Sym *sym) sym->st_shndx != SHN_ABS; } -static bool elf_sym__is_a(GElf_Sym *sym, enum map_type type) +static bool elf_sym__filter(GElf_Sym *sym) { - switch (type) { - case MAP__FUNCTION: - return elf_sym__is_function(sym); - case MAP__VARIABLE: - return elf_sym__is_object(sym); - default: - return false; - } + return elf_sym__is_function(sym) || elf_sym__is_object(sym); } static inline const char *elf_sym__name(const GElf_Sym *sym, @@ -150,17 +143,10 @@ static inline bool elf_sec__is_data(const GElf_Shdr *shdr, return strstr(elf_sec__name(shdr, secstrs), "data") != NULL; } -static bool elf_sec__is_a(GElf_Shdr *shdr, Elf_Data *secstrs, - enum map_type type) +static bool elf_sec__filter(GElf_Shdr *shdr, Elf_Data *secstrs) { - switch (type) { - case MAP__FUNCTION: - return elf_sec__is_text(shdr, secstrs); - case MAP__VARIABLE: - return elf_sec__is_data(shdr, secstrs); - default: - return false; - } + return elf_sec__is_text(shdr, secstrs) || + elf_sec__is_data(shdr, secstrs); } static size_t elf_addr_to_index(Elf *elf, GElf_Addr addr) @@ -256,7 +242,7 @@ static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name) * And always look at the original dso, not at debuginfo packages, that * have the PLT data stripped out (shdr_rel_plt.sh_type == SHT_NOBITS). */ -int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *map) +int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss) { uint32_t nr_rel_entries, idx; GElf_Sym sym; @@ -364,12 +350,12 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map * free(demangled); f = symbol__new(plt_offset, plt_entry_size, - STB_GLOBAL, sympltname); + STB_GLOBAL, STT_FUNC, sympltname); if (!f) goto out_elf_end; plt_offset += plt_entry_size; - symbols__insert(&dso->symbols[map->type], f); + symbols__insert(&dso->symbols, f); ++nr; } } else if (shdr_rel_plt.sh_type == SHT_REL) { @@ -390,12 +376,12 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map * free(demangled); f = symbol__new(plt_offset, plt_entry_size, - STB_GLOBAL, sympltname); + STB_GLOBAL, STT_FUNC, sympltname); if (!f) goto out_elf_end; plt_offset += plt_entry_size; - symbols__insert(&dso->symbols[map->type], f); + symbols__insert(&dso->symbols, f); ++nr; } } @@ -811,6 +797,110 @@ static u64 ref_reloc(struct kmap *kmap) void __weak arch__sym_update(struct symbol *s __maybe_unused, GElf_Sym *sym __maybe_unused) { } +static int dso__process_kernel_symbol(struct dso *dso, struct map *map, + GElf_Sym *sym, GElf_Shdr *shdr, + struct map_groups *kmaps, struct kmap *kmap, + struct dso **curr_dsop, struct map **curr_mapp, + const char *section_name, + bool adjust_kernel_syms, bool kmodule, bool *remap_kernel) +{ + struct dso *curr_dso = *curr_dsop; + struct map *curr_map; + char dso_name[PATH_MAX]; + + /* Adjust symbol to map to file offset */ + if (adjust_kernel_syms) + sym->st_value -= shdr->sh_addr - shdr->sh_offset; + + if (strcmp(section_name, (curr_dso->short_name + dso->short_name_len)) == 0) + return 0; + + if (strcmp(section_name, ".text") == 0) { + /* + * The initial kernel mapping is based on + * kallsyms and identity maps. Overwrite it to + * map to the kernel dso. + */ + if (*remap_kernel && dso->kernel) { + *remap_kernel = false; + map->start = shdr->sh_addr + ref_reloc(kmap); + map->end = map->start + shdr->sh_size; + map->pgoff = shdr->sh_offset; + map->map_ip = map__map_ip; + map->unmap_ip = map__unmap_ip; + /* Ensure maps are correctly ordered */ + if (kmaps) { + map__get(map); + map_groups__remove(kmaps, map); + map_groups__insert(kmaps, map); + map__put(map); + } + } + + /* + * The initial module mapping is based on + * /proc/modules mapped to offset zero. + * Overwrite it to map to the module dso. + */ + if (*remap_kernel && kmodule) { + *remap_kernel = false; + map->pgoff = shdr->sh_offset; + } + + *curr_mapp = map; + *curr_dsop = dso; + return 0; + } + + if (!kmap) + return 0; + + snprintf(dso_name, sizeof(dso_name), "%s%s", dso->short_name, section_name); + + curr_map = map_groups__find_by_name(kmaps, dso_name); + if (curr_map == NULL) { + u64 start = sym->st_value; + + if (kmodule) + start += map->start + shdr->sh_offset; + + curr_dso = dso__new(dso_name); + if (curr_dso == NULL) + return -1; + curr_dso->kernel = dso->kernel; + curr_dso->long_name = dso->long_name; + curr_dso->long_name_len = dso->long_name_len; + curr_map = map__new2(start, curr_dso); + dso__put(curr_dso); + if (curr_map == NULL) + return -1; + + if (adjust_kernel_syms) { + curr_map->start = shdr->sh_addr + ref_reloc(kmap); + curr_map->end = curr_map->start + shdr->sh_size; + curr_map->pgoff = shdr->sh_offset; + } else { + curr_map->map_ip = curr_map->unmap_ip = identity__map_ip; + } + curr_dso->symtab_type = dso->symtab_type; + map_groups__insert(kmaps, curr_map); + /* + * Add it before we drop the referece to curr_map, i.e. while + * we still are sure to have a reference to this DSO via + * *curr_map->dso. + */ + dsos__add(&map->groups->machine->dsos, curr_dso); + /* kmaps already got it */ + map__put(curr_map); + dso__set_loaded(curr_dso); + *curr_mapp = curr_map; + *curr_dsop = curr_dso; + } else + *curr_dsop = curr_map->dso; + + return 0; +} + int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, struct symsrc *runtime_ss, int kmodule) { @@ -844,7 +934,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, * have the wrong values for the dso maps, so remove them. */ if (kmodule && syms_ss->symtab) - symbols__delete(&dso->symbols[map->type]); + symbols__delete(&dso->symbols); if (!syms_ss->symtab) { /* @@ -921,10 +1011,10 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, dso->adjust_symbols = runtime_ss->adjust_symbols || ref_reloc(kmap); /* - * Initial kernel and module mappings do not map to the dso. For - * function mappings, flag the fixups. + * Initial kernel and module mappings do not map to the dso. + * Flag the fixups. */ - if (map->type == MAP__FUNCTION && (dso->kernel || kmodule)) { + if (dso->kernel || kmodule) { remap_kernel = true; adjust_kernel_syms = dso->adjust_symbols; } @@ -936,7 +1026,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, const char *section_name; bool used_opd = false; - if (!is_label && !elf_sym__is_a(&sym, map->type)) + if (!is_label && !elf_sym__filter(&sym)) continue; /* Reject ARM ELF "mapping symbols": these aren't unique and @@ -974,7 +1064,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, gelf_getshdr(sec, &shdr); - if (is_label && !elf_sec__is_a(&shdr, secstrs, map->type)) + if (is_label && !elf_sec__filter(&shdr, secstrs)) continue; section_name = elf_sec__name(&shdr, secstrs); @@ -982,134 +1072,37 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, /* On ARM, symbols for thumb functions have 1 added to * the symbol address as a flag - remove it */ if ((ehdr.e_machine == EM_ARM) && - (map->type == MAP__FUNCTION) && + (GELF_ST_TYPE(sym.st_info) == STT_FUNC) && (sym.st_value & 1)) --sym.st_value; if (dso->kernel || kmodule) { - char dso_name[PATH_MAX]; - - /* Adjust symbol to map to file offset */ - if (adjust_kernel_syms) - sym.st_value -= shdr.sh_addr - shdr.sh_offset; - - if (strcmp(section_name, - (curr_dso->short_name + - dso->short_name_len)) == 0) - goto new_symbol; - - if (strcmp(section_name, ".text") == 0) { - /* - * The initial kernel mapping is based on - * kallsyms and identity maps. Overwrite it to - * map to the kernel dso. - */ - if (remap_kernel && dso->kernel) { - remap_kernel = false; - map->start = shdr.sh_addr + - ref_reloc(kmap); - map->end = map->start + shdr.sh_size; - map->pgoff = shdr.sh_offset; - map->map_ip = map__map_ip; - map->unmap_ip = map__unmap_ip; - /* Ensure maps are correctly ordered */ - if (kmaps) { - map__get(map); - map_groups__remove(kmaps, map); - map_groups__insert(kmaps, map); - map__put(map); - } - } - - /* - * The initial module mapping is based on - * /proc/modules mapped to offset zero. - * Overwrite it to map to the module dso. - */ - if (remap_kernel && kmodule) { - remap_kernel = false; - map->pgoff = shdr.sh_offset; - } - - curr_map = map; - curr_dso = dso; - goto new_symbol; - } - - if (!kmap) - goto new_symbol; - - snprintf(dso_name, sizeof(dso_name), - "%s%s", dso->short_name, section_name); - - curr_map = map_groups__find_by_name(kmaps, map->type, dso_name); - if (curr_map == NULL) { - u64 start = sym.st_value; - - if (kmodule) - start += map->start + shdr.sh_offset; - - curr_dso = dso__new(dso_name); - if (curr_dso == NULL) - goto out_elf_end; - curr_dso->kernel = dso->kernel; - curr_dso->long_name = dso->long_name; - curr_dso->long_name_len = dso->long_name_len; - curr_map = map__new2(start, curr_dso, - map->type); - dso__put(curr_dso); - if (curr_map == NULL) { - goto out_elf_end; - } - if (adjust_kernel_syms) { - curr_map->start = shdr.sh_addr + - ref_reloc(kmap); - curr_map->end = curr_map->start + - shdr.sh_size; - curr_map->pgoff = shdr.sh_offset; - } else { - curr_map->map_ip = identity__map_ip; - curr_map->unmap_ip = identity__map_ip; - } - curr_dso->symtab_type = dso->symtab_type; - map_groups__insert(kmaps, curr_map); - /* - * Add it before we drop the referece to curr_map, - * i.e. while we still are sure to have a reference - * to this DSO via curr_map->dso. - */ - dsos__add(&map->groups->machine->dsos, curr_dso); - /* kmaps already got it */ - map__put(curr_map); - dso__set_loaded(curr_dso, map->type); - } else - curr_dso = curr_map->dso; - - goto new_symbol; - } - - if ((used_opd && runtime_ss->adjust_symbols) - || (!used_opd && syms_ss->adjust_symbols)) { + if (dso__process_kernel_symbol(dso, map, &sym, &shdr, kmaps, kmap, &curr_dso, &curr_map, + section_name, adjust_kernel_syms, kmodule, &remap_kernel)) + goto out_elf_end; + } else if ((used_opd && runtime_ss->adjust_symbols) || + (!used_opd && syms_ss->adjust_symbols)) { pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " " "sh_addr: %#" PRIx64 " sh_offset: %#" PRIx64 "\n", __func__, (u64)sym.st_value, (u64)shdr.sh_addr, (u64)shdr.sh_offset); sym.st_value -= shdr.sh_addr - shdr.sh_offset; } -new_symbol: + demangled = demangle_sym(dso, kmodule, elf_name); if (demangled != NULL) elf_name = demangled; f = symbol__new(sym.st_value, sym.st_size, - GELF_ST_BIND(sym.st_info), elf_name); + GELF_ST_BIND(sym.st_info), + GELF_ST_TYPE(sym.st_info), elf_name); free(demangled); if (!f) goto out_elf_end; arch__sym_update(f, &sym); - __symbols__insert(&curr_dso->symbols[curr_map->type], f, dso->kernel); + __symbols__insert(&curr_dso->symbols, f, dso->kernel); nr++; } @@ -1117,14 +1110,14 @@ new_symbol: * For misannotated, zeroed, ASM function sizes. */ if (nr > 0) { - symbols__fixup_end(&dso->symbols[map->type]); - symbols__fixup_duplicate(&dso->symbols[map->type]); + symbols__fixup_end(&dso->symbols); + symbols__fixup_duplicate(&dso->symbols); if (kmap) { /* * We need to fixup this here too because we create new * maps here, for things like vsyscall sections. */ - __map_groups__fixup_end(kmaps, map->type); + map_groups__fixup_end(kmaps); } } err = nr; @@ -1393,8 +1386,16 @@ static off_t kcore__write(struct kcore *kcore) struct phdr_data { off_t offset; + off_t rel; u64 addr; u64 len; + struct list_head node; + struct phdr_data *remaps; +}; + +struct sym_data { + u64 addr; + struct list_head node; }; struct kcore_copy_info { @@ -1404,16 +1405,78 @@ struct kcore_copy_info { u64 last_symbol; u64 first_module; u64 last_module_symbol; - struct phdr_data kernel_map; - struct phdr_data modules_map; + size_t phnum; + struct list_head phdrs; + struct list_head syms; }; +#define kcore_copy__for_each_phdr(k, p) \ + list_for_each_entry((p), &(k)->phdrs, node) + +static struct phdr_data *phdr_data__new(u64 addr, u64 len, off_t offset) +{ + struct phdr_data *p = zalloc(sizeof(*p)); + + if (p) { + p->addr = addr; + p->len = len; + p->offset = offset; + } + + return p; +} + +static struct phdr_data *kcore_copy_info__addnew(struct kcore_copy_info *kci, + u64 addr, u64 len, + off_t offset) +{ + struct phdr_data *p = phdr_data__new(addr, len, offset); + + if (p) + list_add_tail(&p->node, &kci->phdrs); + + return p; +} + +static void kcore_copy__free_phdrs(struct kcore_copy_info *kci) +{ + struct phdr_data *p, *tmp; + + list_for_each_entry_safe(p, tmp, &kci->phdrs, node) { + list_del(&p->node); + free(p); + } +} + +static struct sym_data *kcore_copy__new_sym(struct kcore_copy_info *kci, + u64 addr) +{ + struct sym_data *s = zalloc(sizeof(*s)); + + if (s) { + s->addr = addr; + list_add_tail(&s->node, &kci->syms); + } + + return s; +} + +static void kcore_copy__free_syms(struct kcore_copy_info *kci) +{ + struct sym_data *s, *tmp; + + list_for_each_entry_safe(s, tmp, &kci->syms, node) { + list_del(&s->node); + free(s); + } +} + static int kcore_copy__process_kallsyms(void *arg, const char *name, char type, u64 start) { struct kcore_copy_info *kci = arg; - if (!symbol_type__is_a(type, MAP__FUNCTION)) + if (!kallsyms__is_function(type)) return 0; if (strchr(name, '[')) { @@ -1438,6 +1501,9 @@ static int kcore_copy__process_kallsyms(void *arg, const char *name, char type, return 0; } + if (is_entry_trampoline(name) && !kcore_copy__new_sym(kci, start)) + return -1; + return 0; } @@ -1487,27 +1553,39 @@ static int kcore_copy__parse_modules(struct kcore_copy_info *kci, return 0; } -static void kcore_copy__map(struct phdr_data *p, u64 start, u64 end, u64 pgoff, - u64 s, u64 e) +static int kcore_copy__map(struct kcore_copy_info *kci, u64 start, u64 end, + u64 pgoff, u64 s, u64 e) { - if (p->addr || s < start || s >= end) - return; + u64 len, offset; + + if (s < start || s >= end) + return 0; - p->addr = s; - p->offset = (s - start) + pgoff; - p->len = e < end ? e - s : end - s; + offset = (s - start) + pgoff; + len = e < end ? e - s : end - s; + + return kcore_copy_info__addnew(kci, s, len, offset) ? 0 : -1; } static int kcore_copy__read_map(u64 start, u64 len, u64 pgoff, void *data) { struct kcore_copy_info *kci = data; u64 end = start + len; + struct sym_data *sdat; - kcore_copy__map(&kci->kernel_map, start, end, pgoff, kci->stext, - kci->etext); + if (kcore_copy__map(kci, start, end, pgoff, kci->stext, kci->etext)) + return -1; - kcore_copy__map(&kci->modules_map, start, end, pgoff, kci->first_module, - kci->last_module_symbol); + if (kcore_copy__map(kci, start, end, pgoff, kci->first_module, + kci->last_module_symbol)) + return -1; + + list_for_each_entry(sdat, &kci->syms, node) { + u64 s = round_down(sdat->addr, page_size); + + if (kcore_copy__map(kci, start, end, pgoff, s, s + len)) + return -1; + } return 0; } @@ -1520,6 +1598,64 @@ static int kcore_copy__read_maps(struct kcore_copy_info *kci, Elf *elf) return 0; } +static void kcore_copy__find_remaps(struct kcore_copy_info *kci) +{ + struct phdr_data *p, *k = NULL; + u64 kend; + + if (!kci->stext) + return; + + /* Find phdr that corresponds to the kernel map (contains stext) */ + kcore_copy__for_each_phdr(kci, p) { + u64 pend = p->addr + p->len - 1; + + if (p->addr <= kci->stext && pend >= kci->stext) { + k = p; + break; + } + } + + if (!k) + return; + + kend = k->offset + k->len; + + /* Find phdrs that remap the kernel */ + kcore_copy__for_each_phdr(kci, p) { + u64 pend = p->offset + p->len; + + if (p == k) + continue; + + if (p->offset >= k->offset && pend <= kend) + p->remaps = k; + } +} + +static void kcore_copy__layout(struct kcore_copy_info *kci) +{ + struct phdr_data *p; + off_t rel = 0; + + kcore_copy__find_remaps(kci); + + kcore_copy__for_each_phdr(kci, p) { + if (!p->remaps) { + p->rel = rel; + rel += p->len; + } + kci->phnum += 1; + } + + kcore_copy__for_each_phdr(kci, p) { + struct phdr_data *k = p->remaps; + + if (k) + p->rel = p->offset - k->offset + k->rel; + } +} + static int kcore_copy__calc_maps(struct kcore_copy_info *kci, const char *dir, Elf *elf) { @@ -1555,7 +1691,12 @@ static int kcore_copy__calc_maps(struct kcore_copy_info *kci, const char *dir, if (kci->first_module && !kci->last_module_symbol) return -1; - return kcore_copy__read_maps(kci, elf); + if (kcore_copy__read_maps(kci, elf)) + return -1; + + kcore_copy__layout(kci); + + return 0; } static int kcore_copy__copy_file(const char *from_dir, const char *to_dir, @@ -1678,12 +1819,15 @@ int kcore_copy(const char *from_dir, const char *to_dir) { struct kcore kcore; struct kcore extract; - size_t count = 2; int idx = 0, err = -1; - off_t offset = page_size, sz, modules_offset = 0; + off_t offset, sz; struct kcore_copy_info kci = { .stext = 0, }; char kcore_filename[PATH_MAX]; char extract_filename[PATH_MAX]; + struct phdr_data *p; + + INIT_LIST_HEAD(&kci.phdrs); + INIT_LIST_HEAD(&kci.syms); if (kcore_copy__copy_file(from_dir, to_dir, "kallsyms")) return -1; @@ -1703,20 +1847,17 @@ int kcore_copy(const char *from_dir, const char *to_dir) if (kcore__init(&extract, extract_filename, kcore.elfclass, false)) goto out_kcore_close; - if (!kci.modules_map.addr) - count -= 1; - - if (kcore__copy_hdr(&kcore, &extract, count)) + if (kcore__copy_hdr(&kcore, &extract, kci.phnum)) goto out_extract_close; - if (kcore__add_phdr(&extract, idx++, offset, kci.kernel_map.addr, - kci.kernel_map.len)) - goto out_extract_close; + offset = gelf_fsize(extract.elf, ELF_T_EHDR, 1, EV_CURRENT) + + gelf_fsize(extract.elf, ELF_T_PHDR, kci.phnum, EV_CURRENT); + offset = round_up(offset, page_size); + + kcore_copy__for_each_phdr(&kci, p) { + off_t offs = p->rel + offset; - if (kci.modules_map.addr) { - modules_offset = offset + kci.kernel_map.len; - if (kcore__add_phdr(&extract, idx, modules_offset, - kci.modules_map.addr, kci.modules_map.len)) + if (kcore__add_phdr(&extract, idx++, offs, p->addr, p->len)) goto out_extract_close; } @@ -1724,14 +1865,14 @@ int kcore_copy(const char *from_dir, const char *to_dir) if (sz < 0 || sz > offset) goto out_extract_close; - if (copy_bytes(kcore.fd, kci.kernel_map.offset, extract.fd, offset, - kci.kernel_map.len)) - goto out_extract_close; + kcore_copy__for_each_phdr(&kci, p) { + off_t offs = p->rel + offset; - if (modules_offset && copy_bytes(kcore.fd, kci.modules_map.offset, - extract.fd, modules_offset, - kci.modules_map.len)) - goto out_extract_close; + if (p->remaps) + continue; + if (copy_bytes(kcore.fd, p->offset, extract.fd, offs, p->len)) + goto out_extract_close; + } if (kcore_copy__compare_file(from_dir, to_dir, "modules")) goto out_extract_close; @@ -1754,6 +1895,9 @@ out_unlink_kallsyms: if (err) kcore_copy__unlink(to_dir, "kallsyms"); + kcore_copy__free_phdrs(&kci); + kcore_copy__free_syms(&kci); + return err; } diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c index ff48d0d..7119df7 100644 --- a/tools/perf/util/symbol-minimal.c +++ b/tools/perf/util/symbol-minimal.c @@ -288,8 +288,7 @@ void symsrc__destroy(struct symsrc *ss) } int dso__synthesize_plt_symbols(struct dso *dso __maybe_unused, - struct symsrc *ss __maybe_unused, - struct map *map __maybe_unused) + struct symsrc *ss __maybe_unused) { return 0; } diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 1466814..d188b75 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -5,6 +5,7 @@ #include <stdio.h> #include <string.h> #include <linux/kernel.h> +#include <linux/mman.h> #include <sys/types.h> #include <sys/stat.h> #include <sys/param.h> @@ -39,7 +40,6 @@ char **vmlinux_path; struct symbol_conf symbol_conf = { .use_modules = true, .try_vmlinux_path = true, - .annotate_src = true, .demangle = true, .demangle_kernel = false, .cumulate_callchain = true, @@ -70,18 +70,10 @@ static enum dso_binary_type binary_type_symtab[] = { #define DSO_BINARY_TYPE__SYMTAB_CNT ARRAY_SIZE(binary_type_symtab) -bool symbol_type__is_a(char symbol_type, enum map_type map_type) +static bool symbol_type__filter(char symbol_type) { symbol_type = toupper(symbol_type); - - switch (map_type) { - case MAP__FUNCTION: - return symbol_type == 'T' || symbol_type == 'W'; - case MAP__VARIABLE: - return symbol_type == 'D'; - default: - return false; - } + return symbol_type == 'T' || symbol_type == 'W' || symbol_type == 'D' || symbol_type == 'B'; } static int prefix_underscores_count(const char *str) @@ -228,9 +220,9 @@ void symbols__fixup_end(struct rb_root *symbols) curr->end = roundup(curr->start, 4096) + 4096; } -void __map_groups__fixup_end(struct map_groups *mg, enum map_type type) +void map_groups__fixup_end(struct map_groups *mg) { - struct maps *maps = &mg->maps[type]; + struct maps *maps = &mg->maps; struct map *next, *curr; down_write(&maps->lock); @@ -256,7 +248,7 @@ out_unlock: up_write(&maps->lock); } -struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name) +struct symbol *symbol__new(u64 start, u64 len, u8 binding, u8 type, const char *name) { size_t namelen = strlen(name) + 1; struct symbol *sym = calloc(1, (symbol_conf.priv_size + @@ -274,6 +266,7 @@ struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name) sym->start = start; sym->end = len ? start + len : start; + sym->type = type; sym->binding = binding; sym->namelen = namelen - 1; @@ -484,45 +477,40 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols, void dso__reset_find_symbol_cache(struct dso *dso) { - enum map_type type; - - for (type = MAP__FUNCTION; type <= MAP__VARIABLE; ++type) { - dso->last_find_result[type].addr = 0; - dso->last_find_result[type].symbol = NULL; - } + dso->last_find_result.addr = 0; + dso->last_find_result.symbol = NULL; } -void dso__insert_symbol(struct dso *dso, enum map_type type, struct symbol *sym) +void dso__insert_symbol(struct dso *dso, struct symbol *sym) { - __symbols__insert(&dso->symbols[type], sym, dso->kernel); + __symbols__insert(&dso->symbols, sym, dso->kernel); /* update the symbol cache if necessary */ - if (dso->last_find_result[type].addr >= sym->start && - (dso->last_find_result[type].addr < sym->end || + if (dso->last_find_result.addr >= sym->start && + (dso->last_find_result.addr < sym->end || sym->start == sym->end)) { - dso->last_find_result[type].symbol = sym; + dso->last_find_result.symbol = sym; } } -struct symbol *dso__find_symbol(struct dso *dso, - enum map_type type, u64 addr) +struct symbol *dso__find_symbol(struct dso *dso, u64 addr) { - if (dso->last_find_result[type].addr != addr || dso->last_find_result[type].symbol == NULL) { - dso->last_find_result[type].addr = addr; - dso->last_find_result[type].symbol = symbols__find(&dso->symbols[type], addr); + if (dso->last_find_result.addr != addr || dso->last_find_result.symbol == NULL) { + dso->last_find_result.addr = addr; + dso->last_find_result.symbol = symbols__find(&dso->symbols, addr); } - return dso->last_find_result[type].symbol; + return dso->last_find_result.symbol; } -struct symbol *dso__first_symbol(struct dso *dso, enum map_type type) +struct symbol *dso__first_symbol(struct dso *dso) { - return symbols__first(&dso->symbols[type]); + return symbols__first(&dso->symbols); } -struct symbol *dso__last_symbol(struct dso *dso, enum map_type type) +struct symbol *dso__last_symbol(struct dso *dso) { - return symbols__last(&dso->symbols[type]); + return symbols__last(&dso->symbols); } struct symbol *dso__next_symbol(struct symbol *sym) @@ -539,24 +527,22 @@ struct symbol *symbol__next_by_name(struct symbol *sym) } /* - * Teturns first symbol that matched with @name. + * Returns first symbol that matched with @name. */ -struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type, - const char *name) +struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name) { - struct symbol *s = symbols__find_by_name(&dso->symbol_names[type], name, + struct symbol *s = symbols__find_by_name(&dso->symbol_names, name, SYMBOL_TAG_INCLUDE__NONE); if (!s) - s = symbols__find_by_name(&dso->symbol_names[type], name, + s = symbols__find_by_name(&dso->symbol_names, name, SYMBOL_TAG_INCLUDE__DEFAULT_ONLY); return s; } -void dso__sort_by_name(struct dso *dso, enum map_type type) +void dso__sort_by_name(struct dso *dso) { - dso__set_sorted_by_name(dso, type); - return symbols__sort_by_name(&dso->symbol_names[type], - &dso->symbols[type]); + dso__set_sorted_by_name(dso); + return symbols__sort_by_name(&dso->symbol_names, &dso->symbols); } int modules__parse(const char *filename, void *arg, @@ -621,11 +607,6 @@ out: return err; } -struct process_kallsyms_args { - struct map *map; - struct dso *dso; -}; - /* * These are symbols in the kernel image, so make sure that * sym is from a kernel DSO. @@ -661,10 +642,10 @@ static int map__process_kallsym_symbol(void *arg, const char *name, char type, u64 start) { struct symbol *sym; - struct process_kallsyms_args *a = arg; - struct rb_root *root = &a->dso->symbols[a->map->type]; + struct dso *dso = arg; + struct rb_root *root = &dso->symbols; - if (!symbol_type__is_a(type, a->map->type)) + if (!symbol_type__filter(type)) return 0; /* @@ -672,7 +653,7 @@ static int map__process_kallsym_symbol(void *arg, const char *name, * symbols, setting length to 0, and rely on * symbols__fixup_end() to fix it up. */ - sym = symbol__new(start, 0, kallsyms2elf_binding(type), name); + sym = symbol__new(start, 0, kallsyms2elf_binding(type), kallsyms2elf_type(type), name); if (sym == NULL) return -ENOMEM; /* @@ -689,21 +670,18 @@ static int map__process_kallsym_symbol(void *arg, const char *name, * so that we can in the next step set the symbol ->end address and then * call kernel_maps__split_kallsyms. */ -static int dso__load_all_kallsyms(struct dso *dso, const char *filename, - struct map *map) +static int dso__load_all_kallsyms(struct dso *dso, const char *filename) { - struct process_kallsyms_args args = { .map = map, .dso = dso, }; - return kallsyms__parse(filename, &args, map__process_kallsym_symbol); + return kallsyms__parse(filename, dso, map__process_kallsym_symbol); } -static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map) +static int map_groups__split_kallsyms_for_kcore(struct map_groups *kmaps, struct dso *dso) { - struct map_groups *kmaps = map__kmaps(map); struct map *curr_map; struct symbol *pos; int count = 0; - struct rb_root old_root = dso->symbols[map->type]; - struct rb_root *root = &dso->symbols[map->type]; + struct rb_root old_root = dso->symbols; + struct rb_root *root = &dso->symbols; struct rb_node *next = rb_first(root); if (!kmaps) @@ -723,7 +701,7 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map) if (module) *module = '\0'; - curr_map = map_groups__find(kmaps, map->type, pos->start); + curr_map = map_groups__find(kmaps, pos->start); if (!curr_map) { symbol__delete(pos); @@ -733,7 +711,7 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map) pos->start -= curr_map->start - curr_map->pgoff; if (pos->end) pos->end -= curr_map->start - curr_map->pgoff; - symbols__insert(&curr_map->dso->symbols[curr_map->type], pos); + symbols__insert(&curr_map->dso->symbols, pos); ++count; } @@ -748,22 +726,25 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map) * kernel range is broken in several maps, named [kernel].N, as we don't have * the original ELF section names vmlinux have. */ -static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta) +static int map_groups__split_kallsyms(struct map_groups *kmaps, struct dso *dso, u64 delta, + struct map *initial_map) { - struct map_groups *kmaps = map__kmaps(map); struct machine *machine; - struct map *curr_map = map; + struct map *curr_map = initial_map; struct symbol *pos; int count = 0, moved = 0; - struct rb_root *root = &dso->symbols[map->type]; + struct rb_root *root = &dso->symbols; struct rb_node *next = rb_first(root); int kernel_range = 0; + bool x86_64; if (!kmaps) return -1; machine = kmaps->machine; + x86_64 = machine__is(machine, "x86_64"); + while (next) { char *module; @@ -778,7 +759,7 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta) *module++ = '\0'; if (strcmp(curr_map->dso->short_name, module)) { - if (curr_map != map && + if (curr_map != initial_map && dso->kernel == DSO_TYPE_GUEST_KERNEL && machine__is_default_guest(machine)) { /* @@ -788,18 +769,16 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta) * symbols are in its kmap. Mark it as * loaded. */ - dso__set_loaded(curr_map->dso, - curr_map->type); + dso__set_loaded(curr_map->dso); } - curr_map = map_groups__find_by_name(kmaps, - map->type, module); + curr_map = map_groups__find_by_name(kmaps, module); if (curr_map == NULL) { pr_debug("%s/proc/{kallsyms,modules} " "inconsistency while looking " "for \"%s\" module!\n", machine->root_dir, module); - curr_map = map; + curr_map = initial_map; goto discard_symbol; } @@ -809,11 +788,21 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta) } /* * So that we look just like we get from .ko files, - * i.e. not prelinked, relative to map->start. + * i.e. not prelinked, relative to initial_map->start. */ pos->start = curr_map->map_ip(curr_map, pos->start); pos->end = curr_map->map_ip(curr_map, pos->end); - } else if (curr_map != map) { + } else if (x86_64 && is_entry_trampoline(pos->name)) { + /* + * These symbols are not needed anymore since the + * trampoline maps refer to the text section and it's + * symbols instead. Avoid having to deal with + * relocations, and the assumption that the first symbol + * is the start of kernel text, by simply removing the + * symbols at this point. + */ + goto discard_symbol; + } else if (curr_map != initial_map) { char dso_name[PATH_MAX]; struct dso *ndso; @@ -824,7 +813,7 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta) } if (count == 0) { - curr_map = map; + curr_map = initial_map; goto add_symbol; } @@ -843,7 +832,7 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta) ndso->kernel = dso->kernel; - curr_map = map__new2(pos->start, ndso, map->type); + curr_map = map__new2(pos->start, ndso); if (curr_map == NULL) { dso__put(ndso); return -1; @@ -858,9 +847,9 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta) pos->end -= delta; } add_symbol: - if (curr_map != map) { + if (curr_map != initial_map) { rb_erase(&pos->rb_node, root); - symbols__insert(&curr_map->dso->symbols[curr_map->type], pos); + symbols__insert(&curr_map->dso->symbols, pos); ++moved; } else ++count; @@ -871,10 +860,10 @@ discard_symbol: symbol__delete(pos); } - if (curr_map != map && + if (curr_map != initial_map && dso->kernel == DSO_TYPE_GUEST_KERNEL && machine__is_default_guest(kmaps->machine)) { - dso__set_loaded(curr_map->dso, curr_map->type); + dso__set_loaded(curr_map->dso); } return count + moved; @@ -1035,7 +1024,12 @@ out_delete_from: return ret; } -static int do_validate_kcore_modules(const char *filename, struct map *map, +struct map *map_groups__first(struct map_groups *mg) +{ + return maps__first(&mg->maps); +} + +static int do_validate_kcore_modules(const char *filename, struct map_groups *kmaps) { struct rb_root modules = RB_ROOT; @@ -1046,13 +1040,12 @@ static int do_validate_kcore_modules(const char *filename, struct map *map, if (err) return err; - old_map = map_groups__first(kmaps, map->type); + old_map = map_groups__first(kmaps); while (old_map) { struct map *next = map_groups__next(old_map); struct module_info *mi; - if (old_map == map || old_map->start == map->start) { - /* The kernel map */ + if (!__map__is_kmodule(old_map)) { old_map = next; continue; } @@ -1109,7 +1102,7 @@ static int validate_kcore_modules(const char *kallsyms_filename, kallsyms_filename)) return -EINVAL; - if (do_validate_kcore_modules(modules_filename, map, kmaps)) + if (do_validate_kcore_modules(modules_filename, kmaps)) return -EINVAL; return 0; @@ -1138,7 +1131,6 @@ static int validate_kcore_addresses(const char *kallsyms_filename, struct kcore_mapfn_data { struct dso *dso; - enum map_type type; struct list_head maps; }; @@ -1147,7 +1139,7 @@ static int kcore_mapfn(u64 start, u64 len, u64 pgoff, void *data) struct kcore_mapfn_data *md = data; struct map *map; - map = map__new2(start, md->dso, md->type); + map = map__new2(start, md->dso); if (map == NULL) return -ENOMEM; @@ -1163,13 +1155,13 @@ static int dso__load_kcore(struct dso *dso, struct map *map, const char *kallsyms_filename) { struct map_groups *kmaps = map__kmaps(map); - struct machine *machine; struct kcore_mapfn_data md; struct map *old_map, *new_map, *replacement_map = NULL; + struct machine *machine; bool is_64_bit; int err, fd; char kcore_filename[PATH_MAX]; - struct symbol *sym; + u64 stext; if (!kmaps) return -EINVAL; @@ -1177,7 +1169,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, machine = kmaps->machine; /* This function requires that the map is the kernel map */ - if (map != machine->vmlinux_maps[map->type]) + if (!__map__is_kernel(map)) return -EINVAL; if (!filename_from_kallsyms_filename(kcore_filename, "kcore", @@ -1189,7 +1181,6 @@ static int dso__load_kcore(struct dso *dso, struct map *map, return -EINVAL; md.dso = dso; - md.type = map->type; INIT_LIST_HEAD(&md.maps); fd = open(kcore_filename, O_RDONLY); @@ -1200,7 +1191,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, } /* Read new maps into temporary lists */ - err = file__read_maps(fd, md.type == MAP__FUNCTION, kcore_mapfn, &md, + err = file__read_maps(fd, map->prot & PROT_EXEC, kcore_mapfn, &md, &is_64_bit); if (err) goto out_err; @@ -1212,7 +1203,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, } /* Remove old maps */ - old_map = map_groups__first(kmaps, map->type); + old_map = map_groups__first(kmaps); while (old_map) { struct map *next = map_groups__next(old_map); @@ -1220,14 +1211,15 @@ static int dso__load_kcore(struct dso *dso, struct map *map, map_groups__remove(kmaps, old_map); old_map = next; } + machine->trampolines_mapped = false; - /* Find the kernel map using the first symbol */ - sym = dso__first_symbol(dso, map->type); - list_for_each_entry(new_map, &md.maps, node) { - if (sym && sym->start >= new_map->start && - sym->start < new_map->end) { - replacement_map = new_map; - break; + /* Find the kernel map using the '_stext' symbol */ + if (!kallsyms__get_function_start(kallsyms_filename, "_stext", &stext)) { + list_for_each_entry(new_map, &md.maps, node) { + if (stext >= new_map->start && stext < new_map->end) { + replacement_map = new_map; + break; + } } } @@ -1256,6 +1248,19 @@ static int dso__load_kcore(struct dso *dso, struct map *map, map__put(new_map); } + if (machine__is(machine, "x86_64")) { + u64 addr; + + /* + * If one of the corresponding symbols is there, assume the + * entry trampoline maps are too. + */ + if (!kallsyms__get_function_start(kallsyms_filename, + ENTRY_TRAMPOLINE_NAME, + &addr)) + machine->trampolines_mapped = true; + } + /* * Set the data type and long name so that kcore can be read via * dso__data_read_addr(). @@ -1268,7 +1273,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, close(fd); - if (map->type == MAP__FUNCTION) + if (map->prot & PROT_EXEC) pr_debug("Using %s for kernel object code\n", kcore_filename); else pr_debug("Using %s for kernel data\n", kcore_filename); @@ -1289,14 +1294,10 @@ out_err: * If the kernel is relocated at boot time, kallsyms won't match. Compute the * delta based on the relocation reference symbol. */ -static int kallsyms__delta(struct map *map, const char *filename, u64 *delta) +static int kallsyms__delta(struct kmap *kmap, const char *filename, u64 *delta) { - struct kmap *kmap = map__kmap(map); u64 addr; - if (!kmap) - return -1; - if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->name) return 0; @@ -1310,19 +1311,23 @@ static int kallsyms__delta(struct map *map, const char *filename, u64 *delta) int __dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map, bool no_kcore) { + struct kmap *kmap = map__kmap(map); u64 delta = 0; if (symbol__restricted_filename(filename, "/proc/kallsyms")) return -1; - if (dso__load_all_kallsyms(dso, filename, map) < 0) + if (!kmap || !kmap->kmaps) return -1; - if (kallsyms__delta(map, filename, &delta)) + if (dso__load_all_kallsyms(dso, filename) < 0) return -1; - symbols__fixup_end(&dso->symbols[map->type]); - symbols__fixup_duplicate(&dso->symbols[map->type]); + if (kallsyms__delta(kmap, filename, &delta)) + return -1; + + symbols__fixup_end(&dso->symbols); + symbols__fixup_duplicate(&dso->symbols); if (dso->kernel == DSO_TYPE_GUEST_KERNEL) dso->symtab_type = DSO_BINARY_TYPE__GUEST_KALLSYMS; @@ -1330,9 +1335,9 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename, dso->symtab_type = DSO_BINARY_TYPE__KALLSYMS; if (!no_kcore && !dso__load_kcore(dso, map, filename)) - return dso__split_kallsyms_for_kcore(dso, map); + return map_groups__split_kallsyms_for_kcore(kmap->kmaps, dso); else - return dso__split_kallsyms(dso, map, delta); + return map_groups__split_kallsyms(kmap->kmaps, dso, delta, map); } int dso__load_kallsyms(struct dso *dso, const char *filename, @@ -1341,8 +1346,7 @@ int dso__load_kallsyms(struct dso *dso, const char *filename, return __dso__load_kallsyms(dso, filename, map, false); } -static int dso__load_perf_map(const char *map_path, struct dso *dso, - struct map *map) +static int dso__load_perf_map(const char *map_path, struct dso *dso) { char *line = NULL; size_t n; @@ -1379,12 +1383,12 @@ static int dso__load_perf_map(const char *map_path, struct dso *dso, if (len + 2 >= line_len) continue; - sym = symbol__new(start, size, STB_GLOBAL, line + len); + sym = symbol__new(start, size, STB_GLOBAL, STT_FUNC, line + len); if (sym == NULL) goto out_delete_line; - symbols__insert(&dso->symbols[map->type], sym); + symbols__insert(&dso->symbols, sym); nr_syms++; } @@ -1509,25 +1513,27 @@ int dso__load(struct dso *dso, struct map *map) pthread_mutex_lock(&dso->lock); /* check again under the dso->lock */ - if (dso__loaded(dso, map->type)) { + if (dso__loaded(dso)) { ret = 1; goto out; } + if (map->groups && map->groups->machine) + machine = map->groups->machine; + else + machine = NULL; + if (dso->kernel) { if (dso->kernel == DSO_TYPE_KERNEL) ret = dso__load_kernel_sym(dso, map); else if (dso->kernel == DSO_TYPE_GUEST_KERNEL) ret = dso__load_guest_kernel_sym(dso, map); + if (machine__is(machine, "x86_64")) + machine__map_x86_64_entry_trampolines(machine, dso); goto out; } - if (map->groups && map->groups->machine) - machine = map->groups->machine; - else - machine = NULL; - dso->adjust_symbols = 0; if (perfmap) { @@ -1542,7 +1548,7 @@ int dso__load(struct dso *dso, struct map *map) goto out; } - ret = dso__load_perf_map(map_path, dso, map); + ret = dso__load_perf_map(map_path, dso); dso->symtab_type = ret > 0 ? DSO_BINARY_TYPE__JAVA_JIT : DSO_BINARY_TYPE__NOT_FOUND; goto out; @@ -1651,7 +1657,7 @@ int dso__load(struct dso *dso, struct map *map) if (ret > 0) { int nr_plt; - nr_plt = dso__synthesize_plt_symbols(dso, runtime_ss, map); + nr_plt = dso__synthesize_plt_symbols(dso, runtime_ss); if (nr_plt > 0) ret += nr_plt; } @@ -1663,17 +1669,16 @@ out_free: if (ret < 0 && strstr(dso->name, " (deleted)") != NULL) ret = 0; out: - dso__set_loaded(dso, map->type); + dso__set_loaded(dso); pthread_mutex_unlock(&dso->lock); nsinfo__mountns_exit(&nsc); return ret; } -struct map *map_groups__find_by_name(struct map_groups *mg, - enum map_type type, const char *name) +struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) { - struct maps *maps = &mg->maps[type]; + struct maps *maps = &mg->maps; struct map *map; down_read(&maps->lock); @@ -1720,7 +1725,7 @@ int dso__load_vmlinux(struct dso *dso, struct map *map, else dso->binary_type = DSO_BINARY_TYPE__VMLINUX; dso__set_long_name(dso, vmlinux, vmlinux_allocated); - dso__set_loaded(dso, map->type); + dso__set_loaded(dso); pr_debug("Using %s for symbols\n", symfs_vmlinux); } diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 70c16741..f25fae4 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -57,7 +57,8 @@ struct symbol { u64 start; u64 end; u16 namelen; - u8 binding; + u8 type:4; + u8 binding:4; u8 idle:1; u8 ignore:1; u8 inlined:1; @@ -89,7 +90,6 @@ struct intlist; struct symbol_conf { unsigned short priv_size; - unsigned short nr_events; bool try_vmlinux_path, init_annotation, force, @@ -108,8 +108,6 @@ struct symbol_conf { show_cpu_utilization, initialized, kptr_restrict, - annotate_asm_raw, - annotate_src, event_group, demangle, demangle_kernel, @@ -259,17 +257,16 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map, bool no_kcore); int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map); -void dso__insert_symbol(struct dso *dso, enum map_type type, +void dso__insert_symbol(struct dso *dso, struct symbol *sym); -struct symbol *dso__find_symbol(struct dso *dso, enum map_type type, - u64 addr); -struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type, - const char *name); +struct symbol *dso__find_symbol(struct dso *dso, u64 addr); +struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name); + struct symbol *symbol__next_by_name(struct symbol *sym); -struct symbol *dso__first_symbol(struct dso *dso, enum map_type type); -struct symbol *dso__last_symbol(struct dso *dso, enum map_type type); +struct symbol *dso__first_symbol(struct dso *dso); +struct symbol *dso__last_symbol(struct dso *dso); struct symbol *dso__next_symbol(struct symbol *sym); enum dso_type dso__type_fd(int fd); @@ -288,7 +285,7 @@ void symbol__exit(void); void symbol__elf_init(void); int symbol__annotation_init(void); -struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name); +struct symbol *symbol__new(u64 start, u64 len, u8 binding, u8 type, const char *name); size_t __symbol__fprintf_symname_offs(const struct symbol *sym, const struct addr_location *al, bool unknown_as_addr, @@ -300,7 +297,6 @@ size_t __symbol__fprintf_symname(const struct symbol *sym, bool unknown_as_addr, FILE *fp); size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp); size_t symbol__fprintf(struct symbol *sym, FILE *fp); -bool symbol_type__is_a(char symbol_type, enum map_type map_type); bool symbol__restricted_filename(const char *filename, const char *restricted_filename); int symbol__config_symfs(const struct option *opt __maybe_unused, @@ -308,8 +304,7 @@ int symbol__config_symfs(const struct option *opt __maybe_unused, int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, struct symsrc *runtime_ss, int kmodule); -int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, - struct map *map); +int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss); char *dso__demangle_sym(struct dso *dso, int kmodule, const char *elf_name); @@ -317,7 +312,7 @@ void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel) void symbols__insert(struct rb_root *symbols, struct symbol *sym); void symbols__fixup_duplicate(struct rb_root *symbols); void symbols__fixup_end(struct rb_root *symbols); -void __map_groups__fixup_end(struct map_groups *mg, enum map_type type); +void map_groups__fixup_end(struct map_groups *mg); typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data); int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data, diff --git a/tools/perf/util/symbol_fprintf.c b/tools/perf/util/symbol_fprintf.c index 6dd2cb8..ed0205c 100644 --- a/tools/perf/util/symbol_fprintf.c +++ b/tools/perf/util/symbol_fprintf.c @@ -58,13 +58,13 @@ size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp) } size_t dso__fprintf_symbols_by_name(struct dso *dso, - enum map_type type, FILE *fp) + FILE *fp) { size_t ret = 0; struct rb_node *nd; struct symbol_name_rb_node *pos; - for (nd = rb_first(&dso->symbol_names[type]); nd; nd = rb_next(nd)) { + for (nd = rb_first(&dso->symbol_names); nd; nd = rb_next(nd)) { pos = rb_entry(nd, struct symbol_name_rb_node, rb_node); fprintf(fp, "%s\n", pos->sym.name); } diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 68b65b1..2048d39 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -302,23 +302,20 @@ int thread__insert_map(struct thread *thread, struct map *map) static int __thread__prepare_access(struct thread *thread) { bool initialized = false; - int i, err = 0; - - for (i = 0; i < MAP__NR_TYPES; ++i) { - struct maps *maps = &thread->mg->maps[i]; - struct map *map; + int err = 0; + struct maps *maps = &thread->mg->maps; + struct map *map; - down_read(&maps->lock); + down_read(&maps->lock); - for (map = maps__first(maps); map; map = map__next(map)) { - err = unwind__prepare_access(thread, map, &initialized); - if (err || initialized) - break; - } - - up_read(&maps->lock); + for (map = maps__first(maps); map; map = map__next(map)) { + err = unwind__prepare_access(thread, map, &initialized); + if (err || initialized) + break; } + up_read(&maps->lock); + return err; } @@ -335,8 +332,6 @@ static int thread__prepare_access(struct thread *thread) static int thread__clone_map_groups(struct thread *thread, struct thread *parent) { - int i; - /* This is new thread, we share map groups for process. */ if (thread->pid_ == parent->pid_) return thread__prepare_access(thread); @@ -348,9 +343,8 @@ static int thread__clone_map_groups(struct thread *thread, } /* But this one is new process, copy maps. */ - for (i = 0; i < MAP__NR_TYPES; ++i) - if (map_groups__clone(thread, parent->mg, i) < 0) - return -ENOMEM; + if (map_groups__clone(thread, parent->mg) < 0) + return -ENOMEM; return 0; } @@ -371,8 +365,7 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp) return thread__clone_map_groups(thread, parent); } -void thread__find_cpumode_addr_location(struct thread *thread, - enum map_type type, u64 addr, +void thread__find_cpumode_addr_location(struct thread *thread, u64 addr, struct addr_location *al) { size_t i; @@ -384,7 +377,7 @@ void thread__find_cpumode_addr_location(struct thread *thread, }; for (i = 0; i < ARRAY_SIZE(cpumodes); i++) { - thread__find_addr_location(thread, cpumodes[i], type, addr, al); + thread__find_symbol(thread, cpumodes[i], addr, al); if (al->map) break; } diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 14d44c3..07606aa 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -92,16 +92,13 @@ size_t thread__fprintf(struct thread *thread, FILE *fp); struct thread *thread__main_thread(struct machine *machine, struct thread *thread); -void thread__find_addr_map(struct thread *thread, - u8 cpumode, enum map_type type, u64 addr, - struct addr_location *al); +struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, + struct addr_location *al); -void thread__find_addr_location(struct thread *thread, - u8 cpumode, enum map_type type, u64 addr, - struct addr_location *al); +struct symbol *thread__find_symbol(struct thread *thread, u8 cpumode, + u64 addr, struct addr_location *al); -void thread__find_cpumode_addr_location(struct thread *thread, - enum map_type type, u64 addr, +void thread__find_cpumode_addr_location(struct thread *thread, u64 addr, struct addr_location *al); static inline void *thread__priv(struct thread *thread) diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h index 9892323..9add1f7 100644 --- a/tools/perf/util/top.h +++ b/tools/perf/util/top.h @@ -3,6 +3,7 @@ #define __PERF_TOP_H 1 #include "tool.h" +#include "annotate.h" #include <linux/types.h> #include <stddef.h> #include <stdbool.h> @@ -16,6 +17,7 @@ struct perf_top { struct perf_tool tool; struct perf_evlist *evlist; struct record_opts record_opts; + struct annotation_options annotation_opts; /* * Symbols will be added here in perf_event__process_sample and will * get out after decayed. @@ -35,7 +37,6 @@ struct perf_top { struct perf_session *session; struct winsize winsize; int realtime_prio; - int sym_pcnt_filter; const char *sym_filter; float min_percent; unsigned int nr_threads_synthesize; diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c index d7f2113..c85d0d1 100644 --- a/tools/perf/util/trace-event-info.c +++ b/tools/perf/util/trace-event-info.c @@ -103,11 +103,10 @@ out: static int record_header_files(void) { - char *path; + char *path = get_events_file("header_page"); struct stat st; int err = -EIO; - path = get_tracing_file("events/header_page"); if (!path) { pr_debug("can't get tracing/events/header_page"); return -ENOMEM; @@ -128,9 +127,9 @@ static int record_header_files(void) goto out; } - put_tracing_file(path); + put_events_file(path); - path = get_tracing_file("events/header_event"); + path = get_events_file("header_event"); if (!path) { pr_debug("can't get tracing/events/header_event"); err = -ENOMEM; @@ -154,7 +153,7 @@ static int record_header_files(void) err = 0; out: - put_tracing_file(path); + put_events_file(path); return err; } @@ -243,7 +242,7 @@ static int record_ftrace_files(struct tracepoint_path *tps) char *path; int ret; - path = get_tracing_file("events/ftrace"); + path = get_events_file("ftrace"); if (!path) { pr_debug("can't get tracing/events/ftrace"); return -ENOMEM; diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c index 16a7763..1aa3686 100644 --- a/tools/perf/util/trace-event.c +++ b/tools/perf/util/trace-event.c @@ -75,6 +75,7 @@ void trace_event__cleanup(struct trace_event *t) static struct event_format* tp_format(const char *sys, const char *name) { + char *tp_dir = get_events_file(sys); struct pevent *pevent = tevent.pevent; struct event_format *event = NULL; char path[PATH_MAX]; @@ -82,8 +83,11 @@ tp_format(const char *sys, const char *name) char *data; int err; - scnprintf(path, PATH_MAX, "%s/%s/%s/format", - tracing_events_path, sys, name); + if (!tp_dir) + return ERR_PTR(-errno); + + scnprintf(path, PATH_MAX, "%s/%s/format", tp_dir, name); + put_events_file(tp_dir); err = filename__read_str(path, &data, &size); if (err) diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index 7bdd239..538db4e 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -28,10 +28,11 @@ static int __report_module(struct addr_location *al, u64 ip, { Dwfl_Module *mod; struct dso *dso = NULL; - - thread__find_addr_location(ui->thread, - PERF_RECORD_MISC_USER, - MAP__FUNCTION, ip, al); + /* + * Some callers will use al->sym, so we can't just use the + * cheaper thread__find_map() here. + */ + thread__find_symbol(ui->thread, PERF_RECORD_MISC_USER, ip, al); if (al->map) dso = al->map->dso; @@ -103,19 +104,7 @@ static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr, struct addr_location al; ssize_t size; - thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER, - MAP__FUNCTION, addr, &al); - if (!al.map) { - /* - * We've seen cases (softice) where DWARF unwinder went - * through non executable mmaps, which we need to lookup - * in MAP__VARIABLE tree. - */ - thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER, - MAP__VARIABLE, addr, &al); - } - - if (!al.map) { + if (!thread__find_map(ui->thread, PERF_RECORD_MISC_USER, addr, &al)) { pr_debug("unwind: no map for %lx\n", (unsigned long)addr); return -1; } diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index af87304..6a11bc7 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -366,19 +366,7 @@ static int read_unwind_spec_debug_frame(struct dso *dso, static struct map *find_map(unw_word_t ip, struct unwind_info *ui) { struct addr_location al; - - thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER, - MAP__FUNCTION, ip, &al); - if (!al.map) { - /* - * We've seen cases (softice) where DWARF unwinder went - * through non executable mmaps, which we need to lookup - * in MAP__VARIABLE tree. - */ - thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER, - MAP__VARIABLE, ip, &al); - } - return al.map; + return thread__find_map(ui->thread, PERF_RECORD_MISC_USER, ip, &al); } static int @@ -586,12 +574,9 @@ static int entry(u64 ip, struct thread *thread, struct unwind_entry e; struct addr_location al; - thread__find_addr_location(thread, PERF_RECORD_MISC_USER, - MAP__FUNCTION, ip, &al); - + e.sym = thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al); e.ip = al.addr; e.map = al.map; - e.sym = al.sym; pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n", al.sym ? al.sym->name : "''", diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 1019bbc..eac5b85 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -38,11 +38,43 @@ void perf_set_multithreaded(void) } unsigned int page_size; -int cacheline_size; + +#ifdef _SC_LEVEL1_DCACHE_LINESIZE +#define cache_line_size(cacheline_sizep) *cacheline_sizep = sysconf(_SC_LEVEL1_DCACHE_LINESIZE) +#else +static void cache_line_size(int *cacheline_sizep) +{ + if (sysfs__read_int("devices/system/cpu/cpu0/cache/index0/coherency_line_size", cacheline_sizep)) + pr_debug("cannot determine cache line size"); +} +#endif + +int cacheline_size(void) +{ + static int size; + + if (!size) + cache_line_size(&size); + + return size; +} int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH; int sysctl_perf_event_max_contexts_per_stack = PERF_MAX_CONTEXTS_PER_STACK; +int sysctl__max_stack(void) +{ + int value; + + if (sysctl__read_int("kernel/perf_event_max_stack", &value) == 0) + sysctl_perf_event_max_stack = value; + + if (sysctl__read_int("kernel/perf_event_max_contexts_per_stack", &value) == 0) + sysctl_perf_event_max_contexts_per_stack = value; + + return sysctl_perf_event_max_stack; +} + bool test_attr__enabled; bool perf_host = true; diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index c9626c2..dc58254 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -43,7 +43,9 @@ size_t hex_width(u64 v); int hex2u64(const char *ptr, u64 *val); extern unsigned int page_size; -extern int cacheline_size; +int __pure cacheline_size(void); + +int sysctl__max_stack(void); int fetch_kernel_version(unsigned int *puint, char *str, size_t str_sz); diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c index 0acb1ec..741af20 100644 --- a/tools/perf/util/vdso.c +++ b/tools/perf/util/vdso.c @@ -139,12 +139,10 @@ static enum dso_type machine__thread_dso_type(struct machine *machine, struct thread *thread) { enum dso_type dso_type = DSO__TYPE_UNKNOWN; - struct map *map; - struct dso *dso; + struct map *map = map_groups__first(thread->mg); - map = map_groups__first(thread->mg, MAP__FUNCTION); for (; map ; map = map_groups__next(map)) { - dso = map->dso; + struct dso *dso = map->dso; if (!dso || dso->long_name[0] != '/') continue; dso_type = dso__type(dso, machine); diff --git a/tools/power/cpupower/bench/parse.c b/tools/power/cpupower/bench/parse.c index 9b65f05..9ba8a44 100644 --- a/tools/power/cpupower/bench/parse.c +++ b/tools/power/cpupower/bench/parse.c @@ -104,7 +104,7 @@ FILE *prepare_output(const char *dirname) dirname, time(NULL)); } - dprintf("logilename: %s\n", filename); + dprintf("logfilename: %s\n", filename); output = fopen(filename, "w+"); if (output == NULL) { diff --git a/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c b/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c index 5b3205f..5b8c495 100644 --- a/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c +++ b/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c @@ -126,6 +126,20 @@ void fix_up_intel_idle_driver_name(char *tmp, int num) } } +#ifdef __powerpc__ +void map_power_idle_state_name(char *tmp) +{ + if (!strncmp(tmp, "stop0_lite", CSTATE_NAME_LEN)) + strcpy(tmp, "stop0L"); + else if (!strncmp(tmp, "stop1_lite", CSTATE_NAME_LEN)) + strcpy(tmp, "stop1L"); + else if (!strncmp(tmp, "stop2_lite", CSTATE_NAME_LEN)) + strcpy(tmp, "stop2L"); +} +#else +void map_power_idle_state_name(char *tmp) { } +#endif + static struct cpuidle_monitor *cpuidle_register(void) { int num; @@ -145,6 +159,7 @@ static struct cpuidle_monitor *cpuidle_register(void) if (tmp == NULL) continue; + map_power_idle_state_name(tmp); fix_up_intel_idle_driver_name(tmp, num); strncpy(cpuidle_cstates[num].name, tmp, CSTATE_NAME_LEN - 1); free(tmp); diff --git a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c index 05f953f..051da0a 100644 --- a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c +++ b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c @@ -70,36 +70,43 @@ void print_n_spaces(int n) printf(" "); } -/* size of s must be at least n + 1 */ +/*s is filled with left and right spaces + *to make its length atleast n+1 + */ int fill_string_with_spaces(char *s, int n) { + char *temp; int len = strlen(s); - if (len > n) + + if (len >= n) return -1; + + temp = malloc(sizeof(char) * (n+1)); for (; len < n; len++) s[len] = ' '; s[len] = '\0'; + snprintf(temp, n+1, " %s", s); + strcpy(s, temp); + free(temp); return 0; } +#define MAX_COL_WIDTH 6 void print_header(int topology_depth) { int unsigned mon; int state, need_len; cstate_t s; char buf[128] = ""; - int percent_width = 4; fill_string_with_spaces(buf, topology_depth * 5 - 1); printf("%s|", buf); for (mon = 0; mon < avail_monitors; mon++) { - need_len = monitors[mon]->hw_states_num * (percent_width + 3) + need_len = monitors[mon]->hw_states_num * (MAX_COL_WIDTH + 1) - 1; - if (mon != 0) { - printf("|| "); - need_len--; - } + if (mon != 0) + printf("||"); sprintf(buf, "%s", monitors[mon]->name); fill_string_with_spaces(buf, need_len); printf("%s", buf); @@ -107,23 +114,21 @@ void print_header(int topology_depth) printf("\n"); if (topology_depth > 2) - printf("PKG |"); + printf(" PKG|"); if (topology_depth > 1) printf("CORE|"); if (topology_depth > 0) - printf("CPU |"); + printf(" CPU|"); for (mon = 0; mon < avail_monitors; mon++) { if (mon != 0) - printf("|| "); - else - printf(" "); + printf("||"); for (state = 0; state < monitors[mon]->hw_states_num; state++) { if (state != 0) - printf(" | "); + printf("|"); s = monitors[mon]->hw_states[state]; sprintf(buf, "%s", s.name); - fill_string_with_spaces(buf, percent_width); + fill_string_with_spaces(buf, MAX_COL_WIDTH); printf("%s", buf); } printf(" "); diff --git a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h index 9e43f33..2ae50b4 100644 --- a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h +++ b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h @@ -15,7 +15,16 @@ #define MONITORS_MAX 20 #define MONITOR_NAME_LEN 20 + +/* CSTATE_NAME_LEN is limited by header field width defined + * in cpupower-monitor.c. Header field width is defined to be + * sum of percent width and two spaces for padding. + */ +#ifdef __powerpc__ +#define CSTATE_NAME_LEN 7 +#else #define CSTATE_NAME_LEN 5 +#endif #define CSTATE_DESC_LEN 60 int cpu_count; diff --git a/tools/power/pm-graph/bootgraph.py b/tools/power/pm-graph/bootgraph.py index abb4c38..8ee626c 100755 --- a/tools/power/pm-graph/bootgraph.py +++ b/tools/power/pm-graph/bootgraph.py @@ -1,4 +1,4 @@ -#!/usr/bin/python +#!/usr/bin/python2 # # Tool for analyzing boot timing # Copyright (c) 2013, Intel Corporation. diff --git a/tools/power/pm-graph/sleepgraph.8 b/tools/power/pm-graph/sleepgraph.8 index 18baaf6..070be2c 100644 --- a/tools/power/pm-graph/sleepgraph.8 +++ b/tools/power/pm-graph/sleepgraph.8 @@ -168,6 +168,7 @@ Create a summary page of all tests in \fIindir\fR. Creates summary.html in the current folder. The output page is a table of tests with suspend and resume values sorted by suspend mode, host, and kernel. Includes test averages by mode and links to the test html files. +Use -genhtml to include tests with missing html. .TP \fB-modes\fR List available suspend modes. @@ -179,6 +180,9 @@ with any options you intend to use to see if they will work. \fB-fpdt\fR Print out the contents of the ACPI Firmware Performance Data Table. .TP +\fB-battery\fR +Print out battery status and current charge. +.TP \fB-sysinfo\fR Print out system info extracted from BIOS. Reads /dev/mem directly instead of going through dmidecode. .TP diff --git a/tools/power/pm-graph/sleepgraph.py b/tools/power/pm-graph/sleepgraph.py index 266409f..0c76047 100755 --- a/tools/power/pm-graph/sleepgraph.py +++ b/tools/power/pm-graph/sleepgraph.py @@ -1,4 +1,4 @@ -#!/usr/bin/python +#!/usr/bin/python2 # # Tool for analyzing suspend/resume timing # Copyright (c) 2013, Intel Corporation. @@ -69,7 +69,7 @@ from subprocess import call, Popen, PIPE # store system values and test parameters class SystemValues: title = 'SleepGraph' - version = '5.0' + version = '5.1' ansi = False rs = 0 display = 0 @@ -240,7 +240,7 @@ class SystemValues: kprobes = dict() timeformat = '%.3f' cmdline = '%s %s' % \ - (os.path.basename(sys.argv[0]), string.join(sys.argv[1:], ' ')) + (os.path.basename(sys.argv[0]), ' '.join(sys.argv[1:])) def __init__(self): self.archargs = 'args_'+platform.machine() self.hostname = platform.node() @@ -917,12 +917,18 @@ class Data: self.devicegroups.append([phase]) self.errorinfo = {'suspend':[],'resume':[]} def extractErrorInfo(self): + elist = { + 'HWERROR' : '.*\[ *Hardware Error *\].*', + 'FWBUG' : '.*\[ *Firmware Bug *\].*', + 'BUG' : '.*BUG.*', + 'ERROR' : '.*ERROR.*', + 'WARNING' : '.*WARNING.*', + 'IRQ' : '.*genirq: .*', + 'TASKFAIL': '.*Freezing of tasks failed.*', + } lf = sysvals.openlog(sysvals.dmesgfile, 'r') i = 0 list = [] - # sl = start line, et = error time, el = error line - type = 'ERROR' - sl = et = el = -1 for line in lf: i += 1 m = re.match('[ \t]*(\[ *)(?P<ktime>[0-9\.]*)(\]) (?P<msg>.*)', line) @@ -931,43 +937,13 @@ class Data: t = float(m.group('ktime')) if t < self.start or t > self.end: continue - if t < self.tSuspended: - dir = 'suspend' - else: - dir = 'resume' + dir = 'suspend' if t < self.tSuspended else 'resume' msg = m.group('msg') - if re.match('-*\[ *cut here *\]-*', msg): - type = 'WARNING' - sl = i - elif re.match('genirq: .*', msg): - type = 'IRQ' - sl = i - elif re.match('BUG: .*', msg) or re.match('kernel BUG .*', msg): - type = 'BUG' - sl = i - elif re.match('-*\[ *end trace .*\]-*', msg) or \ - re.match('R13: .*', msg): - if et >= 0 and sl >= 0: - list.append((type, dir, et, sl, i)) - self.kerror = True - sl = et = el = -1 - type = 'ERROR' - elif 'Call Trace:' in msg: - if el >= 0 and et >= 0: - list.append((type, dir, et, el, el)) + for err in elist: + if re.match(elist[err], msg): + list.append((err, dir, t, i, i)) self.kerror = True - et, el = t, i - if sl < 0 or type == 'BUG': - slval = i - if sl >= 0: - slval = sl - list.append((type, dir, et, slval, i)) - self.kerror = True - sl = et = el = -1 - type = 'ERROR' - if el >= 0 and et >= 0: - list.append((type, dir, et, el, el)) - self.kerror = True + break for e in list: type, dir, t, idx1, idx2 = e sysvals.vprint('kernel %s found in %s at %f' % (type, dir, t)) @@ -2331,12 +2307,14 @@ class TestProps: sv.suspendmode = data.stamp['mode'] if sv.suspendmode == 'command' and sv.ftracefile != '': modes = ['on', 'freeze', 'standby', 'mem', 'disk'] - out = Popen(['grep', 'machine_suspend', sv.ftracefile], - stderr=PIPE, stdout=PIPE).stdout.read() - m = re.match('.* machine_suspend\[(?P<mode>.*)\]', out) - if m and m.group('mode') in ['1', '2', '3', '4']: - sv.suspendmode = modes[int(m.group('mode'))] - data.stamp['mode'] = sv.suspendmode + fp = sysvals.openlog(sv.ftracefile, 'r') + for line in fp: + m = re.match('.* machine_suspend\[(?P<mode>.*)\]', line) + if m and m.group('mode') in ['1', '2', '3', '4']: + sv.suspendmode = modes[int(m.group('mode'))] + data.stamp['mode'] = sv.suspendmode + break + fp.close() m = re.match(self.cmdlinefmt, self.cmdline) if m: sv.cmdline = m.group('cmd') @@ -2413,7 +2391,7 @@ class ProcessMonitor: # markers, and/or kprobes required for primary parsing. def doesTraceLogHaveTraceEvents(): kpcheck = ['_cal: (', '_cpu_down()'] - techeck = sysvals.traceevents[:] + techeck = ['suspend_resume'] tmcheck = ['SUSPEND START', 'RESUME COMPLETE'] sysvals.usekprobes = False fp = sysvals.openlog(sysvals.ftracefile, 'r') @@ -2808,7 +2786,7 @@ def parseTraceLog(live=False): # -- phase changes -- # start of kernel suspend if(re.match('suspend_enter\[.*', t.name)): - if(isbegin): + if(isbegin and data.start == data.tKernSus): data.dmesg[phase]['start'] = t.time data.tKernSus = t.time continue @@ -3072,13 +3050,20 @@ def parseTraceLog(live=False): sysvals.vprint('Callgraph found for task %d: %.3fms, %s' % (cg.pid, (cg.end - cg.start)*1000, name)) cg.newActionFromFunction(data) if sysvals.suspendmode == 'command': - return testdata + return (testdata, '') # fill in any missing phases + error = [] for data in testdata: + tn = '' if len(testdata) == 1 else ('%d' % (data.testnumber + 1)) + terr = '' lp = data.phases[0] for p in data.phases: if(data.dmesg[p]['start'] < 0 and data.dmesg[p]['end'] < 0): + if not terr: + print 'TEST%s FAILED: %s failed in %s phase' % (tn, sysvals.suspendmode, lp) + terr = '%s%s failed in %s phase' % (sysvals.suspendmode, tn, lp) + error.append(terr) sysvals.vprint('WARNING: phase "%s" is missing!' % p) if(data.dmesg[p]['start'] < 0): data.dmesg[p]['start'] = data.dmesg[lp]['end'] @@ -3106,7 +3091,7 @@ def parseTraceLog(live=False): for j in range(i + 1, tc): testdata[j].mergeOverlapDevices(devlist) testdata[0].stitchTouchingThreads(testdata[1:]) - return testdata + return (testdata, ', '.join(error)) # Function: loadKernelLog # Description: @@ -3173,7 +3158,7 @@ def loadKernelLog(): if data: testruns.append(data) if len(testruns) < 1: - doError(' dmesg log has no suspend/resume data: %s' \ + print('ERROR: dmesg log has no suspend/resume data: %s' \ % sysvals.dmesgfile) # fix lines with same timestamp/function with the call and return swapped @@ -3521,68 +3506,144 @@ def createHTMLSummarySimple(testruns, htmlfile, folder): .summary {border:1px solid;}\n\ th {border: 1px solid black;background:#222;color:white;}\n\ td {font: 16px "Times New Roman";text-align: center;}\n\ - tr.alt td {background:#ddd;}\n\ - tr.avg td {background:#aaa;}\n\ + tr.head td {border: 1px solid black;background:#aaa;}\n\ + tr.alt {background-color:#ddd;}\n\ + tr.notice {color:red;}\n\ + .minval {background-color:#BBFFBB;}\n\ + .medval {background-color:#BBBBFF;}\n\ + .maxval {background-color:#FFBBBB;}\n\ + .head a {color:#000;text-decoration: none;}\n\ </style>\n</head>\n<body>\n' + # extract the test data into list + list = dict() + tAvg, tMin, tMax, tMed = [0.0, 0.0], [0.0, 0.0], [0.0, 0.0], [[], []] + iMin, iMed, iMax = [0, 0], [0, 0], [0, 0] + num = 0 + lastmode = '' + cnt = {'pass':0, 'fail':0, 'hang':0} + for data in sorted(testruns, key=lambda v:(v['mode'], v['host'], v['kernel'], v['time'])): + mode = data['mode'] + if mode not in list: + list[mode] = {'data': [], 'avg': [0,0], 'min': [0,0], 'max': [0,0], 'med': [0,0]} + if lastmode and lastmode != mode and num > 0: + for i in range(2): + s = sorted(tMed[i]) + list[lastmode]['med'][i] = s[int(len(s)/2)] + iMed[i] = tMed[i].index(list[lastmode]['med'][i]) + list[lastmode]['avg'] = [tAvg[0] / num, tAvg[1] / num] + list[lastmode]['min'] = tMin + list[lastmode]['max'] = tMax + list[lastmode]['idx'] = (iMin, iMed, iMax) + tAvg, tMin, tMax, tMed = [0.0, 0.0], [0.0, 0.0], [0.0, 0.0], [[], []] + iMin, iMed, iMax = [0, 0], [0, 0], [0, 0] + num = 0 + tVal = [float(data['suspend']), float(data['resume'])] + list[mode]['data'].append([data['host'], data['kernel'], + data['time'], tVal[0], tVal[1], data['url'], data['result'], + data['issues']]) + idx = len(list[mode]['data']) - 1 + if data['result'] == 'pass': + cnt['pass'] += 1 + for i in range(2): + tMed[i].append(tVal[i]) + tAvg[i] += tVal[i] + if tMin[i] == 0 or tVal[i] < tMin[i]: + iMin[i] = idx + tMin[i] = tVal[i] + if tMax[i] == 0 or tVal[i] > tMax[i]: + iMax[i] = idx + tMax[i] = tVal[i] + num += 1 + elif data['result'] == 'hang': + cnt['hang'] += 1 + elif data['result'] == 'fail': + cnt['fail'] += 1 + lastmode = mode + if lastmode and num > 0: + for i in range(2): + s = sorted(tMed[i]) + list[lastmode]['med'][i] = s[int(len(s)/2)] + iMed[i] = tMed[i].index(list[lastmode]['med'][i]) + list[lastmode]['avg'] = [tAvg[0] / num, tAvg[1] / num] + list[lastmode]['min'] = tMin + list[lastmode]['max'] = tMax + list[lastmode]['idx'] = (iMin, iMed, iMax) + # group test header - html += '<div class="stamp">%s (%d tests)</div>\n' % (folder, len(testruns)) + desc = [] + for ilk in sorted(cnt, reverse=True): + if cnt[ilk] > 0: + desc.append('%d %s' % (cnt[ilk], ilk)) + html += '<div class="stamp">%s (%d tests: %s)</div>\n' % (folder, len(testruns), ', '.join(desc)) th = '\t<th>{0}</th>\n' td = '\t<td>{0}</td>\n' + tdh = '\t<td{1}>{0}</td>\n' tdlink = '\t<td><a href="{0}">html</a></td>\n' # table header html += '<table class="summary">\n<tr>\n' + th.format('#') +\ th.format('Mode') + th.format('Host') + th.format('Kernel') +\ - th.format('Test Time') + th.format('Suspend') + th.format('Resume') +\ - th.format('Detail') + '</tr>\n' - - # test data, 1 row per test - avg = '<tr class="avg"><td></td><td></td><td></td><td></td>'+\ - '<td>Average of {0} {1} tests</td><td>{2}</td><td>{3}</td><td></td></tr>\n' - sTimeAvg = rTimeAvg = 0.0 - mode = '' - num = 0 - for data in sorted(testruns, key=lambda v:(v['mode'], v['host'], v['kernel'], v['time'])): - if mode != data['mode']: - # test average line - if(num > 0): - sTimeAvg /= (num - 1) - rTimeAvg /= (num - 1) - html += avg.format('%d' % (num - 1), mode, - '%3.3f ms' % sTimeAvg, '%3.3f ms' % rTimeAvg) - sTimeAvg = rTimeAvg = 0.0 - mode = data['mode'] - num = 1 - # alternate row color - if num % 2 == 1: - html += '<tr class="alt">\n' + th.format('Test Time') + th.format('Result') + th.format('Issues') +\ + th.format('Suspend') + th.format('Resume') + th.format('Detail') + '</tr>\n' + + # export list into html + head = '<tr class="head"><td>{0}</td><td>{1}</td>'+\ + '<td colspan=8 class="sus">Suspend Avg={2} '+\ + '<span class=minval><a href="#s{10}min">Min={3}</a></span> '+\ + '<span class=medval><a href="#s{10}med">Med={4}</a></span> '+\ + '<span class=maxval><a href="#s{10}max">Max={5}</a></span> '+\ + 'Resume Avg={6} '+\ + '<span class=minval><a href="#r{10}min">Min={7}</a></span> '+\ + '<span class=medval><a href="#r{10}med">Med={8}</a></span> '+\ + '<span class=maxval><a href="#r{10}max">Max={9}</a></span></td>'+\ + '</tr>\n' + headnone = '<tr class="head"><td>{0}</td><td>{1}</td><td colspan=8></td></tr>\n' + for mode in list: + # header line for each suspend mode + num = 0 + tAvg, tMin, tMax, tMed = list[mode]['avg'], list[mode]['min'],\ + list[mode]['max'], list[mode]['med'] + count = len(list[mode]['data']) + if 'idx' in list[mode]: + iMin, iMed, iMax = list[mode]['idx'] + html += head.format('%d' % count, mode.upper(), + '%.3f' % tAvg[0], '%.3f' % tMin[0], '%.3f' % tMed[0], '%.3f' % tMax[0], + '%.3f' % tAvg[1], '%.3f' % tMin[1], '%.3f' % tMed[1], '%.3f' % tMax[1], + mode.lower() + ) else: - html += '<tr>\n' - html += td.format("%d" % num) - num += 1 - # basic info - for item in ['mode', 'host', 'kernel', 'time']: - val = "unknown" - if(item in data): - val = data[item] - html += td.format(val) - # suspend time - sTime = float(data['suspend']) - sTimeAvg += sTime - html += td.format('%.3f ms' % sTime) - # resume time - rTime = float(data['resume']) - rTimeAvg += rTime - html += td.format('%.3f ms' % rTime) - # link to the output html - html += tdlink.format(data['url']) + '</tr>\n' - # last test average line - if(num > 0): - sTimeAvg /= (num - 1) - rTimeAvg /= (num - 1) - html += avg.format('%d' % (num - 1), mode, - '%3.3f ms' % sTimeAvg, '%3.3f ms' % rTimeAvg) + iMin = iMed = iMax = [-1, -1, -1] + html += headnone.format('%d' % count, mode.upper()) + for d in list[mode]['data']: + # row classes - alternate row color + rcls = ['alt'] if num % 2 == 1 else [] + if d[6] != 'pass': + rcls.append('notice') + html += '<tr class="'+(' '.join(rcls))+'">\n' if len(rcls) > 0 else '<tr>\n' + # figure out if the line has sus or res highlighted + idx = list[mode]['data'].index(d) + tHigh = ['', ''] + for i in range(2): + tag = 's%s' % mode if i == 0 else 'r%s' % mode + if idx == iMin[i]: + tHigh[i] = ' id="%smin" class=minval title="Minimum"' % tag + elif idx == iMax[i]: + tHigh[i] = ' id="%smax" class=maxval title="Maximum"' % tag + elif idx == iMed[i]: + tHigh[i] = ' id="%smed" class=medval title="Median"' % tag + html += td.format("%d" % (list[mode]['data'].index(d) + 1)) # row + html += td.format(mode) # mode + html += td.format(d[0]) # host + html += td.format(d[1]) # kernel + html += td.format(d[2]) # time + html += td.format(d[6]) # result + html += td.format(d[7]) # issues + html += tdh.format('%.3f ms' % d[3], tHigh[0]) if d[3] else td.format('') # suspend + html += tdh.format('%.3f ms' % d[4], tHigh[1]) if d[4] else td.format('') # resume + html += tdlink.format(d[5]) if d[5] else td.format('') # url + html += '</tr>\n' + num += 1 # flush the data to file hf = open(htmlfile, 'w') @@ -3607,7 +3668,7 @@ def ordinal(value): # testruns: array of Data objects from parseKernelLog or parseTraceLog # Output: # True if the html file was created, false if it failed -def createHTML(testruns): +def createHTML(testruns, testfail): if len(testruns) < 1: print('ERROR: Not enough test data to build a timeline') return @@ -3641,6 +3702,7 @@ def createHTML(testruns): '<td class="purple">{4}Firmware Resume: {2} ms</td>'\ '<td class="yellow" title="time from firmware mode to return from kernel enter_state({5}) [kernel time only]">{4}Kernel Resume: {3} ms</td>'\ '</tr>\n</table>\n' + html_fail = '<table class="testfail"><tr><td>{0}</td></tr></table>\n' # html format variables scaleH = 20 @@ -3708,6 +3770,9 @@ def createHTML(testruns): resume_time, testdesc, stitle, rtitle) devtl.html += thtml + if testfail: + devtl.html += html_fail.format(testfail) + # time scale for potentially multiple datasets t0 = testruns[0].start tMax = testruns[-1].end @@ -4006,6 +4071,7 @@ def addCSS(hf, sv, testcount=1, kerror=False, extra=''): .blue {background:rgba(169,208,245,0.4);}\n\ .time1 {font:22px Arial;border:1px solid;}\n\ .time2 {font:15px Arial;border-bottom:1px solid;border-left:1px solid;border-right:1px solid;}\n\ + .testfail {font:bold 22px Arial;color:red;border:1px dashed;}\n\ td {text-align:center;}\n\ r {color:#500000;font:15px Tahoma;}\n\ n {color:#505050;font:15px Tahoma;}\n\ @@ -4927,6 +4993,25 @@ def dmidecode(mempath, fatal=False): count += 1 return out +def getBattery(): + p = '/sys/class/power_supply' + bat = dict() + for d in os.listdir(p): + type = sysvals.getVal(os.path.join(p, d, 'type')).strip().lower() + if type != 'battery': + continue + for v in ['status', 'energy_now', 'capacity_now']: + bat[v] = sysvals.getVal(os.path.join(p, d, v)).strip().lower() + break + ac = True + if 'status' in bat and 'discharging' in bat['status']: + ac = False + charge = 0 + for v in ['energy_now', 'capacity_now']: + if v in bat and bat[v]: + charge = int(bat[v]) + return (ac, charge) + # Function: getFPDT # Description: # Read the acpi bios tables and pull out FPDT, the firmware data @@ -5202,8 +5287,9 @@ def getArgFloat(name, args, min, max, main=True): def processData(live=False): print('PROCESSING DATA') + error = '' if(sysvals.usetraceevents): - testruns = parseTraceLog(live) + testruns, error = parseTraceLog(live) if sysvals.dmesgfile: for data in testruns: data.extractErrorInfo() @@ -5220,15 +5306,18 @@ def processData(live=False): for data in testruns: data.debugPrint() sys.exit() - + if len(testruns) < 1: + return (testruns, {'error': 'timeline generation failed'}) sysvals.vprint('Creating the html timeline (%s)...' % sysvals.htmlfile) - createHTML(testruns) + createHTML(testruns, error) print('DONE') data = testruns[0] stamp = data.stamp stamp['suspend'], stamp['resume'] = data.getTimeValues() if data.fwValid: stamp['fwsuspend'], stamp['fwresume'] = data.fwSuspend, data.fwResume + if error: + stamp['error'] = error return (testruns, stamp) # Function: rerunTest @@ -5268,58 +5357,88 @@ def runTest(n=0): sysvals.sudouser(sysvals.testdir) sysvals.outputResult(stamp, n) -def find_in_html(html, strs, div=False): - for str in strs: - l = len(str) - i = html.find(str) - if i >= 0: +def find_in_html(html, start, end, firstonly=True): + n, out = 0, [] + while n < len(html): + m = re.search(start, html[n:]) + if not m: break - if i < 0: - return '' - if not div: - return re.search(r'[-+]?\d*\.\d+|\d+', html[i+l:i+l+50]).group() - n = html[i+l:].find('</div>') - if n < 0: + i = m.end() + m = re.search(end, html[n+i:]) + if not m: + break + j = m.start() + str = html[n+i:n+i+j] + if end == 'ms': + num = re.search(r'[-+]?\d*\.\d+|\d+', str) + str = num.group() if num else 'NaN' + if firstonly: + return str + out.append(str) + n += i+j + if firstonly: return '' - return html[i+l:i+l+n] + return out # Function: runSummary # Description: # create a summary of tests in a sub-directory -def runSummary(subdir, local=True): +def runSummary(subdir, local=True, genhtml=False): inpath = os.path.abspath(subdir) outpath = inpath if local: outpath = os.path.abspath('.') print('Generating a summary of folder "%s"' % inpath) + if genhtml: + for dirname, dirnames, filenames in os.walk(subdir): + sysvals.dmesgfile = sysvals.ftracefile = sysvals.htmlfile = '' + for filename in filenames: + if(re.match('.*_dmesg.txt', filename)): + sysvals.dmesgfile = os.path.join(dirname, filename) + elif(re.match('.*_ftrace.txt', filename)): + sysvals.ftracefile = os.path.join(dirname, filename) + sysvals.setOutputFile() + if sysvals.ftracefile and sysvals.htmlfile and \ + not os.path.exists(sysvals.htmlfile): + print('FTRACE: %s' % sysvals.ftracefile) + if sysvals.dmesgfile: + print('DMESG : %s' % sysvals.dmesgfile) + rerunTest() testruns = [] for dirname, dirnames, filenames in os.walk(subdir): for filename in filenames: if(not re.match('.*.html', filename)): continue file = os.path.join(dirname, filename) - html = open(file, 'r').read(10000) - suspend = find_in_html(html, - ['Kernel Suspend: ', 'Kernel Suspend Time: ']) - resume = find_in_html(html, - ['Kernel Resume: ', 'Kernel Resume Time: ']) - line = find_in_html(html, ['<div class="stamp">'], True) + html = open(file, 'r').read() + suspend = find_in_html(html, 'Kernel Suspend', 'ms') + resume = find_in_html(html, 'Kernel Resume', 'ms') + line = find_in_html(html, '<div class="stamp">', '</div>') stmp = line.split() - if not suspend or not resume or len(stmp) < 4: + if not suspend or not resume or len(stmp) != 8: continue + try: + dt = datetime.strptime(' '.join(stmp[3:]), '%B %d %Y, %I:%M:%S %p') + except: + continue + tstr = dt.strftime('%Y/%m/%d %H:%M:%S') + error = find_in_html(html, '<table class="testfail"><tr><td>', '</td>') + result = 'fail' if error else 'pass' + ilist = [] + e = find_in_html(html, 'class="err"[\w=":;\.%\- ]*>', '→</div>', False) + for i in list(set(e)): + ilist.append('%sx%d' % (i, e.count(i)) if e.count(i) > 1 else i) data = { + 'mode': stmp[2], 'host': stmp[0], 'kernel': stmp[1], - 'mode': stmp[2], - 'time': string.join(stmp[3:], ' '), + 'time': tstr, + 'result': result, + 'issues': ','.join(ilist), 'suspend': suspend, 'resume': resume, 'url': os.path.relpath(file, outpath), } - if len(stmp) == 7: - data['kernel'] = 'unknown' - data['mode'] = stmp[1] - data['time'] = string.join(stmp[2:], ' ') testruns.append(data) outfile = os.path.join(outpath, 'summary.html') print('Summary file: %s' % outfile) @@ -5609,11 +5728,12 @@ def printHelp(): print(' -modes List available suspend modes') print(' -status Test to see if the system is enabled to run this tool') print(' -fpdt Print out the contents of the ACPI Firmware Performance Data Table') + print(' -battery Print out battery info (if available)') print(' -sysinfo Print out system info extracted from BIOS') print(' -devinfo Print out the pm settings of all devices which support runtime suspend') print(' -flist Print the list of functions currently being captured in ftrace') print(' -flistall Print all functions capable of being captured in ftrace') - print(' -summary directory Create a summary of all test in this dir') + print(' -summary dir Create a summary of tests in this dir [-genhtml builds missing html]') print(' [redo]') print(' -ftrace ftracefile Create HTML output using ftrace input (used with -dmesg)') print(' -dmesg dmesgfile Create HTML output using dmesg (used with -ftrace)') @@ -5623,8 +5743,9 @@ def printHelp(): # ----------------- MAIN -------------------- # exec start (skipped if script is loaded as library) if __name__ == '__main__': + genhtml = False cmd = '' - simplecmds = ['-sysinfo', '-modes', '-fpdt', '-flist', '-flistall', '-devinfo', '-status'] + simplecmds = ['-sysinfo', '-modes', '-fpdt', '-flist', '-flistall', '-devinfo', '-status', '-battery'] if '-f' in sys.argv: sysvals.cgskip = sysvals.configFile('cgskip.txt') # loop through the command line arguments @@ -5660,6 +5781,8 @@ if __name__ == '__main__': sysvals.skiphtml = True elif(arg == '-cgdump'): sysvals.cgdump = True + elif(arg == '-genhtml'): + genhtml = True elif(arg == '-addlogs'): sysvals.dmesglog = sysvals.ftracelog = True elif(arg == '-verbose'): @@ -5856,6 +5979,8 @@ if __name__ == '__main__': statusCheck(True) elif(cmd == 'fpdt'): getFPDT(True) + elif(cmd == 'battery'): + print 'AC Connect: %s\nCharge: %d' % getBattery() elif(cmd == 'sysinfo'): sysvals.printSystemInfo(True) elif(cmd == 'devinfo'): @@ -5867,7 +5992,7 @@ if __name__ == '__main__': elif(cmd == 'flistall'): sysvals.getFtraceFilterFunctions(False) elif(cmd == 'summary'): - runSummary(sysvals.outdir, True) + runSummary(sysvals.outdir, True, genhtml) sys.exit() # if instructed, re-analyze existing data files @@ -5920,7 +6045,7 @@ if __name__ == '__main__': print('TEST (%d/%d) COMPLETE' % (i+1, sysvals.multitest['count'])) sysvals.logmsg = '' if not sysvals.skiphtml: - runSummary(sysvals.outdir, False) + runSummary(sysvals.outdir, False, False) sysvals.sudouser(sysvals.outdir) else: if sysvals.outdir: diff --git a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py index 29f50d4..84e2b64 100755 --- a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py +++ b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py @@ -28,6 +28,7 @@ import subprocess import os import time import re +import signal import sys import getopt import Gnuplot @@ -78,11 +79,12 @@ def print_help(): print(' Or') print(' ./intel_pstate_tracer.py [--cpu cpus] ---trace_file <trace_file> --name <test_name>') print(' To generate trace file, parse and plot, use (sudo required):') - print(' sudo ./intel_pstate_tracer.py [-c cpus] -i <interval> -n <test_name>') + print(' sudo ./intel_pstate_tracer.py [-c cpus] -i <interval> -n <test_name> -m <kbytes>') print(' Or') - print(' sudo ./intel_pstate_tracer.py [--cpu cpus] --interval <interval> --name <test_name>') + print(' sudo ./intel_pstate_tracer.py [--cpu cpus] --interval <interval> --name <test_name> --memory <kbytes>') print(' Optional argument:') - print(' cpus: comma separated list of CPUs') + print(' cpus: comma separated list of CPUs') + print(' kbytes: Kilo bytes of memory per CPU to allocate to the trace buffer. Default: 10240') print(' Output:') print(' If not already present, creates a "results/test_name" folder in the current working directory with:') print(' cpu.csv - comma seperated values file with trace contents and some additional calculations.') @@ -379,7 +381,7 @@ def clear_trace_file(): f_handle.close() except: print('IO error clearing trace file ') - quit() + sys.exit(2) def enable_trace(): """ Enable trace """ @@ -389,7 +391,7 @@ def enable_trace(): , 'w').write("1") except: print('IO error enabling trace ') - quit() + sys.exit(2) def disable_trace(): """ Disable trace """ @@ -399,17 +401,17 @@ def disable_trace(): , 'w').write("0") except: print('IO error disabling trace ') - quit() + sys.exit(2) def set_trace_buffer_size(): """ Set trace buffer size """ try: - open('/sys/kernel/debug/tracing/buffer_size_kb' - , 'w').write("10240") + with open('/sys/kernel/debug/tracing/buffer_size_kb', 'w') as fp: + fp.write(memory) except: - print('IO error setting trace buffer size ') - quit() + print('IO error setting trace buffer size ') + sys.exit(2) def free_trace_buffer(): """ Free the trace buffer memory """ @@ -418,8 +420,8 @@ def free_trace_buffer(): open('/sys/kernel/debug/tracing/buffer_size_kb' , 'w').write("1") except: - print('IO error setting trace buffer size ') - quit() + print('IO error freeing trace buffer ') + sys.exit(2) def read_trace_data(filename): """ Read and parse trace data """ @@ -431,7 +433,7 @@ def read_trace_data(filename): data = open(filename, 'r').read() except: print('Error opening ', filename) - quit() + sys.exit(2) for line in data.splitlines(): search_obj = \ @@ -489,10 +491,22 @@ def read_trace_data(filename): # Now seperate the main overall csv file into per CPU csv files. split_csv() +def signal_handler(signal, frame): + print(' SIGINT: Forcing cleanup before exit.') + if interval: + disable_trace() + clear_trace_file() + # Free the memory + free_trace_buffer() + sys.exit(0) + +signal.signal(signal.SIGINT, signal_handler) + interval = "" filename = "" cpu_list = "" testname = "" +memory = "10240" graph_data_present = False; valid1 = False @@ -501,7 +515,7 @@ valid2 = False cpu_mask = zeros((MAX_CPUS,), dtype=int) try: - opts, args = getopt.getopt(sys.argv[1:],"ht:i:c:n:",["help","trace_file=","interval=","cpu=","name="]) + opts, args = getopt.getopt(sys.argv[1:],"ht:i:c:n:m:",["help","trace_file=","interval=","cpu=","name=","memory="]) except getopt.GetoptError: print_help() sys.exit(2) @@ -521,6 +535,8 @@ for opt, arg in opts: elif opt in ("-n", "--name"): valid2 = True testname = arg + elif opt in ("-m", "--memory"): + memory = arg if not (valid1 and valid2): print_help() @@ -569,6 +585,11 @@ current_max_cpu = 0 read_trace_data(filename) +clear_trace_file() +# Free the memory +if interval: + free_trace_buffer() + if graph_data_present == False: print('No valid data to plot') sys.exit(2) @@ -593,9 +614,4 @@ for root, dirs, files in os.walk('.'): for f in files: fix_ownership(f) -clear_trace_file() -# Free the memory -if interval: - free_trace_buffer() - os.chdir('../../') diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile index a9bc914..2ab25aa 100644 --- a/tools/power/x86/turbostat/Makefile +++ b/tools/power/x86/turbostat/Makefile @@ -25,4 +25,4 @@ install : turbostat install -d $(DESTDIR)$(PREFIX)/bin install $(BUILD_OUTPUT)/turbostat $(DESTDIR)$(PREFIX)/bin/turbostat install -d $(DESTDIR)$(PREFIX)/share/man/man8 - install turbostat.8 $(DESTDIR)$(PREFIX)/share/man/man8 + install -m 644 turbostat.8 $(DESTDIR)$(PREFIX)/share/man/man8 diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index ccf2a69..ca9ef70 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -54,9 +54,12 @@ name as necessary to disambiguate it from others is necessary. Note that option .PP \fB--cpu cpu-set\fP limit output to system summary plus the specified cpu-set. If cpu-set is the string "core", then the system summary plus the first CPU in each core are printed -- eg. subsequent HT siblings are not printed. Or if cpu-set is the string "package", then the system summary plus the first CPU in each package is printed. Otherwise, the system summary plus the specified set of CPUs are printed. The cpu-set is ordered from low to high, comma delimited with ".." and "-" permitted to denote a range. eg. 1,2,8,14..17,21-44 .PP -\fB--hide column\fP do not show the specified columns. May be invoked multiple times, or with a comma-separated list of column names. Use "--hide sysfs" to hide the sysfs statistics columns as a group. +\fB--hide column\fP do not show the specified built-in columns. May be invoked multiple times, or with a comma-separated list of column names. Use "--hide sysfs" to hide the sysfs statistics columns as a group. .PP -\fB--show column\fP show only the specified columns. May be invoked multiple times, or with a comma-separated list of column names. Use "--show sysfs" to show the sysfs statistics columns as a group. +\fB--enable column\fP show the specified built-in columns, which are otherwise disabled, by default. Currently the only built-in counters disabled by default are "usec" and "Time_Of_Day_Seconds". +The column name "all" can be used to enable all disabled-by-default built-in counters. +.PP +\fB--show column\fP show only the specified built-in columns. May be invoked multiple times, or with a comma-separated list of column names. Use "--show sysfs" to show the sysfs statistics columns as a group. .PP \fB--Dump\fP displays the raw counter values. .PP @@ -64,6 +67,8 @@ name as necessary to disambiguate it from others is necessary. Note that option .PP \fB--interval seconds\fP overrides the default 5.0 second measurement interval. .PP +\fB--num_iterations num\fP number of the measurement iterations. +.PP \fB--out output_file\fP turbostat output is written to the specified output_file. The file is truncated if it already exists, and it is created if it does not exist. .PP @@ -86,6 +91,8 @@ displays the statistics gathered since it was forked. The system configuration dump (if --quiet is not used) is followed by statistics. The first row of the statistics labels the content of each column (below). The second row of statistics is the system summary line. The system summary line has a '-' in the columns for the Package, Core, and CPU. The contents of the system summary line depends on the type of column. Columns that count items (eg. IRQ) show the sum across all CPUs in the system. Columns that show a percentage show the average across all CPUs in the system. Columns that dump raw MSR values simply show 0 in the summary. After the system summary row, each row describes a specific Package/Core/CPU. Note that if the --cpu parameter is used to limit which specific CPUs are displayed, turbostat will still collect statistics for all CPUs in the system and will still show the system summary for all CPUs in the system. .SH COLUMN DESCRIPTIONS .nf +\fBusec\fP For each CPU, the number of microseconds elapsed during counter collection, including thread migration -- if any. This counter is disabled by default, and is enabled with "--enable usec", or --debug. On the summary row, usec refers to the total elapsed time to collect the counters on all cpus. +\fBTime_Of_Day_Seconds\fP For each CPU, the gettimeofday(2) value (seconds.subsec since Epoch) when the counters ending the measurement interval were collected. This column is disabled by default, and can be enabled with "--enable Time_Of_Day_Seconds" or "--debug". On the summary row, Time_Of_Day_Seconds refers to the timestamp following collection of counters on the last CPU. \fBCore\fP processor core number. Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading Technology (HT). \fBCPU\fP Linux CPU (logical processor) number. Yes, it is okay that on many systems the CPUs are not listed in numerical order -- for efficiency reasons, turbostat runs in topology order, so HT siblings appear together. \fBPackage\fP processor package number -- not present on systems with a single processor package. @@ -262,6 +269,21 @@ CPU PRF_CTRL .fi +.SH INPUT + +For interval-mode, turbostat will immediately end the current interval +when it sees a newline on standard input. +turbostat will then start the next interval. +Control-C will be send a SIGINT to turbostat, +which will immediately abort the program with no further processing. +.SH SIGNALS + +SIGINT will interrupt interval-mode. +The end-of-interval data will be collected and displayed before turbostat exits. + +SIGUSR1 will end current interval, +end-of-interval data will be collected and displayed before turbostat +starts a new interval. .SH NOTES .B "turbostat " diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index bd9c6b3..d6cff30 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -29,6 +29,7 @@ #include <sys/types.h> #include <sys/wait.h> #include <sys/stat.h> +#include <sys/select.h> #include <sys/resource.h> #include <fcntl.h> #include <signal.h> @@ -47,9 +48,13 @@ char *proc_stat = "/proc/stat"; FILE *outf; int *fd_percpu; +struct timeval interval_tv = {5, 0}; struct timespec interval_ts = {5, 0}; +struct timespec one_msec = {0, 1000000}; +unsigned int num_iterations; unsigned int debug; unsigned int quiet; +unsigned int shown; unsigned int sums_need_wide_columns; unsigned int rapl_joules; unsigned int summary_only; @@ -58,6 +63,7 @@ unsigned int dump_only; unsigned int do_snb_cstates; unsigned int do_knl_cstates; unsigned int do_slm_cstates; +unsigned int do_cnl_cstates; unsigned int use_c1_residency_msr; unsigned int has_aperf; unsigned int has_epb; @@ -80,6 +86,8 @@ unsigned int do_rapl; unsigned int do_dts; unsigned int do_ptm; unsigned long long gfx_cur_rc6_ms; +unsigned long long cpuidle_cur_cpu_lpi_us; +unsigned long long cpuidle_cur_sys_lpi_us; unsigned int gfx_cur_mhz; unsigned int tcc_activation_temp; unsigned int tcc_activation_temp_override; @@ -87,6 +95,7 @@ double rapl_power_units, rapl_time_units; double rapl_dram_energy_units, rapl_energy_units; double rapl_joule_counter_range; unsigned int do_core_perf_limit_reasons; +unsigned int has_automatic_cstate_conversion; unsigned int do_gfx_perf_limit_reasons; unsigned int do_ring_perf_limit_reasons; unsigned int crystal_hz; @@ -147,7 +156,9 @@ char *progname; #define CPU_SUBSET_MAXCPUS 1024 /* need to use before probe... */ cpu_set_t *cpu_present_set, *cpu_affinity_set, *cpu_subset; size_t cpu_present_setsize, cpu_affinity_setsize, cpu_subset_size; -#define MAX_ADDED_COUNTERS 16 +#define MAX_ADDED_COUNTERS 8 +#define MAX_ADDED_THREAD_COUNTERS 24 +#define BITMASK_SIZE 32 struct thread_data { struct timeval tv_begin; @@ -162,7 +173,7 @@ struct thread_data { unsigned int flags; #define CPU_IS_FIRST_THREAD_IN_CORE 0x2 #define CPU_IS_FIRST_CORE_IN_PACKAGE 0x4 - unsigned long long counter[MAX_ADDED_COUNTERS]; + unsigned long long counter[MAX_ADDED_THREAD_COUNTERS]; } *thread_even, *thread_odd; struct core_data { @@ -183,6 +194,8 @@ struct pkg_data { unsigned long long pc8; unsigned long long pc9; unsigned long long pc10; + unsigned long long cpu_lpi; + unsigned long long sys_lpi; unsigned long long pkg_wtd_core_c0; unsigned long long pkg_any_core_c0; unsigned long long pkg_any_gfxe_c0; @@ -203,12 +216,21 @@ struct pkg_data { #define ODD_COUNTERS thread_odd, core_odd, package_odd #define EVEN_COUNTERS thread_even, core_even, package_even -#define GET_THREAD(thread_base, thread_no, core_no, pkg_no) \ - (thread_base + (pkg_no) * topo.num_cores_per_pkg * \ - topo.num_threads_per_core + \ - (core_no) * topo.num_threads_per_core + (thread_no)) -#define GET_CORE(core_base, core_no, pkg_no) \ - (core_base + (pkg_no) * topo.num_cores_per_pkg + (core_no)) +#define GET_THREAD(thread_base, thread_no, core_no, node_no, pkg_no) \ + ((thread_base) + \ + ((pkg_no) * \ + topo.nodes_per_pkg * topo.cores_per_node * topo.threads_per_core) + \ + ((node_no) * topo.cores_per_node * topo.threads_per_core) + \ + ((core_no) * topo.threads_per_core) + \ + (thread_no)) + +#define GET_CORE(core_base, core_no, node_no, pkg_no) \ + ((core_base) + \ + ((pkg_no) * topo.nodes_per_pkg * topo.cores_per_node) + \ + ((node_no) * topo.cores_per_node) + \ + (core_no)) + + #define GET_PKG(pkg_base, pkg_no) (pkg_base + pkg_no) enum counter_scope {SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE}; @@ -244,14 +266,25 @@ struct system_summary { struct pkg_data packages; } average; +struct cpu_topology { + int physical_package_id; + int logical_cpu_id; + int physical_node_id; + int logical_node_id; /* 0-based count within the package */ + int physical_core_id; + int thread_id; + cpu_set_t *put_ids; /* Processing Unit/Thread IDs */ +} *cpus; struct topo_params { int num_packages; int num_cpus; int num_cores; int max_cpu_num; - int num_cores_per_pkg; - int num_threads_per_core; + int max_node_num; + int nodes_per_pkg; + int cores_per_node; + int threads_per_core; } topo; struct timeval tv_even, tv_odd, tv_delta; @@ -273,27 +306,33 @@ int cpu_is_not_present(int cpu) int for_all_cpus(int (func)(struct thread_data *, struct core_data *, struct pkg_data *), struct thread_data *thread_base, struct core_data *core_base, struct pkg_data *pkg_base) { - int retval, pkg_no, core_no, thread_no; + int retval, pkg_no, core_no, thread_no, node_no; for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) { - for (core_no = 0; core_no < topo.num_cores_per_pkg; ++core_no) { - for (thread_no = 0; thread_no < - topo.num_threads_per_core; ++thread_no) { - struct thread_data *t; - struct core_data *c; - struct pkg_data *p; - - t = GET_THREAD(thread_base, thread_no, core_no, pkg_no); - - if (cpu_is_not_present(t->cpu_id)) - continue; - - c = GET_CORE(core_base, core_no, pkg_no); - p = GET_PKG(pkg_base, pkg_no); - - retval = func(t, c, p); - if (retval) - return retval; + for (core_no = 0; core_no < topo.cores_per_node; ++core_no) { + for (node_no = 0; node_no < topo.nodes_per_pkg; + node_no++) { + for (thread_no = 0; thread_no < + topo.threads_per_core; ++thread_no) { + struct thread_data *t; + struct core_data *c; + struct pkg_data *p; + + t = GET_THREAD(thread_base, thread_no, + core_no, node_no, + pkg_no); + + if (cpu_is_not_present(t->cpu_id)) + continue; + + c = GET_CORE(core_base, core_no, + node_no, pkg_no); + p = GET_PKG(pkg_base, pkg_no); + + retval = func(t, c, p); + if (retval) + return retval; + } } } } @@ -346,6 +385,8 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr) * Thus, strings that are proper sub-sets must follow their more specific peers. */ struct msr_counter bic[] = { + { 0x0, "usec" }, + { 0x0, "Time_Of_Day_Seconds" }, { 0x0, "Package" }, { 0x0, "Avg_MHz" }, { 0x0, "Bzy_MHz" }, @@ -369,7 +410,9 @@ struct msr_counter bic[] = { { 0x0, "Pkg%pc7" }, { 0x0, "Pkg%pc8" }, { 0x0, "Pkg%pc9" }, - { 0x0, "Pkg%pc10" }, + { 0x0, "Pk%pc10" }, + { 0x0, "CPU%LPI" }, + { 0x0, "SYS%LPI" }, { 0x0, "PkgWatt" }, { 0x0, "CorWatt" }, { 0x0, "GFXWatt" }, @@ -389,62 +432,72 @@ struct msr_counter bic[] = { { 0x0, "Any%C0" }, { 0x0, "GFX%C0" }, { 0x0, "CPUGFX%" }, + { 0x0, "Node%" }, }; #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter)) -#define BIC_Package (1ULL << 0) -#define BIC_Avg_MHz (1ULL << 1) -#define BIC_Bzy_MHz (1ULL << 2) -#define BIC_TSC_MHz (1ULL << 3) -#define BIC_IRQ (1ULL << 4) -#define BIC_SMI (1ULL << 5) -#define BIC_Busy (1ULL << 6) -#define BIC_CPU_c1 (1ULL << 7) -#define BIC_CPU_c3 (1ULL << 8) -#define BIC_CPU_c6 (1ULL << 9) -#define BIC_CPU_c7 (1ULL << 10) -#define BIC_ThreadC (1ULL << 11) -#define BIC_CoreTmp (1ULL << 12) -#define BIC_CoreCnt (1ULL << 13) -#define BIC_PkgTmp (1ULL << 14) -#define BIC_GFX_rc6 (1ULL << 15) -#define BIC_GFXMHz (1ULL << 16) -#define BIC_Pkgpc2 (1ULL << 17) -#define BIC_Pkgpc3 (1ULL << 18) -#define BIC_Pkgpc6 (1ULL << 19) -#define BIC_Pkgpc7 (1ULL << 20) -#define BIC_Pkgpc8 (1ULL << 21) -#define BIC_Pkgpc9 (1ULL << 22) -#define BIC_Pkgpc10 (1ULL << 23) -#define BIC_PkgWatt (1ULL << 24) -#define BIC_CorWatt (1ULL << 25) -#define BIC_GFXWatt (1ULL << 26) -#define BIC_PkgCnt (1ULL << 27) -#define BIC_RAMWatt (1ULL << 28) -#define BIC_PKG__ (1ULL << 29) -#define BIC_RAM__ (1ULL << 30) -#define BIC_Pkg_J (1ULL << 31) -#define BIC_Cor_J (1ULL << 32) -#define BIC_GFX_J (1ULL << 33) -#define BIC_RAM_J (1ULL << 34) -#define BIC_Core (1ULL << 35) -#define BIC_CPU (1ULL << 36) -#define BIC_Mod_c6 (1ULL << 37) -#define BIC_sysfs (1ULL << 38) -#define BIC_Totl_c0 (1ULL << 39) -#define BIC_Any_c0 (1ULL << 40) -#define BIC_GFX_c0 (1ULL << 41) -#define BIC_CPUGFX (1ULL << 42) - -unsigned long long bic_enabled = 0xFFFFFFFFFFFFFFFFULL; -unsigned long long bic_present = BIC_sysfs; +#define BIC_USEC (1ULL << 0) +#define BIC_TOD (1ULL << 1) +#define BIC_Package (1ULL << 2) +#define BIC_Avg_MHz (1ULL << 3) +#define BIC_Bzy_MHz (1ULL << 4) +#define BIC_TSC_MHz (1ULL << 5) +#define BIC_IRQ (1ULL << 6) +#define BIC_SMI (1ULL << 7) +#define BIC_Busy (1ULL << 8) +#define BIC_CPU_c1 (1ULL << 9) +#define BIC_CPU_c3 (1ULL << 10) +#define BIC_CPU_c6 (1ULL << 11) +#define BIC_CPU_c7 (1ULL << 12) +#define BIC_ThreadC (1ULL << 13) +#define BIC_CoreTmp (1ULL << 14) +#define BIC_CoreCnt (1ULL << 15) +#define BIC_PkgTmp (1ULL << 16) +#define BIC_GFX_rc6 (1ULL << 17) +#define BIC_GFXMHz (1ULL << 18) +#define BIC_Pkgpc2 (1ULL << 19) +#define BIC_Pkgpc3 (1ULL << 20) +#define BIC_Pkgpc6 (1ULL << 21) +#define BIC_Pkgpc7 (1ULL << 22) +#define BIC_Pkgpc8 (1ULL << 23) +#define BIC_Pkgpc9 (1ULL << 24) +#define BIC_Pkgpc10 (1ULL << 25) +#define BIC_CPU_LPI (1ULL << 26) +#define BIC_SYS_LPI (1ULL << 27) +#define BIC_PkgWatt (1ULL << 26) +#define BIC_CorWatt (1ULL << 27) +#define BIC_GFXWatt (1ULL << 28) +#define BIC_PkgCnt (1ULL << 29) +#define BIC_RAMWatt (1ULL << 30) +#define BIC_PKG__ (1ULL << 31) +#define BIC_RAM__ (1ULL << 32) +#define BIC_Pkg_J (1ULL << 33) +#define BIC_Cor_J (1ULL << 34) +#define BIC_GFX_J (1ULL << 35) +#define BIC_RAM_J (1ULL << 36) +#define BIC_Core (1ULL << 37) +#define BIC_CPU (1ULL << 38) +#define BIC_Mod_c6 (1ULL << 39) +#define BIC_sysfs (1ULL << 40) +#define BIC_Totl_c0 (1ULL << 41) +#define BIC_Any_c0 (1ULL << 42) +#define BIC_GFX_c0 (1ULL << 43) +#define BIC_CPUGFX (1ULL << 44) +#define BIC_Node (1ULL << 45) + +#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD) + +unsigned long long bic_enabled = (0xFFFFFFFFFFFFFFFFULL & ~BIC_DISABLED_BY_DEFAULT); +unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs; #define DO_BIC(COUNTER_NAME) (bic_enabled & bic_present & COUNTER_NAME) +#define ENABLE_BIC(COUNTER_NAME) (bic_enabled |= COUNTER_NAME) #define BIC_PRESENT(COUNTER_BIT) (bic_present |= COUNTER_BIT) #define BIC_NOT_PRESENT(COUNTER_BIT) (bic_present &= ~COUNTER_BIT) + #define MAX_DEFERRED 16 char *deferred_skip_names[MAX_DEFERRED]; int deferred_skip_index; @@ -469,9 +522,10 @@ void help(void) "--cpu cpu-set limit output to summary plus cpu-set:\n" " {core | package | j,k,l..m,n-p }\n" "--quiet skip decoding system configuration header\n" - "--interval sec Override default 5-second measurement interval\n" + "--interval sec.subsec Override default 5-second measurement interval\n" "--help print this help message\n" "--list list column headers only\n" + "--num_iterations num number of the measurement iterations\n" "--out file create or truncate \"file\" for all output\n" "--version print version information\n" "\n" @@ -496,6 +550,9 @@ unsigned long long bic_lookup(char *name_list, enum show_hide_mode mode) if (comma) *comma = '\0'; + if (!strcmp(name_list, "all")) + return ~0; + for (i = 0; i < MAX_BIC; ++i) { if (!strcmp(name_list, bic[i].name)) { retval |= (1ULL << i); @@ -532,10 +589,14 @@ void print_header(char *delim) struct msr_counter *mp; int printed = 0; - if (debug) - outp += sprintf(outp, "usec %s", delim); + if (DO_BIC(BIC_USEC)) + outp += sprintf(outp, "%susec", (printed++ ? delim : "")); + if (DO_BIC(BIC_TOD)) + outp += sprintf(outp, "%sTime_Of_Day_Seconds", (printed++ ? delim : "")); if (DO_BIC(BIC_Package)) outp += sprintf(outp, "%sPackage", (printed++ ? delim : "")); + if (DO_BIC(BIC_Node)) + outp += sprintf(outp, "%sNode", (printed++ ? delim : "")); if (DO_BIC(BIC_Core)) outp += sprintf(outp, "%sCore", (printed++ ? delim : "")); if (DO_BIC(BIC_CPU)) @@ -576,7 +637,7 @@ void print_header(char *delim) if (DO_BIC(BIC_CPU_c1)) outp += sprintf(outp, "%sCPU%%c1", (printed++ ? delim : "")); - if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates) + if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates) outp += sprintf(outp, "%sCPU%%c3", (printed++ ? delim : "")); if (DO_BIC(BIC_CPU_c6)) outp += sprintf(outp, "%sCPU%%c6", (printed++ ? delim : "")); @@ -635,6 +696,10 @@ void print_header(char *delim) outp += sprintf(outp, "%sPkg%%pc9", (printed++ ? delim : "")); if (DO_BIC(BIC_Pkgpc10)) outp += sprintf(outp, "%sPk%%pc10", (printed++ ? delim : "")); + if (DO_BIC(BIC_CPU_LPI)) + outp += sprintf(outp, "%sCPU%%LPI", (printed++ ? delim : "")); + if (DO_BIC(BIC_SYS_LPI)) + outp += sprintf(outp, "%sSYS%%LPI", (printed++ ? delim : "")); if (do_rapl && !rapl_joules) { if (DO_BIC(BIC_PkgWatt)) @@ -739,6 +804,9 @@ int dump_counters(struct thread_data *t, struct core_data *c, outp += sprintf(outp, "pc8: %016llX\n", p->pc8); outp += sprintf(outp, "pc9: %016llX\n", p->pc9); outp += sprintf(outp, "pc10: %016llX\n", p->pc10); + outp += sprintf(outp, "pc10: %016llX\n", p->pc10); + outp += sprintf(outp, "cpu_lpi: %016llX\n", p->cpu_lpi); + outp += sprintf(outp, "sys_lpi: %016llX\n", p->sys_lpi); outp += sprintf(outp, "Joules PKG: %0X\n", p->energy_pkg); outp += sprintf(outp, "Joules COR: %0X\n", p->energy_cores); outp += sprintf(outp, "Joules GFX: %0X\n", p->energy_gfx); @@ -786,7 +854,7 @@ int format_counters(struct thread_data *t, struct core_data *c, (cpu_subset && !CPU_ISSET_S(t->cpu_id, cpu_subset_size, cpu_subset))) return 0; - if (debug) { + if (DO_BIC(BIC_USEC)) { /* on each row, print how many usec each timestamp took to gather */ struct timeval tv; @@ -794,6 +862,10 @@ int format_counters(struct thread_data *t, struct core_data *c, outp += sprintf(outp, "%5ld\t", tv.tv_sec * 1000000 + tv.tv_usec); } + /* Time_Of_Day_Seconds: on each row, print sec.usec last timestamp taken */ + if (DO_BIC(BIC_TOD)) + outp += sprintf(outp, "%10ld.%06ld\t", t->tv_end.tv_sec, t->tv_end.tv_usec); + interval_float = tv_delta.tv_sec + tv_delta.tv_usec/1000000.0; tsc = t->tsc * tsc_tweak; @@ -802,6 +874,8 @@ int format_counters(struct thread_data *t, struct core_data *c, if (t == &average.threads) { if (DO_BIC(BIC_Package)) outp += sprintf(outp, "%s-", (printed++ ? delim : "")); + if (DO_BIC(BIC_Node)) + outp += sprintf(outp, "%s-", (printed++ ? delim : "")); if (DO_BIC(BIC_Core)) outp += sprintf(outp, "%s-", (printed++ ? delim : "")); if (DO_BIC(BIC_CPU)) @@ -813,6 +887,15 @@ int format_counters(struct thread_data *t, struct core_data *c, else outp += sprintf(outp, "%s-", (printed++ ? delim : "")); } + if (DO_BIC(BIC_Node)) { + if (t) + outp += sprintf(outp, "%s%d", + (printed++ ? delim : ""), + cpus[t->cpu_id].physical_node_id); + else + outp += sprintf(outp, "%s-", + (printed++ ? delim : "")); + } if (DO_BIC(BIC_Core)) { if (c) outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), c->core_id); @@ -882,7 +965,7 @@ int format_counters(struct thread_data *t, struct core_data *c, if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) goto done; - if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates) + if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates) outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c3/tsc); if (DO_BIC(BIC_CPU_c6)) outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c6/tsc); @@ -959,6 +1042,11 @@ int format_counters(struct thread_data *t, struct core_data *c, if (DO_BIC(BIC_Pkgpc10)) outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc10/tsc); + if (DO_BIC(BIC_CPU_LPI)) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->cpu_lpi / 1000000.0 / interval_float); + if (DO_BIC(BIC_SYS_LPI)) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->sys_lpi / 1000000.0 / interval_float); + /* * If measurement interval exceeds minimum RAPL Joule Counter range, * indicate that results are suspect by printing "**" in fraction place. @@ -1006,7 +1094,8 @@ int format_counters(struct thread_data *t, struct core_data *c, } done: - outp += sprintf(outp, "\n"); + if (*(outp - 1) != '\n') + outp += sprintf(outp, "\n"); return 0; } @@ -1083,6 +1172,8 @@ delta_package(struct pkg_data *new, struct pkg_data *old) old->pc8 = new->pc8 - old->pc8; old->pc9 = new->pc9 - old->pc9; old->pc10 = new->pc10 - old->pc10; + old->cpu_lpi = new->cpu_lpi - old->cpu_lpi; + old->sys_lpi = new->sys_lpi - old->sys_lpi; old->pkg_temp_c = new->pkg_temp_c; /* flag an error when rc6 counter resets/wraps */ @@ -1140,6 +1231,15 @@ delta_thread(struct thread_data *new, struct thread_data *old, int i; struct msr_counter *mp; + /* + * the timestamps from start of measurement interval are in "old" + * the timestamp from end of measurement interval are in "new" + * over-write old w/ new so we can print end of interval values + */ + + old->tv_begin = new->tv_begin; + old->tv_end = new->tv_end; + old->tsc = new->tsc - old->tsc; /* check for TSC < 1 Mcycles over interval */ @@ -1228,6 +1328,11 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data int i; struct msr_counter *mp; + t->tv_begin.tv_sec = 0; + t->tv_begin.tv_usec = 0; + t->tv_end.tv_sec = 0; + t->tv_end.tv_usec = 0; + t->tsc = 0; t->aperf = 0; t->mperf = 0; @@ -1260,6 +1365,8 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data p->pc8 = 0; p->pc9 = 0; p->pc10 = 0; + p->cpu_lpi = 0; + p->sys_lpi = 0; p->energy_pkg = 0; p->energy_dram = 0; @@ -1286,6 +1393,13 @@ int sum_counters(struct thread_data *t, struct core_data *c, int i; struct msr_counter *mp; + /* remember first tv_begin */ + if (average.threads.tv_begin.tv_sec == 0) + average.threads.tv_begin = t->tv_begin; + + /* remember last tv_end */ + average.threads.tv_end = t->tv_end; + average.threads.tsc += t->tsc; average.threads.aperf += t->aperf; average.threads.mperf += t->mperf; @@ -1341,6 +1455,9 @@ int sum_counters(struct thread_data *t, struct core_data *c, average.packages.pc9 += p->pc9; average.packages.pc10 += p->pc10; + average.packages.cpu_lpi = p->cpu_lpi; + average.packages.sys_lpi = p->sys_lpi; + average.packages.energy_pkg += p->energy_pkg; average.packages.energy_dram += p->energy_dram; average.packages.energy_cores += p->energy_cores; @@ -1487,7 +1604,7 @@ int get_mp(int cpu, struct msr_counter *mp, unsigned long long *counterp) if (get_msr(cpu, mp->msr_num, counterp)) return -1; } else { - char path[128]; + char path[128 + PATH_BYTES]; if (mp->flags & SYSFS_PERCPU) { sprintf(path, "/sys/devices/system/cpu/cpu%d/%s", @@ -1603,7 +1720,7 @@ retry: if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) goto done; - if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates) { + if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates) { if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3)) return -6; } @@ -1684,6 +1801,11 @@ retry: if (get_msr(cpu, MSR_PKG_C10_RESIDENCY, &p->pc10)) return -13; + if (DO_BIC(BIC_CPU_LPI)) + p->cpu_lpi = cpuidle_cur_cpu_lpi_us; + if (DO_BIC(BIC_SYS_LPI)) + p->sys_lpi = cpuidle_cur_sys_lpi_us; + if (do_rapl & RAPL_PKG) { if (get_msr(cpu, MSR_PKG_ENERGY_STATUS, &msr)) return -13; @@ -1769,7 +1891,7 @@ int slv_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCLRSV, PCLRSV, PCL__4, PCLRSV, int amt_pkg_cstate_limits[16] = {PCLUNL, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; int phi_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; int bxt_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; -int skx_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; +int skx_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; static void @@ -2071,12 +2193,9 @@ dump_nhm_cst_cfg(void) get_msr(base_cpu, MSR_PKG_CST_CONFIG_CONTROL, &msr); -#define SNB_C1_AUTO_UNDEMOTE (1UL << 27) -#define SNB_C3_AUTO_UNDEMOTE (1UL << 28) - fprintf(outf, "cpu%d: MSR_PKG_CST_CONFIG_CONTROL: 0x%08llx", base_cpu, msr); - fprintf(outf, " (%s%s%s%s%slocked: pkg-cstate-limit=%d: %s)\n", + fprintf(outf, " (%s%s%s%s%slocked, pkg-cstate-limit=%d (%s)", (msr & SNB_C3_AUTO_UNDEMOTE) ? "UNdemote-C3, " : "", (msr & SNB_C1_AUTO_UNDEMOTE) ? "UNdemote-C1, " : "", (msr & NHM_C3_AUTO_DEMOTE) ? "demote-C3, " : "", @@ -2084,6 +2203,15 @@ dump_nhm_cst_cfg(void) (msr & (1 << 15)) ? "" : "UN", (unsigned int)msr & 0xF, pkg_cstate_limit_strings[pkg_cstate_limit]); + +#define AUTOMATIC_CSTATE_CONVERSION (1UL << 16) + if (has_automatic_cstate_conversion) { + fprintf(outf, ", automatic c-state conversion=%s", + (msr & AUTOMATIC_CSTATE_CONVERSION) ? "on" : "off"); + } + + fprintf(outf, ")\n"); + return; } @@ -2184,6 +2312,8 @@ void free_fd_percpu(void) void free_all_buffers(void) { + int i; + CPU_FREE(cpu_present_set); cpu_present_set = NULL; cpu_present_setsize = 0; @@ -2216,6 +2346,12 @@ void free_all_buffers(void) free(irq_column_2_cpu); free(irqs_per_cpu); + + for (i = 0; i <= topo.max_cpu_num; ++i) { + if (cpus[i].put_ids) + CPU_FREE(cpus[i].put_ids); + } + free(cpus); } @@ -2240,44 +2376,6 @@ int parse_int_file(const char *fmt, ...) } /* - * get_cpu_position_in_core(cpu) - * return the position of the CPU among its HT siblings in the core - * return -1 if the sibling is not in list - */ -int get_cpu_position_in_core(int cpu) -{ - char path[64]; - FILE *filep; - int this_cpu; - char character; - int i; - - sprintf(path, - "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", - cpu); - filep = fopen(path, "r"); - if (filep == NULL) { - perror(path); - exit(1); - } - - for (i = 0; i < topo.num_threads_per_core; i++) { - fscanf(filep, "%d", &this_cpu); - if (this_cpu == cpu) { - fclose(filep); - return i; - } - - /* Account for no separator after last thread*/ - if (i != (topo.num_threads_per_core - 1)) - fscanf(filep, "%c", &character); - } - - fclose(filep); - return -1; -} - -/* * cpu_is_first_core_in_package(cpu) * return 1 if given CPU is 1st core in package */ @@ -2296,35 +2394,115 @@ int get_core_id(int cpu) return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/core_id", cpu); } -int get_num_ht_siblings(int cpu) +void set_node_data(void) { char path[80]; FILE *filep; - int sib1; - int matches = 0; - char character; - char str[100]; - char *ch; + int pkg, node, cpu; - sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", cpu); - filep = fopen_or_die(path, "r"); + struct pkg_node_info { + int count; + int min; + } *pni; - /* - * file format: - * A ',' separated or '-' separated set of numbers - * (eg 1-2 or 1,3,4,5) - */ - fscanf(filep, "%d%c\n", &sib1, &character); - fseek(filep, 0, SEEK_SET); - fgets(str, 100, filep); - ch = strchr(str, character); - while (ch != NULL) { - matches++; - ch = strchr(ch+1, character); + pni = calloc(topo.num_packages, sizeof(struct pkg_node_info)); + if (!pni) + err(1, "calloc pkg_node_count"); + + for (pkg = 0; pkg < topo.num_packages; pkg++) + pni[pkg].min = topo.num_cpus; + + for (node = 0; node <= topo.max_node_num; node++) { + /* find the "first" cpu in the node */ + sprintf(path, "/sys/bus/node/devices/node%d/cpulist", node); + filep = fopen(path, "r"); + if (!filep) + continue; + fscanf(filep, "%d", &cpu); + fclose(filep); + + pkg = cpus[cpu].physical_package_id; + pni[pkg].count++; + + if (node < pni[pkg].min) + pni[pkg].min = node; } + for (pkg = 0; pkg < topo.num_packages; pkg++) + if (pni[pkg].count > topo.nodes_per_pkg) + topo.nodes_per_pkg = pni[0].count; + + for (cpu = 0; cpu < topo.num_cpus; cpu++) { + pkg = cpus[cpu].physical_package_id; + node = cpus[cpu].physical_node_id; + cpus[cpu].logical_node_id = node - pni[pkg].min; + } + free(pni); + +} + +int get_physical_node_id(struct cpu_topology *thiscpu) +{ + char path[80]; + FILE *filep; + int i; + int cpu = thiscpu->logical_cpu_id; + + for (i = 0; i <= topo.max_cpu_num; i++) { + sprintf(path, "/sys/devices/system/cpu/cpu%d/node%i/cpulist", + cpu, i); + filep = fopen(path, "r"); + if (!filep) + continue; + fclose(filep); + return i; + } + return -1; +} + +int get_thread_siblings(struct cpu_topology *thiscpu) +{ + char path[80], character; + FILE *filep; + unsigned long map; + int so, shift, sib_core; + int cpu = thiscpu->logical_cpu_id; + int offset = topo.max_cpu_num + 1; + size_t size; + int thread_id = 0; + + thiscpu->put_ids = CPU_ALLOC((topo.max_cpu_num + 1)); + if (thiscpu->thread_id < 0) + thiscpu->thread_id = thread_id++; + if (!thiscpu->put_ids) + return -1; + + size = CPU_ALLOC_SIZE((topo.max_cpu_num + 1)); + CPU_ZERO_S(size, thiscpu->put_ids); + + sprintf(path, + "/sys/devices/system/cpu/cpu%d/topology/thread_siblings", cpu); + filep = fopen_or_die(path, "r"); + do { + offset -= BITMASK_SIZE; + fscanf(filep, "%lx%c", &map, &character); + for (shift = 0; shift < BITMASK_SIZE; shift++) { + if ((map >> shift) & 0x1) { + so = shift + offset; + sib_core = get_core_id(so); + if (sib_core == thiscpu->physical_core_id) { + CPU_SET_S(so, size, thiscpu->put_ids); + if ((so != cpu) && + (cpus[so].thread_id < 0)) + cpus[so].thread_id = + thread_id++; + } + } + } + } while (!strncmp(&character, ",", 1)); fclose(filep); - return matches+1; + + return CPU_COUNT_S(size, thiscpu->put_ids); } /* @@ -2339,32 +2517,42 @@ int for_all_cpus_2(int (func)(struct thread_data *, struct core_data *, struct thread_data *thread_base2, struct core_data *core_base2, struct pkg_data *pkg_base2) { - int retval, pkg_no, core_no, thread_no; + int retval, pkg_no, node_no, core_no, thread_no; for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) { - for (core_no = 0; core_no < topo.num_cores_per_pkg; ++core_no) { - for (thread_no = 0; thread_no < - topo.num_threads_per_core; ++thread_no) { - struct thread_data *t, *t2; - struct core_data *c, *c2; - struct pkg_data *p, *p2; - - t = GET_THREAD(thread_base, thread_no, core_no, pkg_no); - - if (cpu_is_not_present(t->cpu_id)) - continue; - - t2 = GET_THREAD(thread_base2, thread_no, core_no, pkg_no); - - c = GET_CORE(core_base, core_no, pkg_no); - c2 = GET_CORE(core_base2, core_no, pkg_no); - - p = GET_PKG(pkg_base, pkg_no); - p2 = GET_PKG(pkg_base2, pkg_no); - - retval = func(t, c, p, t2, c2, p2); - if (retval) - return retval; + for (node_no = 0; node_no < topo.nodes_per_pkg; ++node_no) { + for (core_no = 0; core_no < topo.cores_per_node; + ++core_no) { + for (thread_no = 0; thread_no < + topo.threads_per_core; ++thread_no) { + struct thread_data *t, *t2; + struct core_data *c, *c2; + struct pkg_data *p, *p2; + + t = GET_THREAD(thread_base, thread_no, + core_no, node_no, + pkg_no); + + if (cpu_is_not_present(t->cpu_id)) + continue; + + t2 = GET_THREAD(thread_base2, thread_no, + core_no, node_no, + pkg_no); + + c = GET_CORE(core_base, core_no, + node_no, pkg_no); + c2 = GET_CORE(core_base2, core_no, + node_no, + pkg_no); + + p = GET_PKG(pkg_base, pkg_no); + p2 = GET_PKG(pkg_base2, pkg_no); + + retval = func(t, c, p, t2, c2, p2); + if (retval) + return retval; + } } } } @@ -2409,6 +2597,20 @@ void re_initialize(void) printf("turbostat: re-initialized with num_cpus %d\n", topo.num_cpus); } +void set_max_cpu_num(void) +{ + FILE *filep; + unsigned long dummy; + + topo.max_cpu_num = 0; + filep = fopen_or_die( + "/sys/devices/system/cpu/cpu0/topology/thread_siblings", + "r"); + while (fscanf(filep, "%lx,", &dummy) == 1) + topo.max_cpu_num += BITMASK_SIZE; + fclose(filep); + topo.max_cpu_num--; /* 0 based */ +} /* * count_cpus() @@ -2416,10 +2618,7 @@ void re_initialize(void) */ int count_cpus(int cpu) { - if (topo.max_cpu_num < cpu) - topo.max_cpu_num = cpu; - - topo.num_cpus += 1; + topo.num_cpus++; return 0; } int mark_cpu_present(int cpu) @@ -2428,6 +2627,12 @@ int mark_cpu_present(int cpu) return 0; } +int init_thread_id(int cpu) +{ + cpus[cpu].thread_id = -1; + return 0; +} + /* * snapshot_proc_interrupts() * @@ -2542,6 +2747,52 @@ int snapshot_gfx_mhz(void) } /* + * snapshot_cpu_lpi() + * + * record snapshot of + * /sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us + * + * return 1 if config change requires a restart, else return 0 + */ +int snapshot_cpu_lpi_us(void) +{ + FILE *fp; + int retval; + + fp = fopen_or_die("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", "r"); + + retval = fscanf(fp, "%lld", &cpuidle_cur_cpu_lpi_us); + if (retval != 1) + err(1, "CPU LPI"); + + fclose(fp); + + return 0; +} +/* + * snapshot_sys_lpi() + * + * record snapshot of + * /sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us + * + * return 1 if config change requires a restart, else return 0 + */ +int snapshot_sys_lpi_us(void) +{ + FILE *fp; + int retval; + + fp = fopen_or_die("/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us", "r"); + + retval = fscanf(fp, "%lld", &cpuidle_cur_sys_lpi_us); + if (retval != 1) + err(1, "SYS LPI"); + + fclose(fp); + + return 0; +} +/* * snapshot /proc and /sys files * * return 1 if configuration restart needed, else return 0 @@ -2558,13 +2809,83 @@ int snapshot_proc_sysfs_files(void) if (DO_BIC(BIC_GFXMHz)) snapshot_gfx_mhz(); + if (DO_BIC(BIC_CPU_LPI)) + snapshot_cpu_lpi_us(); + + if (DO_BIC(BIC_SYS_LPI)) + snapshot_sys_lpi_us(); + return 0; } +int exit_requested; + +static void signal_handler (int signal) +{ + switch (signal) { + case SIGINT: + exit_requested = 1; + if (debug) + fprintf(stderr, " SIGINT\n"); + break; + case SIGUSR1: + if (debug > 1) + fprintf(stderr, "SIGUSR1\n"); + break; + } + /* make sure this manually-invoked interval is at least 1ms long */ + nanosleep(&one_msec, NULL); +} + +void setup_signal_handler(void) +{ + struct sigaction sa; + + memset(&sa, 0, sizeof(sa)); + + sa.sa_handler = &signal_handler; + + if (sigaction(SIGINT, &sa, NULL) < 0) + err(1, "sigaction SIGINT"); + if (sigaction(SIGUSR1, &sa, NULL) < 0) + err(1, "sigaction SIGUSR1"); +} + +void do_sleep(void) +{ + struct timeval select_timeout; + fd_set readfds; + int retval; + + FD_ZERO(&readfds); + FD_SET(0, &readfds); + + if (!isatty(fileno(stdin))) { + nanosleep(&interval_ts, NULL); + return; + } + + select_timeout = interval_tv; + retval = select(1, &readfds, NULL, NULL, &select_timeout); + + if (retval == 1) { + switch (getc(stdin)) { + case 'q': + exit_requested = 1; + break; + } + /* make sure this manually-invoked interval is at least 1ms long */ + nanosleep(&one_msec, NULL); + } +} + void turbostat_loop() { int retval; int restarted = 0; + int done_iters = 0; + + setup_signal_handler(); restart: restarted++; @@ -2581,6 +2902,7 @@ restart: goto restart; } restarted = 0; + done_iters = 0; gettimeofday(&tv_even, (struct timezone *)NULL); while (1) { @@ -2588,7 +2910,7 @@ restart: re_initialize(); goto restart; } - nanosleep(&interval_ts, NULL); + do_sleep(); if (snapshot_proc_sysfs_files()) goto restart; retval = for_all_cpus(get_counters, ODD_COUNTERS); @@ -2607,7 +2929,11 @@ restart: compute_average(EVEN_COUNTERS); format_all_counters(EVEN_COUNTERS); flush_output_stdout(); - nanosleep(&interval_ts, NULL); + if (exit_requested) + break; + if (num_iterations && ++done_iters >= num_iterations) + break; + do_sleep(); if (snapshot_proc_sysfs_files()) goto restart; retval = for_all_cpus(get_counters, EVEN_COUNTERS); @@ -2626,6 +2952,10 @@ restart: compute_average(ODD_COUNTERS); format_all_counters(ODD_COUNTERS); flush_output_stdout(); + if (exit_requested) + break; + if (num_iterations && ++done_iters >= num_iterations) + break; } } @@ -2740,6 +3070,7 @@ int probe_nhm_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_SKYLAKE_DESKTOP: /* SKL */ case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */ case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */ + case INTEL_FAM6_CANNONLAKE_MOBILE: /* CNL */ pkg_cstate_limits = hsw_pkg_cstate_limits; has_misc_feature_control = 1; break; @@ -2945,6 +3276,7 @@ int has_config_tdp(unsigned int family, unsigned int model) case INTEL_FAM6_SKYLAKE_DESKTOP: /* SKL */ case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */ case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */ + case INTEL_FAM6_CANNONLAKE_MOBILE: /* CNL */ case INTEL_FAM6_SKYLAKE_X: /* SKX */ case INTEL_FAM6_XEON_PHI_KNL: /* Knights Landing */ @@ -3399,6 +3731,7 @@ void rapl_probe(unsigned int family, unsigned int model) case INTEL_FAM6_SKYLAKE_DESKTOP: /* SKL */ case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */ case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */ + case INTEL_FAM6_CANNONLAKE_MOBILE: /* CNL */ do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_GFX | RAPL_PKG_POWER_INFO; BIC_PRESENT(BIC_PKG__); BIC_PRESENT(BIC_RAM__); @@ -3523,6 +3856,12 @@ void perf_limit_reasons_probe(unsigned int family, unsigned int model) } } +void automatic_cstate_conversion_probe(unsigned int family, unsigned int model) +{ + if (is_skx(family, model) || is_bdx(family, model)) + has_automatic_cstate_conversion = 1; +} + int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p) { unsigned long long msr; @@ -3728,6 +4067,7 @@ int has_snb_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_SKYLAKE_DESKTOP: /* SKL */ case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */ case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */ + case INTEL_FAM6_CANNONLAKE_MOBILE: /* CNL */ case INTEL_FAM6_SKYLAKE_X: /* SKX */ case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ case INTEL_FAM6_ATOM_GEMINI_LAKE: @@ -3761,6 +4101,7 @@ int has_hsw_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_SKYLAKE_DESKTOP: /* SKL */ case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */ case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */ + case INTEL_FAM6_CANNONLAKE_MOBILE: /* CNL */ case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ case INTEL_FAM6_ATOM_GEMINI_LAKE: return 1; @@ -3786,6 +4127,7 @@ int has_skl_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_SKYLAKE_DESKTOP: /* SKL */ case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */ case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */ + case INTEL_FAM6_CANNONLAKE_MOBILE: /* CNL */ return 1; } return 0; @@ -3815,6 +4157,19 @@ int is_knl(unsigned int family, unsigned int model) return 0; } +int is_cnl(unsigned int family, unsigned int model) +{ + if (!genuine_intel) + return 0; + + switch (model) { + case INTEL_FAM6_CANNONLAKE_MOBILE: /* CNL */ + return 1; + } + + return 0; +} + unsigned int get_aperf_mperf_multiplier(unsigned int family, unsigned int model) { if (is_knl(family, model)) @@ -3947,7 +4302,7 @@ void decode_misc_enable_msr(void) base_cpu, msr, msr & MSR_IA32_MISC_ENABLE_TM1 ? "" : "No-", msr & MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP ? "" : "No-", - msr & MSR_IA32_MISC_ENABLE_MWAIT ? "No-" : "", + msr & MSR_IA32_MISC_ENABLE_MWAIT ? "" : "No-", msr & MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE ? "No-" : "", msr & MSR_IA32_MISC_ENABLE_TURBO_DISABLE ? "No-" : ""); } @@ -4152,7 +4507,6 @@ void process_cpuid() case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */ crystal_hz = 24000000; /* 24.0 MHz */ break; - case INTEL_FAM6_SKYLAKE_X: /* SKX */ case INTEL_FAM6_ATOM_DENVERTON: /* DNV */ crystal_hz = 25000000; /* 25.0 MHz */ break; @@ -4253,6 +4607,7 @@ void process_cpuid() } do_slm_cstates = is_slm(family, model); do_knl_cstates = is_knl(family, model); + do_cnl_cstates = is_cnl(family, model); if (!quiet) decode_misc_pwr_mgmt_msr(); @@ -4262,6 +4617,7 @@ void process_cpuid() rapl_probe(family, model); perf_limit_reasons_probe(family, model); + automatic_cstate_conversion_probe(family, model); if (!quiet) dump_cstate_pstate_config_info(family, model); @@ -4280,6 +4636,16 @@ void process_cpuid() if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK)) BIC_PRESENT(BIC_GFXMHz); + if (!access("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", R_OK)) + BIC_PRESENT(BIC_CPU_LPI); + else + BIC_NOT_PRESENT(BIC_CPU_LPI); + + if (!access("/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us", R_OK)) + BIC_PRESENT(BIC_SYS_LPI); + else + BIC_NOT_PRESENT(BIC_SYS_LPI); + if (!quiet) decode_misc_feature_control(); @@ -4310,14 +4676,10 @@ void topology_probe() int max_core_id = 0; int max_package_id = 0; int max_siblings = 0; - struct cpu_topology { - int core_id; - int physical_package_id; - } *cpus; /* Initialize num_cpus, max_cpu_num */ + set_max_cpu_num(); topo.num_cpus = 0; - topo.max_cpu_num = 0; for_all_proc_cpus(count_cpus); if (!summary_only && topo.num_cpus > 1) BIC_PRESENT(BIC_CPU); @@ -4357,6 +4719,7 @@ void topology_probe() cpu_affinity_setsize = CPU_ALLOC_SIZE((topo.max_cpu_num + 1)); CPU_ZERO_S(cpu_affinity_setsize, cpu_affinity_set); + for_all_proc_cpus(init_thread_id); /* * For online cpus @@ -4370,26 +4733,45 @@ void topology_probe() fprintf(outf, "cpu%d NOT PRESENT\n", i); continue; } - cpus[i].core_id = get_core_id(i); - if (cpus[i].core_id > max_core_id) - max_core_id = cpus[i].core_id; + cpus[i].logical_cpu_id = i; + + /* get package information */ cpus[i].physical_package_id = get_physical_package_id(i); if (cpus[i].physical_package_id > max_package_id) max_package_id = cpus[i].physical_package_id; - siblings = get_num_ht_siblings(i); + /* get numa node information */ + cpus[i].physical_node_id = get_physical_node_id(&cpus[i]); + if (cpus[i].physical_node_id > topo.max_node_num) + topo.max_node_num = cpus[i].physical_node_id; + + /* get core information */ + cpus[i].physical_core_id = get_core_id(i); + if (cpus[i].physical_core_id > max_core_id) + max_core_id = cpus[i].physical_core_id; + + /* get thread information */ + siblings = get_thread_siblings(&cpus[i]); if (siblings > max_siblings) max_siblings = siblings; + if (cpus[i].thread_id != -1) + topo.num_cores++; + if (debug > 1) - fprintf(outf, "cpu %d pkg %d core %d\n", - i, cpus[i].physical_package_id, cpus[i].core_id); + fprintf(outf, + "cpu %d pkg %d node %d core %d thread %d\n", + i, cpus[i].physical_package_id, + cpus[i].physical_node_id, + cpus[i].physical_core_id, + cpus[i].thread_id); } - topo.num_cores_per_pkg = max_core_id + 1; + + topo.cores_per_node = max_core_id + 1; if (debug > 1) fprintf(outf, "max_core_id %d, sizing for %d cores per package\n", - max_core_id, topo.num_cores_per_pkg); - if (!summary_only && topo.num_cores_per_pkg > 1) + max_core_id, topo.cores_per_node); + if (!summary_only && topo.cores_per_node > 1) BIC_PRESENT(BIC_Core); topo.num_packages = max_package_id + 1; @@ -4399,33 +4781,38 @@ void topology_probe() if (!summary_only && topo.num_packages > 1) BIC_PRESENT(BIC_Package); - topo.num_threads_per_core = max_siblings; + set_node_data(); if (debug > 1) - fprintf(outf, "max_siblings %d\n", max_siblings); + fprintf(outf, "nodes_per_pkg %d\n", topo.nodes_per_pkg); + if (!summary_only && topo.nodes_per_pkg > 1) + BIC_PRESENT(BIC_Node); - free(cpus); + topo.threads_per_core = max_siblings; + if (debug > 1) + fprintf(outf, "max_siblings %d\n", max_siblings); } void -allocate_counters(struct thread_data **t, struct core_data **c, struct pkg_data **p) +allocate_counters(struct thread_data **t, struct core_data **c, + struct pkg_data **p) { int i; + int num_cores = topo.cores_per_node * topo.nodes_per_pkg * + topo.num_packages; + int num_threads = topo.threads_per_core * num_cores; - *t = calloc(topo.num_threads_per_core * topo.num_cores_per_pkg * - topo.num_packages, sizeof(struct thread_data)); + *t = calloc(num_threads, sizeof(struct thread_data)); if (*t == NULL) goto error; - for (i = 0; i < topo.num_threads_per_core * - topo.num_cores_per_pkg * topo.num_packages; i++) + for (i = 0; i < num_threads; i++) (*t)[i].cpu_id = -1; - *c = calloc(topo.num_cores_per_pkg * topo.num_packages, - sizeof(struct core_data)); + *c = calloc(num_cores, sizeof(struct core_data)); if (*c == NULL) goto error; - for (i = 0; i < topo.num_cores_per_pkg * topo.num_packages; i++) + for (i = 0; i < num_cores; i++) (*c)[i].core_id = -1; *p = calloc(topo.num_packages, sizeof(struct pkg_data)); @@ -4442,47 +4829,39 @@ error: /* * init_counter() * - * set cpu_id, core_num, pkg_num * set FIRST_THREAD_IN_CORE and FIRST_CORE_IN_PACKAGE - * - * increment topo.num_cores when 1st core in pkg seen */ void init_counter(struct thread_data *thread_base, struct core_data *core_base, - struct pkg_data *pkg_base, int thread_num, int core_num, - int pkg_num, int cpu_id) + struct pkg_data *pkg_base, int cpu_id) { + int pkg_id = cpus[cpu_id].physical_package_id; + int node_id = cpus[cpu_id].logical_node_id; + int core_id = cpus[cpu_id].physical_core_id; + int thread_id = cpus[cpu_id].thread_id; struct thread_data *t; struct core_data *c; struct pkg_data *p; - t = GET_THREAD(thread_base, thread_num, core_num, pkg_num); - c = GET_CORE(core_base, core_num, pkg_num); - p = GET_PKG(pkg_base, pkg_num); + t = GET_THREAD(thread_base, thread_id, core_id, node_id, pkg_id); + c = GET_CORE(core_base, core_id, node_id, pkg_id); + p = GET_PKG(pkg_base, pkg_id); t->cpu_id = cpu_id; - if (thread_num == 0) { + if (thread_id == 0) { t->flags |= CPU_IS_FIRST_THREAD_IN_CORE; if (cpu_is_first_core_in_package(cpu_id)) t->flags |= CPU_IS_FIRST_CORE_IN_PACKAGE; } - c->core_id = core_num; - p->package_id = pkg_num; + c->core_id = core_id; + p->package_id = pkg_id; } int initialize_counters(int cpu_id) { - int my_thread_id, my_core_id, my_package_id; - - my_package_id = get_physical_package_id(cpu_id); - my_core_id = get_core_id(cpu_id); - my_thread_id = get_cpu_position_in_core(cpu_id); - if (!my_thread_id) - topo.num_cores++; - - init_counter(EVEN_COUNTERS, my_thread_id, my_core_id, my_package_id, cpu_id); - init_counter(ODD_COUNTERS, my_thread_id, my_core_id, my_package_id, cpu_id); + init_counter(EVEN_COUNTERS, cpu_id); + init_counter(ODD_COUNTERS, cpu_id); return 0; } @@ -4630,7 +5009,7 @@ int get_and_dump_counters(void) } void print_version() { - fprintf(outf, "turbostat version 17.06.23" + fprintf(outf, "turbostat version 18.06.01" " - Len Brown <lenb@kernel.org>\n"); } @@ -4661,7 +5040,7 @@ int add_counter(unsigned int msr_num, char *path, char *name, msrp->next = sys.tp; sys.tp = msrp; sys.added_thread_counters++; - if (sys.added_thread_counters > MAX_ADDED_COUNTERS) { + if (sys.added_thread_counters > MAX_ADDED_THREAD_COUNTERS) { fprintf(stderr, "exceeded max %d added thread counters\n", MAX_ADDED_COUNTERS); exit(-1); @@ -4820,7 +5199,7 @@ void probe_sysfs(void) if (!DO_BIC(BIC_sysfs)) return; - for (state = 10; state > 0; --state) { + for (state = 10; state >= 0; --state) { sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/name", base_cpu, state); @@ -4847,7 +5226,7 @@ void probe_sysfs(void) FORMAT_PERCENT, SYSFS_PERCPU); } - for (state = 10; state > 0; --state) { + for (state = 10; state >= 0; --state) { sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/name", base_cpu, state); @@ -4960,34 +5339,6 @@ error: exit(-1); } -int shown; -/* - * parse_show_hide() - process cmdline to set default counter action - */ -void parse_show_hide(char *optarg, enum show_hide_mode new_mode) -{ - /* - * --show: show only those specified - * The 1st invocation will clear and replace the enabled mask - * subsequent invocations can add to it. - */ - if (new_mode == SHOW_LIST) { - if (shown == 0) - bic_enabled = bic_lookup(optarg, new_mode); - else - bic_enabled |= bic_lookup(optarg, new_mode); - shown = 1; - - return; - } - - /* - * --hide: do not show those specified - * multiple invocations simply clear more bits in enabled mask - */ - bic_enabled &= ~bic_lookup(optarg, new_mode); - -} void cmdline(int argc, char **argv) { @@ -4998,7 +5349,9 @@ void cmdline(int argc, char **argv) {"cpu", required_argument, 0, 'c'}, {"Dump", no_argument, 0, 'D'}, {"debug", no_argument, 0, 'd'}, /* internal, not documented */ + {"enable", required_argument, 0, 'e'}, {"interval", required_argument, 0, 'i'}, + {"num_iterations", required_argument, 0, 'n'}, {"help", no_argument, 0, 'h'}, {"hide", required_argument, 0, 'H'}, // meh, -h taken by --help {"Joules", no_argument, 0, 'J'}, @@ -5014,7 +5367,7 @@ void cmdline(int argc, char **argv) progname = argv[0]; - while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:JM:m:o:qST:v", + while ((opt = getopt_long_only(argc, argv, "+C:c:Dde:hi:Jn:o:qST:v", long_options, &option_index)) != -1) { switch (opt) { case 'a': @@ -5026,11 +5379,20 @@ void cmdline(int argc, char **argv) case 'D': dump_only++; break; + case 'e': + /* --enable specified counter */ + bic_enabled |= bic_lookup(optarg, SHOW_LIST); + break; case 'd': debug++; + ENABLE_BIC(BIC_DISABLED_BY_DEFAULT); break; case 'H': - parse_show_hide(optarg, HIDE_LIST); + /* + * --hide: do not show those specified + * multiple invocations simply clear more bits in enabled mask + */ + bic_enabled &= ~bic_lookup(optarg, HIDE_LIST); break; case 'h': default: @@ -5046,7 +5408,8 @@ void cmdline(int argc, char **argv) exit(2); } - interval_ts.tv_sec = interval; + interval_tv.tv_sec = interval_ts.tv_sec = interval; + interval_tv.tv_usec = (interval - interval_tv.tv_sec) * 1000000; interval_ts.tv_nsec = (interval - interval_ts.tv_sec) * 1000000000; } break; @@ -5054,6 +5417,7 @@ void cmdline(int argc, char **argv) rapl_joules++; break; case 'l': + ENABLE_BIC(BIC_DISABLED_BY_DEFAULT); list_header_only++; quiet++; break; @@ -5063,8 +5427,26 @@ void cmdline(int argc, char **argv) case 'q': quiet = 1; break; + case 'n': + num_iterations = strtod(optarg, NULL); + + if (num_iterations <= 0) { + fprintf(outf, "iterations %d should be positive number\n", + num_iterations); + exit(2); + } + break; case 's': - parse_show_hide(optarg, SHOW_LIST); + /* + * --show: show only those specified + * The 1st invocation will clear and replace the enabled mask + * subsequent invocations can add to it. + */ + if (shown == 0) + bic_enabled = bic_lookup(optarg, SHOW_LIST); + else + bic_enabled |= bic_lookup(optarg, SHOW_LIST); + shown = 1; break; case 'S': summary_only++; diff --git a/tools/power/x86/x86_energy_perf_policy/Makefile b/tools/power/x86/x86_energy_perf_policy/Makefile index 2447b1b..f4534fb 100644 --- a/tools/power/x86/x86_energy_perf_policy/Makefile +++ b/tools/power/x86/x86_energy_perf_policy/Makefile @@ -24,5 +24,5 @@ install : x86_energy_perf_policy install -d $(DESTDIR)$(PREFIX)/bin install $(BUILD_OUTPUT)/x86_energy_perf_policy $(DESTDIR)$(PREFIX)/bin/x86_energy_perf_policy install -d $(DESTDIR)$(PREFIX)/share/man/man8 - install x86_energy_perf_policy.8 $(DESTDIR)$(PREFIX)/share/man/man8 + install -m 644 x86_energy_perf_policy.8 $(DESTDIR)$(PREFIX)/share/man/man8 diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index 4ea385b..a8fb63e 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -29,6 +29,8 @@ #include "nfit_test.h" #include "../watermark.h" +#include <asm/mcsafe_test.h> + /* * Generate an NFIT table to describe the following topology: * @@ -2681,6 +2683,107 @@ static struct platform_driver nfit_test_driver = { .id_table = nfit_test_id, }; +static char mcsafe_buf[PAGE_SIZE] __attribute__((__aligned__(PAGE_SIZE))); + +enum INJECT { + INJECT_NONE, + INJECT_SRC, + INJECT_DST, +}; + +static void mcsafe_test_init(char *dst, char *src, size_t size) +{ + size_t i; + + memset(dst, 0xff, size); + for (i = 0; i < size; i++) + src[i] = (char) i; +} + +static bool mcsafe_test_validate(unsigned char *dst, unsigned char *src, + size_t size, unsigned long rem) +{ + size_t i; + + for (i = 0; i < size - rem; i++) + if (dst[i] != (unsigned char) i) { + pr_info_once("%s:%d: offset: %zd got: %#x expect: %#x\n", + __func__, __LINE__, i, dst[i], + (unsigned char) i); + return false; + } + for (i = size - rem; i < size; i++) + if (dst[i] != 0xffU) { + pr_info_once("%s:%d: offset: %zd got: %#x expect: 0xff\n", + __func__, __LINE__, i, dst[i]); + return false; + } + return true; +} + +void mcsafe_test(void) +{ + char *inject_desc[] = { "none", "source", "destination" }; + enum INJECT inj; + + if (IS_ENABLED(CONFIG_MCSAFE_TEST)) { + pr_info("%s: run...\n", __func__); + } else { + pr_info("%s: disabled, skip.\n", __func__); + return; + } + + for (inj = INJECT_NONE; inj <= INJECT_DST; inj++) { + int i; + + pr_info("%s: inject: %s\n", __func__, inject_desc[inj]); + for (i = 0; i < 512; i++) { + unsigned long expect, rem; + void *src, *dst; + bool valid; + + switch (inj) { + case INJECT_NONE: + mcsafe_inject_src(NULL); + mcsafe_inject_dst(NULL); + dst = &mcsafe_buf[2048]; + src = &mcsafe_buf[1024 - i]; + expect = 0; + break; + case INJECT_SRC: + mcsafe_inject_src(&mcsafe_buf[1024]); + mcsafe_inject_dst(NULL); + dst = &mcsafe_buf[2048]; + src = &mcsafe_buf[1024 - i]; + expect = 512 - i; + break; + case INJECT_DST: + mcsafe_inject_src(NULL); + mcsafe_inject_dst(&mcsafe_buf[2048]); + dst = &mcsafe_buf[2048 - i]; + src = &mcsafe_buf[1024]; + expect = 512 - i; + break; + } + + mcsafe_test_init(dst, src, 512); + rem = __memcpy_mcsafe(dst, src, 512); + valid = mcsafe_test_validate(dst, src, 512, expect); + if (rem == expect && valid) + continue; + pr_info("%s: copy(%#lx, %#lx, %d) off: %d rem: %ld %s expect: %ld\n", + __func__, + ((unsigned long) dst) & ~PAGE_MASK, + ((unsigned long ) src) & ~PAGE_MASK, + 512, i, rem, valid ? "valid" : "bad", + expect); + } + } + + mcsafe_inject_src(NULL); + mcsafe_inject_dst(NULL); +} + static __init int nfit_test_init(void) { int rc, i; @@ -2689,6 +2792,7 @@ static __init int nfit_test_init(void) libnvdimm_test(); acpi_nfit_test(); device_dax_test(); + mcsafe_test(); nfit_test_setup(nfit_test_lookup, nfit_test_evaluate_dsm); diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 305130d..f1fe492 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -29,10 +29,12 @@ TARGETS += powerpc TARGETS += proc TARGETS += pstore TARGETS += ptrace +TARGETS += rseq TARGETS += rtc TARGETS += seccomp TARGETS += sigaltstack TARGETS += size +TARGETS += sparc64 TARGETS += splice TARGETS += static_keys TARGETS += sync diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 5e1ab2f..49938d7 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -15,3 +15,7 @@ test_libbpf_open test_sock test_sock_addr urandom_read +test_btf +test_sockmap +test_lirc_mode2_user +get_cgroup_id_user diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 0a315dd..607ed87 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -10,7 +10,7 @@ ifneq ($(wildcard $(GENHDR)),) GENFLAGS := -DHAVE_GENHDR endif -CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include +CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(BPFDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include LDLIBS += -lcap -lelf -lrt -lpthread TEST_CUSTOM_PROGS = $(OUTPUT)/urandom_read @@ -19,19 +19,23 @@ all: $(TEST_CUSTOM_PROGS) $(TEST_CUSTOM_PROGS): urandom_read urandom_read: urandom_read.c - $(CC) -o $(TEST_CUSTOM_PROGS) -static $< + $(CC) -o $(TEST_CUSTOM_PROGS) -static $< -Wl,--build-id # Order correspond to 'make run_tests' order TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \ - test_sock test_sock_addr + test_sock test_btf test_sockmap test_lirc_mode2_user get_cgroup_id_user TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \ test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \ sockmap_verdict_prog.o dev_cgroup.o sample_ret0.o test_tracepoint.o \ test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o \ sample_map_ret0.o test_tcpbpf_kern.o test_stacktrace_build_id.o \ - sockmap_tcp_msg_prog.o connect4_prog.o connect6_prog.o + sockmap_tcp_msg_prog.o connect4_prog.o connect6_prog.o test_adjust_tail.o \ + test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o test_tunnel_kern.o \ + test_get_stack_rawtp.o test_sockmap_kern.o test_sockhash_kern.o \ + test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \ + get_cgroup_id_kern.o # Order correspond to 'make run_tests' order TEST_PROGS := test_kmod.sh \ @@ -39,10 +43,13 @@ TEST_PROGS := test_kmod.sh \ test_xdp_redirect.sh \ test_xdp_meta.sh \ test_offload.py \ - test_sock_addr.sh + test_sock_addr.sh \ + test_tunnel.sh \ + test_lwt_seg6local.sh \ + test_lirc_mode2.sh # Compile but not part of 'make run_tests' -TEST_GEN_PROGS_EXTENDED = test_libbpf_open +TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr include ../lib.mk @@ -55,6 +62,9 @@ $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/libbpf.a $(OUTPUT)/test_dev_cgroup: cgroup_helpers.c $(OUTPUT)/test_sock: cgroup_helpers.c $(OUTPUT)/test_sock_addr: cgroup_helpers.c +$(OUTPUT)/test_sockmap: cgroup_helpers.c +$(OUTPUT)/test_progs: trace_helpers.c +$(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c .PHONY: force @@ -66,6 +76,8 @@ $(BPFOBJ): force CLANG ?= clang LLC ?= llc +LLVM_OBJCOPY ?= llvm-objcopy +BTF_PAHOLE ?= pahole PROBE := $(shell $(LLC) -march=bpf -mcpu=probe -filetype=null /dev/null 2>&1) @@ -77,15 +89,42 @@ else CPU ?= generic endif +# Get Clang's default includes on this system, as opposed to those seen by +# '-target bpf'. This fixes "missing" files on some architectures/distros, +# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc. +# +# Use '-idirafter': Don't interfere with include mechanics except where the +# build would have failed anyways. +CLANG_SYS_INCLUDES := $(shell $(CLANG) -v -E - </dev/null 2>&1 \ + | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') + CLANG_FLAGS = -I. -I./include/uapi -I../../../include/uapi \ + $(CLANG_SYS_INCLUDES) \ -Wno-compare-distinct-pointer-types $(OUTPUT)/test_l4lb_noinline.o: CLANG_FLAGS += -fno-inline $(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline +BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris) +BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF) +BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --version 2>&1 | grep LLVM) + +ifneq ($(BTF_LLC_PROBE),) +ifneq ($(BTF_PAHOLE_PROBE),) +ifneq ($(BTF_OBJCOPY_PROBE),) + CLANG_FLAGS += -g + LLC_FLAGS += -mattr=dwarfris + DWARF2BTF = y +endif +endif +endif + $(OUTPUT)/%.o: %.c $(CLANG) $(CLANG_FLAGS) \ -O2 -target bpf -emit-llvm -c $< -o - | \ - $(LLC) -march=bpf -mcpu=$(CPU) -filetype=obj -o $@ + $(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@ +ifeq ($(DWARF2BTF),y) + $(BTF_PAHOLE) -J $@ +endif EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index d8223d9..f2f28b6 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -75,9 +75,14 @@ static int (*bpf_sock_ops_cb_flags_set)(void *ctx, int flags) = (void *) BPF_FUNC_sock_ops_cb_flags_set; static int (*bpf_sk_redirect_map)(void *ctx, void *map, int key, int flags) = (void *) BPF_FUNC_sk_redirect_map; +static int (*bpf_sk_redirect_hash)(void *ctx, void *map, void *key, int flags) = + (void *) BPF_FUNC_sk_redirect_hash; static int (*bpf_sock_map_update)(void *map, void *key, void *value, unsigned long long flags) = (void *) BPF_FUNC_sock_map_update; +static int (*bpf_sock_hash_update)(void *map, void *key, void *value, + unsigned long long flags) = + (void *) BPF_FUNC_sock_hash_update; static int (*bpf_perf_event_read_value)(void *map, unsigned long long flags, void *buf, unsigned int buf_size) = (void *) BPF_FUNC_perf_event_read_value; @@ -88,6 +93,9 @@ static int (*bpf_override_return)(void *ctx, unsigned long rc) = (void *) BPF_FUNC_override_return; static int (*bpf_msg_redirect_map)(void *ctx, void *map, int key, int flags) = (void *) BPF_FUNC_msg_redirect_map; +static int (*bpf_msg_redirect_hash)(void *ctx, + void *map, void *key, int flags) = + (void *) BPF_FUNC_msg_redirect_hash; static int (*bpf_msg_apply_bytes)(void *ctx, int len) = (void *) BPF_FUNC_msg_apply_bytes; static int (*bpf_msg_cork_bytes)(void *ctx, int len) = @@ -96,6 +104,35 @@ static int (*bpf_msg_pull_data)(void *ctx, int start, int end, int flags) = (void *) BPF_FUNC_msg_pull_data; static int (*bpf_bind)(void *ctx, void *addr, int addr_len) = (void *) BPF_FUNC_bind; +static int (*bpf_xdp_adjust_tail)(void *ctx, int offset) = + (void *) BPF_FUNC_xdp_adjust_tail; +static int (*bpf_skb_get_xfrm_state)(void *ctx, int index, void *state, + int size, int flags) = + (void *) BPF_FUNC_skb_get_xfrm_state; +static int (*bpf_get_stack)(void *ctx, void *buf, int size, int flags) = + (void *) BPF_FUNC_get_stack; +static int (*bpf_fib_lookup)(void *ctx, struct bpf_fib_lookup *params, + int plen, __u32 flags) = + (void *) BPF_FUNC_fib_lookup; +static int (*bpf_lwt_push_encap)(void *ctx, unsigned int type, void *hdr, + unsigned int len) = + (void *) BPF_FUNC_lwt_push_encap; +static int (*bpf_lwt_seg6_store_bytes)(void *ctx, unsigned int offset, + void *from, unsigned int len) = + (void *) BPF_FUNC_lwt_seg6_store_bytes; +static int (*bpf_lwt_seg6_action)(void *ctx, unsigned int action, void *param, + unsigned int param_len) = + (void *) BPF_FUNC_lwt_seg6_action; +static int (*bpf_lwt_seg6_adjust_srh)(void *ctx, unsigned int offset, + unsigned int len) = + (void *) BPF_FUNC_lwt_seg6_adjust_srh; +static int (*bpf_rc_repeat)(void *ctx) = + (void *) BPF_FUNC_rc_repeat; +static int (*bpf_rc_keydown)(void *ctx, unsigned int protocol, + unsigned long long scancode, unsigned int toggle) = + (void *) BPF_FUNC_rc_keydown; +static unsigned long long (*bpf_get_current_cgroup_id)(void) = + (void *) BPF_FUNC_get_current_cgroup_id; /* llvm builtin functions that eBPF C program may use to * emit BPF_LD_ABS and BPF_LD_IND instructions @@ -129,6 +166,8 @@ static int (*bpf_l3_csum_replace)(void *ctx, int off, int from, int to, int flag (void *) BPF_FUNC_l3_csum_replace; static int (*bpf_l4_csum_replace)(void *ctx, int off, int from, int to, int flags) = (void *) BPF_FUNC_l4_csum_replace; +static int (*bpf_csum_diff)(void *from, int from_size, void *to, int to_size, int seed) = + (void *) BPF_FUNC_csum_diff; static int (*bpf_skb_under_cgroup)(void *ctx, void *map, int index) = (void *) BPF_FUNC_skb_under_cgroup; static int (*bpf_skb_change_head)(void *, int len, int flags) = diff --git a/tools/testing/selftests/bpf/bpf_rand.h b/tools/testing/selftests/bpf/bpf_rand.h new file mode 100644 index 0000000..59bf3e1 --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_rand.h @@ -0,0 +1,80 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __BPF_RAND__ +#define __BPF_RAND__ + +#include <stdint.h> +#include <stdlib.h> +#include <time.h> + +static inline uint64_t bpf_rand_mask(uint64_t mask) +{ + return (((uint64_t)(uint32_t)rand()) | + ((uint64_t)(uint32_t)rand() << 32)) & mask; +} + +#define bpf_rand_ux(x, m) \ +static inline uint64_t bpf_rand_u##x(int shift) \ +{ \ + return bpf_rand_mask((m)) << shift; \ +} + +bpf_rand_ux( 8, 0xffULL) +bpf_rand_ux(16, 0xffffULL) +bpf_rand_ux(24, 0xffffffULL) +bpf_rand_ux(32, 0xffffffffULL) +bpf_rand_ux(40, 0xffffffffffULL) +bpf_rand_ux(48, 0xffffffffffffULL) +bpf_rand_ux(56, 0xffffffffffffffULL) +bpf_rand_ux(64, 0xffffffffffffffffULL) + +static inline void bpf_semi_rand_init(void) +{ + srand(time(NULL)); +} + +static inline uint64_t bpf_semi_rand_get(void) +{ + switch (rand() % 39) { + case 0: return 0x000000ff00000000ULL | bpf_rand_u8(0); + case 1: return 0xffffffff00000000ULL | bpf_rand_u16(0); + case 2: return 0x00000000ffff0000ULL | bpf_rand_u16(0); + case 3: return 0x8000000000000000ULL | bpf_rand_u32(0); + case 4: return 0x00000000f0000000ULL | bpf_rand_u32(0); + case 5: return 0x0000000100000000ULL | bpf_rand_u24(0); + case 6: return 0x800ff00000000000ULL | bpf_rand_u32(0); + case 7: return 0x7fffffff00000000ULL | bpf_rand_u32(0); + case 8: return 0xffffffffffffff00ULL ^ bpf_rand_u32(24); + case 9: return 0xffffffffffffff00ULL | bpf_rand_u8(0); + case 10: return 0x0000000010000000ULL | bpf_rand_u32(0); + case 11: return 0xf000000000000000ULL | bpf_rand_u8(0); + case 12: return 0x0000f00000000000ULL | bpf_rand_u8(8); + case 13: return 0x000000000f000000ULL | bpf_rand_u8(16); + case 14: return 0x0000000000000f00ULL | bpf_rand_u8(32); + case 15: return 0x00fff00000000f00ULL | bpf_rand_u8(48); + case 16: return 0x00007fffffffffffULL ^ bpf_rand_u32(1); + case 17: return 0xffff800000000000ULL | bpf_rand_u8(4); + case 18: return 0xffff800000000000ULL | bpf_rand_u8(20); + case 19: return (0xffffffc000000000ULL + 0x80000ULL) | bpf_rand_u32(0); + case 20: return (0xffffffc000000000ULL - 0x04000000ULL) | bpf_rand_u32(0); + case 21: return 0x0000000000000000ULL | bpf_rand_u8(55) | bpf_rand_u32(20); + case 22: return 0xffffffffffffffffULL ^ bpf_rand_u8(3) ^ bpf_rand_u32(40); + case 23: return 0x0000000000000000ULL | bpf_rand_u8(bpf_rand_u8(0) % 64); + case 24: return 0x0000000000000000ULL | bpf_rand_u16(bpf_rand_u8(0) % 64); + case 25: return 0xffffffffffffffffULL ^ bpf_rand_u8(bpf_rand_u8(0) % 64); + case 26: return 0xffffffffffffffffULL ^ bpf_rand_u40(bpf_rand_u8(0) % 64); + case 27: return 0x0000800000000000ULL; + case 28: return 0x8000000000000000ULL; + case 29: return 0x0000000000000000ULL; + case 30: return 0xffffffffffffffffULL; + case 31: return bpf_rand_u16(bpf_rand_u8(0) % 64); + case 32: return bpf_rand_u24(bpf_rand_u8(0) % 64); + case 33: return bpf_rand_u32(bpf_rand_u8(0) % 64); + case 34: return bpf_rand_u40(bpf_rand_u8(0) % 64); + case 35: return bpf_rand_u48(bpf_rand_u8(0) % 64); + case 36: return bpf_rand_u56(bpf_rand_u8(0) % 64); + case 37: return bpf_rand_u64(bpf_rand_u8(0) % 64); + default: return bpf_rand_u64(0); + } +} + +#endif /* __BPF_RAND__ */ diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c index f3bca3a..c87b4e0 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.c +++ b/tools/testing/selftests/bpf/cgroup_helpers.c @@ -6,6 +6,7 @@ #include <sys/types.h> #include <linux/limits.h> #include <stdio.h> +#include <stdlib.h> #include <linux/sched.h> #include <fcntl.h> #include <unistd.h> @@ -176,3 +177,59 @@ int create_and_get_cgroup(char *path) return fd; } + +/** + * get_cgroup_id() - Get cgroup id for a particular cgroup path + * @path: The cgroup path, relative to the workdir, to join + * + * On success, it returns the cgroup id. On failure it returns 0, + * which is an invalid cgroup id. + * If there is a failure, it prints the error to stderr. + */ +unsigned long long get_cgroup_id(char *path) +{ + int dirfd, err, flags, mount_id, fhsize; + union { + unsigned long long cgid; + unsigned char raw_bytes[8]; + } id; + char cgroup_workdir[PATH_MAX + 1]; + struct file_handle *fhp, *fhp2; + unsigned long long ret = 0; + + format_cgroup_path(cgroup_workdir, path); + + dirfd = AT_FDCWD; + flags = 0; + fhsize = sizeof(*fhp); + fhp = calloc(1, fhsize); + if (!fhp) { + log_err("calloc"); + return 0; + } + err = name_to_handle_at(dirfd, cgroup_workdir, fhp, &mount_id, flags); + if (err >= 0 || fhp->handle_bytes != 8) { + log_err("name_to_handle_at"); + goto free_mem; + } + + fhsize = sizeof(struct file_handle) + fhp->handle_bytes; + fhp2 = realloc(fhp, fhsize); + if (!fhp2) { + log_err("realloc"); + goto free_mem; + } + err = name_to_handle_at(dirfd, cgroup_workdir, fhp2, &mount_id, flags); + fhp = fhp2; + if (err < 0) { + log_err("name_to_handle_at"); + goto free_mem; + } + + memcpy(id.raw_bytes, fhp->f_handle, 8); + ret = id.cgid; + +free_mem: + free(fhp); + return ret; +} diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h index 06485e0..20a4a5d 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.h +++ b/tools/testing/selftests/bpf/cgroup_helpers.h @@ -13,5 +13,6 @@ int create_and_get_cgroup(char *path); int join_cgroup(char *path); int setup_cgroup_environment(void); void cleanup_cgroup_environment(void); +unsigned long long get_cgroup_id(char *path); #endif diff --git a/tools/testing/selftests/bpf/get_cgroup_id_kern.c b/tools/testing/selftests/bpf/get_cgroup_id_kern.c new file mode 100644 index 0000000..014dba1 --- /dev/null +++ b/tools/testing/selftests/bpf/get_cgroup_id_kern.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Facebook + +#include <linux/bpf.h> +#include "bpf_helpers.h" + +struct bpf_map_def SEC("maps") cg_ids = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(__u64), + .max_entries = 1, +}; + +struct bpf_map_def SEC("maps") pidmap = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(__u32), + .max_entries = 1, +}; + +SEC("tracepoint/syscalls/sys_enter_nanosleep") +int trace(void *ctx) +{ + __u32 pid = bpf_get_current_pid_tgid(); + __u32 key = 0, *expected_pid; + __u64 *val; + + expected_pid = bpf_map_lookup_elem(&pidmap, &key); + if (!expected_pid || *expected_pid != pid) + return 0; + + val = bpf_map_lookup_elem(&cg_ids, &key); + if (val) + *val = bpf_get_current_cgroup_id(); + + return 0; +} + +char _license[] SEC("license") = "GPL"; +__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */ diff --git a/tools/testing/selftests/bpf/get_cgroup_id_user.c b/tools/testing/selftests/bpf/get_cgroup_id_user.c new file mode 100644 index 0000000..e8da7b3 --- /dev/null +++ b/tools/testing/selftests/bpf/get_cgroup_id_user.c @@ -0,0 +1,149 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Facebook + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <errno.h> +#include <fcntl.h> +#include <syscall.h> +#include <unistd.h> +#include <linux/perf_event.h> +#include <sys/ioctl.h> +#include <sys/time.h> +#include <sys/types.h> +#include <sys/stat.h> + +#include <linux/bpf.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include "cgroup_helpers.h" +#include "bpf_rlimit.h" + +#define CHECK(condition, tag, format...) ({ \ + int __ret = !!(condition); \ + if (__ret) { \ + printf("%s:FAIL:%s ", __func__, tag); \ + printf(format); \ + } else { \ + printf("%s:PASS:%s\n", __func__, tag); \ + } \ + __ret; \ +}) + +static int bpf_find_map(const char *test, struct bpf_object *obj, + const char *name) +{ + struct bpf_map *map; + + map = bpf_object__find_map_by_name(obj, name); + if (!map) + return -1; + return bpf_map__fd(map); +} + +#define TEST_CGROUP "/test-bpf-get-cgroup-id/" + +int main(int argc, char **argv) +{ + const char *probe_name = "syscalls/sys_enter_nanosleep"; + const char *file = "get_cgroup_id_kern.o"; + int err, bytes, efd, prog_fd, pmu_fd; + int cgroup_fd, cgidmap_fd, pidmap_fd; + struct perf_event_attr attr = {}; + struct bpf_object *obj; + __u64 kcgid = 0, ucgid; + __u32 key = 0, pid; + int exit_code = 1; + char buf[256]; + + err = setup_cgroup_environment(); + if (CHECK(err, "setup_cgroup_environment", "err %d errno %d\n", err, + errno)) + return 1; + + cgroup_fd = create_and_get_cgroup(TEST_CGROUP); + if (CHECK(cgroup_fd < 0, "create_and_get_cgroup", "err %d errno %d\n", + cgroup_fd, errno)) + goto cleanup_cgroup_env; + + err = join_cgroup(TEST_CGROUP); + if (CHECK(err, "join_cgroup", "err %d errno %d\n", err, errno)) + goto cleanup_cgroup_env; + + err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd); + if (CHECK(err, "bpf_prog_load", "err %d errno %d\n", err, errno)) + goto cleanup_cgroup_env; + + cgidmap_fd = bpf_find_map(__func__, obj, "cg_ids"); + if (CHECK(cgidmap_fd < 0, "bpf_find_map", "err %d errno %d\n", + cgidmap_fd, errno)) + goto close_prog; + + pidmap_fd = bpf_find_map(__func__, obj, "pidmap"); + if (CHECK(pidmap_fd < 0, "bpf_find_map", "err %d errno %d\n", + pidmap_fd, errno)) + goto close_prog; + + pid = getpid(); + bpf_map_update_elem(pidmap_fd, &key, &pid, 0); + + snprintf(buf, sizeof(buf), + "/sys/kernel/debug/tracing/events/%s/id", probe_name); + efd = open(buf, O_RDONLY, 0); + if (CHECK(efd < 0, "open", "err %d errno %d\n", efd, errno)) + goto close_prog; + bytes = read(efd, buf, sizeof(buf)); + close(efd); + if (CHECK(bytes <= 0 || bytes >= sizeof(buf), "read", + "bytes %d errno %d\n", bytes, errno)) + goto close_prog; + + attr.config = strtol(buf, NULL, 0); + attr.type = PERF_TYPE_TRACEPOINT; + attr.sample_type = PERF_SAMPLE_RAW; + attr.sample_period = 1; + attr.wakeup_events = 1; + + /* attach to this pid so the all bpf invocations will be in the + * cgroup associated with this pid. + */ + pmu_fd = syscall(__NR_perf_event_open, &attr, getpid(), -1, -1, 0); + if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n", pmu_fd, + errno)) + goto close_prog; + + err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0); + if (CHECK(err, "perf_event_ioc_enable", "err %d errno %d\n", err, + errno)) + goto close_pmu; + + err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd); + if (CHECK(err, "perf_event_ioc_set_bpf", "err %d errno %d\n", err, + errno)) + goto close_pmu; + + /* trigger some syscalls */ + sleep(1); + + err = bpf_map_lookup_elem(cgidmap_fd, &key, &kcgid); + if (CHECK(err, "bpf_map_lookup_elem", "err %d errno %d\n", err, errno)) + goto close_pmu; + + ucgid = get_cgroup_id(TEST_CGROUP); + if (CHECK(kcgid != ucgid, "compare_cgroup_id", + "kern cgid %llx user cgid %llx", kcgid, ucgid)) + goto close_pmu; + + exit_code = 0; + printf("%s:PASS\n", argv[0]); + +close_pmu: + close(pmu_fd); +close_prog: + bpf_object__close(obj); +cleanup_cgroup_env: + cleanup_cgroup_environment(); + return exit_code; +} diff --git a/tools/testing/selftests/bpf/sendmsg4_prog.c b/tools/testing/selftests/bpf/sendmsg4_prog.c new file mode 100644 index 0000000..a91536b --- /dev/null +++ b/tools/testing/selftests/bpf/sendmsg4_prog.c @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Facebook + +#include <linux/stddef.h> +#include <linux/bpf.h> +#include <sys/socket.h> + +#include "bpf_helpers.h" +#include "bpf_endian.h" + +#define SRC1_IP4 0xAC100001U /* 172.16.0.1 */ +#define SRC2_IP4 0x00000000U +#define SRC_REWRITE_IP4 0x7f000004U +#define DST_IP4 0xC0A801FEU /* 192.168.1.254 */ +#define DST_REWRITE_IP4 0x7f000001U +#define DST_PORT 4040 +#define DST_REWRITE_PORT4 4444 + +int _version SEC("version") = 1; + +SEC("cgroup/sendmsg4") +int sendmsg_v4_prog(struct bpf_sock_addr *ctx) +{ + if (ctx->type != SOCK_DGRAM) + return 0; + + /* Rewrite source. */ + if (ctx->msg_src_ip4 == bpf_htonl(SRC1_IP4) || + ctx->msg_src_ip4 == bpf_htonl(SRC2_IP4)) { + ctx->msg_src_ip4 = bpf_htonl(SRC_REWRITE_IP4); + } else { + /* Unexpected source. Reject sendmsg. */ + return 0; + } + + /* Rewrite destination. */ + if ((ctx->user_ip4 >> 24) == (bpf_htonl(DST_IP4) >> 24) && + ctx->user_port == bpf_htons(DST_PORT)) { + ctx->user_ip4 = bpf_htonl(DST_REWRITE_IP4); + ctx->user_port = bpf_htons(DST_REWRITE_PORT4); + } else { + /* Unexpected source. Reject sendmsg. */ + return 0; + } + + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/sendmsg6_prog.c b/tools/testing/selftests/bpf/sendmsg6_prog.c new file mode 100644 index 0000000..5aeaa28 --- /dev/null +++ b/tools/testing/selftests/bpf/sendmsg6_prog.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Facebook + +#include <linux/stddef.h> +#include <linux/bpf.h> +#include <sys/socket.h> + +#include "bpf_helpers.h" +#include "bpf_endian.h" + +#define SRC_REWRITE_IP6_0 0 +#define SRC_REWRITE_IP6_1 0 +#define SRC_REWRITE_IP6_2 0 +#define SRC_REWRITE_IP6_3 6 + +#define DST_REWRITE_IP6_0 0 +#define DST_REWRITE_IP6_1 0 +#define DST_REWRITE_IP6_2 0 +#define DST_REWRITE_IP6_3 1 + +#define DST_REWRITE_PORT6 6666 + +int _version SEC("version") = 1; + +SEC("cgroup/sendmsg6") +int sendmsg_v6_prog(struct bpf_sock_addr *ctx) +{ + if (ctx->type != SOCK_DGRAM) + return 0; + + /* Rewrite source. */ + if (ctx->msg_src_ip6[3] == bpf_htonl(1) || + ctx->msg_src_ip6[3] == bpf_htonl(0)) { + ctx->msg_src_ip6[0] = bpf_htonl(SRC_REWRITE_IP6_0); + ctx->msg_src_ip6[1] = bpf_htonl(SRC_REWRITE_IP6_1); + ctx->msg_src_ip6[2] = bpf_htonl(SRC_REWRITE_IP6_2); + ctx->msg_src_ip6[3] = bpf_htonl(SRC_REWRITE_IP6_3); + } else { + /* Unexpected source. Reject sendmsg. */ + return 0; + } + + /* Rewrite destination. */ + if ((ctx->user_ip6[0] & 0xFFFF) == bpf_htons(0xFACE) && + ctx->user_ip6[0] >> 16 == bpf_htons(0xB00C)) { + ctx->user_ip6[0] = bpf_htonl(DST_REWRITE_IP6_0); + ctx->user_ip6[1] = bpf_htonl(DST_REWRITE_IP6_1); + ctx->user_ip6[2] = bpf_htonl(DST_REWRITE_IP6_2); + ctx->user_ip6[3] = bpf_htonl(DST_REWRITE_IP6_3); + + ctx->user_port = bpf_htons(DST_REWRITE_PORT6); + } else { + /* Unexpected destination. Reject sendmsg. */ + return 0; + } + + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_adjust_tail.c b/tools/testing/selftests/bpf/test_adjust_tail.c new file mode 100644 index 0000000..4cd5e86 --- /dev/null +++ b/tools/testing/selftests/bpf/test_adjust_tail.c @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0 + * Copyright (c) 2018 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include "bpf_helpers.h" + +int _version SEC("version") = 1; + +SEC("xdp_adjust_tail") +int _xdp_adjust_tail(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + int offset = 0; + + if (data_end - data == 54) + offset = 256; + else + offset = 20; + if (bpf_xdp_adjust_tail(xdp, 0 - offset)) + return XDP_DROP; + return XDP_TX; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c new file mode 100644 index 0000000..3619f30 --- /dev/null +++ b/tools/testing/selftests/bpf/test_btf.c @@ -0,0 +1,2315 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018 Facebook */ + +#include <linux/bpf.h> +#include <linux/btf.h> +#include <linux/err.h> +#include <bpf/bpf.h> +#include <sys/resource.h> +#include <libelf.h> +#include <gelf.h> +#include <string.h> +#include <stdlib.h> +#include <stdio.h> +#include <stdarg.h> +#include <unistd.h> +#include <fcntl.h> +#include <errno.h> +#include <bpf/libbpf.h> +#include <bpf/btf.h> + +#include "bpf_rlimit.h" + +static uint32_t pass_cnt; +static uint32_t error_cnt; +static uint32_t skip_cnt; + +#define CHECK(condition, format...) ({ \ + int __ret = !!(condition); \ + if (__ret) { \ + fprintf(stderr, "%s:%d:FAIL ", __func__, __LINE__); \ + fprintf(stderr, format); \ + } \ + __ret; \ +}) + +static int count_result(int err) +{ + if (err) + error_cnt++; + else + pass_cnt++; + + fprintf(stderr, "\n"); + return err; +} + +#define min(a, b) ((a) < (b) ? (a) : (b)) +#define __printf(a, b) __attribute__((format(printf, a, b))) + +__printf(1, 2) +static int __base_pr(const char *format, ...) +{ + va_list args; + int err; + + va_start(args, format); + err = vfprintf(stderr, format, args); + va_end(args); + return err; +} + +#define BTF_INFO_ENC(kind, root, vlen) \ + ((!!(root) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN)) + +#define BTF_TYPE_ENC(name, info, size_or_type) \ + (name), (info), (size_or_type) + +#define BTF_INT_ENC(encoding, bits_offset, nr_bits) \ + ((encoding) << 24 | (bits_offset) << 16 | (nr_bits)) +#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \ + BTF_INT_ENC(encoding, bits_offset, bits) + +#define BTF_ARRAY_ENC(type, index_type, nr_elems) \ + (type), (index_type), (nr_elems) +#define BTF_TYPE_ARRAY_ENC(type, index_type, nr_elems) \ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ARRAY, 0, 0), 0), \ + BTF_ARRAY_ENC(type, index_type, nr_elems) + +#define BTF_MEMBER_ENC(name, type, bits_offset) \ + (name), (type), (bits_offset) +#define BTF_ENUM_ENC(name, val) (name), (val) + +#define BTF_TYPEDEF_ENC(name, type) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0), type) + +#define BTF_PTR_ENC(name, type) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), type) + +#define BTF_END_RAW 0xdeadbeef +#define NAME_TBD 0xdeadb33f + +#define MAX_NR_RAW_TYPES 1024 +#define BTF_LOG_BUF_SIZE 65535 + +#ifndef ARRAY_SIZE +# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +static struct args { + unsigned int raw_test_num; + unsigned int file_test_num; + unsigned int get_info_test_num; + bool raw_test; + bool file_test; + bool get_info_test; + bool pprint_test; + bool always_log; +} args; + +static char btf_log_buf[BTF_LOG_BUF_SIZE]; + +static struct btf_header hdr_tmpl = { + .magic = BTF_MAGIC, + .version = BTF_VERSION, + .hdr_len = sizeof(struct btf_header), +}; + +struct btf_raw_test { + const char *descr; + const char *str_sec; + const char *map_name; + const char *err_str; + __u32 raw_types[MAX_NR_RAW_TYPES]; + __u32 str_sec_size; + enum bpf_map_type map_type; + __u32 key_size; + __u32 value_size; + __u32 key_type_id; + __u32 value_type_id; + __u32 max_entries; + bool btf_load_err; + bool map_create_err; + int hdr_len_delta; + int type_off_delta; + int str_off_delta; + int str_len_delta; +}; + +static struct btf_raw_test raw_tests[] = { +/* enum E { + * E0, + * E1, + * }; + * + * struct A { + * unsigned long long m; + * int n; + * char o; + * [3 bytes hole] + * int p[8]; + * int q[4][8]; + * enum E r; + * }; + */ +{ + .descr = "struct test #1", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* unsigned long long */ + BTF_TYPE_INT_ENC(0, 0, 0, 64, 8), /* [2] */ + /* char */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1), /* [3] */ + /* int[8] */ + BTF_TYPE_ARRAY_ENC(1, 1, 8), /* [4] */ + /* struct A { */ /* [5] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 6), 180), + BTF_MEMBER_ENC(NAME_TBD, 2, 0), /* unsigned long long m;*/ + BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n; */ + BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o; */ + BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8] */ + BTF_MEMBER_ENC(NAME_TBD, 6, 384),/* int q[4][8] */ + BTF_MEMBER_ENC(NAME_TBD, 7, 1408), /* enum E r */ + /* } */ + /* int[4][8] */ + BTF_TYPE_ARRAY_ENC(4, 1, 4), /* [6] */ + /* enum E */ /* [7] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 2), sizeof(int)), + BTF_ENUM_ENC(NAME_TBD, 0), + BTF_ENUM_ENC(NAME_TBD, 1), + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0n\0o\0p\0q\0r\0E\0E0\0E1", + .str_sec_size = sizeof("\0A\0m\0n\0o\0p\0q\0r\0E\0E0\0E1"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "struct_test1_map", + .key_size = sizeof(int), + .value_size = 180, + .key_type_id = 1, + .value_type_id = 5, + .max_entries = 4, +}, + +/* typedef struct b Struct_B; + * + * struct A { + * int m; + * struct b n[4]; + * const Struct_B o[4]; + * }; + * + * struct B { + * int m; + * int n; + * }; + */ +{ + .descr = "struct test #2", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* struct b [4] */ /* [2] */ + BTF_TYPE_ARRAY_ENC(4, 1, 4), + + /* struct A { */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 3), 68), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */ + BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* struct B n[4] */ + BTF_MEMBER_ENC(NAME_TBD, 8, 288),/* const Struct_B o[4];*/ + /* } */ + + /* struct B { */ /* [4] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */ + BTF_MEMBER_ENC(NAME_TBD, 1, 32),/* int n; */ + /* } */ + + /* const int */ /* [5] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 1), + /* typedef struct b Struct_B */ /* [6] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0), 4), + /* const Struct_B */ /* [7] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 6), + /* const Struct_B [4] */ /* [8] */ + BTF_TYPE_ARRAY_ENC(7, 1, 4), + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0n\0o\0B\0m\0n\0Struct_B", + .str_sec_size = sizeof("\0A\0m\0n\0o\0B\0m\0n\0Struct_B"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "struct_test2_map", + .key_size = sizeof(int), + .value_size = 68, + .key_type_id = 1, + .value_type_id = 3, + .max_entries = 4, +}, + +/* Test member exceeds the size of struct. + * + * struct A { + * int m; + * int n; + * }; + */ +{ + .descr = "size check test #1", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* struct A { */ /* [2] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), sizeof(int) * 2 - 1), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */ + BTF_MEMBER_ENC(NAME_TBD, 1, 32),/* int n; */ + /* } */ + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0n", + .str_sec_size = sizeof("\0A\0m\0n"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "size_check1_map", + .key_size = sizeof(int), + .value_size = 1, + .key_type_id = 1, + .value_type_id = 2, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Member exceeds struct_size", +}, + +/* Test member exeeds the size of struct + * + * struct A { + * int m; + * int n[2]; + * }; + */ +{ + .descr = "size check test #2", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, sizeof(int)), + /* int[2] */ /* [2] */ + BTF_TYPE_ARRAY_ENC(1, 1, 2), + /* struct A { */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), sizeof(int) * 3 - 1), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */ + BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* int n[2]; */ + /* } */ + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0n", + .str_sec_size = sizeof("\0A\0m\0n"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "size_check2_map", + .key_size = sizeof(int), + .value_size = 1, + .key_type_id = 1, + .value_type_id = 3, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Member exceeds struct_size", +}, + +/* Test member exeeds the size of struct + * + * struct A { + * int m; + * void *n; + * }; + */ +{ + .descr = "size check test #3", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, sizeof(int)), + /* void* */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 0), + /* struct A { */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), sizeof(int) + sizeof(void *) - 1), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */ + BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* void *n; */ + /* } */ + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0n", + .str_sec_size = sizeof("\0A\0m\0n"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "size_check3_map", + .key_size = sizeof(int), + .value_size = 1, + .key_type_id = 1, + .value_type_id = 3, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Member exceeds struct_size", +}, + +/* Test member exceeds the size of struct + * + * enum E { + * E0, + * E1, + * }; + * + * struct A { + * int m; + * enum E n; + * }; + */ +{ + .descr = "size check test #4", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, sizeof(int)), + /* enum E { */ /* [2] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 2), sizeof(int)), + BTF_ENUM_ENC(NAME_TBD, 0), + BTF_ENUM_ENC(NAME_TBD, 1), + /* } */ + /* struct A { */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), sizeof(int) * 2 - 1), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */ + BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* enum E n; */ + /* } */ + BTF_END_RAW, + }, + .str_sec = "\0E\0E0\0E1\0A\0m\0n", + .str_sec_size = sizeof("\0E\0E0\0E1\0A\0m\0n"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "size_check4_map", + .key_size = sizeof(int), + .value_size = 1, + .key_type_id = 1, + .value_type_id = 3, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Member exceeds struct_size", +}, + +/* typedef const void * const_void_ptr; + * struct A { + * const_void_ptr m; + * }; + */ +{ + .descr = "void test #1", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* const void */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 0), + /* const void* */ /* [3] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2), + /* typedef const void * const_void_ptr */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 3), + /* struct A { */ /* [4] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), sizeof(void *)), + /* const_void_ptr m; */ + BTF_MEMBER_ENC(NAME_TBD, 3, 0), + /* } */ + BTF_END_RAW, + }, + .str_sec = "\0const_void_ptr\0A\0m", + .str_sec_size = sizeof("\0const_void_ptr\0A\0m"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "void_test1_map", + .key_size = sizeof(int), + .value_size = sizeof(void *), + .key_type_id = 1, + .value_type_id = 4, + .max_entries = 4, +}, + +/* struct A { + * const void m; + * }; + */ +{ + .descr = "void test #2", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* const void */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 0), + /* struct A { */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), 8), + /* const void m; */ + BTF_MEMBER_ENC(NAME_TBD, 2, 0), + /* } */ + BTF_END_RAW, + }, + .str_sec = "\0A\0m", + .str_sec_size = sizeof("\0A\0m"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "void_test2_map", + .key_size = sizeof(int), + .value_size = sizeof(void *), + .key_type_id = 1, + .value_type_id = 3, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid member", +}, + +/* typedef const void * const_void_ptr; + * const_void_ptr[4] + */ +{ + .descr = "void test #3", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* const void */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 0), + /* const void* */ /* [3] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2), + /* typedef const void * const_void_ptr */ /* [4] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 3), + /* const_void_ptr[4] */ /* [5] */ + BTF_TYPE_ARRAY_ENC(3, 1, 4), + BTF_END_RAW, + }, + .str_sec = "\0const_void_ptr", + .str_sec_size = sizeof("\0const_void_ptr"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "void_test3_map", + .key_size = sizeof(int), + .value_size = sizeof(void *) * 4, + .key_type_id = 1, + .value_type_id = 4, + .max_entries = 4, +}, + +/* const void[4] */ +{ + .descr = "void test #4", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* const void */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 0), + /* const void[4] */ /* [3] */ + BTF_TYPE_ARRAY_ENC(2, 1, 4), + BTF_END_RAW, + }, + .str_sec = "\0A\0m", + .str_sec_size = sizeof("\0A\0m"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "void_test4_map", + .key_size = sizeof(int), + .value_size = sizeof(void *) * 4, + .key_type_id = 1, + .value_type_id = 3, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid elem", +}, + +/* Array_A <------------------+ + * elem_type == Array_B | + * | | + * | | + * Array_B <-------- + | + * elem_type == Array A --+ + */ +{ + .descr = "loop test #1", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* Array_A */ /* [2] */ + BTF_TYPE_ARRAY_ENC(3, 1, 8), + /* Array_B */ /* [3] */ + BTF_TYPE_ARRAY_ENC(2, 1, 8), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "loop_test1_map", + .key_size = sizeof(int), + .value_size = sizeof(sizeof(int) * 8), + .key_type_id = 1, + .value_type_id = 2, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Loop detected", +}, + +/* typedef is _before_ the BTF type of Array_A and Array_B + * + * typedef Array_B int_array; + * + * Array_A <------------------+ + * elem_type == int_array | + * | | + * | | + * Array_B <-------- + | + * elem_type == Array_A --+ + */ +{ + .descr = "loop test #2", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* typedef Array_B int_array */ + BTF_TYPEDEF_ENC(1, 4), /* [2] */ + /* Array_A */ + BTF_TYPE_ARRAY_ENC(2, 1, 8), /* [3] */ + /* Array_B */ + BTF_TYPE_ARRAY_ENC(3, 1, 8), /* [4] */ + BTF_END_RAW, + }, + .str_sec = "\0int_array\0", + .str_sec_size = sizeof("\0int_array"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "loop_test2_map", + .key_size = sizeof(int), + .value_size = sizeof(sizeof(int) * 8), + .key_type_id = 1, + .value_type_id = 2, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Loop detected", +}, + +/* Array_A <------------------+ + * elem_type == Array_B | + * | | + * | | + * Array_B <-------- + | + * elem_type == Array_A --+ + */ +{ + .descr = "loop test #3", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* Array_A */ /* [2] */ + BTF_TYPE_ARRAY_ENC(3, 1, 8), + /* Array_B */ /* [3] */ + BTF_TYPE_ARRAY_ENC(2, 1, 8), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "loop_test3_map", + .key_size = sizeof(int), + .value_size = sizeof(sizeof(int) * 8), + .key_type_id = 1, + .value_type_id = 2, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Loop detected", +}, + +/* typedef is _between_ the BTF type of Array_A and Array_B + * + * typedef Array_B int_array; + * + * Array_A <------------------+ + * elem_type == int_array | + * | | + * | | + * Array_B <-------- + | + * elem_type == Array_A --+ + */ +{ + .descr = "loop test #4", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* Array_A */ /* [2] */ + BTF_TYPE_ARRAY_ENC(3, 1, 8), + /* typedef Array_B int_array */ /* [3] */ + BTF_TYPEDEF_ENC(NAME_TBD, 4), + /* Array_B */ /* [4] */ + BTF_TYPE_ARRAY_ENC(2, 1, 8), + BTF_END_RAW, + }, + .str_sec = "\0int_array\0", + .str_sec_size = sizeof("\0int_array"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "loop_test4_map", + .key_size = sizeof(int), + .value_size = sizeof(sizeof(int) * 8), + .key_type_id = 1, + .value_type_id = 2, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Loop detected", +}, + +/* typedef struct B Struct_B + * + * struct A { + * int x; + * Struct_B y; + * }; + * + * struct B { + * int x; + * struct A y; + * }; + */ +{ + .descr = "loop test #5", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* struct A */ /* [2] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int x; */ + BTF_MEMBER_ENC(NAME_TBD, 3, 32),/* Struct_B y; */ + /* typedef struct B Struct_B */ + BTF_TYPEDEF_ENC(NAME_TBD, 4), /* [3] */ + /* struct B */ /* [4] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int x; */ + BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* struct A y; */ + BTF_END_RAW, + }, + .str_sec = "\0A\0x\0y\0Struct_B\0B\0x\0y", + .str_sec_size = sizeof("\0A\0x\0y\0Struct_B\0B\0x\0y"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "loop_test5_map", + .key_size = sizeof(int), + .value_size = 8, + .key_type_id = 1, + .value_type_id = 2, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Loop detected", +}, + +/* struct A { + * int x; + * struct A array_a[4]; + * }; + */ +{ + .descr = "loop test #6", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_ARRAY_ENC(3, 1, 4), /* [2] */ + /* struct A */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int x; */ + BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* struct A array_a[4]; */ + BTF_END_RAW, + }, + .str_sec = "\0A\0x\0y", + .str_sec_size = sizeof("\0A\0x\0y"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "loop_test6_map", + .key_size = sizeof(int), + .value_size = 8, + .key_type_id = 1, + .value_type_id = 2, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Loop detected", +}, + +{ + .descr = "loop test #7", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* struct A { */ /* [2] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), sizeof(void *)), + /* const void *m; */ + BTF_MEMBER_ENC(NAME_TBD, 3, 0), + /* CONST type_id=3 */ /* [3] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 4), + /* PTR type_id=2 */ /* [4] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 3), + BTF_END_RAW, + }, + .str_sec = "\0A\0m", + .str_sec_size = sizeof("\0A\0m"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "loop_test7_map", + .key_size = sizeof(int), + .value_size = sizeof(void *), + .key_type_id = 1, + .value_type_id = 2, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Loop detected", +}, + +{ + .descr = "loop test #8", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* struct A { */ /* [2] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), sizeof(void *)), + /* const void *m; */ + BTF_MEMBER_ENC(NAME_TBD, 4, 0), + /* struct B { */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), sizeof(void *)), + /* const void *n; */ + BTF_MEMBER_ENC(NAME_TBD, 6, 0), + /* CONST type_id=5 */ /* [4] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 5), + /* PTR type_id=6 */ /* [5] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 6), + /* CONST type_id=7 */ /* [6] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 7), + /* PTR type_id=4 */ /* [7] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 4), + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0B\0n", + .str_sec_size = sizeof("\0A\0m\0B\0n"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "loop_test8_map", + .key_size = sizeof(int), + .value_size = sizeof(void *), + .key_type_id = 1, + .value_type_id = 2, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Loop detected", +}, + +{ + .descr = "string section does not end with null", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "\0int", + .str_sec_size = sizeof("\0int") - 1, + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "hdr_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid string section", +}, + +{ + .descr = "empty string section", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = 0, + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "hdr_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid string section", +}, + +{ + .descr = "empty type section", + .raw_types = { + BTF_END_RAW, + }, + .str_sec = "\0int", + .str_sec_size = sizeof("\0int"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "hdr_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "No type found", +}, + +{ + .descr = "btf_header test. Longer hdr_len", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "\0int", + .str_sec_size = sizeof("\0int"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "hdr_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .hdr_len_delta = 4, + .err_str = "Unsupported btf_header", +}, + +{ + .descr = "btf_header test. Gap between hdr and type", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "\0int", + .str_sec_size = sizeof("\0int"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "hdr_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .type_off_delta = 4, + .err_str = "Unsupported section found", +}, + +{ + .descr = "btf_header test. Gap between type and str", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "\0int", + .str_sec_size = sizeof("\0int"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "hdr_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .str_off_delta = 4, + .err_str = "Unsupported section found", +}, + +{ + .descr = "btf_header test. Overlap between type and str", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "\0int", + .str_sec_size = sizeof("\0int"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "hdr_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .str_off_delta = -4, + .err_str = "Section overlap found", +}, + +{ + .descr = "btf_header test. Larger BTF size", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "\0int", + .str_sec_size = sizeof("\0int"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "hdr_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .str_len_delta = -4, + .err_str = "Unsupported section found", +}, + +{ + .descr = "btf_header test. Smaller BTF size", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "\0int", + .str_sec_size = sizeof("\0int"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "hdr_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .str_len_delta = 4, + .err_str = "Total section length too long", +}, + +{ + .descr = "array test. index_type/elem_type \"int\"", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* int[16] */ /* [2] */ + BTF_TYPE_ARRAY_ENC(1, 1, 16), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, +}, + +{ + .descr = "array test. index_type/elem_type \"const int\"", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* int[16] */ /* [2] */ + BTF_TYPE_ARRAY_ENC(3, 3, 16), + /* CONST type_id=1 */ /* [3] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 1), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, +}, + +{ + .descr = "array test. index_type \"const int:31\"", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* int:31 */ /* [2] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 31, 4), + /* int[16] */ /* [3] */ + BTF_TYPE_ARRAY_ENC(1, 4, 16), + /* CONST type_id=2 */ /* [4] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 2), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid index", +}, + +{ + .descr = "array test. elem_type \"const int:31\"", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* int:31 */ /* [2] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 31, 4), + /* int[16] */ /* [3] */ + BTF_TYPE_ARRAY_ENC(4, 1, 16), + /* CONST type_id=2 */ /* [4] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 2), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid array of int", +}, + +{ + .descr = "array test. index_type \"void\"", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* int[16] */ /* [2] */ + BTF_TYPE_ARRAY_ENC(1, 0, 16), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid index", +}, + +{ + .descr = "array test. index_type \"const void\"", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* int[16] */ /* [2] */ + BTF_TYPE_ARRAY_ENC(1, 3, 16), + /* CONST type_id=0 (void) */ /* [3] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 0), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid index", +}, + +{ + .descr = "array test. elem_type \"const void\"", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* int[16] */ /* [2] */ + BTF_TYPE_ARRAY_ENC(3, 1, 16), + /* CONST type_id=0 (void) */ /* [3] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 0), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid elem", +}, + +{ + .descr = "array test. elem_type \"const void *\"", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* const void *[16] */ /* [2] */ + BTF_TYPE_ARRAY_ENC(3, 1, 16), + /* CONST type_id=4 */ /* [3] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 4), + /* void* */ /* [4] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 0), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, +}, + +{ + .descr = "array test. index_type \"const void *\"", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* const void *[16] */ /* [2] */ + BTF_TYPE_ARRAY_ENC(3, 3, 16), + /* CONST type_id=4 */ /* [3] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 4), + /* void* */ /* [4] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 0), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid index", +}, + +{ + .descr = "array test. t->size != 0\"", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* int[16] */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ARRAY, 0, 0), 1), + BTF_ARRAY_ENC(1, 1, 16), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "size != 0", +}, + +{ + .descr = "int test. invalid int_data", + .raw_types = { + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), 4), + 0x10000000, + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid int_data", +}, + +{ + .descr = "invalid BTF_INFO", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + BTF_TYPE_ENC(0, 0x10000000, 4), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid btf_info", +}, + +{ + .descr = "fwd test. t->type != 0\"", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* fwd type */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FWD, 0, 0), 1), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "fwd_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "type != 0", +}, + +}; /* struct btf_raw_test raw_tests[] */ + +static const char *get_next_str(const char *start, const char *end) +{ + return start < end - 1 ? start + 1 : NULL; +} + +static int get_type_sec_size(const __u32 *raw_types) +{ + int i; + + for (i = MAX_NR_RAW_TYPES - 1; + i >= 0 && raw_types[i] != BTF_END_RAW; + i--) + ; + + return i < 0 ? i : i * sizeof(raw_types[0]); +} + +static void *btf_raw_create(const struct btf_header *hdr, + const __u32 *raw_types, + const char *str, + unsigned int str_sec_size, + unsigned int *btf_size) +{ + const char *next_str = str, *end_str = str + str_sec_size; + unsigned int size_needed, offset; + struct btf_header *ret_hdr; + int i, type_sec_size; + uint32_t *ret_types; + void *raw_btf; + + type_sec_size = get_type_sec_size(raw_types); + if (CHECK(type_sec_size < 0, "Cannot get nr_raw_types")) + return NULL; + + size_needed = sizeof(*hdr) + type_sec_size + str_sec_size; + raw_btf = malloc(size_needed); + if (CHECK(!raw_btf, "Cannot allocate memory for raw_btf")) + return NULL; + + /* Copy header */ + memcpy(raw_btf, hdr, sizeof(*hdr)); + offset = sizeof(*hdr); + + /* Copy type section */ + ret_types = raw_btf + offset; + for (i = 0; i < type_sec_size / sizeof(raw_types[0]); i++) { + if (raw_types[i] == NAME_TBD) { + next_str = get_next_str(next_str, end_str); + if (CHECK(!next_str, "Error in getting next_str")) { + free(raw_btf); + return NULL; + } + ret_types[i] = next_str - str; + next_str += strlen(next_str); + } else { + ret_types[i] = raw_types[i]; + } + } + offset += type_sec_size; + + /* Copy string section */ + memcpy(raw_btf + offset, str, str_sec_size); + + ret_hdr = (struct btf_header *)raw_btf; + ret_hdr->type_len = type_sec_size; + ret_hdr->str_off = type_sec_size; + ret_hdr->str_len = str_sec_size; + + *btf_size = size_needed; + + return raw_btf; +} + +static int do_test_raw(unsigned int test_num) +{ + struct btf_raw_test *test = &raw_tests[test_num - 1]; + struct bpf_create_map_attr create_attr = {}; + int map_fd = -1, btf_fd = -1; + unsigned int raw_btf_size; + struct btf_header *hdr; + void *raw_btf; + int err; + + fprintf(stderr, "BTF raw test[%u] (%s): ", test_num, test->descr); + raw_btf = btf_raw_create(&hdr_tmpl, + test->raw_types, + test->str_sec, + test->str_sec_size, + &raw_btf_size); + + if (!raw_btf) + return -1; + + hdr = raw_btf; + + hdr->hdr_len = (int)hdr->hdr_len + test->hdr_len_delta; + hdr->type_off = (int)hdr->type_off + test->type_off_delta; + hdr->str_off = (int)hdr->str_off + test->str_off_delta; + hdr->str_len = (int)hdr->str_len + test->str_len_delta; + + *btf_log_buf = '\0'; + btf_fd = bpf_load_btf(raw_btf, raw_btf_size, + btf_log_buf, BTF_LOG_BUF_SIZE, + args.always_log); + free(raw_btf); + + err = ((btf_fd == -1) != test->btf_load_err); + if (CHECK(err, "btf_fd:%d test->btf_load_err:%u", + btf_fd, test->btf_load_err) || + CHECK(test->err_str && !strstr(btf_log_buf, test->err_str), + "expected err_str:%s", test->err_str)) { + err = -1; + goto done; + } + + if (err || btf_fd == -1) + goto done; + + create_attr.name = test->map_name; + create_attr.map_type = test->map_type; + create_attr.key_size = test->key_size; + create_attr.value_size = test->value_size; + create_attr.max_entries = test->max_entries; + create_attr.btf_fd = btf_fd; + create_attr.btf_key_type_id = test->key_type_id; + create_attr.btf_value_type_id = test->value_type_id; + + map_fd = bpf_create_map_xattr(&create_attr); + + err = ((map_fd == -1) != test->map_create_err); + CHECK(err, "map_fd:%d test->map_create_err:%u", + map_fd, test->map_create_err); + +done: + if (!err) + fprintf(stderr, "OK"); + + if (*btf_log_buf && (err || args.always_log)) + fprintf(stderr, "\n%s", btf_log_buf); + + if (btf_fd != -1) + close(btf_fd); + if (map_fd != -1) + close(map_fd); + + return err; +} + +static int test_raw(void) +{ + unsigned int i; + int err = 0; + + if (args.raw_test_num) + return count_result(do_test_raw(args.raw_test_num)); + + for (i = 1; i <= ARRAY_SIZE(raw_tests); i++) + err |= count_result(do_test_raw(i)); + + return err; +} + +struct btf_get_info_test { + const char *descr; + const char *str_sec; + __u32 raw_types[MAX_NR_RAW_TYPES]; + __u32 str_sec_size; + int btf_size_delta; + int (*special_test)(unsigned int test_num); +}; + +static int test_big_btf_info(unsigned int test_num); +static int test_btf_id(unsigned int test_num); + +const struct btf_get_info_test get_info_tests[] = { +{ + .descr = "== raw_btf_size+1", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .btf_size_delta = 1, +}, +{ + .descr = "== raw_btf_size-3", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .btf_size_delta = -3, +}, +{ + .descr = "Large bpf_btf_info", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .special_test = test_big_btf_info, +}, +{ + .descr = "BTF ID", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* unsigned int */ /* [2] */ + BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .special_test = test_btf_id, +}, +}; + +static inline __u64 ptr_to_u64(const void *ptr) +{ + return (__u64)(unsigned long)ptr; +} + +static int test_big_btf_info(unsigned int test_num) +{ + const struct btf_get_info_test *test = &get_info_tests[test_num - 1]; + uint8_t *raw_btf = NULL, *user_btf = NULL; + unsigned int raw_btf_size; + struct { + struct bpf_btf_info info; + uint64_t garbage; + } info_garbage; + struct bpf_btf_info *info; + int btf_fd = -1, err; + uint32_t info_len; + + raw_btf = btf_raw_create(&hdr_tmpl, + test->raw_types, + test->str_sec, + test->str_sec_size, + &raw_btf_size); + + if (!raw_btf) + return -1; + + *btf_log_buf = '\0'; + + user_btf = malloc(raw_btf_size); + if (CHECK(!user_btf, "!user_btf")) { + err = -1; + goto done; + } + + btf_fd = bpf_load_btf(raw_btf, raw_btf_size, + btf_log_buf, BTF_LOG_BUF_SIZE, + args.always_log); + if (CHECK(btf_fd == -1, "errno:%d", errno)) { + err = -1; + goto done; + } + + /* + * GET_INFO should error out if the userspace info + * has non zero tailing bytes. + */ + info = &info_garbage.info; + memset(info, 0, sizeof(*info)); + info_garbage.garbage = 0xdeadbeef; + info_len = sizeof(info_garbage); + info->btf = ptr_to_u64(user_btf); + info->btf_size = raw_btf_size; + + err = bpf_obj_get_info_by_fd(btf_fd, info, &info_len); + if (CHECK(!err, "!err")) { + err = -1; + goto done; + } + + /* + * GET_INFO should succeed even info_len is larger than + * the kernel supported as long as tailing bytes are zero. + * The kernel supported info len should also be returned + * to userspace. + */ + info_garbage.garbage = 0; + err = bpf_obj_get_info_by_fd(btf_fd, info, &info_len); + if (CHECK(err || info_len != sizeof(*info), + "err:%d errno:%d info_len:%u sizeof(*info):%lu", + err, errno, info_len, sizeof(*info))) { + err = -1; + goto done; + } + + fprintf(stderr, "OK"); + +done: + if (*btf_log_buf && (err || args.always_log)) + fprintf(stderr, "\n%s", btf_log_buf); + + free(raw_btf); + free(user_btf); + + if (btf_fd != -1) + close(btf_fd); + + return err; +} + +static int test_btf_id(unsigned int test_num) +{ + const struct btf_get_info_test *test = &get_info_tests[test_num - 1]; + struct bpf_create_map_attr create_attr = {}; + uint8_t *raw_btf = NULL, *user_btf[2] = {}; + int btf_fd[2] = {-1, -1}, map_fd = -1; + struct bpf_map_info map_info = {}; + struct bpf_btf_info info[2] = {}; + unsigned int raw_btf_size; + uint32_t info_len; + int err, i, ret; + + raw_btf = btf_raw_create(&hdr_tmpl, + test->raw_types, + test->str_sec, + test->str_sec_size, + &raw_btf_size); + + if (!raw_btf) + return -1; + + *btf_log_buf = '\0'; + + for (i = 0; i < 2; i++) { + user_btf[i] = malloc(raw_btf_size); + if (CHECK(!user_btf[i], "!user_btf[%d]", i)) { + err = -1; + goto done; + } + info[i].btf = ptr_to_u64(user_btf[i]); + info[i].btf_size = raw_btf_size; + } + + btf_fd[0] = bpf_load_btf(raw_btf, raw_btf_size, + btf_log_buf, BTF_LOG_BUF_SIZE, + args.always_log); + if (CHECK(btf_fd[0] == -1, "errno:%d", errno)) { + err = -1; + goto done; + } + + /* Test BPF_OBJ_GET_INFO_BY_ID on btf_id */ + info_len = sizeof(info[0]); + err = bpf_obj_get_info_by_fd(btf_fd[0], &info[0], &info_len); + if (CHECK(err, "errno:%d", errno)) { + err = -1; + goto done; + } + + btf_fd[1] = bpf_btf_get_fd_by_id(info[0].id); + if (CHECK(btf_fd[1] == -1, "errno:%d", errno)) { + err = -1; + goto done; + } + + ret = 0; + err = bpf_obj_get_info_by_fd(btf_fd[1], &info[1], &info_len); + if (CHECK(err || info[0].id != info[1].id || + info[0].btf_size != info[1].btf_size || + (ret = memcmp(user_btf[0], user_btf[1], info[0].btf_size)), + "err:%d errno:%d id0:%u id1:%u btf_size0:%u btf_size1:%u memcmp:%d", + err, errno, info[0].id, info[1].id, + info[0].btf_size, info[1].btf_size, ret)) { + err = -1; + goto done; + } + + /* Test btf members in struct bpf_map_info */ + create_attr.name = "test_btf_id"; + create_attr.map_type = BPF_MAP_TYPE_ARRAY; + create_attr.key_size = sizeof(int); + create_attr.value_size = sizeof(unsigned int); + create_attr.max_entries = 4; + create_attr.btf_fd = btf_fd[0]; + create_attr.btf_key_type_id = 1; + create_attr.btf_value_type_id = 2; + + map_fd = bpf_create_map_xattr(&create_attr); + if (CHECK(map_fd == -1, "errno:%d", errno)) { + err = -1; + goto done; + } + + info_len = sizeof(map_info); + err = bpf_obj_get_info_by_fd(map_fd, &map_info, &info_len); + if (CHECK(err || map_info.btf_id != info[0].id || + map_info.btf_key_type_id != 1 || map_info.btf_value_type_id != 2, + "err:%d errno:%d info.id:%u btf_id:%u btf_key_type_id:%u btf_value_type_id:%u", + err, errno, info[0].id, map_info.btf_id, map_info.btf_key_type_id, + map_info.btf_value_type_id)) { + err = -1; + goto done; + } + + for (i = 0; i < 2; i++) { + close(btf_fd[i]); + btf_fd[i] = -1; + } + + /* Test BTF ID is removed from the kernel */ + btf_fd[0] = bpf_btf_get_fd_by_id(map_info.btf_id); + if (CHECK(btf_fd[0] == -1, "errno:%d", errno)) { + err = -1; + goto done; + } + close(btf_fd[0]); + btf_fd[0] = -1; + + /* The map holds the last ref to BTF and its btf_id */ + close(map_fd); + map_fd = -1; + btf_fd[0] = bpf_btf_get_fd_by_id(map_info.btf_id); + if (CHECK(btf_fd[0] != -1, "BTF lingers")) { + err = -1; + goto done; + } + + fprintf(stderr, "OK"); + +done: + if (*btf_log_buf && (err || args.always_log)) + fprintf(stderr, "\n%s", btf_log_buf); + + free(raw_btf); + if (map_fd != -1) + close(map_fd); + for (i = 0; i < 2; i++) { + free(user_btf[i]); + if (btf_fd[i] != -1) + close(btf_fd[i]); + } + + return err; +} + +static int do_test_get_info(unsigned int test_num) +{ + const struct btf_get_info_test *test = &get_info_tests[test_num - 1]; + unsigned int raw_btf_size, user_btf_size, expected_nbytes; + uint8_t *raw_btf = NULL, *user_btf = NULL; + struct bpf_btf_info info = {}; + int btf_fd = -1, err, ret; + uint32_t info_len; + + fprintf(stderr, "BTF GET_INFO test[%u] (%s): ", + test_num, test->descr); + + if (test->special_test) + return test->special_test(test_num); + + raw_btf = btf_raw_create(&hdr_tmpl, + test->raw_types, + test->str_sec, + test->str_sec_size, + &raw_btf_size); + + if (!raw_btf) + return -1; + + *btf_log_buf = '\0'; + + user_btf = malloc(raw_btf_size); + if (CHECK(!user_btf, "!user_btf")) { + err = -1; + goto done; + } + + btf_fd = bpf_load_btf(raw_btf, raw_btf_size, + btf_log_buf, BTF_LOG_BUF_SIZE, + args.always_log); + if (CHECK(btf_fd == -1, "errno:%d", errno)) { + err = -1; + goto done; + } + + user_btf_size = (int)raw_btf_size + test->btf_size_delta; + expected_nbytes = min(raw_btf_size, user_btf_size); + if (raw_btf_size > expected_nbytes) + memset(user_btf + expected_nbytes, 0xff, + raw_btf_size - expected_nbytes); + + info_len = sizeof(info); + info.btf = ptr_to_u64(user_btf); + info.btf_size = user_btf_size; + + ret = 0; + err = bpf_obj_get_info_by_fd(btf_fd, &info, &info_len); + if (CHECK(err || !info.id || info_len != sizeof(info) || + info.btf_size != raw_btf_size || + (ret = memcmp(raw_btf, user_btf, expected_nbytes)), + "err:%d errno:%d info.id:%u info_len:%u sizeof(info):%lu raw_btf_size:%u info.btf_size:%u expected_nbytes:%u memcmp:%d", + err, errno, info.id, info_len, sizeof(info), + raw_btf_size, info.btf_size, expected_nbytes, ret)) { + err = -1; + goto done; + } + + while (expected_nbytes < raw_btf_size) { + fprintf(stderr, "%u...", expected_nbytes); + if (CHECK(user_btf[expected_nbytes++] != 0xff, + "user_btf[%u]:%x != 0xff", expected_nbytes - 1, + user_btf[expected_nbytes - 1])) { + err = -1; + goto done; + } + } + + fprintf(stderr, "OK"); + +done: + if (*btf_log_buf && (err || args.always_log)) + fprintf(stderr, "\n%s", btf_log_buf); + + free(raw_btf); + free(user_btf); + + if (btf_fd != -1) + close(btf_fd); + + return err; +} + +static int test_get_info(void) +{ + unsigned int i; + int err = 0; + + if (args.get_info_test_num) + return count_result(do_test_get_info(args.get_info_test_num)); + + for (i = 1; i <= ARRAY_SIZE(get_info_tests); i++) + err |= count_result(do_test_get_info(i)); + + return err; +} + +struct btf_file_test { + const char *file; + bool btf_kv_notfound; +}; + +static struct btf_file_test file_tests[] = { +{ + .file = "test_btf_haskv.o", +}, +{ + .file = "test_btf_nokv.o", + .btf_kv_notfound = true, +}, +}; + +static int file_has_btf_elf(const char *fn) +{ + Elf_Scn *scn = NULL; + GElf_Ehdr ehdr; + int elf_fd; + Elf *elf; + int ret; + + if (CHECK(elf_version(EV_CURRENT) == EV_NONE, + "elf_version(EV_CURRENT) == EV_NONE")) + return -1; + + elf_fd = open(fn, O_RDONLY); + if (CHECK(elf_fd == -1, "open(%s): errno:%d", fn, errno)) + return -1; + + elf = elf_begin(elf_fd, ELF_C_READ, NULL); + if (CHECK(!elf, "elf_begin(%s): %s", fn, elf_errmsg(elf_errno()))) { + ret = -1; + goto done; + } + + if (CHECK(!gelf_getehdr(elf, &ehdr), "!gelf_getehdr(%s)", fn)) { + ret = -1; + goto done; + } + + while ((scn = elf_nextscn(elf, scn))) { + const char *sh_name; + GElf_Shdr sh; + + if (CHECK(gelf_getshdr(scn, &sh) != &sh, + "file:%s gelf_getshdr != &sh", fn)) { + ret = -1; + goto done; + } + + sh_name = elf_strptr(elf, ehdr.e_shstrndx, sh.sh_name); + if (!strcmp(sh_name, BTF_ELF_SEC)) { + ret = 1; + goto done; + } + } + + ret = 0; + +done: + close(elf_fd); + elf_end(elf); + return ret; +} + +static int do_test_file(unsigned int test_num) +{ + const struct btf_file_test *test = &file_tests[test_num - 1]; + struct bpf_object *obj = NULL; + struct bpf_program *prog; + struct bpf_map *map; + int err; + + fprintf(stderr, "BTF libbpf test[%u] (%s): ", test_num, + test->file); + + err = file_has_btf_elf(test->file); + if (err == -1) + return err; + + if (err == 0) { + fprintf(stderr, "SKIP. No ELF %s found", BTF_ELF_SEC); + skip_cnt++; + return 0; + } + + obj = bpf_object__open(test->file); + if (CHECK(IS_ERR(obj), "obj: %ld", PTR_ERR(obj))) + return PTR_ERR(obj); + + err = bpf_object__btf_fd(obj); + if (CHECK(err == -1, "bpf_object__btf_fd: -1")) + goto done; + + prog = bpf_program__next(NULL, obj); + if (CHECK(!prog, "Cannot find bpf_prog")) { + err = -1; + goto done; + } + + bpf_program__set_type(prog, BPF_PROG_TYPE_TRACEPOINT); + err = bpf_object__load(obj); + if (CHECK(err < 0, "bpf_object__load: %d", err)) + goto done; + + map = bpf_object__find_map_by_name(obj, "btf_map"); + if (CHECK(!map, "btf_map not found")) { + err = -1; + goto done; + } + + err = (bpf_map__btf_key_type_id(map) == 0 || bpf_map__btf_value_type_id(map) == 0) + != test->btf_kv_notfound; + if (CHECK(err, "btf_key_type_id:%u btf_value_type_id:%u test->btf_kv_notfound:%u", + bpf_map__btf_key_type_id(map), bpf_map__btf_value_type_id(map), + test->btf_kv_notfound)) + goto done; + + fprintf(stderr, "OK"); + +done: + bpf_object__close(obj); + return err; +} + +static int test_file(void) +{ + unsigned int i; + int err = 0; + + if (args.file_test_num) + return count_result(do_test_file(args.file_test_num)); + + for (i = 1; i <= ARRAY_SIZE(file_tests); i++) + err |= count_result(do_test_file(i)); + + return err; +} + +const char *pprint_enum_str[] = { + "ENUM_ZERO", + "ENUM_ONE", + "ENUM_TWO", + "ENUM_THREE", +}; + +struct pprint_mapv { + uint32_t ui32; + uint16_t ui16; + /* 2 bytes hole */ + int32_t si32; + uint32_t unused_bits2a:2, + bits28:28, + unused_bits2b:2; + union { + uint64_t ui64; + uint8_t ui8a[8]; + }; + enum { + ENUM_ZERO, + ENUM_ONE, + ENUM_TWO, + ENUM_THREE, + } aenum; +}; + +static struct btf_raw_test pprint_test = { + .descr = "BTF pretty print test #1", + .raw_types = { + /* unsighed char */ /* [1] */ + BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 8, 1), + /* unsigned short */ /* [2] */ + BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 16, 2), + /* unsigned int */ /* [3] */ + BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 32, 4), + /* int */ /* [4] */ + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), + /* unsigned long long */ /* [5] */ + BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 64, 8), + /* 2 bits */ /* [6] */ + BTF_TYPE_INT_ENC(0, 0, 0, 2, 2), + /* 28 bits */ /* [7] */ + BTF_TYPE_INT_ENC(0, 0, 0, 28, 4), + /* uint8_t[8] */ /* [8] */ + BTF_TYPE_ARRAY_ENC(9, 1, 8), + /* typedef unsigned char uint8_t */ /* [9] */ + BTF_TYPEDEF_ENC(NAME_TBD, 1), + /* typedef unsigned short uint16_t */ /* [10] */ + BTF_TYPEDEF_ENC(NAME_TBD, 2), + /* typedef unsigned int uint32_t */ /* [11] */ + BTF_TYPEDEF_ENC(NAME_TBD, 3), + /* typedef int int32_t */ /* [12] */ + BTF_TYPEDEF_ENC(NAME_TBD, 4), + /* typedef unsigned long long uint64_t *//* [13] */ + BTF_TYPEDEF_ENC(NAME_TBD, 5), + /* union (anon) */ /* [14] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_UNION, 0, 2), 8), + BTF_MEMBER_ENC(NAME_TBD, 13, 0),/* uint64_t ui64; */ + BTF_MEMBER_ENC(NAME_TBD, 8, 0), /* uint8_t ui8a[8]; */ + /* enum (anon) */ /* [15] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 4), 4), + BTF_ENUM_ENC(NAME_TBD, 0), + BTF_ENUM_ENC(NAME_TBD, 1), + BTF_ENUM_ENC(NAME_TBD, 2), + BTF_ENUM_ENC(NAME_TBD, 3), + /* struct pprint_mapv */ /* [16] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 8), 28), + BTF_MEMBER_ENC(NAME_TBD, 11, 0), /* uint32_t ui32 */ + BTF_MEMBER_ENC(NAME_TBD, 10, 32), /* uint16_t ui16 */ + BTF_MEMBER_ENC(NAME_TBD, 12, 64), /* int32_t si32 */ + BTF_MEMBER_ENC(NAME_TBD, 6, 96), /* unused_bits2a */ + BTF_MEMBER_ENC(NAME_TBD, 7, 98), /* bits28 */ + BTF_MEMBER_ENC(NAME_TBD, 6, 126), /* unused_bits2b */ + BTF_MEMBER_ENC(0, 14, 128), /* union (anon) */ + BTF_MEMBER_ENC(NAME_TBD, 15, 192), /* aenum */ + BTF_END_RAW, + }, + .str_sec = "\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum", + .str_sec_size = sizeof("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "pprint_test", + .key_size = sizeof(unsigned int), + .value_size = sizeof(struct pprint_mapv), + .key_type_id = 3, /* unsigned int */ + .value_type_id = 16, /* struct pprint_mapv */ + .max_entries = 128 * 1024, +}; + +static void set_pprint_mapv(struct pprint_mapv *v, uint32_t i) +{ + v->ui32 = i; + v->si32 = -i; + v->unused_bits2a = 3; + v->bits28 = i; + v->unused_bits2b = 3; + v->ui64 = i; + v->aenum = i & 0x03; +} + +static int test_pprint(void) +{ + const struct btf_raw_test *test = &pprint_test; + struct bpf_create_map_attr create_attr = {}; + int map_fd = -1, btf_fd = -1; + struct pprint_mapv mapv = {}; + unsigned int raw_btf_size; + char expected_line[255]; + FILE *pin_file = NULL; + char pin_path[255]; + size_t line_len = 0; + char *line = NULL; + unsigned int key; + uint8_t *raw_btf; + ssize_t nread; + int err, ret; + + fprintf(stderr, "%s......", test->descr); + raw_btf = btf_raw_create(&hdr_tmpl, test->raw_types, + test->str_sec, test->str_sec_size, + &raw_btf_size); + + if (!raw_btf) + return -1; + + *btf_log_buf = '\0'; + btf_fd = bpf_load_btf(raw_btf, raw_btf_size, + btf_log_buf, BTF_LOG_BUF_SIZE, + args.always_log); + free(raw_btf); + + if (CHECK(btf_fd == -1, "errno:%d", errno)) { + err = -1; + goto done; + } + + create_attr.name = test->map_name; + create_attr.map_type = test->map_type; + create_attr.key_size = test->key_size; + create_attr.value_size = test->value_size; + create_attr.max_entries = test->max_entries; + create_attr.btf_fd = btf_fd; + create_attr.btf_key_type_id = test->key_type_id; + create_attr.btf_value_type_id = test->value_type_id; + + map_fd = bpf_create_map_xattr(&create_attr); + if (CHECK(map_fd == -1, "errno:%d", errno)) { + err = -1; + goto done; + } + + ret = snprintf(pin_path, sizeof(pin_path), "%s/%s", + "/sys/fs/bpf", test->map_name); + + if (CHECK(ret == sizeof(pin_path), "pin_path %s/%s is too long", + "/sys/fs/bpf", test->map_name)) { + err = -1; + goto done; + } + + err = bpf_obj_pin(map_fd, pin_path); + if (CHECK(err, "bpf_obj_pin(%s): errno:%d.", pin_path, errno)) + goto done; + + for (key = 0; key < test->max_entries; key++) { + set_pprint_mapv(&mapv, key); + bpf_map_update_elem(map_fd, &key, &mapv, 0); + } + + pin_file = fopen(pin_path, "r"); + if (CHECK(!pin_file, "fopen(%s): errno:%d", pin_path, errno)) { + err = -1; + goto done; + } + + /* Skip lines start with '#' */ + while ((nread = getline(&line, &line_len, pin_file)) > 0 && + *line == '#') + ; + + if (CHECK(nread <= 0, "Unexpected EOF")) { + err = -1; + goto done; + } + + key = 0; + do { + ssize_t nexpected_line; + + set_pprint_mapv(&mapv, key); + nexpected_line = snprintf(expected_line, sizeof(expected_line), + "%u: {%u,0,%d,0x%x,0x%x,0x%x,{%lu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s}\n", + key, + mapv.ui32, mapv.si32, + mapv.unused_bits2a, mapv.bits28, mapv.unused_bits2b, + mapv.ui64, + mapv.ui8a[0], mapv.ui8a[1], mapv.ui8a[2], mapv.ui8a[3], + mapv.ui8a[4], mapv.ui8a[5], mapv.ui8a[6], mapv.ui8a[7], + pprint_enum_str[mapv.aenum]); + + if (CHECK(nexpected_line == sizeof(expected_line), + "expected_line is too long")) { + err = -1; + goto done; + } + + if (strcmp(expected_line, line)) { + err = -1; + fprintf(stderr, "unexpected pprint output\n"); + fprintf(stderr, "expected: %s", expected_line); + fprintf(stderr, " read: %s", line); + goto done; + } + + nread = getline(&line, &line_len, pin_file); + } while (++key < test->max_entries && nread > 0); + + if (CHECK(key < test->max_entries, + "Unexpected EOF. key:%u test->max_entries:%u", + key, test->max_entries)) { + err = -1; + goto done; + } + + if (CHECK(nread > 0, "Unexpected extra pprint output: %s", line)) { + err = -1; + goto done; + } + + err = 0; + +done: + if (!err) + fprintf(stderr, "OK"); + if (*btf_log_buf && (err || args.always_log)) + fprintf(stderr, "\n%s", btf_log_buf); + if (btf_fd != -1) + close(btf_fd); + if (map_fd != -1) + close(map_fd); + if (pin_file) + fclose(pin_file); + unlink(pin_path); + free(line); + + return err; +} + +static void usage(const char *cmd) +{ + fprintf(stderr, "Usage: %s [-l] [[-r test_num (1 - %zu)] | [-g test_num (1 - %zu)] | [-f test_num (1 - %zu)] | [-p]]\n", + cmd, ARRAY_SIZE(raw_tests), ARRAY_SIZE(get_info_tests), + ARRAY_SIZE(file_tests)); +} + +static int parse_args(int argc, char **argv) +{ + const char *optstr = "lpf:r:g:"; + int opt; + + while ((opt = getopt(argc, argv, optstr)) != -1) { + switch (opt) { + case 'l': + args.always_log = true; + break; + case 'f': + args.file_test_num = atoi(optarg); + args.file_test = true; + break; + case 'r': + args.raw_test_num = atoi(optarg); + args.raw_test = true; + break; + case 'g': + args.get_info_test_num = atoi(optarg); + args.get_info_test = true; + break; + case 'p': + args.pprint_test = true; + break; + case 'h': + usage(argv[0]); + exit(0); + default: + usage(argv[0]); + return -1; + } + } + + if (args.raw_test_num && + (args.raw_test_num < 1 || + args.raw_test_num > ARRAY_SIZE(raw_tests))) { + fprintf(stderr, "BTF raw test number must be [1 - %zu]\n", + ARRAY_SIZE(raw_tests)); + return -1; + } + + if (args.file_test_num && + (args.file_test_num < 1 || + args.file_test_num > ARRAY_SIZE(file_tests))) { + fprintf(stderr, "BTF file test number must be [1 - %zu]\n", + ARRAY_SIZE(file_tests)); + return -1; + } + + if (args.get_info_test_num && + (args.get_info_test_num < 1 || + args.get_info_test_num > ARRAY_SIZE(get_info_tests))) { + fprintf(stderr, "BTF get info test number must be [1 - %zu]\n", + ARRAY_SIZE(get_info_tests)); + return -1; + } + + return 0; +} + +static void print_summary(void) +{ + fprintf(stderr, "PASS:%u SKIP:%u FAIL:%u\n", + pass_cnt - skip_cnt, skip_cnt, error_cnt); +} + +int main(int argc, char **argv) +{ + int err = 0; + + err = parse_args(argc, argv); + if (err) + return err; + + if (args.always_log) + libbpf_set_print(__base_pr, __base_pr, __base_pr); + + if (args.raw_test) + err |= test_raw(); + + if (args.get_info_test) + err |= test_get_info(); + + if (args.file_test) + err |= test_file(); + + if (args.pprint_test) + err |= count_result(test_pprint()); + + if (args.raw_test || args.get_info_test || args.file_test || + args.pprint_test) + goto done; + + err |= test_raw(); + err |= test_get_info(); + err |= test_file(); + +done: + print_summary(); + return err; +} diff --git a/tools/testing/selftests/bpf/test_btf_haskv.c b/tools/testing/selftests/bpf/test_btf_haskv.c new file mode 100644 index 0000000..8c7ca09 --- /dev/null +++ b/tools/testing/selftests/bpf/test_btf_haskv.c @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018 Facebook */ +#include <linux/bpf.h> +#include "bpf_helpers.h" + +int _version SEC("version") = 1; + +struct ipv_counts { + unsigned int v4; + unsigned int v6; +}; + +typedef int btf_map_key; +typedef struct ipv_counts btf_map_value; +btf_map_key dumm_key; +btf_map_value dummy_value; + +struct bpf_map_def SEC("maps") btf_map = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(struct ipv_counts), + .max_entries = 4, +}; + +struct dummy_tracepoint_args { + unsigned long long pad; + struct sock *sock; +}; + +SEC("dummy_tracepoint") +int _dummy_tracepoint(struct dummy_tracepoint_args *arg) +{ + struct ipv_counts *counts; + int key = 0; + + if (!arg->sock) + return 0; + + counts = bpf_map_lookup_elem(&btf_map, &key); + if (!counts) + return 0; + + counts->v6++; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_btf_nokv.c b/tools/testing/selftests/bpf/test_btf_nokv.c new file mode 100644 index 0000000..0ed8e08 --- /dev/null +++ b/tools/testing/selftests/bpf/test_btf_nokv.c @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018 Facebook */ +#include <linux/bpf.h> +#include "bpf_helpers.h" + +int _version SEC("version") = 1; + +struct ipv_counts { + unsigned int v4; + unsigned int v6; +}; + +struct bpf_map_def SEC("maps") btf_map = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(struct ipv_counts), + .max_entries = 4, +}; + +struct dummy_tracepoint_args { + unsigned long long pad; + struct sock *sock; +}; + +SEC("dummy_tracepoint") +int _dummy_tracepoint(struct dummy_tracepoint_args *arg) +{ + struct ipv_counts *counts; + int key = 0; + + if (!arg->sock) + return 0; + + counts = bpf_map_lookup_elem(&btf_map, &key); + if (!counts) + return 0; + + counts->v6++; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_get_stack_rawtp.c b/tools/testing/selftests/bpf/test_get_stack_rawtp.c new file mode 100644 index 0000000..f6d9f23 --- /dev/null +++ b/tools/testing/selftests/bpf/test_get_stack_rawtp.c @@ -0,0 +1,102 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include "bpf_helpers.h" + +/* Permit pretty deep stack traces */ +#define MAX_STACK_RAWTP 100 +struct stack_trace_t { + int pid; + int kern_stack_size; + int user_stack_size; + int user_stack_buildid_size; + __u64 kern_stack[MAX_STACK_RAWTP]; + __u64 user_stack[MAX_STACK_RAWTP]; + struct bpf_stack_build_id user_stack_buildid[MAX_STACK_RAWTP]; +}; + +struct bpf_map_def SEC("maps") perfmap = { + .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(__u32), + .max_entries = 2, +}; + +struct bpf_map_def SEC("maps") stackdata_map = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct stack_trace_t), + .max_entries = 1, +}; + +/* Allocate per-cpu space twice the needed. For the code below + * usize = bpf_get_stack(ctx, raw_data, max_len, BPF_F_USER_STACK); + * if (usize < 0) + * return 0; + * ksize = bpf_get_stack(ctx, raw_data + usize, max_len - usize, 0); + * + * If we have value_size = MAX_STACK_RAWTP * sizeof(__u64), + * verifier will complain that access "raw_data + usize" + * with size "max_len - usize" may be out of bound. + * The maximum "raw_data + usize" is "raw_data + max_len" + * and the maximum "max_len - usize" is "max_len", verifier + * concludes that the maximum buffer access range is + * "raw_data[0...max_len * 2 - 1]" and hence reject the program. + * + * Doubling the to-be-used max buffer size can fix this verifier + * issue and avoid complicated C programming massaging. + * This is an acceptable workaround since there is one entry here. + */ +struct bpf_map_def SEC("maps") rawdata_map = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(__u32), + .value_size = MAX_STACK_RAWTP * sizeof(__u64) * 2, + .max_entries = 1, +}; + +SEC("tracepoint/raw_syscalls/sys_enter") +int bpf_prog1(void *ctx) +{ + int max_len, max_buildid_len, usize, ksize, total_size; + struct stack_trace_t *data; + void *raw_data; + __u32 key = 0; + + data = bpf_map_lookup_elem(&stackdata_map, &key); + if (!data) + return 0; + + max_len = MAX_STACK_RAWTP * sizeof(__u64); + max_buildid_len = MAX_STACK_RAWTP * sizeof(struct bpf_stack_build_id); + data->pid = bpf_get_current_pid_tgid(); + data->kern_stack_size = bpf_get_stack(ctx, data->kern_stack, + max_len, 0); + data->user_stack_size = bpf_get_stack(ctx, data->user_stack, max_len, + BPF_F_USER_STACK); + data->user_stack_buildid_size = bpf_get_stack( + ctx, data->user_stack_buildid, max_buildid_len, + BPF_F_USER_STACK | BPF_F_USER_BUILD_ID); + bpf_perf_event_output(ctx, &perfmap, 0, data, sizeof(*data)); + + /* write both kernel and user stacks to the same buffer */ + raw_data = bpf_map_lookup_elem(&rawdata_map, &key); + if (!raw_data) + return 0; + + usize = bpf_get_stack(ctx, raw_data, max_len, BPF_F_USER_STACK); + if (usize < 0) + return 0; + + ksize = bpf_get_stack(ctx, raw_data + usize, max_len - usize, 0); + if (ksize < 0) + return 0; + + total_size = usize + ksize; + if (total_size > 0 && total_size <= max_len) + bpf_perf_event_output(ctx, &perfmap, 0, raw_data, total_size); + + return 0; +} + +char _license[] SEC("license") = "GPL"; +__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */ diff --git a/tools/testing/selftests/bpf/test_lirc_mode2.sh b/tools/testing/selftests/bpf/test_lirc_mode2.sh new file mode 100755 index 0000000..ce2e15e --- /dev/null +++ b/tools/testing/selftests/bpf/test_lirc_mode2.sh @@ -0,0 +1,28 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +GREEN='\033[0;92m' +RED='\033[0;31m' +NC='\033[0m' # No Color + +modprobe rc-loopback + +for i in /sys/class/rc/rc* +do + if grep -q DRV_NAME=rc-loopback $i/uevent + then + LIRCDEV=$(grep DEVNAME= $i/lirc*/uevent | sed sQDEVNAME=Q/dev/Q) + fi +done + +if [ -n $LIRCDEV ]; +then + TYPE=lirc_mode2 + ./test_lirc_mode2_user $LIRCDEV + ret=$? + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + else + echo -e ${GREEN}"PASS: $TYPE"${NC} + fi +fi diff --git a/tools/testing/selftests/bpf/test_lirc_mode2_kern.c b/tools/testing/selftests/bpf/test_lirc_mode2_kern.c new file mode 100644 index 0000000..ba26855 --- /dev/null +++ b/tools/testing/selftests/bpf/test_lirc_mode2_kern.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 +// test ir decoder +// +// Copyright (C) 2018 Sean Young <sean@mess.org> + +#include <linux/bpf.h> +#include <linux/lirc.h> +#include "bpf_helpers.h" + +SEC("lirc_mode2") +int bpf_decoder(unsigned int *sample) +{ + if (LIRC_IS_PULSE(*sample)) { + unsigned int duration = LIRC_VALUE(*sample); + + if (duration & 0x10000) + bpf_rc_keydown(sample, 0x40, duration & 0xffff, 0); + } + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_lirc_mode2_user.c b/tools/testing/selftests/bpf/test_lirc_mode2_user.c new file mode 100644 index 0000000..d470d63 --- /dev/null +++ b/tools/testing/selftests/bpf/test_lirc_mode2_user.c @@ -0,0 +1,149 @@ +// SPDX-License-Identifier: GPL-2.0 +// test ir decoder +// +// Copyright (C) 2018 Sean Young <sean@mess.org> + +// A lirc chardev is a device representing a consumer IR (cir) device which +// can receive infrared signals from remote control and/or transmit IR. +// +// IR is sent as a series of pulses and space somewhat like morse code. The +// BPF program can decode this into scancodes so that rc-core can translate +// this into input key codes using the rc keymap. +// +// This test works by sending IR over rc-loopback, so the IR is processed by +// BPF and then decoded into scancodes. The lirc chardev must be the one +// associated with rc-loopback, see the output of ir-keytable(1). +// +// The following CONFIG options must be enabled for the test to succeed: +// CONFIG_RC_CORE=y +// CONFIG_BPF_RAWIR_EVENT=y +// CONFIG_RC_LOOPBACK=y + +// Steps: +// 1. Open the /dev/lircN device for rc-loopback (given on command line) +// 2. Attach bpf_lirc_mode2 program which decodes some IR. +// 3. Send some IR to the same IR device; since it is loopback, this will +// end up in the bpf program +// 4. bpf program should decode IR and report keycode +// 5. We can read keycode from same /dev/lirc device + +#include <linux/bpf.h> +#include <linux/lirc.h> +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <poll.h> +#include <sys/types.h> +#include <sys/ioctl.h> +#include <sys/stat.h> +#include <fcntl.h> + +#include "bpf_util.h" +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +int main(int argc, char **argv) +{ + struct bpf_object *obj; + int ret, lircfd, progfd, mode; + int testir = 0x1dead; + u32 prog_ids[10], prog_flags[10], prog_cnt; + + if (argc != 2) { + printf("Usage: %s /dev/lircN\n", argv[0]); + return 2; + } + + ret = bpf_prog_load("test_lirc_mode2_kern.o", + BPF_PROG_TYPE_LIRC_MODE2, &obj, &progfd); + if (ret) { + printf("Failed to load bpf program\n"); + return 1; + } + + lircfd = open(argv[1], O_RDWR | O_NONBLOCK); + if (lircfd == -1) { + printf("failed to open lirc device %s: %m\n", argv[1]); + return 1; + } + + /* Let's try detach it before it was ever attached */ + ret = bpf_prog_detach2(progfd, lircfd, BPF_LIRC_MODE2); + if (ret != -1 || errno != ENOENT) { + printf("bpf_prog_detach2 not attached should fail: %m\n"); + return 1; + } + + mode = LIRC_MODE_SCANCODE; + if (ioctl(lircfd, LIRC_SET_REC_MODE, &mode)) { + printf("failed to set rec mode: %m\n"); + return 1; + } + + prog_cnt = 10; + ret = bpf_prog_query(lircfd, BPF_LIRC_MODE2, 0, prog_flags, prog_ids, + &prog_cnt); + if (ret) { + printf("Failed to query bpf programs on lirc device: %m\n"); + return 1; + } + + if (prog_cnt != 0) { + printf("Expected nothing to be attached\n"); + return 1; + } + + ret = bpf_prog_attach(progfd, lircfd, BPF_LIRC_MODE2, 0); + if (ret) { + printf("Failed to attach bpf to lirc device: %m\n"); + return 1; + } + + /* Write raw IR */ + ret = write(lircfd, &testir, sizeof(testir)); + if (ret != sizeof(testir)) { + printf("Failed to send test IR message: %m\n"); + return 1; + } + + struct pollfd pfd = { .fd = lircfd, .events = POLLIN }; + struct lirc_scancode lsc; + + poll(&pfd, 1, 100); + + /* Read decoded IR */ + ret = read(lircfd, &lsc, sizeof(lsc)); + if (ret != sizeof(lsc)) { + printf("Failed to read decoded IR: %m\n"); + return 1; + } + + if (lsc.scancode != 0xdead || lsc.rc_proto != 64) { + printf("Incorrect scancode decoded\n"); + return 1; + } + + prog_cnt = 10; + ret = bpf_prog_query(lircfd, BPF_LIRC_MODE2, 0, prog_flags, prog_ids, + &prog_cnt); + if (ret) { + printf("Failed to query bpf programs on lirc device: %m\n"); + return 1; + } + + if (prog_cnt != 1) { + printf("Expected one program to be attached\n"); + return 1; + } + + /* Let's try detaching it now it is actually attached */ + ret = bpf_prog_detach2(progfd, lircfd, BPF_LIRC_MODE2); + if (ret) { + printf("bpf_prog_detach2: returned %m\n"); + return 1; + } + + return 0; +} diff --git a/tools/testing/selftests/bpf/test_lwt_seg6local.c b/tools/testing/selftests/bpf/test_lwt_seg6local.c new file mode 100644 index 0000000..0575751 --- /dev/null +++ b/tools/testing/selftests/bpf/test_lwt_seg6local.c @@ -0,0 +1,437 @@ +#include <stddef.h> +#include <inttypes.h> +#include <errno.h> +#include <linux/seg6_local.h> +#include <linux/bpf.h> +#include "bpf_helpers.h" +#include "bpf_endian.h" + +#define bpf_printk(fmt, ...) \ +({ \ + char ____fmt[] = fmt; \ + bpf_trace_printk(____fmt, sizeof(____fmt), \ + ##__VA_ARGS__); \ +}) + +/* Packet parsing state machine helpers. */ +#define cursor_advance(_cursor, _len) \ + ({ void *_tmp = _cursor; _cursor += _len; _tmp; }) + +#define SR6_FLAG_ALERT (1 << 4) + +#define htonll(x) ((bpf_htonl(1)) == 1 ? (x) : ((uint64_t)bpf_htonl((x) & \ + 0xFFFFFFFF) << 32) | bpf_htonl((x) >> 32)) +#define ntohll(x) ((bpf_ntohl(1)) == 1 ? (x) : ((uint64_t)bpf_ntohl((x) & \ + 0xFFFFFFFF) << 32) | bpf_ntohl((x) >> 32)) +#define BPF_PACKET_HEADER __attribute__((packed)) + +struct ip6_t { + unsigned int ver:4; + unsigned int priority:8; + unsigned int flow_label:20; + unsigned short payload_len; + unsigned char next_header; + unsigned char hop_limit; + unsigned long long src_hi; + unsigned long long src_lo; + unsigned long long dst_hi; + unsigned long long dst_lo; +} BPF_PACKET_HEADER; + +struct ip6_addr_t { + unsigned long long hi; + unsigned long long lo; +} BPF_PACKET_HEADER; + +struct ip6_srh_t { + unsigned char nexthdr; + unsigned char hdrlen; + unsigned char type; + unsigned char segments_left; + unsigned char first_segment; + unsigned char flags; + unsigned short tag; + + struct ip6_addr_t segments[0]; +} BPF_PACKET_HEADER; + +struct sr6_tlv_t { + unsigned char type; + unsigned char len; + unsigned char value[0]; +} BPF_PACKET_HEADER; + +__attribute__((always_inline)) struct ip6_srh_t *get_srh(struct __sk_buff *skb) +{ + void *cursor, *data_end; + struct ip6_srh_t *srh; + struct ip6_t *ip; + uint8_t *ipver; + + data_end = (void *)(long)skb->data_end; + cursor = (void *)(long)skb->data; + ipver = (uint8_t *)cursor; + + if ((void *)ipver + sizeof(*ipver) > data_end) + return NULL; + + if ((*ipver >> 4) != 6) + return NULL; + + ip = cursor_advance(cursor, sizeof(*ip)); + if ((void *)ip + sizeof(*ip) > data_end) + return NULL; + + if (ip->next_header != 43) + return NULL; + + srh = cursor_advance(cursor, sizeof(*srh)); + if ((void *)srh + sizeof(*srh) > data_end) + return NULL; + + if (srh->type != 4) + return NULL; + + return srh; +} + +__attribute__((always_inline)) +int update_tlv_pad(struct __sk_buff *skb, uint32_t new_pad, + uint32_t old_pad, uint32_t pad_off) +{ + int err; + + if (new_pad != old_pad) { + err = bpf_lwt_seg6_adjust_srh(skb, pad_off, + (int) new_pad - (int) old_pad); + if (err) + return err; + } + + if (new_pad > 0) { + char pad_tlv_buf[16] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0}; + struct sr6_tlv_t *pad_tlv = (struct sr6_tlv_t *) pad_tlv_buf; + + pad_tlv->type = SR6_TLV_PADDING; + pad_tlv->len = new_pad - 2; + + err = bpf_lwt_seg6_store_bytes(skb, pad_off, + (void *)pad_tlv_buf, new_pad); + if (err) + return err; + } + + return 0; +} + +__attribute__((always_inline)) +int is_valid_tlv_boundary(struct __sk_buff *skb, struct ip6_srh_t *srh, + uint32_t *tlv_off, uint32_t *pad_size, + uint32_t *pad_off) +{ + uint32_t srh_off, cur_off; + int offset_valid = 0; + int err; + + srh_off = (char *)srh - (char *)(long)skb->data; + // cur_off = end of segments, start of possible TLVs + cur_off = srh_off + sizeof(*srh) + + sizeof(struct ip6_addr_t) * (srh->first_segment + 1); + + *pad_off = 0; + + // we can only go as far as ~10 TLVs due to the BPF max stack size + #pragma clang loop unroll(full) + for (int i = 0; i < 10; i++) { + struct sr6_tlv_t tlv; + + if (cur_off == *tlv_off) + offset_valid = 1; + + if (cur_off >= srh_off + ((srh->hdrlen + 1) << 3)) + break; + + err = bpf_skb_load_bytes(skb, cur_off, &tlv, sizeof(tlv)); + if (err) + return err; + + if (tlv.type == SR6_TLV_PADDING) { + *pad_size = tlv.len + sizeof(tlv); + *pad_off = cur_off; + + if (*tlv_off == srh_off) { + *tlv_off = cur_off; + offset_valid = 1; + } + break; + + } else if (tlv.type == SR6_TLV_HMAC) { + break; + } + + cur_off += sizeof(tlv) + tlv.len; + } // we reached the padding or HMAC TLVs, or the end of the SRH + + if (*pad_off == 0) + *pad_off = cur_off; + + if (*tlv_off == -1) + *tlv_off = cur_off; + else if (!offset_valid) + return -EINVAL; + + return 0; +} + +__attribute__((always_inline)) +int add_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh, uint32_t tlv_off, + struct sr6_tlv_t *itlv, uint8_t tlv_size) +{ + uint32_t srh_off = (char *)srh - (char *)(long)skb->data; + uint8_t len_remaining, new_pad; + uint32_t pad_off = 0; + uint32_t pad_size = 0; + uint32_t partial_srh_len; + int err; + + if (tlv_off != -1) + tlv_off += srh_off; + + if (itlv->type == SR6_TLV_PADDING || itlv->type == SR6_TLV_HMAC) + return -EINVAL; + + err = is_valid_tlv_boundary(skb, srh, &tlv_off, &pad_size, &pad_off); + if (err) + return err; + + err = bpf_lwt_seg6_adjust_srh(skb, tlv_off, sizeof(*itlv) + itlv->len); + if (err) + return err; + + err = bpf_lwt_seg6_store_bytes(skb, tlv_off, (void *)itlv, tlv_size); + if (err) + return err; + + // the following can't be moved inside update_tlv_pad because the + // bpf verifier has some issues with it + pad_off += sizeof(*itlv) + itlv->len; + partial_srh_len = pad_off - srh_off; + len_remaining = partial_srh_len % 8; + new_pad = 8 - len_remaining; + + if (new_pad == 1) // cannot pad for 1 byte only + new_pad = 9; + else if (new_pad == 8) + new_pad = 0; + + return update_tlv_pad(skb, new_pad, pad_size, pad_off); +} + +__attribute__((always_inline)) +int delete_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh, + uint32_t tlv_off) +{ + uint32_t srh_off = (char *)srh - (char *)(long)skb->data; + uint8_t len_remaining, new_pad; + uint32_t partial_srh_len; + uint32_t pad_off = 0; + uint32_t pad_size = 0; + struct sr6_tlv_t tlv; + int err; + + tlv_off += srh_off; + + err = is_valid_tlv_boundary(skb, srh, &tlv_off, &pad_size, &pad_off); + if (err) + return err; + + err = bpf_skb_load_bytes(skb, tlv_off, &tlv, sizeof(tlv)); + if (err) + return err; + + err = bpf_lwt_seg6_adjust_srh(skb, tlv_off, -(sizeof(tlv) + tlv.len)); + if (err) + return err; + + pad_off -= sizeof(tlv) + tlv.len; + partial_srh_len = pad_off - srh_off; + len_remaining = partial_srh_len % 8; + new_pad = 8 - len_remaining; + if (new_pad == 1) // cannot pad for 1 byte only + new_pad = 9; + else if (new_pad == 8) + new_pad = 0; + + return update_tlv_pad(skb, new_pad, pad_size, pad_off); +} + +__attribute__((always_inline)) +int has_egr_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh) +{ + int tlv_offset = sizeof(struct ip6_t) + sizeof(struct ip6_srh_t) + + ((srh->first_segment + 1) << 4); + struct sr6_tlv_t tlv; + + if (bpf_skb_load_bytes(skb, tlv_offset, &tlv, sizeof(struct sr6_tlv_t))) + return 0; + + if (tlv.type == SR6_TLV_EGRESS && tlv.len == 18) { + struct ip6_addr_t egr_addr; + + if (bpf_skb_load_bytes(skb, tlv_offset + 4, &egr_addr, 16)) + return 0; + + // check if egress TLV value is correct + if (ntohll(egr_addr.hi) == 0xfd00000000000000 && + ntohll(egr_addr.lo) == 0x4) + return 1; + } + + return 0; +} + +// This function will push a SRH with segments fd00::1, fd00::2, fd00::3, +// fd00::4 +SEC("encap_srh") +int __encap_srh(struct __sk_buff *skb) +{ + unsigned long long hi = 0xfd00000000000000; + struct ip6_addr_t *seg; + struct ip6_srh_t *srh; + char srh_buf[72]; // room for 4 segments + int err; + + srh = (struct ip6_srh_t *)srh_buf; + srh->nexthdr = 0; + srh->hdrlen = 8; + srh->type = 4; + srh->segments_left = 3; + srh->first_segment = 3; + srh->flags = 0; + srh->tag = 0; + + seg = (struct ip6_addr_t *)((char *)srh + sizeof(*srh)); + + #pragma clang loop unroll(full) + for (unsigned long long lo = 0; lo < 4; lo++) { + seg->lo = htonll(4 - lo); + seg->hi = htonll(hi); + seg = (struct ip6_addr_t *)((char *)seg + sizeof(*seg)); + } + + err = bpf_lwt_push_encap(skb, 0, (void *)srh, sizeof(srh_buf)); + if (err) + return BPF_DROP; + + return BPF_REDIRECT; +} + +// Add an Egress TLV fc00::4, add the flag A, +// and apply End.X action to fc42::1 +SEC("add_egr_x") +int __add_egr_x(struct __sk_buff *skb) +{ + unsigned long long hi = 0xfc42000000000000; + unsigned long long lo = 0x1; + struct ip6_srh_t *srh = get_srh(skb); + uint8_t new_flags = SR6_FLAG_ALERT; + struct ip6_addr_t addr; + int err, offset; + + if (srh == NULL) + return BPF_DROP; + + uint8_t tlv[20] = {2, 18, 0, 0, 0xfd, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x4}; + + err = add_tlv(skb, srh, (srh->hdrlen+1) << 3, + (struct sr6_tlv_t *)&tlv, 20); + if (err) + return BPF_DROP; + + offset = sizeof(struct ip6_t) + offsetof(struct ip6_srh_t, flags); + err = bpf_lwt_seg6_store_bytes(skb, offset, + (void *)&new_flags, sizeof(new_flags)); + if (err) + return BPF_DROP; + + addr.lo = htonll(lo); + addr.hi = htonll(hi); + err = bpf_lwt_seg6_action(skb, SEG6_LOCAL_ACTION_END_X, + (void *)&addr, sizeof(addr)); + if (err) + return BPF_DROP; + return BPF_REDIRECT; +} + +// Pop the Egress TLV, reset the flags, change the tag 2442 and finally do a +// simple End action +SEC("pop_egr") +int __pop_egr(struct __sk_buff *skb) +{ + struct ip6_srh_t *srh = get_srh(skb); + uint16_t new_tag = bpf_htons(2442); + uint8_t new_flags = 0; + int err, offset; + + if (srh == NULL) + return BPF_DROP; + + if (srh->flags != SR6_FLAG_ALERT) + return BPF_DROP; + + if (srh->hdrlen != 11) // 4 segments + Egress TLV + Padding TLV + return BPF_DROP; + + if (!has_egr_tlv(skb, srh)) + return BPF_DROP; + + err = delete_tlv(skb, srh, 8 + (srh->first_segment + 1) * 16); + if (err) + return BPF_DROP; + + offset = sizeof(struct ip6_t) + offsetof(struct ip6_srh_t, flags); + if (bpf_lwt_seg6_store_bytes(skb, offset, (void *)&new_flags, + sizeof(new_flags))) + return BPF_DROP; + + offset = sizeof(struct ip6_t) + offsetof(struct ip6_srh_t, tag); + if (bpf_lwt_seg6_store_bytes(skb, offset, (void *)&new_tag, + sizeof(new_tag))) + return BPF_DROP; + + return BPF_OK; +} + +// Inspect if the Egress TLV and flag have been removed, if the tag is correct, +// then apply a End.T action to reach the last segment +SEC("inspect_t") +int __inspect_t(struct __sk_buff *skb) +{ + struct ip6_srh_t *srh = get_srh(skb); + int table = 117; + int err; + + if (srh == NULL) + return BPF_DROP; + + if (srh->flags != 0) + return BPF_DROP; + + if (srh->tag != bpf_htons(2442)) + return BPF_DROP; + + if (srh->hdrlen != 8) // 4 segments + return BPF_DROP; + + err = bpf_lwt_seg6_action(skb, SEG6_LOCAL_ACTION_END_T, + (void *)&table, sizeof(table)); + + if (err) + return BPF_DROP; + + return BPF_REDIRECT; +} + +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_lwt_seg6local.sh b/tools/testing/selftests/bpf/test_lwt_seg6local.sh new file mode 100755 index 0000000..1c77994 --- /dev/null +++ b/tools/testing/selftests/bpf/test_lwt_seg6local.sh @@ -0,0 +1,140 @@ +#!/bin/bash +# Connects 6 network namespaces through veths. +# Each NS may have different IPv6 global scope addresses : +# NS1 ---- NS2 ---- NS3 ---- NS4 ---- NS5 ---- NS6 +# fb00::1 fd00::1 fd00::2 fd00::3 fb00::6 +# fc42::1 fd00::4 +# +# All IPv6 packets going to fb00::/16 through NS2 will be encapsulated in a +# IPv6 header with a Segment Routing Header, with segments : +# fd00::1 -> fd00::2 -> fd00::3 -> fd00::4 +# +# 3 fd00::/16 IPv6 addresses are binded to seg6local End.BPF actions : +# - fd00::1 : add a TLV, change the flags and apply a End.X action to fc42::1 +# - fd00::2 : remove the TLV, change the flags, add a tag +# - fd00::3 : apply an End.T action to fd00::4, through routing table 117 +# +# fd00::4 is a simple Segment Routing node decapsulating the inner IPv6 packet. +# Each End.BPF action will validate the operations applied on the SRH by the +# previous BPF program in the chain, otherwise the packet is dropped. +# +# An UDP datagram is sent from fb00::1 to fb00::6. The test succeeds if this +# datagram can be read on NS6 when binding to fb00::6. + +TMP_FILE="/tmp/selftest_lwt_seg6local.txt" + +cleanup() +{ + if [ "$?" = "0" ]; then + echo "selftests: test_lwt_seg6local [PASS]"; + else + echo "selftests: test_lwt_seg6local [FAILED]"; + fi + + set +e + ip netns del ns1 2> /dev/null + ip netns del ns2 2> /dev/null + ip netns del ns3 2> /dev/null + ip netns del ns4 2> /dev/null + ip netns del ns5 2> /dev/null + ip netns del ns6 2> /dev/null + rm -f $TMP_FILE +} + +set -e + +ip netns add ns1 +ip netns add ns2 +ip netns add ns3 +ip netns add ns4 +ip netns add ns5 +ip netns add ns6 + +trap cleanup 0 2 3 6 9 + +ip link add veth1 type veth peer name veth2 +ip link add veth3 type veth peer name veth4 +ip link add veth5 type veth peer name veth6 +ip link add veth7 type veth peer name veth8 +ip link add veth9 type veth peer name veth10 + +ip link set veth1 netns ns1 +ip link set veth2 netns ns2 +ip link set veth3 netns ns2 +ip link set veth4 netns ns3 +ip link set veth5 netns ns3 +ip link set veth6 netns ns4 +ip link set veth7 netns ns4 +ip link set veth8 netns ns5 +ip link set veth9 netns ns5 +ip link set veth10 netns ns6 + +ip netns exec ns1 ip link set dev veth1 up +ip netns exec ns2 ip link set dev veth2 up +ip netns exec ns2 ip link set dev veth3 up +ip netns exec ns3 ip link set dev veth4 up +ip netns exec ns3 ip link set dev veth5 up +ip netns exec ns4 ip link set dev veth6 up +ip netns exec ns4 ip link set dev veth7 up +ip netns exec ns5 ip link set dev veth8 up +ip netns exec ns5 ip link set dev veth9 up +ip netns exec ns6 ip link set dev veth10 up +ip netns exec ns6 ip link set dev lo up + +# All link scope addresses and routes required between veths +ip netns exec ns1 ip -6 addr add fb00::12/16 dev veth1 scope link +ip netns exec ns1 ip -6 route add fb00::21 dev veth1 scope link +ip netns exec ns2 ip -6 addr add fb00::21/16 dev veth2 scope link +ip netns exec ns2 ip -6 addr add fb00::34/16 dev veth3 scope link +ip netns exec ns2 ip -6 route add fb00::43 dev veth3 scope link +ip netns exec ns3 ip -6 route add fb00::65 dev veth5 scope link +ip netns exec ns3 ip -6 addr add fb00::43/16 dev veth4 scope link +ip netns exec ns3 ip -6 addr add fb00::56/16 dev veth5 scope link +ip netns exec ns4 ip -6 addr add fb00::65/16 dev veth6 scope link +ip netns exec ns4 ip -6 addr add fb00::78/16 dev veth7 scope link +ip netns exec ns4 ip -6 route add fb00::87 dev veth7 scope link +ip netns exec ns5 ip -6 addr add fb00::87/16 dev veth8 scope link +ip netns exec ns5 ip -6 addr add fb00::910/16 dev veth9 scope link +ip netns exec ns5 ip -6 route add fb00::109 dev veth9 scope link +ip netns exec ns5 ip -6 route add fb00::109 table 117 dev veth9 scope link +ip netns exec ns6 ip -6 addr add fb00::109/16 dev veth10 scope link + +ip netns exec ns1 ip -6 addr add fb00::1/16 dev lo +ip netns exec ns1 ip -6 route add fb00::6 dev veth1 via fb00::21 + +ip netns exec ns2 ip -6 route add fb00::6 encap bpf in obj test_lwt_seg6local.o sec encap_srh dev veth2 +ip netns exec ns2 ip -6 route add fd00::1 dev veth3 via fb00::43 scope link + +ip netns exec ns3 ip -6 route add fc42::1 dev veth5 via fb00::65 +ip netns exec ns3 ip -6 route add fd00::1 encap seg6local action End.BPF obj test_lwt_seg6local.o sec add_egr_x dev veth4 + +ip netns exec ns4 ip -6 route add fd00::2 encap seg6local action End.BPF obj test_lwt_seg6local.o sec pop_egr dev veth6 +ip netns exec ns4 ip -6 addr add fc42::1 dev lo +ip netns exec ns4 ip -6 route add fd00::3 dev veth7 via fb00::87 + +ip netns exec ns5 ip -6 route add fd00::4 table 117 dev veth9 via fb00::109 +ip netns exec ns5 ip -6 route add fd00::3 encap seg6local action End.BPF obj test_lwt_seg6local.o sec inspect_t dev veth8 + +ip netns exec ns6 ip -6 addr add fb00::6/16 dev lo +ip netns exec ns6 ip -6 addr add fd00::4/16 dev lo + +ip netns exec ns1 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null +ip netns exec ns2 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null +ip netns exec ns3 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null +ip netns exec ns4 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null +ip netns exec ns5 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null + +ip netns exec ns6 sysctl net.ipv6.conf.all.seg6_enabled=1 > /dev/null +ip netns exec ns6 sysctl net.ipv6.conf.lo.seg6_enabled=1 > /dev/null +ip netns exec ns6 sysctl net.ipv6.conf.veth10.seg6_enabled=1 > /dev/null + +ip netns exec ns6 nc -l -6 -u -d 7330 > $TMP_FILE & +ip netns exec ns1 bash -c "echo 'foobar' | nc -w0 -6 -u -p 2121 -s fb00::1 fb00::6 7330" +sleep 5 # wait enough time to ensure the UDP datagram arrived to the last segment +kill -INT $! + +if [[ $(< $TMP_FILE) != "foobar" ]]; then + exit 1 +fi + +exit 0 diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 4123d0a..0ef6820 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -38,8 +38,10 @@ typedef __u16 __sum16; #include "bpf_util.h" #include "bpf_endian.h" #include "bpf_rlimit.h" +#include "trace_helpers.h" static int error_cnt, pass_cnt; +static bool jit_enabled; #define MAGIC_BYTES 123 @@ -166,6 +168,37 @@ out: bpf_object__close(obj); } +static void test_xdp_adjust_tail(void) +{ + const char *file = "./test_adjust_tail.o"; + struct bpf_object *obj; + char buf[128]; + __u32 duration, retval, size; + int err, prog_fd; + + err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); + if (err) { + error_cnt++; + return; + } + + err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), + buf, &size, &retval, &duration); + + CHECK(err || errno || retval != XDP_DROP, + "ipv4", "err %d errno %d retval %d size %d\n", + err, errno, retval, size); + + err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6), + buf, &size, &retval, &duration); + CHECK(err || errno || retval != XDP_TX || size != 54, + "ipv6", "err %d errno %d retval %d size %d\n", + err, errno, retval, size); + bpf_object__close(obj); +} + + + #define MAGIC_VAL 0x1234 #define NUM_ITER 100000 #define VIP_NUM 5 @@ -360,13 +393,30 @@ static inline __u64 ptr_to_u64(const void *ptr) return (__u64) (unsigned long) ptr; } +static bool is_jit_enabled(void) +{ + const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable"; + bool enabled = false; + int sysctl_fd; + + sysctl_fd = open(jit_sysctl, 0, O_RDONLY); + if (sysctl_fd != -1) { + char tmpc; + + if (read(sysctl_fd, &tmpc, sizeof(tmpc)) == 1) + enabled = (tmpc != '0'); + close(sysctl_fd); + } + + return enabled; +} + static void test_bpf_obj_id(void) { const __u64 array_magic_value = 0xfaceb00c; const __u32 array_key = 0; const int nr_iters = 2; const char *file = "./test_obj_id.o"; - const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable"; const char *expected_prog_name = "test_obj_id"; const char *expected_map_name = "test_map_id"; const __u64 nsec_per_sec = 1000000000; @@ -383,20 +433,11 @@ static void test_bpf_obj_id(void) char jited_insns[128], xlated_insns[128], zeros[128]; __u32 i, next_id, info_len, nr_id_found, duration = 0; struct timespec real_time_ts, boot_time_ts; - int sysctl_fd, jit_enabled = 0, err = 0; + int err = 0; __u64 array_value; uid_t my_uid = getuid(); time_t now, load_time; - sysctl_fd = open(jit_sysctl, 0, O_RDONLY); - if (sysctl_fd != -1) { - char tmpc; - - if (read(sysctl_fd, &tmpc, sizeof(tmpc)) == 1) - jit_enabled = (tmpc != '0'); - close(sysctl_fd); - } - err = bpf_prog_get_fd_by_id(0); CHECK(err >= 0 || errno != ENOENT, "get-fd-by-notexist-prog-id", "err %d errno %d\n", err, errno); @@ -865,11 +906,47 @@ static int compare_map_keys(int map1_fd, int map2_fd) return 0; } +static int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len) +{ + __u32 key, next_key, *cur_key_p, *next_key_p; + char *val_buf1, *val_buf2; + int i, err = 0; + + val_buf1 = malloc(stack_trace_len); + val_buf2 = malloc(stack_trace_len); + cur_key_p = NULL; + next_key_p = &key; + while (bpf_map_get_next_key(smap_fd, cur_key_p, next_key_p) == 0) { + err = bpf_map_lookup_elem(smap_fd, next_key_p, val_buf1); + if (err) + goto out; + err = bpf_map_lookup_elem(amap_fd, next_key_p, val_buf2); + if (err) + goto out; + for (i = 0; i < stack_trace_len; i++) { + if (val_buf1[i] != val_buf2[i]) { + err = -1; + goto out; + } + } + key = *next_key_p; + cur_key_p = &key; + next_key_p = &next_key; + } + if (errno != ENOENT) + err = -1; + +out: + free(val_buf1); + free(val_buf2); + return err; +} + static void test_stacktrace_map() { - int control_map_fd, stackid_hmap_fd, stackmap_fd; + int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd; const char *file = "./test_stacktrace_map.o"; - int bytes, efd, err, pmu_fd, prog_fd; + int bytes, efd, err, pmu_fd, prog_fd, stack_trace_len; struct perf_event_attr attr = {}; __u32 key, val, duration = 0; struct bpf_object *obj; @@ -925,6 +1002,10 @@ static void test_stacktrace_map() if (stackmap_fd < 0) goto disable_pmu; + stack_amap_fd = bpf_find_map(__func__, obj, "stack_amap"); + if (stack_amap_fd < 0) + goto disable_pmu; + /* give some time for bpf program run */ sleep(1); @@ -946,6 +1027,12 @@ static void test_stacktrace_map() "err %d errno %d\n", err, errno)) goto disable_pmu_noerr; + stack_trace_len = PERF_MAX_STACK_DEPTH * sizeof(__u64); + err = compare_stack_ips(stackmap_fd, stack_amap_fd, stack_trace_len); + if (CHECK(err, "compare_stack_ips stackmap vs. stack_amap", + "err %d errno %d\n", err, errno)) + goto disable_pmu_noerr; + goto disable_pmu_noerr; disable_pmu: error_cnt++; @@ -1039,9 +1126,9 @@ err: static void test_stacktrace_build_id(void) { - int control_map_fd, stackid_hmap_fd, stackmap_fd; + int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd; const char *file = "./test_stacktrace_build_id.o"; - int bytes, efd, err, pmu_fd, prog_fd; + int bytes, efd, err, pmu_fd, prog_fd, stack_trace_len; struct perf_event_attr attr = {}; __u32 key, previous_key, val, duration = 0; struct bpf_object *obj; @@ -1106,6 +1193,11 @@ static void test_stacktrace_build_id(void) err, errno)) goto disable_pmu; + stack_amap_fd = bpf_find_map(__func__, obj, "stack_amap"); + if (CHECK(stack_amap_fd < 0, "bpf_find_map stack_amap", + "err %d errno %d\n", err, errno)) + goto disable_pmu; + assert(system("dd if=/dev/urandom of=/dev/zero count=4 2> /dev/null") == 0); assert(system("./urandom_read") == 0); @@ -1157,8 +1249,15 @@ static void test_stacktrace_build_id(void) previous_key = key; } while (bpf_map_get_next_key(stackmap_fd, &previous_key, &key) == 0); - CHECK(build_id_matches < 1, "build id match", - "Didn't find expected build ID from the map\n"); + if (CHECK(build_id_matches < 1, "build id match", + "Didn't find expected build ID from the map\n")) + goto disable_pmu; + + stack_trace_len = PERF_MAX_STACK_DEPTH + * sizeof(struct bpf_stack_build_id); + err = compare_stack_ips(stackmap_fd, stack_amap_fd, stack_trace_len); + CHECK(err, "compare_stack_ips stackmap vs. stack_amap", + "err %d errno %d\n", err, errno); disable_pmu: ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE); @@ -1173,10 +1272,439 @@ out: return; } +static void test_stacktrace_build_id_nmi(void) +{ + int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd; + const char *file = "./test_stacktrace_build_id.o"; + int err, pmu_fd, prog_fd; + struct perf_event_attr attr = { + .sample_freq = 5000, + .freq = 1, + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + }; + __u32 key, previous_key, val, duration = 0; + struct bpf_object *obj; + char buf[256]; + int i, j; + struct bpf_stack_build_id id_offs[PERF_MAX_STACK_DEPTH]; + int build_id_matches = 0; + + err = bpf_prog_load(file, BPF_PROG_TYPE_PERF_EVENT, &obj, &prog_fd); + if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno)) + return; + + pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */, + 0 /* cpu 0 */, -1 /* group id */, + 0 /* flags */); + if (CHECK(pmu_fd < 0, "perf_event_open", + "err %d errno %d. Does the test host support PERF_COUNT_HW_CPU_CYCLES?\n", + pmu_fd, errno)) + goto close_prog; + + err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0); + if (CHECK(err, "perf_event_ioc_enable", "err %d errno %d\n", + err, errno)) + goto close_pmu; + + err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd); + if (CHECK(err, "perf_event_ioc_set_bpf", "err %d errno %d\n", + err, errno)) + goto disable_pmu; + + /* find map fds */ + control_map_fd = bpf_find_map(__func__, obj, "control_map"); + if (CHECK(control_map_fd < 0, "bpf_find_map control_map", + "err %d errno %d\n", err, errno)) + goto disable_pmu; + + stackid_hmap_fd = bpf_find_map(__func__, obj, "stackid_hmap"); + if (CHECK(stackid_hmap_fd < 0, "bpf_find_map stackid_hmap", + "err %d errno %d\n", err, errno)) + goto disable_pmu; + + stackmap_fd = bpf_find_map(__func__, obj, "stackmap"); + if (CHECK(stackmap_fd < 0, "bpf_find_map stackmap", "err %d errno %d\n", + err, errno)) + goto disable_pmu; + + stack_amap_fd = bpf_find_map(__func__, obj, "stack_amap"); + if (CHECK(stack_amap_fd < 0, "bpf_find_map stack_amap", + "err %d errno %d\n", err, errno)) + goto disable_pmu; + + assert(system("dd if=/dev/urandom of=/dev/zero count=4 2> /dev/null") + == 0); + assert(system("taskset 0x1 ./urandom_read 100000") == 0); + /* disable stack trace collection */ + key = 0; + val = 1; + bpf_map_update_elem(control_map_fd, &key, &val, 0); + + /* for every element in stackid_hmap, we can find a corresponding one + * in stackmap, and vise versa. + */ + err = compare_map_keys(stackid_hmap_fd, stackmap_fd); + if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap", + "err %d errno %d\n", err, errno)) + goto disable_pmu; + + err = compare_map_keys(stackmap_fd, stackid_hmap_fd); + if (CHECK(err, "compare_map_keys stackmap vs. stackid_hmap", + "err %d errno %d\n", err, errno)) + goto disable_pmu; + + err = extract_build_id(buf, 256); + + if (CHECK(err, "get build_id with readelf", + "err %d errno %d\n", err, errno)) + goto disable_pmu; + + err = bpf_map_get_next_key(stackmap_fd, NULL, &key); + if (CHECK(err, "get_next_key from stackmap", + "err %d, errno %d\n", err, errno)) + goto disable_pmu; + + do { + char build_id[64]; + + err = bpf_map_lookup_elem(stackmap_fd, &key, id_offs); + if (CHECK(err, "lookup_elem from stackmap", + "err %d, errno %d\n", err, errno)) + goto disable_pmu; + for (i = 0; i < PERF_MAX_STACK_DEPTH; ++i) + if (id_offs[i].status == BPF_STACK_BUILD_ID_VALID && + id_offs[i].offset != 0) { + for (j = 0; j < 20; ++j) + sprintf(build_id + 2 * j, "%02x", + id_offs[i].build_id[j] & 0xff); + if (strstr(buf, build_id) != NULL) + build_id_matches = 1; + } + previous_key = key; + } while (bpf_map_get_next_key(stackmap_fd, &previous_key, &key) == 0); + + if (CHECK(build_id_matches < 1, "build id match", + "Didn't find expected build ID from the map\n")) + goto disable_pmu; + + /* + * We intentionally skip compare_stack_ips(). This is because we + * only support one in_nmi() ips-to-build_id translation per cpu + * at any time, thus stack_amap here will always fallback to + * BPF_STACK_BUILD_ID_IP; + */ + +disable_pmu: + ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE); + +close_pmu: + close(pmu_fd); + +close_prog: + bpf_object__close(obj); +} + +#define MAX_CNT_RAWTP 10ull +#define MAX_STACK_RAWTP 100 +struct get_stack_trace_t { + int pid; + int kern_stack_size; + int user_stack_size; + int user_stack_buildid_size; + __u64 kern_stack[MAX_STACK_RAWTP]; + __u64 user_stack[MAX_STACK_RAWTP]; + struct bpf_stack_build_id user_stack_buildid[MAX_STACK_RAWTP]; +}; + +static int get_stack_print_output(void *data, int size) +{ + bool good_kern_stack = false, good_user_stack = false; + const char *nonjit_func = "___bpf_prog_run"; + struct get_stack_trace_t *e = data; + int i, num_stack; + static __u64 cnt; + struct ksym *ks; + + cnt++; + + if (size < sizeof(struct get_stack_trace_t)) { + __u64 *raw_data = data; + bool found = false; + + num_stack = size / sizeof(__u64); + /* If jit is enabled, we do not have a good way to + * verify the sanity of the kernel stack. So we + * just assume it is good if the stack is not empty. + * This could be improved in the future. + */ + if (jit_enabled) { + found = num_stack > 0; + } else { + for (i = 0; i < num_stack; i++) { + ks = ksym_search(raw_data[i]); + if (strcmp(ks->name, nonjit_func) == 0) { + found = true; + break; + } + } + } + if (found) { + good_kern_stack = true; + good_user_stack = true; + } + } else { + num_stack = e->kern_stack_size / sizeof(__u64); + if (jit_enabled) { + good_kern_stack = num_stack > 0; + } else { + for (i = 0; i < num_stack; i++) { + ks = ksym_search(e->kern_stack[i]); + if (strcmp(ks->name, nonjit_func) == 0) { + good_kern_stack = true; + break; + } + } + } + if (e->user_stack_size > 0 && e->user_stack_buildid_size > 0) + good_user_stack = true; + } + if (!good_kern_stack || !good_user_stack) + return LIBBPF_PERF_EVENT_ERROR; + + if (cnt == MAX_CNT_RAWTP) + return LIBBPF_PERF_EVENT_DONE; + + return LIBBPF_PERF_EVENT_CONT; +} + +static void test_get_stack_raw_tp(void) +{ + const char *file = "./test_get_stack_rawtp.o"; + int i, efd, err, prog_fd, pmu_fd, perfmap_fd; + struct perf_event_attr attr = {}; + struct timespec tv = {0, 10}; + __u32 key = 0, duration = 0; + struct bpf_object *obj; + + err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd); + if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno)) + return; + + efd = bpf_raw_tracepoint_open("sys_enter", prog_fd); + if (CHECK(efd < 0, "raw_tp_open", "err %d errno %d\n", efd, errno)) + goto close_prog; + + perfmap_fd = bpf_find_map(__func__, obj, "perfmap"); + if (CHECK(perfmap_fd < 0, "bpf_find_map", "err %d errno %d\n", + perfmap_fd, errno)) + goto close_prog; + + err = load_kallsyms(); + if (CHECK(err < 0, "load_kallsyms", "err %d errno %d\n", err, errno)) + goto close_prog; + + attr.sample_type = PERF_SAMPLE_RAW; + attr.type = PERF_TYPE_SOFTWARE; + attr.config = PERF_COUNT_SW_BPF_OUTPUT; + pmu_fd = syscall(__NR_perf_event_open, &attr, getpid()/*pid*/, -1/*cpu*/, + -1/*group_fd*/, 0); + if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n", pmu_fd, + errno)) + goto close_prog; + + err = bpf_map_update_elem(perfmap_fd, &key, &pmu_fd, BPF_ANY); + if (CHECK(err < 0, "bpf_map_update_elem", "err %d errno %d\n", err, + errno)) + goto close_prog; + + err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0); + if (CHECK(err < 0, "ioctl PERF_EVENT_IOC_ENABLE", "err %d errno %d\n", + err, errno)) + goto close_prog; + + err = perf_event_mmap(pmu_fd); + if (CHECK(err < 0, "perf_event_mmap", "err %d errno %d\n", err, errno)) + goto close_prog; + + /* trigger some syscall action */ + for (i = 0; i < MAX_CNT_RAWTP; i++) + nanosleep(&tv, NULL); + + err = perf_event_poller(pmu_fd, get_stack_print_output); + if (CHECK(err < 0, "perf_event_poller", "err %d errno %d\n", err, errno)) + goto close_prog; + + goto close_prog_noerr; +close_prog: + error_cnt++; +close_prog_noerr: + bpf_object__close(obj); +} + +static void test_task_fd_query_rawtp(void) +{ + const char *file = "./test_get_stack_rawtp.o"; + __u64 probe_offset, probe_addr; + __u32 len, prog_id, fd_type; + struct bpf_object *obj; + int efd, err, prog_fd; + __u32 duration = 0; + char buf[256]; + + err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd); + if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno)) + return; + + efd = bpf_raw_tracepoint_open("sys_enter", prog_fd); + if (CHECK(efd < 0, "raw_tp_open", "err %d errno %d\n", efd, errno)) + goto close_prog; + + /* query (getpid(), efd) */ + len = sizeof(buf); + err = bpf_task_fd_query(getpid(), efd, 0, buf, &len, &prog_id, + &fd_type, &probe_offset, &probe_addr); + if (CHECK(err < 0, "bpf_task_fd_query", "err %d errno %d\n", err, + errno)) + goto close_prog; + + err = fd_type == BPF_FD_TYPE_RAW_TRACEPOINT && + strcmp(buf, "sys_enter") == 0; + if (CHECK(!err, "check_results", "fd_type %d tp_name %s\n", + fd_type, buf)) + goto close_prog; + + /* test zero len */ + len = 0; + err = bpf_task_fd_query(getpid(), efd, 0, buf, &len, &prog_id, + &fd_type, &probe_offset, &probe_addr); + if (CHECK(err < 0, "bpf_task_fd_query (len = 0)", "err %d errno %d\n", + err, errno)) + goto close_prog; + err = fd_type == BPF_FD_TYPE_RAW_TRACEPOINT && + len == strlen("sys_enter"); + if (CHECK(!err, "check_results", "fd_type %d len %u\n", fd_type, len)) + goto close_prog; + + /* test empty buffer */ + len = sizeof(buf); + err = bpf_task_fd_query(getpid(), efd, 0, 0, &len, &prog_id, + &fd_type, &probe_offset, &probe_addr); + if (CHECK(err < 0, "bpf_task_fd_query (buf = 0)", "err %d errno %d\n", + err, errno)) + goto close_prog; + err = fd_type == BPF_FD_TYPE_RAW_TRACEPOINT && + len == strlen("sys_enter"); + if (CHECK(!err, "check_results", "fd_type %d len %u\n", fd_type, len)) + goto close_prog; + + /* test smaller buffer */ + len = 3; + err = bpf_task_fd_query(getpid(), efd, 0, buf, &len, &prog_id, + &fd_type, &probe_offset, &probe_addr); + if (CHECK(err >= 0 || errno != ENOSPC, "bpf_task_fd_query (len = 3)", + "err %d errno %d\n", err, errno)) + goto close_prog; + err = fd_type == BPF_FD_TYPE_RAW_TRACEPOINT && + len == strlen("sys_enter") && + strcmp(buf, "sy") == 0; + if (CHECK(!err, "check_results", "fd_type %d len %u\n", fd_type, len)) + goto close_prog; + + goto close_prog_noerr; +close_prog: + error_cnt++; +close_prog_noerr: + bpf_object__close(obj); +} + +static void test_task_fd_query_tp_core(const char *probe_name, + const char *tp_name) +{ + const char *file = "./test_tracepoint.o"; + int err, bytes, efd, prog_fd, pmu_fd; + struct perf_event_attr attr = {}; + __u64 probe_offset, probe_addr; + __u32 len, prog_id, fd_type; + struct bpf_object *obj; + __u32 duration = 0; + char buf[256]; + + err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd); + if (CHECK(err, "bpf_prog_load", "err %d errno %d\n", err, errno)) + goto close_prog; + + snprintf(buf, sizeof(buf), + "/sys/kernel/debug/tracing/events/%s/id", probe_name); + efd = open(buf, O_RDONLY, 0); + if (CHECK(efd < 0, "open", "err %d errno %d\n", efd, errno)) + goto close_prog; + bytes = read(efd, buf, sizeof(buf)); + close(efd); + if (CHECK(bytes <= 0 || bytes >= sizeof(buf), "read", + "bytes %d errno %d\n", bytes, errno)) + goto close_prog; + + attr.config = strtol(buf, NULL, 0); + attr.type = PERF_TYPE_TRACEPOINT; + attr.sample_type = PERF_SAMPLE_RAW; + attr.sample_period = 1; + attr.wakeup_events = 1; + pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */, + 0 /* cpu 0 */, -1 /* group id */, + 0 /* flags */); + if (CHECK(err, "perf_event_open", "err %d errno %d\n", err, errno)) + goto close_pmu; + + err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0); + if (CHECK(err, "perf_event_ioc_enable", "err %d errno %d\n", err, + errno)) + goto close_pmu; + + err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd); + if (CHECK(err, "perf_event_ioc_set_bpf", "err %d errno %d\n", err, + errno)) + goto close_pmu; + + /* query (getpid(), pmu_fd) */ + len = sizeof(buf); + err = bpf_task_fd_query(getpid(), pmu_fd, 0, buf, &len, &prog_id, + &fd_type, &probe_offset, &probe_addr); + if (CHECK(err < 0, "bpf_task_fd_query", "err %d errno %d\n", err, + errno)) + goto close_pmu; + + err = (fd_type == BPF_FD_TYPE_TRACEPOINT) && !strcmp(buf, tp_name); + if (CHECK(!err, "check_results", "fd_type %d tp_name %s\n", + fd_type, buf)) + goto close_pmu; + + close(pmu_fd); + goto close_prog_noerr; + +close_pmu: + close(pmu_fd); +close_prog: + error_cnt++; +close_prog_noerr: + bpf_object__close(obj); +} + +static void test_task_fd_query_tp(void) +{ + test_task_fd_query_tp_core("sched/sched_switch", + "sched_switch"); + test_task_fd_query_tp_core("syscalls/sys_enter_read", + "sys_enter_read"); +} + int main(void) { + jit_enabled = is_jit_enabled(); + test_pkt_access(); test_xdp(); + test_xdp_adjust_tail(); test_l4lb_all(); test_xdp_noinline(); test_tcp_estats(); @@ -1186,7 +1714,11 @@ int main(void) test_tp_attach_query(); test_stacktrace_map(); test_stacktrace_build_id(); + test_stacktrace_build_id_nmi(); test_stacktrace_map_raw_tp(); + test_get_stack_raw_tp(); + test_task_fd_query_rawtp(); + test_task_fd_query_tp(); printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt); return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS; diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c index 2950f80..a5e76b9 100644 --- a/tools/testing/selftests/bpf/test_sock_addr.c +++ b/tools/testing/selftests/bpf/test_sock_addr.c @@ -1,12 +1,16 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2018 Facebook +#define _GNU_SOURCE + #include <stdio.h> #include <stdlib.h> #include <unistd.h> #include <arpa/inet.h> +#include <netinet/in.h> #include <sys/types.h> +#include <sys/select.h> #include <sys/socket.h> #include <linux/filter.h> @@ -17,34 +21,465 @@ #include "cgroup_helpers.h" #include "bpf_rlimit.h" +#ifndef ENOTSUPP +# define ENOTSUPP 524 +#endif + +#ifndef ARRAY_SIZE +# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + #define CG_PATH "/foo" #define CONNECT4_PROG_PATH "./connect4_prog.o" #define CONNECT6_PROG_PATH "./connect6_prog.o" +#define SENDMSG4_PROG_PATH "./sendmsg4_prog.o" +#define SENDMSG6_PROG_PATH "./sendmsg6_prog.o" #define SERV4_IP "192.168.1.254" #define SERV4_REWRITE_IP "127.0.0.1" +#define SRC4_IP "172.16.0.1" +#define SRC4_REWRITE_IP "127.0.0.4" #define SERV4_PORT 4040 #define SERV4_REWRITE_PORT 4444 #define SERV6_IP "face:b00c:1234:5678::abcd" #define SERV6_REWRITE_IP "::1" +#define SERV6_V4MAPPED_IP "::ffff:192.168.0.4" +#define SRC6_IP "::1" +#define SRC6_REWRITE_IP "::6" #define SERV6_PORT 6060 #define SERV6_REWRITE_PORT 6666 #define INET_NTOP_BUF 40 -typedef int (*load_fn)(enum bpf_attach_type, const char *comment); +struct sock_addr_test; + +typedef int (*load_fn)(const struct sock_addr_test *test); typedef int (*info_fn)(int, struct sockaddr *, socklen_t *); -struct program { - enum bpf_attach_type type; - load_fn loadfn; - int fd; - const char *name; - enum bpf_attach_type invalid_type; +char bpf_log_buf[BPF_LOG_BUF_SIZE]; + +struct sock_addr_test { + const char *descr; + /* BPF prog properties */ + load_fn loadfn; + enum bpf_attach_type expected_attach_type; + enum bpf_attach_type attach_type; + /* Socket properties */ + int domain; + int type; + /* IP:port pairs for BPF prog to override */ + const char *requested_ip; + unsigned short requested_port; + const char *expected_ip; + unsigned short expected_port; + const char *expected_src_ip; + /* Expected test result */ + enum { + LOAD_REJECT, + ATTACH_REJECT, + SYSCALL_EPERM, + SYSCALL_ENOTSUPP, + SUCCESS, + } expected_result; }; -char bpf_log_buf[BPF_LOG_BUF_SIZE]; +static int bind4_prog_load(const struct sock_addr_test *test); +static int bind6_prog_load(const struct sock_addr_test *test); +static int connect4_prog_load(const struct sock_addr_test *test); +static int connect6_prog_load(const struct sock_addr_test *test); +static int sendmsg_deny_prog_load(const struct sock_addr_test *test); +static int sendmsg4_rw_asm_prog_load(const struct sock_addr_test *test); +static int sendmsg4_rw_c_prog_load(const struct sock_addr_test *test); +static int sendmsg6_rw_asm_prog_load(const struct sock_addr_test *test); +static int sendmsg6_rw_c_prog_load(const struct sock_addr_test *test); +static int sendmsg6_rw_v4mapped_prog_load(const struct sock_addr_test *test); + +static struct sock_addr_test tests[] = { + /* bind */ + { + "bind4: load prog with wrong expected attach type", + bind4_prog_load, + BPF_CGROUP_INET6_BIND, + BPF_CGROUP_INET4_BIND, + AF_INET, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + LOAD_REJECT, + }, + { + "bind4: attach prog with wrong attach type", + bind4_prog_load, + BPF_CGROUP_INET4_BIND, + BPF_CGROUP_INET6_BIND, + AF_INET, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + ATTACH_REJECT, + }, + { + "bind4: rewrite IP & TCP port in", + bind4_prog_load, + BPF_CGROUP_INET4_BIND, + BPF_CGROUP_INET4_BIND, + AF_INET, + SOCK_STREAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + NULL, + SUCCESS, + }, + { + "bind4: rewrite IP & UDP port in", + bind4_prog_load, + BPF_CGROUP_INET4_BIND, + BPF_CGROUP_INET4_BIND, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + NULL, + SUCCESS, + }, + { + "bind6: load prog with wrong expected attach type", + bind6_prog_load, + BPF_CGROUP_INET4_BIND, + BPF_CGROUP_INET6_BIND, + AF_INET6, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + LOAD_REJECT, + }, + { + "bind6: attach prog with wrong attach type", + bind6_prog_load, + BPF_CGROUP_INET6_BIND, + BPF_CGROUP_INET4_BIND, + AF_INET, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + ATTACH_REJECT, + }, + { + "bind6: rewrite IP & TCP port in", + bind6_prog_load, + BPF_CGROUP_INET6_BIND, + BPF_CGROUP_INET6_BIND, + AF_INET6, + SOCK_STREAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + NULL, + SUCCESS, + }, + { + "bind6: rewrite IP & UDP port in", + bind6_prog_load, + BPF_CGROUP_INET6_BIND, + BPF_CGROUP_INET6_BIND, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + NULL, + SUCCESS, + }, + + /* connect */ + { + "connect4: load prog with wrong expected attach type", + connect4_prog_load, + BPF_CGROUP_INET6_CONNECT, + BPF_CGROUP_INET4_CONNECT, + AF_INET, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + LOAD_REJECT, + }, + { + "connect4: attach prog with wrong attach type", + connect4_prog_load, + BPF_CGROUP_INET4_CONNECT, + BPF_CGROUP_INET6_CONNECT, + AF_INET, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + ATTACH_REJECT, + }, + { + "connect4: rewrite IP & TCP port", + connect4_prog_load, + BPF_CGROUP_INET4_CONNECT, + BPF_CGROUP_INET4_CONNECT, + AF_INET, + SOCK_STREAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SUCCESS, + }, + { + "connect4: rewrite IP & UDP port", + connect4_prog_load, + BPF_CGROUP_INET4_CONNECT, + BPF_CGROUP_INET4_CONNECT, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SUCCESS, + }, + { + "connect6: load prog with wrong expected attach type", + connect6_prog_load, + BPF_CGROUP_INET4_CONNECT, + BPF_CGROUP_INET6_CONNECT, + AF_INET6, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + LOAD_REJECT, + }, + { + "connect6: attach prog with wrong attach type", + connect6_prog_load, + BPF_CGROUP_INET6_CONNECT, + BPF_CGROUP_INET4_CONNECT, + AF_INET, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + ATTACH_REJECT, + }, + { + "connect6: rewrite IP & TCP port", + connect6_prog_load, + BPF_CGROUP_INET6_CONNECT, + BPF_CGROUP_INET6_CONNECT, + AF_INET6, + SOCK_STREAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SUCCESS, + }, + { + "connect6: rewrite IP & UDP port", + connect6_prog_load, + BPF_CGROUP_INET6_CONNECT, + BPF_CGROUP_INET6_CONNECT, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SUCCESS, + }, + + /* sendmsg */ + { + "sendmsg4: load prog with wrong expected attach type", + sendmsg4_rw_asm_prog_load, + BPF_CGROUP_UDP6_SENDMSG, + BPF_CGROUP_UDP4_SENDMSG, + AF_INET, + SOCK_DGRAM, + NULL, + 0, + NULL, + 0, + NULL, + LOAD_REJECT, + }, + { + "sendmsg4: attach prog with wrong attach type", + sendmsg4_rw_asm_prog_load, + BPF_CGROUP_UDP4_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + AF_INET, + SOCK_DGRAM, + NULL, + 0, + NULL, + 0, + NULL, + ATTACH_REJECT, + }, + { + "sendmsg4: rewrite IP & port (asm)", + sendmsg4_rw_asm_prog_load, + BPF_CGROUP_UDP4_SENDMSG, + BPF_CGROUP_UDP4_SENDMSG, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SUCCESS, + }, + { + "sendmsg4: rewrite IP & port (C)", + sendmsg4_rw_c_prog_load, + BPF_CGROUP_UDP4_SENDMSG, + BPF_CGROUP_UDP4_SENDMSG, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SUCCESS, + }, + { + "sendmsg4: deny call", + sendmsg_deny_prog_load, + BPF_CGROUP_UDP4_SENDMSG, + BPF_CGROUP_UDP4_SENDMSG, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SYSCALL_EPERM, + }, + { + "sendmsg6: load prog with wrong expected attach type", + sendmsg6_rw_asm_prog_load, + BPF_CGROUP_UDP4_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + AF_INET6, + SOCK_DGRAM, + NULL, + 0, + NULL, + 0, + NULL, + LOAD_REJECT, + }, + { + "sendmsg6: attach prog with wrong attach type", + sendmsg6_rw_asm_prog_load, + BPF_CGROUP_UDP6_SENDMSG, + BPF_CGROUP_UDP4_SENDMSG, + AF_INET6, + SOCK_DGRAM, + NULL, + 0, + NULL, + 0, + NULL, + ATTACH_REJECT, + }, + { + "sendmsg6: rewrite IP & port (asm)", + sendmsg6_rw_asm_prog_load, + BPF_CGROUP_UDP6_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SUCCESS, + }, + { + "sendmsg6: rewrite IP & port (C)", + sendmsg6_rw_c_prog_load, + BPF_CGROUP_UDP6_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SUCCESS, + }, + { + "sendmsg6: IPv4-mapped IPv6", + sendmsg6_rw_v4mapped_prog_load, + BPF_CGROUP_UDP6_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SYSCALL_ENOTSUPP, + }, + { + "sendmsg6: deny call", + sendmsg_deny_prog_load, + BPF_CGROUP_UDP6_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SYSCALL_EPERM, + }, +}; static int mk_sockaddr(int domain, const char *ip, unsigned short port, struct sockaddr *addr, socklen_t addr_len) @@ -84,25 +519,23 @@ static int mk_sockaddr(int domain, const char *ip, unsigned short port, return 0; } -static int load_insns(enum bpf_attach_type attach_type, - const struct bpf_insn *insns, size_t insns_cnt, - const char *comment) +static int load_insns(const struct sock_addr_test *test, + const struct bpf_insn *insns, size_t insns_cnt) { struct bpf_load_program_attr load_attr; int ret; memset(&load_attr, 0, sizeof(struct bpf_load_program_attr)); load_attr.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR; - load_attr.expected_attach_type = attach_type; + load_attr.expected_attach_type = test->expected_attach_type; load_attr.insns = insns; load_attr.insns_cnt = insns_cnt; load_attr.license = "GPL"; ret = bpf_load_program_xattr(&load_attr, bpf_log_buf, BPF_LOG_BUF_SIZE); - if (ret < 0 && comment) { - log_err(">>> Loading %s program error.\n" - ">>> Output from verifier:\n%s\n-------\n", - comment, bpf_log_buf); + if (ret < 0 && test->expected_result != LOAD_REJECT) { + log_err(">>> Loading program error.\n" + ">>> Verifier output:\n%s\n-------\n", bpf_log_buf); } return ret; @@ -119,8 +552,7 @@ static int load_insns(enum bpf_attach_type attach_type, * to count jumps properly. */ -static int bind4_prog_load(enum bpf_attach_type attach_type, - const char *comment) +static int bind4_prog_load(const struct sock_addr_test *test) { union { uint8_t u4_addr8[4]; @@ -186,12 +618,10 @@ static int bind4_prog_load(enum bpf_attach_type attach_type, BPF_EXIT_INSN(), }; - return load_insns(attach_type, insns, - sizeof(insns) / sizeof(struct bpf_insn), comment); + return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn)); } -static int bind6_prog_load(enum bpf_attach_type attach_type, - const char *comment) +static int bind6_prog_load(const struct sock_addr_test *test) { struct sockaddr_in6 addr6_rw; struct in6_addr ip6; @@ -254,13 +684,10 @@ static int bind6_prog_load(enum bpf_attach_type attach_type, BPF_EXIT_INSN(), }; - return load_insns(attach_type, insns, - sizeof(insns) / sizeof(struct bpf_insn), comment); + return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn)); } -static int connect_prog_load_path(const char *path, - enum bpf_attach_type attach_type, - const char *comment) +static int load_path(const struct sock_addr_test *test, const char *path) { struct bpf_prog_load_attr attr; struct bpf_object *obj; @@ -269,75 +696,218 @@ static int connect_prog_load_path(const char *path, memset(&attr, 0, sizeof(struct bpf_prog_load_attr)); attr.file = path; attr.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR; - attr.expected_attach_type = attach_type; + attr.expected_attach_type = test->expected_attach_type; if (bpf_prog_load_xattr(&attr, &obj, &prog_fd)) { - if (comment) - log_err(">>> Loading %s program at %s error.\n", - comment, path); + if (test->expected_result != LOAD_REJECT) + log_err(">>> Loading program (%s) error.\n", path); return -1; } return prog_fd; } -static int connect4_prog_load(enum bpf_attach_type attach_type, - const char *comment) +static int connect4_prog_load(const struct sock_addr_test *test) { - return connect_prog_load_path(CONNECT4_PROG_PATH, attach_type, comment); + return load_path(test, CONNECT4_PROG_PATH); } -static int connect6_prog_load(enum bpf_attach_type attach_type, - const char *comment) +static int connect6_prog_load(const struct sock_addr_test *test) { - return connect_prog_load_path(CONNECT6_PROG_PATH, attach_type, comment); + return load_path(test, CONNECT6_PROG_PATH); } -static void print_ip_port(int sockfd, info_fn fn, const char *fmt) +static int sendmsg_deny_prog_load(const struct sock_addr_test *test) { - char addr_buf[INET_NTOP_BUF]; - struct sockaddr_storage addr; - struct sockaddr_in6 *addr6; - struct sockaddr_in *addr4; - socklen_t addr_len; - unsigned short port; - void *nip; - - addr_len = sizeof(struct sockaddr_storage); - memset(&addr, 0, addr_len); - - if (fn(sockfd, (struct sockaddr *)&addr, (socklen_t *)&addr_len) == 0) { - if (addr.ss_family == AF_INET) { - addr4 = (struct sockaddr_in *)&addr; - nip = (void *)&addr4->sin_addr; - port = ntohs(addr4->sin_port); - } else if (addr.ss_family == AF_INET6) { - addr6 = (struct sockaddr_in6 *)&addr; - nip = (void *)&addr6->sin6_addr; - port = ntohs(addr6->sin6_port); - } else { - return; - } - const char *addr_str = - inet_ntop(addr.ss_family, nip, addr_buf, INET_NTOP_BUF); - printf(fmt, addr_str ? addr_str : "??", port); + struct bpf_insn insns[] = { + /* return 0 */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn)); +} + +static int sendmsg4_rw_asm_prog_load(const struct sock_addr_test *test) +{ + struct sockaddr_in dst4_rw_addr; + struct in_addr src4_rw_ip; + + if (inet_pton(AF_INET, SRC4_REWRITE_IP, (void *)&src4_rw_ip) != 1) { + log_err("Invalid IPv4: %s", SRC4_REWRITE_IP); + return -1; + } + + if (mk_sockaddr(AF_INET, SERV4_REWRITE_IP, SERV4_REWRITE_PORT, + (struct sockaddr *)&dst4_rw_addr, + sizeof(dst4_rw_addr)) == -1) + return -1; + + struct bpf_insn insns[] = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + + /* if (sk.family == AF_INET && */ + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, + offsetof(struct bpf_sock_addr, family)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET, 8), + + /* sk.type == SOCK_DGRAM) { */ + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, + offsetof(struct bpf_sock_addr, type)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_DGRAM, 6), + + /* msg_src_ip4 = src4_rw_ip */ + BPF_MOV32_IMM(BPF_REG_7, src4_rw_ip.s_addr), + BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7, + offsetof(struct bpf_sock_addr, msg_src_ip4)), + + /* user_ip4 = dst4_rw_addr.sin_addr */ + BPF_MOV32_IMM(BPF_REG_7, dst4_rw_addr.sin_addr.s_addr), + BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7, + offsetof(struct bpf_sock_addr, user_ip4)), + + /* user_port = dst4_rw_addr.sin_port */ + BPF_MOV32_IMM(BPF_REG_7, dst4_rw_addr.sin_port), + BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7, + offsetof(struct bpf_sock_addr, user_port)), + /* } */ + + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }; + + return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn)); +} + +static int sendmsg4_rw_c_prog_load(const struct sock_addr_test *test) +{ + return load_path(test, SENDMSG4_PROG_PATH); +} + +static int sendmsg6_rw_dst_asm_prog_load(const struct sock_addr_test *test, + const char *rw_dst_ip) +{ + struct sockaddr_in6 dst6_rw_addr; + struct in6_addr src6_rw_ip; + + if (inet_pton(AF_INET6, SRC6_REWRITE_IP, (void *)&src6_rw_ip) != 1) { + log_err("Invalid IPv6: %s", SRC6_REWRITE_IP); + return -1; + } + + if (mk_sockaddr(AF_INET6, rw_dst_ip, SERV6_REWRITE_PORT, + (struct sockaddr *)&dst6_rw_addr, + sizeof(dst6_rw_addr)) == -1) + return -1; + + struct bpf_insn insns[] = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + + /* if (sk.family == AF_INET6) { */ + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, + offsetof(struct bpf_sock_addr, family)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET6, 18), + +#define STORE_IPV6_WORD_N(DST, SRC, N) \ + BPF_MOV32_IMM(BPF_REG_7, SRC[N]), \ + BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7, \ + offsetof(struct bpf_sock_addr, DST[N])) + +#define STORE_IPV6(DST, SRC) \ + STORE_IPV6_WORD_N(DST, SRC, 0), \ + STORE_IPV6_WORD_N(DST, SRC, 1), \ + STORE_IPV6_WORD_N(DST, SRC, 2), \ + STORE_IPV6_WORD_N(DST, SRC, 3) + + STORE_IPV6(msg_src_ip6, src6_rw_ip.s6_addr32), + STORE_IPV6(user_ip6, dst6_rw_addr.sin6_addr.s6_addr32), + + /* user_port = dst6_rw_addr.sin6_port */ + BPF_MOV32_IMM(BPF_REG_7, dst6_rw_addr.sin6_port), + BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7, + offsetof(struct bpf_sock_addr, user_port)), + + /* } */ + + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }; + + return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn)); +} + +static int sendmsg6_rw_asm_prog_load(const struct sock_addr_test *test) +{ + return sendmsg6_rw_dst_asm_prog_load(test, SERV6_REWRITE_IP); +} + +static int sendmsg6_rw_v4mapped_prog_load(const struct sock_addr_test *test) +{ + return sendmsg6_rw_dst_asm_prog_load(test, SERV6_V4MAPPED_IP); +} + +static int sendmsg6_rw_c_prog_load(const struct sock_addr_test *test) +{ + return load_path(test, SENDMSG6_PROG_PATH); +} + +static int cmp_addr(const struct sockaddr_storage *addr1, + const struct sockaddr_storage *addr2, int cmp_port) +{ + const struct sockaddr_in *four1, *four2; + const struct sockaddr_in6 *six1, *six2; + + if (addr1->ss_family != addr2->ss_family) + return -1; + + if (addr1->ss_family == AF_INET) { + four1 = (const struct sockaddr_in *)addr1; + four2 = (const struct sockaddr_in *)addr2; + return !((four1->sin_port == four2->sin_port || !cmp_port) && + four1->sin_addr.s_addr == four2->sin_addr.s_addr); + } else if (addr1->ss_family == AF_INET6) { + six1 = (const struct sockaddr_in6 *)addr1; + six2 = (const struct sockaddr_in6 *)addr2; + return !((six1->sin6_port == six2->sin6_port || !cmp_port) && + !memcmp(&six1->sin6_addr, &six2->sin6_addr, + sizeof(struct in6_addr))); } + + return -1; } -static void print_local_ip_port(int sockfd, const char *fmt) +static int cmp_sock_addr(info_fn fn, int sock1, + const struct sockaddr_storage *addr2, int cmp_port) { - print_ip_port(sockfd, getsockname, fmt); + struct sockaddr_storage addr1; + socklen_t len1 = sizeof(addr1); + + memset(&addr1, 0, len1); + if (fn(sock1, (struct sockaddr *)&addr1, (socklen_t *)&len1) != 0) + return -1; + + return cmp_addr(&addr1, addr2, cmp_port); +} + +static int cmp_local_ip(int sock1, const struct sockaddr_storage *addr2) +{ + return cmp_sock_addr(getsockname, sock1, addr2, /*cmp_port*/ 0); } -static void print_remote_ip_port(int sockfd, const char *fmt) +static int cmp_local_addr(int sock1, const struct sockaddr_storage *addr2) { - print_ip_port(sockfd, getpeername, fmt); + return cmp_sock_addr(getsockname, sock1, addr2, /*cmp_port*/ 1); +} + +static int cmp_peer_addr(int sock1, const struct sockaddr_storage *addr2) +{ + return cmp_sock_addr(getpeername, sock1, addr2, /*cmp_port*/ 1); } static int start_server(int type, const struct sockaddr_storage *addr, socklen_t addr_len) { - int fd; fd = socket(addr->ss_family, type, 0); @@ -358,8 +928,6 @@ static int start_server(int type, const struct sockaddr_storage *addr, } } - print_local_ip_port(fd, "\t Actual: bind(%s, %d)\n"); - goto out; close_out: close(fd); @@ -372,19 +940,19 @@ static int connect_to_server(int type, const struct sockaddr_storage *addr, socklen_t addr_len) { int domain; - int fd; + int fd = -1; domain = addr->ss_family; if (domain != AF_INET && domain != AF_INET6) { log_err("Unsupported address family"); - return -1; + goto err; } fd = socket(domain, type, 0); if (fd == -1) { - log_err("Failed to creating client socket"); - return -1; + log_err("Failed to create client socket"); + goto err; } if (connect(fd, (const struct sockaddr *)addr, addr_len) == -1) { @@ -392,162 +960,394 @@ static int connect_to_server(int type, const struct sockaddr_storage *addr, goto err; } - print_remote_ip_port(fd, "\t Actual: connect(%s, %d)"); - print_local_ip_port(fd, " from (%s, %d)\n"); + goto out; +err: + close(fd); + fd = -1; +out: + return fd; +} + +int init_pktinfo(int domain, struct cmsghdr *cmsg) +{ + struct in6_pktinfo *pktinfo6; + struct in_pktinfo *pktinfo4; + + if (domain == AF_INET) { + cmsg->cmsg_level = SOL_IP; + cmsg->cmsg_type = IP_PKTINFO; + cmsg->cmsg_len = CMSG_LEN(sizeof(struct in_pktinfo)); + pktinfo4 = (struct in_pktinfo *)CMSG_DATA(cmsg); + memset(pktinfo4, 0, sizeof(struct in_pktinfo)); + if (inet_pton(domain, SRC4_IP, + (void *)&pktinfo4->ipi_spec_dst) != 1) + return -1; + } else if (domain == AF_INET6) { + cmsg->cmsg_level = SOL_IPV6; + cmsg->cmsg_type = IPV6_PKTINFO; + cmsg->cmsg_len = CMSG_LEN(sizeof(struct in6_pktinfo)); + pktinfo6 = (struct in6_pktinfo *)CMSG_DATA(cmsg); + memset(pktinfo6, 0, sizeof(struct in6_pktinfo)); + if (inet_pton(domain, SRC6_IP, + (void *)&pktinfo6->ipi6_addr) != 1) + return -1; + } else { + return -1; + } return 0; +} + +static int sendmsg_to_server(const struct sockaddr_storage *addr, + socklen_t addr_len, int set_cmsg, int *syscall_err) +{ + union { + char buf[CMSG_SPACE(sizeof(struct in6_pktinfo))]; + struct cmsghdr align; + } control6; + union { + char buf[CMSG_SPACE(sizeof(struct in_pktinfo))]; + struct cmsghdr align; + } control4; + struct msghdr hdr; + struct iovec iov; + char data = 'a'; + int domain; + int fd = -1; + + domain = addr->ss_family; + + if (domain != AF_INET && domain != AF_INET6) { + log_err("Unsupported address family"); + goto err; + } + + fd = socket(domain, SOCK_DGRAM, 0); + if (fd == -1) { + log_err("Failed to create client socket"); + goto err; + } + + memset(&iov, 0, sizeof(iov)); + iov.iov_base = &data; + iov.iov_len = sizeof(data); + + memset(&hdr, 0, sizeof(hdr)); + hdr.msg_name = (void *)addr; + hdr.msg_namelen = addr_len; + hdr.msg_iov = &iov; + hdr.msg_iovlen = 1; + + if (set_cmsg) { + if (domain == AF_INET) { + hdr.msg_control = &control4; + hdr.msg_controllen = sizeof(control4.buf); + } else if (domain == AF_INET6) { + hdr.msg_control = &control6; + hdr.msg_controllen = sizeof(control6.buf); + } + if (init_pktinfo(domain, CMSG_FIRSTHDR(&hdr))) { + log_err("Fail to init pktinfo"); + goto err; + } + } + + if (sendmsg(fd, &hdr, 0) != sizeof(data)) { + log_err("Fail to send message to server"); + *syscall_err = errno; + goto err; + } + + goto out; err: close(fd); - return -1; + fd = -1; +out: + return fd; } -static void print_test_case_num(int domain, int type) +static int recvmsg_from_client(int sockfd, struct sockaddr_storage *src_addr) { - static int test_num; - - printf("Test case #%d (%s/%s):\n", ++test_num, - (domain == AF_INET ? "IPv4" : - domain == AF_INET6 ? "IPv6" : - "unknown_domain"), - (type == SOCK_STREAM ? "TCP" : - type == SOCK_DGRAM ? "UDP" : - "unknown_type")); + struct timeval tv; + struct msghdr hdr; + struct iovec iov; + char data[64]; + fd_set rfds; + + FD_ZERO(&rfds); + FD_SET(sockfd, &rfds); + + tv.tv_sec = 2; + tv.tv_usec = 0; + + if (select(sockfd + 1, &rfds, NULL, NULL, &tv) <= 0 || + !FD_ISSET(sockfd, &rfds)) + return -1; + + memset(&iov, 0, sizeof(iov)); + iov.iov_base = data; + iov.iov_len = sizeof(data); + + memset(&hdr, 0, sizeof(hdr)); + hdr.msg_name = src_addr; + hdr.msg_namelen = sizeof(struct sockaddr_storage); + hdr.msg_iov = &iov; + hdr.msg_iovlen = 1; + + return recvmsg(sockfd, &hdr, 0); } -static int run_test_case(int domain, int type, const char *ip, - unsigned short port) +static int init_addrs(const struct sock_addr_test *test, + struct sockaddr_storage *requested_addr, + struct sockaddr_storage *expected_addr, + struct sockaddr_storage *expected_src_addr) { - struct sockaddr_storage addr; - socklen_t addr_len = sizeof(addr); + socklen_t addr_len = sizeof(struct sockaddr_storage); + + if (mk_sockaddr(test->domain, test->expected_ip, test->expected_port, + (struct sockaddr *)expected_addr, addr_len) == -1) + goto err; + + if (mk_sockaddr(test->domain, test->requested_ip, test->requested_port, + (struct sockaddr *)requested_addr, addr_len) == -1) + goto err; + + if (test->expected_src_ip && + mk_sockaddr(test->domain, test->expected_src_ip, 0, + (struct sockaddr *)expected_src_addr, addr_len) == -1) + goto err; + + return 0; +err: + return -1; +} + +static int run_bind_test_case(const struct sock_addr_test *test) +{ + socklen_t addr_len = sizeof(struct sockaddr_storage); + struct sockaddr_storage requested_addr; + struct sockaddr_storage expected_addr; + int clientfd = -1; int servfd = -1; int err = 0; - print_test_case_num(domain, type); - - if (mk_sockaddr(domain, ip, port, (struct sockaddr *)&addr, - addr_len) == -1) - return -1; + if (init_addrs(test, &requested_addr, &expected_addr, NULL)) + goto err; - printf("\tRequested: bind(%s, %d) ..\n", ip, port); - servfd = start_server(type, &addr, addr_len); + servfd = start_server(test->type, &requested_addr, addr_len); if (servfd == -1) goto err; - printf("\tRequested: connect(%s, %d) from (*, *) ..\n", ip, port); - if (connect_to_server(type, &addr, addr_len)) + if (cmp_local_addr(servfd, &expected_addr)) + goto err; + + /* Try to connect to server just in case */ + clientfd = connect_to_server(test->type, &expected_addr, addr_len); + if (clientfd == -1) goto err; goto out; err: err = -1; out: + close(clientfd); close(servfd); return err; } -static void close_progs_fds(struct program *progs, size_t prog_cnt) +static int run_connect_test_case(const struct sock_addr_test *test) { - size_t i; + socklen_t addr_len = sizeof(struct sockaddr_storage); + struct sockaddr_storage expected_src_addr; + struct sockaddr_storage requested_addr; + struct sockaddr_storage expected_addr; + int clientfd = -1; + int servfd = -1; + int err = 0; - for (i = 0; i < prog_cnt; ++i) { - close(progs[i].fd); - progs[i].fd = -1; - } + if (init_addrs(test, &requested_addr, &expected_addr, + &expected_src_addr)) + goto err; + + /* Prepare server to connect to */ + servfd = start_server(test->type, &expected_addr, addr_len); + if (servfd == -1) + goto err; + + clientfd = connect_to_server(test->type, &requested_addr, addr_len); + if (clientfd == -1) + goto err; + + /* Make sure src and dst addrs were overridden properly */ + if (cmp_peer_addr(clientfd, &expected_addr)) + goto err; + + if (cmp_local_ip(clientfd, &expected_src_addr)) + goto err; + + goto out; +err: + err = -1; +out: + close(clientfd); + close(servfd); + return err; } -static int load_and_attach_progs(int cgfd, struct program *progs, - size_t prog_cnt) +static int run_sendmsg_test_case(const struct sock_addr_test *test) { - size_t i; - - for (i = 0; i < prog_cnt; ++i) { - printf("Load %s with invalid type (can pollute stderr) ", - progs[i].name); - fflush(stdout); - progs[i].fd = progs[i].loadfn(progs[i].invalid_type, NULL); - if (progs[i].fd != -1) { - log_err("Load with invalid type accepted for %s", - progs[i].name); - goto err; - } - printf("... REJECTED\n"); + socklen_t addr_len = sizeof(struct sockaddr_storage); + struct sockaddr_storage expected_src_addr; + struct sockaddr_storage requested_addr; + struct sockaddr_storage expected_addr; + struct sockaddr_storage real_src_addr; + int clientfd = -1; + int servfd = -1; + int set_cmsg; + int err = 0; + + if (test->type != SOCK_DGRAM) + goto err; - printf("Load %s with valid type", progs[i].name); - progs[i].fd = progs[i].loadfn(progs[i].type, progs[i].name); - if (progs[i].fd == -1) { - log_err("Failed to load program %s", progs[i].name); + if (init_addrs(test, &requested_addr, &expected_addr, + &expected_src_addr)) + goto err; + + /* Prepare server to sendmsg to */ + servfd = start_server(test->type, &expected_addr, addr_len); + if (servfd == -1) + goto err; + + for (set_cmsg = 0; set_cmsg <= 1; ++set_cmsg) { + if (clientfd >= 0) + close(clientfd); + + clientfd = sendmsg_to_server(&requested_addr, addr_len, + set_cmsg, &err); + if (err) + goto out; + else if (clientfd == -1) goto err; - } - printf(" ... OK\n"); - printf("Attach %s with invalid type", progs[i].name); - if (bpf_prog_attach(progs[i].fd, cgfd, progs[i].invalid_type, - BPF_F_ALLOW_OVERRIDE) != -1) { - log_err("Attach with invalid type accepted for %s", - progs[i].name); + /* Try to receive message on server instead of using + * getpeername(2) on client socket, to check that client's + * destination address was rewritten properly, since + * getpeername(2) doesn't work with unconnected datagram + * sockets. + * + * Get source address from recvmsg(2) as well to make sure + * source was rewritten properly: getsockname(2) can't be used + * since socket is unconnected and source defined for one + * specific packet may differ from the one used by default and + * returned by getsockname(2). + */ + if (recvmsg_from_client(servfd, &real_src_addr) == -1) goto err; - } - printf(" ... REJECTED\n"); - printf("Attach %s with valid type", progs[i].name); - if (bpf_prog_attach(progs[i].fd, cgfd, progs[i].type, - BPF_F_ALLOW_OVERRIDE) == -1) { - log_err("Failed to attach program %s", progs[i].name); + if (cmp_addr(&real_src_addr, &expected_src_addr, /*cmp_port*/0)) goto err; - } - printf(" ... OK\n"); } - return 0; + goto out; err: - close_progs_fds(progs, prog_cnt); - return -1; + err = -1; +out: + close(clientfd); + close(servfd); + return err; } -static int run_domain_test(int domain, int cgfd, struct program *progs, - size_t prog_cnt, const char *ip, unsigned short port) +static int run_test_case(int cgfd, const struct sock_addr_test *test) { + int progfd = -1; int err = 0; - if (load_and_attach_progs(cgfd, progs, prog_cnt) == -1) + printf("Test case: %s .. ", test->descr); + + progfd = test->loadfn(test); + if (test->expected_result == LOAD_REJECT && progfd < 0) + goto out; + else if (test->expected_result == LOAD_REJECT || progfd < 0) + goto err; + + err = bpf_prog_attach(progfd, cgfd, test->attach_type, + BPF_F_ALLOW_OVERRIDE); + if (test->expected_result == ATTACH_REJECT && err) { + err = 0; /* error was expected, reset it */ + goto out; + } else if (test->expected_result == ATTACH_REJECT || err) { goto err; + } - if (run_test_case(domain, SOCK_STREAM, ip, port) == -1) + switch (test->attach_type) { + case BPF_CGROUP_INET4_BIND: + case BPF_CGROUP_INET6_BIND: + err = run_bind_test_case(test); + break; + case BPF_CGROUP_INET4_CONNECT: + case BPF_CGROUP_INET6_CONNECT: + err = run_connect_test_case(test); + break; + case BPF_CGROUP_UDP4_SENDMSG: + case BPF_CGROUP_UDP6_SENDMSG: + err = run_sendmsg_test_case(test); + break; + default: goto err; + } + + if (test->expected_result == SYSCALL_EPERM && err == EPERM) { + err = 0; /* error was expected, reset it */ + goto out; + } + + if (test->expected_result == SYSCALL_ENOTSUPP && err == ENOTSUPP) { + err = 0; /* error was expected, reset it */ + goto out; + } - if (run_test_case(domain, SOCK_DGRAM, ip, port) == -1) + if (err || test->expected_result != SUCCESS) goto err; goto out; err: err = -1; out: - close_progs_fds(progs, prog_cnt); + /* Detaching w/o checking return code: best effort attempt. */ + if (progfd != -1) + bpf_prog_detach(cgfd, test->attach_type); + close(progfd); + printf("[%s]\n", err ? "FAIL" : "PASS"); return err; } -static int run_test(void) +static int run_tests(int cgfd) +{ + int passes = 0; + int fails = 0; + int i; + + for (i = 0; i < ARRAY_SIZE(tests); ++i) { + if (run_test_case(cgfd, &tests[i])) + ++fails; + else + ++passes; + } + printf("Summary: %d PASSED, %d FAILED\n", passes, fails); + return fails ? -1 : 0; +} + +int main(int argc, char **argv) { - size_t inet6_prog_cnt; - size_t inet_prog_cnt; int cgfd = -1; int err = 0; - struct program inet6_progs[] = { - {BPF_CGROUP_INET6_BIND, bind6_prog_load, -1, "bind6", - BPF_CGROUP_INET4_BIND}, - {BPF_CGROUP_INET6_CONNECT, connect6_prog_load, -1, "connect6", - BPF_CGROUP_INET4_CONNECT}, - }; - inet6_prog_cnt = sizeof(inet6_progs) / sizeof(struct program); - - struct program inet_progs[] = { - {BPF_CGROUP_INET4_BIND, bind4_prog_load, -1, "bind4", - BPF_CGROUP_INET6_BIND}, - {BPF_CGROUP_INET4_CONNECT, connect4_prog_load, -1, "connect4", - BPF_CGROUP_INET6_CONNECT}, - }; - inet_prog_cnt = sizeof(inet_progs) / sizeof(struct program); + if (argc < 2) { + fprintf(stderr, + "%s has to be run via %s.sh. Skip direct run.\n", + argv[0], argv[0]); + exit(err); + } if (setup_cgroup_environment()) goto err; @@ -559,12 +1359,7 @@ static int run_test(void) if (join_cgroup(CG_PATH)) goto err; - if (run_domain_test(AF_INET, cgfd, inet_progs, inet_prog_cnt, SERV4_IP, - SERV4_PORT) == -1) - goto err; - - if (run_domain_test(AF_INET6, cgfd, inet6_progs, inet6_prog_cnt, - SERV6_IP, SERV6_PORT) == -1) + if (run_tests(cgfd)) goto err; goto out; @@ -573,17 +1368,5 @@ err: out: close(cgfd); cleanup_cgroup_environment(); - printf(err ? "### FAIL\n" : "### SUCCESS\n"); return err; } - -int main(int argc, char **argv) -{ - if (argc < 2) { - fprintf(stderr, - "%s has to be run via %s.sh. Skip direct run.\n", - argv[0], argv[0]); - exit(0); - } - return run_test(); -} diff --git a/tools/testing/selftests/bpf/test_sockhash_kern.c b/tools/testing/selftests/bpf/test_sockhash_kern.c new file mode 100644 index 0000000..e675591 --- /dev/null +++ b/tools/testing/selftests/bpf/test_sockhash_kern.c @@ -0,0 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Covalent IO, Inc. http://covalent.io +#undef SOCKMAP +#define TEST_MAP_TYPE BPF_MAP_TYPE_SOCKHASH +#include "./test_sockmap_kern.h" diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c new file mode 100644 index 0000000..05c8cb7 --- /dev/null +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -0,0 +1,1524 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2017-2018 Covalent IO, Inc. http://covalent.io +#include <stdio.h> +#include <stdlib.h> +#include <sys/socket.h> +#include <sys/ioctl.h> +#include <sys/select.h> +#include <netinet/in.h> +#include <arpa/inet.h> +#include <unistd.h> +#include <string.h> +#include <errno.h> +#include <sys/ioctl.h> +#include <stdbool.h> +#include <signal.h> +#include <fcntl.h> +#include <sys/wait.h> +#include <time.h> +#include <sched.h> + +#include <sys/time.h> +#include <sys/resource.h> +#include <sys/types.h> +#include <sys/sendfile.h> + +#include <linux/netlink.h> +#include <linux/socket.h> +#include <linux/sock_diag.h> +#include <linux/bpf.h> +#include <linux/if_link.h> +#include <assert.h> +#include <libgen.h> + +#include <getopt.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include "bpf_util.h" +#include "bpf_rlimit.h" +#include "cgroup_helpers.h" + +int running; +static void running_handler(int a); + +/* randomly selected ports for testing on lo */ +#define S1_PORT 10000 +#define S2_PORT 10001 + +#define BPF_SOCKMAP_FILENAME "test_sockmap_kern.o" +#define BPF_SOCKHASH_FILENAME "test_sockhash_kern.o" +#define CG_PATH "/sockmap" + +/* global sockets */ +int s1, s2, c1, c2, p1, p2; +int test_cnt; +int passed; +int failed; +int map_fd[8]; +struct bpf_map *maps[8]; +int prog_fd[11]; + +int txmsg_pass; +int txmsg_noisy; +int txmsg_redir; +int txmsg_redir_noisy; +int txmsg_drop; +int txmsg_apply; +int txmsg_cork; +int txmsg_start; +int txmsg_end; +int txmsg_ingress; +int txmsg_skb; + +static const struct option long_options[] = { + {"help", no_argument, NULL, 'h' }, + {"cgroup", required_argument, NULL, 'c' }, + {"rate", required_argument, NULL, 'r' }, + {"verbose", no_argument, NULL, 'v' }, + {"iov_count", required_argument, NULL, 'i' }, + {"length", required_argument, NULL, 'l' }, + {"test", required_argument, NULL, 't' }, + {"data_test", no_argument, NULL, 'd' }, + {"txmsg", no_argument, &txmsg_pass, 1 }, + {"txmsg_noisy", no_argument, &txmsg_noisy, 1 }, + {"txmsg_redir", no_argument, &txmsg_redir, 1 }, + {"txmsg_redir_noisy", no_argument, &txmsg_redir_noisy, 1}, + {"txmsg_drop", no_argument, &txmsg_drop, 1 }, + {"txmsg_apply", required_argument, NULL, 'a'}, + {"txmsg_cork", required_argument, NULL, 'k'}, + {"txmsg_start", required_argument, NULL, 's'}, + {"txmsg_end", required_argument, NULL, 'e'}, + {"txmsg_ingress", no_argument, &txmsg_ingress, 1 }, + {"txmsg_skb", no_argument, &txmsg_skb, 1 }, + {0, 0, NULL, 0 } +}; + +static void usage(char *argv[]) +{ + int i; + + printf(" Usage: %s --cgroup <cgroup_path>\n", argv[0]); + printf(" options:\n"); + for (i = 0; long_options[i].name != 0; i++) { + printf(" --%-12s", long_options[i].name); + if (long_options[i].flag != NULL) + printf(" flag (internal value:%d)\n", + *long_options[i].flag); + else + printf(" -%c\n", long_options[i].val); + } + printf("\n"); +} + +static int sockmap_init_sockets(int verbose) +{ + int i, err, one = 1; + struct sockaddr_in addr; + int *fds[4] = {&s1, &s2, &c1, &c2}; + + s1 = s2 = p1 = p2 = c1 = c2 = 0; + + /* Init sockets */ + for (i = 0; i < 4; i++) { + *fds[i] = socket(AF_INET, SOCK_STREAM, 0); + if (*fds[i] < 0) { + perror("socket s1 failed()"); + return errno; + } + } + + /* Allow reuse */ + for (i = 0; i < 2; i++) { + err = setsockopt(*fds[i], SOL_SOCKET, SO_REUSEADDR, + (char *)&one, sizeof(one)); + if (err) { + perror("setsockopt failed()"); + return errno; + } + } + + /* Non-blocking sockets */ + for (i = 0; i < 2; i++) { + err = ioctl(*fds[i], FIONBIO, (char *)&one); + if (err < 0) { + perror("ioctl s1 failed()"); + return errno; + } + } + + /* Bind server sockets */ + memset(&addr, 0, sizeof(struct sockaddr_in)); + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = inet_addr("127.0.0.1"); + + addr.sin_port = htons(S1_PORT); + err = bind(s1, (struct sockaddr *)&addr, sizeof(addr)); + if (err < 0) { + perror("bind s1 failed()\n"); + return errno; + } + + addr.sin_port = htons(S2_PORT); + err = bind(s2, (struct sockaddr *)&addr, sizeof(addr)); + if (err < 0) { + perror("bind s2 failed()\n"); + return errno; + } + + /* Listen server sockets */ + addr.sin_port = htons(S1_PORT); + err = listen(s1, 32); + if (err < 0) { + perror("listen s1 failed()\n"); + return errno; + } + + addr.sin_port = htons(S2_PORT); + err = listen(s2, 32); + if (err < 0) { + perror("listen s1 failed()\n"); + return errno; + } + + /* Initiate Connect */ + addr.sin_port = htons(S1_PORT); + err = connect(c1, (struct sockaddr *)&addr, sizeof(addr)); + if (err < 0 && errno != EINPROGRESS) { + perror("connect c1 failed()\n"); + return errno; + } + + addr.sin_port = htons(S2_PORT); + err = connect(c2, (struct sockaddr *)&addr, sizeof(addr)); + if (err < 0 && errno != EINPROGRESS) { + perror("connect c2 failed()\n"); + return errno; + } else if (err < 0) { + err = 0; + } + + /* Accept Connecrtions */ + p1 = accept(s1, NULL, NULL); + if (p1 < 0) { + perror("accept s1 failed()\n"); + return errno; + } + + p2 = accept(s2, NULL, NULL); + if (p2 < 0) { + perror("accept s1 failed()\n"); + return errno; + } + + if (verbose) { + printf("connected sockets: c1 <-> p1, c2 <-> p2\n"); + printf("cgroups binding: c1(%i) <-> s1(%i) - - - c2(%i) <-> s2(%i)\n", + c1, s1, c2, s2); + } + return 0; +} + +struct msg_stats { + size_t bytes_sent; + size_t bytes_recvd; + struct timespec start; + struct timespec end; +}; + +struct sockmap_options { + int verbose; + bool base; + bool sendpage; + bool data_test; + bool drop_expected; + int iov_count; + int iov_length; + int rate; +}; + +static int msg_loop_sendpage(int fd, int iov_length, int cnt, + struct msg_stats *s, + struct sockmap_options *opt) +{ + bool drop = opt->drop_expected; + unsigned char k = 0; + FILE *file; + int i, fp; + + file = fopen(".sendpage_tst.tmp", "w+"); + for (i = 0; i < iov_length * cnt; i++, k++) + fwrite(&k, sizeof(char), 1, file); + fflush(file); + fseek(file, 0, SEEK_SET); + fclose(file); + + fp = open(".sendpage_tst.tmp", O_RDONLY); + clock_gettime(CLOCK_MONOTONIC, &s->start); + for (i = 0; i < cnt; i++) { + int sent = sendfile(fd, fp, NULL, iov_length); + + if (!drop && sent < 0) { + perror("send loop error:"); + close(fp); + return sent; + } else if (drop && sent >= 0) { + printf("sendpage loop error expected: %i\n", sent); + close(fp); + return -EIO; + } + + if (sent > 0) + s->bytes_sent += sent; + } + clock_gettime(CLOCK_MONOTONIC, &s->end); + close(fp); + return 0; +} + +static int msg_loop(int fd, int iov_count, int iov_length, int cnt, + struct msg_stats *s, bool tx, + struct sockmap_options *opt) +{ + struct msghdr msg = {0}; + int err, i, flags = MSG_NOSIGNAL; + struct iovec *iov; + unsigned char k; + bool data_test = opt->data_test; + bool drop = opt->drop_expected; + + iov = calloc(iov_count, sizeof(struct iovec)); + if (!iov) + return errno; + + k = 0; + for (i = 0; i < iov_count; i++) { + unsigned char *d = calloc(iov_length, sizeof(char)); + + if (!d) { + fprintf(stderr, "iov_count %i/%i OOM\n", i, iov_count); + goto out_errno; + } + iov[i].iov_base = d; + iov[i].iov_len = iov_length; + + if (data_test && tx) { + int j; + + for (j = 0; j < iov_length; j++) + d[j] = k++; + } + } + + msg.msg_iov = iov; + msg.msg_iovlen = iov_count; + k = 0; + + if (tx) { + clock_gettime(CLOCK_MONOTONIC, &s->start); + for (i = 0; i < cnt; i++) { + int sent = sendmsg(fd, &msg, flags); + + if (!drop && sent < 0) { + perror("send loop error:"); + goto out_errno; + } else if (drop && sent >= 0) { + printf("send loop error expected: %i\n", sent); + errno = -EIO; + goto out_errno; + } + if (sent > 0) + s->bytes_sent += sent; + } + clock_gettime(CLOCK_MONOTONIC, &s->end); + } else { + int slct, recv, max_fd = fd; + int fd_flags = O_NONBLOCK; + struct timeval timeout; + float total_bytes; + int bytes_cnt = 0; + int chunk_sz; + fd_set w; + + if (opt->sendpage) + chunk_sz = iov_length * cnt; + else + chunk_sz = iov_length * iov_count; + + fcntl(fd, fd_flags); + total_bytes = (float)iov_count * (float)iov_length * (float)cnt; + err = clock_gettime(CLOCK_MONOTONIC, &s->start); + if (err < 0) + perror("recv start time: "); + while (s->bytes_recvd < total_bytes) { + if (txmsg_cork) { + timeout.tv_sec = 0; + timeout.tv_usec = 1000; + } else { + timeout.tv_sec = 1; + timeout.tv_usec = 0; + } + + /* FD sets */ + FD_ZERO(&w); + FD_SET(fd, &w); + + slct = select(max_fd + 1, &w, NULL, NULL, &timeout); + if (slct == -1) { + perror("select()"); + clock_gettime(CLOCK_MONOTONIC, &s->end); + goto out_errno; + } else if (!slct) { + if (opt->verbose) + fprintf(stderr, "unexpected timeout\n"); + errno = -EIO; + clock_gettime(CLOCK_MONOTONIC, &s->end); + goto out_errno; + } + + recv = recvmsg(fd, &msg, flags); + if (recv < 0) { + if (errno != EWOULDBLOCK) { + clock_gettime(CLOCK_MONOTONIC, &s->end); + perror("recv failed()\n"); + goto out_errno; + } + } + + s->bytes_recvd += recv; + + if (data_test) { + int j; + + for (i = 0; i < msg.msg_iovlen; i++) { + unsigned char *d = iov[i].iov_base; + + for (j = 0; + j < iov[i].iov_len && recv; j++) { + if (d[j] != k++) { + errno = -EIO; + fprintf(stderr, + "detected data corruption @iov[%i]:%i %02x != %02x, %02x ?= %02x\n", + i, j, d[j], k - 1, d[j+1], k); + goto out_errno; + } + bytes_cnt++; + if (bytes_cnt == chunk_sz) { + k = 0; + bytes_cnt = 0; + } + recv--; + } + } + } + } + clock_gettime(CLOCK_MONOTONIC, &s->end); + } + + for (i = 0; i < iov_count; i++) + free(iov[i].iov_base); + free(iov); + return 0; +out_errno: + for (i = 0; i < iov_count; i++) + free(iov[i].iov_base); + free(iov); + return errno; +} + +static float giga = 1000000000; + +static inline float sentBps(struct msg_stats s) +{ + return s.bytes_sent / (s.end.tv_sec - s.start.tv_sec); +} + +static inline float recvdBps(struct msg_stats s) +{ + return s.bytes_recvd / (s.end.tv_sec - s.start.tv_sec); +} + +static int sendmsg_test(struct sockmap_options *opt) +{ + float sent_Bps = 0, recvd_Bps = 0; + int rx_fd, txpid, rxpid, err = 0; + struct msg_stats s = {0}; + int iov_count = opt->iov_count; + int iov_buf = opt->iov_length; + int rx_status, tx_status; + int cnt = opt->rate; + + errno = 0; + + if (opt->base) + rx_fd = p1; + else + rx_fd = p2; + + rxpid = fork(); + if (rxpid == 0) { + if (opt->drop_expected) + exit(0); + + if (opt->sendpage) + iov_count = 1; + err = msg_loop(rx_fd, iov_count, iov_buf, + cnt, &s, false, opt); + if (err && opt->verbose) + fprintf(stderr, + "msg_loop_rx: iov_count %i iov_buf %i cnt %i err %i\n", + iov_count, iov_buf, cnt, err); + shutdown(p2, SHUT_RDWR); + shutdown(p1, SHUT_RDWR); + if (s.end.tv_sec - s.start.tv_sec) { + sent_Bps = sentBps(s); + recvd_Bps = recvdBps(s); + } + if (opt->verbose) + fprintf(stdout, + "rx_sendmsg: TX: %zuB %fB/s %fGB/s RX: %zuB %fB/s %fGB/s\n", + s.bytes_sent, sent_Bps, sent_Bps/giga, + s.bytes_recvd, recvd_Bps, recvd_Bps/giga); + if (err && txmsg_cork) + err = 0; + exit(err ? 1 : 0); + } else if (rxpid == -1) { + perror("msg_loop_rx: "); + return errno; + } + + txpid = fork(); + if (txpid == 0) { + if (opt->sendpage) + err = msg_loop_sendpage(c1, iov_buf, cnt, &s, opt); + else + err = msg_loop(c1, iov_count, iov_buf, + cnt, &s, true, opt); + + if (err) + fprintf(stderr, + "msg_loop_tx: iov_count %i iov_buf %i cnt %i err %i\n", + iov_count, iov_buf, cnt, err); + shutdown(c1, SHUT_RDWR); + if (s.end.tv_sec - s.start.tv_sec) { + sent_Bps = sentBps(s); + recvd_Bps = recvdBps(s); + } + if (opt->verbose) + fprintf(stdout, + "tx_sendmsg: TX: %zuB %fB/s %f GB/s RX: %zuB %fB/s %fGB/s\n", + s.bytes_sent, sent_Bps, sent_Bps/giga, + s.bytes_recvd, recvd_Bps, recvd_Bps/giga); + exit(err ? 1 : 0); + } else if (txpid == -1) { + perror("msg_loop_tx: "); + return errno; + } + + assert(waitpid(rxpid, &rx_status, 0) == rxpid); + assert(waitpid(txpid, &tx_status, 0) == txpid); + if (WIFEXITED(rx_status)) { + err = WEXITSTATUS(rx_status); + if (err) { + fprintf(stderr, "rx thread exited with err %d. ", err); + goto out; + } + } + if (WIFEXITED(tx_status)) { + err = WEXITSTATUS(tx_status); + if (err) + fprintf(stderr, "tx thread exited with err %d. ", err); + } +out: + return err; +} + +static int forever_ping_pong(int rate, struct sockmap_options *opt) +{ + struct timeval timeout; + char buf[1024] = {0}; + int sc; + + timeout.tv_sec = 10; + timeout.tv_usec = 0; + + /* Ping/Pong data from client to server */ + sc = send(c1, buf, sizeof(buf), 0); + if (sc < 0) { + perror("send failed()\n"); + return sc; + } + + do { + int s, rc, i, max_fd = p2; + fd_set w; + + /* FD sets */ + FD_ZERO(&w); + FD_SET(c1, &w); + FD_SET(c2, &w); + FD_SET(p1, &w); + FD_SET(p2, &w); + + s = select(max_fd + 1, &w, NULL, NULL, &timeout); + if (s == -1) { + perror("select()"); + break; + } else if (!s) { + fprintf(stderr, "unexpected timeout\n"); + break; + } + + for (i = 0; i <= max_fd && s > 0; ++i) { + if (!FD_ISSET(i, &w)) + continue; + + s--; + + rc = recv(i, buf, sizeof(buf), 0); + if (rc < 0) { + if (errno != EWOULDBLOCK) { + perror("recv failed()\n"); + return rc; + } + } + + if (rc == 0) { + close(i); + break; + } + + sc = send(i, buf, rc, 0); + if (sc < 0) { + perror("send failed()\n"); + return sc; + } + } + + if (rate) + sleep(rate); + + if (opt->verbose) { + printf("."); + fflush(stdout); + + } + } while (running); + + return 0; +} + +enum { + PING_PONG, + SENDMSG, + BASE, + BASE_SENDPAGE, + SENDPAGE, +}; + +static int run_options(struct sockmap_options *options, int cg_fd, int test) +{ + int i, key, next_key, err, tx_prog_fd = -1, zero = 0; + + /* If base test skip BPF setup */ + if (test == BASE || test == BASE_SENDPAGE) + goto run; + + /* Attach programs to sockmap */ + err = bpf_prog_attach(prog_fd[0], map_fd[0], + BPF_SK_SKB_STREAM_PARSER, 0); + if (err) { + fprintf(stderr, + "ERROR: bpf_prog_attach (sockmap %i->%i): %d (%s)\n", + prog_fd[0], map_fd[0], err, strerror(errno)); + return err; + } + + err = bpf_prog_attach(prog_fd[1], map_fd[0], + BPF_SK_SKB_STREAM_VERDICT, 0); + if (err) { + fprintf(stderr, "ERROR: bpf_prog_attach (sockmap): %d (%s)\n", + err, strerror(errno)); + return err; + } + + /* Attach to cgroups */ + err = bpf_prog_attach(prog_fd[2], cg_fd, BPF_CGROUP_SOCK_OPS, 0); + if (err) { + fprintf(stderr, "ERROR: bpf_prog_attach (groups): %d (%s)\n", + err, strerror(errno)); + return err; + } + +run: + err = sockmap_init_sockets(options->verbose); + if (err) { + fprintf(stderr, "ERROR: test socket failed: %d\n", err); + goto out; + } + + /* Attach txmsg program to sockmap */ + if (txmsg_pass) + tx_prog_fd = prog_fd[3]; + else if (txmsg_noisy) + tx_prog_fd = prog_fd[4]; + else if (txmsg_redir) + tx_prog_fd = prog_fd[5]; + else if (txmsg_redir_noisy) + tx_prog_fd = prog_fd[6]; + else if (txmsg_drop) + tx_prog_fd = prog_fd[9]; + /* apply and cork must be last */ + else if (txmsg_apply) + tx_prog_fd = prog_fd[7]; + else if (txmsg_cork) + tx_prog_fd = prog_fd[8]; + else + tx_prog_fd = 0; + + if (tx_prog_fd) { + int redir_fd, i = 0; + + err = bpf_prog_attach(tx_prog_fd, + map_fd[1], BPF_SK_MSG_VERDICT, 0); + if (err) { + fprintf(stderr, + "ERROR: bpf_prog_attach (txmsg): %d (%s)\n", + err, strerror(errno)); + goto out; + } + + err = bpf_map_update_elem(map_fd[1], &i, &c1, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (txmsg): %d (%s\n", + err, strerror(errno)); + goto out; + } + + if (txmsg_redir || txmsg_redir_noisy) + redir_fd = c2; + else + redir_fd = c1; + + err = bpf_map_update_elem(map_fd[2], &i, &redir_fd, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (txmsg): %d (%s\n", + err, strerror(errno)); + goto out; + } + + if (txmsg_apply) { + err = bpf_map_update_elem(map_fd[3], + &i, &txmsg_apply, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (apply_bytes): %d (%s\n", + err, strerror(errno)); + goto out; + } + } + + if (txmsg_cork) { + err = bpf_map_update_elem(map_fd[4], + &i, &txmsg_cork, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (cork_bytes): %d (%s\n", + err, strerror(errno)); + goto out; + } + } + + if (txmsg_start) { + err = bpf_map_update_elem(map_fd[5], + &i, &txmsg_start, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (txmsg_start): %d (%s)\n", + err, strerror(errno)); + goto out; + } + } + + if (txmsg_end) { + i = 1; + err = bpf_map_update_elem(map_fd[5], + &i, &txmsg_end, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (txmsg_end): %d (%s)\n", + err, strerror(errno)); + goto out; + } + } + + if (txmsg_ingress) { + int in = BPF_F_INGRESS; + + i = 0; + err = bpf_map_update_elem(map_fd[6], &i, &in, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (txmsg_ingress): %d (%s)\n", + err, strerror(errno)); + } + i = 1; + err = bpf_map_update_elem(map_fd[1], &i, &p1, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (p1 txmsg): %d (%s)\n", + err, strerror(errno)); + } + err = bpf_map_update_elem(map_fd[2], &i, &p1, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (p1 redir): %d (%s)\n", + err, strerror(errno)); + } + + i = 2; + err = bpf_map_update_elem(map_fd[2], &i, &p2, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (p2 txmsg): %d (%s)\n", + err, strerror(errno)); + } + } + + if (txmsg_skb) { + int skb_fd = (test == SENDMSG || test == SENDPAGE) ? + p2 : p1; + int ingress = BPF_F_INGRESS; + + i = 0; + err = bpf_map_update_elem(map_fd[7], + &i, &ingress, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (txmsg_ingress): %d (%s)\n", + err, strerror(errno)); + } + + i = 3; + err = bpf_map_update_elem(map_fd[0], + &i, &skb_fd, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (c1 sockmap): %d (%s)\n", + err, strerror(errno)); + } + } + } + + if (txmsg_drop) + options->drop_expected = true; + + if (test == PING_PONG) + err = forever_ping_pong(options->rate, options); + else if (test == SENDMSG) { + options->base = false; + options->sendpage = false; + err = sendmsg_test(options); + } else if (test == SENDPAGE) { + options->base = false; + options->sendpage = true; + err = sendmsg_test(options); + } else if (test == BASE) { + options->base = true; + options->sendpage = false; + err = sendmsg_test(options); + } else if (test == BASE_SENDPAGE) { + options->base = true; + options->sendpage = true; + err = sendmsg_test(options); + } else + fprintf(stderr, "unknown test\n"); +out: + /* Detatch and zero all the maps */ + bpf_prog_detach2(prog_fd[2], cg_fd, BPF_CGROUP_SOCK_OPS); + bpf_prog_detach2(prog_fd[0], map_fd[0], BPF_SK_SKB_STREAM_PARSER); + bpf_prog_detach2(prog_fd[1], map_fd[0], BPF_SK_SKB_STREAM_VERDICT); + if (tx_prog_fd >= 0) + bpf_prog_detach2(tx_prog_fd, map_fd[1], BPF_SK_MSG_VERDICT); + + for (i = 0; i < 8; i++) { + key = next_key = 0; + bpf_map_update_elem(map_fd[i], &key, &zero, BPF_ANY); + while (bpf_map_get_next_key(map_fd[i], &key, &next_key) == 0) { + bpf_map_update_elem(map_fd[i], &key, &zero, BPF_ANY); + key = next_key; + } + } + + close(s1); + close(s2); + close(p1); + close(p2); + close(c1); + close(c2); + return err; +} + +static char *test_to_str(int test) +{ + switch (test) { + case SENDMSG: + return "sendmsg"; + case SENDPAGE: + return "sendpage"; + } + return "unknown"; +} + +#define OPTSTRING 60 +static void test_options(char *options) +{ + char tstr[OPTSTRING]; + + memset(options, 0, OPTSTRING); + + if (txmsg_pass) + strncat(options, "pass,", OPTSTRING); + if (txmsg_noisy) + strncat(options, "pass_noisy,", OPTSTRING); + if (txmsg_redir) + strncat(options, "redir,", OPTSTRING); + if (txmsg_redir_noisy) + strncat(options, "redir_noisy,", OPTSTRING); + if (txmsg_drop) + strncat(options, "drop,", OPTSTRING); + if (txmsg_apply) { + snprintf(tstr, OPTSTRING, "apply %d,", txmsg_apply); + strncat(options, tstr, OPTSTRING); + } + if (txmsg_cork) { + snprintf(tstr, OPTSTRING, "cork %d,", txmsg_cork); + strncat(options, tstr, OPTSTRING); + } + if (txmsg_start) { + snprintf(tstr, OPTSTRING, "start %d,", txmsg_start); + strncat(options, tstr, OPTSTRING); + } + if (txmsg_end) { + snprintf(tstr, OPTSTRING, "end %d,", txmsg_end); + strncat(options, tstr, OPTSTRING); + } + if (txmsg_ingress) + strncat(options, "ingress,", OPTSTRING); + if (txmsg_skb) + strncat(options, "skb,", OPTSTRING); +} + +static int __test_exec(int cgrp, int test, struct sockmap_options *opt) +{ + char *options = calloc(OPTSTRING, sizeof(char)); + int err; + + if (test == SENDPAGE) + opt->sendpage = true; + else + opt->sendpage = false; + + if (txmsg_drop) + opt->drop_expected = true; + else + opt->drop_expected = false; + + test_options(options); + + fprintf(stdout, + "[TEST %i]: (%i, %i, %i, %s, %s): ", + test_cnt, opt->rate, opt->iov_count, opt->iov_length, + test_to_str(test), options); + fflush(stdout); + err = run_options(opt, cgrp, test); + fprintf(stdout, "%s\n", !err ? "PASS" : "FAILED"); + test_cnt++; + !err ? passed++ : failed++; + free(options); + return err; +} + +static int test_exec(int cgrp, struct sockmap_options *opt) +{ + int err = __test_exec(cgrp, SENDMSG, opt); + + if (err) + goto out; + + err = __test_exec(cgrp, SENDPAGE, opt); +out: + return err; +} + +static int test_loop(int cgrp) +{ + struct sockmap_options opt; + + int err, i, l, r; + + opt.verbose = 0; + opt.base = false; + opt.sendpage = false; + opt.data_test = false; + opt.drop_expected = false; + opt.iov_count = 0; + opt.iov_length = 0; + opt.rate = 0; + + r = 1; + for (i = 1; i < 100; i += 33) { + for (l = 1; l < 100; l += 33) { + opt.rate = r; + opt.iov_count = i; + opt.iov_length = l; + err = test_exec(cgrp, &opt); + if (err) + goto out; + } + } + sched_yield(); +out: + return err; +} + +static int test_txmsg(int cgrp) +{ + int err; + + txmsg_pass = txmsg_noisy = txmsg_redir_noisy = txmsg_drop = 0; + txmsg_apply = txmsg_cork = 0; + txmsg_ingress = txmsg_skb = 0; + + txmsg_pass = 1; + err = test_loop(cgrp); + txmsg_pass = 0; + if (err) + goto out; + + txmsg_redir = 1; + err = test_loop(cgrp); + txmsg_redir = 0; + if (err) + goto out; + + txmsg_drop = 1; + err = test_loop(cgrp); + txmsg_drop = 0; + if (err) + goto out; + + txmsg_redir = 1; + txmsg_ingress = 1; + err = test_loop(cgrp); + txmsg_redir = 0; + txmsg_ingress = 0; + if (err) + goto out; +out: + txmsg_pass = 0; + txmsg_redir = 0; + txmsg_drop = 0; + return err; +} + +static int test_send(struct sockmap_options *opt, int cgrp) +{ + int err; + + opt->iov_length = 1; + opt->iov_count = 1; + opt->rate = 1; + err = test_exec(cgrp, opt); + if (err) + goto out; + + opt->iov_length = 1; + opt->iov_count = 1024; + opt->rate = 1; + err = test_exec(cgrp, opt); + if (err) + goto out; + + opt->iov_length = 1024; + opt->iov_count = 1; + opt->rate = 1; + err = test_exec(cgrp, opt); + if (err) + goto out; + + opt->iov_length = 1; + opt->iov_count = 1; + opt->rate = 512; + err = test_exec(cgrp, opt); + if (err) + goto out; + + opt->iov_length = 256; + opt->iov_count = 1024; + opt->rate = 2; + err = test_exec(cgrp, opt); + if (err) + goto out; + + opt->rate = 100; + opt->iov_count = 1; + opt->iov_length = 5; + err = test_exec(cgrp, opt); + if (err) + goto out; +out: + sched_yield(); + return err; +} + +static int test_mixed(int cgrp) +{ + struct sockmap_options opt = {0}; + int err; + + txmsg_pass = txmsg_noisy = txmsg_redir_noisy = txmsg_drop = 0; + txmsg_apply = txmsg_cork = 0; + txmsg_start = txmsg_end = 0; + /* Test small and large iov_count values with pass/redir/apply/cork */ + txmsg_pass = 1; + txmsg_redir = 0; + txmsg_apply = 1; + txmsg_cork = 0; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 1; + txmsg_redir = 0; + txmsg_apply = 0; + txmsg_cork = 1; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 1; + txmsg_redir = 0; + txmsg_apply = 1; + txmsg_cork = 1; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 1; + txmsg_redir = 0; + txmsg_apply = 1024; + txmsg_cork = 0; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 1; + txmsg_redir = 0; + txmsg_apply = 0; + txmsg_cork = 1024; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 1; + txmsg_redir = 0; + txmsg_apply = 1024; + txmsg_cork = 1024; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 1; + txmsg_redir = 0; + txmsg_cork = 4096; + txmsg_apply = 4096; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 0; + txmsg_redir = 1; + txmsg_apply = 1; + txmsg_cork = 0; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 0; + txmsg_redir = 1; + txmsg_apply = 0; + txmsg_cork = 1; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 0; + txmsg_redir = 1; + txmsg_apply = 1024; + txmsg_cork = 0; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 0; + txmsg_redir = 1; + txmsg_apply = 0; + txmsg_cork = 1024; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 0; + txmsg_redir = 1; + txmsg_apply = 1024; + txmsg_cork = 1024; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 0; + txmsg_redir = 1; + txmsg_cork = 4096; + txmsg_apply = 4096; + err = test_send(&opt, cgrp); + if (err) + goto out; +out: + return err; +} + +static int test_start_end(int cgrp) +{ + struct sockmap_options opt = {0}; + int err, i; + + /* Test basic start/end with lots of iov_count and iov_lengths */ + txmsg_start = 1; + txmsg_end = 2; + err = test_txmsg(cgrp); + if (err) + goto out; + + /* Test start/end with cork */ + opt.rate = 16; + opt.iov_count = 1; + opt.iov_length = 100; + txmsg_cork = 1600; + + for (i = 99; i <= 1600; i += 500) { + txmsg_start = 0; + txmsg_end = i; + err = test_exec(cgrp, &opt); + if (err) + goto out; + } + + /* Test start/end with cork but pull data in middle */ + for (i = 199; i <= 1600; i += 500) { + txmsg_start = 100; + txmsg_end = i; + err = test_exec(cgrp, &opt); + if (err) + goto out; + } + + /* Test start/end with cork pulling last sg entry */ + txmsg_start = 1500; + txmsg_end = 1600; + err = test_exec(cgrp, &opt); + if (err) + goto out; + + /* Test start/end pull of single byte in last page */ + txmsg_start = 1111; + txmsg_end = 1112; + err = test_exec(cgrp, &opt); + if (err) + goto out; + + /* Test start/end with end < start */ + txmsg_start = 1111; + txmsg_end = 0; + err = test_exec(cgrp, &opt); + if (err) + goto out; + + /* Test start/end with end > data */ + txmsg_start = 0; + txmsg_end = 1601; + err = test_exec(cgrp, &opt); + if (err) + goto out; + + /* Test start/end with start > data */ + txmsg_start = 1601; + txmsg_end = 1600; + err = test_exec(cgrp, &opt); + +out: + txmsg_start = 0; + txmsg_end = 0; + sched_yield(); + return err; +} + +char *map_names[] = { + "sock_map", + "sock_map_txmsg", + "sock_map_redir", + "sock_apply_bytes", + "sock_cork_bytes", + "sock_pull_bytes", + "sock_redir_flags", + "sock_skb_opts", +}; + +int prog_attach_type[] = { + BPF_SK_SKB_STREAM_PARSER, + BPF_SK_SKB_STREAM_VERDICT, + BPF_CGROUP_SOCK_OPS, + BPF_SK_MSG_VERDICT, + BPF_SK_MSG_VERDICT, + BPF_SK_MSG_VERDICT, + BPF_SK_MSG_VERDICT, + BPF_SK_MSG_VERDICT, + BPF_SK_MSG_VERDICT, + BPF_SK_MSG_VERDICT, +}; + +int prog_type[] = { + BPF_PROG_TYPE_SK_SKB, + BPF_PROG_TYPE_SK_SKB, + BPF_PROG_TYPE_SOCK_OPS, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_SK_MSG, +}; + +static int populate_progs(char *bpf_file) +{ + struct bpf_program *prog; + struct bpf_object *obj; + int i = 0; + long err; + + obj = bpf_object__open(bpf_file); + err = libbpf_get_error(obj); + if (err) { + char err_buf[256]; + + libbpf_strerror(err, err_buf, sizeof(err_buf)); + printf("Unable to load eBPF objects in file '%s' : %s\n", + bpf_file, err_buf); + return -1; + } + + bpf_object__for_each_program(prog, obj) { + bpf_program__set_type(prog, prog_type[i]); + bpf_program__set_expected_attach_type(prog, + prog_attach_type[i]); + i++; + } + + i = bpf_object__load(obj); + i = 0; + bpf_object__for_each_program(prog, obj) { + prog_fd[i] = bpf_program__fd(prog); + i++; + } + + for (i = 0; i < sizeof(map_fd)/sizeof(int); i++) { + maps[i] = bpf_object__find_map_by_name(obj, map_names[i]); + map_fd[i] = bpf_map__fd(maps[i]); + if (map_fd[i] < 0) { + fprintf(stderr, "load_bpf_file: (%i) %s\n", + map_fd[i], strerror(errno)); + return -1; + } + } + + return 0; +} + +static int __test_suite(char *bpf_file) +{ + int cg_fd, err; + + err = populate_progs(bpf_file); + if (err < 0) { + fprintf(stderr, "ERROR: (%i) load bpf failed\n", err); + return err; + } + + if (setup_cgroup_environment()) { + fprintf(stderr, "ERROR: cgroup env failed\n"); + return -EINVAL; + } + + cg_fd = create_and_get_cgroup(CG_PATH); + if (cg_fd < 0) { + fprintf(stderr, + "ERROR: (%i) open cg path failed: %s\n", + cg_fd, optarg); + return cg_fd; + } + + if (join_cgroup(CG_PATH)) { + fprintf(stderr, "ERROR: failed to join cgroup\n"); + return -EINVAL; + } + + /* Tests basic commands and APIs with range of iov values */ + txmsg_start = txmsg_end = 0; + err = test_txmsg(cg_fd); + if (err) + goto out; + + /* Tests interesting combinations of APIs used together */ + err = test_mixed(cg_fd); + if (err) + goto out; + + /* Tests pull_data API using start/end API */ + err = test_start_end(cg_fd); + if (err) + goto out; + +out: + printf("Summary: %i PASSED %i FAILED\n", passed, failed); + cleanup_cgroup_environment(); + close(cg_fd); + return err; +} + +static int test_suite(void) +{ + int err; + + err = __test_suite(BPF_SOCKMAP_FILENAME); + if (err) + goto out; + err = __test_suite(BPF_SOCKHASH_FILENAME); +out: + return err; +} + +int main(int argc, char **argv) +{ + struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY}; + int iov_count = 1, length = 1024, rate = 1; + struct sockmap_options options = {0}; + int opt, longindex, err, cg_fd = 0; + char *bpf_file = BPF_SOCKMAP_FILENAME; + int test = PING_PONG; + + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return 1; + } + + if (argc < 2) + return test_suite(); + + while ((opt = getopt_long(argc, argv, ":dhvc:r:i:l:t:", + long_options, &longindex)) != -1) { + switch (opt) { + case 's': + txmsg_start = atoi(optarg); + break; + case 'e': + txmsg_end = atoi(optarg); + break; + case 'a': + txmsg_apply = atoi(optarg); + break; + case 'k': + txmsg_cork = atoi(optarg); + break; + case 'c': + cg_fd = open(optarg, O_DIRECTORY, O_RDONLY); + if (cg_fd < 0) { + fprintf(stderr, + "ERROR: (%i) open cg path failed: %s\n", + cg_fd, optarg); + return cg_fd; + } + break; + case 'r': + rate = atoi(optarg); + break; + case 'v': + options.verbose = 1; + break; + case 'i': + iov_count = atoi(optarg); + break; + case 'l': + length = atoi(optarg); + break; + case 'd': + options.data_test = true; + break; + case 't': + if (strcmp(optarg, "ping") == 0) { + test = PING_PONG; + } else if (strcmp(optarg, "sendmsg") == 0) { + test = SENDMSG; + } else if (strcmp(optarg, "base") == 0) { + test = BASE; + } else if (strcmp(optarg, "base_sendpage") == 0) { + test = BASE_SENDPAGE; + } else if (strcmp(optarg, "sendpage") == 0) { + test = SENDPAGE; + } else { + usage(argv); + return -1; + } + break; + case 0: + break; + case 'h': + default: + usage(argv); + return -1; + } + } + + if (!cg_fd) { + fprintf(stderr, "%s requires cgroup option: --cgroup <path>\n", + argv[0]); + return -1; + } + + err = populate_progs(bpf_file); + if (err) { + fprintf(stderr, "populate program: (%s) %s\n", + bpf_file, strerror(errno)); + return 1; + } + running = 1; + + /* catch SIGINT */ + signal(SIGINT, running_handler); + + options.iov_count = iov_count; + options.iov_length = length; + options.rate = rate; + + err = run_options(&options, cg_fd, test); + close(cg_fd); + return err; +} + +void running_handler(int a) +{ + running = 0; +} diff --git a/tools/testing/selftests/bpf/test_sockmap_kern.c b/tools/testing/selftests/bpf/test_sockmap_kern.c new file mode 100644 index 0000000..677b2ed --- /dev/null +++ b/tools/testing/selftests/bpf/test_sockmap_kern.c @@ -0,0 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Covalent IO, Inc. http://covalent.io +#define SOCKMAP +#define TEST_MAP_TYPE BPF_MAP_TYPE_SOCKMAP +#include "./test_sockmap_kern.h" diff --git a/tools/testing/selftests/bpf/test_sockmap_kern.h b/tools/testing/selftests/bpf/test_sockmap_kern.h new file mode 100644 index 0000000..8e8e417 --- /dev/null +++ b/tools/testing/selftests/bpf/test_sockmap_kern.h @@ -0,0 +1,363 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2017-2018 Covalent IO, Inc. http://covalent.io */ +#include <stddef.h> +#include <string.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/in.h> +#include <linux/udp.h> +#include <linux/tcp.h> +#include <linux/pkt_cls.h> +#include <sys/socket.h> +#include "bpf_helpers.h" +#include "bpf_endian.h" + +/* Sockmap sample program connects a client and a backend together + * using cgroups. + * + * client:X <---> frontend:80 client:X <---> backend:80 + * + * For simplicity we hard code values here and bind 1:1. The hard + * coded values are part of the setup in sockmap.sh script that + * is associated with this BPF program. + * + * The bpf_printk is verbose and prints information as connections + * are established and verdicts are decided. + */ + +#define bpf_printk(fmt, ...) \ +({ \ + char ____fmt[] = fmt; \ + bpf_trace_printk(____fmt, sizeof(____fmt), \ + ##__VA_ARGS__); \ +}) + +struct bpf_map_def SEC("maps") sock_map = { + .type = TEST_MAP_TYPE, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 20, +}; + +struct bpf_map_def SEC("maps") sock_map_txmsg = { + .type = TEST_MAP_TYPE, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 20, +}; + +struct bpf_map_def SEC("maps") sock_map_redir = { + .type = TEST_MAP_TYPE, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 20, +}; + +struct bpf_map_def SEC("maps") sock_apply_bytes = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 1 +}; + +struct bpf_map_def SEC("maps") sock_cork_bytes = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 1 +}; + +struct bpf_map_def SEC("maps") sock_pull_bytes = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 2 +}; + +struct bpf_map_def SEC("maps") sock_redir_flags = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 1 +}; + +struct bpf_map_def SEC("maps") sock_skb_opts = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 1 +}; + +SEC("sk_skb1") +int bpf_prog1(struct __sk_buff *skb) +{ + return skb->len; +} + +SEC("sk_skb2") +int bpf_prog2(struct __sk_buff *skb) +{ + __u32 lport = skb->local_port; + __u32 rport = skb->remote_port; + int len, *f, ret, zero = 0; + __u64 flags = 0; + + if (lport == 10000) + ret = 10; + else + ret = 1; + + len = (__u32)skb->data_end - (__u32)skb->data; + f = bpf_map_lookup_elem(&sock_skb_opts, &zero); + if (f && *f) { + ret = 3; + flags = *f; + } + + bpf_printk("sk_skb2: redirect(%iB) flags=%i\n", + len, flags); +#ifdef SOCKMAP + return bpf_sk_redirect_map(skb, &sock_map, ret, flags); +#else + return bpf_sk_redirect_hash(skb, &sock_map, &ret, flags); +#endif + +} + +SEC("sockops") +int bpf_sockmap(struct bpf_sock_ops *skops) +{ + __u32 lport, rport; + int op, err = 0, index, key, ret; + + + op = (int) skops->op; + + switch (op) { + case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: + lport = skops->local_port; + rport = skops->remote_port; + + if (lport == 10000) { + ret = 1; +#ifdef SOCKMAP + err = bpf_sock_map_update(skops, &sock_map, &ret, + BPF_NOEXIST); +#else + err = bpf_sock_hash_update(skops, &sock_map, &ret, + BPF_NOEXIST); +#endif + bpf_printk("passive(%i -> %i) map ctx update err: %d\n", + lport, bpf_ntohl(rport), err); + } + break; + case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: + lport = skops->local_port; + rport = skops->remote_port; + + if (bpf_ntohl(rport) == 10001) { + ret = 10; +#ifdef SOCKMAP + err = bpf_sock_map_update(skops, &sock_map, &ret, + BPF_NOEXIST); +#else + err = bpf_sock_hash_update(skops, &sock_map, &ret, + BPF_NOEXIST); +#endif + bpf_printk("active(%i -> %i) map ctx update err: %d\n", + lport, bpf_ntohl(rport), err); + } + break; + default: + break; + } + + return 0; +} + +SEC("sk_msg1") +int bpf_prog4(struct sk_msg_md *msg) +{ + int *bytes, zero = 0, one = 1; + int *start, *end; + + bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); + if (bytes) + bpf_msg_apply_bytes(msg, *bytes); + bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); + if (bytes) + bpf_msg_cork_bytes(msg, *bytes); + start = bpf_map_lookup_elem(&sock_pull_bytes, &zero); + end = bpf_map_lookup_elem(&sock_pull_bytes, &one); + if (start && end) + bpf_msg_pull_data(msg, *start, *end, 0); + return SK_PASS; +} + +SEC("sk_msg2") +int bpf_prog5(struct sk_msg_md *msg) +{ + int err1 = -1, err2 = -1, zero = 0, one = 1; + int *bytes, *start, *end, len1, len2; + + bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); + if (bytes) + err1 = bpf_msg_apply_bytes(msg, *bytes); + bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); + if (bytes) + err2 = bpf_msg_cork_bytes(msg, *bytes); + len1 = (__u64)msg->data_end - (__u64)msg->data; + start = bpf_map_lookup_elem(&sock_pull_bytes, &zero); + end = bpf_map_lookup_elem(&sock_pull_bytes, &one); + if (start && end) { + int err; + + bpf_printk("sk_msg2: pull(%i:%i)\n", + start ? *start : 0, end ? *end : 0); + err = bpf_msg_pull_data(msg, *start, *end, 0); + if (err) + bpf_printk("sk_msg2: pull_data err %i\n", + err); + len2 = (__u64)msg->data_end - (__u64)msg->data; + bpf_printk("sk_msg2: length update %i->%i\n", + len1, len2); + } + bpf_printk("sk_msg2: data length %i err1 %i err2 %i\n", + len1, err1, err2); + return SK_PASS; +} + +SEC("sk_msg3") +int bpf_prog6(struct sk_msg_md *msg) +{ + int *bytes, zero = 0, one = 1, key = 0; + int *start, *end, *f; + __u64 flags = 0; + + bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); + if (bytes) + bpf_msg_apply_bytes(msg, *bytes); + bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); + if (bytes) + bpf_msg_cork_bytes(msg, *bytes); + start = bpf_map_lookup_elem(&sock_pull_bytes, &zero); + end = bpf_map_lookup_elem(&sock_pull_bytes, &one); + if (start && end) + bpf_msg_pull_data(msg, *start, *end, 0); + f = bpf_map_lookup_elem(&sock_redir_flags, &zero); + if (f && *f) { + key = 2; + flags = *f; + } +#ifdef SOCKMAP + return bpf_msg_redirect_map(msg, &sock_map_redir, key, flags); +#else + return bpf_msg_redirect_hash(msg, &sock_map_redir, &key, flags); +#endif +} + +SEC("sk_msg4") +int bpf_prog7(struct sk_msg_md *msg) +{ + int err1 = 0, err2 = 0, zero = 0, one = 1, key = 0; + int *f, *bytes, *start, *end, len1, len2; + __u64 flags = 0; + + int err; + bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); + if (bytes) + err1 = bpf_msg_apply_bytes(msg, *bytes); + bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); + if (bytes) + err2 = bpf_msg_cork_bytes(msg, *bytes); + len1 = (__u64)msg->data_end - (__u64)msg->data; + start = bpf_map_lookup_elem(&sock_pull_bytes, &zero); + end = bpf_map_lookup_elem(&sock_pull_bytes, &one); + if (start && end) { + + bpf_printk("sk_msg2: pull(%i:%i)\n", + start ? *start : 0, end ? *end : 0); + err = bpf_msg_pull_data(msg, *start, *end, 0); + if (err) + bpf_printk("sk_msg2: pull_data err %i\n", + err); + len2 = (__u64)msg->data_end - (__u64)msg->data; + bpf_printk("sk_msg2: length update %i->%i\n", + len1, len2); + } + f = bpf_map_lookup_elem(&sock_redir_flags, &zero); + if (f && *f) { + key = 2; + flags = *f; + } + bpf_printk("sk_msg3: redirect(%iB) flags=%i err=%i\n", + len1, flags, err1 ? err1 : err2); +#ifdef SOCKMAP + err = bpf_msg_redirect_map(msg, &sock_map_redir, key, flags); +#else + err = bpf_msg_redirect_hash(msg, &sock_map_redir, &key, flags); +#endif + bpf_printk("sk_msg3: err %i\n", err); + return err; +} + +SEC("sk_msg5") +int bpf_prog8(struct sk_msg_md *msg) +{ + void *data_end = (void *)(long) msg->data_end; + void *data = (void *)(long) msg->data; + int ret = 0, *bytes, zero = 0; + + bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); + if (bytes) { + ret = bpf_msg_apply_bytes(msg, *bytes); + if (ret) + return SK_DROP; + } else { + return SK_DROP; + } + return SK_PASS; +} +SEC("sk_msg6") +int bpf_prog9(struct sk_msg_md *msg) +{ + void *data_end = (void *)(long) msg->data_end; + void *data = (void *)(long) msg->data; + int ret = 0, *bytes, zero = 0; + + bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); + if (bytes) { + if (((__u64)data_end - (__u64)data) >= *bytes) + return SK_PASS; + ret = bpf_msg_cork_bytes(msg, *bytes); + if (ret) + return SK_DROP; + } + return SK_PASS; +} + +SEC("sk_msg7") +int bpf_prog10(struct sk_msg_md *msg) +{ + int *bytes, zero = 0, one = 1; + int *start, *end; + + bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); + if (bytes) + bpf_msg_apply_bytes(msg, *bytes); + bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); + if (bytes) + bpf_msg_cork_bytes(msg, *bytes); + start = bpf_map_lookup_elem(&sock_pull_bytes, &zero); + end = bpf_map_lookup_elem(&sock_pull_bytes, &one); + if (start && end) + bpf_msg_pull_data(msg, *start, *end, 0); + + return SK_DROP; +} + +int _version SEC("version") = 1; +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_stacktrace_build_id.c b/tools/testing/selftests/bpf/test_stacktrace_build_id.c index b755bd7..d86c281 100644 --- a/tools/testing/selftests/bpf/test_stacktrace_build_id.c +++ b/tools/testing/selftests/bpf/test_stacktrace_build_id.c @@ -19,7 +19,7 @@ struct bpf_map_def SEC("maps") stackid_hmap = { .type = BPF_MAP_TYPE_HASH, .key_size = sizeof(__u32), .value_size = sizeof(__u32), - .max_entries = 10000, + .max_entries = 16384, }; struct bpf_map_def SEC("maps") stackmap = { @@ -31,6 +31,14 @@ struct bpf_map_def SEC("maps") stackmap = { .map_flags = BPF_F_STACK_BUILD_ID, }; +struct bpf_map_def SEC("maps") stack_amap = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct bpf_stack_build_id) + * PERF_MAX_STACK_DEPTH, + .max_entries = 128, +}; + /* taken from /sys/kernel/debug/tracing/events/random/urandom_read/format */ struct random_urandom_args { unsigned long long pad; @@ -42,7 +50,10 @@ struct random_urandom_args { SEC("tracepoint/random/urandom_read") int oncpu(struct random_urandom_args *args) { + __u32 max_len = sizeof(struct bpf_stack_build_id) + * PERF_MAX_STACK_DEPTH; __u32 key = 0, val = 0, *value_p; + void *stack_p; value_p = bpf_map_lookup_elem(&control_map, &key); if (value_p && *value_p) @@ -50,8 +61,13 @@ int oncpu(struct random_urandom_args *args) /* The size of stackmap and stackid_hmap should be the same */ key = bpf_get_stackid(args, &stackmap, BPF_F_USER_STACK); - if ((int)key >= 0) + if ((int)key >= 0) { bpf_map_update_elem(&stackid_hmap, &key, &val, 0); + stack_p = bpf_map_lookup_elem(&stack_amap, &key); + if (stack_p) + bpf_get_stack(args, stack_p, max_len, + BPF_F_USER_STACK | BPF_F_USER_BUILD_ID); + } return 0; } diff --git a/tools/testing/selftests/bpf/test_stacktrace_map.c b/tools/testing/selftests/bpf/test_stacktrace_map.c index 76d85c5d..af111af 100644 --- a/tools/testing/selftests/bpf/test_stacktrace_map.c +++ b/tools/testing/selftests/bpf/test_stacktrace_map.c @@ -19,14 +19,21 @@ struct bpf_map_def SEC("maps") stackid_hmap = { .type = BPF_MAP_TYPE_HASH, .key_size = sizeof(__u32), .value_size = sizeof(__u32), - .max_entries = 10000, + .max_entries = 16384, }; struct bpf_map_def SEC("maps") stackmap = { .type = BPF_MAP_TYPE_STACK_TRACE, .key_size = sizeof(__u32), .value_size = sizeof(__u64) * PERF_MAX_STACK_DEPTH, - .max_entries = 10000, + .max_entries = 16384, +}; + +struct bpf_map_def SEC("maps") stack_amap = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(__u64) * PERF_MAX_STACK_DEPTH, + .max_entries = 16384, }; /* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */ @@ -44,7 +51,9 @@ struct sched_switch_args { SEC("tracepoint/sched/sched_switch") int oncpu(struct sched_switch_args *ctx) { + __u32 max_len = PERF_MAX_STACK_DEPTH * sizeof(__u64); __u32 key = 0, val = 0, *value_p; + void *stack_p; value_p = bpf_map_lookup_elem(&control_map, &key); if (value_p && *value_p) @@ -52,8 +61,12 @@ int oncpu(struct sched_switch_args *ctx) /* The size of stackmap and stackid_hmap should be the same */ key = bpf_get_stackid(ctx, &stackmap, 0); - if ((int)key >= 0) + if ((int)key >= 0) { bpf_map_update_elem(&stackid_hmap, &key, &val, 0); + stack_p = bpf_map_lookup_elem(&stack_amap, &key); + if (stack_p) + bpf_get_stack(ctx, stack_p, max_len, 0); + } return 0; } diff --git a/tools/testing/selftests/bpf/test_tunnel.sh b/tools/testing/selftests/bpf/test_tunnel.sh new file mode 100755 index 0000000..aeb2901 --- /dev/null +++ b/tools/testing/selftests/bpf/test_tunnel.sh @@ -0,0 +1,729 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# End-to-end eBPF tunnel test suite +# The script tests BPF network tunnel implementation. +# +# Topology: +# --------- +# root namespace | at_ns0 namespace +# | +# ----------- | ----------- +# | tnl dev | | | tnl dev | (overlay network) +# ----------- | ----------- +# metadata-mode | native-mode +# with bpf | +# | +# ---------- | ---------- +# | veth1 | --------- | veth0 | (underlay network) +# ---------- peer ---------- +# +# +# Device Configuration +# -------------------- +# Root namespace with metadata-mode tunnel + BPF +# Device names and addresses: +# veth1 IP: 172.16.1.200, IPv6: 00::22 (underlay) +# tunnel dev <type>11, ex: gre11, IPv4: 10.1.1.200 (overlay) +# +# Namespace at_ns0 with native tunnel +# Device names and addresses: +# veth0 IPv4: 172.16.1.100, IPv6: 00::11 (underlay) +# tunnel dev <type>00, ex: gre00, IPv4: 10.1.1.100 (overlay) +# +# +# End-to-end ping packet flow +# --------------------------- +# Most of the tests start by namespace creation, device configuration, +# then ping the underlay and overlay network. When doing 'ping 10.1.1.100' +# from root namespace, the following operations happen: +# 1) Route lookup shows 10.1.1.100/24 belongs to tnl dev, fwd to tnl dev. +# 2) Tnl device's egress BPF program is triggered and set the tunnel metadata, +# with remote_ip=172.16.1.200 and others. +# 3) Outer tunnel header is prepended and route the packet to veth1's egress +# 4) veth0's ingress queue receive the tunneled packet at namespace at_ns0 +# 5) Tunnel protocol handler, ex: vxlan_rcv, decap the packet +# 6) Forward the packet to the overlay tnl dev + +PING_ARG="-c 3 -w 10 -q" +ret=0 +GREEN='\033[0;92m' +RED='\033[0;31m' +NC='\033[0m' # No Color + +config_device() +{ + ip netns add at_ns0 + ip link add veth0 type veth peer name veth1 + ip link set veth0 netns at_ns0 + ip netns exec at_ns0 ip addr add 172.16.1.100/24 dev veth0 + ip netns exec at_ns0 ip link set dev veth0 up + ip link set dev veth1 up mtu 1500 + ip addr add dev veth1 172.16.1.200/24 +} + +add_gre_tunnel() +{ + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE seq key 2 \ + local 172.16.1.100 remote 172.16.1.200 + ip netns exec at_ns0 ip link set dev $DEV_NS up + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + + # root namespace + ip link add dev $DEV type $TYPE key 2 external + ip link set dev $DEV up + ip addr add dev $DEV 10.1.1.200/24 +} + +add_ip6gretap_tunnel() +{ + + # assign ipv6 address + ip netns exec at_ns0 ip addr add ::11/96 dev veth0 + ip netns exec at_ns0 ip link set dev veth0 up + ip addr add dev veth1 ::22/96 + ip link set dev veth1 up + + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE seq flowlabel 0xbcdef key 2 \ + local ::11 remote ::22 + + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + ip netns exec at_ns0 ip addr add dev $DEV_NS fc80::100/96 + ip netns exec at_ns0 ip link set dev $DEV_NS up + + # root namespace + ip link add dev $DEV type $TYPE external + ip addr add dev $DEV 10.1.1.200/24 + ip addr add dev $DEV fc80::200/24 + ip link set dev $DEV up +} + +add_erspan_tunnel() +{ + # at_ns0 namespace + if [ "$1" == "v1" ]; then + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE seq key 2 \ + local 172.16.1.100 remote 172.16.1.200 \ + erspan_ver 1 erspan 123 + else + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE seq key 2 \ + local 172.16.1.100 remote 172.16.1.200 \ + erspan_ver 2 erspan_dir egress erspan_hwid 3 + fi + ip netns exec at_ns0 ip link set dev $DEV_NS up + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + + # root namespace + ip link add dev $DEV type $TYPE external + ip link set dev $DEV up + ip addr add dev $DEV 10.1.1.200/24 +} + +add_ip6erspan_tunnel() +{ + + # assign ipv6 address + ip netns exec at_ns0 ip addr add ::11/96 dev veth0 + ip netns exec at_ns0 ip link set dev veth0 up + ip addr add dev veth1 ::22/96 + ip link set dev veth1 up + + # at_ns0 namespace + if [ "$1" == "v1" ]; then + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE seq key 2 \ + local ::11 remote ::22 \ + erspan_ver 1 erspan 123 + else + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE seq key 2 \ + local ::11 remote ::22 \ + erspan_ver 2 erspan_dir egress erspan_hwid 7 + fi + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + ip netns exec at_ns0 ip link set dev $DEV_NS up + + # root namespace + ip link add dev $DEV type $TYPE external + ip addr add dev $DEV 10.1.1.200/24 + ip link set dev $DEV up +} + +add_vxlan_tunnel() +{ + # Set static ARP entry here because iptables set-mark works + # on L3 packet, as a result not applying to ARP packets, + # causing errors at get_tunnel_{key/opt}. + + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE \ + id 2 dstport 4789 gbp remote 172.16.1.200 + ip netns exec at_ns0 \ + ip link set dev $DEV_NS address 52:54:00:d9:01:00 up + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + ip netns exec at_ns0 arp -s 10.1.1.200 52:54:00:d9:02:00 + ip netns exec at_ns0 iptables -A OUTPUT -j MARK --set-mark 0x800FF + + # root namespace + ip link add dev $DEV type $TYPE external gbp dstport 4789 + ip link set dev $DEV address 52:54:00:d9:02:00 up + ip addr add dev $DEV 10.1.1.200/24 + arp -s 10.1.1.100 52:54:00:d9:01:00 +} + +add_ip6vxlan_tunnel() +{ + #ip netns exec at_ns0 ip -4 addr del 172.16.1.100 dev veth0 + ip netns exec at_ns0 ip -6 addr add ::11/96 dev veth0 + ip netns exec at_ns0 ip link set dev veth0 up + #ip -4 addr del 172.16.1.200 dev veth1 + ip -6 addr add dev veth1 ::22/96 + ip link set dev veth1 up + + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE id 22 dstport 4789 \ + local ::11 remote ::22 + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + ip netns exec at_ns0 ip link set dev $DEV_NS up + + # root namespace + ip link add dev $DEV type $TYPE external dstport 4789 + ip addr add dev $DEV 10.1.1.200/24 + ip link set dev $DEV up +} + +add_geneve_tunnel() +{ + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE \ + id 2 dstport 6081 remote 172.16.1.200 + ip netns exec at_ns0 ip link set dev $DEV_NS up + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + + # root namespace + ip link add dev $DEV type $TYPE dstport 6081 external + ip link set dev $DEV up + ip addr add dev $DEV 10.1.1.200/24 +} + +add_ip6geneve_tunnel() +{ + ip netns exec at_ns0 ip addr add ::11/96 dev veth0 + ip netns exec at_ns0 ip link set dev veth0 up + ip addr add dev veth1 ::22/96 + ip link set dev veth1 up + + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE id 22 \ + remote ::22 # geneve has no local option + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + ip netns exec at_ns0 ip link set dev $DEV_NS up + + # root namespace + ip link add dev $DEV type $TYPE external + ip addr add dev $DEV 10.1.1.200/24 + ip link set dev $DEV up +} + +add_ipip_tunnel() +{ + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE \ + local 172.16.1.100 remote 172.16.1.200 + ip netns exec at_ns0 ip link set dev $DEV_NS up + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + + # root namespace + ip link add dev $DEV type $TYPE external + ip link set dev $DEV up + ip addr add dev $DEV 10.1.1.200/24 +} + +add_ipip6tnl_tunnel() +{ + ip netns exec at_ns0 ip addr add ::11/96 dev veth0 + ip netns exec at_ns0 ip link set dev veth0 up + ip addr add dev veth1 ::22/96 + ip link set dev veth1 up + + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE \ + local ::11 remote ::22 + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + ip netns exec at_ns0 ip link set dev $DEV_NS up + + # root namespace + ip link add dev $DEV type $TYPE external + ip addr add dev $DEV 10.1.1.200/24 + ip link set dev $DEV up +} + +test_gre() +{ + TYPE=gretap + DEV_NS=gretap00 + DEV=gretap11 + ret=0 + + check $TYPE + config_device + add_gre_tunnel + attach_bpf $DEV gre_set_tunnel gre_get_tunnel + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_ip6gre() +{ + TYPE=ip6gre + DEV_NS=ip6gre00 + DEV=ip6gre11 + ret=0 + + check $TYPE + config_device + # reuse the ip6gretap function + add_ip6gretap_tunnel + attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel + # underlay + ping6 $PING_ARG ::11 + # overlay: ipv4 over ipv6 + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + ping $PING_ARG 10.1.1.100 + check_err $? + # overlay: ipv6 over ipv6 + ip netns exec at_ns0 ping6 $PING_ARG fc80::200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_ip6gretap() +{ + TYPE=ip6gretap + DEV_NS=ip6gretap00 + DEV=ip6gretap11 + ret=0 + + check $TYPE + config_device + add_ip6gretap_tunnel + attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel + # underlay + ping6 $PING_ARG ::11 + # overlay: ipv4 over ipv6 + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + ping $PING_ARG 10.1.1.100 + check_err $? + # overlay: ipv6 over ipv6 + ip netns exec at_ns0 ping6 $PING_ARG fc80::200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_erspan() +{ + TYPE=erspan + DEV_NS=erspan00 + DEV=erspan11 + ret=0 + + check $TYPE + config_device + add_erspan_tunnel $1 + attach_bpf $DEV erspan_set_tunnel erspan_get_tunnel + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_ip6erspan() +{ + TYPE=ip6erspan + DEV_NS=ip6erspan00 + DEV=ip6erspan11 + ret=0 + + check $TYPE + config_device + add_ip6erspan_tunnel $1 + attach_bpf $DEV ip4ip6erspan_set_tunnel ip4ip6erspan_get_tunnel + ping6 $PING_ARG ::11 + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_vxlan() +{ + TYPE=vxlan + DEV_NS=vxlan00 + DEV=vxlan11 + ret=0 + + check $TYPE + config_device + add_vxlan_tunnel + attach_bpf $DEV vxlan_set_tunnel vxlan_get_tunnel + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_ip6vxlan() +{ + TYPE=vxlan + DEV_NS=ip6vxlan00 + DEV=ip6vxlan11 + ret=0 + + check $TYPE + config_device + add_ip6vxlan_tunnel + ip link set dev veth1 mtu 1500 + attach_bpf $DEV ip6vxlan_set_tunnel ip6vxlan_get_tunnel + # underlay + ping6 $PING_ARG ::11 + # ip4 over ip6 + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: ip6$TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: ip6$TYPE"${NC} +} + +test_geneve() +{ + TYPE=geneve + DEV_NS=geneve00 + DEV=geneve11 + ret=0 + + check $TYPE + config_device + add_geneve_tunnel + attach_bpf $DEV geneve_set_tunnel geneve_get_tunnel + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_ip6geneve() +{ + TYPE=geneve + DEV_NS=ip6geneve00 + DEV=ip6geneve11 + ret=0 + + check $TYPE + config_device + add_ip6geneve_tunnel + attach_bpf $DEV ip6geneve_set_tunnel ip6geneve_get_tunnel + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: ip6$TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: ip6$TYPE"${NC} +} + +test_ipip() +{ + TYPE=ipip + DEV_NS=ipip00 + DEV=ipip11 + ret=0 + + check $TYPE + config_device + add_ipip_tunnel + ip link set dev veth1 mtu 1500 + attach_bpf $DEV ipip_set_tunnel ipip_get_tunnel + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_ipip6() +{ + TYPE=ip6tnl + DEV_NS=ipip6tnl00 + DEV=ipip6tnl11 + ret=0 + + check $TYPE + config_device + add_ipip6tnl_tunnel + ip link set dev veth1 mtu 1500 + attach_bpf $DEV ipip6_set_tunnel ipip6_get_tunnel + # underlay + ping6 $PING_ARG ::11 + # ip4 over ip6 + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +setup_xfrm_tunnel() +{ + auth=0x$(printf '1%.0s' {1..40}) + enc=0x$(printf '2%.0s' {1..32}) + spi_in_to_out=0x1 + spi_out_to_in=0x2 + # at_ns0 namespace + # at_ns0 -> root + ip netns exec at_ns0 \ + ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \ + spi $spi_in_to_out reqid 1 mode tunnel \ + auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc + ip netns exec at_ns0 \ + ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir out \ + tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \ + mode tunnel + # root -> at_ns0 + ip netns exec at_ns0 \ + ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \ + spi $spi_out_to_in reqid 2 mode tunnel \ + auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc + ip netns exec at_ns0 \ + ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir in \ + tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \ + mode tunnel + # address & route + ip netns exec at_ns0 \ + ip addr add dev veth0 10.1.1.100/32 + ip netns exec at_ns0 \ + ip route add 10.1.1.200 dev veth0 via 172.16.1.200 \ + src 10.1.1.100 + + # root namespace + # at_ns0 -> root + ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \ + spi $spi_in_to_out reqid 1 mode tunnel \ + auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc + ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir in \ + tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \ + mode tunnel + # root -> at_ns0 + ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \ + spi $spi_out_to_in reqid 2 mode tunnel \ + auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc + ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir out \ + tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \ + mode tunnel + # address & route + ip addr add dev veth1 10.1.1.200/32 + ip route add 10.1.1.100 dev veth1 via 172.16.1.100 src 10.1.1.200 +} + +test_xfrm_tunnel() +{ + config_device + #tcpdump -nei veth1 ip & + output=$(mktemp) + cat /sys/kernel/debug/tracing/trace_pipe | tee $output & + setup_xfrm_tunnel + tc qdisc add dev veth1 clsact + tc filter add dev veth1 proto ip ingress bpf da obj test_tunnel_kern.o \ + sec xfrm_get_state + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + sleep 1 + grep "reqid 1" $output + check_err $? + grep "spi 0x1" $output + check_err $? + grep "remote ip 0xac100164" $output + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: xfrm tunnel"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: xfrm tunnel"${NC} +} + +attach_bpf() +{ + DEV=$1 + SET=$2 + GET=$3 + tc qdisc add dev $DEV clsact + tc filter add dev $DEV egress bpf da obj test_tunnel_kern.o sec $SET + tc filter add dev $DEV ingress bpf da obj test_tunnel_kern.o sec $GET +} + +cleanup() +{ + ip netns delete at_ns0 2> /dev/null + ip link del veth1 2> /dev/null + ip link del ipip11 2> /dev/null + ip link del ipip6tnl11 2> /dev/null + ip link del gretap11 2> /dev/null + ip link del ip6gre11 2> /dev/null + ip link del ip6gretap11 2> /dev/null + ip link del vxlan11 2> /dev/null + ip link del ip6vxlan11 2> /dev/null + ip link del geneve11 2> /dev/null + ip link del ip6geneve11 2> /dev/null + ip link del erspan11 2> /dev/null + ip link del ip6erspan11 2> /dev/null +} + +cleanup_exit() +{ + echo "CATCH SIGKILL or SIGINT, cleanup and exit" + cleanup + exit 0 +} + +check() +{ + ip link help $1 2>&1 | grep -q "^Usage:" + if [ $? -ne 0 ];then + echo "SKIP $1: iproute2 not support" + cleanup + return 1 + fi +} + +enable_debug() +{ + echo 'file ip_gre.c +p' > /sys/kernel/debug/dynamic_debug/control + echo 'file ip6_gre.c +p' > /sys/kernel/debug/dynamic_debug/control + echo 'file vxlan.c +p' > /sys/kernel/debug/dynamic_debug/control + echo 'file geneve.c +p' > /sys/kernel/debug/dynamic_debug/control + echo 'file ipip.c +p' > /sys/kernel/debug/dynamic_debug/control +} + +check_err() +{ + if [ $ret -eq 0 ]; then + ret=$1 + fi +} + +bpf_tunnel_test() +{ + echo "Testing GRE tunnel..." + test_gre + echo "Testing IP6GRE tunnel..." + test_ip6gre + echo "Testing IP6GRETAP tunnel..." + test_ip6gretap + echo "Testing ERSPAN tunnel..." + test_erspan v2 + echo "Testing IP6ERSPAN tunnel..." + test_ip6erspan v2 + echo "Testing VXLAN tunnel..." + test_vxlan + echo "Testing IP6VXLAN tunnel..." + test_ip6vxlan + echo "Testing GENEVE tunnel..." + test_geneve + echo "Testing IP6GENEVE tunnel..." + test_ip6geneve + echo "Testing IPIP tunnel..." + test_ipip + echo "Testing IPIP6 tunnel..." + test_ipip6 + echo "Testing IPSec tunnel..." + test_xfrm_tunnel +} + +trap cleanup 0 3 6 +trap cleanup_exit 2 9 + +cleanup +bpf_tunnel_test + +exit 0 diff --git a/tools/testing/selftests/bpf/test_tunnel_kern.c b/tools/testing/selftests/bpf/test_tunnel_kern.c new file mode 100644 index 0000000..504df69 --- /dev/null +++ b/tools/testing/selftests/bpf/test_tunnel_kern.c @@ -0,0 +1,713 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2016 VMware + * Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <stddef.h> +#include <string.h> +#include <arpa/inet.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/types.h> +#include <linux/tcp.h> +#include <linux/socket.h> +#include <linux/pkt_cls.h> +#include <linux/erspan.h> +#include "bpf_helpers.h" +#include "bpf_endian.h" + +#define ERROR(ret) do {\ + char fmt[] = "ERROR line:%d ret:%d\n";\ + bpf_trace_printk(fmt, sizeof(fmt), __LINE__, ret); \ + } while (0) + +int _version SEC("version") = 1; + +struct geneve_opt { + __be16 opt_class; + __u8 type; + __u8 length:5; + __u8 r3:1; + __u8 r2:1; + __u8 r1:1; + __u8 opt_data[8]; /* hard-coded to 8 byte */ +}; + +struct vxlan_metadata { + __u32 gbp; +}; + +SEC("gre_set_tunnel") +int _gre_set_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ + key.tunnel_id = 2; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_ZERO_CSUM_TX | BPF_F_SEQ_NUMBER); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("gre_get_tunnel") +int _gre_get_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + char fmt[] = "key %d remote ip 0x%x\n"; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), key.tunnel_id, key.remote_ipv4); + return TC_ACT_OK; +} + +SEC("ip6gretap_set_tunnel") +int _ip6gretap_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + int ret; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */ + key.tunnel_id = 2; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + key.tunnel_label = 0xabcde; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6 | BPF_F_ZERO_CSUM_TX | + BPF_F_SEQ_NUMBER); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("ip6gretap_get_tunnel") +int _ip6gretap_get_tunnel(struct __sk_buff *skb) +{ + char fmt[] = "key %d remote ip6 ::%x label %x\n"; + struct bpf_tunnel_key key; + int ret; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), + key.tunnel_id, key.remote_ipv6[3], key.tunnel_label); + + return TC_ACT_OK; +} + +SEC("erspan_set_tunnel") +int _erspan_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + struct erspan_metadata md; + int ret; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ + key.tunnel_id = 2; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_ZERO_CSUM_TX); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + __builtin_memset(&md, 0, sizeof(md)); +#ifdef ERSPAN_V1 + md.version = 1; + md.u.index = bpf_htonl(123); +#else + __u8 direction = 1; + __u8 hwid = 7; + + md.version = 2; + md.u.md2.dir = direction; + md.u.md2.hwid = hwid & 0xf; + md.u.md2.hwid_upper = (hwid >> 4) & 0x3; +#endif + + ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("erspan_get_tunnel") +int _erspan_get_tunnel(struct __sk_buff *skb) +{ + char fmt[] = "key %d remote ip 0x%x erspan version %d\n"; + struct bpf_tunnel_key key; + struct erspan_metadata md; + __u32 index; + int ret; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + ret = bpf_skb_get_tunnel_opt(skb, &md, sizeof(md)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), + key.tunnel_id, key.remote_ipv4, md.version); + +#ifdef ERSPAN_V1 + char fmt2[] = "\tindex %x\n"; + + index = bpf_ntohl(md.u.index); + bpf_trace_printk(fmt2, sizeof(fmt2), index); +#else + char fmt2[] = "\tdirection %d hwid %x timestamp %u\n"; + + bpf_trace_printk(fmt2, sizeof(fmt2), + md.u.md2.dir, + (md.u.md2.hwid_upper << 4) + md.u.md2.hwid, + bpf_ntohl(md.u.md2.timestamp)); +#endif + + return TC_ACT_OK; +} + +SEC("ip4ip6erspan_set_tunnel") +int _ip4ip6erspan_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + struct erspan_metadata md; + int ret; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv6[3] = bpf_htonl(0x11); + key.tunnel_id = 2; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + __builtin_memset(&md, 0, sizeof(md)); + +#ifdef ERSPAN_V1 + md.u.index = bpf_htonl(123); + md.version = 1; +#else + __u8 direction = 0; + __u8 hwid = 17; + + md.version = 2; + md.u.md2.dir = direction; + md.u.md2.hwid = hwid & 0xf; + md.u.md2.hwid_upper = (hwid >> 4) & 0x3; +#endif + + ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("ip4ip6erspan_get_tunnel") +int _ip4ip6erspan_get_tunnel(struct __sk_buff *skb) +{ + char fmt[] = "ip6erspan get key %d remote ip6 ::%x erspan version %d\n"; + struct bpf_tunnel_key key; + struct erspan_metadata md; + __u32 index; + int ret; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + ret = bpf_skb_get_tunnel_opt(skb, &md, sizeof(md)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), + key.tunnel_id, key.remote_ipv4, md.version); + +#ifdef ERSPAN_V1 + char fmt2[] = "\tindex %x\n"; + + index = bpf_ntohl(md.u.index); + bpf_trace_printk(fmt2, sizeof(fmt2), index); +#else + char fmt2[] = "\tdirection %d hwid %x timestamp %u\n"; + + bpf_trace_printk(fmt2, sizeof(fmt2), + md.u.md2.dir, + (md.u.md2.hwid_upper << 4) + md.u.md2.hwid, + bpf_ntohl(md.u.md2.timestamp)); +#endif + + return TC_ACT_OK; +} + +SEC("vxlan_set_tunnel") +int _vxlan_set_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + struct vxlan_metadata md; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ + key.tunnel_id = 2; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_ZERO_CSUM_TX); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + md.gbp = 0x800FF; /* Set VXLAN Group Policy extension */ + ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("vxlan_get_tunnel") +int _vxlan_get_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + struct vxlan_metadata md; + char fmt[] = "key %d remote ip 0x%x vxlan gbp 0x%x\n"; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + ret = bpf_skb_get_tunnel_opt(skb, &md, sizeof(md)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), + key.tunnel_id, key.remote_ipv4, md.gbp); + + return TC_ACT_OK; +} + +SEC("ip6vxlan_set_tunnel") +int _ip6vxlan_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + int ret; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */ + key.tunnel_id = 22; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("ip6vxlan_get_tunnel") +int _ip6vxlan_get_tunnel(struct __sk_buff *skb) +{ + char fmt[] = "key %d remote ip6 ::%x label %x\n"; + struct bpf_tunnel_key key; + int ret; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), + key.tunnel_id, key.remote_ipv6[3], key.tunnel_label); + + return TC_ACT_OK; +} + +SEC("geneve_set_tunnel") +int _geneve_set_tunnel(struct __sk_buff *skb) +{ + int ret, ret2; + struct bpf_tunnel_key key; + struct geneve_opt gopt; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ + key.tunnel_id = 2; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + __builtin_memset(&gopt, 0x0, sizeof(gopt)); + gopt.opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */ + gopt.type = 0x08; + gopt.r1 = 0; + gopt.r2 = 0; + gopt.r3 = 0; + gopt.length = 2; /* 4-byte multiple */ + *(int *) &gopt.opt_data = bpf_htonl(0xdeadbeef); + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_ZERO_CSUM_TX); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + ret = bpf_skb_set_tunnel_opt(skb, &gopt, sizeof(gopt)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("geneve_get_tunnel") +int _geneve_get_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + struct geneve_opt gopt; + char fmt[] = "key %d remote ip 0x%x geneve class 0x%x\n"; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), + key.tunnel_id, key.remote_ipv4, gopt.opt_class); + return TC_ACT_OK; +} + +SEC("ip6geneve_set_tunnel") +int _ip6geneve_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + struct geneve_opt gopt; + int ret; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */ + key.tunnel_id = 22; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + __builtin_memset(&gopt, 0x0, sizeof(gopt)); + gopt.opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */ + gopt.type = 0x08; + gopt.r1 = 0; + gopt.r2 = 0; + gopt.r3 = 0; + gopt.length = 2; /* 4-byte multiple */ + *(int *) &gopt.opt_data = bpf_htonl(0xfeedbeef); + + ret = bpf_skb_set_tunnel_opt(skb, &gopt, sizeof(gopt)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("ip6geneve_get_tunnel") +int _ip6geneve_get_tunnel(struct __sk_buff *skb) +{ + char fmt[] = "key %d remote ip 0x%x geneve class 0x%x\n"; + struct bpf_tunnel_key key; + struct geneve_opt gopt; + int ret; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), + key.tunnel_id, key.remote_ipv4, gopt.opt_class); + + return TC_ACT_OK; +} + +SEC("ipip_set_tunnel") +int _ipip_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key = {}; + void *data = (void *)(long)skb->data; + struct iphdr *iph = data; + struct tcphdr *tcp = data + sizeof(*iph); + void *data_end = (void *)(long)skb->data_end; + int ret; + + /* single length check */ + if (data + sizeof(*iph) + sizeof(*tcp) > data_end) { + ERROR(1); + return TC_ACT_SHOT; + } + + key.tunnel_ttl = 64; + if (iph->protocol == IPPROTO_ICMP) { + key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ + } else { + if (iph->protocol != IPPROTO_TCP || iph->ihl != 5) + return TC_ACT_SHOT; + + if (tcp->dest == bpf_htons(5200)) + key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ + else if (tcp->dest == bpf_htons(5201)) + key.remote_ipv4 = 0xac100165; /* 172.16.1.101 */ + else + return TC_ACT_SHOT; + } + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("ipip_get_tunnel") +int _ipip_get_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + char fmt[] = "remote ip 0x%x\n"; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), key.remote_ipv4); + return TC_ACT_OK; +} + +SEC("ipip6_set_tunnel") +int _ipip6_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key = {}; + void *data = (void *)(long)skb->data; + struct iphdr *iph = data; + struct tcphdr *tcp = data + sizeof(*iph); + void *data_end = (void *)(long)skb->data_end; + int ret; + + /* single length check */ + if (data + sizeof(*iph) + sizeof(*tcp) > data_end) { + ERROR(1); + return TC_ACT_SHOT; + } + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */ + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("ipip6_get_tunnel") +int _ipip6_get_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + char fmt[] = "remote ip6 %x::%x\n"; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), bpf_htonl(key.remote_ipv6[0]), + bpf_htonl(key.remote_ipv6[3])); + return TC_ACT_OK; +} + +SEC("ip6ip6_set_tunnel") +int _ip6ip6_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key = {}; + void *data = (void *)(long)skb->data; + struct ipv6hdr *iph = data; + struct tcphdr *tcp = data + sizeof(*iph); + void *data_end = (void *)(long)skb->data_end; + int ret; + + /* single length check */ + if (data + sizeof(*iph) + sizeof(*tcp) > data_end) { + ERROR(1); + return TC_ACT_SHOT; + } + + key.remote_ipv6[0] = bpf_htonl(0x2401db00); + key.tunnel_ttl = 64; + + if (iph->nexthdr == 58 /* NEXTHDR_ICMP */) { + key.remote_ipv6[3] = bpf_htonl(1); + } else { + if (iph->nexthdr != 6 /* NEXTHDR_TCP */) { + ERROR(iph->nexthdr); + return TC_ACT_SHOT; + } + + if (tcp->dest == bpf_htons(5200)) { + key.remote_ipv6[3] = bpf_htonl(1); + } else if (tcp->dest == bpf_htons(5201)) { + key.remote_ipv6[3] = bpf_htonl(2); + } else { + ERROR(tcp->dest); + return TC_ACT_SHOT; + } + } + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("ip6ip6_get_tunnel") +int _ip6ip6_get_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + char fmt[] = "remote ip6 %x::%x\n"; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), bpf_htonl(key.remote_ipv6[0]), + bpf_htonl(key.remote_ipv6[3])); + return TC_ACT_OK; +} + +SEC("xfrm_get_state") +int _xfrm_get_state(struct __sk_buff *skb) +{ + struct bpf_xfrm_state x; + char fmt[] = "reqid %d spi 0x%x remote ip 0x%x\n"; + int ret; + + ret = bpf_skb_get_xfrm_state(skb, 0, &x, sizeof(x), 0); + if (ret < 0) + return TC_ACT_OK; + + bpf_trace_printk(fmt, sizeof(fmt), x.reqid, bpf_ntohl(x.spi), + bpf_ntohl(x.remote_ipv4)); + return TC_ACT_OK; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index fd7de7e..2ecd27b 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -41,15 +41,16 @@ # endif #endif #include "bpf_rlimit.h" +#include "bpf_rand.h" #include "../../../include/linux/filter.h" #ifndef ARRAY_SIZE # define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) #endif -#define MAX_INSNS 512 +#define MAX_INSNS BPF_MAXINSNS #define MAX_FIXUPS 8 -#define MAX_NR_MAPS 4 +#define MAX_NR_MAPS 7 #define POINTER_VALUE 0xcafe4all #define TEST_DATA_LEN 64 @@ -64,7 +65,10 @@ struct bpf_test { struct bpf_insn insns[MAX_INSNS]; int fixup_map1[MAX_FIXUPS]; int fixup_map2[MAX_FIXUPS]; - int fixup_prog[MAX_FIXUPS]; + int fixup_map3[MAX_FIXUPS]; + int fixup_map4[MAX_FIXUPS]; + int fixup_prog1[MAX_FIXUPS]; + int fixup_prog2[MAX_FIXUPS]; int fixup_map_in_map[MAX_FIXUPS]; const char *errstr; const char *errstr_unpriv; @@ -76,6 +80,8 @@ struct bpf_test { } result, result_unpriv; enum bpf_prog_type prog_type; uint8_t flags; + __u8 data[TEST_DATA_LEN]; + void (*fill_helper)(struct bpf_test *self); }; /* Note we want this to be 64 bit aligned so that the end of our array is @@ -88,6 +94,91 @@ struct test_val { int foo[MAX_ENTRIES]; }; +struct other_val { + long long foo; + long long bar; +}; + +static void bpf_fill_ld_abs_vlan_push_pop(struct bpf_test *self) +{ + /* test: {skb->data[0], vlan_push} x 68 + {skb->data[0], vlan_pop} x 68 */ +#define PUSH_CNT 51 + unsigned int len = BPF_MAXINSNS; + struct bpf_insn *insn = self->insns; + int i = 0, j, k = 0; + + insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1); +loop: + for (j = 0; j < PUSH_CNT; j++) { + insn[i++] = BPF_LD_ABS(BPF_B, 0); + insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x34, len - i - 2); + i++; + insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6); + insn[i++] = BPF_MOV64_IMM(BPF_REG_2, 1); + insn[i++] = BPF_MOV64_IMM(BPF_REG_3, 2); + insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_vlan_push), + insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, len - i - 2); + i++; + } + + for (j = 0; j < PUSH_CNT; j++) { + insn[i++] = BPF_LD_ABS(BPF_B, 0); + insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x34, len - i - 2); + i++; + insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6); + insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_vlan_pop), + insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, len - i - 2); + i++; + } + if (++k < 5) + goto loop; + + for (; i < len - 1; i++) + insn[i] = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, 0xbef); + insn[len - 1] = BPF_EXIT_INSN(); +} + +static void bpf_fill_jump_around_ld_abs(struct bpf_test *self) +{ + struct bpf_insn *insn = self->insns; + unsigned int len = BPF_MAXINSNS; + int i = 0; + + insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1); + insn[i++] = BPF_LD_ABS(BPF_B, 0); + insn[i] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 10, len - i - 2); + i++; + while (i < len - 1) + insn[i++] = BPF_LD_ABS(BPF_B, 1); + insn[i] = BPF_EXIT_INSN(); +} + +static void bpf_fill_rand_ld_dw(struct bpf_test *self) +{ + struct bpf_insn *insn = self->insns; + uint64_t res = 0; + int i = 0; + + insn[i++] = BPF_MOV32_IMM(BPF_REG_0, 0); + while (i < self->retval) { + uint64_t val = bpf_semi_rand_get(); + struct bpf_insn tmp[2] = { BPF_LD_IMM64(BPF_REG_1, val) }; + + res ^= val; + insn[i++] = tmp[0]; + insn[i++] = tmp[1]; + insn[i++] = BPF_ALU64_REG(BPF_XOR, BPF_REG_0, BPF_REG_1); + } + insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_0); + insn[i++] = BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 32); + insn[i++] = BPF_ALU64_REG(BPF_XOR, BPF_REG_0, BPF_REG_1); + insn[i] = BPF_EXIT_INSN(); + res ^= (res >> 32); + self->retval = (uint32_t)res; +} + static struct bpf_test tests[] = { { "add+sub+mul", @@ -1597,6 +1688,121 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_SK_SKB, }, { + "valid access family in SK_MSG", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct sk_msg_md, family)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_MSG, + }, + { + "valid access remote_ip4 in SK_MSG", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct sk_msg_md, remote_ip4)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_MSG, + }, + { + "valid access local_ip4 in SK_MSG", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct sk_msg_md, local_ip4)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_MSG, + }, + { + "valid access remote_port in SK_MSG", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct sk_msg_md, remote_port)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_MSG, + }, + { + "valid access local_port in SK_MSG", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct sk_msg_md, local_port)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_MSG, + }, + { + "valid access remote_ip6 in SK_MSG", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct sk_msg_md, remote_ip6[0])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct sk_msg_md, remote_ip6[1])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct sk_msg_md, remote_ip6[2])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct sk_msg_md, remote_ip6[3])), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { + "valid access local_ip6 in SK_MSG", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct sk_msg_md, local_ip6[0])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct sk_msg_md, local_ip6[1])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct sk_msg_md, local_ip6[2])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct sk_msg_md, local_ip6[3])), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { + "invalid 64B read of family in SK_MSG", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, + offsetof(struct sk_msg_md, family)), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_MSG, + }, + { + "invalid read past end of SK_MSG", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct sk_msg_md, local_port) + 4), + BPF_EXIT_INSN(), + }, + .errstr = "R0 !read_ok", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_MSG, + }, + { + "invalid read offset in SK_MSG", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct sk_msg_md, family) + 1), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_MSG, + }, + { "direct packet read for SK_MSG", .insns = { BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, @@ -2565,7 +2771,7 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_prog = { 1 }, + .fixup_prog1 = { 1 }, .errstr_unpriv = "R3 leaks addr into helper", .result_unpriv = REJECT, .result = ACCEPT, @@ -2652,7 +2858,7 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - .fixup_prog = { 1 }, + .fixup_prog1 = { 1 }, .result = ACCEPT, .retval = 42, }, @@ -2666,7 +2872,7 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - .fixup_prog = { 1 }, + .fixup_prog1 = { 1 }, .result = ACCEPT, .retval = 41, }, @@ -2680,7 +2886,7 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - .fixup_prog = { 1 }, + .fixup_prog1 = { 1 }, .result = ACCEPT, .retval = 1, }, @@ -2694,7 +2900,7 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 2), BPF_EXIT_INSN(), }, - .fixup_prog = { 1 }, + .fixup_prog1 = { 1 }, .result = ACCEPT, .retval = 2, }, @@ -2708,7 +2914,7 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 2), BPF_EXIT_INSN(), }, - .fixup_prog = { 1 }, + .fixup_prog1 = { 1 }, .result = ACCEPT, .retval = 2, }, @@ -2722,7 +2928,7 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 2), BPF_EXIT_INSN(), }, - .fixup_prog = { 2 }, + .fixup_prog1 = { 2 }, .result = ACCEPT, .retval = 42, }, @@ -5594,6 +5800,257 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, { + "map lookup helper access to map", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 8 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map update helper access to map", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_update_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 10 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map update helper access to map: wrong size", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_update_elem), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .fixup_map3 = { 10 }, + .result = REJECT, + .errstr = "invalid access to map value, value_size=8 off=0 size=16", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via const imm)", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, + offsetof(struct other_val, bar)), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 9 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via const imm): out-of-bound 1", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, + sizeof(struct other_val) - 4), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 9 }, + .result = REJECT, + .errstr = "invalid access to map value, value_size=16 off=12 size=8", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via const imm): out-of-bound 2", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 9 }, + .result = REJECT, + .errstr = "invalid access to map value, value_size=16 off=-4 size=8", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via const reg)", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_3, + offsetof(struct other_val, bar)), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 10 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via const reg): out-of-bound 1", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_3, + sizeof(struct other_val) - 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 10 }, + .result = REJECT, + .errstr = "invalid access to map value, value_size=16 off=12 size=8", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via const reg): out-of-bound 2", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_3, -4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 10 }, + .result = REJECT, + .errstr = "invalid access to map value, value_size=16 off=-4 size=8", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via variable)", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JGT, BPF_REG_3, + offsetof(struct other_val, bar), 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 11 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via variable): no max check", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 10 }, + .result = REJECT, + .errstr = "R2 unbounded memory access, make sure to bounds check any array access into a map", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via variable): wrong max check", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JGT, BPF_REG_3, + offsetof(struct other_val, bar) + 1, 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 11 }, + .result = REJECT, + .errstr = "invalid access to map value, value_size=16 off=9 size=8", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { "map element value is preserved across register spilling", .insns = { BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), @@ -8190,7 +8647,7 @@ static struct bpf_test tests[] = { offsetof(struct __sk_buff, mark)), BPF_EXIT_INSN(), }, - .errstr = "dereference of modified ctx ptr R1 off=68+8, ctx+const is allowed, ctx+const+const is not", + .errstr = "dereference of modified ctx ptr", .result = REJECT, .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, @@ -11227,6 +11684,112 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_XDP, }, { + "calls: two calls returning different map pointers for lookup (hash, array)", + .insns = { + /* main prog */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_CALL_REL(11), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_CALL_REL(12), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, + offsetof(struct test_val, foo)), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + /* subprog 1 */ + BPF_LD_MAP_FD(BPF_REG_0, 0), + BPF_EXIT_INSN(), + /* subprog 2 */ + BPF_LD_MAP_FD(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .fixup_map2 = { 13 }, + .fixup_map4 = { 16 }, + .result = ACCEPT, + .retval = 1, + }, + { + "calls: two calls returning different map pointers for lookup (hash, map in map)", + .insns = { + /* main prog */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_CALL_REL(11), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_CALL_REL(12), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, + offsetof(struct test_val, foo)), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + /* subprog 1 */ + BPF_LD_MAP_FD(BPF_REG_0, 0), + BPF_EXIT_INSN(), + /* subprog 2 */ + BPF_LD_MAP_FD(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .fixup_map_in_map = { 16 }, + .fixup_map4 = { 13 }, + .result = REJECT, + .errstr = "R0 invalid mem access 'map_ptr'", + }, + { + "cond: two branches returning different map pointers for lookup (tail, tail)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct __sk_buff, mark)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_6, 0, 3), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 2), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_3, 7), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_prog1 = { 5 }, + .fixup_prog2 = { 2 }, + .result_unpriv = REJECT, + .errstr_unpriv = "tail_call abusing map_ptr", + .result = ACCEPT, + .retval = 42, + }, + { + "cond: two branches returning same map pointers for lookup (tail, tail)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct __sk_buff, mark)), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 3), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 2), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_3, 7), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_prog2 = { 2, 5 }, + .result_unpriv = ACCEPT, + .result = ACCEPT, + .retval = 42, + }, + { "search pruning: all branches should be verified (nop operation)", .insns = { BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), @@ -11423,6 +11986,334 @@ static struct bpf_test tests[] = { .errstr = "BPF_XADD stores into R2 packet", .prog_type = BPF_PROG_TYPE_XDP, }, + { + "bpf_get_stack return R0 within range", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 28), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_9, sizeof(struct test_val)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + BPF_MOV64_IMM(BPF_REG_3, sizeof(struct test_val)), + BPF_MOV64_IMM(BPF_REG_4, 256), + BPF_EMIT_CALL(BPF_FUNC_get_stack), + BPF_MOV64_IMM(BPF_REG_1, 0), + BPF_MOV64_REG(BPF_REG_8, BPF_REG_0), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_8, 32), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_8, 32), + BPF_JMP_REG(BPF_JSLT, BPF_REG_1, BPF_REG_8, 16), + BPF_ALU64_REG(BPF_SUB, BPF_REG_9, BPF_REG_8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_8), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_9), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 32), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_1, 32), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_1), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + BPF_MOV64_IMM(BPF_REG_5, sizeof(struct test_val)), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_5), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_9), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_EMIT_CALL(BPF_FUNC_get_stack), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 4 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "ld_abs: invalid op 1", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_LD_ABS(BPF_DW, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "unknown opcode", + }, + { + "ld_abs: invalid op 2", + .insns = { + BPF_MOV32_IMM(BPF_REG_0, 256), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_LD_IND(BPF_DW, BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "unknown opcode", + }, + { + "ld_abs: nmap reduced", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_LD_ABS(BPF_H, 12), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x806, 28), + BPF_LD_ABS(BPF_H, 12), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x806, 26), + BPF_MOV32_IMM(BPF_REG_0, 18), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -64), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_10, -64), + BPF_LD_IND(BPF_W, BPF_REG_7, 14), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -60), + BPF_MOV32_IMM(BPF_REG_0, 280971478), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -56), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_10, -56), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_10, -60), + BPF_ALU32_REG(BPF_SUB, BPF_REG_0, BPF_REG_7), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 15), + BPF_LD_ABS(BPF_H, 12), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x806, 13), + BPF_MOV32_IMM(BPF_REG_0, 22), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -56), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_10, -56), + BPF_LD_IND(BPF_H, BPF_REG_7, 14), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -52), + BPF_MOV32_IMM(BPF_REG_0, 17366), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -48), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_10, -48), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_10, -52), + BPF_ALU32_REG(BPF_SUB, BPF_REG_0, BPF_REG_7), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV32_IMM(BPF_REG_0, 256), + BPF_EXIT_INSN(), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .data = { + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0x06, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0x10, 0xbf, 0x48, 0xd6, 0x43, 0xd6, + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 256, + }, + { + "ld_abs: div + abs, test 1", + .insns = { + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1), + BPF_LD_ABS(BPF_B, 3), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_2, 2), + BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_2), + BPF_ALU64_REG(BPF_MOV, BPF_REG_8, BPF_REG_0), + BPF_LD_ABS(BPF_B, 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_8, BPF_REG_0), + BPF_LD_IND(BPF_B, BPF_REG_8, -70), + BPF_EXIT_INSN(), + }, + .data = { + 10, 20, 30, 40, 50, + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 10, + }, + { + "ld_abs: div + abs, test 2", + .insns = { + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1), + BPF_LD_ABS(BPF_B, 3), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_2, 2), + BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_2), + BPF_ALU64_REG(BPF_MOV, BPF_REG_8, BPF_REG_0), + BPF_LD_ABS(BPF_B, 128), + BPF_ALU64_REG(BPF_ADD, BPF_REG_8, BPF_REG_0), + BPF_LD_IND(BPF_B, BPF_REG_8, -70), + BPF_EXIT_INSN(), + }, + .data = { + 10, 20, 30, 40, 50, + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 0, + }, + { + "ld_abs: div + abs, test 3", + .insns = { + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_7, 0), + BPF_LD_ABS(BPF_B, 3), + BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_7), + BPF_EXIT_INSN(), + }, + .data = { + 10, 20, 30, 40, 50, + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 0, + }, + { + "ld_abs: div + abs, test 4", + .insns = { + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_7, 0), + BPF_LD_ABS(BPF_B, 256), + BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_7), + BPF_EXIT_INSN(), + }, + .data = { + 10, 20, 30, 40, 50, + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 0, + }, + { + "ld_abs: vlan + abs, test 1", + .insns = { }, + .data = { + 0x34, + }, + .fill_helper = bpf_fill_ld_abs_vlan_push_pop, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 0xbef, + }, + { + "ld_abs: vlan + abs, test 2", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_LD_ABS(BPF_B, 0), + BPF_LD_ABS(BPF_H, 0), + BPF_LD_ABS(BPF_W, 0), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_6, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + BPF_MOV64_IMM(BPF_REG_2, 1), + BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_vlan_push), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_7), + BPF_LD_ABS(BPF_B, 0), + BPF_LD_ABS(BPF_H, 0), + BPF_LD_ABS(BPF_W, 0), + BPF_MOV64_IMM(BPF_REG_0, 42), + BPF_EXIT_INSN(), + }, + .data = { + 0x34, + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 42, + }, + { + "ld_abs: jump around ld_abs", + .insns = { }, + .data = { + 10, 11, + }, + .fill_helper = bpf_fill_jump_around_ld_abs, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 10, + }, + { + "ld_dw: xor semi-random 64 bit imms, test 1", + .insns = { }, + .data = { }, + .fill_helper = bpf_fill_rand_ld_dw, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 4090, + }, + { + "ld_dw: xor semi-random 64 bit imms, test 2", + .insns = { }, + .data = { }, + .fill_helper = bpf_fill_rand_ld_dw, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 2047, + }, + { + "ld_dw: xor semi-random 64 bit imms, test 3", + .insns = { }, + .data = { }, + .fill_helper = bpf_fill_rand_ld_dw, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 511, + }, + { + "ld_dw: xor semi-random 64 bit imms, test 4", + .insns = { }, + .data = { }, + .fill_helper = bpf_fill_rand_ld_dw, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 5, + }, + { + "pass unmodified ctx pointer to helper", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_csum_update), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + }, + { + "pass modified ctx pointer to helper, 1", + .insns = { + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -612), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_csum_update), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "dereference of modified ctx ptr", + }, + { + "pass modified ctx pointer to helper, 2", + .insns = { + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -612), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_get_socket_cookie), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result_unpriv = REJECT, + .result = REJECT, + .errstr_unpriv = "dereference of modified ctx ptr", + .errstr = "dereference of modified ctx ptr", + }, + { + "pass modified ctx pointer to helper, 3", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_3, 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_csum_update), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "variable ctx access var_off=(0x0; 0x4)", + }, }; static int probe_filter_length(const struct bpf_insn *fp) @@ -11435,12 +12326,13 @@ static int probe_filter_length(const struct bpf_insn *fp) return len + 1; } -static int create_map(uint32_t size_value, uint32_t max_elem) +static int create_map(uint32_t type, uint32_t size_key, + uint32_t size_value, uint32_t max_elem) { int fd; - fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(long long), - size_value, max_elem, BPF_F_NO_PREALLOC); + fd = bpf_create_map(type, size_key, size_value, max_elem, + type == BPF_MAP_TYPE_HASH ? BPF_F_NO_PREALLOC : 0); if (fd < 0) printf("Failed to create hash map '%s'!\n", strerror(errno)); @@ -11473,13 +12365,13 @@ static int create_prog_dummy2(int mfd, int idx) ARRAY_SIZE(prog), "GPL", 0, NULL, 0); } -static int create_prog_array(void) +static int create_prog_array(uint32_t max_elem, int p1key) { - int p1key = 0, p2key = 1; + int p2key = 1; int mfd, p1fd, p2fd; mfd = bpf_create_map(BPF_MAP_TYPE_PROG_ARRAY, sizeof(int), - sizeof(int), 4, 0); + sizeof(int), max_elem, 0); if (mfd < 0) { printf("Failed to create prog array '%s'!\n", strerror(errno)); return -1; @@ -11526,22 +12418,29 @@ static int create_map_in_map(void) return outer_map_fd; } -static char bpf_vlog[32768]; +static char bpf_vlog[UINT_MAX >> 8]; static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog, int *map_fds) { int *fixup_map1 = test->fixup_map1; int *fixup_map2 = test->fixup_map2; - int *fixup_prog = test->fixup_prog; + int *fixup_map3 = test->fixup_map3; + int *fixup_map4 = test->fixup_map4; + int *fixup_prog1 = test->fixup_prog1; + int *fixup_prog2 = test->fixup_prog2; int *fixup_map_in_map = test->fixup_map_in_map; + if (test->fill_helper) + test->fill_helper(test); + /* Allocating HTs with 1 elem is fine here, since we only test * for verifier and not do a runtime lookup, so the only thing * that really matters is value size in this case. */ if (*fixup_map1) { - map_fds[0] = create_map(sizeof(long long), 1); + map_fds[0] = create_map(BPF_MAP_TYPE_HASH, sizeof(long long), + sizeof(long long), 1); do { prog[*fixup_map1].imm = map_fds[0]; fixup_map1++; @@ -11549,25 +12448,52 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog, } if (*fixup_map2) { - map_fds[1] = create_map(sizeof(struct test_val), 1); + map_fds[1] = create_map(BPF_MAP_TYPE_HASH, sizeof(long long), + sizeof(struct test_val), 1); do { prog[*fixup_map2].imm = map_fds[1]; fixup_map2++; } while (*fixup_map2); } - if (*fixup_prog) { - map_fds[2] = create_prog_array(); + if (*fixup_map3) { + map_fds[2] = create_map(BPF_MAP_TYPE_HASH, sizeof(long long), + sizeof(struct other_val), 1); + do { + prog[*fixup_map3].imm = map_fds[2]; + fixup_map3++; + } while (*fixup_map3); + } + + if (*fixup_map4) { + map_fds[3] = create_map(BPF_MAP_TYPE_ARRAY, sizeof(int), + sizeof(struct test_val), 1); + do { + prog[*fixup_map4].imm = map_fds[3]; + fixup_map4++; + } while (*fixup_map4); + } + + if (*fixup_prog1) { + map_fds[4] = create_prog_array(4, 0); + do { + prog[*fixup_prog1].imm = map_fds[4]; + fixup_prog1++; + } while (*fixup_prog1); + } + + if (*fixup_prog2) { + map_fds[5] = create_prog_array(8, 7); do { - prog[*fixup_prog].imm = map_fds[2]; - fixup_prog++; - } while (*fixup_prog); + prog[*fixup_prog2].imm = map_fds[5]; + fixup_prog2++; + } while (*fixup_prog2); } if (*fixup_map_in_map) { - map_fds[3] = create_map_in_map(); + map_fds[6] = create_map_in_map(); do { - prog[*fixup_map_in_map].imm = map_fds[3]; + prog[*fixup_map_in_map].imm = map_fds[6]; fixup_map_in_map++; } while (*fixup_map_in_map); } @@ -11577,10 +12503,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv, int *passes, int *errors) { int fd_prog, expected_ret, reject_from_alignment; + int prog_len, prog_type = test->prog_type; struct bpf_insn *prog = test->insns; - int prog_len = probe_filter_length(prog); - char data_in[TEST_DATA_LEN] = {}; - int prog_type = test->prog_type; int map_fds[MAX_NR_MAPS]; const char *expected_err; uint32_t retval; @@ -11590,6 +12514,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv, map_fds[i] = -1; do_test_fixup(test, prog, map_fds); + prog_len = probe_filter_length(prog); fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER, prog, prog_len, test->flags & F_LOAD_WITH_STRICT_ALIGNMENT, @@ -11629,8 +12554,9 @@ static void do_test_single(struct bpf_test *test, bool unpriv, } if (fd_prog >= 0) { - err = bpf_prog_test_run(fd_prog, 1, data_in, sizeof(data_in), - NULL, NULL, &retval, NULL); + err = bpf_prog_test_run(fd_prog, 1, test->data, + sizeof(test->data), NULL, NULL, + &retval, NULL); if (err && errno != 524/*ENOTSUPP*/ && errno != EPERM) { printf("Unexpected bpf_prog_test_run error\n"); goto fail_log; @@ -11788,5 +12714,6 @@ int main(int argc, char **argv) return EXIT_FAILURE; } + bpf_semi_rand_init(); return do_test(unpriv, from, to); } diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c new file mode 100644 index 0000000..3868dcb --- /dev/null +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -0,0 +1,165 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <assert.h> +#include <errno.h> +#include <poll.h> +#include <unistd.h> +#include <linux/perf_event.h> +#include <sys/mman.h> +#include "trace_helpers.h" + +#define MAX_SYMS 300000 +static struct ksym syms[MAX_SYMS]; +static int sym_cnt; + +static int ksym_cmp(const void *p1, const void *p2) +{ + return ((struct ksym *)p1)->addr - ((struct ksym *)p2)->addr; +} + +int load_kallsyms(void) +{ + FILE *f = fopen("/proc/kallsyms", "r"); + char func[256], buf[256]; + char symbol; + void *addr; + int i = 0; + + if (!f) + return -ENOENT; + + while (!feof(f)) { + if (!fgets(buf, sizeof(buf), f)) + break; + if (sscanf(buf, "%p %c %s", &addr, &symbol, func) != 3) + break; + if (!addr) + continue; + syms[i].addr = (long) addr; + syms[i].name = strdup(func); + i++; + } + sym_cnt = i; + qsort(syms, sym_cnt, sizeof(struct ksym), ksym_cmp); + return 0; +} + +struct ksym *ksym_search(long key) +{ + int start = 0, end = sym_cnt; + int result; + + while (start < end) { + size_t mid = start + (end - start) / 2; + + result = key - syms[mid].addr; + if (result < 0) + end = mid; + else if (result > 0) + start = mid + 1; + else + return &syms[mid]; + } + + if (start >= 1 && syms[start - 1].addr < key && + key < syms[start].addr) + /* valid ksym */ + return &syms[start - 1]; + + /* out of range. return _stext */ + return &syms[0]; +} + +long ksym_get_addr(const char *name) +{ + int i; + + for (i = 0; i < sym_cnt; i++) { + if (strcmp(syms[i].name, name) == 0) + return syms[i].addr; + } + + return 0; +} + +static int page_size; +static int page_cnt = 8; +static struct perf_event_mmap_page *header; + +int perf_event_mmap(int fd) +{ + void *base; + int mmap_size; + + page_size = getpagesize(); + mmap_size = page_size * (page_cnt + 1); + + base = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + if (base == MAP_FAILED) { + printf("mmap err\n"); + return -1; + } + + header = base; + return 0; +} + +static int perf_event_poll(int fd) +{ + struct pollfd pfd = { .fd = fd, .events = POLLIN }; + + return poll(&pfd, 1, 1000); +} + +struct perf_event_sample { + struct perf_event_header header; + __u32 size; + char data[]; +}; + +static enum bpf_perf_event_ret bpf_perf_event_print(void *event, void *priv) +{ + struct perf_event_sample *e = event; + perf_event_print_fn fn = priv; + int ret; + + if (e->header.type == PERF_RECORD_SAMPLE) { + ret = fn(e->data, e->size); + if (ret != LIBBPF_PERF_EVENT_CONT) + return ret; + } else if (e->header.type == PERF_RECORD_LOST) { + struct { + struct perf_event_header header; + __u64 id; + __u64 lost; + } *lost = (void *) e; + printf("lost %lld events\n", lost->lost); + } else { + printf("unknown event type=%d size=%d\n", + e->header.type, e->header.size); + } + + return LIBBPF_PERF_EVENT_CONT; +} + +int perf_event_poller(int fd, perf_event_print_fn output_fn) +{ + enum bpf_perf_event_ret ret; + void *buf = NULL; + size_t len = 0; + + for (;;) { + perf_event_poll(fd); + ret = bpf_perf_event_read_simple(header, page_cnt * page_size, + page_size, &buf, &len, + bpf_perf_event_print, + output_fn); + if (ret != LIBBPF_PERF_EVENT_CONT) + break; + } + free(buf); + + return ret; +} diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h new file mode 100644 index 0000000..3b4bcf7 --- /dev/null +++ b/tools/testing/selftests/bpf/trace_helpers.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __TRACE_HELPER_H +#define __TRACE_HELPER_H + +#include <libbpf.h> + +struct ksym { + long addr; + char *name; +}; + +int load_kallsyms(void); +struct ksym *ksym_search(long key); +long ksym_get_addr(const char *name); + +typedef enum bpf_perf_event_ret (*perf_event_print_fn)(void *data, int size); + +int perf_event_mmap(int fd); +/* return LIBBPF_PERF_EVENT_DONE or LIBBPF_PERF_EVENT_ERROR */ +int perf_event_poller(int fd, perf_event_print_fn output_fn); +#endif diff --git a/tools/testing/selftests/bpf/urandom_read.c b/tools/testing/selftests/bpf/urandom_read.c index 4acfdeb..9de8b7c 100644 --- a/tools/testing/selftests/bpf/urandom_read.c +++ b/tools/testing/selftests/bpf/urandom_read.c @@ -6,15 +6,21 @@ #include <stdlib.h> #define BUF_SIZE 256 -int main(void) + +int main(int argc, char *argv[]) { int fd = open("/dev/urandom", O_RDONLY); int i; char buf[BUF_SIZE]; + int count = 4; if (fd < 0) return 1; - for (i = 0; i < 4; ++i) + + if (argc == 2) + count = atoi(argv[1]); + + for (i = 0; i < count; ++i) read(fd, buf, BUF_SIZE); close(fd); diff --git a/tools/testing/selftests/drivers/usb/usbip/usbip_test.sh b/tools/testing/selftests/drivers/usb/usbip/usbip_test.sh new file mode 100755 index 0000000..1893d0f --- /dev/null +++ b/tools/testing/selftests/drivers/usb/usbip/usbip_test.sh @@ -0,0 +1,198 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +usage() { echo "usbip_test.sh -b <busid> -p <usbip tools path>"; exit 1; } + +while getopts "h:b:p:" arg; do + case "${arg}" in + h) + usage + ;; + b) + busid=${OPTARG} + ;; + p) + tools_path=${OPTARG} + ;; + *) + usage + ;; + esac +done +shift $((OPTIND-1)) + +if [ -z "${busid}" ]; then + usage +fi + +echo "Running USB over IP Testing on $busid"; + +test_end_msg="End of USB over IP Testing on $busid" + +if [ $UID != 0 ]; then + echo "Please run usbip_test as root [SKIP]" + echo $test_end_msg + exit $ksft_skip +fi + +echo "Load usbip_host module" +if ! /sbin/modprobe -q -n usbip_host; then + echo "usbip_test: module usbip_host is not found [SKIP]" + echo $test_end_msg + exit $ksft_skip +fi + +if /sbin/modprobe -q usbip_host; then + /sbin/modprobe -q -r test_bitmap + echo "usbip_test: module usbip_host is loaded [OK]" +else + echo "usbip_test: module usbip_host failed to load [FAIL]" + echo $test_end_msg + exit 1 +fi + +echo "Load vhci_hcd module" +if /sbin/modprobe -q vhci_hcd; then + /sbin/modprobe -q -r test_bitmap + echo "usbip_test: module vhci_hcd is loaded [OK]" +else + echo "usbip_test: module vhci_hcd failed to load [FAIL]" + echo $test_end_msg + exit 1 +fi +echo "==============================================================" + +cd $tools_path; + +if [ ! -f src/usbip ]; then + echo "Please build usbip tools" + echo $test_end_msg + exit $ksft_skip +fi + +echo "Expect to see export-able devices"; +src/usbip list -l; +echo "==============================================================" + +echo "Run lsusb to see all usb devices" +lsusb -t; +echo "==============================================================" + +src/usbipd -D; + +echo "Get exported devices from localhost - expect to see none"; +src/usbip list -r localhost; +echo "==============================================================" + +echo "bind devices"; +src/usbip bind -b $busid; +echo "==============================================================" + +echo "Run lsusb - bound devices should be under usbip_host control" +lsusb -t; +echo "==============================================================" + +echo "bind devices - expect already bound messages" +src/usbip bind -b $busid; +echo "==============================================================" + +echo "Get exported devices from localhost - expect to see exported devices"; +src/usbip list -r localhost; +echo "==============================================================" + +echo "unbind devices"; +src/usbip unbind -b $busid; +echo "==============================================================" + +echo "Run lsusb - bound devices should be rebound to original drivers" +lsusb -t; +echo "==============================================================" + +echo "unbind devices - expect no devices bound message"; +src/usbip unbind -b $busid; +echo "==============================================================" + +echo "Get exported devices from localhost - expect to see none"; +src/usbip list -r localhost; +echo "==============================================================" + +echo "List imported devices - expect to see none"; +src/usbip port; +echo "==============================================================" + +echo "Import devices from localhost - should fail with no devices" +src/usbip attach -r localhost -b $busid; +echo "==============================================================" + +echo "bind devices"; +src/usbip bind -b $busid; +echo "==============================================================" + +echo "List imported devices - expect to see exported devices"; +src/usbip list -r localhost; +echo "==============================================================" + +echo "List imported devices - expect to see none"; +src/usbip port; +echo "==============================================================" + +echo "Import devices from localhost - should work" +src/usbip attach -r localhost -b $busid; +echo "==============================================================" + +echo "List imported devices - expect to see imported devices"; +src/usbip port; +echo "==============================================================" + +echo "Import devices from localhost - expect already imported messages" +src/usbip attach -r localhost -b $busid; +echo "==============================================================" + +echo "Un-import devices"; +src/usbip detach -p 00; +src/usbip detach -p 01; +echo "==============================================================" + +echo "List imported devices - expect to see none"; +src/usbip port; +echo "==============================================================" + +echo "Un-import devices - expect no devices to detach messages"; +src/usbip detach -p 00; +src/usbip detach -p 01; +echo "==============================================================" + +echo "Detach invalid port tests - expect invalid port error message"; +src/usbip detach -p 100; +echo "==============================================================" + +echo "Expect to see export-able devices"; +src/usbip list -l; +echo "==============================================================" + +echo "Remove usbip_host module"; +rmmod usbip_host; + +echo "Run lsusb - bound devices should be rebound to original drivers" +lsusb -t; +echo "==============================================================" + +echo "Run bind without usbip_host - expect fail" +src/usbip bind -b $busid; +echo "==============================================================" + +echo "Run lsusb - devices that failed to bind aren't bound to any driver" +lsusb -t; +echo "==============================================================" + +echo "modprobe usbip_host - does it work?" +/sbin/modprobe usbip_host +echo "Should see -busid- is not in match_busid table... skip! dmesg" +echo "==============================================================" +dmesg | grep "is not in match_busid table" +echo "==============================================================" + +echo $test_end_msg diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions index 2a4f16f..e4645d5 100644 --- a/tools/testing/selftests/ftrace/test.d/functions +++ b/tools/testing/selftests/ftrace/test.d/functions @@ -15,14 +15,29 @@ reset_tracer() { # reset the current tracer echo nop > current_tracer } -reset_trigger() { # reset all current setting triggers - grep -v ^# events/*/*/trigger | +reset_trigger_file() { + # remove action triggers first + grep -H ':on[^:]*(' $@ | + while read line; do + cmd=`echo $line | cut -f2- -d: | cut -f1 -d"["` + file=`echo $line | cut -f1 -d:` + echo "!$cmd" >> $file + done + grep -Hv ^# $@ | while read line; do - cmd=`echo $line | cut -f2- -d: | cut -f1 -d" "` - echo "!$cmd" > `echo $line | cut -f1 -d:` + cmd=`echo $line | cut -f2- -d: | cut -f1 -d"["` + file=`echo $line | cut -f1 -d:` + echo "!$cmd" > $file done } +reset_trigger() { # reset all current setting triggers + if [ -d events/synthetic ]; then + reset_trigger_file events/synthetic/*/trigger + fi + reset_trigger_file events/*/*/trigger +} + reset_events_filter() { # reset all current setting filters grep -v ^none events/*/*/filter | while read line; do diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-hist.tc new file mode 100644 index 0000000..2acbfe2 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-hist.tc @@ -0,0 +1,49 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: trace_marker trigger - test histogram trigger +# flags: instance + +do_reset() { + reset_trigger + echo > set_event + clear_trace +} + +fail() { #msg + do_reset + echo $1 + exit_fail +} + +if [ ! -f set_event ]; then + echo "event tracing is not supported" + exit_unsupported +fi + +if [ ! -d events/ftrace/print ]; then + echo "event trace_marker is not supported" + exit_unsupported +fi + +if [ ! -f events/ftrace/print/trigger ]; then + echo "event trigger is not supported" + exit_unsupported +fi + +if [ ! -f events/ftrace/print/hist ]; then + echo "hist trigger is not supported" + exit_unsupported +fi + +do_reset + +echo "Test histogram trace_marker tigger" + +echo 'hist:keys=common_pid' > events/ftrace/print/trigger +for i in `seq 1 10` ; do echo "hello" > trace_marker; done +grep 'hitcount: *10$' events/ftrace/print/hist > /dev/null || \ + fail "hist trigger did not trigger correct times on trace_marker" + +do_reset + +exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc new file mode 100644 index 0000000..6748e8c --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc @@ -0,0 +1,74 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: trace_marker trigger - test snapshot trigger +# flags: instance + +do_reset() { + reset_trigger + echo > set_event + echo 0 > snapshot + clear_trace +} + +fail() { #msg + do_reset + echo $1 + exit_fail +} + +if [ ! -f set_event ]; then + echo "event tracing is not supported" + exit_unsupported +fi + +if [ ! -f snapshot ]; then + echo "snapshot is not supported" + exit_unsupported +fi + +if [ ! -d events/ftrace/print ]; then + echo "event trace_marker is not supported" + exit_unsupported +fi + +if [ ! -f events/ftrace/print/trigger ]; then + echo "event trigger is not supported" + exit_unsupported +fi + +test_trace() { + file=$1 + x=$2 + + cat $file | while read line; do + comment=`echo $line | sed -e 's/^#//'` + if [ "$line" != "$comment" ]; then + continue + fi + echo "testing $line for >$x<" + match=`echo $line | sed -e "s/>$x<//"` + if [ "$line" == "$match" ]; then + fail "$line does not have >$x< in it" + fi + let x=$x+2 + done +} + +do_reset + +echo "Test snapshot trace_marker tigger" + +echo 'snapshot' > events/ftrace/print/trigger + +# make sure the snapshot is allocated + +grep -q 'Snapshot is allocated' snapshot + +for i in `seq 1 10` ; do echo "hello >$i<" > trace_marker; done + +test_trace trace 1 +test_trace snapshot 2 + +do_reset + +exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic-kernel.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic-kernel.tc new file mode 100644 index 0000000..0a69c5d --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic-kernel.tc @@ -0,0 +1,68 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: trace_marker trigger - test histogram with synthetic event against kernel event +# flags: + +do_reset() { + reset_trigger + echo > set_event + echo > synthetic_events + clear_trace +} + +fail() { #msg + do_reset + echo $1 + exit_fail +} + +if [ ! -f set_event ]; then + echo "event tracing is not supported" + exit_unsupported +fi + +if [ ! -f synthetic_events ]; then + echo "synthetic events not supported" + exit_unsupported +fi + +if [ ! -d events/ftrace/print ]; then + echo "event trace_marker is not supported" + exit_unsupported +fi + +if [ ! -d events/sched/sched_waking ]; then + echo "event sched_waking is not supported" + exit_unsupported +fi + +if [ ! -f events/ftrace/print/trigger ]; then + echo "event trigger is not supported" + exit_unsupported +fi + +if [ ! -f events/ftrace/print/hist ]; then + echo "hist trigger is not supported" + exit_unsupported +fi + +do_reset + +echo "Test histogram kernel event to trace_marker latency histogram trigger" + +echo 'latency u64 lat' > synthetic_events +echo 'hist:keys=pid:ts0=common_timestamp.usecs' > events/sched/sched_waking/trigger +echo 'hist:keys=common_pid:lat=common_timestamp.usecs-$ts0:onmatch(sched.sched_waking).latency($lat)' > events/ftrace/print/trigger +echo 'hist:keys=common_pid,lat:sort=lat' > events/synthetic/latency/trigger +sleep 1 +echo "hello" > trace_marker + +grep 'hitcount: *1$' events/ftrace/print/hist > /dev/null || \ + fail "hist trigger did not trigger correct times on trace_marker" + +grep 'hitcount: *1$' events/synthetic/latency/hist > /dev/null || \ + fail "hist trigger did not trigger " + +do_reset + +exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic.tc new file mode 100644 index 0000000..3666dd6 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic.tc @@ -0,0 +1,66 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: trace_marker trigger - test histogram with synthetic event +# flags: + +do_reset() { + reset_trigger + echo > set_event + echo > synthetic_events + clear_trace +} + +fail() { #msg + do_reset + echo $1 + exit_fail +} + +if [ ! -f set_event ]; then + echo "event tracing is not supported" + exit_unsupported +fi + +if [ ! -f synthetic_events ]; then + echo "synthetic events not supported" + exit_unsupported +fi + +if [ ! -d events/ftrace/print ]; then + echo "event trace_marker is not supported" + exit_unsupported +fi + +if [ ! -f events/ftrace/print/trigger ]; then + echo "event trigger is not supported" + exit_unsupported +fi + +if [ ! -f events/ftrace/print/hist ]; then + echo "hist trigger is not supported" + exit_unsupported +fi + +do_reset + +echo "Test histogram trace_marker to trace_marker latency histogram trigger" + +echo 'latency u64 lat' > synthetic_events +echo 'hist:keys=common_pid:ts0=common_timestamp.usecs if buf == "start"' > events/ftrace/print/trigger +echo 'hist:keys=common_pid:lat=common_timestamp.usecs-$ts0:onmatch(ftrace.print).latency($lat) if buf == "end"' >> events/ftrace/print/trigger +echo 'hist:keys=common_pid,lat:sort=lat' > events/synthetic/latency/trigger +echo -n "start" > trace_marker +echo -n "end" > trace_marker + +cnt=`grep 'hitcount: *1$' events/ftrace/print/hist | wc -l` + +if [ $cnt -ne 2 ]; then + fail "hist trace_marker trigger did not trigger correctly" +fi + +grep 'hitcount: *1$' events/synthetic/latency/hist > /dev/null || \ + fail "hist trigger did not trigger " + +do_reset + +exit 0 diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 6466294..17ab366 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -133,6 +133,9 @@ COMPILE.S = $(CC) $(ASFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c LINK.S = $(CC) $(ASFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) endif +# Selftest makefiles can override those targets by setting +# OVERRIDE_TARGETS = 1. +ifeq ($(OVERRIDE_TARGETS),) $(OUTPUT)/%:%.c $(LINK.c) $^ $(LDLIBS) -o $@ @@ -141,5 +144,6 @@ $(OUTPUT)/%.o:%.S $(OUTPUT)/%:%.S $(LINK.S) $^ $(LDLIBS) -o $@ +endif .PHONY: run_tests all clean install emit_tests diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index c612d6e..128e548 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -1,9 +1,14 @@ msg_zerocopy socket psock_fanout +psock_snd psock_tpacket reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa reuseport_dualstack reuseaddr_conflict +tcp_mmap +udpgso +udpgso_bench_rx +udpgso_bench_tx diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 3ff81a4..663e11e 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -5,13 +5,18 @@ CFLAGS = -Wall -Wl,--no-as-needed -O2 -g CFLAGS += -I../../../../usr/include/ TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh -TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh +TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh +TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh TEST_PROGS_EXTENDED := in_netns.sh TEST_GEN_FILES = socket TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy +TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd +TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict include ../lib.mk $(OUTPUT)/reuseport_bpf_numa: LDFLAGS += -lnuma +$(OUTPUT)/tcp_mmap: LDFLAGS += -lpthread +$(OUTPUT)/tcp_inq: LDFLAGS += -lpthread diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh new file mode 100755 index 0000000..d4cfb6a --- /dev/null +++ b/tools/testing/selftests/net/fib_rule_tests.sh @@ -0,0 +1,248 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test is for checking IPv4 and IPv6 FIB rules API + +ret=0 + +PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no} +IP="ip -netns testns" + +RTABLE=100 +GW_IP4=192.51.100.2 +SRC_IP=192.51.100.3 +GW_IP6=2001:db8:1::2 +SRC_IP6=2001:db8:1::3 + +DEV_ADDR=192.51.100.1 +DEV=dummy0 + +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + nsuccess=$((nsuccess+1)) + printf "\n TEST: %-50s [ OK ]\n" "${msg}" + else + nfail=$((nfail+1)) + printf "\n TEST: %-50s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi +} + +log_section() +{ + echo + echo "######################################################################" + echo "TEST SECTION: $*" + echo "######################################################################" +} + +setup() +{ + set -e + ip netns add testns + $IP link set dev lo up + + $IP link add dummy0 type dummy + $IP link set dev dummy0 up + $IP address add 198.51.100.1/24 dev dummy0 + $IP -6 address add 2001:db8:1::1/64 dev dummy0 + + set +e +} + +cleanup() +{ + $IP link del dev dummy0 &> /dev/null + ip netns del testns +} + +fib_check_iproute_support() +{ + ip rule help 2>&1 | grep -q $1 + if [ $? -ne 0 ]; then + echo "SKIP: iproute2 iprule too old, missing $1 match" + return 1 + fi + + ip route get help 2>&1 | grep -q $2 + if [ $? -ne 0 ]; then + echo "SKIP: iproute2 get route too old, missing $2 match" + return 1 + fi + + return 0 +} + +fib_rule6_del() +{ + $IP -6 rule del $1 + log_test $? 0 "rule6 del $1" +} + +fib_rule6_del_by_pref() +{ + pref=$($IP -6 rule show | grep "$1 lookup $TABLE" | cut -d ":" -f 1) + $IP -6 rule del pref $pref +} + +fib_rule6_test_match_n_redirect() +{ + local match="$1" + local getmatch="$2" + + $IP -6 rule add $match table $RTABLE + $IP -6 route get $GW_IP6 $getmatch | grep -q "table $RTABLE" + log_test $? 0 "rule6 check: $1" + + fib_rule6_del_by_pref "$match" + log_test $? 0 "rule6 del by pref: $match" +} + +fib_rule6_test() +{ + # setup the fib rule redirect route + $IP -6 route add table $RTABLE default via $GW_IP6 dev $DEV onlink + + match="oif $DEV" + fib_rule6_test_match_n_redirect "$match" "$match" "oif redirect to table" + + match="from $SRC_IP6 iif $DEV" + fib_rule6_test_match_n_redirect "$match" "$match" "iif redirect to table" + + match="tos 0x10" + fib_rule6_test_match_n_redirect "$match" "$match" "tos redirect to table" + + match="fwmark 0x64" + getmatch="mark 0x64" + fib_rule6_test_match_n_redirect "$match" "$getmatch" "fwmark redirect to table" + + fib_check_iproute_support "uidrange" "uid" + if [ $? -eq 0 ]; then + match="uidrange 100-100" + getmatch="uid 100" + fib_rule6_test_match_n_redirect "$match" "$getmatch" "uid redirect to table" + fi + + fib_check_iproute_support "sport" "sport" + if [ $? -eq 0 ]; then + match="sport 666 dport 777" + fib_rule6_test_match_n_redirect "$match" "$match" "sport and dport redirect to table" + fi + + fib_check_iproute_support "ipproto" "ipproto" + if [ $? -eq 0 ]; then + match="ipproto tcp" + fib_rule6_test_match_n_redirect "$match" "$match" "ipproto match" + fi + + fib_check_iproute_support "ipproto" "ipproto" + if [ $? -eq 0 ]; then + match="ipproto icmp" + fib_rule6_test_match_n_redirect "$match" "$match" "ipproto icmp match" + fi +} + +fib_rule4_del() +{ + $IP rule del $1 + log_test $? 0 "del $1" +} + +fib_rule4_del_by_pref() +{ + pref=$($IP rule show | grep "$1 lookup $TABLE" | cut -d ":" -f 1) + $IP rule del pref $pref +} + +fib_rule4_test_match_n_redirect() +{ + local match="$1" + local getmatch="$2" + + $IP rule add $match table $RTABLE + $IP route get $GW_IP4 $getmatch | grep -q "table $RTABLE" + log_test $? 0 "rule4 check: $1" + + fib_rule4_del_by_pref "$match" + log_test $? 0 "rule4 del by pref: $match" +} + +fib_rule4_test() +{ + # setup the fib rule redirect route + $IP route add table $RTABLE default via $GW_IP4 dev $DEV onlink + + match="oif $DEV" + fib_rule4_test_match_n_redirect "$match" "$match" "oif redirect to table" + + match="from $SRC_IP iif $DEV" + fib_rule4_test_match_n_redirect "$match" "$match" "iif redirect to table" + + match="tos 0x10" + fib_rule4_test_match_n_redirect "$match" "$match" "tos redirect to table" + + match="fwmark 0x64" + getmatch="mark 0x64" + fib_rule4_test_match_n_redirect "$match" "$getmatch" "fwmark redirect to table" + + fib_check_iproute_support "uidrange" "uid" + if [ $? -eq 0 ]; then + match="uidrange 100-100" + getmatch="uid 100" + fib_rule4_test_match_n_redirect "$match" "$getmatch" "uid redirect to table" + fi + + fib_check_iproute_support "sport" "sport" + if [ $? -eq 0 ]; then + match="sport 666 dport 777" + fib_rule4_test_match_n_redirect "$match" "$match" "sport and dport redirect to table" + fi + + fib_check_iproute_support "ipproto" "ipproto" + if [ $? -eq 0 ]; then + match="ipproto tcp" + fib_rule4_test_match_n_redirect "$match" "$match" "ipproto tcp match" + fi + + fib_check_iproute_support "ipproto" "ipproto" + if [ $? -eq 0 ]; then + match="ipproto icmp" + fib_rule4_test_match_n_redirect "$match" "$match" "ipproto icmp match" + fi +} + +run_fibrule_tests() +{ + log_section "IPv4 fib rule" + fib_rule4_test + log_section "IPv6 fib rule" + fib_rule6_test +} + +if [ "$(id -u)" -ne 0 ];then + echo "SKIP: Need root privileges" + exit 0 +fi + +if [ ! -x "$(command -v ip)" ]; then + echo "SKIP: Could not run test without ip tool" + exit 0 +fi + +# start clean +cleanup &> /dev/null +setup +run_fibrule_tests +cleanup + +exit $ret diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 5baac82..78245d6 100755..100644 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -8,8 +8,11 @@ ret=0 # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 -VERBOSE=${VERBOSE:=0} -PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no} +# all tests in this script. Can be overridden with -t option +TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric" +VERBOSE=0 +PAUSE_ON_FAIL=no +PAUSE=no IP="ip -netns testns" log_test() @@ -20,8 +23,10 @@ log_test() if [ ${rc} -eq ${expected} ]; then printf " TEST: %-60s [ OK ]\n" "${msg}" + nsuccess=$((nsuccess+1)) else ret=1 + nfail=$((nfail+1)) printf " TEST: %-60s [FAIL]\n" "${msg}" if [ "${PAUSE_ON_FAIL}" = "yes" ]; then echo @@ -30,6 +35,13 @@ log_test() [ "$a" = "q" ] && exit 1 fi fi + + if [ "${PAUSE}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi } setup() @@ -565,20 +577,825 @@ fib_nexthop_test() } ################################################################################ -# +# Tests on route add and replace + +run_cmd() +{ + local cmd="$1" + local out + local stderr="2>/dev/null" + + if [ "$VERBOSE" = "1" ]; then + printf " COMMAND: $cmd\n" + stderr= + fi + + out=$(eval $cmd $stderr) + rc=$? + if [ "$VERBOSE" = "1" -a -n "$out" ]; then + echo " $out" + fi + + [ "$VERBOSE" = "1" ] && echo + + return $rc +} + +# add route for a prefix, flushing any existing routes first +# expected to be the first step of a test +add_route6() +{ + local pfx="$1" + local nh="$2" + local out + + if [ "$VERBOSE" = "1" ]; then + echo + echo " ##################################################" + echo + fi + + run_cmd "$IP -6 ro flush ${pfx}" + [ $? -ne 0 ] && exit 1 + + out=$($IP -6 ro ls match ${pfx}) + if [ -n "$out" ]; then + echo "Failed to flush routes for prefix used for tests." + exit 1 + fi + + run_cmd "$IP -6 ro add ${pfx} ${nh}" + if [ $? -ne 0 ]; then + echo "Failed to add initial route for test." + exit 1 + fi +} + +# add initial route - used in replace route tests +add_initial_route6() +{ + add_route6 "2001:db8:104::/64" "$1" +} + +check_route6() +{ + local pfx="2001:db8:104::/64" + local expected="$1" + local out + local rc=0 + + out=$($IP -6 ro ls match ${pfx} | sed -e 's/ pref medium//') + [ "${out}" = "${expected}" ] && return 0 + + if [ -z "${out}" ]; then + if [ "$VERBOSE" = "1" ]; then + printf "\nNo route entry found\n" + printf "Expected:\n" + printf " ${expected}\n" + fi + return 1 + fi + + # tricky way to convert output to 1-line without ip's + # messy '\'; this drops all extra white space + out=$(echo ${out}) + if [ "${out}" != "${expected}" ]; then + rc=1 + if [ "${VERBOSE}" = "1" ]; then + printf " Unexpected route entry. Have:\n" + printf " ${out}\n" + printf " Expected:\n" + printf " ${expected}\n\n" + fi + fi + + return $rc +} + +route_cleanup() +{ + $IP li del red 2>/dev/null + $IP li del dummy1 2>/dev/null + $IP li del veth1 2>/dev/null + $IP li del veth3 2>/dev/null + + cleanup &> /dev/null +} + +route_setup() +{ + route_cleanup + setup + + [ "${VERBOSE}" = "1" ] && set -x + set -e + + $IP li add red up type vrf table 101 + $IP li add veth1 type veth peer name veth2 + $IP li add veth3 type veth peer name veth4 + + $IP li set veth1 up + $IP li set veth3 up + $IP li set veth2 vrf red up + $IP li set veth4 vrf red up + $IP li add dummy1 type dummy + $IP li set dummy1 vrf red up + + $IP -6 addr add 2001:db8:101::1/64 dev veth1 + $IP -6 addr add 2001:db8:101::2/64 dev veth2 + $IP -6 addr add 2001:db8:103::1/64 dev veth3 + $IP -6 addr add 2001:db8:103::2/64 dev veth4 + $IP -6 addr add 2001:db8:104::1/64 dev dummy1 + + $IP addr add 172.16.101.1/24 dev veth1 + $IP addr add 172.16.101.2/24 dev veth2 + $IP addr add 172.16.103.1/24 dev veth3 + $IP addr add 172.16.103.2/24 dev veth4 + $IP addr add 172.16.104.1/24 dev dummy1 + + set +ex +} + +# assumption is that basic add of a single path route works +# otherwise just adding an address on an interface is broken +ipv6_rt_add() +{ + local rc + + echo + echo "IPv6 route add / append tests" + + # route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL + add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" + run_cmd "$IP -6 ro add 2001:db8:104::/64 via 2001:db8:103::2" + log_test $? 2 "Attempt to add duplicate route - gw" + + # route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL + add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" + run_cmd "$IP -6 ro add 2001:db8:104::/64 dev veth3" + log_test $? 2 "Attempt to add duplicate route - dev only" + + # route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL + add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" + run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64" + log_test $? 2 "Attempt to add duplicate route - reject route" + + # iproute2 prepend only sets NLM_F_CREATE + # - adds a new route; does NOT convert existing route to ECMP + add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" + run_cmd "$IP -6 ro prepend 2001:db8:104::/64 via 2001:db8:103::2" + check_route6 "2001:db8:104::/64 via 2001:db8:101::2 dev veth1 metric 1024 2001:db8:104::/64 via 2001:db8:103::2 dev veth3 metric 1024" + log_test $? 0 "Add new route for existing prefix (w/o NLM_F_EXCL)" + + # route append with same prefix adds a new route + # - iproute2 sets NLM_F_CREATE | NLM_F_APPEND + add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" + run_cmd "$IP -6 ro append 2001:db8:104::/64 via 2001:db8:103::2" + check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" + log_test $? 0 "Append nexthop to existing route - gw" + + add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" + run_cmd "$IP -6 ro append 2001:db8:104::/64 dev veth3" + check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop dev veth3 weight 1" + log_test $? 0 "Append nexthop to existing route - dev only" + + # multipath route can not have a nexthop that is a reject route + add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" + run_cmd "$IP -6 ro append unreachable 2001:db8:104::/64" + log_test $? 2 "Append nexthop to existing route - reject route" + + # reject route can not be converted to multipath route + run_cmd "$IP -6 ro flush 2001:db8:104::/64" + run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64" + run_cmd "$IP -6 ro append 2001:db8:104::/64 via 2001:db8:103::2" + log_test $? 2 "Append nexthop to existing reject route - gw" + + run_cmd "$IP -6 ro flush 2001:db8:104::/64" + run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64" + run_cmd "$IP -6 ro append 2001:db8:104::/64 dev veth3" + log_test $? 2 "Append nexthop to existing reject route - dev only" + + # insert mpath directly + add_route6 "2001:db8:104::/64" "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" + log_test $? 0 "Add multipath route" + + add_route6 "2001:db8:104::/64" "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro add 2001:db8:104::/64 nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + log_test $? 2 "Attempt to add duplicate multipath route" + + # insert of a second route without append but different metric + add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" + run_cmd "$IP -6 ro add 2001:db8:104::/64 via 2001:db8:103::2 metric 512" + rc=$? + if [ $rc -eq 0 ]; then + run_cmd "$IP -6 ro add 2001:db8:104::/64 via 2001:db8:103::3 metric 256" + rc=$? + fi + log_test $rc 0 "Route add with different metrics" + + run_cmd "$IP -6 ro del 2001:db8:104::/64 metric 512" + rc=$? + if [ $rc -eq 0 ]; then + check_route6 "2001:db8:104::/64 via 2001:db8:103::3 dev veth3 metric 256 2001:db8:104::/64 via 2001:db8:101::2 dev veth1 metric 1024" + rc=$? + fi + log_test $rc 0 "Route delete with metric" +} -fib_test() +ipv6_rt_replace_single() { - if [ -n "$TEST" ]; then - eval $TEST + # single path with single path + # + add_initial_route6 "via 2001:db8:101::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 via 2001:db8:103::2" + check_route6 "2001:db8:104::/64 via 2001:db8:103::2 dev veth3 metric 1024" + log_test $? 0 "Single path with single path" + + # single path with multipath + # + add_initial_route6 "nexthop via 2001:db8:101::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:101::3 nexthop via 2001:db8:103::2" + check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::3 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" + log_test $? 0 "Single path with multipath" + + # single path with reject + # + add_initial_route6 "nexthop via 2001:db8:101::2" + run_cmd "$IP -6 ro replace unreachable 2001:db8:104::/64" + check_route6 "unreachable 2001:db8:104::/64 dev lo metric 1024" + log_test $? 0 "Single path with reject route" + + # single path with single path using MULTIPATH attribute + # + add_initial_route6 "via 2001:db8:101::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:103::2" + check_route6 "2001:db8:104::/64 via 2001:db8:103::2 dev veth3 metric 1024" + log_test $? 0 "Single path with single path via multipath attribute" + + # route replace fails - invalid nexthop + add_initial_route6 "via 2001:db8:101::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 via 2001:db8:104::2" + if [ $? -eq 0 ]; then + # previous command is expected to fail so if it returns 0 + # that means the test failed. + log_test 0 1 "Invalid nexthop" else - fib_unreg_test - fib_down_test - fib_carrier_test - fib_nexthop_test + check_route6 "2001:db8:104::/64 via 2001:db8:101::2 dev veth1 metric 1024" + log_test $? 0 "Invalid nexthop" fi + + # replace non-existent route + # - note use of change versus replace since ip adds NLM_F_CREATE + # for replace + add_initial_route6 "via 2001:db8:101::2" + run_cmd "$IP -6 ro change 2001:db8:105::/64 via 2001:db8:101::2" + log_test $? 2 "Single path - replace of non-existent route" +} + +ipv6_rt_replace_mpath() +{ + # multipath with multipath + add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:101::3 nexthop via 2001:db8:103::3" + check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::3 dev veth1 weight 1 nexthop via 2001:db8:103::3 dev veth3 weight 1" + log_test $? 0 "Multipath with multipath" + + # multipath with single + add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 via 2001:db8:101::3" + check_route6 "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024" + log_test $? 0 "Multipath with single path" + + # multipath with single + add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:101::3" + check_route6 "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024" + log_test $? 0 "Multipath with single path via multipath attribute" + + # multipath with reject + add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro replace unreachable 2001:db8:104::/64" + check_route6 "unreachable 2001:db8:104::/64 dev lo metric 1024" + log_test $? 0 "Multipath with reject route" + + # route replace fails - invalid nexthop 1 + add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:111::3 nexthop via 2001:db8:103::3" + check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" + log_test $? 0 "Multipath - invalid first nexthop" + + # route replace fails - invalid nexthop 2 + add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:101::3 nexthop via 2001:db8:113::3" + check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" + log_test $? 0 "Multipath - invalid second nexthop" + + # multipath non-existent route + add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro change 2001:db8:105::/64 nexthop via 2001:db8:101::3 nexthop via 2001:db8:103::3" + log_test $? 2 "Multipath - replace of non-existent route" +} + +ipv6_rt_replace() +{ + echo + echo "IPv6 route replace tests" + + ipv6_rt_replace_single + ipv6_rt_replace_mpath +} + +ipv6_route_test() +{ + route_setup + + ipv6_rt_add + ipv6_rt_replace + + route_cleanup } +ip_addr_metric_check() +{ + ip addr help 2>&1 | grep -q metric + if [ $? -ne 0 ]; then + echo "iproute2 command does not support metric for addresses. Skipping test" + return 1 + fi + + return 0 +} + +ipv6_addr_metric_test() +{ + local rc + + echo + echo "IPv6 prefix route tests" + + ip_addr_metric_check || return 1 + + setup + + set -e + $IP li add dummy1 type dummy + $IP li add dummy2 type dummy + $IP li set dummy1 up + $IP li set dummy2 up + + # default entry is metric 256 + run_cmd "$IP -6 addr add dev dummy1 2001:db8:104::1/64" + run_cmd "$IP -6 addr add dev dummy2 2001:db8:104::2/64" + set +e + + check_route6 "2001:db8:104::/64 dev dummy1 proto kernel metric 256 2001:db8:104::/64 dev dummy2 proto kernel metric 256" + log_test $? 0 "Default metric" + + set -e + run_cmd "$IP -6 addr flush dev dummy1" + run_cmd "$IP -6 addr add dev dummy1 2001:db8:104::1/64 metric 257" + set +e + + check_route6 "2001:db8:104::/64 dev dummy2 proto kernel metric 256 2001:db8:104::/64 dev dummy1 proto kernel metric 257" + log_test $? 0 "User specified metric on first device" + + set -e + run_cmd "$IP -6 addr flush dev dummy2" + run_cmd "$IP -6 addr add dev dummy2 2001:db8:104::2/64 metric 258" + set +e + + check_route6 "2001:db8:104::/64 dev dummy1 proto kernel metric 257 2001:db8:104::/64 dev dummy2 proto kernel metric 258" + log_test $? 0 "User specified metric on second device" + + run_cmd "$IP -6 addr del dev dummy1 2001:db8:104::1/64 metric 257" + rc=$? + if [ $rc -eq 0 ]; then + check_route6 "2001:db8:104::/64 dev dummy2 proto kernel metric 258" + rc=$? + fi + log_test $rc 0 "Delete of address on first device" + + run_cmd "$IP -6 addr change dev dummy2 2001:db8:104::2/64 metric 259" + rc=$? + if [ $rc -eq 0 ]; then + check_route6 "2001:db8:104::/64 dev dummy2 proto kernel metric 259" + rc=$? + fi + log_test $rc 0 "Modify metric of address" + + # verify prefix route removed on down + run_cmd "ip netns exec testns sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1" + run_cmd "$IP li set dev dummy2 down" + rc=$? + if [ $rc -eq 0 ]; then + check_route6 "" + rc=$? + fi + log_test $rc 0 "Prefix route removed on link down" + + # verify prefix route re-inserted with assigned metric + run_cmd "$IP li set dev dummy2 up" + rc=$? + if [ $rc -eq 0 ]; then + check_route6 "2001:db8:104::/64 dev dummy2 proto kernel metric 259" + rc=$? + fi + log_test $rc 0 "Prefix route with metric on link up" + + $IP li del dummy1 + $IP li del dummy2 + cleanup +} + +# add route for a prefix, flushing any existing routes first +# expected to be the first step of a test +add_route() +{ + local pfx="$1" + local nh="$2" + local out + + if [ "$VERBOSE" = "1" ]; then + echo + echo " ##################################################" + echo + fi + + run_cmd "$IP ro flush ${pfx}" + [ $? -ne 0 ] && exit 1 + + out=$($IP ro ls match ${pfx}) + if [ -n "$out" ]; then + echo "Failed to flush routes for prefix used for tests." + exit 1 + fi + + run_cmd "$IP ro add ${pfx} ${nh}" + if [ $? -ne 0 ]; then + echo "Failed to add initial route for test." + exit 1 + fi +} + +# add initial route - used in replace route tests +add_initial_route() +{ + add_route "172.16.104.0/24" "$1" +} + +check_route() +{ + local pfx="172.16.104.0/24" + local expected="$1" + local out + local rc=0 + + out=$($IP ro ls match ${pfx}) + [ "${out}" = "${expected}" ] && return 0 + + if [ -z "${out}" ]; then + if [ "$VERBOSE" = "1" ]; then + printf "\nNo route entry found\n" + printf "Expected:\n" + printf " ${expected}\n" + fi + return 1 + fi + + # tricky way to convert output to 1-line without ip's + # messy '\'; this drops all extra white space + out=$(echo ${out}) + if [ "${out}" != "${expected}" ]; then + rc=1 + if [ "${VERBOSE}" = "1" ]; then + printf " Unexpected route entry. Have:\n" + printf " ${out}\n" + printf " Expected:\n" + printf " ${expected}\n\n" + fi + fi + + return $rc +} + +# assumption is that basic add of a single path route works +# otherwise just adding an address on an interface is broken +ipv4_rt_add() +{ + local rc + + echo + echo "IPv4 route add / append tests" + + # route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL + add_route "172.16.104.0/24" "via 172.16.101.2" + run_cmd "$IP ro add 172.16.104.0/24 via 172.16.103.2" + log_test $? 2 "Attempt to add duplicate route - gw" + + # route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL + add_route "172.16.104.0/24" "via 172.16.101.2" + run_cmd "$IP ro add 172.16.104.0/24 dev veth3" + log_test $? 2 "Attempt to add duplicate route - dev only" + + # route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL + add_route "172.16.104.0/24" "via 172.16.101.2" + run_cmd "$IP ro add unreachable 172.16.104.0/24" + log_test $? 2 "Attempt to add duplicate route - reject route" + + # iproute2 prepend only sets NLM_F_CREATE + # - adds a new route; does NOT convert existing route to ECMP + add_route "172.16.104.0/24" "via 172.16.101.2" + run_cmd "$IP ro prepend 172.16.104.0/24 via 172.16.103.2" + check_route "172.16.104.0/24 via 172.16.103.2 dev veth3 172.16.104.0/24 via 172.16.101.2 dev veth1" + log_test $? 0 "Add new nexthop for existing prefix" + + # route append with same prefix adds a new route + # - iproute2 sets NLM_F_CREATE | NLM_F_APPEND + add_route "172.16.104.0/24" "via 172.16.101.2" + run_cmd "$IP ro append 172.16.104.0/24 via 172.16.103.2" + check_route "172.16.104.0/24 via 172.16.101.2 dev veth1 172.16.104.0/24 via 172.16.103.2 dev veth3" + log_test $? 0 "Append nexthop to existing route - gw" + + add_route "172.16.104.0/24" "via 172.16.101.2" + run_cmd "$IP ro append 172.16.104.0/24 dev veth3" + check_route "172.16.104.0/24 via 172.16.101.2 dev veth1 172.16.104.0/24 dev veth3 scope link" + log_test $? 0 "Append nexthop to existing route - dev only" + + add_route "172.16.104.0/24" "via 172.16.101.2" + run_cmd "$IP ro append unreachable 172.16.104.0/24" + check_route "172.16.104.0/24 via 172.16.101.2 dev veth1 unreachable 172.16.104.0/24" + log_test $? 0 "Append nexthop to existing route - reject route" + + run_cmd "$IP ro flush 172.16.104.0/24" + run_cmd "$IP ro add unreachable 172.16.104.0/24" + run_cmd "$IP ro append 172.16.104.0/24 via 172.16.103.2" + check_route "unreachable 172.16.104.0/24 172.16.104.0/24 via 172.16.103.2 dev veth3" + log_test $? 0 "Append nexthop to existing reject route - gw" + + run_cmd "$IP ro flush 172.16.104.0/24" + run_cmd "$IP ro add unreachable 172.16.104.0/24" + run_cmd "$IP ro append 172.16.104.0/24 dev veth3" + check_route "unreachable 172.16.104.0/24 172.16.104.0/24 dev veth3 scope link" + log_test $? 0 "Append nexthop to existing reject route - dev only" + + # insert mpath directly + add_route "172.16.104.0/24" "nexthop via 172.16.101.2 nexthop via 172.16.103.2" + check_route "172.16.104.0/24 nexthop via 172.16.101.2 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1" + log_test $? 0 "add multipath route" + + add_route "172.16.104.0/24" "nexthop via 172.16.101.2 nexthop via 172.16.103.2" + run_cmd "$IP ro add 172.16.104.0/24 nexthop via 172.16.101.2 nexthop via 172.16.103.2" + log_test $? 2 "Attempt to add duplicate multipath route" + + # insert of a second route without append but different metric + add_route "172.16.104.0/24" "via 172.16.101.2" + run_cmd "$IP ro add 172.16.104.0/24 via 172.16.103.2 metric 512" + rc=$? + if [ $rc -eq 0 ]; then + run_cmd "$IP ro add 172.16.104.0/24 via 172.16.103.3 metric 256" + rc=$? + fi + log_test $rc 0 "Route add with different metrics" + + run_cmd "$IP ro del 172.16.104.0/24 metric 512" + rc=$? + if [ $rc -eq 0 ]; then + check_route "172.16.104.0/24 via 172.16.101.2 dev veth1 172.16.104.0/24 via 172.16.103.3 dev veth3 metric 256" + rc=$? + fi + log_test $rc 0 "Route delete with metric" +} + +ipv4_rt_replace_single() +{ + # single path with single path + # + add_initial_route "via 172.16.101.2" + run_cmd "$IP ro replace 172.16.104.0/24 via 172.16.103.2" + check_route "172.16.104.0/24 via 172.16.103.2 dev veth3" + log_test $? 0 "Single path with single path" + + # single path with multipath + # + add_initial_route "nexthop via 172.16.101.2" + run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.101.3 nexthop via 172.16.103.2" + check_route "172.16.104.0/24 nexthop via 172.16.101.3 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1" + log_test $? 0 "Single path with multipath" + + # single path with reject + # + add_initial_route "nexthop via 172.16.101.2" + run_cmd "$IP ro replace unreachable 172.16.104.0/24" + check_route "unreachable 172.16.104.0/24" + log_test $? 0 "Single path with reject route" + + # single path with single path using MULTIPATH attribute + # + add_initial_route "via 172.16.101.2" + run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.103.2" + check_route "172.16.104.0/24 via 172.16.103.2 dev veth3" + log_test $? 0 "Single path with single path via multipath attribute" + + # route replace fails - invalid nexthop + add_initial_route "via 172.16.101.2" + run_cmd "$IP ro replace 172.16.104.0/24 via 2001:db8:104::2" + if [ $? -eq 0 ]; then + # previous command is expected to fail so if it returns 0 + # that means the test failed. + log_test 0 1 "Invalid nexthop" + else + check_route "172.16.104.0/24 via 172.16.101.2 dev veth1" + log_test $? 0 "Invalid nexthop" + fi + + # replace non-existent route + # - note use of change versus replace since ip adds NLM_F_CREATE + # for replace + add_initial_route "via 172.16.101.2" + run_cmd "$IP ro change 172.16.105.0/24 via 172.16.101.2" + log_test $? 2 "Single path - replace of non-existent route" +} + +ipv4_rt_replace_mpath() +{ + # multipath with multipath + add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2" + run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.101.3 nexthop via 172.16.103.3" + check_route "172.16.104.0/24 nexthop via 172.16.101.3 dev veth1 weight 1 nexthop via 172.16.103.3 dev veth3 weight 1" + log_test $? 0 "Multipath with multipath" + + # multipath with single + add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2" + run_cmd "$IP ro replace 172.16.104.0/24 via 172.16.101.3" + check_route "172.16.104.0/24 via 172.16.101.3 dev veth1" + log_test $? 0 "Multipath with single path" + + # multipath with single + add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2" + run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.101.3" + check_route "172.16.104.0/24 via 172.16.101.3 dev veth1" + log_test $? 0 "Multipath with single path via multipath attribute" + + # multipath with reject + add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2" + run_cmd "$IP ro replace unreachable 172.16.104.0/24" + check_route "unreachable 172.16.104.0/24" + log_test $? 0 "Multipath with reject route" + + # route replace fails - invalid nexthop 1 + add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2" + run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.111.3 nexthop via 172.16.103.3" + check_route "172.16.104.0/24 nexthop via 172.16.101.2 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1" + log_test $? 0 "Multipath - invalid first nexthop" + + # route replace fails - invalid nexthop 2 + add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2" + run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.101.3 nexthop via 172.16.113.3" + check_route "172.16.104.0/24 nexthop via 172.16.101.2 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1" + log_test $? 0 "Multipath - invalid second nexthop" + + # multipath non-existent route + add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2" + run_cmd "$IP ro change 172.16.105.0/24 nexthop via 172.16.101.3 nexthop via 172.16.103.3" + log_test $? 2 "Multipath - replace of non-existent route" +} + +ipv4_rt_replace() +{ + echo + echo "IPv4 route replace tests" + + ipv4_rt_replace_single + ipv4_rt_replace_mpath +} + +ipv4_route_test() +{ + route_setup + + ipv4_rt_add + ipv4_rt_replace + + route_cleanup +} + +ipv4_addr_metric_test() +{ + local rc + + echo + echo "IPv4 prefix route tests" + + ip_addr_metric_check || return 1 + + setup + + set -e + $IP li add dummy1 type dummy + $IP li add dummy2 type dummy + $IP li set dummy1 up + $IP li set dummy2 up + + # default entry is metric 256 + run_cmd "$IP addr add dev dummy1 172.16.104.1/24" + run_cmd "$IP addr add dev dummy2 172.16.104.2/24" + set +e + + check_route "172.16.104.0/24 dev dummy1 proto kernel scope link src 172.16.104.1 172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2" + log_test $? 0 "Default metric" + + set -e + run_cmd "$IP addr flush dev dummy1" + run_cmd "$IP addr add dev dummy1 172.16.104.1/24 metric 257" + set +e + + check_route "172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 172.16.104.0/24 dev dummy1 proto kernel scope link src 172.16.104.1 metric 257" + log_test $? 0 "User specified metric on first device" + + set -e + run_cmd "$IP addr flush dev dummy2" + run_cmd "$IP addr add dev dummy2 172.16.104.2/24 metric 258" + set +e + + check_route "172.16.104.0/24 dev dummy1 proto kernel scope link src 172.16.104.1 metric 257 172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 metric 258" + log_test $? 0 "User specified metric on second device" + + run_cmd "$IP addr del dev dummy1 172.16.104.1/24 metric 257" + rc=$? + if [ $rc -eq 0 ]; then + check_route "172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 metric 258" + rc=$? + fi + log_test $rc 0 "Delete of address on first device" + + run_cmd "$IP addr change dev dummy2 172.16.104.2/24 metric 259" + rc=$? + if [ $rc -eq 0 ]; then + check_route "172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 metric 259" + rc=$? + fi + log_test $rc 0 "Modify metric of address" + + # verify prefix route removed on down + run_cmd "$IP li set dev dummy2 down" + rc=$? + if [ $rc -eq 0 ]; then + check_route "" + rc=$? + fi + log_test $rc 0 "Prefix route removed on link down" + + # verify prefix route re-inserted with assigned metric + run_cmd "$IP li set dev dummy2 up" + rc=$? + if [ $rc -eq 0 ]; then + check_route "172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 metric 259" + rc=$? + fi + log_test $rc 0 "Prefix route with metric on link up" + + $IP li del dummy1 + $IP li del dummy2 + cleanup +} + +################################################################################ +# usage + +usage() +{ + cat <<EOF +usage: ${0##*/} OPTS + + -t <test> Test(s) to run (default: all) + (options: $TESTS) + -p Pause on fail + -P Pause after each test before cleanup + -v verbose mode (show commands and output) +EOF +} + +################################################################################ +# main + +while getopts :t:pPhv o +do + case $o in + t) TESTS=$OPTARG;; + p) PAUSE_ON_FAIL=yes;; + P) PAUSE=yes;; + v) VERBOSE=$(($VERBOSE + 1));; + h) usage; exit 0;; + *) usage; exit 1;; + esac +done + +PEER_CMD="ip netns exec ${PEER_NS}" + +# make sure we don't pause twice +[ "${PAUSE}" = "yes" ] && PAUSE_ON_FAIL=no + if [ "$(id -u)" -ne 0 ];then echo "SKIP: Need root privileges" exit $ksft_skip; @@ -598,6 +1415,25 @@ fi # start clean cleanup &> /dev/null -fib_test +for t in $TESTS +do + case $t in + fib_unreg_test|unregister) fib_unreg_test;; + fib_down_test|down) fib_down_test;; + fib_carrier_test|carrier) fib_carrier_test;; + fib_nexthop_test|nexthop) fib_nexthop_test;; + ipv6_route_test|ipv6_rt) ipv6_route_test;; + ipv4_route_test|ipv4_rt) ipv4_route_test;; + ipv6_addr_metric) ipv6_addr_metric_test;; + ipv4_addr_metric) ipv4_addr_metric_test;; + + help) echo "Test names: $TESTS"; exit 0;; + esac +done + +if [ "$TESTS" != "none" ]; then + printf "\nTests passed: %3d\n" ${nsuccess} + printf "Tests failed: %3d\n" ${nfail} +fi exit $ret diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh index 75d9224..d8313d0 100755 --- a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh +++ b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh @@ -1,6 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding" NUM_NETIFS=4 CHECK_TC="yes" source lib.sh @@ -75,14 +76,31 @@ cleanup() vrf_cleanup } +ping_ipv4() +{ + ping_test $h1 192.0.2.2 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:1::2 +} + +learning() +{ + learning_test "br0" $swp1 $h1 $h2 +} + +flooding() +{ + flood_test $swp2 $h1 $h2 +} + trap cleanup EXIT setup_prepare setup_wait -ping_test $h1 192.0.2.2 -ping6_test $h1 2001:db8:1::2 -learning_test "br0" $swp1 $h1 $h2 -flood_test $swp2 $h1 $h2 +tests_run exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh index 1cddf06..c15c6c8 100755 --- a/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh +++ b/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh @@ -1,6 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding" NUM_NETIFS=4 source lib.sh @@ -73,14 +74,31 @@ cleanup() vrf_cleanup } +ping_ipv4() +{ + ping_test $h1 192.0.2.2 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:1::2 +} + +learning() +{ + learning_test "br0" $swp1 $h1 $h2 +} + +flooding() +{ + flood_test $swp2 $h1 $h2 +} + trap cleanup EXIT setup_prepare setup_wait -ping_test $h1 192.0.2.2 -ping6_test $h1 2001:db8:1::2 -learning_test "br0" $swp1 $h1 $h2 -flood_test $swp2 $h1 $h2 +tests_run exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 1ac6c62..7b18a53 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -321,6 +321,50 @@ simple_if_fini() vrf_destroy $vrf_name } +tunnel_create() +{ + local name=$1; shift + local type=$1; shift + local local=$1; shift + local remote=$1; shift + + ip link add name $name type $type \ + local $local remote $remote "$@" + ip link set dev $name up +} + +tunnel_destroy() +{ + local name=$1; shift + + ip link del dev $name +} + +vlan_create() +{ + local if_name=$1; shift + local vid=$1; shift + local vrf=$1; shift + local ips=("${@}") + local name=$if_name.$vid + + ip link add name $name link $if_name type vlan id $vid + if [ "$vrf" != "" ]; then + ip link set dev $name master $vrf + fi + ip link set dev $name up + __addr_add_del $name add "${ips[@]}" +} + +vlan_destroy() +{ + local if_name=$1; shift + local vid=$1; shift + local name=$if_name.$vid + + ip link del dev $name +} + master_name_get() { local if_name=$1 @@ -335,6 +379,15 @@ link_stats_tx_packets_get() ip -j -s link show dev $if_name | jq '.[]["stats64"]["tx"]["packets"]' } +tc_rule_stats_get() +{ + local dev=$1; shift + local pref=$1; shift + + tc -j -s filter show dev $dev ingress pref $pref | + jq '.[1].options.actions[].stats.packets' +} + mac_get() { local if_name=$1 @@ -353,19 +406,33 @@ bridge_ageing_time_get() echo $((ageing_time / 100)) } -forwarding_enable() +declare -A SYSCTL_ORIG +sysctl_set() +{ + local key=$1; shift + local value=$1; shift + + SYSCTL_ORIG[$key]=$(sysctl -n $key) + sysctl -qw $key=$value +} + +sysctl_restore() { - ipv4_fwd=$(sysctl -n net.ipv4.conf.all.forwarding) - ipv6_fwd=$(sysctl -n net.ipv6.conf.all.forwarding) + local key=$1; shift - sysctl -q -w net.ipv4.conf.all.forwarding=1 - sysctl -q -w net.ipv6.conf.all.forwarding=1 + sysctl -qw $key=${SYSCTL_ORIG["$key"]} +} + +forwarding_enable() +{ + sysctl_set net.ipv4.conf.all.forwarding 1 + sysctl_set net.ipv6.conf.all.forwarding 1 } forwarding_restore() { - sysctl -q -w net.ipv6.conf.all.forwarding=$ipv6_fwd - sysctl -q -w net.ipv4.conf.all.forwarding=$ipv4_fwd + sysctl_restore net.ipv6.conf.all.forwarding + sysctl_restore net.ipv4.conf.all.forwarding } tc_offload_check() @@ -381,6 +448,115 @@ tc_offload_check() return 0 } +trap_install() +{ + local dev=$1; shift + local direction=$1; shift + + # For slow-path testing, we need to install a trap to get to + # slow path the packets that would otherwise be switched in HW. + tc filter add dev $dev $direction pref 1 flower skip_sw action trap +} + +trap_uninstall() +{ + local dev=$1; shift + local direction=$1; shift + + tc filter del dev $dev $direction pref 1 flower skip_sw +} + +slow_path_trap_install() +{ + if [ "${tcflags/skip_hw}" != "$tcflags" ]; then + trap_install "$@" + fi +} + +slow_path_trap_uninstall() +{ + if [ "${tcflags/skip_hw}" != "$tcflags" ]; then + trap_uninstall "$@" + fi +} + +__icmp_capture_add_del() +{ + local add_del=$1; shift + local pref=$1; shift + local vsuf=$1; shift + local tundev=$1; shift + local filter=$1; shift + + tc filter $add_del dev "$tundev" ingress \ + proto ip$vsuf pref $pref \ + flower ip_proto icmp$vsuf $filter \ + action pass +} + +icmp_capture_install() +{ + __icmp_capture_add_del add 100 "" "$@" +} + +icmp_capture_uninstall() +{ + __icmp_capture_add_del del 100 "" "$@" +} + +icmp6_capture_install() +{ + __icmp_capture_add_del add 100 v6 "$@" +} + +icmp6_capture_uninstall() +{ + __icmp_capture_add_del del 100 v6 "$@" +} + +__vlan_capture_add_del() +{ + local add_del=$1; shift + local pref=$1; shift + local dev=$1; shift + local filter=$1; shift + + tc filter $add_del dev "$dev" ingress \ + proto 802.1q pref $pref \ + flower $filter \ + action pass +} + +vlan_capture_install() +{ + __vlan_capture_add_del add 100 "$@" +} + +vlan_capture_uninstall() +{ + __vlan_capture_add_del del 100 "$@" +} + +matchall_sink_create() +{ + local dev=$1; shift + + tc qdisc add dev $dev clsact + tc filter add dev $dev ingress \ + pref 10000 \ + matchall \ + action drop +} + +tests_run() +{ + local current_test + + for current_test in ${TESTS:-$ALL_TESTS}; do + $current_test + done +} + ############################################################################## # Tests diff --git a/tools/testing/selftests/net/forwarding/mirror_gre.sh b/tools/testing/selftests/net/forwarding/mirror_gre.sh new file mode 100755 index 0000000..e6fd7a1 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre.sh @@ -0,0 +1,159 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test uses standard topology for testing gretap. See +# mirror_gre_topo_lib.sh for more details. +# +# Test for "tc action mirred egress mirror" when the device to mirror to is a +# gretap or ip6gretap netdevice. Expect that the packets come out encapsulated, +# and another gretap / ip6gretap netdevice is then capable of decapsulating the +# traffic. Test that the payload is what is expected (ICMP ping request or +# reply, depending on test). + +ALL_TESTS=" + test_gretap + test_ip6gretap + test_gretap_mac + test_ip6gretap_mac + test_two_spans +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh +source mirror_gre_topo_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + mirror_gre_topo_create + + ip address add dev $swp3 192.0.2.129/28 + ip address add dev $h3 192.0.2.130/28 + + ip address add dev $swp3 2001:db8:2::1/64 + ip address add dev $h3 2001:db8:2::2/64 +} + +cleanup() +{ + pre_cleanup + + ip address del dev $h3 2001:db8:2::2/64 + ip address del dev $swp3 2001:db8:2::1/64 + + ip address del dev $h3 192.0.2.130/28 + ip address del dev $swp3 192.0.2.129/28 + + mirror_gre_topo_destroy + vrf_cleanup +} + +test_span_gre_mac() +{ + local tundev=$1; shift + local direction=$1; shift + local prot=$1; shift + local what=$1; shift + + local swp3mac=$(mac_get $swp3) + local h3mac=$(mac_get $h3) + + RET=0 + + mirror_install $swp1 $direction $tundev "matchall $tcflags" + tc filter add dev $h3 ingress pref 77 prot $prot \ + flower ip_proto 0x2f src_mac $swp3mac dst_mac $h3mac \ + action pass + + mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 10 + + tc filter del dev $h3 ingress pref 77 + mirror_uninstall $swp1 $direction + + log_test "$direction $what: envelope MAC ($tcflags)" +} + +test_two_spans() +{ + RET=0 + + mirror_install $swp1 ingress gt4 "matchall $tcflags" + mirror_install $swp1 egress gt6 "matchall $tcflags" + quick_test_span_gre_dir gt4 ingress + quick_test_span_gre_dir gt6 egress + + mirror_uninstall $swp1 ingress + fail_test_span_gre_dir gt4 ingress + quick_test_span_gre_dir gt6 egress + + mirror_install $swp1 ingress gt4 "matchall $tcflags" + mirror_uninstall $swp1 egress + quick_test_span_gre_dir gt4 ingress + fail_test_span_gre_dir gt6 egress + + mirror_uninstall $swp1 ingress + log_test "two simultaneously configured mirrors ($tcflags)" +} + +test_gretap() +{ + full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap" + full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap" +} + +test_ip6gretap() +{ + full_test_span_gre_dir gt6 ingress 8 0 "mirror to ip6gretap" + full_test_span_gre_dir gt6 egress 0 8 "mirror to ip6gretap" +} + +test_gretap_mac() +{ + test_span_gre_mac gt4 ingress ip "mirror to gretap" + test_span_gre_mac gt4 egress ip "mirror to gretap" +} + +test_ip6gretap_mac() +{ + test_span_gre_mac gt6 ingress ipv6 "mirror to ip6gretap" + test_span_gre_mac gt6 egress ipv6 "mirror to ip6gretap" +} + +test_all() +{ + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bound.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bound.sh new file mode 100755 index 0000000..360ca13 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bound.sh @@ -0,0 +1,226 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +---------------------+ +---------------------+ +# | H1 | | H2 | +# | + $h1 | | $h2 + | +# | | 192.0.2.1/28 | | 192.0.2.2/28 | | +# +-----|---------------+ +---------------|-----+ +# | | +# +-----|-------------------------------------------------------------|-----+ +# | SW o--> mirror | | +# | +---|-------------------------------------------------------------|---+ | +# | | + $swp1 BR $swp2 + | | +# | +---------------------------------------------------------------------+ | +# | | +# | +---------------------------------------------------------------------+ | +# | | OL + gt6 (ip6gretap) + gt4 (gretap) | | +# | | : loc=2001:db8:2::1 : loc=192.0.2.129 | | +# | | : rem=2001:db8:2::2 : rem=192.0.2.130 | | +# | | : ttl=100 : ttl=100 | | +# | | : tos=inherit : tos=inherit | | +# | +-------------------------:--|-------------------:--|-----------------+ | +# | : | : | | +# | +-------------------------:--|-------------------:--|-----------------+ | +# | | UL : |,---------------------' | | +# | | + $swp3 : || : | | +# | | | 192.0.2.129/28 : vv : | | +# | | | 2001:db8:2::1/64 : + ul (dummy) : | | +# | +---|---------------------:----------------------:--------------------+ | +# +-----|---------------------:----------------------:----------------------+ +# | : : +# +-----|---------------------:----------------------:----------------------+ +# | H3 + $h3 + h3-gt6 (ip6gretap) + h3-gt4 (gretap) | +# | 192.0.2.130/28 loc=2001:db8:2::2 loc=192.0.2.130 | +# | 2001:db8:2::2/64 rem=2001:db8:2::1 rem=192.0.2.129 | +# | ttl=100 ttl=100 | +# | tos=inherit tos=inherit | +# | | +# +-------------------------------------------------------------------------+ +# +# This tests mirroring to gretap and ip6gretap configured in an overlay / +# underlay manner, i.e. with a bound dummy device that marks underlay VRF where +# the encapsulated packed should be routed. + +ALL_TESTS=" + test_gretap + test_ip6gretap +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/28 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.2/28 +} + +h2_destroy() +{ + simple_if_fini $h2 192.0.2.2/28 +} + +h3_create() +{ + simple_if_init $h3 192.0.2.130/28 2001:db8:2::2/64 + + tunnel_create h3-gt4 gretap 192.0.2.130 192.0.2.129 + ip link set h3-gt4 vrf v$h3 + matchall_sink_create h3-gt4 + + tunnel_create h3-gt6 ip6gretap 2001:db8:2::2 2001:db8:2::1 + ip link set h3-gt6 vrf v$h3 + matchall_sink_create h3-gt6 +} + +h3_destroy() +{ + tunnel_destroy h3-gt6 + tunnel_destroy h3-gt4 + + simple_if_fini $h3 192.0.2.130/28 2001:db8:2::2/64 +} + +switch_create() +{ + # Bridge between H1 and H2. + + ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 up + + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + + ip link set dev $swp2 master br1 + ip link set dev $swp2 up + + tc qdisc add dev $swp1 clsact + + # Underlay. + + simple_if_init $swp3 192.0.2.129/28 2001:db8:2::1/64 + + ip link add name ul type dummy + ip link set dev ul master v$swp3 + ip link set dev ul up + + # Overlay. + + vrf_create vrf-ol + ip link set dev vrf-ol up + + tunnel_create gt4 gretap 192.0.2.129 192.0.2.130 \ + ttl 100 tos inherit dev ul + ip link set dev gt4 master vrf-ol + ip link set dev gt4 up + + tunnel_create gt6 ip6gretap 2001:db8:2::1 2001:db8:2::2 \ + ttl 100 tos inherit dev ul allow-localremote + ip link set dev gt6 master vrf-ol + ip link set dev gt6 up +} + +switch_destroy() +{ + vrf_destroy vrf-ol + + tunnel_destroy gt6 + tunnel_destroy gt4 + + simple_if_fini $swp3 192.0.2.129/28 2001:db8:2::1/64 + + ip link del dev ul + + tc qdisc del dev $swp1 clsact + + ip link set dev $swp1 down + ip link set dev $swp2 down + ip link del dev br1 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + + h1_create + h2_create + h3_create + + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + + h3_destroy + h2_destroy + h1_destroy + + vrf_cleanup +} + +test_gretap() +{ + full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap w/ UL" + full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap w/ UL" +} + +test_ip6gretap() +{ + full_test_span_gre_dir gt6 ingress 8 0 "mirror to ip6gretap w/ UL" + full_test_span_gre_dir gt6 egress 0 8 "mirror to ip6gretap w/ UL" +} + +test_all() +{ + RET=0 + + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh new file mode 100755 index 0000000..3bb4c2b --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh @@ -0,0 +1,121 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test uses standard topology for testing gretap. See +# mirror_gre_topo_lib.sh for more details. +# +# Test for "tc action mirred egress mirror" when the underlay route points at a +# bridge device without vlan filtering (802.1d). The device attached to that +# bridge is a VLAN. + +ALL_TESTS=" + test_gretap + test_ip6gretap + test_gretap_stp + test_ip6gretap_stp +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh +source mirror_gre_topo_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + mirror_gre_topo_create + + ip link add name br2 type bridge vlan_filtering 0 + ip link set dev br2 up + + vlan_create $swp3 555 + + ip link set dev $swp3.555 master br2 + ip route add 192.0.2.130/32 dev br2 + ip -6 route add 2001:db8:2::2/128 dev br2 + + ip address add dev br2 192.0.2.129/32 + ip address add dev br2 2001:db8:2::1/128 + + vlan_create $h3 555 v$h3 192.0.2.130/28 2001:db8:2::2/64 +} + +cleanup() +{ + pre_cleanup + + vlan_destroy $h3 555 + ip link del dev br2 + vlan_destroy $swp3 555 + + mirror_gre_topo_destroy + vrf_cleanup +} + +test_vlan_match() +{ + local tundev=$1; shift + local vlan_match=$1; shift + local what=$1; shift + + full_test_span_gre_dir_vlan $tundev ingress "$vlan_match" 8 0 "$what" + full_test_span_gre_dir_vlan $tundev egress "$vlan_match" 0 8 "$what" +} + +test_gretap() +{ + test_vlan_match gt4 'vlan_id 555 vlan_ethtype ip' "mirror to gretap" +} + +test_ip6gretap() +{ + test_vlan_match gt6 'vlan_id 555 vlan_ethtype ipv6' "mirror to ip6gretap" +} + +test_gretap_stp() +{ + full_test_span_gre_stp gt4 $swp3.555 "mirror to gretap" +} + +test_ip6gretap_stp() +{ + full_test_span_gre_stp gt6 $swp3.555 "mirror to ip6gretap" +} + +test_all() +{ + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh new file mode 100755 index 0000000..aa29d46 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh @@ -0,0 +1,278 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test uses standard topology for testing gretap. See +# mirror_gre_topo_lib.sh for more details. +# +# Test how mirrors to gretap and ip6gretap react to changes to relevant +# configuration. + +ALL_TESTS=" + test_ttl + test_tun_up + test_egress_up + test_remote_ip + test_tun_del + test_route_del +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh +source mirror_gre_topo_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + mirror_gre_topo_create + + # This test downs $swp3, which deletes the configured IPv6 address + # unless this sysctl is set. + sysctl_set net.ipv6.conf.$swp3.keep_addr_on_down 1 + + ip address add dev $swp3 192.0.2.129/28 + ip address add dev $h3 192.0.2.130/28 + + ip address add dev $swp3 2001:db8:2::1/64 + ip address add dev $h3 2001:db8:2::2/64 +} + +cleanup() +{ + pre_cleanup + + ip address del dev $h3 2001:db8:2::2/64 + ip address del dev $swp3 2001:db8:2::1/64 + + ip address del dev $h3 192.0.2.130/28 + ip address del dev $swp3 192.0.2.129/28 + + sysctl_restore net.ipv6.conf.$swp3.keep_addr_on_down + + mirror_gre_topo_destroy + vrf_cleanup +} + +test_span_gre_ttl() +{ + local tundev=$1; shift + local type=$1; shift + local prot=$1; shift + local what=$1; shift + + RET=0 + + mirror_install $swp1 ingress $tundev "matchall $tcflags" + tc filter add dev $h3 ingress pref 77 prot $prot \ + flower ip_ttl 50 action pass + + mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 0 + + ip link set dev $tundev type $type ttl 50 + mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 10 + + ip link set dev $tundev type $type ttl 100 + tc filter del dev $h3 ingress pref 77 + mirror_uninstall $swp1 ingress + + log_test "$what: TTL change ($tcflags)" +} + +test_span_gre_tun_up() +{ + local tundev=$1; shift + local what=$1; shift + + RET=0 + + ip link set dev $tundev down + mirror_install $swp1 ingress $tundev "matchall $tcflags" + fail_test_span_gre_dir $tundev ingress + + ip link set dev $tundev up + + quick_test_span_gre_dir $tundev ingress + mirror_uninstall $swp1 ingress + + log_test "$what: tunnel down/up ($tcflags)" +} + +test_span_gre_egress_up() +{ + local tundev=$1; shift + local remote_ip=$1; shift + local what=$1; shift + + RET=0 + + ip link set dev $swp3 down + mirror_install $swp1 ingress $tundev "matchall $tcflags" + fail_test_span_gre_dir $tundev ingress + + # After setting the device up, wait for neighbor to get resolved so that + # we can expect mirroring to work. + ip link set dev $swp3 up + while true; do + ip neigh sh dev $swp3 $remote_ip nud reachable | + grep -q ^ + if [[ $? -ne 0 ]]; then + sleep 1 + else + break + fi + done + + quick_test_span_gre_dir $tundev ingress + mirror_uninstall $swp1 ingress + + log_test "$what: egress down/up ($tcflags)" +} + +test_span_gre_remote_ip() +{ + local tundev=$1; shift + local type=$1; shift + local correct_ip=$1; shift + local wrong_ip=$1; shift + local what=$1; shift + + RET=0 + + ip link set dev $tundev type $type remote $wrong_ip + mirror_install $swp1 ingress $tundev "matchall $tcflags" + fail_test_span_gre_dir $tundev ingress + + ip link set dev $tundev type $type remote $correct_ip + quick_test_span_gre_dir $tundev ingress + mirror_uninstall $swp1 ingress + + log_test "$what: remote address change ($tcflags)" +} + +test_span_gre_tun_del() +{ + local tundev=$1; shift + local type=$1; shift + local flags=$1; shift + local local_ip=$1; shift + local remote_ip=$1; shift + local what=$1; shift + + RET=0 + + mirror_install $swp1 ingress $tundev "matchall $tcflags" + quick_test_span_gre_dir $tundev ingress + ip link del dev $tundev + fail_test_span_gre_dir $tundev ingress + + tunnel_create $tundev $type $local_ip $remote_ip \ + ttl 100 tos inherit $flags + + # Recreating the tunnel doesn't reestablish mirroring, so reinstall it + # and verify it works for the follow-up tests. + mirror_uninstall $swp1 ingress + mirror_install $swp1 ingress $tundev "matchall $tcflags" + quick_test_span_gre_dir $tundev ingress + mirror_uninstall $swp1 ingress + + log_test "$what: tunnel deleted ($tcflags)" +} + +test_span_gre_route_del() +{ + local tundev=$1; shift + local edev=$1; shift + local route=$1; shift + local what=$1; shift + + RET=0 + + mirror_install $swp1 ingress $tundev "matchall $tcflags" + quick_test_span_gre_dir $tundev ingress + + ip route del $route dev $edev + fail_test_span_gre_dir $tundev ingress + + ip route add $route dev $edev + quick_test_span_gre_dir $tundev ingress + + mirror_uninstall $swp1 ingress + + log_test "$what: underlay route removal ($tcflags)" +} + +test_ttl() +{ + test_span_gre_ttl gt4 gretap ip "mirror to gretap" + test_span_gre_ttl gt6 ip6gretap ipv6 "mirror to ip6gretap" +} + +test_tun_up() +{ + test_span_gre_tun_up gt4 "mirror to gretap" + test_span_gre_tun_up gt6 "mirror to ip6gretap" +} + +test_egress_up() +{ + test_span_gre_egress_up gt4 192.0.2.130 "mirror to gretap" + test_span_gre_egress_up gt6 2001:db8:2::2 "mirror to ip6gretap" +} + +test_remote_ip() +{ + test_span_gre_remote_ip gt4 gretap 192.0.2.130 192.0.2.132 "mirror to gretap" + test_span_gre_remote_ip gt6 ip6gretap 2001:db8:2::2 2001:db8:2::4 "mirror to ip6gretap" +} + +test_tun_del() +{ + test_span_gre_tun_del gt4 gretap "" \ + 192.0.2.129 192.0.2.130 "mirror to gretap" + test_span_gre_tun_del gt6 ip6gretap allow-localremote \ + 2001:db8:2::1 2001:db8:2::2 "mirror to ip6gretap" +} + +test_route_del() +{ + test_span_gre_route_del gt4 $swp3 192.0.2.128/28 "mirror to gretap" + test_span_gre_route_del gt6 $swp3 2001:db8:2::/64 "mirror to ip6gretap" +} + +test_all() +{ + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_flower.sh b/tools/testing/selftests/net/forwarding/mirror_gre_flower.sh new file mode 100755 index 0000000..12914f4 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_flower.sh @@ -0,0 +1,137 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test uses standard topology for testing gretap. See +# mirror_gre_topo_lib.sh for more details. +# +# This tests flower-triggered mirroring to gretap and ip6gretap netdevices. The +# interfaces on H1 and H2 have two addresses each. Flower match on one of the +# addresses is configured with mirror action. It is expected that when pinging +# this address, mirroring takes place, whereas when pinging the other one, +# there's no mirroring. + +ALL_TESTS=" + test_gretap + test_ip6gretap +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh +source mirror_gre_topo_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + mirror_gre_topo_create + + ip address add dev $swp3 192.0.2.129/28 + ip address add dev $h3 192.0.2.130/28 + + ip address add dev $swp3 2001:db8:2::1/64 + ip address add dev $h3 2001:db8:2::2/64 + + ip address add dev $h1 192.0.2.3/28 + ip address add dev $h2 192.0.2.4/28 +} + +cleanup() +{ + pre_cleanup + + ip address del dev $h2 192.0.2.4/28 + ip address del dev $h1 192.0.2.3/28 + + ip address del dev $h3 2001:db8:2::2/64 + ip address del dev $swp3 2001:db8:2::1/64 + + ip address del dev $h3 192.0.2.130/28 + ip address del dev $swp3 192.0.2.129/28 + + mirror_gre_topo_destroy + vrf_cleanup +} + +test_span_gre_dir_acl() +{ + test_span_gre_dir_ips "$@" 192.0.2.3 192.0.2.4 +} + +fail_test_span_gre_dir_acl() +{ + fail_test_span_gre_dir_ips "$@" 192.0.2.3 192.0.2.4 +} + +full_test_span_gre_dir_acl() +{ + local tundev=$1; shift + local direction=$1; shift + local forward_type=$1; shift + local backward_type=$1; shift + local match_dip=$1; shift + local what=$1; shift + + mirror_install $swp1 $direction $tundev \ + "protocol ip flower $tcflags dst_ip $match_dip" + fail_test_span_gre_dir $tundev $direction + test_span_gre_dir_acl "$tundev" "$direction" \ + "$forward_type" "$backward_type" + mirror_uninstall $swp1 $direction + + # Test lack of mirroring after ACL mirror is uninstalled. + fail_test_span_gre_dir_acl "$tundev" "$direction" + + log_test "$direction $what ($tcflags)" +} + +test_gretap() +{ + full_test_span_gre_dir_acl gt4 ingress 8 0 192.0.2.4 "ACL mirror to gretap" + full_test_span_gre_dir_acl gt4 egress 0 8 192.0.2.3 "ACL mirror to gretap" +} + +test_ip6gretap() +{ + full_test_span_gre_dir_acl gt6 ingress 8 0 192.0.2.4 "ACL mirror to ip6gretap" + full_test_span_gre_dir_acl gt6 egress 0 8 192.0.2.3 "ACL mirror to ip6gretap" +} + +test_all() +{ + RET=0 + + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh b/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh new file mode 100644 index 0000000..619b469 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh @@ -0,0 +1,130 @@ +# SPDX-License-Identifier: GPL-2.0 + +source mirror_lib.sh + +quick_test_span_gre_dir_ips() +{ + local tundev=$1; shift + + do_test_span_dir_ips 10 h3-$tundev "$@" +} + +fail_test_span_gre_dir_ips() +{ + local tundev=$1; shift + + do_test_span_dir_ips 0 h3-$tundev "$@" +} + +test_span_gre_dir_ips() +{ + local tundev=$1; shift + + test_span_dir_ips h3-$tundev "$@" +} + +full_test_span_gre_dir_ips() +{ + local tundev=$1; shift + local direction=$1; shift + local forward_type=$1; shift + local backward_type=$1; shift + local what=$1; shift + local ip1=$1; shift + local ip2=$1; shift + + RET=0 + + mirror_install $swp1 $direction $tundev "matchall $tcflags" + test_span_dir_ips "h3-$tundev" "$direction" "$forward_type" \ + "$backward_type" "$ip1" "$ip2" + mirror_uninstall $swp1 $direction + + log_test "$direction $what ($tcflags)" +} + +full_test_span_gre_dir_vlan_ips() +{ + local tundev=$1; shift + local direction=$1; shift + local vlan_match=$1; shift + local forward_type=$1; shift + local backward_type=$1; shift + local what=$1; shift + local ip1=$1; shift + local ip2=$1; shift + + RET=0 + + mirror_install $swp1 $direction $tundev "matchall $tcflags" + + test_span_dir_ips "h3-$tundev" "$direction" "$forward_type" \ + "$backward_type" "$ip1" "$ip2" + + tc filter add dev $h3 ingress pref 77 prot 802.1q \ + flower $vlan_match ip_proto 0x2f \ + action pass + mirror_test v$h1 $ip1 $ip2 $h3 77 10 + tc filter del dev $h3 ingress pref 77 + + mirror_uninstall $swp1 $direction + + log_test "$direction $what ($tcflags)" +} + +quick_test_span_gre_dir() +{ + quick_test_span_gre_dir_ips "$@" 192.0.2.1 192.0.2.2 +} + +fail_test_span_gre_dir() +{ + fail_test_span_gre_dir_ips "$@" 192.0.2.1 192.0.2.2 +} + +test_span_gre_dir() +{ + test_span_gre_dir_ips "$@" 192.0.2.1 192.0.2.2 +} + +full_test_span_gre_dir() +{ + full_test_span_gre_dir_ips "$@" 192.0.2.1 192.0.2.2 +} + +full_test_span_gre_dir_vlan() +{ + full_test_span_gre_dir_vlan_ips "$@" 192.0.2.1 192.0.2.2 +} + +full_test_span_gre_stp_ips() +{ + local tundev=$1; shift + local nbpdev=$1; shift + local what=$1; shift + local ip1=$1; shift + local ip2=$1; shift + local h3mac=$(mac_get $h3) + + RET=0 + + mirror_install $swp1 ingress $tundev "matchall $tcflags" + quick_test_span_gre_dir_ips $tundev ingress $ip1 $ip2 + + bridge link set dev $nbpdev state disabled + sleep 1 + fail_test_span_gre_dir_ips $tundev ingress $ip1 $ip2 + + bridge link set dev $nbpdev state forwarding + sleep 1 + quick_test_span_gre_dir_ips $tundev ingress $ip1 $ip2 + + mirror_uninstall $swp1 ingress + + log_test "$what: STP state ($tcflags)" +} + +full_test_span_gre_stp() +{ + full_test_span_gre_stp_ips "$@" 192.0.2.1 192.0.2.2 +} diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_neigh.sh b/tools/testing/selftests/net/forwarding/mirror_gre_neigh.sh new file mode 100755 index 0000000..fc0508e --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_neigh.sh @@ -0,0 +1,115 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test uses standard topology for testing gretap. See +# mirror_gre_topo_lib.sh for more details. +# +# Test for mirroring to gretap and ip6gretap, such that the neighbor entry for +# the tunnel remote address has invalid address at the time that the mirroring +# is set up. Later on, the neighbor is deleted and it is expected to be +# reinitialized using the usual ARP process, and the mirroring offload updated. + +ALL_TESTS=" + test_gretap + test_ip6gretap +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh +source mirror_gre_topo_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + mirror_gre_topo_create + + ip address add dev $swp3 192.0.2.129/28 + ip address add dev $h3 192.0.2.130/28 + + ip address add dev $swp3 2001:db8:2::1/64 + ip address add dev $h3 2001:db8:2::2/64 +} + +cleanup() +{ + pre_cleanup + + ip address del dev $h3 2001:db8:2::2/64 + ip address del dev $swp3 2001:db8:2::1/64 + + ip address del dev $h3 192.0.2.130/28 + ip address del dev $swp3 192.0.2.129/28 + + mirror_gre_topo_destroy + vrf_cleanup +} + +test_span_gre_neigh() +{ + local addr=$1; shift + local tundev=$1; shift + local direction=$1; shift + local what=$1; shift + + RET=0 + + ip neigh replace dev $swp3 $addr lladdr 00:11:22:33:44:55 + mirror_install $swp1 $direction $tundev "matchall $tcflags" + fail_test_span_gre_dir $tundev ingress + ip neigh del dev $swp3 $addr + quick_test_span_gre_dir $tundev ingress + mirror_uninstall $swp1 $direction + + log_test "$direction $what: neighbor change ($tcflags)" +} + +test_gretap() +{ + test_span_gre_neigh 192.0.2.130 gt4 ingress "mirror to gretap" + test_span_gre_neigh 192.0.2.130 gt4 egress "mirror to gretap" +} + +test_ip6gretap() +{ + test_span_gre_neigh 2001:db8:2::2 gt6 ingress "mirror to ip6gretap" + test_span_gre_neigh 2001:db8:2::2 gt6 egress "mirror to ip6gretap" +} + +test_all() +{ + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_nh.sh b/tools/testing/selftests/net/forwarding/mirror_gre_nh.sh new file mode 100755 index 0000000..8fa681e --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_nh.sh @@ -0,0 +1,127 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test uses standard topology for testing gretap. See +# mirror_gre_topo_lib.sh for more details. +# +# Test that gretap and ip6gretap mirroring works when the other tunnel endpoint +# is reachable through a next-hop route (as opposed to directly-attached route). + +ALL_TESTS=" + test_gretap + test_ip6gretap +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh +source mirror_gre_topo_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + sysctl_set net.ipv4.conf.all.rp_filter 0 + sysctl_set net.ipv4.conf.$h3.rp_filter 0 + + vrf_prepare + mirror_gre_topo_create + + ip address add dev $swp3 192.0.2.161/28 + ip address add dev $h3 192.0.2.162/28 + ip address add dev gt4 192.0.2.129/32 + ip address add dev h3-gt4 192.0.2.130/32 + + # IPv6 route can't be added after address. Such routes are rejected due + # to the gateway address having been configured on the local system. It + # works the other way around though. + ip address add dev $swp3 2001:db8:4::1/64 + ip -6 route add 2001:db8:2::2/128 via 2001:db8:4::2 + ip address add dev $h3 2001:db8:4::2/64 + ip address add dev gt6 2001:db8:2::1 + ip address add dev h3-gt6 2001:db8:2::2 +} + +cleanup() +{ + pre_cleanup + + ip -6 route del 2001:db8:2::2/128 via 2001:db8:4::2 + ip address del dev $h3 2001:db8:4::2/64 + ip address del dev $swp3 2001:db8:4::1/64 + + ip address del dev $h3 192.0.2.162/28 + ip address del dev $swp3 192.0.2.161/28 + + mirror_gre_topo_destroy + vrf_cleanup + + sysctl_restore net.ipv4.conf.$h3.rp_filter + sysctl_restore net.ipv4.conf.all.rp_filter +} + +test_gretap() +{ + RET=0 + mirror_install $swp1 ingress gt4 "matchall $tcflags" + + # For IPv4, test that there's no mirroring without the route directing + # the traffic to tunnel remote address. Then add it and test that + # mirroring starts. For IPv6 we can't test this due to the limitation + # that routes for locally-specified IPv6 addresses can't be added. + fail_test_span_gre_dir gt4 ingress + + ip route add 192.0.2.130/32 via 192.0.2.162 + quick_test_span_gre_dir gt4 ingress + ip route del 192.0.2.130/32 via 192.0.2.162 + + mirror_uninstall $swp1 ingress + log_test "mirror to gre with next-hop remote ($tcflags)" +} + +test_ip6gretap() +{ + RET=0 + + mirror_install $swp1 ingress gt6 "matchall $tcflags" + quick_test_span_gre_dir gt6 ingress + mirror_uninstall $swp1 ingress + + log_test "mirror to ip6gre with next-hop remote ($tcflags)" +} + +test_all() +{ + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh b/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh new file mode 100644 index 0000000..2534195 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh @@ -0,0 +1,94 @@ +# SPDX-License-Identifier: GPL-2.0 + +# This is the standard topology for testing mirroring to gretap and ip6gretap +# netdevices. The tests that use it tweak it in one way or another--importantly, +# $swp3 and $h3 need to have addresses set up. +# +# +---------------------+ +---------------------+ +# | H1 | | H2 | +# | + $h1 | | $h2 + | +# | | 192.0.2.1/28 | | 192.0.2.2/28 | | +# +-----|---------------+ +---------------|-----+ +# | | +# +-----|-------------------------------------------------------------|-----+ +# | SW o--> mirror | | +# | +---|-------------------------------------------------------------|---+ | +# | | + $swp1 BR $swp2 + | | +# | +---------------------------------------------------------------------+ | +# | | +# | + $swp3 + gt6 (ip6gretap) + gt4 (gretap) | +# | | : loc=2001:db8:2::1 : loc=192.0.2.129 | +# | | : rem=2001:db8:2::2 : rem=192.0.2.130 | +# | | : ttl=100 : ttl=100 | +# | | : tos=inherit : tos=inherit | +# | | : : | +# +-----|---------------------:----------------------:----------------------+ +# | : : +# +-----|---------------------:----------------------:----------------------+ +# | H3 + $h3 + h3-gt6 (ip6gretap) + h3-gt4 (gretap) | +# | loc=2001:db8:2::2 loc=192.0.2.130 | +# | rem=2001:db8:2::1 rem=192.0.2.129 | +# | ttl=100 ttl=100 | +# | tos=inherit tos=inherit | +# | | +# +-------------------------------------------------------------------------+ + +source mirror_topo_lib.sh + +mirror_gre_topo_h3_create() +{ + mirror_topo_h3_create + + tunnel_create h3-gt4 gretap 192.0.2.130 192.0.2.129 + ip link set h3-gt4 vrf v$h3 + matchall_sink_create h3-gt4 + + tunnel_create h3-gt6 ip6gretap 2001:db8:2::2 2001:db8:2::1 + ip link set h3-gt6 vrf v$h3 + matchall_sink_create h3-gt6 +} + +mirror_gre_topo_h3_destroy() +{ + tunnel_destroy h3-gt6 + tunnel_destroy h3-gt4 + + mirror_topo_h3_destroy +} + +mirror_gre_topo_switch_create() +{ + mirror_topo_switch_create + + tunnel_create gt4 gretap 192.0.2.129 192.0.2.130 \ + ttl 100 tos inherit + + tunnel_create gt6 ip6gretap 2001:db8:2::1 2001:db8:2::2 \ + ttl 100 tos inherit allow-localremote +} + +mirror_gre_topo_switch_destroy() +{ + tunnel_destroy gt6 + tunnel_destroy gt4 + + mirror_topo_switch_destroy +} + +mirror_gre_topo_create() +{ + mirror_topo_h1_create + mirror_topo_h2_create + mirror_gre_topo_h3_create + + mirror_gre_topo_switch_create +} + +mirror_gre_topo_destroy() +{ + mirror_gre_topo_switch_destroy + + mirror_gre_topo_h3_destroy + mirror_topo_h2_destroy + mirror_topo_h1_destroy +} diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_vlan.sh b/tools/testing/selftests/net/forwarding/mirror_gre_vlan.sh new file mode 100755 index 0000000..88cecdb --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_vlan.sh @@ -0,0 +1,92 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test uses standard topology for testing gretap. See +# mirror_gre_topo_lib.sh for more details. +# +# Test for "tc action mirred egress mirror" that mirrors to a gretap netdevice +# whose underlay route points at a vlan device. + +ALL_TESTS=" + test_gretap +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh +source mirror_gre_topo_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + mirror_gre_topo_create + + ip link add name $swp3.555 link $swp3 type vlan id 555 + ip address add dev $swp3.555 192.0.2.129/32 + ip address add dev $swp3.555 2001:db8:2::1/128 + ip link set dev $swp3.555 up + + ip route add 192.0.2.130/32 dev $swp3.555 + ip -6 route add 2001:db8:2::2/128 dev $swp3.555 + + ip link add name $h3.555 link $h3 type vlan id 555 + ip link set dev $h3.555 master v$h3 + ip address add dev $h3.555 192.0.2.130/28 + ip address add dev $h3.555 2001:db8:2::2/64 + ip link set dev $h3.555 up +} + +cleanup() +{ + pre_cleanup + + ip link del dev $h3.555 + ip link del dev $swp3.555 + + mirror_gre_topo_destroy + vrf_cleanup +} + +test_gretap() +{ + full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap" + full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap" +} + +test_all() +{ + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh new file mode 100755 index 0000000..5dbc7a0 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh @@ -0,0 +1,270 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test uses standard topology for testing gretap. See +# mirror_gre_topo_lib.sh for more details. +# +# Test for "tc action mirred egress mirror" when the underlay route points at a +# vlan device on top of a bridge device with vlan filtering (802.1q). + +ALL_TESTS=" + test_gretap + test_ip6gretap + test_gretap_forbidden_cpu + test_ip6gretap_forbidden_cpu + test_gretap_forbidden_egress + test_ip6gretap_forbidden_egress + test_gretap_untagged_egress + test_ip6gretap_untagged_egress + test_gretap_fdb_roaming + test_ip6gretap_fdb_roaming + test_gretap_stp + test_ip6gretap_stp +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh +source mirror_gre_topo_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + mirror_gre_topo_create + + vlan_create br1 555 "" 192.0.2.129/32 2001:db8:2::1/128 + bridge vlan add dev br1 vid 555 self + ip route rep 192.0.2.130/32 dev br1.555 + ip -6 route rep 2001:db8:2::2/128 dev br1.555 + + vlan_create $h3 555 v$h3 192.0.2.130/28 2001:db8:2::2/64 + + ip link set dev $swp3 master br1 + bridge vlan add dev $swp3 vid 555 + bridge vlan add dev $swp2 vid 555 +} + +cleanup() +{ + pre_cleanup + + ip link set dev $swp2 nomaster + ip link set dev $swp3 nomaster + vlan_destroy $h3 555 + vlan_destroy br1 555 + + mirror_gre_topo_destroy + vrf_cleanup +} + +test_vlan_match() +{ + local tundev=$1; shift + local vlan_match=$1; shift + local what=$1; shift + + full_test_span_gre_dir_vlan $tundev ingress "$vlan_match" 8 0 "$what" + full_test_span_gre_dir_vlan $tundev egress "$vlan_match" 0 8 "$what" +} + +test_gretap() +{ + test_vlan_match gt4 'vlan_id 555 vlan_ethtype ip' "mirror to gretap" +} + +test_ip6gretap() +{ + test_vlan_match gt6 'vlan_id 555 vlan_ethtype ipv6' "mirror to ip6gretap" +} + +test_span_gre_forbidden_cpu() +{ + local tundev=$1; shift + local what=$1; shift + + RET=0 + + # Run the pass-test first, to prime neighbor table. + mirror_install $swp1 ingress $tundev "matchall $tcflags" + quick_test_span_gre_dir $tundev ingress + + # Now forbid the VLAN at the bridge and see it fail. + bridge vlan del dev br1 vid 555 self + sleep 1 + fail_test_span_gre_dir $tundev ingress + + bridge vlan add dev br1 vid 555 self + sleep 1 + quick_test_span_gre_dir $tundev ingress + + mirror_uninstall $swp1 ingress + + log_test "$what: vlan forbidden at a bridge ($tcflags)" +} + +test_gretap_forbidden_cpu() +{ + test_span_gre_forbidden_cpu gt4 "mirror to gretap" +} + +test_ip6gretap_forbidden_cpu() +{ + test_span_gre_forbidden_cpu gt6 "mirror to ip6gretap" +} + +test_span_gre_forbidden_egress() +{ + local tundev=$1; shift + local what=$1; shift + + RET=0 + + mirror_install $swp1 ingress $tundev "matchall $tcflags" + quick_test_span_gre_dir $tundev ingress + + bridge vlan del dev $swp3 vid 555 + sleep 1 + fail_test_span_gre_dir $tundev ingress + + bridge vlan add dev $swp3 vid 555 + # Re-prime FDB + arping -I br1.555 192.0.2.130 -fqc 1 + sleep 1 + quick_test_span_gre_dir $tundev ingress + + mirror_uninstall $swp1 ingress + + log_test "$what: vlan forbidden at a bridge egress ($tcflags)" +} + +test_gretap_forbidden_egress() +{ + test_span_gre_forbidden_egress gt4 "mirror to gretap" +} + +test_ip6gretap_forbidden_egress() +{ + test_span_gre_forbidden_egress gt6 "mirror to ip6gretap" +} + +test_span_gre_untagged_egress() +{ + local tundev=$1; shift + local what=$1; shift + + RET=0 + + mirror_install $swp1 ingress $tundev "matchall $tcflags" + + quick_test_span_gre_dir $tundev ingress + quick_test_span_vlan_dir $h3 555 ingress + + bridge vlan add dev $swp3 vid 555 pvid untagged + sleep 1 + quick_test_span_gre_dir $tundev ingress + fail_test_span_vlan_dir $h3 555 ingress + + bridge vlan add dev $swp3 vid 555 + sleep 1 + quick_test_span_gre_dir $tundev ingress + quick_test_span_vlan_dir $h3 555 ingress + + mirror_uninstall $swp1 ingress + + log_test "$what: vlan untagged at a bridge egress ($tcflags)" +} + +test_gretap_untagged_egress() +{ + test_span_gre_untagged_egress gt4 "mirror to gretap" +} + +test_ip6gretap_untagged_egress() +{ + test_span_gre_untagged_egress gt6 "mirror to ip6gretap" +} + +test_span_gre_fdb_roaming() +{ + local tundev=$1; shift + local what=$1; shift + local h3mac=$(mac_get $h3) + + RET=0 + + mirror_install $swp1 ingress $tundev "matchall $tcflags" + quick_test_span_gre_dir $tundev ingress + + bridge fdb del dev $swp3 $h3mac vlan 555 master + bridge fdb add dev $swp2 $h3mac vlan 555 master + sleep 1 + fail_test_span_gre_dir $tundev ingress + + bridge fdb del dev $swp2 $h3mac vlan 555 master + # Re-prime FDB + arping -I br1.555 192.0.2.130 -fqc 1 + sleep 1 + quick_test_span_gre_dir $tundev ingress + + mirror_uninstall $swp1 ingress + + log_test "$what: MAC roaming ($tcflags)" +} + +test_gretap_fdb_roaming() +{ + test_span_gre_fdb_roaming gt4 "mirror to gretap" +} + +test_ip6gretap_fdb_roaming() +{ + test_span_gre_fdb_roaming gt6 "mirror to ip6gretap" +} + +test_gretap_stp() +{ + full_test_span_gre_stp gt4 $swp3 "mirror to gretap" +} + +test_ip6gretap_stp() +{ + full_test_span_gre_stp gt6 $swp3 "mirror to ip6gretap" +} + +test_all() +{ + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_lib.sh b/tools/testing/selftests/net/forwarding/mirror_lib.sh new file mode 100644 index 0000000..d36dc26 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_lib.sh @@ -0,0 +1,132 @@ +# SPDX-License-Identifier: GPL-2.0 + +mirror_install() +{ + local from_dev=$1; shift + local direction=$1; shift + local to_dev=$1; shift + local filter=$1; shift + + tc filter add dev $from_dev $direction \ + pref 1000 $filter \ + action mirred egress mirror dev $to_dev +} + +mirror_uninstall() +{ + local from_dev=$1; shift + local direction=$1; shift + + tc filter del dev $swp1 $direction pref 1000 +} + +mirror_test() +{ + local vrf_name=$1; shift + local sip=$1; shift + local dip=$1; shift + local dev=$1; shift + local pref=$1; shift + local expect=$1; shift + + local t0=$(tc_rule_stats_get $dev $pref) + ip vrf exec $vrf_name \ + ${PING} ${sip:+-I $sip} $dip -c 10 -i 0.1 -w 2 &> /dev/null + local t1=$(tc_rule_stats_get $dev $pref) + local delta=$((t1 - t0)) + # Tolerate a couple stray extra packets. + ((expect <= delta && delta <= expect + 2)) + check_err $? "Expected to capture $expect packets, got $delta." +} + +do_test_span_dir_ips() +{ + local expect=$1; shift + local dev=$1; shift + local direction=$1; shift + local ip1=$1; shift + local ip2=$1; shift + + icmp_capture_install $dev + mirror_test v$h1 $ip1 $ip2 $dev 100 $expect + mirror_test v$h2 $ip2 $ip1 $dev 100 $expect + icmp_capture_uninstall $dev +} + +quick_test_span_dir_ips() +{ + do_test_span_dir_ips 10 "$@" +} + +fail_test_span_dir_ips() +{ + do_test_span_dir_ips 0 "$@" +} + +test_span_dir_ips() +{ + local dev=$1; shift + local direction=$1; shift + local forward_type=$1; shift + local backward_type=$1; shift + local ip1=$1; shift + local ip2=$1; shift + + quick_test_span_dir_ips "$dev" "$direction" "$ip1" "$ip2" + + icmp_capture_install $dev "type $forward_type" + mirror_test v$h1 $ip1 $ip2 $dev 100 10 + icmp_capture_uninstall $dev + + icmp_capture_install $dev "type $backward_type" + mirror_test v$h2 $ip2 $ip1 $dev 100 10 + icmp_capture_uninstall $dev +} + +fail_test_span_dir() +{ + fail_test_span_dir_ips "$@" 192.0.2.1 192.0.2.2 +} + +test_span_dir() +{ + test_span_dir_ips "$@" 192.0.2.1 192.0.2.2 +} + +do_test_span_vlan_dir_ips() +{ + local expect=$1; shift + local dev=$1; shift + local vid=$1; shift + local direction=$1; shift + local ip1=$1; shift + local ip2=$1; shift + + # Install the capture as skip_hw to avoid double-counting of packets. + # The traffic is meant for local box anyway, so will be trapped to + # kernel. + vlan_capture_install $dev "skip_hw vlan_id $vid" + mirror_test v$h1 $ip1 $ip2 $dev 100 $expect + mirror_test v$h2 $ip2 $ip1 $dev 100 $expect + vlan_capture_uninstall $dev +} + +quick_test_span_vlan_dir_ips() +{ + do_test_span_vlan_dir_ips 10 "$@" +} + +fail_test_span_vlan_dir_ips() +{ + do_test_span_vlan_dir_ips 0 "$@" +} + +quick_test_span_vlan_dir() +{ + quick_test_span_vlan_dir_ips "$@" 192.0.2.1 192.0.2.2 +} + +fail_test_span_vlan_dir() +{ + fail_test_span_vlan_dir_ips "$@" 192.0.2.1 192.0.2.2 +} diff --git a/tools/testing/selftests/net/forwarding/mirror_topo_lib.sh b/tools/testing/selftests/net/forwarding/mirror_topo_lib.sh new file mode 100644 index 0000000..04979e5 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_topo_lib.sh @@ -0,0 +1,101 @@ +# SPDX-License-Identifier: GPL-2.0 + +# This is the standard topology for testing mirroring. The tests that use it +# tweak it in one way or another--typically add more devices to the topology. +# +# +---------------------+ +---------------------+ +# | H1 | | H2 | +# | + $h1 | | $h2 + | +# | | 192.0.2.1/28 | | 192.0.2.2/28 | | +# +-----|---------------+ +---------------|-----+ +# | | +# +-----|-------------------------------------------------------------|-----+ +# | SW o--> mirror | | +# | +---|-------------------------------------------------------------|---+ | +# | | + $swp1 BR $swp2 + | | +# | +---------------------------------------------------------------------+ | +# | | +# | + $swp3 | +# +-----|-------------------------------------------------------------------+ +# | +# +-----|-------------------------------------------------------------------+ +# | H3 + $h3 | +# | | +# +-------------------------------------------------------------------------+ + +mirror_topo_h1_create() +{ + simple_if_init $h1 192.0.2.1/28 +} + +mirror_topo_h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/28 +} + +mirror_topo_h2_create() +{ + simple_if_init $h2 192.0.2.2/28 +} + +mirror_topo_h2_destroy() +{ + simple_if_fini $h2 192.0.2.2/28 +} + +mirror_topo_h3_create() +{ + simple_if_init $h3 + tc qdisc add dev $h3 clsact +} + +mirror_topo_h3_destroy() +{ + tc qdisc del dev $h3 clsact + simple_if_fini $h3 +} + +mirror_topo_switch_create() +{ + ip link set dev $swp3 up + + ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 up + + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + + ip link set dev $swp2 master br1 + ip link set dev $swp2 up + + tc qdisc add dev $swp1 clsact +} + +mirror_topo_switch_destroy() +{ + tc qdisc del dev $swp1 clsact + + ip link set dev $swp1 down + ip link set dev $swp2 down + ip link del dev br1 + + ip link set dev $swp3 down +} + +mirror_topo_create() +{ + mirror_topo_h1_create + mirror_topo_h2_create + mirror_topo_h3_create + + mirror_topo_switch_create +} + +mirror_topo_destroy() +{ + mirror_topo_switch_destroy + + mirror_topo_h3_destroy + mirror_topo_h2_destroy + mirror_topo_h1_destroy +} diff --git a/tools/testing/selftests/net/forwarding/mirror_vlan.sh b/tools/testing/selftests/net/forwarding/mirror_vlan.sh new file mode 100755 index 0000000..9ab2ce7 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_vlan.sh @@ -0,0 +1,131 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test uses standard topology for testing mirroring. See mirror_topo_lib.sh +# for more details. +# +# Test for "tc action mirred egress mirror" that mirrors to a vlan device. + +ALL_TESTS=" + test_vlan + test_tagged_vlan +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_topo_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + mirror_topo_create + + vlan_create $swp3 555 + + vlan_create $h3 555 v$h3 + matchall_sink_create $h3.555 + + vlan_create $h1 111 v$h1 192.0.2.17/28 + bridge vlan add dev $swp1 vid 111 + + vlan_create $h2 111 v$h2 192.0.2.18/28 + bridge vlan add dev $swp2 vid 111 +} + +cleanup() +{ + pre_cleanup + + vlan_destroy $h2 111 + vlan_destroy $h1 111 + vlan_destroy $h3 555 + vlan_destroy $swp3 555 + + mirror_topo_destroy + vrf_cleanup +} + +test_vlan_dir() +{ + local direction=$1; shift + local forward_type=$1; shift + local backward_type=$1; shift + + RET=0 + + mirror_install $swp1 $direction $swp3.555 "matchall $tcflags" + test_span_dir "$h3.555" "$direction" "$forward_type" "$backward_type" + mirror_uninstall $swp1 $direction + + log_test "$direction mirror to vlan ($tcflags)" +} + +test_vlan() +{ + test_vlan_dir ingress 8 0 + test_vlan_dir egress 0 8 +} + +test_tagged_vlan_dir() +{ + local direction=$1; shift + local forward_type=$1; shift + local backward_type=$1; shift + + RET=0 + + mirror_install $swp1 $direction $swp3.555 "matchall $tcflags" + do_test_span_vlan_dir_ips 10 "$h3.555" 111 "$direction" \ + 192.0.2.17 192.0.2.18 + do_test_span_vlan_dir_ips 0 "$h3.555" 555 "$direction" \ + 192.0.2.17 192.0.2.18 + mirror_uninstall $swp1 $direction + + log_test "$direction mirror tagged to vlan ($tcflags)" +} + +test_tagged_vlan() +{ + test_tagged_vlan_dir ingress 8 0 + test_tagged_vlan_dir egress 0 8 +} + +test_all() +{ + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + trap_install $h3 ingress + + tests_run + + trap_uninstall $h3 ingress + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/router.sh b/tools/testing/selftests/net/forwarding/router.sh index cc6a14a..a75cb51 100755 --- a/tools/testing/selftests/net/forwarding/router.sh +++ b/tools/testing/selftests/net/forwarding/router.sh @@ -1,6 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +ALL_TESTS="ping_ipv4 ping_ipv6" NUM_NETIFS=4 source lib.sh @@ -114,12 +115,21 @@ cleanup() vrf_cleanup } +ping_ipv4() +{ + ping_test $h1 198.51.100.2 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:2::2 +} + trap cleanup EXIT setup_prepare setup_wait -ping_test $h1 198.51.100.2 -ping6_test $h1 2001:db8:2::2 +tests_run exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/router_multipath.sh b/tools/testing/selftests/net/forwarding/router_multipath.sh index 3bc3510..8b6d0fb 100755 --- a/tools/testing/selftests/net/forwarding/router_multipath.sh +++ b/tools/testing/selftests/net/forwarding/router_multipath.sh @@ -1,6 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +ALL_TESTS="ping_ipv4 ping_ipv6 multipath_test" NUM_NETIFS=8 source lib.sh @@ -191,7 +192,7 @@ multipath_eval() diff=$(echo $weights_ratio - $packets_ratio | bc -l) diff=${diff#-} - test "$(echo "$diff / $weights_ratio > 0.1" | bc -l)" -eq 0 + test "$(echo "$diff / $weights_ratio > 0.15" | bc -l)" -eq 0 check_err $? "Too large discrepancy between expected and measured ratios" log_test "$desc" log_info "Expected ratio $weights_ratio Measured ratio $packets_ratio" @@ -204,13 +205,11 @@ multipath4_test() local weight_rp13=$3 local t0_rp12 t0_rp13 t1_rp12 t1_rp13 local packets_rp12 packets_rp13 - local hash_policy # Transmit multiple flows from h1 to h2 and make sure they are # distributed between both multipath links (rp12 and rp13) # according to the configured weights. - hash_policy=$(sysctl -n net.ipv4.fib_multipath_hash_policy) - sysctl -q -w net.ipv4.fib_multipath_hash_policy=1 + sysctl_set net.ipv4.fib_multipath_hash_policy 1 ip route replace 198.51.100.0/24 vrf vrf-r1 \ nexthop via 169.254.2.22 dev $rp12 weight $weight_rp12 \ nexthop via 169.254.3.23 dev $rp13 weight $weight_rp13 @@ -232,7 +231,7 @@ multipath4_test() ip route replace 198.51.100.0/24 vrf vrf-r1 \ nexthop via 169.254.2.22 dev $rp12 \ nexthop via 169.254.3.23 dev $rp13 - sysctl -q -w net.ipv4.fib_multipath_hash_policy=$hash_policy + sysctl_restore net.ipv4.fib_multipath_hash_policy } multipath6_l4_test() @@ -242,13 +241,11 @@ multipath6_l4_test() local weight_rp13=$3 local t0_rp12 t0_rp13 t1_rp12 t1_rp13 local packets_rp12 packets_rp13 - local hash_policy # Transmit multiple flows from h1 to h2 and make sure they are # distributed between both multipath links (rp12 and rp13) # according to the configured weights. - hash_policy=$(sysctl -n net.ipv6.fib_multipath_hash_policy) - sysctl -q -w net.ipv6.fib_multipath_hash_policy=1 + sysctl_set net.ipv6.fib_multipath_hash_policy 1 ip route replace 2001:db8:2::/64 vrf vrf-r1 \ nexthop via fe80:2::22 dev $rp12 weight $weight_rp12 \ @@ -271,7 +268,7 @@ multipath6_l4_test() nexthop via fe80:2::22 dev $rp12 \ nexthop via fe80:3::23 dev $rp13 - sysctl -q -w net.ipv6.fib_multipath_hash_policy=$hash_policy + sysctl_restore net.ipv6.fib_multipath_hash_policy } multipath6_test() @@ -364,13 +361,21 @@ cleanup() vrf_cleanup } +ping_ipv4() +{ + ping_test $h1 198.51.100.2 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:2::2 +} + trap cleanup EXIT setup_prepare setup_wait -ping_test $h1 198.51.100.2 -ping6_test $h1 2001:db8:2::2 -multipath_test +tests_run exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh index 3a6385e..813d02d 100755 --- a/tools/testing/selftests/net/forwarding/tc_actions.sh +++ b/tools/testing/selftests/net/forwarding/tc_actions.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +ALL_TESTS="gact_drop_and_ok_test mirred_egress_redirect_test \ + mirred_egress_mirror_test gact_trap_test" NUM_NETIFS=4 source tc_common.sh source lib.sh @@ -111,6 +113,10 @@ gact_trap_test() { RET=0 + if [[ "$tcflags" != "skip_sw" ]]; then + return 0; + fi + tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 flower \ skip_hw dst_ip 192.0.2.2 action drop tc filter add dev $swp1 ingress protocol ip pref 3 handle 103 flower \ @@ -179,24 +185,29 @@ cleanup() ip link set $swp1 address $swp1origmac } +mirred_egress_redirect_test() +{ + mirred_egress_test "redirect" +} + +mirred_egress_mirror_test() +{ + mirred_egress_test "mirror" +} + trap cleanup EXIT setup_prepare setup_wait -gact_drop_and_ok_test -mirred_egress_test "redirect" -mirred_egress_test "mirror" +tests_run tc_offload_check if [[ $? -ne 0 ]]; then log_info "Could not test offloaded functionality" else tcflags="skip_sw" - gact_drop_and_ok_test - mirred_egress_test "redirect" - mirred_egress_test "mirror" - gact_trap_test + tests_run fi exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/tc_chains.sh b/tools/testing/selftests/net/forwarding/tc_chains.sh index 2fd1522..d2c783e 100755 --- a/tools/testing/selftests/net/forwarding/tc_chains.sh +++ b/tools/testing/selftests/net/forwarding/tc_chains.sh @@ -1,6 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +ALL_TESTS="unreachable_chain_test gact_goto_chain_test" NUM_NETIFS=2 source tc_common.sh source lib.sh @@ -107,16 +108,14 @@ trap cleanup EXIT setup_prepare setup_wait -unreachable_chain_test -gact_goto_chain_test +tests_run tc_offload_check if [[ $? -ne 0 ]]; then log_info "Could not test offloaded functionality" else tcflags="skip_sw" - unreachable_chain_test - gact_goto_chain_test + tests_run fi exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/tc_flower.sh b/tools/testing/selftests/net/forwarding/tc_flower.sh index 032b882..20d1077 100755 --- a/tools/testing/selftests/net/forwarding/tc_flower.sh +++ b/tools/testing/selftests/net/forwarding/tc_flower.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +ALL_TESTS="match_dst_mac_test match_src_mac_test match_dst_ip_test \ + match_src_ip_test match_ip_flags_test" NUM_NETIFS=2 source tc_common.sh source lib.sh @@ -149,6 +151,74 @@ match_src_ip_test() log_test "src_ip match ($tcflags)" } +match_ip_flags_test() +{ + RET=0 + + tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \ + $tcflags ip_flags frag action continue + tc filter add dev $h2 ingress protocol ip pref 2 handle 102 flower \ + $tcflags ip_flags firstfrag action continue + tc filter add dev $h2 ingress protocol ip pref 3 handle 103 flower \ + $tcflags ip_flags nofirstfrag action continue + tc filter add dev $h2 ingress protocol ip pref 4 handle 104 flower \ + $tcflags ip_flags nofrag action drop + + $MZ $h1 -c 1 -p 1000 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip "frag=0" -q + + tc_check_packets "dev $h2 ingress" 101 1 + check_fail $? "Matched on wrong frag filter (nofrag)" + + tc_check_packets "dev $h2 ingress" 102 1 + check_fail $? "Matched on wrong firstfrag filter (nofrag)" + + tc_check_packets "dev $h2 ingress" 103 1 + check_err $? "Did not match on nofirstfrag filter (nofrag) " + + tc_check_packets "dev $h2 ingress" 104 1 + check_err $? "Did not match on nofrag filter (nofrag)" + + $MZ $h1 -c 1 -p 1000 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip "frag=0,mf" -q + + tc_check_packets "dev $h2 ingress" 101 1 + check_err $? "Did not match on frag filter (1stfrag)" + + tc_check_packets "dev $h2 ingress" 102 1 + check_err $? "Did not match fistfrag filter (1stfrag)" + + tc_check_packets "dev $h2 ingress" 103 1 + check_err $? "Matched on wrong nofirstfrag filter (1stfrag)" + + tc_check_packets "dev $h2 ingress" 104 1 + check_err $? "Match on wrong nofrag filter (1stfrag)" + + $MZ $h1 -c 1 -p 1000 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip "frag=256,mf" -q + $MZ $h1 -c 1 -p 1000 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip "frag=256" -q + + tc_check_packets "dev $h2 ingress" 101 3 + check_err $? "Did not match on frag filter (no1stfrag)" + + tc_check_packets "dev $h2 ingress" 102 1 + check_err $? "Matched on wrong firstfrag filter (no1stfrag)" + + tc_check_packets "dev $h2 ingress" 103 3 + check_err $? "Did not match on nofirstfrag filter (no1stfrag)" + + tc_check_packets "dev $h2 ingress" 104 1 + check_err $? "Matched on nofrag filter (no1stfrag)" + + tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower + tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower + tc filter del dev $h2 ingress protocol ip pref 3 handle 103 flower + tc filter del dev $h2 ingress protocol ip pref 4 handle 104 flower + + log_test "ip_flags match ($tcflags)" +} + setup_prepare() { h1=${NETIFS[p1]} @@ -177,20 +247,14 @@ trap cleanup EXIT setup_prepare setup_wait -match_dst_mac_test -match_src_mac_test -match_dst_ip_test -match_src_ip_test +tests_run tc_offload_check if [[ $? -ne 0 ]]; then log_info "Could not test offloaded functionality" else tcflags="skip_sw" - match_dst_mac_test - match_src_mac_test - match_dst_ip_test - match_src_ip_test + tests_run fi exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/tc_shblocks.sh b/tools/testing/selftests/net/forwarding/tc_shblocks.sh index 077b980..b5b9172 100755 --- a/tools/testing/selftests/net/forwarding/tc_shblocks.sh +++ b/tools/testing/selftests/net/forwarding/tc_shblocks.sh @@ -1,6 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +ALL_TESTS="shared_block_test" NUM_NETIFS=4 source tc_common.sh source lib.sh @@ -109,14 +110,14 @@ trap cleanup EXIT setup_prepare setup_wait -shared_block_test +tests_run tc_offload_check if [[ $? -ne 0 ]]; then log_info "Could not test offloaded functionality" else tcflags="skip_sw" - shared_block_test + tests_run fi exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/msg_zerocopy.sh b/tools/testing/selftests/net/msg_zerocopy.sh index d571d21..c43c6de 100755 --- a/tools/testing/selftests/net/msg_zerocopy.sh +++ b/tools/testing/selftests/net/msg_zerocopy.sh @@ -21,6 +21,14 @@ readonly DADDR6='fd::2' readonly path_sysctl_mem="net.core.optmem_max" +# No arguments: automated test +if [[ "$#" -eq "0" ]]; then + $0 4 tcp -t 1 + $0 6 tcp -t 1 + echo "OK. All tests passed" + exit 0 +fi + # Argument parsing if [[ "$#" -lt "2" ]]; then echo "Usage: $0 [4|6] [tcp|udp|raw|raw_hdrincl|packet|packet_dgram] <args>" diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 7514f93..f8cc38a 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -371,7 +371,7 @@ test_pmtu_vti6_link_add_mtu() { fail=0 - min=1280 + min=68 # vti6 can carry IPv4 packets too max=$((65535 - 40)) # Check invalid values first for v in $((min - 1)) $((max + 1)); do @@ -387,7 +387,7 @@ test_pmtu_vti6_link_add_mtu() { done # Now check valid values - for v in 1280 1300 $((65535 - 40)); do + for v in 68 1280 1300 $((65535 - 40)); do ${ns_a} ip link add vti6_a mtu ${v} type vti6 local ${veth6_a_addr} remote ${veth6_b_addr} key 10 mtu="$(link_get_mtu "${ns_a}" vti6_a)" ${ns_a} ip link del vti6_a diff --git a/tools/testing/selftests/net/psock_snd.c b/tools/testing/selftests/net/psock_snd.c new file mode 100644 index 0000000..7d15e10 --- /dev/null +++ b/tools/testing/selftests/net/psock_snd.c @@ -0,0 +1,397 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE + +#include <arpa/inet.h> +#include <errno.h> +#include <error.h> +#include <fcntl.h> +#include <limits.h> +#include <linux/filter.h> +#include <linux/bpf.h> +#include <linux/if_packet.h> +#include <linux/if_vlan.h> +#include <linux/virtio_net.h> +#include <net/if.h> +#include <net/ethernet.h> +#include <netinet/ip.h> +#include <netinet/udp.h> +#include <poll.h> +#include <sched.h> +#include <stdbool.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/socket.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <unistd.h> + +#include "psock_lib.h" + +static bool cfg_use_bind; +static bool cfg_use_csum_off; +static bool cfg_use_csum_off_bad; +static bool cfg_use_dgram; +static bool cfg_use_gso; +static bool cfg_use_qdisc_bypass; +static bool cfg_use_vlan; +static bool cfg_use_vnet; + +static char *cfg_ifname = "lo"; +static int cfg_mtu = 1500; +static int cfg_payload_len = DATA_LEN; +static int cfg_truncate_len = INT_MAX; +static uint16_t cfg_port = 8000; + +/* test sending up to max mtu + 1 */ +#define TEST_SZ (sizeof(struct virtio_net_hdr) + ETH_HLEN + ETH_MAX_MTU + 1) + +static char tbuf[TEST_SZ], rbuf[TEST_SZ]; + +static unsigned long add_csum_hword(const uint16_t *start, int num_u16) +{ + unsigned long sum = 0; + int i; + + for (i = 0; i < num_u16; i++) + sum += start[i]; + + return sum; +} + +static uint16_t build_ip_csum(const uint16_t *start, int num_u16, + unsigned long sum) +{ + sum += add_csum_hword(start, num_u16); + + while (sum >> 16) + sum = (sum & 0xffff) + (sum >> 16); + + return ~sum; +} + +static int build_vnet_header(void *header) +{ + struct virtio_net_hdr *vh = header; + + vh->hdr_len = ETH_HLEN + sizeof(struct iphdr) + sizeof(struct udphdr); + + if (cfg_use_csum_off) { + vh->flags |= VIRTIO_NET_HDR_F_NEEDS_CSUM; + vh->csum_start = ETH_HLEN + sizeof(struct iphdr); + vh->csum_offset = __builtin_offsetof(struct udphdr, check); + + /* position check field exactly one byte beyond end of packet */ + if (cfg_use_csum_off_bad) + vh->csum_start += sizeof(struct udphdr) + cfg_payload_len - + vh->csum_offset - 1; + } + + if (cfg_use_gso) { + vh->gso_type = VIRTIO_NET_HDR_GSO_UDP; + vh->gso_size = cfg_mtu - sizeof(struct iphdr); + } + + return sizeof(*vh); +} + +static int build_eth_header(void *header) +{ + struct ethhdr *eth = header; + + if (cfg_use_vlan) { + uint16_t *tag = header + ETH_HLEN; + + eth->h_proto = htons(ETH_P_8021Q); + tag[1] = htons(ETH_P_IP); + return ETH_HLEN + 4; + } + + eth->h_proto = htons(ETH_P_IP); + return ETH_HLEN; +} + +static int build_ipv4_header(void *header, int payload_len) +{ + struct iphdr *iph = header; + + iph->ihl = 5; + iph->version = 4; + iph->ttl = 8; + iph->tot_len = htons(sizeof(*iph) + sizeof(struct udphdr) + payload_len); + iph->id = htons(1337); + iph->protocol = IPPROTO_UDP; + iph->saddr = htonl((172 << 24) | (17 << 16) | 2); + iph->daddr = htonl((172 << 24) | (17 << 16) | 1); + iph->check = build_ip_csum((void *) iph, iph->ihl << 1, 0); + + return iph->ihl << 2; +} + +static int build_udp_header(void *header, int payload_len) +{ + const int alen = sizeof(uint32_t); + struct udphdr *udph = header; + int len = sizeof(*udph) + payload_len; + + udph->source = htons(9); + udph->dest = htons(cfg_port); + udph->len = htons(len); + + if (cfg_use_csum_off) + udph->check = build_ip_csum(header - (2 * alen), alen, + htons(IPPROTO_UDP) + udph->len); + else + udph->check = 0; + + return sizeof(*udph); +} + +static int build_packet(int payload_len) +{ + int off = 0; + + off += build_vnet_header(tbuf); + off += build_eth_header(tbuf + off); + off += build_ipv4_header(tbuf + off, payload_len); + off += build_udp_header(tbuf + off, payload_len); + + if (off + payload_len > sizeof(tbuf)) + error(1, 0, "payload length exceeds max"); + + memset(tbuf + off, DATA_CHAR, payload_len); + + return off + payload_len; +} + +static void do_bind(int fd) +{ + struct sockaddr_ll laddr = {0}; + + laddr.sll_family = AF_PACKET; + laddr.sll_protocol = htons(ETH_P_IP); + laddr.sll_ifindex = if_nametoindex(cfg_ifname); + if (!laddr.sll_ifindex) + error(1, errno, "if_nametoindex"); + + if (bind(fd, (void *)&laddr, sizeof(laddr))) + error(1, errno, "bind"); +} + +static void do_send(int fd, char *buf, int len) +{ + int ret; + + if (!cfg_use_vnet) { + buf += sizeof(struct virtio_net_hdr); + len -= sizeof(struct virtio_net_hdr); + } + if (cfg_use_dgram) { + buf += ETH_HLEN; + len -= ETH_HLEN; + } + + if (cfg_use_bind) { + ret = write(fd, buf, len); + } else { + struct sockaddr_ll laddr = {0}; + + laddr.sll_protocol = htons(ETH_P_IP); + laddr.sll_ifindex = if_nametoindex(cfg_ifname); + if (!laddr.sll_ifindex) + error(1, errno, "if_nametoindex"); + + ret = sendto(fd, buf, len, 0, (void *)&laddr, sizeof(laddr)); + } + + if (ret == -1) + error(1, errno, "write"); + if (ret != len) + error(1, 0, "write: %u %u", ret, len); + + fprintf(stderr, "tx: %u\n", ret); +} + +static int do_tx(void) +{ + const int one = 1; + int fd, len; + + fd = socket(PF_PACKET, cfg_use_dgram ? SOCK_DGRAM : SOCK_RAW, 0); + if (fd == -1) + error(1, errno, "socket t"); + + if (cfg_use_bind) + do_bind(fd); + + if (cfg_use_qdisc_bypass && + setsockopt(fd, SOL_PACKET, PACKET_QDISC_BYPASS, &one, sizeof(one))) + error(1, errno, "setsockopt qdisc bypass"); + + if (cfg_use_vnet && + setsockopt(fd, SOL_PACKET, PACKET_VNET_HDR, &one, sizeof(one))) + error(1, errno, "setsockopt vnet"); + + len = build_packet(cfg_payload_len); + + if (cfg_truncate_len < len) + len = cfg_truncate_len; + + do_send(fd, tbuf, len); + + if (close(fd)) + error(1, errno, "close t"); + + return len; +} + +static int setup_rx(void) +{ + struct timeval tv = { .tv_usec = 100 * 1000 }; + struct sockaddr_in raddr = {0}; + int fd; + + fd = socket(PF_INET, SOCK_DGRAM, 0); + if (fd == -1) + error(1, errno, "socket r"); + + if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv))) + error(1, errno, "setsockopt rcv timeout"); + + raddr.sin_family = AF_INET; + raddr.sin_port = htons(cfg_port); + raddr.sin_addr.s_addr = htonl(INADDR_ANY); + + if (bind(fd, (void *)&raddr, sizeof(raddr))) + error(1, errno, "bind r"); + + return fd; +} + +static void do_rx(int fd, int expected_len, char *expected) +{ + int ret; + + ret = recv(fd, rbuf, sizeof(rbuf), 0); + if (ret == -1) + error(1, errno, "recv"); + if (ret != expected_len) + error(1, 0, "recv: %u != %u", ret, expected_len); + + if (memcmp(rbuf, expected, ret)) + error(1, 0, "recv: data mismatch"); + + fprintf(stderr, "rx: %u\n", ret); +} + +static int setup_sniffer(void) +{ + struct timeval tv = { .tv_usec = 100 * 1000 }; + int fd; + + fd = socket(PF_PACKET, SOCK_RAW, 0); + if (fd == -1) + error(1, errno, "socket p"); + + if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv))) + error(1, errno, "setsockopt rcv timeout"); + + pair_udp_setfilter(fd); + do_bind(fd); + + return fd; +} + +static void parse_opts(int argc, char **argv) +{ + int c; + + while ((c = getopt(argc, argv, "bcCdgl:qt:vV")) != -1) { + switch (c) { + case 'b': + cfg_use_bind = true; + break; + case 'c': + cfg_use_csum_off = true; + break; + case 'C': + cfg_use_csum_off_bad = true; + break; + case 'd': + cfg_use_dgram = true; + break; + case 'g': + cfg_use_gso = true; + break; + case 'l': + cfg_payload_len = strtoul(optarg, NULL, 0); + break; + case 'q': + cfg_use_qdisc_bypass = true; + break; + case 't': + cfg_truncate_len = strtoul(optarg, NULL, 0); + break; + case 'v': + cfg_use_vnet = true; + break; + case 'V': + cfg_use_vlan = true; + break; + default: + error(1, 0, "%s: parse error", argv[0]); + } + } + + if (cfg_use_vlan && cfg_use_dgram) + error(1, 0, "option vlan (-V) conflicts with dgram (-d)"); + + if (cfg_use_csum_off && !cfg_use_vnet) + error(1, 0, "option csum offload (-c) requires vnet (-v)"); + + if (cfg_use_csum_off_bad && !cfg_use_csum_off) + error(1, 0, "option csum bad (-C) requires csum offload (-c)"); + + if (cfg_use_gso && !cfg_use_csum_off) + error(1, 0, "option gso (-g) requires csum offload (-c)"); +} + +static void run_test(void) +{ + int fdr, fds, total_len; + + fdr = setup_rx(); + fds = setup_sniffer(); + + total_len = do_tx(); + + /* BPF filter accepts only this length, vlan changes MAC */ + if (cfg_payload_len == DATA_LEN && !cfg_use_vlan) + do_rx(fds, total_len - sizeof(struct virtio_net_hdr), + tbuf + sizeof(struct virtio_net_hdr)); + + do_rx(fdr, cfg_payload_len, tbuf + total_len - cfg_payload_len); + + if (close(fds)) + error(1, errno, "close s"); + if (close(fdr)) + error(1, errno, "close r"); +} + +int main(int argc, char **argv) +{ + parse_opts(argc, argv); + + if (system("ip link set dev lo mtu 1500")) + error(1, errno, "ip link set mtu"); + if (system("ip addr add dev lo 172.17.0.1/24")) + error(1, errno, "ip addr add"); + + run_test(); + + fprintf(stderr, "OK\n\n"); + return 0; +} diff --git a/tools/testing/selftests/net/psock_snd.sh b/tools/testing/selftests/net/psock_snd.sh new file mode 100755 index 0000000..6331d91 --- /dev/null +++ b/tools/testing/selftests/net/psock_snd.sh @@ -0,0 +1,98 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Run a series of packet socket send regression tests + +set -e + +readonly mtu=1500 +readonly iphlen=20 +readonly udphlen=8 + +readonly vnet_hlen=10 +readonly eth_hlen=14 + +readonly mss="$((${mtu} - ${iphlen} - ${udphlen}))" +readonly mss_exceeds="$((${mss} + 1))" + +readonly max_mtu=65535 +readonly max_mss="$((${max_mtu} - ${iphlen} - ${udphlen}))" +readonly max_mss_exceeds="$((${max_mss} + 1))" + +# functional checks (not a full cross-product) + +echo "dgram" +./in_netns.sh ./psock_snd -d + +echo "dgram bind" +./in_netns.sh ./psock_snd -d -b + +echo "raw" +./in_netns.sh ./psock_snd + +echo "raw bind" +./in_netns.sh ./psock_snd -b + +echo "raw qdisc bypass" +./in_netns.sh ./psock_snd -q + +echo "raw vlan" +./in_netns.sh ./psock_snd -V + +echo "raw vnet hdr" +./in_netns.sh ./psock_snd -v + +echo "raw csum_off" +./in_netns.sh ./psock_snd -v -c + +echo "raw csum_off with bad offset (fails)" +(! ./in_netns.sh ./psock_snd -v -c -C) + + +# bounds check: send {max, max + 1, min, min - 1} lengths + +echo "raw min size" +./in_netns.sh ./psock_snd -l 0 + +echo "raw mtu size" +./in_netns.sh ./psock_snd -l "${mss}" + +echo "raw mtu size + 1 (fails)" +(! ./in_netns.sh ./psock_snd -l "${mss_exceeds}") + +# fails due to ARPHRD_ETHER check in packet_extra_vlan_len_allowed +# +# echo "raw vlan mtu size" +# ./in_netns.sh ./psock_snd -V -l "${mss}" + +echo "raw vlan mtu size + 1 (fails)" +(! ./in_netns.sh ./psock_snd -V -l "${mss_exceeds}") + +echo "dgram mtu size" +./in_netns.sh ./psock_snd -d -l "${mss}" + +echo "dgram mtu size + 1 (fails)" +(! ./in_netns.sh ./psock_snd -d -l "${mss_exceeds}") + +echo "raw truncate hlen (fails: does not arrive)" +(! ./in_netns.sh ./psock_snd -t "$((${vnet_hlen} + ${eth_hlen}))") + +echo "raw truncate hlen - 1 (fails: EINVAL)" +(! ./in_netns.sh ./psock_snd -t "$((${vnet_hlen} + ${eth_hlen} - 1))") + + +# gso checks: implies -l, because with gso len must exceed gso_size + +echo "raw gso min size" +./in_netns.sh ./psock_snd -v -c -g -l "${mss_exceeds}" + +echo "raw gso min size - 1 (fails)" +(! ./in_netns.sh ./psock_snd -v -c -g -l "${mss}") + +echo "raw gso max size" +./in_netns.sh ./psock_snd -v -c -g -l "${max_mss}" + +echo "raw gso max size + 1 (fails)" +(! ./in_netns.sh ./psock_snd -v -c -g -l "${max_mss_exceeds}") + +echo "OK. All tests passed" diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index fb37678..0d7a44f 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -505,6 +505,108 @@ kci_test_macsec() echo "PASS: macsec" } +#------------------------------------------------------------------- +# Example commands +# ip x s add proto esp src 14.0.0.52 dst 14.0.0.70 \ +# spi 0x07 mode transport reqid 0x07 replay-window 32 \ +# aead 'rfc4106(gcm(aes))' 1234567890123456dcba 128 \ +# sel src 14.0.0.52/24 dst 14.0.0.70/24 +# ip x p add dir out src 14.0.0.52/24 dst 14.0.0.70/24 \ +# tmpl proto esp src 14.0.0.52 dst 14.0.0.70 \ +# spi 0x07 mode transport reqid 0x07 +# +# Subcommands not tested +# ip x s update +# ip x s allocspi +# ip x s deleteall +# ip x p update +# ip x p deleteall +# ip x p set +#------------------------------------------------------------------- +kci_test_ipsec() +{ + srcip="14.0.0.52" + dstip="14.0.0.70" + algo="aead rfc4106(gcm(aes)) 0x3132333435363738393031323334353664636261 128" + + # flush to be sure there's nothing configured + ip x s flush ; ip x p flush + check_err $? + + # start the monitor in the background + tmpfile=`mktemp ipsectestXXX` + ip x m > $tmpfile & + mpid=$! + sleep 0.2 + + ipsecid="proto esp src $srcip dst $dstip spi 0x07" + ip x s add $ipsecid \ + mode transport reqid 0x07 replay-window 32 \ + $algo sel src $srcip/24 dst $dstip/24 + check_err $? + + lines=`ip x s list | grep $srcip | grep $dstip | wc -l` + test $lines -eq 2 + check_err $? + + ip x s count | grep -q "SAD count 1" + check_err $? + + lines=`ip x s get $ipsecid | grep $srcip | grep $dstip | wc -l` + test $lines -eq 2 + check_err $? + + ip x s delete $ipsecid + check_err $? + + lines=`ip x s list | wc -l` + test $lines -eq 0 + check_err $? + + ipsecsel="dir out src $srcip/24 dst $dstip/24" + ip x p add $ipsecsel \ + tmpl proto esp src $srcip dst $dstip \ + spi 0x07 mode transport reqid 0x07 + check_err $? + + lines=`ip x p list | grep $srcip | grep $dstip | wc -l` + test $lines -eq 2 + check_err $? + + ip x p count | grep -q "SPD IN 0 OUT 1 FWD 0" + check_err $? + + lines=`ip x p get $ipsecsel | grep $srcip | grep $dstip | wc -l` + test $lines -eq 2 + check_err $? + + ip x p delete $ipsecsel + check_err $? + + lines=`ip x p list | wc -l` + test $lines -eq 0 + check_err $? + + # check the monitor results + kill $mpid + lines=`wc -l $tmpfile | cut "-d " -f1` + test $lines -eq 20 + check_err $? + rm -rf $tmpfile + + # clean up any leftovers + ip x s flush + check_err $? + ip x p flush + check_err $? + + if [ $ret -ne 0 ]; then + echo "FAIL: ipsec" + return 1 + fi + echo "PASS: ipsec" +} + kci_test_gretap() { testns="testns" @@ -758,6 +860,7 @@ kci_test_rtnl() kci_test_vrf kci_test_encap kci_test_macsec + kci_test_ipsec kci_del_dummy } diff --git a/tools/testing/selftests/net/tcp_inq.c b/tools/testing/selftests/net/tcp_inq.c new file mode 100644 index 0000000..d044b29 --- /dev/null +++ b/tools/testing/selftests/net/tcp_inq.c @@ -0,0 +1,189 @@ +/* + * Copyright 2018 Google Inc. + * Author: Soheil Hassas Yeganeh (soheil@google.com) + * + * Simple example on how to use TCP_INQ and TCP_CM_INQ. + * + * License (GPLv2): + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. * See the GNU General Public License for + * more details. + */ +#define _GNU_SOURCE + +#include <error.h> +#include <netinet/in.h> +#include <netinet/tcp.h> +#include <pthread.h> +#include <stdio.h> +#include <errno.h> +#include <stdlib.h> +#include <string.h> +#include <sys/socket.h> +#include <unistd.h> + +#ifndef TCP_INQ +#define TCP_INQ 36 +#endif + +#ifndef TCP_CM_INQ +#define TCP_CM_INQ TCP_INQ +#endif + +#define BUF_SIZE 8192 +#define CMSG_SIZE 32 + +static int family = AF_INET6; +static socklen_t addr_len = sizeof(struct sockaddr_in6); +static int port = 4974; + +static void setup_loopback_addr(int family, struct sockaddr_storage *sockaddr) +{ + struct sockaddr_in6 *addr6 = (void *) sockaddr; + struct sockaddr_in *addr4 = (void *) sockaddr; + + switch (family) { + case PF_INET: + memset(addr4, 0, sizeof(*addr4)); + addr4->sin_family = AF_INET; + addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); + addr4->sin_port = htons(port); + break; + case PF_INET6: + memset(addr6, 0, sizeof(*addr6)); + addr6->sin6_family = AF_INET6; + addr6->sin6_addr = in6addr_loopback; + addr6->sin6_port = htons(port); + break; + default: + error(1, 0, "illegal family"); + } +} + +void *start_server(void *arg) +{ + int server_fd = (int)(unsigned long)arg; + struct sockaddr_in addr; + socklen_t addrlen = sizeof(addr); + char *buf; + int fd; + int r; + + buf = malloc(BUF_SIZE); + + for (;;) { + fd = accept(server_fd, (struct sockaddr *)&addr, &addrlen); + if (fd == -1) { + perror("accept"); + break; + } + do { + r = send(fd, buf, BUF_SIZE, 0); + } while (r < 0 && errno == EINTR); + if (r < 0) + perror("send"); + if (r != BUF_SIZE) + fprintf(stderr, "can only send %d bytes\n", r); + /* TCP_INQ can overestimate in-queue by one byte if we send + * the FIN packet. Sleep for 1 second, so that the client + * likely invoked recvmsg(). + */ + sleep(1); + close(fd); + } + + free(buf); + close(server_fd); + pthread_exit(0); +} + +int main(int argc, char *argv[]) +{ + struct sockaddr_storage listen_addr, addr; + int c, one = 1, inq = -1; + pthread_t server_thread; + char cmsgbuf[CMSG_SIZE]; + struct iovec iov[1]; + struct cmsghdr *cm; + struct msghdr msg; + int server_fd, fd; + char *buf; + + while ((c = getopt(argc, argv, "46p:")) != -1) { + switch (c) { + case '4': + family = PF_INET; + addr_len = sizeof(struct sockaddr_in); + break; + case '6': + family = PF_INET6; + addr_len = sizeof(struct sockaddr_in6); + break; + case 'p': + port = atoi(optarg); + break; + } + } + + server_fd = socket(family, SOCK_STREAM, 0); + if (server_fd < 0) + error(1, errno, "server socket"); + setup_loopback_addr(family, &listen_addr); + if (setsockopt(server_fd, SOL_SOCKET, SO_REUSEADDR, + &one, sizeof(one)) != 0) + error(1, errno, "setsockopt(SO_REUSEADDR)"); + if (bind(server_fd, (const struct sockaddr *)&listen_addr, + addr_len) == -1) + error(1, errno, "bind"); + if (listen(server_fd, 128) == -1) + error(1, errno, "listen"); + if (pthread_create(&server_thread, NULL, start_server, + (void *)(unsigned long)server_fd) != 0) + error(1, errno, "pthread_create"); + + fd = socket(family, SOCK_STREAM, 0); + if (fd < 0) + error(1, errno, "client socket"); + setup_loopback_addr(family, &addr); + if (connect(fd, (const struct sockaddr *)&addr, addr_len) == -1) + error(1, errno, "connect"); + if (setsockopt(fd, SOL_TCP, TCP_INQ, &one, sizeof(one)) != 0) + error(1, errno, "setsockopt(TCP_INQ)"); + + msg.msg_name = NULL; + msg.msg_namelen = 0; + msg.msg_iov = iov; + msg.msg_iovlen = 1; + msg.msg_control = cmsgbuf; + msg.msg_controllen = sizeof(cmsgbuf); + msg.msg_flags = 0; + + buf = malloc(BUF_SIZE); + iov[0].iov_base = buf; + iov[0].iov_len = BUF_SIZE / 2; + + if (recvmsg(fd, &msg, 0) != iov[0].iov_len) + error(1, errno, "recvmsg"); + if (msg.msg_flags & MSG_CTRUNC) + error(1, 0, "control message is truncated"); + + for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) + if (cm->cmsg_level == SOL_TCP && cm->cmsg_type == TCP_CM_INQ) + inq = *((int *) CMSG_DATA(cm)); + + if (inq != BUF_SIZE - iov[0].iov_len) { + fprintf(stderr, "unexpected inq: %d\n", inq); + exit(1); + } + + printf("PASSED\n"); + free(buf); + close(fd); + return 0; +} diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c new file mode 100644 index 0000000..77f7627 --- /dev/null +++ b/tools/testing/selftests/net/tcp_mmap.c @@ -0,0 +1,447 @@ +/* + * Copyright 2018 Google Inc. + * Author: Eric Dumazet (edumazet@google.com) + * + * Reference program demonstrating tcp mmap() usage, + * and SO_RCVLOWAT hints for receiver. + * + * Note : NIC with header split is needed to use mmap() on TCP : + * Each incoming frame must be a multiple of PAGE_SIZE bytes of TCP payload. + * + * How to use on loopback interface : + * + * ifconfig lo mtu 61512 # 15*4096 + 40 (ipv6 header) + 32 (TCP with TS option header) + * tcp_mmap -s -z & + * tcp_mmap -H ::1 -z + * + * Or leave default lo mtu, but use -M option to set TCP_MAXSEG option to (4096 + 12) + * (4096 : page size on x86, 12: TCP TS option length) + * tcp_mmap -s -z -M $((4096+12)) & + * tcp_mmap -H ::1 -z -M $((4096+12)) + * + * Note: -z option on sender uses MSG_ZEROCOPY, which forces a copy when packets go through loopback interface. + * We might use sendfile() instead, but really this test program is about mmap(), for receivers ;) + * + * $ ./tcp_mmap -s & # Without mmap() + * $ for i in {1..4}; do ./tcp_mmap -H ::1 -z ; done + * received 32768 MB (0 % mmap'ed) in 14.1157 s, 19.4732 Gbit + * cpu usage user:0.057 sys:7.815, 240.234 usec per MB, 65531 c-switches + * received 32768 MB (0 % mmap'ed) in 14.6833 s, 18.7204 Gbit + * cpu usage user:0.043 sys:8.103, 248.596 usec per MB, 65524 c-switches + * received 32768 MB (0 % mmap'ed) in 11.143 s, 24.6682 Gbit + * cpu usage user:0.044 sys:6.576, 202.026 usec per MB, 65519 c-switches + * received 32768 MB (0 % mmap'ed) in 14.9056 s, 18.4413 Gbit + * cpu usage user:0.036 sys:8.193, 251.129 usec per MB, 65530 c-switches + * $ kill %1 # kill tcp_mmap server + * + * $ ./tcp_mmap -s -z & # With mmap() + * $ for i in {1..4}; do ./tcp_mmap -H ::1 -z ; done + * received 32768 MB (99.9939 % mmap'ed) in 6.73792 s, 40.7956 Gbit + * cpu usage user:0.045 sys:2.827, 87.6465 usec per MB, 65532 c-switches + * received 32768 MB (99.9939 % mmap'ed) in 7.26732 s, 37.8238 Gbit + * cpu usage user:0.037 sys:3.087, 95.3369 usec per MB, 65532 c-switches + * received 32768 MB (99.9939 % mmap'ed) in 7.61661 s, 36.0893 Gbit + * cpu usage user:0.046 sys:3.559, 110.016 usec per MB, 65529 c-switches + * received 32768 MB (99.9939 % mmap'ed) in 7.43764 s, 36.9577 Gbit + * cpu usage user:0.035 sys:3.467, 106.873 usec per MB, 65530 c-switches + * + * License (GPLv2): + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. * See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + */ +#define _GNU_SOURCE +#include <pthread.h> +#include <sys/types.h> +#include <fcntl.h> +#include <error.h> +#include <sys/socket.h> +#include <sys/mman.h> +#include <sys/resource.h> +#include <unistd.h> +#include <string.h> +#include <stdlib.h> +#include <stdio.h> +#include <errno.h> +#include <time.h> +#include <sys/time.h> +#include <netinet/in.h> +#include <arpa/inet.h> +#include <poll.h> +#include <linux/tcp.h> +#include <assert.h> + +#ifndef MSG_ZEROCOPY +#define MSG_ZEROCOPY 0x4000000 +#endif + +#define FILE_SZ (1UL << 35) +static int cfg_family = AF_INET6; +static socklen_t cfg_alen = sizeof(struct sockaddr_in6); +static int cfg_port = 8787; + +static int rcvbuf; /* Default: autotuning. Can be set with -r <integer> option */ +static int sndbuf; /* Default: autotuning. Can be set with -w <integer> option */ +static int zflg; /* zero copy option. (MSG_ZEROCOPY for sender, mmap() for receiver */ +static int xflg; /* hash received data (simple xor) (-h option) */ +static int keepflag; /* -k option: receiver shall keep all received file in memory (no munmap() calls) */ + +static int chunk_size = 512*1024; + +unsigned long htotal; + +static inline void prefetch(const void *x) +{ +#if defined(__x86_64__) + asm volatile("prefetcht0 %P0" : : "m" (*(const char *)x)); +#endif +} + +void hash_zone(void *zone, unsigned int length) +{ + unsigned long temp = htotal; + + while (length >= 8*sizeof(long)) { + prefetch(zone + 384); + temp ^= *(unsigned long *)zone; + temp ^= *(unsigned long *)(zone + sizeof(long)); + temp ^= *(unsigned long *)(zone + 2*sizeof(long)); + temp ^= *(unsigned long *)(zone + 3*sizeof(long)); + temp ^= *(unsigned long *)(zone + 4*sizeof(long)); + temp ^= *(unsigned long *)(zone + 5*sizeof(long)); + temp ^= *(unsigned long *)(zone + 6*sizeof(long)); + temp ^= *(unsigned long *)(zone + 7*sizeof(long)); + zone += 8*sizeof(long); + length -= 8*sizeof(long); + } + while (length >= 1) { + temp ^= *(unsigned char *)zone; + zone += 1; + length--; + } + htotal = temp; +} + +void *child_thread(void *arg) +{ + unsigned long total_mmap = 0, total = 0; + struct tcp_zerocopy_receive zc; + unsigned long delta_usec; + int flags = MAP_SHARED; + struct timeval t0, t1; + char *buffer = NULL; + void *addr = NULL; + double throughput; + struct rusage ru; + int lu, fd; + + fd = (int)(unsigned long)arg; + + gettimeofday(&t0, NULL); + + fcntl(fd, F_SETFL, O_NDELAY); + buffer = malloc(chunk_size); + if (!buffer) { + perror("malloc"); + goto error; + } + if (zflg) { + addr = mmap(NULL, chunk_size, PROT_READ, flags, fd, 0); + if (addr == (void *)-1) + zflg = 0; + } + while (1) { + struct pollfd pfd = { .fd = fd, .events = POLLIN, }; + int sub; + + poll(&pfd, 1, 10000); + if (zflg) { + socklen_t zc_len = sizeof(zc); + int res; + + zc.address = (__u64)addr; + zc.length = chunk_size; + zc.recv_skip_hint = 0; + res = getsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, + &zc, &zc_len); + if (res == -1) + break; + + if (zc.length) { + assert(zc.length <= chunk_size); + total_mmap += zc.length; + if (xflg) + hash_zone(addr, zc.length); + total += zc.length; + } + if (zc.recv_skip_hint) { + assert(zc.recv_skip_hint <= chunk_size); + lu = read(fd, buffer, zc.recv_skip_hint); + if (lu > 0) { + if (xflg) + hash_zone(buffer, lu); + total += lu; + } + } + continue; + } + sub = 0; + while (sub < chunk_size) { + lu = read(fd, buffer + sub, chunk_size - sub); + if (lu == 0) + goto end; + if (lu < 0) + break; + if (xflg) + hash_zone(buffer + sub, lu); + total += lu; + sub += lu; + } + } +end: + gettimeofday(&t1, NULL); + delta_usec = (t1.tv_sec - t0.tv_sec) * 1000000 + t1.tv_usec - t0.tv_usec; + + throughput = 0; + if (delta_usec) + throughput = total * 8.0 / (double)delta_usec / 1000.0; + getrusage(RUSAGE_THREAD, &ru); + if (total > 1024*1024) { + unsigned long total_usec; + unsigned long mb = total >> 20; + total_usec = 1000000*ru.ru_utime.tv_sec + ru.ru_utime.tv_usec + + 1000000*ru.ru_stime.tv_sec + ru.ru_stime.tv_usec; + printf("received %lg MB (%lg %% mmap'ed) in %lg s, %lg Gbit\n" + " cpu usage user:%lg sys:%lg, %lg usec per MB, %lu c-switches\n", + total / (1024.0 * 1024.0), + 100.0*total_mmap/total, + (double)delta_usec / 1000000.0, + throughput, + (double)ru.ru_utime.tv_sec + (double)ru.ru_utime.tv_usec / 1000000.0, + (double)ru.ru_stime.tv_sec + (double)ru.ru_stime.tv_usec / 1000000.0, + (double)total_usec/mb, + ru.ru_nvcsw); + } +error: + free(buffer); + close(fd); + if (zflg) + munmap(addr, chunk_size); + pthread_exit(0); +} + +static void apply_rcvsnd_buf(int fd) +{ + if (rcvbuf && setsockopt(fd, SOL_SOCKET, + SO_RCVBUF, &rcvbuf, sizeof(rcvbuf)) == -1) { + perror("setsockopt SO_RCVBUF"); + } + + if (sndbuf && setsockopt(fd, SOL_SOCKET, + SO_SNDBUF, &sndbuf, sizeof(sndbuf)) == -1) { + perror("setsockopt SO_SNDBUF"); + } +} + + +static void setup_sockaddr(int domain, const char *str_addr, + struct sockaddr_storage *sockaddr) +{ + struct sockaddr_in6 *addr6 = (void *) sockaddr; + struct sockaddr_in *addr4 = (void *) sockaddr; + + switch (domain) { + case PF_INET: + memset(addr4, 0, sizeof(*addr4)); + addr4->sin_family = AF_INET; + addr4->sin_port = htons(cfg_port); + if (str_addr && + inet_pton(AF_INET, str_addr, &(addr4->sin_addr)) != 1) + error(1, 0, "ipv4 parse error: %s", str_addr); + break; + case PF_INET6: + memset(addr6, 0, sizeof(*addr6)); + addr6->sin6_family = AF_INET6; + addr6->sin6_port = htons(cfg_port); + if (str_addr && + inet_pton(AF_INET6, str_addr, &(addr6->sin6_addr)) != 1) + error(1, 0, "ipv6 parse error: %s", str_addr); + break; + default: + error(1, 0, "illegal domain"); + } +} + +static void do_accept(int fdlisten) +{ + if (setsockopt(fdlisten, SOL_SOCKET, SO_RCVLOWAT, + &chunk_size, sizeof(chunk_size)) == -1) { + perror("setsockopt SO_RCVLOWAT"); + } + + apply_rcvsnd_buf(fdlisten); + + while (1) { + struct sockaddr_in addr; + socklen_t addrlen = sizeof(addr); + pthread_t th; + int fd, res; + + fd = accept(fdlisten, (struct sockaddr *)&addr, &addrlen); + if (fd == -1) { + perror("accept"); + continue; + } + res = pthread_create(&th, NULL, child_thread, + (void *)(unsigned long)fd); + if (res) { + errno = res; + perror("pthread_create"); + close(fd); + } + } +} + +int main(int argc, char *argv[]) +{ + struct sockaddr_storage listenaddr, addr; + unsigned int max_pacing_rate = 0; + unsigned long total = 0; + char *host = NULL; + int fd, c, on = 1; + char *buffer; + int sflg = 0; + int mss = 0; + + while ((c = getopt(argc, argv, "46p:svr:w:H:zxkP:M:")) != -1) { + switch (c) { + case '4': + cfg_family = PF_INET; + cfg_alen = sizeof(struct sockaddr_in); + break; + case '6': + cfg_family = PF_INET6; + cfg_alen = sizeof(struct sockaddr_in6); + break; + case 'p': + cfg_port = atoi(optarg); + break; + case 'H': + host = optarg; + break; + case 's': /* server : listen for incoming connections */ + sflg++; + break; + case 'r': + rcvbuf = atoi(optarg); + break; + case 'w': + sndbuf = atoi(optarg); + break; + case 'z': + zflg = 1; + break; + case 'M': + mss = atoi(optarg); + break; + case 'x': + xflg = 1; + break; + case 'k': + keepflag = 1; + break; + case 'P': + max_pacing_rate = atoi(optarg) ; + break; + default: + exit(1); + } + } + if (sflg) { + int fdlisten = socket(cfg_family, SOCK_STREAM, 0); + + if (fdlisten == -1) { + perror("socket"); + exit(1); + } + apply_rcvsnd_buf(fdlisten); + setsockopt(fdlisten, SOL_SOCKET, SO_REUSEADDR, &on, sizeof(on)); + + setup_sockaddr(cfg_family, host, &listenaddr); + + if (mss && + setsockopt(fdlisten, IPPROTO_TCP, TCP_MAXSEG, + &mss, sizeof(mss)) == -1) { + perror("setsockopt TCP_MAXSEG"); + exit(1); + } + if (bind(fdlisten, (const struct sockaddr *)&listenaddr, cfg_alen) == -1) { + perror("bind"); + exit(1); + } + if (listen(fdlisten, 128) == -1) { + perror("listen"); + exit(1); + } + do_accept(fdlisten); + } + buffer = mmap(NULL, chunk_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (buffer == (char *)-1) { + perror("mmap"); + exit(1); + } + + fd = socket(AF_INET6, SOCK_STREAM, 0); + if (fd == -1) { + perror("socket"); + exit(1); + } + apply_rcvsnd_buf(fd); + + setup_sockaddr(cfg_family, host, &addr); + + if (mss && + setsockopt(fd, IPPROTO_TCP, TCP_MAXSEG, &mss, sizeof(mss)) == -1) { + perror("setsockopt TCP_MAXSEG"); + exit(1); + } + if (connect(fd, (const struct sockaddr *)&addr, cfg_alen) == -1) { + perror("connect"); + exit(1); + } + if (max_pacing_rate && + setsockopt(fd, SOL_SOCKET, SO_MAX_PACING_RATE, + &max_pacing_rate, sizeof(max_pacing_rate)) == -1) + perror("setsockopt SO_MAX_PACING_RATE"); + + if (zflg && setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY, + &on, sizeof(on)) == -1) { + perror("setsockopt SO_ZEROCOPY, (-z option disabled)"); + zflg = 0; + } + while (total < FILE_SZ) { + long wr = FILE_SZ - total; + + if (wr > chunk_size) + wr = chunk_size; + /* Note : we just want to fill the pipe with 0 bytes */ + wr = send(fd, buffer, wr, zflg ? MSG_ZEROCOPY : 0); + if (wr <= 0) + break; + total += wr; + } + close(fd); + munmap(buffer, chunk_size); + return 0; +} diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c new file mode 100644 index 0000000..e279051 --- /dev/null +++ b/tools/testing/selftests/net/udpgso.c @@ -0,0 +1,693 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE + +#include <stddef.h> +#include <arpa/inet.h> +#include <error.h> +#include <errno.h> +#include <net/if.h> +#include <linux/in.h> +#include <linux/netlink.h> +#include <linux/rtnetlink.h> +#include <netinet/if_ether.h> +#include <netinet/ip.h> +#include <netinet/ip6.h> +#include <netinet/udp.h> +#include <stdbool.h> +#include <stdlib.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/socket.h> +#include <sys/stat.h> +#include <sys/time.h> +#include <sys/types.h> +#include <unistd.h> + +#ifndef ETH_MAX_MTU +#define ETH_MAX_MTU 0xFFFFU +#endif + +#ifndef UDP_SEGMENT +#define UDP_SEGMENT 103 +#endif + +#ifndef UDP_MAX_SEGMENTS +#define UDP_MAX_SEGMENTS (1 << 6UL) +#endif + +#define CONST_MTU_TEST 1500 + +#define CONST_HDRLEN_V4 (sizeof(struct iphdr) + sizeof(struct udphdr)) +#define CONST_HDRLEN_V6 (sizeof(struct ip6_hdr) + sizeof(struct udphdr)) + +#define CONST_MSS_V4 (CONST_MTU_TEST - CONST_HDRLEN_V4) +#define CONST_MSS_V6 (CONST_MTU_TEST - CONST_HDRLEN_V6) + +#define CONST_MAX_SEGS_V4 (ETH_MAX_MTU / CONST_MSS_V4) +#define CONST_MAX_SEGS_V6 (ETH_MAX_MTU / CONST_MSS_V6) + +static bool cfg_do_ipv4; +static bool cfg_do_ipv6; +static bool cfg_do_connected; +static bool cfg_do_connectionless; +static bool cfg_do_msgmore; +static bool cfg_do_setsockopt; +static int cfg_specific_test_id = -1; + +static const char cfg_ifname[] = "lo"; +static unsigned short cfg_port = 9000; + +static char buf[ETH_MAX_MTU]; + +struct testcase { + int tlen; /* send() buffer size, may exceed mss */ + bool tfail; /* send() call is expected to fail */ + int gso_len; /* mss after applying gso */ + int r_num_mss; /* recv(): number of calls of full mss */ + int r_len_last; /* recv(): size of last non-mss dgram, if any */ +}; + +const struct in6_addr addr6 = IN6ADDR_LOOPBACK_INIT; +const struct in_addr addr4 = { .s_addr = __constant_htonl(INADDR_LOOPBACK + 2) }; + +struct testcase testcases_v4[] = { + { + /* no GSO: send a single byte */ + .tlen = 1, + .r_len_last = 1, + }, + { + /* no GSO: send a single MSS */ + .tlen = CONST_MSS_V4, + .r_num_mss = 1, + }, + { + /* no GSO: send a single MSS + 1B: fail */ + .tlen = CONST_MSS_V4 + 1, + .tfail = true, + }, + { + /* send a single MSS: will fail with GSO, because the segment + * logic in udp4_ufo_fragment demands a gso skb to be > MTU + */ + .tlen = CONST_MSS_V4, + .gso_len = CONST_MSS_V4, + .tfail = true, + .r_num_mss = 1, + }, + { + /* send a single MSS + 1B */ + .tlen = CONST_MSS_V4 + 1, + .gso_len = CONST_MSS_V4, + .r_num_mss = 1, + .r_len_last = 1, + }, + { + /* send exactly 2 MSS */ + .tlen = CONST_MSS_V4 * 2, + .gso_len = CONST_MSS_V4, + .r_num_mss = 2, + }, + { + /* send 2 MSS + 1B */ + .tlen = (CONST_MSS_V4 * 2) + 1, + .gso_len = CONST_MSS_V4, + .r_num_mss = 2, + .r_len_last = 1, + }, + { + /* send MAX segs */ + .tlen = (ETH_MAX_MTU / CONST_MSS_V4) * CONST_MSS_V4, + .gso_len = CONST_MSS_V4, + .r_num_mss = (ETH_MAX_MTU / CONST_MSS_V4), + }, + + { + /* send MAX bytes */ + .tlen = ETH_MAX_MTU - CONST_HDRLEN_V4, + .gso_len = CONST_MSS_V4, + .r_num_mss = CONST_MAX_SEGS_V4, + .r_len_last = ETH_MAX_MTU - CONST_HDRLEN_V4 - + (CONST_MAX_SEGS_V4 * CONST_MSS_V4), + }, + { + /* send MAX + 1: fail */ + .tlen = ETH_MAX_MTU - CONST_HDRLEN_V4 + 1, + .gso_len = CONST_MSS_V4, + .tfail = true, + }, + { + /* send a single 1B MSS: will fail, see single MSS above */ + .tlen = 1, + .gso_len = 1, + .tfail = true, + .r_num_mss = 1, + }, + { + /* send 2 1B segments */ + .tlen = 2, + .gso_len = 1, + .r_num_mss = 2, + }, + { + /* send 2B + 2B + 1B segments */ + .tlen = 5, + .gso_len = 2, + .r_num_mss = 2, + .r_len_last = 1, + }, + { + /* send max number of min sized segments */ + .tlen = UDP_MAX_SEGMENTS - CONST_HDRLEN_V4, + .gso_len = 1, + .r_num_mss = UDP_MAX_SEGMENTS - CONST_HDRLEN_V4, + }, + { + /* send max number + 1 of min sized segments: fail */ + .tlen = UDP_MAX_SEGMENTS - CONST_HDRLEN_V4 + 1, + .gso_len = 1, + .tfail = true, + }, + { + /* EOL */ + } +}; + +#ifndef IP6_MAX_MTU +#define IP6_MAX_MTU (ETH_MAX_MTU + sizeof(struct ip6_hdr)) +#endif + +struct testcase testcases_v6[] = { + { + /* no GSO: send a single byte */ + .tlen = 1, + .r_len_last = 1, + }, + { + /* no GSO: send a single MSS */ + .tlen = CONST_MSS_V6, + .r_num_mss = 1, + }, + { + /* no GSO: send a single MSS + 1B: fail */ + .tlen = CONST_MSS_V6 + 1, + .tfail = true, + }, + { + /* send a single MSS: will fail with GSO, because the segment + * logic in udp4_ufo_fragment demands a gso skb to be > MTU + */ + .tlen = CONST_MSS_V6, + .gso_len = CONST_MSS_V6, + .tfail = true, + .r_num_mss = 1, + }, + { + /* send a single MSS + 1B */ + .tlen = CONST_MSS_V6 + 1, + .gso_len = CONST_MSS_V6, + .r_num_mss = 1, + .r_len_last = 1, + }, + { + /* send exactly 2 MSS */ + .tlen = CONST_MSS_V6 * 2, + .gso_len = CONST_MSS_V6, + .r_num_mss = 2, + }, + { + /* send 2 MSS + 1B */ + .tlen = (CONST_MSS_V6 * 2) + 1, + .gso_len = CONST_MSS_V6, + .r_num_mss = 2, + .r_len_last = 1, + }, + { + /* send MAX segs */ + .tlen = (IP6_MAX_MTU / CONST_MSS_V6) * CONST_MSS_V6, + .gso_len = CONST_MSS_V6, + .r_num_mss = (IP6_MAX_MTU / CONST_MSS_V6), + }, + + { + /* send MAX bytes */ + .tlen = IP6_MAX_MTU - CONST_HDRLEN_V6, + .gso_len = CONST_MSS_V6, + .r_num_mss = CONST_MAX_SEGS_V6, + .r_len_last = IP6_MAX_MTU - CONST_HDRLEN_V6 - + (CONST_MAX_SEGS_V6 * CONST_MSS_V6), + }, + { + /* send MAX + 1: fail */ + .tlen = IP6_MAX_MTU - CONST_HDRLEN_V6 + 1, + .gso_len = CONST_MSS_V6, + .tfail = true, + }, + { + /* send a single 1B MSS: will fail, see single MSS above */ + .tlen = 1, + .gso_len = 1, + .tfail = true, + .r_num_mss = 1, + }, + { + /* send 2 1B segments */ + .tlen = 2, + .gso_len = 1, + .r_num_mss = 2, + }, + { + /* send 2B + 2B + 1B segments */ + .tlen = 5, + .gso_len = 2, + .r_num_mss = 2, + .r_len_last = 1, + }, + { + /* send max number of min sized segments */ + .tlen = UDP_MAX_SEGMENTS - CONST_HDRLEN_V6, + .gso_len = 1, + .r_num_mss = UDP_MAX_SEGMENTS - CONST_HDRLEN_V6, + }, + { + /* send max number + 1 of min sized segments: fail */ + .tlen = UDP_MAX_SEGMENTS - CONST_HDRLEN_V6 + 1, + .gso_len = 1, + .tfail = true, + }, + { + /* EOL */ + } +}; + +static unsigned int get_device_mtu(int fd, const char *ifname) +{ + struct ifreq ifr; + + memset(&ifr, 0, sizeof(ifr)); + + strcpy(ifr.ifr_name, ifname); + + if (ioctl(fd, SIOCGIFMTU, &ifr)) + error(1, errno, "ioctl get mtu"); + + return ifr.ifr_mtu; +} + +static void __set_device_mtu(int fd, const char *ifname, unsigned int mtu) +{ + struct ifreq ifr; + + memset(&ifr, 0, sizeof(ifr)); + + ifr.ifr_mtu = mtu; + strcpy(ifr.ifr_name, ifname); + + if (ioctl(fd, SIOCSIFMTU, &ifr)) + error(1, errno, "ioctl set mtu"); +} + +static void set_device_mtu(int fd, int mtu) +{ + int val; + + val = get_device_mtu(fd, cfg_ifname); + fprintf(stderr, "device mtu (orig): %u\n", val); + + __set_device_mtu(fd, cfg_ifname, mtu); + val = get_device_mtu(fd, cfg_ifname); + if (val != mtu) + error(1, 0, "unable to set device mtu to %u\n", val); + + fprintf(stderr, "device mtu (test): %u\n", val); +} + +static void set_pmtu_discover(int fd, bool is_ipv4) +{ + int level, name, val; + + if (is_ipv4) { + level = SOL_IP; + name = IP_MTU_DISCOVER; + val = IP_PMTUDISC_DO; + } else { + level = SOL_IPV6; + name = IPV6_MTU_DISCOVER; + val = IPV6_PMTUDISC_DO; + } + + if (setsockopt(fd, level, name, &val, sizeof(val))) + error(1, errno, "setsockopt path mtu"); +} + +static unsigned int get_path_mtu(int fd, bool is_ipv4) +{ + socklen_t vallen; + unsigned int mtu; + int ret; + + vallen = sizeof(mtu); + if (is_ipv4) + ret = getsockopt(fd, SOL_IP, IP_MTU, &mtu, &vallen); + else + ret = getsockopt(fd, SOL_IPV6, IPV6_MTU, &mtu, &vallen); + + if (ret) + error(1, errno, "getsockopt mtu"); + + + fprintf(stderr, "path mtu (read): %u\n", mtu); + return mtu; +} + +/* very wordy version of system("ip route add dev lo mtu 1500 127.0.0.3/32") */ +static void set_route_mtu(int mtu, bool is_ipv4) +{ + struct sockaddr_nl nladdr = { .nl_family = AF_NETLINK }; + struct nlmsghdr *nh; + struct rtattr *rta; + struct rtmsg *rt; + char data[NLMSG_ALIGN(sizeof(*nh)) + + NLMSG_ALIGN(sizeof(*rt)) + + NLMSG_ALIGN(RTA_LENGTH(sizeof(addr6))) + + NLMSG_ALIGN(RTA_LENGTH(sizeof(int))) + + NLMSG_ALIGN(RTA_LENGTH(0) + RTA_LENGTH(sizeof(int)))]; + int fd, ret, alen, off = 0; + + alen = is_ipv4 ? sizeof(addr4) : sizeof(addr6); + + fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); + if (fd == -1) + error(1, errno, "socket netlink"); + + memset(data, 0, sizeof(data)); + + nh = (void *)data; + nh->nlmsg_type = RTM_NEWROUTE; + nh->nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE; + off += NLMSG_ALIGN(sizeof(*nh)); + + rt = (void *)(data + off); + rt->rtm_family = is_ipv4 ? AF_INET : AF_INET6; + rt->rtm_table = RT_TABLE_MAIN; + rt->rtm_dst_len = alen << 3; + rt->rtm_protocol = RTPROT_BOOT; + rt->rtm_scope = RT_SCOPE_UNIVERSE; + rt->rtm_type = RTN_UNICAST; + off += NLMSG_ALIGN(sizeof(*rt)); + + rta = (void *)(data + off); + rta->rta_type = RTA_DST; + rta->rta_len = RTA_LENGTH(alen); + if (is_ipv4) + memcpy(RTA_DATA(rta), &addr4, alen); + else + memcpy(RTA_DATA(rta), &addr6, alen); + off += NLMSG_ALIGN(rta->rta_len); + + rta = (void *)(data + off); + rta->rta_type = RTA_OIF; + rta->rta_len = RTA_LENGTH(sizeof(int)); + *((int *)(RTA_DATA(rta))) = 1; //if_nametoindex("lo"); + off += NLMSG_ALIGN(rta->rta_len); + + /* MTU is a subtype in a metrics type */ + rta = (void *)(data + off); + rta->rta_type = RTA_METRICS; + rta->rta_len = RTA_LENGTH(0) + RTA_LENGTH(sizeof(int)); + off += NLMSG_ALIGN(rta->rta_len); + + /* now fill MTU subtype. Note that it fits within above rta_len */ + rta = (void *)(((char *) rta) + RTA_LENGTH(0)); + rta->rta_type = RTAX_MTU; + rta->rta_len = RTA_LENGTH(sizeof(int)); + *((int *)(RTA_DATA(rta))) = mtu; + + nh->nlmsg_len = off; + + ret = sendto(fd, data, off, 0, (void *)&nladdr, sizeof(nladdr)); + if (ret != off) + error(1, errno, "send netlink: %uB != %uB\n", ret, off); + + if (close(fd)) + error(1, errno, "close netlink"); + + fprintf(stderr, "route mtu (test): %u\n", mtu); +} + +static bool __send_one(int fd, struct msghdr *msg, int flags) +{ + int ret; + + ret = sendmsg(fd, msg, flags); + if (ret == -1 && + (errno == EMSGSIZE || errno == ENOMEM || errno == EINVAL)) + return false; + if (ret == -1) + error(1, errno, "sendmsg"); + if (ret != msg->msg_iov->iov_len) + error(1, 0, "sendto: %d != %lu", ret, msg->msg_iov->iov_len); + if (msg->msg_flags) + error(1, 0, "sendmsg: return flags 0x%x\n", msg->msg_flags); + + return true; +} + +static bool send_one(int fd, int len, int gso_len, + struct sockaddr *addr, socklen_t alen) +{ + char control[CMSG_SPACE(sizeof(uint16_t))] = {0}; + struct msghdr msg = {0}; + struct iovec iov = {0}; + struct cmsghdr *cm; + + iov.iov_base = buf; + iov.iov_len = len; + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + + msg.msg_name = addr; + msg.msg_namelen = alen; + + if (gso_len && !cfg_do_setsockopt) { + msg.msg_control = control; + msg.msg_controllen = sizeof(control); + + cm = CMSG_FIRSTHDR(&msg); + cm->cmsg_level = SOL_UDP; + cm->cmsg_type = UDP_SEGMENT; + cm->cmsg_len = CMSG_LEN(sizeof(uint16_t)); + *((uint16_t *) CMSG_DATA(cm)) = gso_len; + } + + /* If MSG_MORE, send 1 byte followed by remainder */ + if (cfg_do_msgmore && len > 1) { + iov.iov_len = 1; + if (!__send_one(fd, &msg, MSG_MORE)) + error(1, 0, "send 1B failed"); + + iov.iov_base++; + iov.iov_len = len - 1; + } + + return __send_one(fd, &msg, 0); +} + +static int recv_one(int fd, int flags) +{ + int ret; + + ret = recv(fd, buf, sizeof(buf), flags); + if (ret == -1 && errno == EAGAIN && (flags & MSG_DONTWAIT)) + return 0; + if (ret == -1) + error(1, errno, "recv"); + + return ret; +} + +static void run_one(struct testcase *test, int fdt, int fdr, + struct sockaddr *addr, socklen_t alen) +{ + int i, ret, val, mss; + bool sent; + + fprintf(stderr, "ipv%d tx:%d gso:%d %s\n", + addr->sa_family == AF_INET ? 4 : 6, + test->tlen, test->gso_len, + test->tfail ? "(fail)" : ""); + + val = test->gso_len; + if (cfg_do_setsockopt) { + if (setsockopt(fdt, SOL_UDP, UDP_SEGMENT, &val, sizeof(val))) + error(1, errno, "setsockopt udp segment"); + } + + sent = send_one(fdt, test->tlen, test->gso_len, addr, alen); + if (sent && test->tfail) + error(1, 0, "send succeeded while expecting failure"); + if (!sent && !test->tfail) + error(1, 0, "send failed while expecting success"); + if (!sent) + return; + + if (test->gso_len) + mss = test->gso_len; + else + mss = addr->sa_family == AF_INET ? CONST_MSS_V4 : CONST_MSS_V6; + + + /* Recv all full MSS datagrams */ + for (i = 0; i < test->r_num_mss; i++) { + ret = recv_one(fdr, 0); + if (ret != mss) + error(1, 0, "recv.%d: %d != %d", i, ret, mss); + } + + /* Recv the non-full last datagram, if tlen was not a multiple of mss */ + if (test->r_len_last) { + ret = recv_one(fdr, 0); + if (ret != test->r_len_last) + error(1, 0, "recv.%d: %d != %d (last)", + i, ret, test->r_len_last); + } + + /* Verify received all data */ + ret = recv_one(fdr, MSG_DONTWAIT); + if (ret) + error(1, 0, "recv: unexpected datagram"); +} + +static void run_all(int fdt, int fdr, struct sockaddr *addr, socklen_t alen) +{ + struct testcase *tests, *test; + + tests = addr->sa_family == AF_INET ? testcases_v4 : testcases_v6; + + for (test = tests; test->tlen; test++) { + /* if a specific test is given, then skip all others */ + if (cfg_specific_test_id == -1 || + cfg_specific_test_id == test - tests) + run_one(test, fdt, fdr, addr, alen); + } +} + +static void run_test(struct sockaddr *addr, socklen_t alen) +{ + struct timeval tv = { .tv_usec = 100 * 1000 }; + int fdr, fdt, val; + + fdr = socket(addr->sa_family, SOCK_DGRAM, 0); + if (fdr == -1) + error(1, errno, "socket r"); + + if (bind(fdr, addr, alen)) + error(1, errno, "bind"); + + /* Have tests fail quickly instead of hang */ + if (setsockopt(fdr, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv))) + error(1, errno, "setsockopt rcv timeout"); + + fdt = socket(addr->sa_family, SOCK_DGRAM, 0); + if (fdt == -1) + error(1, errno, "socket t"); + + /* Do not fragment these datagrams: only succeed if GSO works */ + set_pmtu_discover(fdt, addr->sa_family == AF_INET); + + if (cfg_do_connectionless) { + set_device_mtu(fdt, CONST_MTU_TEST); + run_all(fdt, fdr, addr, alen); + } + + if (cfg_do_connected) { + set_device_mtu(fdt, CONST_MTU_TEST + 100); + set_route_mtu(CONST_MTU_TEST, addr->sa_family == AF_INET); + + if (connect(fdt, addr, alen)) + error(1, errno, "connect"); + + val = get_path_mtu(fdt, addr->sa_family == AF_INET); + if (val != CONST_MTU_TEST) + error(1, 0, "bad path mtu %u\n", val); + + run_all(fdt, fdr, addr, 0 /* use connected addr */); + } + + if (close(fdt)) + error(1, errno, "close t"); + if (close(fdr)) + error(1, errno, "close r"); +} + +static void run_test_v4(void) +{ + struct sockaddr_in addr = {0}; + + addr.sin_family = AF_INET; + addr.sin_port = htons(cfg_port); + addr.sin_addr = addr4; + + run_test((void *)&addr, sizeof(addr)); +} + +static void run_test_v6(void) +{ + struct sockaddr_in6 addr = {0}; + + addr.sin6_family = AF_INET6; + addr.sin6_port = htons(cfg_port); + addr.sin6_addr = addr6; + + run_test((void *)&addr, sizeof(addr)); +} + +static void parse_opts(int argc, char **argv) +{ + int c; + + while ((c = getopt(argc, argv, "46cCmst:")) != -1) { + switch (c) { + case '4': + cfg_do_ipv4 = true; + break; + case '6': + cfg_do_ipv6 = true; + break; + case 'c': + cfg_do_connected = true; + break; + case 'C': + cfg_do_connectionless = true; + break; + case 'm': + cfg_do_msgmore = true; + break; + case 's': + cfg_do_setsockopt = true; + break; + case 't': + cfg_specific_test_id = strtoul(optarg, NULL, 0); + break; + default: + error(1, 0, "%s: parse error", argv[0]); + } + } +} + +int main(int argc, char **argv) +{ + parse_opts(argc, argv); + + if (cfg_do_ipv4) + run_test_v4(); + if (cfg_do_ipv6) + run_test_v6(); + + fprintf(stderr, "OK\n"); + return 0; +} diff --git a/tools/testing/selftests/net/udpgso.sh b/tools/testing/selftests/net/udpgso.sh new file mode 100755 index 0000000..fec24f5 --- /dev/null +++ b/tools/testing/selftests/net/udpgso.sh @@ -0,0 +1,29 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Run a series of udpgso regression tests + +echo "ipv4 cmsg" +./in_netns.sh ./udpgso -4 -C + +echo "ipv4 setsockopt" +./in_netns.sh ./udpgso -4 -C -s + +echo "ipv6 cmsg" +./in_netns.sh ./udpgso -6 -C + +echo "ipv6 setsockopt" +./in_netns.sh ./udpgso -6 -C -s + +echo "ipv4 connected" +./in_netns.sh ./udpgso -4 -c + +# blocked on 2nd loopback address +# echo "ipv6 connected" +# ./in_netns.sh ./udpgso -6 -c + +echo "ipv4 msg_more" +./in_netns.sh ./udpgso -4 -C -m + +echo "ipv6 msg_more" +./in_netns.sh ./udpgso -6 -C -m diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh new file mode 100755 index 0000000..792fa4d --- /dev/null +++ b/tools/testing/selftests/net/udpgso_bench.sh @@ -0,0 +1,74 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Run a series of udpgso benchmarks + +wake_children() { + local -r jobs="$(jobs -p)" + + if [[ "${jobs}" != "" ]]; then + kill -1 ${jobs} 2>/dev/null + fi +} +trap wake_children EXIT + +run_one() { + local -r args=$@ + + ./udpgso_bench_rx & + ./udpgso_bench_rx -t & + + ./udpgso_bench_tx ${args} +} + +run_in_netns() { + local -r args=$@ + + ./in_netns.sh $0 __subprocess ${args} +} + +run_udp() { + local -r args=$@ + + echo "udp" + run_in_netns ${args} + + echo "udp gso" + run_in_netns ${args} -S + + echo "udp gso zerocopy" + run_in_netns ${args} -S -z +} + +run_tcp() { + local -r args=$@ + + echo "tcp" + run_in_netns ${args} -t + + echo "tcp zerocopy" + run_in_netns ${args} -t -z +} + +run_all() { + local -r core_args="-l 4" + local -r ipv4_args="${core_args} -4 -D 127.0.0.1" + local -r ipv6_args="${core_args} -6 -D ::1" + + echo "ipv4" + run_tcp "${ipv4_args}" + run_udp "${ipv4_args}" + + echo "ipv6" + run_tcp "${ipv4_args}" + run_udp "${ipv6_args}" +} + +if [[ $# -eq 0 ]]; then + run_all +elif [[ $1 == "__subprocess" ]]; then + shift + run_one $@ +else + run_in_netns $@ +fi diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c new file mode 100644 index 0000000..727cf67 --- /dev/null +++ b/tools/testing/selftests/net/udpgso_bench_rx.c @@ -0,0 +1,265 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE + +#include <arpa/inet.h> +#include <error.h> +#include <errno.h> +#include <limits.h> +#include <linux/errqueue.h> +#include <linux/if_packet.h> +#include <linux/socket.h> +#include <linux/sockios.h> +#include <net/ethernet.h> +#include <net/if.h> +#include <netinet/ip.h> +#include <netinet/ip6.h> +#include <netinet/tcp.h> +#include <netinet/udp.h> +#include <poll.h> +#include <sched.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdint.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/socket.h> +#include <sys/stat.h> +#include <sys/time.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <unistd.h> + +static int cfg_port = 8000; +static bool cfg_tcp; +static bool cfg_verify; + +static bool interrupted; +static unsigned long packets, bytes; + +static void sigint_handler(int signum) +{ + if (signum == SIGINT) + interrupted = true; +} + +static unsigned long gettimeofday_ms(void) +{ + struct timeval tv; + + gettimeofday(&tv, NULL); + return (tv.tv_sec * 1000) + (tv.tv_usec / 1000); +} + +static void do_poll(int fd) +{ + struct pollfd pfd; + int ret; + + pfd.events = POLLIN; + pfd.revents = 0; + pfd.fd = fd; + + do { + ret = poll(&pfd, 1, 10); + if (ret == -1) + error(1, errno, "poll"); + if (ret == 0) + continue; + if (pfd.revents != POLLIN) + error(1, errno, "poll: 0x%x expected 0x%x\n", + pfd.revents, POLLIN); + } while (!ret && !interrupted); +} + +static int do_socket(bool do_tcp) +{ + struct sockaddr_in6 addr = {0}; + int fd, val; + + fd = socket(PF_INET6, cfg_tcp ? SOCK_STREAM : SOCK_DGRAM, 0); + if (fd == -1) + error(1, errno, "socket"); + + val = 1 << 21; + if (setsockopt(fd, SOL_SOCKET, SO_RCVBUF, &val, sizeof(val))) + error(1, errno, "setsockopt rcvbuf"); + val = 1; + if (setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, &val, sizeof(val))) + error(1, errno, "setsockopt reuseport"); + + addr.sin6_family = PF_INET6; + addr.sin6_port = htons(cfg_port); + addr.sin6_addr = in6addr_any; + if (bind(fd, (void *) &addr, sizeof(addr))) + error(1, errno, "bind"); + + if (do_tcp) { + int accept_fd = fd; + + if (listen(accept_fd, 1)) + error(1, errno, "listen"); + + do_poll(accept_fd); + + fd = accept(accept_fd, NULL, NULL); + if (fd == -1) + error(1, errno, "accept"); + if (close(accept_fd)) + error(1, errno, "close accept fd"); + } + + return fd; +} + +/* Flush all outstanding bytes for the tcp receive queue */ +static void do_flush_tcp(int fd) +{ + int ret; + + while (true) { + /* MSG_TRUNC flushes up to len bytes */ + ret = recv(fd, NULL, 1 << 21, MSG_TRUNC | MSG_DONTWAIT); + if (ret == -1 && errno == EAGAIN) + return; + if (ret == -1) + error(1, errno, "flush"); + if (ret == 0) { + /* client detached */ + exit(0); + } + + packets++; + bytes += ret; + } + +} + +static char sanitized_char(char val) +{ + return (val >= 'a' && val <= 'z') ? val : '.'; +} + +static void do_verify_udp(const char *data, int len) +{ + char cur = data[0]; + int i; + + /* verify contents */ + if (cur < 'a' || cur > 'z') + error(1, 0, "data initial byte out of range"); + + for (i = 1; i < len; i++) { + if (cur == 'z') + cur = 'a'; + else + cur++; + + if (data[i] != cur) + error(1, 0, "data[%d]: len %d, %c(%hhu) != %c(%hhu)\n", + i, len, + sanitized_char(data[i]), data[i], + sanitized_char(cur), cur); + } +} + +/* Flush all outstanding datagrams. Verify first few bytes of each. */ +static void do_flush_udp(int fd) +{ + static char rbuf[ETH_DATA_LEN]; + int ret, len, budget = 256; + + len = cfg_verify ? sizeof(rbuf) : 0; + while (budget--) { + /* MSG_TRUNC will make return value full datagram length */ + ret = recv(fd, rbuf, len, MSG_TRUNC | MSG_DONTWAIT); + if (ret == -1 && errno == EAGAIN) + return; + if (ret == -1) + error(1, errno, "recv"); + if (len) { + if (ret == 0) + error(1, errno, "recv: 0 byte datagram\n"); + + do_verify_udp(rbuf, ret); + } + + packets++; + bytes += ret; + } +} + +static void usage(const char *filepath) +{ + error(1, 0, "Usage: %s [-tv] [-p port]", filepath); +} + +static void parse_opts(int argc, char **argv) +{ + int c; + + while ((c = getopt(argc, argv, "ptv")) != -1) { + switch (c) { + case 'p': + cfg_port = htons(strtoul(optarg, NULL, 0)); + break; + case 't': + cfg_tcp = true; + break; + case 'v': + cfg_verify = true; + break; + } + } + + if (optind != argc) + usage(argv[0]); + + if (cfg_tcp && cfg_verify) + error(1, 0, "TODO: implement verify mode for tcp"); +} + +static void do_recv(void) +{ + unsigned long tnow, treport; + int fd; + + fd = do_socket(cfg_tcp); + + treport = gettimeofday_ms() + 1000; + do { + do_poll(fd); + + if (cfg_tcp) + do_flush_tcp(fd); + else + do_flush_udp(fd); + + tnow = gettimeofday_ms(); + if (tnow > treport) { + if (packets) + fprintf(stderr, + "%s rx: %6lu MB/s %8lu calls/s\n", + cfg_tcp ? "tcp" : "udp", + bytes >> 20, packets); + bytes = packets = 0; + treport = tnow + 1000; + } + + } while (!interrupted); + + if (close(fd)) + error(1, errno, "close"); +} + +int main(int argc, char **argv) +{ + parse_opts(argc, argv); + + signal(SIGINT, sigint_handler); + + do_recv(); + + return 0; +} diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c new file mode 100644 index 0000000..e821564 --- /dev/null +++ b/tools/testing/selftests/net/udpgso_bench_tx.c @@ -0,0 +1,420 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE + +#include <arpa/inet.h> +#include <errno.h> +#include <error.h> +#include <netinet/if_ether.h> +#include <netinet/in.h> +#include <netinet/ip.h> +#include <netinet/ip6.h> +#include <netinet/udp.h> +#include <poll.h> +#include <sched.h> +#include <signal.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/socket.h> +#include <sys/time.h> +#include <sys/types.h> +#include <unistd.h> + +#ifndef ETH_MAX_MTU +#define ETH_MAX_MTU 0xFFFFU +#endif + +#ifndef UDP_SEGMENT +#define UDP_SEGMENT 103 +#endif + +#ifndef SO_ZEROCOPY +#define SO_ZEROCOPY 60 +#endif + +#ifndef MSG_ZEROCOPY +#define MSG_ZEROCOPY 0x4000000 +#endif + +#define NUM_PKT 100 + +static bool cfg_cache_trash; +static int cfg_cpu = -1; +static int cfg_connected = true; +static int cfg_family = PF_UNSPEC; +static uint16_t cfg_mss; +static int cfg_payload_len = (1472 * 42); +static int cfg_port = 8000; +static int cfg_runtime_ms = -1; +static bool cfg_segment; +static bool cfg_sendmmsg; +static bool cfg_tcp; +static bool cfg_zerocopy; + +static socklen_t cfg_alen; +static struct sockaddr_storage cfg_dst_addr; + +static bool interrupted; +static char buf[NUM_PKT][ETH_MAX_MTU]; + +static void sigint_handler(int signum) +{ + if (signum == SIGINT) + interrupted = true; +} + +static unsigned long gettimeofday_ms(void) +{ + struct timeval tv; + + gettimeofday(&tv, NULL); + return (tv.tv_sec * 1000) + (tv.tv_usec / 1000); +} + +static int set_cpu(int cpu) +{ + cpu_set_t mask; + + CPU_ZERO(&mask); + CPU_SET(cpu, &mask); + if (sched_setaffinity(0, sizeof(mask), &mask)) + error(1, 0, "setaffinity %d", cpu); + + return 0; +} + +static void setup_sockaddr(int domain, const char *str_addr, void *sockaddr) +{ + struct sockaddr_in6 *addr6 = (void *) sockaddr; + struct sockaddr_in *addr4 = (void *) sockaddr; + + switch (domain) { + case PF_INET: + addr4->sin_family = AF_INET; + addr4->sin_port = htons(cfg_port); + if (inet_pton(AF_INET, str_addr, &(addr4->sin_addr)) != 1) + error(1, 0, "ipv4 parse error: %s", str_addr); + break; + case PF_INET6: + addr6->sin6_family = AF_INET6; + addr6->sin6_port = htons(cfg_port); + if (inet_pton(AF_INET6, str_addr, &(addr6->sin6_addr)) != 1) + error(1, 0, "ipv6 parse error: %s", str_addr); + break; + default: + error(1, 0, "illegal domain"); + } +} + +static void flush_zerocopy(int fd) +{ + struct msghdr msg = {0}; /* flush */ + int ret; + + while (1) { + ret = recvmsg(fd, &msg, MSG_ERRQUEUE); + if (ret == -1 && errno == EAGAIN) + break; + if (ret == -1) + error(1, errno, "errqueue"); + if (msg.msg_flags != (MSG_ERRQUEUE | MSG_CTRUNC)) + error(1, 0, "errqueue: flags 0x%x\n", msg.msg_flags); + msg.msg_flags = 0; + } +} + +static int send_tcp(int fd, char *data) +{ + int ret, done = 0, count = 0; + + while (done < cfg_payload_len) { + ret = send(fd, data + done, cfg_payload_len - done, + cfg_zerocopy ? MSG_ZEROCOPY : 0); + if (ret == -1) + error(1, errno, "write"); + + done += ret; + count++; + } + + return count; +} + +static int send_udp(int fd, char *data) +{ + int ret, total_len, len, count = 0; + + total_len = cfg_payload_len; + + while (total_len) { + len = total_len < cfg_mss ? total_len : cfg_mss; + + ret = sendto(fd, data, len, cfg_zerocopy ? MSG_ZEROCOPY : 0, + cfg_connected ? NULL : (void *)&cfg_dst_addr, + cfg_connected ? 0 : cfg_alen); + if (ret == -1) + error(1, errno, "write"); + if (ret != len) + error(1, errno, "write: %uB != %uB\n", ret, len); + + total_len -= len; + count++; + } + + return count; +} + +static int send_udp_sendmmsg(int fd, char *data) +{ + const int max_nr_msg = ETH_MAX_MTU / ETH_DATA_LEN; + struct mmsghdr mmsgs[max_nr_msg]; + struct iovec iov[max_nr_msg]; + unsigned int off = 0, left; + int i = 0, ret; + + memset(mmsgs, 0, sizeof(mmsgs)); + + left = cfg_payload_len; + while (left) { + if (i == max_nr_msg) + error(1, 0, "sendmmsg: exceeds max_nr_msg"); + + iov[i].iov_base = data + off; + iov[i].iov_len = cfg_mss < left ? cfg_mss : left; + + mmsgs[i].msg_hdr.msg_iov = iov + i; + mmsgs[i].msg_hdr.msg_iovlen = 1; + + off += iov[i].iov_len; + left -= iov[i].iov_len; + i++; + } + + ret = sendmmsg(fd, mmsgs, i, cfg_zerocopy ? MSG_ZEROCOPY : 0); + if (ret == -1) + error(1, errno, "sendmmsg"); + + return ret; +} + +static void send_udp_segment_cmsg(struct cmsghdr *cm) +{ + uint16_t *valp; + + cm->cmsg_level = SOL_UDP; + cm->cmsg_type = UDP_SEGMENT; + cm->cmsg_len = CMSG_LEN(sizeof(cfg_mss)); + valp = (void *)CMSG_DATA(cm); + *valp = cfg_mss; +} + +static int send_udp_segment(int fd, char *data) +{ + char control[CMSG_SPACE(sizeof(cfg_mss))] = {0}; + struct msghdr msg = {0}; + struct iovec iov = {0}; + int ret; + + iov.iov_base = data; + iov.iov_len = cfg_payload_len; + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + + msg.msg_control = control; + msg.msg_controllen = sizeof(control); + send_udp_segment_cmsg(CMSG_FIRSTHDR(&msg)); + + msg.msg_name = (void *)&cfg_dst_addr; + msg.msg_namelen = cfg_alen; + + ret = sendmsg(fd, &msg, cfg_zerocopy ? MSG_ZEROCOPY : 0); + if (ret == -1) + error(1, errno, "sendmsg"); + if (ret != iov.iov_len) + error(1, 0, "sendmsg: %u != %lu\n", ret, iov.iov_len); + + return 1; +} + +static void usage(const char *filepath) +{ + error(1, 0, "Usage: %s [-46cmStuz] [-C cpu] [-D dst ip] [-l secs] [-p port] [-s sendsize]", + filepath); +} + +static void parse_opts(int argc, char **argv) +{ + int max_len, hdrlen; + int c; + + while ((c = getopt(argc, argv, "46cC:D:l:mp:s:Stuz")) != -1) { + switch (c) { + case '4': + if (cfg_family != PF_UNSPEC) + error(1, 0, "Pass one of -4 or -6"); + cfg_family = PF_INET; + cfg_alen = sizeof(struct sockaddr_in); + break; + case '6': + if (cfg_family != PF_UNSPEC) + error(1, 0, "Pass one of -4 or -6"); + cfg_family = PF_INET6; + cfg_alen = sizeof(struct sockaddr_in6); + break; + case 'c': + cfg_cache_trash = true; + break; + case 'C': + cfg_cpu = strtol(optarg, NULL, 0); + break; + case 'D': + setup_sockaddr(cfg_family, optarg, &cfg_dst_addr); + break; + case 'l': + cfg_runtime_ms = strtoul(optarg, NULL, 10) * 1000; + break; + case 'm': + cfg_sendmmsg = true; + break; + case 'p': + cfg_port = strtoul(optarg, NULL, 0); + break; + case 's': + cfg_payload_len = strtoul(optarg, NULL, 0); + break; + case 'S': + cfg_segment = true; + break; + case 't': + cfg_tcp = true; + break; + case 'u': + cfg_connected = false; + break; + case 'z': + cfg_zerocopy = true; + break; + } + } + + if (optind != argc) + usage(argv[0]); + + if (cfg_family == PF_UNSPEC) + error(1, 0, "must pass one of -4 or -6"); + if (cfg_tcp && !cfg_connected) + error(1, 0, "connectionless tcp makes no sense"); + if (cfg_segment && cfg_sendmmsg) + error(1, 0, "cannot combine segment offload and sendmmsg"); + + if (cfg_family == PF_INET) + hdrlen = sizeof(struct iphdr) + sizeof(struct udphdr); + else + hdrlen = sizeof(struct ip6_hdr) + sizeof(struct udphdr); + + cfg_mss = ETH_DATA_LEN - hdrlen; + max_len = ETH_MAX_MTU - hdrlen; + + if (cfg_payload_len > max_len) + error(1, 0, "payload length %u exceeds max %u", + cfg_payload_len, max_len); +} + +static void set_pmtu_discover(int fd, bool is_ipv4) +{ + int level, name, val; + + if (is_ipv4) { + level = SOL_IP; + name = IP_MTU_DISCOVER; + val = IP_PMTUDISC_DO; + } else { + level = SOL_IPV6; + name = IPV6_MTU_DISCOVER; + val = IPV6_PMTUDISC_DO; + } + + if (setsockopt(fd, level, name, &val, sizeof(val))) + error(1, errno, "setsockopt path mtu"); +} + +int main(int argc, char **argv) +{ + unsigned long num_msgs, num_sends; + unsigned long tnow, treport, tstop; + int fd, i, val; + + parse_opts(argc, argv); + + if (cfg_cpu > 0) + set_cpu(cfg_cpu); + + for (i = 0; i < sizeof(buf[0]); i++) + buf[0][i] = 'a' + (i % 26); + for (i = 1; i < NUM_PKT; i++) + memcpy(buf[i], buf[0], sizeof(buf[0])); + + signal(SIGINT, sigint_handler); + + fd = socket(cfg_family, cfg_tcp ? SOCK_STREAM : SOCK_DGRAM, 0); + if (fd == -1) + error(1, errno, "socket"); + + if (cfg_zerocopy) { + val = 1; + if (setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY, &val, sizeof(val))) + error(1, errno, "setsockopt zerocopy"); + } + + if (cfg_connected && + connect(fd, (void *)&cfg_dst_addr, cfg_alen)) + error(1, errno, "connect"); + + if (cfg_segment) + set_pmtu_discover(fd, cfg_family == PF_INET); + + num_msgs = num_sends = 0; + tnow = gettimeofday_ms(); + tstop = tnow + cfg_runtime_ms; + treport = tnow + 1000; + + i = 0; + do { + if (cfg_tcp) + num_sends += send_tcp(fd, buf[i]); + else if (cfg_segment) + num_sends += send_udp_segment(fd, buf[i]); + else if (cfg_sendmmsg) + num_sends += send_udp_sendmmsg(fd, buf[i]); + else + num_sends += send_udp(fd, buf[i]); + num_msgs++; + + if (cfg_zerocopy && ((num_msgs & 0xF) == 0)) + flush_zerocopy(fd); + + tnow = gettimeofday_ms(); + if (tnow > treport) { + fprintf(stderr, + "%s tx: %6lu MB/s %8lu calls/s %6lu msg/s\n", + cfg_tcp ? "tcp" : "udp", + (num_msgs * cfg_payload_len) >> 20, + num_sends, num_msgs); + num_msgs = num_sends = 0; + treport = tnow + 1000; + } + + /* cold cache when writing buffer */ + if (cfg_cache_trash) + i = ++i < NUM_PKT ? i : 0; + + } while (!interrupted && (cfg_runtime_ms == -1 || tnow < tstop)); + + if (close(fd)) + error(1, errno, "close"); + + return 0; +} diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile index f6b1338..201b598 100644 --- a/tools/testing/selftests/powerpc/Makefile +++ b/tools/testing/selftests/powerpc/Makefile @@ -17,7 +17,6 @@ SUB_DIRS = alignment \ benchmarks \ cache_shape \ copyloops \ - context_switch \ dscr \ mm \ pmu \ diff --git a/tools/testing/selftests/powerpc/alignment/.gitignore b/tools/testing/selftests/powerpc/alignment/.gitignore index 1d980e3..9d38307 100644 --- a/tools/testing/selftests/powerpc/alignment/.gitignore +++ b/tools/testing/selftests/powerpc/alignment/.gitignore @@ -3,3 +3,4 @@ copy_first_unaligned paste_unaligned paste_last_unaligned copy_paste_unaligned_common +alignment_handler diff --git a/tools/testing/selftests/powerpc/benchmarks/exec_target.c b/tools/testing/selftests/powerpc/benchmarks/exec_target.c index 3c9c144..c14b0fc 100644 --- a/tools/testing/selftests/powerpc/benchmarks/exec_target.c +++ b/tools/testing/selftests/powerpc/benchmarks/exec_target.c @@ -6,8 +6,11 @@ * Copyright 2018, Anton Blanchard, IBM Corp. */ -void _exit(int); +#define _GNU_SOURCE +#include <unistd.h> +#include <sys/syscall.h> + void _start(void) { - _exit(0); + syscall(SYS_exit, 0); } diff --git a/tools/testing/selftests/powerpc/context_switch/.gitignore b/tools/testing/selftests/powerpc/context_switch/.gitignore deleted file mode 100644 index c1431af..0000000 --- a/tools/testing/selftests/powerpc/context_switch/.gitignore +++ /dev/null @@ -1 +0,0 @@ -cp_abort diff --git a/tools/testing/selftests/powerpc/context_switch/Makefile b/tools/testing/selftests/powerpc/context_switch/Makefile deleted file mode 100644 index e9351bb..0000000 --- a/tools/testing/selftests/powerpc/context_switch/Makefile +++ /dev/null @@ -1,5 +0,0 @@ -TEST_GEN_PROGS := cp_abort - -include ../../lib.mk - -$(TEST_GEN_PROGS): ../harness.c ../utils.c diff --git a/tools/testing/selftests/powerpc/context_switch/cp_abort.c b/tools/testing/selftests/powerpc/context_switch/cp_abort.c deleted file mode 100644 index 5a5b55a..0000000 --- a/tools/testing/selftests/powerpc/context_switch/cp_abort.c +++ /dev/null @@ -1,110 +0,0 @@ -/* - * Adapted from Anton Blanchard's context switch microbenchmark. - * - * Copyright 2009, Anton Blanchard, IBM Corporation. - * Copyright 2016, Mikey Neuling, Chris Smart, IBM Corporation. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - * This program tests the copy paste abort functionality of a P9 - * (or later) by setting up two processes on the same CPU, one - * which executes the copy instruction and the other which - * executes paste. - * - * The paste instruction should never succeed, as the cp_abort - * instruction is called by the kernel during a context switch. - * - */ - -#define _GNU_SOURCE - -#include <stdio.h> -#include <unistd.h> -#include <stdlib.h> -#include "utils.h" -#include <sched.h> - -#define READ_FD 0 -#define WRITE_FD 1 - -#define NUM_LOOPS 1000 - -/* This defines the "paste" instruction from Power ISA 3.0 Book II, section 4.4. */ -#define PASTE(RA, RB, L, RC) \ - .long (0x7c00070c | (RA) << (31-15) | (RB) << (31-20) | (L) << (31-10) | (RC) << (31-31)) - -int paste(void *i) -{ - int cr; - - asm volatile(str(PASTE(0, %1, 1, 1))";" - "mfcr %0;" - : "=r" (cr) - : "b" (i) - : "memory" - ); - return cr; -} - -/* This defines the "copy" instruction from Power ISA 3.0 Book II, section 4.4. */ -#define COPY(RA, RB, L) \ - .long (0x7c00060c | (RA) << (31-15) | (RB) << (31-20) | (L) << (31-10)) - -void copy(void *i) -{ - asm volatile(str(COPY(0, %0, 1))";" - : - : "b" (i) - : "memory" - ); -} - -int test_cp_abort(void) -{ - /* 128 bytes for a full cache line */ - char buf[128] __cacheline_aligned; - cpu_set_t cpuset; - int fd1[2], fd2[2], pid; - char c; - - /* only run this test on a P9 or later */ - SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_00)); - - /* - * Run both processes on the same CPU, so that copy is more likely - * to leak into a paste. - */ - CPU_ZERO(&cpuset); - CPU_SET(pick_online_cpu(), &cpuset); - FAIL_IF(sched_setaffinity(0, sizeof(cpuset), &cpuset)); - - FAIL_IF(pipe(fd1) || pipe(fd2)); - - pid = fork(); - FAIL_IF(pid < 0); - - if (!pid) { - for (int i = 0; i < NUM_LOOPS; i++) { - FAIL_IF((write(fd1[WRITE_FD], &c, 1)) != 1); - FAIL_IF((read(fd2[READ_FD], &c, 1)) != 1); - /* A paste succeeds if CR0 EQ bit is set */ - FAIL_IF(paste(buf) & 0x20000000); - } - } else { - for (int i = 0; i < NUM_LOOPS; i++) { - FAIL_IF((read(fd1[READ_FD], &c, 1)) != 1); - copy(buf); - FAIL_IF((write(fd2[WRITE_FD], &c, 1) != 1)); - } - } - return 0; - -} - -int main(int argc, char *argv[]) -{ - return test_harness(test_cp_abort, "cp_abort"); -} diff --git a/tools/testing/selftests/powerpc/include/reg.h b/tools/testing/selftests/powerpc/include/reg.h index 4afdebc..7f348c0 100644 --- a/tools/testing/selftests/powerpc/include/reg.h +++ b/tools/testing/selftests/powerpc/include/reg.h @@ -54,6 +54,7 @@ #define SPRN_DSCR_PRIV 0x11 /* Privilege State DSCR */ #define SPRN_DSCR 0x03 /* Data Stream Control Register */ #define SPRN_PPR 896 /* Program Priority Register */ +#define SPRN_AMR 13 /* Authority Mask Register - problem state */ /* TEXASR register bits */ #define TEXASR_FC 0xFE00000000000000 diff --git a/tools/testing/selftests/powerpc/ptrace/.gitignore b/tools/testing/selftests/powerpc/ptrace/.gitignore index 349acfa..07ec449 100644 --- a/tools/testing/selftests/powerpc/ptrace/.gitignore +++ b/tools/testing/selftests/powerpc/ptrace/.gitignore @@ -8,3 +8,5 @@ ptrace-vsx ptrace-tm-vsx ptrace-tm-spd-vsx ptrace-tm-spr +ptrace-hwbreak +perf-hwbreak diff --git a/tools/testing/selftests/powerpc/ptrace/Makefile b/tools/testing/selftests/powerpc/ptrace/Makefile index 4803052..28f5b78 100644 --- a/tools/testing/selftests/powerpc/ptrace/Makefile +++ b/tools/testing/selftests/powerpc/ptrace/Makefile @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 TEST_PROGS := ptrace-gpr ptrace-tm-gpr ptrace-tm-spd-gpr \ ptrace-tar ptrace-tm-tar ptrace-tm-spd-tar ptrace-vsx ptrace-tm-vsx \ - ptrace-tm-spd-vsx ptrace-tm-spr + ptrace-tm-spd-vsx ptrace-tm-spr ptrace-hwbreak ptrace-pkey core-pkey \ + perf-hwbreak include ../../lib.mk @@ -9,6 +10,9 @@ all: $(TEST_PROGS) CFLAGS += -m64 -I../../../../../usr/include -I../tm -mhtm -fno-pie +ptrace-pkey core-pkey: child.h +ptrace-pkey core-pkey: LDLIBS += -pthread + $(TEST_PROGS): ../harness.c ../utils.c ../lib/reg.S ptrace.h clean: diff --git a/tools/testing/selftests/powerpc/ptrace/child.h b/tools/testing/selftests/powerpc/ptrace/child.h new file mode 100644 index 0000000..d7275b7 --- /dev/null +++ b/tools/testing/selftests/powerpc/ptrace/child.h @@ -0,0 +1,139 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Helper functions to sync execution between parent and child processes. + * + * Copyright 2018, Thiago Jung Bauermann, IBM Corporation. + */ +#include <stdio.h> +#include <stdbool.h> +#include <semaphore.h> + +/* + * Information in a shared memory location for synchronization between child and + * parent. + */ +struct child_sync { + /* The parent waits on this semaphore. */ + sem_t sem_parent; + + /* If true, the child should give up as well. */ + bool parent_gave_up; + + /* The child waits on this semaphore. */ + sem_t sem_child; + + /* If true, the parent should give up as well. */ + bool child_gave_up; +}; + +#define CHILD_FAIL_IF(x, sync) \ + do { \ + if (x) { \ + fprintf(stderr, \ + "[FAIL] Test FAILED on line %d\n", __LINE__); \ + (sync)->child_gave_up = true; \ + prod_parent(sync); \ + return 1; \ + } \ + } while (0) + +#define PARENT_FAIL_IF(x, sync) \ + do { \ + if (x) { \ + fprintf(stderr, \ + "[FAIL] Test FAILED on line %d\n", __LINE__); \ + (sync)->parent_gave_up = true; \ + prod_child(sync); \ + return 1; \ + } \ + } while (0) + +#define PARENT_SKIP_IF_UNSUPPORTED(x, sync) \ + do { \ + if ((x) == -1 && (errno == ENODEV || errno == EINVAL)) { \ + (sync)->parent_gave_up = true; \ + prod_child(sync); \ + SKIP_IF(1); \ + } \ + } while (0) + +int init_child_sync(struct child_sync *sync) +{ + int ret; + + ret = sem_init(&sync->sem_parent, 1, 0); + if (ret) { + perror("Semaphore initialization failed"); + return 1; + } + + ret = sem_init(&sync->sem_child, 1, 0); + if (ret) { + perror("Semaphore initialization failed"); + return 1; + } + + return 0; +} + +void destroy_child_sync(struct child_sync *sync) +{ + sem_destroy(&sync->sem_parent); + sem_destroy(&sync->sem_child); +} + +int wait_child(struct child_sync *sync) +{ + int ret; + + /* Wait until the child prods us. */ + ret = sem_wait(&sync->sem_parent); + if (ret) { + perror("Error waiting for child"); + return 1; + } + + return sync->child_gave_up; +} + +int prod_child(struct child_sync *sync) +{ + int ret; + + /* Unblock the child now. */ + ret = sem_post(&sync->sem_child); + if (ret) { + perror("Error prodding child"); + return 1; + } + + return 0; +} + +int wait_parent(struct child_sync *sync) +{ + int ret; + + /* Wait until the parent prods us. */ + ret = sem_wait(&sync->sem_child); + if (ret) { + perror("Error waiting for parent"); + return 1; + } + + return sync->parent_gave_up; +} + +int prod_parent(struct child_sync *sync) +{ + int ret; + + /* Unblock the parent now. */ + ret = sem_post(&sync->sem_parent); + if (ret) { + perror("Error prodding parent"); + return 1; + } + + return 0; +} diff --git a/tools/testing/selftests/powerpc/ptrace/core-pkey.c b/tools/testing/selftests/powerpc/ptrace/core-pkey.c new file mode 100644 index 0000000..36bc312 --- /dev/null +++ b/tools/testing/selftests/powerpc/ptrace/core-pkey.c @@ -0,0 +1,461 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Ptrace test for Memory Protection Key registers + * + * Copyright (C) 2015 Anshuman Khandual, IBM Corporation. + * Copyright (C) 2018 IBM Corporation. + */ +#include <limits.h> +#include <linux/kernel.h> +#include <sys/mman.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <sys/time.h> +#include <sys/resource.h> +#include <fcntl.h> +#include <unistd.h> +#include "ptrace.h" +#include "child.h" + +#ifndef __NR_pkey_alloc +#define __NR_pkey_alloc 384 +#endif + +#ifndef __NR_pkey_free +#define __NR_pkey_free 385 +#endif + +#ifndef NT_PPC_PKEY +#define NT_PPC_PKEY 0x110 +#endif + +#ifndef PKEY_DISABLE_EXECUTE +#define PKEY_DISABLE_EXECUTE 0x4 +#endif + +#define AMR_BITS_PER_PKEY 2 +#define PKEY_REG_BITS (sizeof(u64) * 8) +#define pkeyshift(pkey) (PKEY_REG_BITS - ((pkey + 1) * AMR_BITS_PER_PKEY)) + +#define CORE_FILE_LIMIT (5 * 1024 * 1024) /* 5 MB should be enough */ + +static const char core_pattern_file[] = "/proc/sys/kernel/core_pattern"; + +static const char user_write[] = "[User Write (Running)]"; +static const char core_read_running[] = "[Core Read (Running)]"; + +/* Information shared between the parent and the child. */ +struct shared_info { + struct child_sync child_sync; + + /* AMR value the parent expects to read in the core file. */ + unsigned long amr; + + /* IAMR value the parent expects to read in the core file. */ + unsigned long iamr; + + /* UAMOR value the parent expects to read in the core file. */ + unsigned long uamor; + + /* When the child crashed. */ + time_t core_time; +}; + +static int sys_pkey_alloc(unsigned long flags, unsigned long init_access_rights) +{ + return syscall(__NR_pkey_alloc, flags, init_access_rights); +} + +static int sys_pkey_free(int pkey) +{ + return syscall(__NR_pkey_free, pkey); +} + +static int increase_core_file_limit(void) +{ + struct rlimit rlim; + int ret; + + ret = getrlimit(RLIMIT_CORE, &rlim); + FAIL_IF(ret); + + if (rlim.rlim_cur != RLIM_INFINITY && rlim.rlim_cur < CORE_FILE_LIMIT) { + rlim.rlim_cur = CORE_FILE_LIMIT; + + if (rlim.rlim_max != RLIM_INFINITY && + rlim.rlim_max < CORE_FILE_LIMIT) + rlim.rlim_max = CORE_FILE_LIMIT; + + ret = setrlimit(RLIMIT_CORE, &rlim); + FAIL_IF(ret); + } + + ret = getrlimit(RLIMIT_FSIZE, &rlim); + FAIL_IF(ret); + + if (rlim.rlim_cur != RLIM_INFINITY && rlim.rlim_cur < CORE_FILE_LIMIT) { + rlim.rlim_cur = CORE_FILE_LIMIT; + + if (rlim.rlim_max != RLIM_INFINITY && + rlim.rlim_max < CORE_FILE_LIMIT) + rlim.rlim_max = CORE_FILE_LIMIT; + + ret = setrlimit(RLIMIT_FSIZE, &rlim); + FAIL_IF(ret); + } + + return TEST_PASS; +} + +static int child(struct shared_info *info) +{ + bool disable_execute = true; + int pkey1, pkey2, pkey3; + int *ptr, ret; + + /* Wait until parent fills out the initial register values. */ + ret = wait_parent(&info->child_sync); + if (ret) + return ret; + + ret = increase_core_file_limit(); + FAIL_IF(ret); + + /* Get some pkeys so that we can change their bits in the AMR. */ + pkey1 = sys_pkey_alloc(0, PKEY_DISABLE_EXECUTE); + if (pkey1 < 0) { + pkey1 = sys_pkey_alloc(0, 0); + FAIL_IF(pkey1 < 0); + + disable_execute = false; + } + + pkey2 = sys_pkey_alloc(0, 0); + FAIL_IF(pkey2 < 0); + + pkey3 = sys_pkey_alloc(0, 0); + FAIL_IF(pkey3 < 0); + + info->amr |= 3ul << pkeyshift(pkey1) | 2ul << pkeyshift(pkey2); + + if (disable_execute) + info->iamr |= 1ul << pkeyshift(pkey1); + + info->uamor |= 3ul << pkeyshift(pkey1) | 3ul << pkeyshift(pkey2); + + printf("%-30s AMR: %016lx pkey1: %d pkey2: %d pkey3: %d\n", + user_write, info->amr, pkey1, pkey2, pkey3); + + mtspr(SPRN_AMR, info->amr); + + /* + * We won't use pkey3. This tests whether the kernel restores the UAMOR + * permissions after a key is freed. + */ + sys_pkey_free(pkey3); + + info->core_time = time(NULL); + + /* Crash. */ + ptr = 0; + *ptr = 1; + + /* Shouldn't get here. */ + FAIL_IF(true); + + return TEST_FAIL; +} + +/* Return file size if filename exists and pass sanity check, or zero if not. */ +static off_t try_core_file(const char *filename, struct shared_info *info, + pid_t pid) +{ + struct stat buf; + int ret; + + ret = stat(filename, &buf); + if (ret == -1) + return TEST_FAIL; + + /* Make sure we're not using a stale core file. */ + return buf.st_mtime >= info->core_time ? buf.st_size : TEST_FAIL; +} + +static Elf64_Nhdr *next_note(Elf64_Nhdr *nhdr) +{ + return (void *) nhdr + sizeof(*nhdr) + + __ALIGN_KERNEL(nhdr->n_namesz, 4) + + __ALIGN_KERNEL(nhdr->n_descsz, 4); +} + +static int check_core_file(struct shared_info *info, Elf64_Ehdr *ehdr, + off_t core_size) +{ + unsigned long *regs; + Elf64_Phdr *phdr; + Elf64_Nhdr *nhdr; + size_t phdr_size; + void *p = ehdr, *note; + int ret; + + ret = memcmp(ehdr->e_ident, ELFMAG, SELFMAG); + FAIL_IF(ret); + + FAIL_IF(ehdr->e_type != ET_CORE); + FAIL_IF(ehdr->e_machine != EM_PPC64); + FAIL_IF(ehdr->e_phoff == 0 || ehdr->e_phnum == 0); + + /* + * e_phnum is at most 65535 so calculating the size of the + * program header cannot overflow. + */ + phdr_size = sizeof(*phdr) * ehdr->e_phnum; + + /* Sanity check the program header table location. */ + FAIL_IF(ehdr->e_phoff + phdr_size < ehdr->e_phoff); + FAIL_IF(ehdr->e_phoff + phdr_size > core_size); + + /* Find the PT_NOTE segment. */ + for (phdr = p + ehdr->e_phoff; + (void *) phdr < p + ehdr->e_phoff + phdr_size; + phdr += ehdr->e_phentsize) + if (phdr->p_type == PT_NOTE) + break; + + FAIL_IF((void *) phdr >= p + ehdr->e_phoff + phdr_size); + + /* Find the NT_PPC_PKEY note. */ + for (nhdr = p + phdr->p_offset; + (void *) nhdr < p + phdr->p_offset + phdr->p_filesz; + nhdr = next_note(nhdr)) + if (nhdr->n_type == NT_PPC_PKEY) + break; + + FAIL_IF((void *) nhdr >= p + phdr->p_offset + phdr->p_filesz); + FAIL_IF(nhdr->n_descsz == 0); + + p = nhdr; + note = p + sizeof(*nhdr) + __ALIGN_KERNEL(nhdr->n_namesz, 4); + + regs = (unsigned long *) note; + + printf("%-30s AMR: %016lx IAMR: %016lx UAMOR: %016lx\n", + core_read_running, regs[0], regs[1], regs[2]); + + FAIL_IF(regs[0] != info->amr); + FAIL_IF(regs[1] != info->iamr); + FAIL_IF(regs[2] != info->uamor); + + return TEST_PASS; +} + +static int parent(struct shared_info *info, pid_t pid) +{ + char *filenames, *filename[3]; + int fd, i, ret, status; + unsigned long regs[3]; + off_t core_size; + void *core; + + /* + * Get the initial values for AMR, IAMR and UAMOR and communicate them + * to the child. + */ + ret = ptrace_read_regs(pid, NT_PPC_PKEY, regs, 3); + PARENT_SKIP_IF_UNSUPPORTED(ret, &info->child_sync); + PARENT_FAIL_IF(ret, &info->child_sync); + + info->amr = regs[0]; + info->iamr = regs[1]; + info->uamor = regs[2]; + + /* Wake up child so that it can set itself up. */ + ret = prod_child(&info->child_sync); + PARENT_FAIL_IF(ret, &info->child_sync); + + ret = wait(&status); + if (ret != pid) { + printf("Child's exit status not captured\n"); + return TEST_FAIL; + } else if (!WIFSIGNALED(status) || !WCOREDUMP(status)) { + printf("Child didn't dump core\n"); + return TEST_FAIL; + } + + /* Construct array of core file names to try. */ + + filename[0] = filenames = malloc(PATH_MAX); + if (!filenames) { + perror("Error allocating memory"); + return TEST_FAIL; + } + + ret = snprintf(filename[0], PATH_MAX, "core-pkey.%d", pid); + if (ret < 0 || ret >= PATH_MAX) { + ret = TEST_FAIL; + goto out; + } + + filename[1] = filename[0] + ret + 1; + ret = snprintf(filename[1], PATH_MAX - ret - 1, "core.%d", pid); + if (ret < 0 || ret >= PATH_MAX - ret - 1) { + ret = TEST_FAIL; + goto out; + } + filename[2] = "core"; + + for (i = 0; i < 3; i++) { + core_size = try_core_file(filename[i], info, pid); + if (core_size != TEST_FAIL) + break; + } + + if (i == 3) { + printf("Couldn't find core file\n"); + ret = TEST_FAIL; + goto out; + } + + fd = open(filename[i], O_RDONLY); + if (fd == -1) { + perror("Error opening core file"); + ret = TEST_FAIL; + goto out; + } + + core = mmap(NULL, core_size, PROT_READ, MAP_PRIVATE, fd, 0); + if (core == (void *) -1) { + perror("Error mmaping core file"); + ret = TEST_FAIL; + goto out; + } + + ret = check_core_file(info, core, core_size); + + munmap(core, core_size); + close(fd); + unlink(filename[i]); + + out: + free(filenames); + + return ret; +} + +static int write_core_pattern(const char *core_pattern) +{ + size_t len = strlen(core_pattern), ret; + FILE *f; + + f = fopen(core_pattern_file, "w"); + if (!f) { + perror("Error writing to core_pattern file"); + return TEST_FAIL; + } + + ret = fwrite(core_pattern, 1, len, f); + fclose(f); + if (ret != len) { + perror("Error writing to core_pattern file"); + return TEST_FAIL; + } + + return TEST_PASS; +} + +static int setup_core_pattern(char **core_pattern_, bool *changed_) +{ + FILE *f; + char *core_pattern; + int ret; + + core_pattern = malloc(PATH_MAX); + if (!core_pattern) { + perror("Error allocating memory"); + return TEST_FAIL; + } + + f = fopen(core_pattern_file, "r"); + if (!f) { + perror("Error opening core_pattern file"); + ret = TEST_FAIL; + goto out; + } + + ret = fread(core_pattern, 1, PATH_MAX, f); + fclose(f); + if (!ret) { + perror("Error reading core_pattern file"); + ret = TEST_FAIL; + goto out; + } + + /* Check whether we can predict the name of the core file. */ + if (!strcmp(core_pattern, "core") || !strcmp(core_pattern, "core.%p")) + *changed_ = false; + else { + ret = write_core_pattern("core-pkey.%p"); + if (ret) + goto out; + + *changed_ = true; + } + + *core_pattern_ = core_pattern; + ret = TEST_PASS; + + out: + if (ret) + free(core_pattern); + + return ret; +} + +static int core_pkey(void) +{ + char *core_pattern; + bool changed_core_pattern; + struct shared_info *info; + int shm_id; + int ret; + pid_t pid; + + ret = setup_core_pattern(&core_pattern, &changed_core_pattern); + if (ret) + return ret; + + shm_id = shmget(IPC_PRIVATE, sizeof(*info), 0777 | IPC_CREAT); + info = shmat(shm_id, NULL, 0); + + ret = init_child_sync(&info->child_sync); + if (ret) + return ret; + + pid = fork(); + if (pid < 0) { + perror("fork() failed"); + ret = TEST_FAIL; + } else if (pid == 0) + ret = child(info); + else + ret = parent(info, pid); + + shmdt(info); + + if (pid) { + destroy_child_sync(&info->child_sync); + shmctl(shm_id, IPC_RMID, NULL); + + if (changed_core_pattern) + write_core_pattern(core_pattern); + } + + free(core_pattern); + + return ret; +} + +int main(int argc, char *argv[]) +{ + return test_harness(core_pkey, "core_pkey"); +} diff --git a/tools/testing/selftests/powerpc/ptrace/perf-hwbreak.c b/tools/testing/selftests/powerpc/ptrace/perf-hwbreak.c new file mode 100644 index 0000000..60df0b5 --- /dev/null +++ b/tools/testing/selftests/powerpc/ptrace/perf-hwbreak.c @@ -0,0 +1,195 @@ +/* + * perf events self profiling example test case for hw breakpoints. + * + * This tests perf PERF_TYPE_BREAKPOINT parameters + * 1) tests all variants of the break on read/write flags + * 2) tests exclude_user == 0 and 1 + * 3) test array matches (if DAWR is supported)) + * 4) test different numbers of breakpoints matches + * + * Configure this breakpoint, then read and write the data a number of + * times. Then check the output count from perf is as expected. + * + * Based on: + * http://ozlabs.org/~anton/junkcode/perf_events_example1.c + * + * Copyright (C) 2018 Michael Neuling, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <unistd.h> +#include <assert.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <elf.h> +#include <pthread.h> +#include <sys/syscall.h> +#include <linux/perf_event.h> +#include <linux/hw_breakpoint.h> +#include "utils.h" + +#define MAX_LOOPS 10000 + +#define DAWR_LENGTH_MAX ((0x3f + 1) * 8) + +static inline int sys_perf_event_open(struct perf_event_attr *attr, pid_t pid, + int cpu, int group_fd, + unsigned long flags) +{ + attr->size = sizeof(*attr); + return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags); +} + +static inline bool breakpoint_test(int len) +{ + struct perf_event_attr attr; + int fd; + + /* setup counters */ + memset(&attr, 0, sizeof(attr)); + attr.disabled = 1; + attr.type = PERF_TYPE_BREAKPOINT; + attr.bp_type = HW_BREAKPOINT_R; + /* bp_addr can point anywhere but needs to be aligned */ + attr.bp_addr = (__u64)(&attr) & 0xfffffffffffff800; + attr.bp_len = len; + fd = sys_perf_event_open(&attr, 0, -1, -1, 0); + if (fd < 0) + return false; + close(fd); + return true; +} + +static inline bool perf_breakpoint_supported(void) +{ + return breakpoint_test(4); +} + +static inline bool dawr_supported(void) +{ + return breakpoint_test(DAWR_LENGTH_MAX); +} + +static int runtestsingle(int readwriteflag, int exclude_user, int arraytest) +{ + int i,j; + struct perf_event_attr attr; + size_t res; + unsigned long long breaks, needed; + int readint; + int readintarraybig[2*DAWR_LENGTH_MAX/sizeof(int)]; + int *readintalign; + volatile int *ptr; + int break_fd; + int loop_num = MAX_LOOPS - (rand() % 100); /* provide some variability */ + volatile int *k; + + /* align to 0x400 boundary as required by DAWR */ + readintalign = (int *)(((unsigned long)readintarraybig + 0x7ff) & + 0xfffffffffffff800); + + ptr = &readint; + if (arraytest) + ptr = &readintalign[0]; + + /* setup counters */ + memset(&attr, 0, sizeof(attr)); + attr.disabled = 1; + attr.type = PERF_TYPE_BREAKPOINT; + attr.bp_type = readwriteflag; + attr.bp_addr = (__u64)ptr; + attr.bp_len = sizeof(int); + if (arraytest) + attr.bp_len = DAWR_LENGTH_MAX; + attr.exclude_user = exclude_user; + break_fd = sys_perf_event_open(&attr, 0, -1, -1, 0); + if (break_fd < 0) { + perror("sys_perf_event_open"); + exit(1); + } + + /* start counters */ + ioctl(break_fd, PERF_EVENT_IOC_ENABLE); + + /* Test a bunch of reads and writes */ + k = &readint; + for (i = 0; i < loop_num; i++) { + if (arraytest) + k = &(readintalign[i % (DAWR_LENGTH_MAX/sizeof(int))]); + + j = *k; + *k = j; + } + + /* stop counters */ + ioctl(break_fd, PERF_EVENT_IOC_DISABLE); + + /* read and check counters */ + res = read(break_fd, &breaks, sizeof(unsigned long long)); + assert(res == sizeof(unsigned long long)); + /* we read and write each loop, so subtract the ones we are counting */ + needed = 0; + if (readwriteflag & HW_BREAKPOINT_R) + needed += loop_num; + if (readwriteflag & HW_BREAKPOINT_W) + needed += loop_num; + needed = needed * (1 - exclude_user); + printf("TESTED: addr:0x%lx brks:% 8lld loops:% 8i rw:%i !user:%i array:%i\n", + (unsigned long int)ptr, breaks, loop_num, readwriteflag, exclude_user, arraytest); + if (breaks != needed) { + printf("FAILED: 0x%lx brks:%lld needed:%lli %i %i %i\n\n", + (unsigned long int)ptr, breaks, needed, loop_num, readwriteflag, exclude_user); + return 1; + } + close(break_fd); + + return 0; +} + +static int runtest(void) +{ + int rwflag; + int exclude_user; + int ret; + + /* + * perf defines rwflag as two bits read and write and at least + * one must be set. So range 1-3. + */ + for (rwflag = 1 ; rwflag < 4; rwflag++) { + for (exclude_user = 0 ; exclude_user < 2; exclude_user++) { + ret = runtestsingle(rwflag, exclude_user, 0); + if (ret) + return ret; + + /* if we have the dawr, we can do an array test */ + if (!dawr_supported()) + continue; + ret = runtestsingle(rwflag, exclude_user, 1); + if (ret) + return ret; + } + } + return 0; +} + + +static int perf_hwbreak(void) +{ + srand ( time(NULL) ); + + SKIP_IF(!perf_breakpoint_supported()); + + return runtest(); +} + +int main(int argc, char *argv[], char **envp) +{ + return test_harness(perf_hwbreak, "perf_hwbreak"); +} diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c b/tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c new file mode 100644 index 0000000..3066d31 --- /dev/null +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c @@ -0,0 +1,342 @@ +// SPDX-License-Identifier: GPL-2.0+ + +/* + * Ptrace test for hw breakpoints + * + * Based on tools/testing/selftests/breakpoints/breakpoint_test.c + * + * This test forks and the parent then traces the child doing various + * types of ptrace enabled breakpoints + * + * Copyright (C) 2018 Michael Neuling, IBM Corporation. + */ + +#include <sys/ptrace.h> +#include <unistd.h> +#include <stddef.h> +#include <sys/user.h> +#include <stdio.h> +#include <stdlib.h> +#include <signal.h> +#include <sys/types.h> +#include <sys/wait.h> +#include "ptrace.h" + +/* Breakpoint access modes */ +enum { + BP_X = 1, + BP_RW = 2, + BP_W = 4, +}; + +static pid_t child_pid; +static struct ppc_debug_info dbginfo; + +static void get_dbginfo(void) +{ + int ret; + + ret = ptrace(PPC_PTRACE_GETHWDBGINFO, child_pid, NULL, &dbginfo); + if (ret) { + perror("Can't get breakpoint info\n"); + exit(-1); + } +} + +static bool hwbreak_present(void) +{ + return (dbginfo.num_data_bps != 0); +} + +static bool dawr_present(void) +{ + return !!(dbginfo.features & PPC_DEBUG_FEATURE_DATA_BP_DAWR); +} + +static void set_breakpoint_addr(void *addr) +{ + int ret; + + ret = ptrace(PTRACE_SET_DEBUGREG, child_pid, 0, addr); + if (ret) { + perror("Can't set breakpoint addr\n"); + exit(-1); + } +} + +static int set_hwbreakpoint_addr(void *addr, int range) +{ + int ret; + + struct ppc_hw_breakpoint info; + + info.version = 1; + info.trigger_type = PPC_BREAKPOINT_TRIGGER_RW; + info.addr_mode = PPC_BREAKPOINT_MODE_EXACT; + if (range > 0) + info.addr_mode = PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE; + info.condition_mode = PPC_BREAKPOINT_CONDITION_NONE; + info.addr = (__u64)addr; + info.addr2 = (__u64)addr + range; + info.condition_value = 0; + + ret = ptrace(PPC_PTRACE_SETHWDEBUG, child_pid, 0, &info); + if (ret < 0) { + perror("Can't set breakpoint\n"); + exit(-1); + } + return ret; +} + +static int del_hwbreakpoint_addr(int watchpoint_handle) +{ + int ret; + + ret = ptrace(PPC_PTRACE_DELHWDEBUG, child_pid, 0, watchpoint_handle); + if (ret < 0) { + perror("Can't delete hw breakpoint\n"); + exit(-1); + } + return ret; +} + +#define DAWR_LENGTH_MAX 512 + +/* Dummy variables to test read/write accesses */ +static unsigned long long + dummy_array[DAWR_LENGTH_MAX / sizeof(unsigned long long)] + __attribute__((aligned(512))); +static unsigned long long *dummy_var = dummy_array; + +static void write_var(int len) +{ + long long *plval; + char *pcval; + short *psval; + int *pival; + + switch (len) { + case 1: + pcval = (char *)dummy_var; + *pcval = 0xff; + break; + case 2: + psval = (short *)dummy_var; + *psval = 0xffff; + break; + case 4: + pival = (int *)dummy_var; + *pival = 0xffffffff; + break; + case 8: + plval = (long long *)dummy_var; + *plval = 0xffffffffffffffffLL; + break; + } +} + +static void read_var(int len) +{ + char cval __attribute__((unused)); + short sval __attribute__((unused)); + int ival __attribute__((unused)); + long long lval __attribute__((unused)); + + switch (len) { + case 1: + cval = *(char *)dummy_var; + break; + case 2: + sval = *(short *)dummy_var; + break; + case 4: + ival = *(int *)dummy_var; + break; + case 8: + lval = *(long long *)dummy_var; + break; + } +} + +/* + * Do the r/w accesses to trigger the breakpoints. And run + * the usual traps. + */ +static void trigger_tests(void) +{ + int len, ret; + + ret = ptrace(PTRACE_TRACEME, 0, NULL, 0); + if (ret) { + perror("Can't be traced?\n"); + return; + } + + /* Wake up father so that it sets up the first test */ + kill(getpid(), SIGUSR1); + + /* Test write watchpoints */ + for (len = 1; len <= sizeof(long); len <<= 1) + write_var(len); + + /* Test read/write watchpoints (on read accesses) */ + for (len = 1; len <= sizeof(long); len <<= 1) + read_var(len); + + /* Test when breakpoint is unset */ + + /* Test write watchpoints */ + for (len = 1; len <= sizeof(long); len <<= 1) + write_var(len); + + /* Test read/write watchpoints (on read accesses) */ + for (len = 1; len <= sizeof(long); len <<= 1) + read_var(len); +} + +static void check_success(const char *msg) +{ + const char *msg2; + int status; + + /* Wait for the child to SIGTRAP */ + wait(&status); + + msg2 = "Failed"; + + if (WIFSTOPPED(status) && WSTOPSIG(status) == SIGTRAP) { + msg2 = "Child process hit the breakpoint"; + } + + printf("%s Result: [%s]\n", msg, msg2); +} + +static void launch_watchpoints(char *buf, int mode, int len, + struct ppc_debug_info *dbginfo, bool dawr) +{ + const char *mode_str; + unsigned long data = (unsigned long)(dummy_var); + int wh, range; + + data &= ~0x7UL; + + if (mode == BP_W) { + data |= (1UL << 1); + mode_str = "write"; + } else { + data |= (1UL << 0); + data |= (1UL << 1); + mode_str = "read"; + } + + /* Set DABR_TRANSLATION bit */ + data |= (1UL << 2); + + /* use PTRACE_SET_DEBUGREG breakpoints */ + set_breakpoint_addr((void *)data); + ptrace(PTRACE_CONT, child_pid, NULL, 0); + sprintf(buf, "Test %s watchpoint with len: %d ", mode_str, len); + check_success(buf); + /* Unregister hw brkpoint */ + set_breakpoint_addr(NULL); + + data = (data & ~7); /* remove dabr control bits */ + + /* use PPC_PTRACE_SETHWDEBUG breakpoint */ + if (!(dbginfo->features & PPC_DEBUG_FEATURE_DATA_BP_RANGE)) + return; /* not supported */ + wh = set_hwbreakpoint_addr((void *)data, 0); + ptrace(PTRACE_CONT, child_pid, NULL, 0); + sprintf(buf, "Test %s watchpoint with len: %d ", mode_str, len); + check_success(buf); + /* Unregister hw brkpoint */ + del_hwbreakpoint_addr(wh); + + /* try a wider range */ + range = 8; + if (dawr) + range = 512 - ((int)data & (DAWR_LENGTH_MAX - 1)); + wh = set_hwbreakpoint_addr((void *)data, range); + ptrace(PTRACE_CONT, child_pid, NULL, 0); + sprintf(buf, "Test %s watchpoint with len: %d ", mode_str, len); + check_success(buf); + /* Unregister hw brkpoint */ + del_hwbreakpoint_addr(wh); +} + +/* Set the breakpoints and check the child successfully trigger them */ +static int launch_tests(bool dawr) +{ + char buf[1024]; + int len, i, status; + + struct ppc_debug_info dbginfo; + + i = ptrace(PPC_PTRACE_GETHWDBGINFO, child_pid, NULL, &dbginfo); + if (i) { + perror("Can't set breakpoint info\n"); + exit(-1); + } + if (!(dbginfo.features & PPC_DEBUG_FEATURE_DATA_BP_RANGE)) + printf("WARNING: Kernel doesn't support PPC_PTRACE_SETHWDEBUG\n"); + + /* Write watchpoint */ + for (len = 1; len <= sizeof(long); len <<= 1) + launch_watchpoints(buf, BP_W, len, &dbginfo, dawr); + + /* Read-Write watchpoint */ + for (len = 1; len <= sizeof(long); len <<= 1) + launch_watchpoints(buf, BP_RW, len, &dbginfo, dawr); + + ptrace(PTRACE_CONT, child_pid, NULL, 0); + + /* + * Now we have unregistered the breakpoint, access by child + * should not cause SIGTRAP. + */ + + wait(&status); + + if (WIFSTOPPED(status) && WSTOPSIG(status) == SIGTRAP) { + printf("FAIL: Child process hit the breakpoint, which is not expected\n"); + ptrace(PTRACE_CONT, child_pid, NULL, 0); + return TEST_FAIL; + } + + if (WIFEXITED(status)) + printf("Child exited normally\n"); + + return TEST_PASS; +} + +static int ptrace_hwbreak(void) +{ + pid_t pid; + int ret; + bool dawr; + + pid = fork(); + if (!pid) { + trigger_tests(); + return 0; + } + + wait(NULL); + + child_pid = pid; + + get_dbginfo(); + SKIP_IF(!hwbreak_present()); + dawr = dawr_present(); + + ret = launch_tests(dawr); + + wait(NULL); + + return ret; +} + +int main(int argc, char **argv, char **envp) +{ + return test_harness(ptrace_hwbreak, "ptrace-hwbreak"); +} diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c b/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c new file mode 100644 index 0000000..5cf631f --- /dev/null +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c @@ -0,0 +1,327 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Ptrace test for Memory Protection Key registers + * + * Copyright (C) 2015 Anshuman Khandual, IBM Corporation. + * Copyright (C) 2018 IBM Corporation. + */ +#include "ptrace.h" +#include "child.h" + +#ifndef __NR_pkey_alloc +#define __NR_pkey_alloc 384 +#endif + +#ifndef __NR_pkey_free +#define __NR_pkey_free 385 +#endif + +#ifndef NT_PPC_PKEY +#define NT_PPC_PKEY 0x110 +#endif + +#ifndef PKEY_DISABLE_EXECUTE +#define PKEY_DISABLE_EXECUTE 0x4 +#endif + +#define AMR_BITS_PER_PKEY 2 +#define PKEY_REG_BITS (sizeof(u64) * 8) +#define pkeyshift(pkey) (PKEY_REG_BITS - ((pkey + 1) * AMR_BITS_PER_PKEY)) + +static const char user_read[] = "[User Read (Running)]"; +static const char user_write[] = "[User Write (Running)]"; +static const char ptrace_read_running[] = "[Ptrace Read (Running)]"; +static const char ptrace_write_running[] = "[Ptrace Write (Running)]"; + +/* Information shared between the parent and the child. */ +struct shared_info { + struct child_sync child_sync; + + /* AMR value the parent expects to read from the child. */ + unsigned long amr1; + + /* AMR value the parent is expected to write to the child. */ + unsigned long amr2; + + /* AMR value that ptrace should refuse to write to the child. */ + unsigned long amr3; + + /* IAMR value the parent expects to read from the child. */ + unsigned long expected_iamr; + + /* UAMOR value the parent expects to read from the child. */ + unsigned long expected_uamor; + + /* + * IAMR and UAMOR values that ptrace should refuse to write to the child + * (even though they're valid ones) because userspace doesn't have + * access to those registers. + */ + unsigned long new_iamr; + unsigned long new_uamor; +}; + +static int sys_pkey_alloc(unsigned long flags, unsigned long init_access_rights) +{ + return syscall(__NR_pkey_alloc, flags, init_access_rights); +} + +static int sys_pkey_free(int pkey) +{ + return syscall(__NR_pkey_free, pkey); +} + +static int child(struct shared_info *info) +{ + unsigned long reg; + bool disable_execute = true; + int pkey1, pkey2, pkey3; + int ret; + + /* Wait until parent fills out the initial register values. */ + ret = wait_parent(&info->child_sync); + if (ret) + return ret; + + /* Get some pkeys so that we can change their bits in the AMR. */ + pkey1 = sys_pkey_alloc(0, PKEY_DISABLE_EXECUTE); + if (pkey1 < 0) { + pkey1 = sys_pkey_alloc(0, 0); + CHILD_FAIL_IF(pkey1 < 0, &info->child_sync); + + disable_execute = false; + } + + pkey2 = sys_pkey_alloc(0, 0); + CHILD_FAIL_IF(pkey2 < 0, &info->child_sync); + + pkey3 = sys_pkey_alloc(0, 0); + CHILD_FAIL_IF(pkey3 < 0, &info->child_sync); + + info->amr1 |= 3ul << pkeyshift(pkey1); + info->amr2 |= 3ul << pkeyshift(pkey2); + info->amr3 |= info->amr2 | 3ul << pkeyshift(pkey3); + + if (disable_execute) + info->expected_iamr |= 1ul << pkeyshift(pkey1); + + info->expected_uamor |= 3ul << pkeyshift(pkey1) | + 3ul << pkeyshift(pkey2); + info->new_iamr |= 1ul << pkeyshift(pkey1) | 1ul << pkeyshift(pkey2); + info->new_uamor |= 3ul << pkeyshift(pkey1); + + /* + * We won't use pkey3. We just want a plausible but invalid key to test + * whether ptrace will let us write to AMR bits we are not supposed to. + * + * This also tests whether the kernel restores the UAMOR permissions + * after a key is freed. + */ + sys_pkey_free(pkey3); + + printf("%-30s AMR: %016lx pkey1: %d pkey2: %d pkey3: %d\n", + user_write, info->amr1, pkey1, pkey2, pkey3); + + mtspr(SPRN_AMR, info->amr1); + + /* Wait for parent to read our AMR value and write a new one. */ + ret = prod_parent(&info->child_sync); + CHILD_FAIL_IF(ret, &info->child_sync); + + ret = wait_parent(&info->child_sync); + if (ret) + return ret; + + reg = mfspr(SPRN_AMR); + + printf("%-30s AMR: %016lx\n", user_read, reg); + + CHILD_FAIL_IF(reg != info->amr2, &info->child_sync); + + /* + * Wait for parent to try to write an invalid AMR value. + */ + ret = prod_parent(&info->child_sync); + CHILD_FAIL_IF(ret, &info->child_sync); + + ret = wait_parent(&info->child_sync); + if (ret) + return ret; + + reg = mfspr(SPRN_AMR); + + printf("%-30s AMR: %016lx\n", user_read, reg); + + CHILD_FAIL_IF(reg != info->amr2, &info->child_sync); + + /* + * Wait for parent to try to write an IAMR and a UAMOR value. We can't + * verify them, but we can verify that the AMR didn't change. + */ + ret = prod_parent(&info->child_sync); + CHILD_FAIL_IF(ret, &info->child_sync); + + ret = wait_parent(&info->child_sync); + if (ret) + return ret; + + reg = mfspr(SPRN_AMR); + + printf("%-30s AMR: %016lx\n", user_read, reg); + + CHILD_FAIL_IF(reg != info->amr2, &info->child_sync); + + /* Now let parent now that we are finished. */ + + ret = prod_parent(&info->child_sync); + CHILD_FAIL_IF(ret, &info->child_sync); + + return TEST_PASS; +} + +static int parent(struct shared_info *info, pid_t pid) +{ + unsigned long regs[3]; + int ret, status; + + /* + * Get the initial values for AMR, IAMR and UAMOR and communicate them + * to the child. + */ + ret = ptrace_read_regs(pid, NT_PPC_PKEY, regs, 3); + PARENT_SKIP_IF_UNSUPPORTED(ret, &info->child_sync); + PARENT_FAIL_IF(ret, &info->child_sync); + + info->amr1 = info->amr2 = info->amr3 = regs[0]; + info->expected_iamr = info->new_iamr = regs[1]; + info->expected_uamor = info->new_uamor = regs[2]; + + /* Wake up child so that it can set itself up. */ + ret = prod_child(&info->child_sync); + PARENT_FAIL_IF(ret, &info->child_sync); + + ret = wait_child(&info->child_sync); + if (ret) + return ret; + + /* Verify that we can read the pkey registers from the child. */ + ret = ptrace_read_regs(pid, NT_PPC_PKEY, regs, 3); + PARENT_FAIL_IF(ret, &info->child_sync); + + printf("%-30s AMR: %016lx IAMR: %016lx UAMOR: %016lx\n", + ptrace_read_running, regs[0], regs[1], regs[2]); + + PARENT_FAIL_IF(regs[0] != info->amr1, &info->child_sync); + PARENT_FAIL_IF(regs[1] != info->expected_iamr, &info->child_sync); + PARENT_FAIL_IF(regs[2] != info->expected_uamor, &info->child_sync); + + /* Write valid AMR value in child. */ + ret = ptrace_write_regs(pid, NT_PPC_PKEY, &info->amr2, 1); + PARENT_FAIL_IF(ret, &info->child_sync); + + printf("%-30s AMR: %016lx\n", ptrace_write_running, info->amr2); + + /* Wake up child so that it can verify it changed. */ + ret = prod_child(&info->child_sync); + PARENT_FAIL_IF(ret, &info->child_sync); + + ret = wait_child(&info->child_sync); + if (ret) + return ret; + + /* Write invalid AMR value in child. */ + ret = ptrace_write_regs(pid, NT_PPC_PKEY, &info->amr3, 1); + PARENT_FAIL_IF(ret, &info->child_sync); + + printf("%-30s AMR: %016lx\n", ptrace_write_running, info->amr3); + + /* Wake up child so that it can verify it didn't change. */ + ret = prod_child(&info->child_sync); + PARENT_FAIL_IF(ret, &info->child_sync); + + ret = wait_child(&info->child_sync); + if (ret) + return ret; + + /* Try to write to IAMR. */ + regs[0] = info->amr1; + regs[1] = info->new_iamr; + ret = ptrace_write_regs(pid, NT_PPC_PKEY, regs, 2); + PARENT_FAIL_IF(!ret, &info->child_sync); + + printf("%-30s AMR: %016lx IAMR: %016lx\n", + ptrace_write_running, regs[0], regs[1]); + + /* Try to write to IAMR and UAMOR. */ + regs[2] = info->new_uamor; + ret = ptrace_write_regs(pid, NT_PPC_PKEY, regs, 3); + PARENT_FAIL_IF(!ret, &info->child_sync); + + printf("%-30s AMR: %016lx IAMR: %016lx UAMOR: %016lx\n", + ptrace_write_running, regs[0], regs[1], regs[2]); + + /* Verify that all registers still have their expected values. */ + ret = ptrace_read_regs(pid, NT_PPC_PKEY, regs, 3); + PARENT_FAIL_IF(ret, &info->child_sync); + + printf("%-30s AMR: %016lx IAMR: %016lx UAMOR: %016lx\n", + ptrace_read_running, regs[0], regs[1], regs[2]); + + PARENT_FAIL_IF(regs[0] != info->amr2, &info->child_sync); + PARENT_FAIL_IF(regs[1] != info->expected_iamr, &info->child_sync); + PARENT_FAIL_IF(regs[2] != info->expected_uamor, &info->child_sync); + + /* Wake up child so that it can verify AMR didn't change and wrap up. */ + ret = prod_child(&info->child_sync); + PARENT_FAIL_IF(ret, &info->child_sync); + + ret = wait(&status); + if (ret != pid) { + printf("Child's exit status not captured\n"); + ret = TEST_PASS; + } else if (!WIFEXITED(status)) { + printf("Child exited abnormally\n"); + ret = TEST_FAIL; + } else + ret = WEXITSTATUS(status) ? TEST_FAIL : TEST_PASS; + + return ret; +} + +static int ptrace_pkey(void) +{ + struct shared_info *info; + int shm_id; + int ret; + pid_t pid; + + shm_id = shmget(IPC_PRIVATE, sizeof(*info), 0777 | IPC_CREAT); + info = shmat(shm_id, NULL, 0); + + ret = init_child_sync(&info->child_sync); + if (ret) + return ret; + + pid = fork(); + if (pid < 0) { + perror("fork() failed"); + ret = TEST_FAIL; + } else if (pid == 0) + ret = child(info); + else + ret = parent(info, pid); + + shmdt(info); + + if (pid) { + destroy_child_sync(&info->child_sync); + shmctl(shm_id, IPC_RMID, NULL); + } + + return ret; +} + +int main(int argc, char *argv[]) +{ + return test_harness(ptrace_pkey, "ptrace_pkey"); +} diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace.h b/tools/testing/selftests/powerpc/ptrace/ptrace.h index 19fb8252..34201cf 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace.h +++ b/tools/testing/selftests/powerpc/ptrace/ptrace.h @@ -102,6 +102,44 @@ int cont_trace(pid_t child) return TEST_PASS; } +int ptrace_read_regs(pid_t child, unsigned long type, unsigned long regs[], + int n) +{ + struct iovec iov; + long ret; + + FAIL_IF(start_trace(child)); + + iov.iov_base = regs; + iov.iov_len = n * sizeof(unsigned long); + + ret = ptrace(PTRACE_GETREGSET, child, type, &iov); + if (ret) + return ret; + + FAIL_IF(stop_trace(child)); + + return TEST_PASS; +} + +long ptrace_write_regs(pid_t child, unsigned long type, unsigned long regs[], + int n) +{ + struct iovec iov; + long ret; + + FAIL_IF(start_trace(child)); + + iov.iov_base = regs; + iov.iov_len = n * sizeof(unsigned long); + + ret = ptrace(PTRACE_SETREGSET, child, type, &iov); + + FAIL_IF(stop_trace(child)); + + return ret; +} + /* TAR, PPR, DSCR */ int show_tar_registers(pid_t child, unsigned long *out) { diff --git a/tools/testing/selftests/powerpc/tm/.gitignore b/tools/testing/selftests/powerpc/tm/.gitignore index bb90d4b..c3ee839 100644 --- a/tools/testing/selftests/powerpc/tm/.gitignore +++ b/tools/testing/selftests/powerpc/tm/.gitignore @@ -14,3 +14,4 @@ tm-signal-context-chk-vsx tm-vmx-unavail tm-unavailable tm-trap +tm-sigreturn diff --git a/tools/testing/selftests/proc/.gitignore b/tools/testing/selftests/proc/.gitignore index 6c16f77..74e5912 100644 --- a/tools/testing/selftests/proc/.gitignore +++ b/tools/testing/selftests/proc/.gitignore @@ -1,3 +1,6 @@ +/fd-001-lookup +/fd-002-posix-eq +/fd-003-kthread /proc-loadavg-001 /proc-self-map-files-001 /proc-self-map-files-002 diff --git a/tools/testing/selftests/proc/Makefile b/tools/testing/selftests/proc/Makefile index dbb87e5..db310ee 100644 --- a/tools/testing/selftests/proc/Makefile +++ b/tools/testing/selftests/proc/Makefile @@ -1,6 +1,9 @@ -CFLAGS += -Wall -O2 +CFLAGS += -Wall -O2 -Wno-unused-function TEST_GEN_PROGS := +TEST_GEN_PROGS += fd-001-lookup +TEST_GEN_PROGS += fd-002-posix-eq +TEST_GEN_PROGS += fd-003-kthread TEST_GEN_PROGS += proc-loadavg-001 TEST_GEN_PROGS += proc-self-map-files-001 TEST_GEN_PROGS += proc-self-map-files-002 diff --git a/tools/testing/selftests/proc/fd-001-lookup.c b/tools/testing/selftests/proc/fd-001-lookup.c new file mode 100644 index 0000000..a2010df --- /dev/null +++ b/tools/testing/selftests/proc/fd-001-lookup.c @@ -0,0 +1,168 @@ +/* + * Copyright © 2018 Alexey Dobriyan <adobriyan@gmail.com> + * + * Permission to use, copy, modify, and distribute this software for any + * purpose with or without fee is hereby granted, provided that the above + * copyright notice and this permission notice appear in all copies. + * + * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES + * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR + * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES + * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN + * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF + * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + */ +// Test /proc/*/fd lookup. +#define _GNU_SOURCE +#undef NDEBUG +#include <assert.h> +#include <dirent.h> +#include <errno.h> +#include <limits.h> +#include <sched.h> +#include <stdio.h> +#include <unistd.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> + +#include "proc.h" + +/* lstat(2) has more "coverage" in case non-symlink pops up somehow. */ +static void test_lookup_pass(const char *pathname) +{ + struct stat st; + ssize_t rv; + + memset(&st, 0, sizeof(struct stat)); + rv = lstat(pathname, &st); + assert(rv == 0); + assert(S_ISLNK(st.st_mode)); +} + +static void test_lookup_fail(const char *pathname) +{ + struct stat st; + ssize_t rv; + + rv = lstat(pathname, &st); + assert(rv == -1 && errno == ENOENT); +} + +static void test_lookup(unsigned int fd) +{ + char buf[64]; + unsigned int c; + unsigned int u; + int i; + + snprintf(buf, sizeof(buf), "/proc/self/fd/%u", fd); + test_lookup_pass(buf); + + /* leading junk */ + for (c = 1; c <= 255; c++) { + if (c == '/') + continue; + snprintf(buf, sizeof(buf), "/proc/self/fd/%c%u", c, fd); + test_lookup_fail(buf); + } + + /* trailing junk */ + for (c = 1; c <= 255; c++) { + if (c == '/') + continue; + snprintf(buf, sizeof(buf), "/proc/self/fd/%u%c", fd, c); + test_lookup_fail(buf); + } + + for (i = INT_MIN; i < INT_MIN + 1024; i++) { + snprintf(buf, sizeof(buf), "/proc/self/fd/%d", i); + test_lookup_fail(buf); + } + for (i = -1024; i < 0; i++) { + snprintf(buf, sizeof(buf), "/proc/self/fd/%d", i); + test_lookup_fail(buf); + } + for (u = INT_MAX - 1024; u <= (unsigned int)INT_MAX + 1024; u++) { + snprintf(buf, sizeof(buf), "/proc/self/fd/%u", u); + test_lookup_fail(buf); + } + for (u = UINT_MAX - 1024; u != 0; u++) { + snprintf(buf, sizeof(buf), "/proc/self/fd/%u", u); + test_lookup_fail(buf); + } + + +} + +int main(void) +{ + struct dirent *de; + unsigned int fd, target_fd; + + if (unshare(CLONE_FILES) == -1) + return 1; + + /* Wipe fdtable. */ + do { + DIR *d; + + d = opendir("/proc/self/fd"); + if (!d) + return 1; + + de = xreaddir(d); + assert(de->d_type == DT_DIR); + assert(streq(de->d_name, ".")); + + de = xreaddir(d); + assert(de->d_type == DT_DIR); + assert(streq(de->d_name, "..")); +next: + de = xreaddir(d); + if (de) { + unsigned long long fd_ull; + unsigned int fd; + char *end; + + assert(de->d_type == DT_LNK); + + fd_ull = xstrtoull(de->d_name, &end); + assert(*end == '\0'); + assert(fd_ull == (unsigned int)fd_ull); + + fd = fd_ull; + if (fd == dirfd(d)) + goto next; + close(fd); + } + + closedir(d); + } while (de); + + /* Now fdtable is clean. */ + + fd = open("/", O_PATH|O_DIRECTORY); + assert(fd == 0); + test_lookup(fd); + close(fd); + + /* Clean again! */ + + fd = open("/", O_PATH|O_DIRECTORY); + assert(fd == 0); + /* Default RLIMIT_NOFILE-1 */ + target_fd = 1023; + while (target_fd > 0) { + if (dup2(fd, target_fd) == target_fd) + break; + target_fd /= 2; + } + assert(target_fd > 0); + close(fd); + test_lookup(target_fd); + close(target_fd); + + return 0; +} diff --git a/tools/testing/selftests/proc/fd-002-posix-eq.c b/tools/testing/selftests/proc/fd-002-posix-eq.c new file mode 100644 index 0000000..417322c --- /dev/null +++ b/tools/testing/selftests/proc/fd-002-posix-eq.c @@ -0,0 +1,57 @@ +/* + * Copyright © 2018 Alexey Dobriyan <adobriyan@gmail.com> + * + * Permission to use, copy, modify, and distribute this software for any + * purpose with or without fee is hereby granted, provided that the above + * copyright notice and this permission notice appear in all copies. + * + * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES + * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR + * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES + * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN + * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF + * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + */ +// Test that open(/proc/*/fd/*) opens the same file. +#undef NDEBUG +#include <assert.h> +#include <stdio.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <unistd.h> + +int main(void) +{ + int fd0, fd1, fd2; + struct stat st0, st1, st2; + char buf[64]; + int rv; + + fd0 = open("/", O_DIRECTORY|O_RDONLY); + assert(fd0 >= 0); + + snprintf(buf, sizeof(buf), "/proc/self/fd/%u", fd0); + fd1 = open(buf, O_RDONLY); + assert(fd1 >= 0); + + snprintf(buf, sizeof(buf), "/proc/thread-self/fd/%u", fd0); + fd2 = open(buf, O_RDONLY); + assert(fd2 >= 0); + + rv = fstat(fd0, &st0); + assert(rv == 0); + rv = fstat(fd1, &st1); + assert(rv == 0); + rv = fstat(fd2, &st2); + assert(rv == 0); + + assert(st0.st_dev == st1.st_dev); + assert(st0.st_ino == st1.st_ino); + + assert(st0.st_dev == st2.st_dev); + assert(st0.st_ino == st2.st_ino); + + return 0; +} diff --git a/tools/testing/selftests/proc/fd-003-kthread.c b/tools/testing/selftests/proc/fd-003-kthread.c new file mode 100644 index 0000000..1d659d5 --- /dev/null +++ b/tools/testing/selftests/proc/fd-003-kthread.c @@ -0,0 +1,178 @@ +/* + * Copyright © 2018 Alexey Dobriyan <adobriyan@gmail.com> + * + * Permission to use, copy, modify, and distribute this software for any + * purpose with or without fee is hereby granted, provided that the above + * copyright notice and this permission notice appear in all copies. + * + * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES + * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR + * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES + * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN + * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF + * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + */ +// Test that /proc/$KERNEL_THREAD/fd/ is empty. +#define _GNU_SOURCE +#undef NDEBUG +#include <sys/syscall.h> +#include <assert.h> +#include <dirent.h> +#include <limits.h> +#include <stdio.h> +#include <string.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <unistd.h> + +#include "proc.h" + +#define PF_KHTREAD 0x00200000 + +/* + * Test for kernel threadness atomically with openat(). + * + * Return /proc/$PID/fd descriptor if process is kernel thread. + * Return -1 if a process is userspace process. + */ +static int kernel_thread_fd(unsigned int pid) +{ + unsigned int flags = 0; + char buf[4096]; + int dir_fd, fd; + ssize_t rv; + + snprintf(buf, sizeof(buf), "/proc/%u", pid); + dir_fd = open(buf, O_RDONLY|O_DIRECTORY); + if (dir_fd == -1) + return -1; + + /* + * Believe it or not, struct task_struct::flags is directly exposed + * to userspace! + */ + fd = openat(dir_fd, "stat", O_RDONLY); + if (fd == -1) { + close(dir_fd); + return -1; + } + rv = read(fd, buf, sizeof(buf)); + close(fd); + if (0 < rv && rv <= sizeof(buf)) { + unsigned long long flags_ull; + char *p, *end; + int i; + + assert(buf[rv - 1] == '\n'); + buf[rv - 1] = '\0'; + + /* Search backwards: ->comm can contain whitespace and ')'. */ + for (i = 0; i < 43; i++) { + p = strrchr(buf, ' '); + assert(p); + *p = '\0'; + } + + p = strrchr(buf, ' '); + assert(p); + + flags_ull = xstrtoull(p + 1, &end); + assert(*end == '\0'); + assert(flags_ull == (unsigned int)flags_ull); + + flags = flags_ull; + } + + fd = -1; + if (flags & PF_KHTREAD) { + fd = openat(dir_fd, "fd", O_RDONLY|O_DIRECTORY); + } + close(dir_fd); + return fd; +} + +static void test_readdir(int fd) +{ + DIR *d; + struct dirent *de; + + d = fdopendir(fd); + assert(d); + + de = xreaddir(d); + assert(streq(de->d_name, ".")); + assert(de->d_type == DT_DIR); + + de = xreaddir(d); + assert(streq(de->d_name, "..")); + assert(de->d_type == DT_DIR); + + de = xreaddir(d); + assert(!de); +} + +static inline int sys_statx(int dirfd, const char *pathname, int flags, + unsigned int mask, void *stx) +{ + return syscall(SYS_statx, dirfd, pathname, flags, mask, stx); +} + +static void test_lookup_fail(int fd, const char *pathname) +{ + char stx[256] __attribute__((aligned(8))); + int rv; + + rv = sys_statx(fd, pathname, AT_SYMLINK_NOFOLLOW, 0, (void *)stx); + assert(rv == -1 && errno == ENOENT); +} + +static void test_lookup(int fd) +{ + char buf[64]; + unsigned int u; + int i; + + for (i = INT_MIN; i < INT_MIN + 1024; i++) { + snprintf(buf, sizeof(buf), "%d", i); + test_lookup_fail(fd, buf); + } + for (i = -1024; i < 1024; i++) { + snprintf(buf, sizeof(buf), "%d", i); + test_lookup_fail(fd, buf); + } + for (u = INT_MAX - 1024; u < (unsigned int)INT_MAX + 1024; u++) { + snprintf(buf, sizeof(buf), "%u", u); + test_lookup_fail(fd, buf); + } + for (u = UINT_MAX - 1024; u != 0; u++) { + snprintf(buf, sizeof(buf), "%u", u); + test_lookup_fail(fd, buf); + } +} + +int main(void) +{ + unsigned int pid; + int fd; + + /* + * In theory this will loop indefinitely if kernel threads are exiled + * from /proc. + * + * Start with kthreadd. + */ + pid = 2; + while ((fd = kernel_thread_fd(pid)) == -1 && pid < 1024) { + pid++; + } + /* EACCES if run as non-root. */ + if (pid >= 1024) + return 1; + + test_readdir(fd); + test_lookup(fd); + + return 0; +} diff --git a/tools/testing/selftests/proc/proc-uptime.h b/tools/testing/selftests/proc/proc-uptime.h index 0e464b5..dc6a42b 100644 --- a/tools/testing/selftests/proc/proc-uptime.h +++ b/tools/testing/selftests/proc/proc-uptime.h @@ -20,21 +20,7 @@ #include <stdlib.h> #include <unistd.h> -static unsigned long long xstrtoull(const char *p, char **end) -{ - if (*p == '0') { - *end = (char *)p + 1; - return 0; - } else if ('1' <= *p && *p <= '9') { - unsigned long long val; - - errno = 0; - val = strtoull(p, end, 10); - assert(errno == 0); - return val; - } else - assert(0); -} +#include "proc.h" static void proc_uptime(int fd, uint64_t *uptime, uint64_t *idle) { diff --git a/tools/testing/selftests/proc/proc.h b/tools/testing/selftests/proc/proc.h new file mode 100644 index 0000000..4e17816 --- /dev/null +++ b/tools/testing/selftests/proc/proc.h @@ -0,0 +1,39 @@ +#pragma once +#undef NDEBUG +#include <assert.h> +#include <dirent.h> +#include <errno.h> +#include <stdbool.h> +#include <stdlib.h> +#include <string.h> + +static inline bool streq(const char *s1, const char *s2) +{ + return strcmp(s1, s2) == 0; +} + +static unsigned long long xstrtoull(const char *p, char **end) +{ + if (*p == '0') { + *end = (char *)p + 1; + return 0; + } else if ('1' <= *p && *p <= '9') { + unsigned long long val; + + errno = 0; + val = strtoull(p, end, 10); + assert(errno == 0); + return val; + } else + assert(0); +} + +static struct dirent *xreaddir(DIR *d) +{ + struct dirent *de; + + errno = 0; + de = readdir(d); + assert(de || errno == 0); + return de; +} diff --git a/tools/testing/selftests/proc/read.c b/tools/testing/selftests/proc/read.c index 1e73c22..563e752 100644 --- a/tools/testing/selftests/proc/read.c +++ b/tools/testing/selftests/proc/read.c @@ -31,22 +31,7 @@ #include <fcntl.h> #include <unistd.h> -static inline bool streq(const char *s1, const char *s2) -{ - return strcmp(s1, s2) == 0; -} - -static struct dirent *xreaddir(DIR *d) -{ - struct dirent *de; - - errno = 0; - de = readdir(d); - if (!de && errno != 0) { - exit(1); - } - return de; -} +#include "proc.h" static void f_reg(DIR *d, const char *filename) { diff --git a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh new file mode 100755 index 0000000..98f650c --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh @@ -0,0 +1,56 @@ +#!/bin/sh +# +# Invoke a text editor on all console.log files for all runs with diagnostics, +# that is, on all such files having a console.log.diags counterpart. +# Note that both console.log.diags and console.log are passed to the +# editor (currently defaulting to "vi"), allowing the user to get an +# idea of what to search for in the console.log file. +# +# Usage: kvm-find-errors.sh directory +# +# The "directory" above should end with the date/time directory, for example, +# "tools/testing/selftests/rcutorture/res/2018.02.25-14:27:27". + +rundir="${1}" +if test -z "$rundir" -o ! -d "$rundir" +then + echo Usage: $0 directory +fi +editor=${EDITOR-vi} + +# Find builds with errors +files= +for i in ${rundir}/*/Make.out +do + if egrep -q "error:|warning:" < $i + then + egrep "error:|warning:" < $i > $i.diags + files="$files $i.diags $i" + fi +done +if test -n "$files" +then + $editor $files +else + echo No build errors. +fi +if grep -q -e "--buildonly" < ${rundir}/log +then + echo Build-only run, no console logs to check. +fi + +# Find console logs with errors +files= +for i in ${rundir}/*/console.log +do + if test -r $i.diags + then + files="$files $i.diags $i" + fi +done +if test -n "$files" +then + $editor $files +else + echo No errors in console logs. +fi diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh index c2e1bb6..477ecb1 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh @@ -34,11 +34,15 @@ fi configfile=`echo $i | sed -e 's/^.*\///'` ngps=`grep ver: $i/console.log 2> /dev/null | tail -1 | sed -e 's/^.* ver: //' -e 's/ .*$//'` +stopstate="`grep 'End-test grace-period state: g' $i/console.log 2> /dev/null | + tail -1 | sed -e 's/^\[[ 0-9.]*] //' | + awk '{ print \"[\" $1 \" \" $5 \" \" $6 \" \" $7 \"]\"; }' | + tr -d '\012\015'`" if test -z "$ngps" then - echo "$configfile -------" + echo "$configfile ------- " $stopstate else - title="$configfile ------- $ngps grace periods" + title="$configfile ------- $ngps GPs" dur=`sed -e 's/^.* rcutorture.shutdown_secs=//' -e 's/ .*$//' < $i/qemu-cmd 2> /dev/null` if test -z "$dur" then @@ -46,9 +50,9 @@ else else ngpsps=`awk -v ngps=$ngps -v dur=$dur ' BEGIN { print ngps / dur }' < /dev/null` - title="$title ($ngpsps per second)" + title="$title ($ngpsps/s)" fi - echo $title + echo $title $stopstate nclosecalls=`grep --binary-files=text 'torture: Reader Batch' $i/console.log | tail -1 | awk '{for (i=NF-8;i<=NF;i++) sum+=$i; } END {print sum}'` if test -z "$nclosecalls" then diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh index f7e988f..c27e978 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh @@ -48,10 +48,6 @@ do cat $i/Make.oldconfig.err fi parse-build.sh $i/Make.out $configfile - if test "$TORTURE_SUITE" != rcuperf - then - parse-torture.sh $i/console.log $configfile - fi parse-console.sh $i/console.log $configfile if test -r $i/Warnings then diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh index 5f8fbb0..c5b0f94 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -267,5 +267,4 @@ then echo Unknown PID, cannot kill qemu command fi -parse-torture.sh $resdir/console.log $title parse-console.sh $resdir/console.log $title diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh index 08aa7d5..1729343 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-console.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh @@ -24,57 +24,146 @@ # # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com> +T=${TMPDIR-/tmp}/parse-console.sh.$$ file="$1" title="$2" +trap 'rm -f $T.seq $T.diags' 0 + . functions.sh +# Check for presence and readability of console output file +if test -f "$file" -a -r "$file" +then + : +else + echo $title unreadable console output file: $file + exit 1 +fi if grep -Pq '\x00' < $file then print_warning Console output contains nul bytes, old qemu still running? fi -egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $1.diags -if test -s $1.diags +cat /dev/null > $file.diags + +# Check for proper termination, except that rcuperf runs don't indicate this. +if test "$TORTURE_SUITE" != rcuperf then - print_warning Assertion failure in $file $title - # cat $1.diags + # check for abject failure + + if grep -q FAILURE $file || grep -q -e '-torture.*!!!' $file + then + nerrs=`grep --binary-files=text '!!!' $file | + tail -1 | + awk ' + { + for (i=NF-8;i<=NF;i++) + sum+=$i; + } + END { print sum }'` + print_bug $title FAILURE, $nerrs instances + exit + fi + + grep --binary-files=text 'torture:.*ver:' $file | + egrep --binary-files=text -v '\(null\)|rtc: 000000000* ' | + sed -e 's/^(initramfs)[^]]*] //' -e 's/^\[[^]]*] //' | + awk ' + BEGIN { + ver = 0; + badseq = 0; + } + + { + if (!badseq && ($5 + 0 != $5 || $5 <= ver)) { + badseqno1 = ver; + badseqno2 = $5; + badseqnr = NR; + badseq = 1; + } + ver = $5 + } + + END { + if (badseq) { + if (badseqno1 == badseqno2 && badseqno2 == ver) + print "GP HANG at " ver " torture stat " badseqnr; + else + print "BAD SEQ " badseqno1 ":" badseqno2 " last:" ver " version " badseqnr; + } + }' > $T.seq + + if grep -q SUCCESS $file + then + if test -s $T.seq + then + print_warning $title `cat $T.seq` + echo " " $file + exit 2 + fi + else + if grep -q "_HOTPLUG:" $file + then + print_warning HOTPLUG FAILURES $title `cat $T.seq` + echo " " $file + exit 3 + fi + echo $title no success message, `grep --binary-files=text 'ver:' $file | wc -l` successful version messages + if test -s $T.seq + then + print_warning $title `cat $T.seq` + fi + exit 2 + fi +fi | tee -a $file.diags + +egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for' < $file | +grep -v 'ODEBUG: ' | +grep -v 'Warning: unable to open an initial console' > $T.diags +if test -s $T.diags +then + print_warning "Assertion failure in $file $title" + # cat $T.diags summary="" - n_badness=`grep -c Badness $1` + n_badness=`grep -c Badness $file` if test "$n_badness" -ne 0 then summary="$summary Badness: $n_badness" fi - n_warn=`grep -v 'Warning: unable to open an initial console' $1 | egrep -c 'WARNING:|Warn'` + n_warn=`grep -v 'Warning: unable to open an initial console' $file | egrep -c 'WARNING:|Warn'` if test "$n_warn" -ne 0 then summary="$summary Warnings: $n_warn" fi - n_bugs=`egrep -c 'BUG|Oops:' $1` + n_bugs=`egrep -c 'BUG|Oops:' $file` if test "$n_bugs" -ne 0 then summary="$summary Bugs: $n_bugs" fi - n_calltrace=`grep -c 'Call Trace:' $1` + n_calltrace=`grep -c 'Call Trace:' $file` if test "$n_calltrace" -ne 0 then summary="$summary Call Traces: $n_calltrace" fi - n_lockdep=`grep -c =========== $1` + n_lockdep=`grep -c =========== $file` if test "$n_badness" -ne 0 then summary="$summary lockdep: $n_badness" fi - n_stalls=`egrep -c 'detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state' $1` + n_stalls=`egrep -c 'detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state' $file` if test "$n_stalls" -ne 0 then summary="$summary Stalls: $n_stalls" fi - n_starves=`grep -c 'rcu_.*kthread starved for' $1` + n_starves=`grep -c 'rcu_.*kthread starved for' $file` if test "$n_starves" -ne 0 then summary="$summary Starves: $n_starves" fi print_warning Summary: $summary -else - rm $1.diags + cat $T.diags >> $file.diags +fi +if ! test -s $file.diags +then + rm -f $file.diags fi diff --git a/tools/testing/selftests/rcutorture/bin/parse-torture.sh b/tools/testing/selftests/rcutorture/bin/parse-torture.sh deleted file mode 100755 index 5987e50..0000000 --- a/tools/testing/selftests/rcutorture/bin/parse-torture.sh +++ /dev/null @@ -1,105 +0,0 @@ -#!/bin/bash -# -# Check the console output from a torture run for goodness. -# The "file" is a pathname on the local system, and "title" is -# a text string for error-message purposes. -# -# The file must contain torture output, but can be interspersed -# with other dmesg text, as in console-log output. -# -# Usage: parse-torture.sh file title -# -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License as published by -# the Free Software Foundation; either version 2 of the License, or -# (at your option) any later version. -# -# This program is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU General Public License for more details. -# -# You should have received a copy of the GNU General Public License -# along with this program; if not, you can access it online at -# http://www.gnu.org/licenses/gpl-2.0.html. -# -# Copyright (C) IBM Corporation, 2011 -# -# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com> - -T=${TMPDIR-/tmp}/parse-torture.sh.$$ -file="$1" -title="$2" - -trap 'rm -f $T.seq' 0 - -. functions.sh - -# check for presence of torture output file. - -if test -f "$file" -a -r "$file" -then - : -else - echo $title unreadable torture output file: $file - exit 1 -fi - -# check for abject failure - -if grep -q FAILURE $file || grep -q -e '-torture.*!!!' $file -then - nerrs=`grep --binary-files=text '!!!' $file | tail -1 | awk '{for (i=NF-8;i<=NF;i++) sum+=$i; } END {print sum}'` - print_bug $title FAILURE, $nerrs instances - echo " " $url - exit -fi - -grep --binary-files=text 'torture:.*ver:' $file | egrep --binary-files=text -v '\(null\)|rtc: 000000000* ' | sed -e 's/^(initramfs)[^]]*] //' -e 's/^\[[^]]*] //' | -awk ' -BEGIN { - ver = 0; - badseq = 0; - } - - { - if (!badseq && ($5 + 0 != $5 || $5 <= ver)) { - badseqno1 = ver; - badseqno2 = $5; - badseqnr = NR; - badseq = 1; - } - ver = $5 - } - -END { - if (badseq) { - if (badseqno1 == badseqno2 && badseqno2 == ver) - print "GP HANG at " ver " torture stat " badseqnr; - else - print "BAD SEQ " badseqno1 ":" badseqno2 " last:" ver " version " badseqnr; - } - }' > $T.seq - -if grep -q SUCCESS $file -then - if test -s $T.seq - then - print_warning $title $title `cat $T.seq` - echo " " $file - exit 2 - fi -else - if grep -q "_HOTPLUG:" $file - then - print_warning HOTPLUG FAILURES $title `cat $T.seq` - echo " " $file - exit 3 - fi - echo $title no success message, `grep --binary-files=text 'ver:' $file | wc -l` successful version messages - if test -s $T.seq - then - print_warning $title `cat $T.seq` - fi - exit 2 -fi diff --git a/tools/testing/selftests/rseq/.gitignore b/tools/testing/selftests/rseq/.gitignore new file mode 100644 index 0000000..cc610da --- /dev/null +++ b/tools/testing/selftests/rseq/.gitignore @@ -0,0 +1,6 @@ +basic_percpu_ops_test +basic_test +basic_rseq_op_test +param_test +param_test_benchmark +param_test_compare_twice diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile new file mode 100644 index 0000000..c30c52e --- /dev/null +++ b/tools/testing/selftests/rseq/Makefile @@ -0,0 +1,30 @@ +# SPDX-License-Identifier: GPL-2.0+ OR MIT +CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -L./ -Wl,-rpath=./ +LDLIBS += -lpthread + +# Own dependencies because we only want to build against 1st prerequisite, but +# still track changes to header files and depend on shared object. +OVERRIDE_TARGETS = 1 + +TEST_GEN_PROGS = basic_test basic_percpu_ops_test param_test \ + param_test_benchmark param_test_compare_twice + +TEST_GEN_PROGS_EXTENDED = librseq.so + +TEST_PROGS = run_param_test.sh + +include ../lib.mk + +$(OUTPUT)/librseq.so: rseq.c rseq.h rseq-*.h + $(CC) $(CFLAGS) -shared -fPIC $< $(LDLIBS) -o $@ + +$(OUTPUT)/%: %.c $(TEST_GEN_PROGS_EXTENDED) rseq.h rseq-*.h + $(CC) $(CFLAGS) $< $(LDLIBS) -lrseq -o $@ + +$(OUTPUT)/param_test_benchmark: param_test.c $(TEST_GEN_PROGS_EXTENDED) \ + rseq.h rseq-*.h + $(CC) $(CFLAGS) -DBENCHMARK $< $(LDLIBS) -lrseq -o $@ + +$(OUTPUT)/param_test_compare_twice: param_test.c $(TEST_GEN_PROGS_EXTENDED) \ + rseq.h rseq-*.h + $(CC) $(CFLAGS) -DRSEQ_COMPARE_TWICE $< $(LDLIBS) -lrseq -o $@ diff --git a/tools/testing/selftests/rseq/basic_percpu_ops_test.c b/tools/testing/selftests/rseq/basic_percpu_ops_test.c new file mode 100644 index 0000000..eb3f6db --- /dev/null +++ b/tools/testing/selftests/rseq/basic_percpu_ops_test.c @@ -0,0 +1,312 @@ +// SPDX-License-Identifier: LGPL-2.1 +#define _GNU_SOURCE +#include <assert.h> +#include <pthread.h> +#include <sched.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <stddef.h> + +#include "rseq.h" + +#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) + +struct percpu_lock_entry { + intptr_t v; +} __attribute__((aligned(128))); + +struct percpu_lock { + struct percpu_lock_entry c[CPU_SETSIZE]; +}; + +struct test_data_entry { + intptr_t count; +} __attribute__((aligned(128))); + +struct spinlock_test_data { + struct percpu_lock lock; + struct test_data_entry c[CPU_SETSIZE]; + int reps; +}; + +struct percpu_list_node { + intptr_t data; + struct percpu_list_node *next; +}; + +struct percpu_list_entry { + struct percpu_list_node *head; +} __attribute__((aligned(128))); + +struct percpu_list { + struct percpu_list_entry c[CPU_SETSIZE]; +}; + +/* A simple percpu spinlock. Returns the cpu lock was acquired on. */ +int rseq_this_cpu_lock(struct percpu_lock *lock) +{ + int cpu; + + for (;;) { + int ret; + + cpu = rseq_cpu_start(); + ret = rseq_cmpeqv_storev(&lock->c[cpu].v, + 0, 1, cpu); + if (rseq_likely(!ret)) + break; + /* Retry if comparison fails or rseq aborts. */ + } + /* + * Acquire semantic when taking lock after control dependency. + * Matches rseq_smp_store_release(). + */ + rseq_smp_acquire__after_ctrl_dep(); + return cpu; +} + +void rseq_percpu_unlock(struct percpu_lock *lock, int cpu) +{ + assert(lock->c[cpu].v == 1); + /* + * Release lock, with release semantic. Matches + * rseq_smp_acquire__after_ctrl_dep(). + */ + rseq_smp_store_release(&lock->c[cpu].v, 0); +} + +void *test_percpu_spinlock_thread(void *arg) +{ + struct spinlock_test_data *data = arg; + int i, cpu; + + if (rseq_register_current_thread()) { + fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n", + errno, strerror(errno)); + abort(); + } + for (i = 0; i < data->reps; i++) { + cpu = rseq_this_cpu_lock(&data->lock); + data->c[cpu].count++; + rseq_percpu_unlock(&data->lock, cpu); + } + if (rseq_unregister_current_thread()) { + fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n", + errno, strerror(errno)); + abort(); + } + + return NULL; +} + +/* + * A simple test which implements a sharded counter using a per-cpu + * lock. Obviously real applications might prefer to simply use a + * per-cpu increment; however, this is reasonable for a test and the + * lock can be extended to synchronize more complicated operations. + */ +void test_percpu_spinlock(void) +{ + const int num_threads = 200; + int i; + uint64_t sum; + pthread_t test_threads[num_threads]; + struct spinlock_test_data data; + + memset(&data, 0, sizeof(data)); + data.reps = 5000; + + for (i = 0; i < num_threads; i++) + pthread_create(&test_threads[i], NULL, + test_percpu_spinlock_thread, &data); + + for (i = 0; i < num_threads; i++) + pthread_join(test_threads[i], NULL); + + sum = 0; + for (i = 0; i < CPU_SETSIZE; i++) + sum += data.c[i].count; + + assert(sum == (uint64_t)data.reps * num_threads); +} + +void this_cpu_list_push(struct percpu_list *list, + struct percpu_list_node *node, + int *_cpu) +{ + int cpu; + + for (;;) { + intptr_t *targetptr, newval, expect; + int ret; + + cpu = rseq_cpu_start(); + /* Load list->c[cpu].head with single-copy atomicity. */ + expect = (intptr_t)RSEQ_READ_ONCE(list->c[cpu].head); + newval = (intptr_t)node; + targetptr = (intptr_t *)&list->c[cpu].head; + node->next = (struct percpu_list_node *)expect; + ret = rseq_cmpeqv_storev(targetptr, expect, newval, cpu); + if (rseq_likely(!ret)) + break; + /* Retry if comparison fails or rseq aborts. */ + } + if (_cpu) + *_cpu = cpu; +} + +/* + * Unlike a traditional lock-less linked list; the availability of a + * rseq primitive allows us to implement pop without concerns over + * ABA-type races. + */ +struct percpu_list_node *this_cpu_list_pop(struct percpu_list *list, + int *_cpu) +{ + for (;;) { + struct percpu_list_node *head; + intptr_t *targetptr, expectnot, *load; + off_t offset; + int ret, cpu; + + cpu = rseq_cpu_start(); + targetptr = (intptr_t *)&list->c[cpu].head; + expectnot = (intptr_t)NULL; + offset = offsetof(struct percpu_list_node, next); + load = (intptr_t *)&head; + ret = rseq_cmpnev_storeoffp_load(targetptr, expectnot, + offset, load, cpu); + if (rseq_likely(!ret)) { + if (_cpu) + *_cpu = cpu; + return head; + } + if (ret > 0) + return NULL; + /* Retry if rseq aborts. */ + } +} + +/* + * __percpu_list_pop is not safe against concurrent accesses. Should + * only be used on lists that are not concurrently modified. + */ +struct percpu_list_node *__percpu_list_pop(struct percpu_list *list, int cpu) +{ + struct percpu_list_node *node; + + node = list->c[cpu].head; + if (!node) + return NULL; + list->c[cpu].head = node->next; + return node; +} + +void *test_percpu_list_thread(void *arg) +{ + int i; + struct percpu_list *list = (struct percpu_list *)arg; + + if (rseq_register_current_thread()) { + fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n", + errno, strerror(errno)); + abort(); + } + + for (i = 0; i < 100000; i++) { + struct percpu_list_node *node; + + node = this_cpu_list_pop(list, NULL); + sched_yield(); /* encourage shuffling */ + if (node) + this_cpu_list_push(list, node, NULL); + } + + if (rseq_unregister_current_thread()) { + fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n", + errno, strerror(errno)); + abort(); + } + + return NULL; +} + +/* Simultaneous modification to a per-cpu linked list from many threads. */ +void test_percpu_list(void) +{ + int i, j; + uint64_t sum = 0, expected_sum = 0; + struct percpu_list list; + pthread_t test_threads[200]; + cpu_set_t allowed_cpus; + + memset(&list, 0, sizeof(list)); + + /* Generate list entries for every usable cpu. */ + sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus); + for (i = 0; i < CPU_SETSIZE; i++) { + if (!CPU_ISSET(i, &allowed_cpus)) + continue; + for (j = 1; j <= 100; j++) { + struct percpu_list_node *node; + + expected_sum += j; + + node = malloc(sizeof(*node)); + assert(node); + node->data = j; + node->next = list.c[i].head; + list.c[i].head = node; + } + } + + for (i = 0; i < 200; i++) + pthread_create(&test_threads[i], NULL, + test_percpu_list_thread, &list); + + for (i = 0; i < 200; i++) + pthread_join(test_threads[i], NULL); + + for (i = 0; i < CPU_SETSIZE; i++) { + struct percpu_list_node *node; + + if (!CPU_ISSET(i, &allowed_cpus)) + continue; + + while ((node = __percpu_list_pop(&list, i))) { + sum += node->data; + free(node); + } + } + + /* + * All entries should now be accounted for (unless some external + * actor is interfering with our allowed affinity while this + * test is running). + */ + assert(sum == expected_sum); +} + +int main(int argc, char **argv) +{ + if (rseq_register_current_thread()) { + fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n", + errno, strerror(errno)); + goto error; + } + printf("spinlock\n"); + test_percpu_spinlock(); + printf("percpu_list\n"); + test_percpu_list(); + if (rseq_unregister_current_thread()) { + fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n", + errno, strerror(errno)); + goto error; + } + return 0; + +error: + return -1; +} diff --git a/tools/testing/selftests/rseq/basic_test.c b/tools/testing/selftests/rseq/basic_test.c new file mode 100644 index 0000000..d8efbfb --- /dev/null +++ b/tools/testing/selftests/rseq/basic_test.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: LGPL-2.1 +/* + * Basic test coverage for critical regions and rseq_current_cpu(). + */ + +#define _GNU_SOURCE +#include <assert.h> +#include <sched.h> +#include <signal.h> +#include <stdio.h> +#include <string.h> +#include <sys/time.h> + +#include "rseq.h" + +void test_cpu_pointer(void) +{ + cpu_set_t affinity, test_affinity; + int i; + + sched_getaffinity(0, sizeof(affinity), &affinity); + CPU_ZERO(&test_affinity); + for (i = 0; i < CPU_SETSIZE; i++) { + if (CPU_ISSET(i, &affinity)) { + CPU_SET(i, &test_affinity); + sched_setaffinity(0, sizeof(test_affinity), + &test_affinity); + assert(sched_getcpu() == i); + assert(rseq_current_cpu() == i); + assert(rseq_current_cpu_raw() == i); + assert(rseq_cpu_start() == i); + CPU_CLR(i, &test_affinity); + } + } + sched_setaffinity(0, sizeof(affinity), &affinity); +} + +int main(int argc, char **argv) +{ + if (rseq_register_current_thread()) { + fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n", + errno, strerror(errno)); + goto init_thread_error; + } + printf("testing current cpu\n"); + test_cpu_pointer(); + if (rseq_unregister_current_thread()) { + fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n", + errno, strerror(errno)); + goto init_thread_error; + } + return 0; + +init_thread_error: + return -1; +} diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c new file mode 100644 index 0000000..6a9f602 --- /dev/null +++ b/tools/testing/selftests/rseq/param_test.c @@ -0,0 +1,1260 @@ +// SPDX-License-Identifier: LGPL-2.1 +#define _GNU_SOURCE +#include <assert.h> +#include <pthread.h> +#include <sched.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <syscall.h> +#include <unistd.h> +#include <poll.h> +#include <sys/types.h> +#include <signal.h> +#include <errno.h> +#include <stddef.h> + +static inline pid_t gettid(void) +{ + return syscall(__NR_gettid); +} + +#define NR_INJECT 9 +static int loop_cnt[NR_INJECT + 1]; + +static int loop_cnt_1 asm("asm_loop_cnt_1") __attribute__((used)); +static int loop_cnt_2 asm("asm_loop_cnt_2") __attribute__((used)); +static int loop_cnt_3 asm("asm_loop_cnt_3") __attribute__((used)); +static int loop_cnt_4 asm("asm_loop_cnt_4") __attribute__((used)); +static int loop_cnt_5 asm("asm_loop_cnt_5") __attribute__((used)); +static int loop_cnt_6 asm("asm_loop_cnt_6") __attribute__((used)); + +static int opt_modulo, verbose; + +static int opt_yield, opt_signal, opt_sleep, + opt_disable_rseq, opt_threads = 200, + opt_disable_mod = 0, opt_test = 's', opt_mb = 0; + +#ifndef RSEQ_SKIP_FASTPATH +static long long opt_reps = 5000; +#else +static long long opt_reps = 100; +#endif + +static __thread __attribute__((tls_model("initial-exec"))) +unsigned int signals_delivered; + +#ifndef BENCHMARK + +static __thread __attribute__((tls_model("initial-exec"), unused)) +unsigned int yield_mod_cnt, nr_abort; + +#define printf_verbose(fmt, ...) \ + do { \ + if (verbose) \ + printf(fmt, ## __VA_ARGS__); \ + } while (0) + +#if defined(__x86_64__) || defined(__i386__) + +#define INJECT_ASM_REG "eax" + +#define RSEQ_INJECT_CLOBBER \ + , INJECT_ASM_REG + +#ifdef __i386__ + +#define RSEQ_INJECT_ASM(n) \ + "mov asm_loop_cnt_" #n ", %%" INJECT_ASM_REG "\n\t" \ + "test %%" INJECT_ASM_REG ",%%" INJECT_ASM_REG "\n\t" \ + "jz 333f\n\t" \ + "222:\n\t" \ + "dec %%" INJECT_ASM_REG "\n\t" \ + "jnz 222b\n\t" \ + "333:\n\t" + +#elif defined(__x86_64__) + +#define RSEQ_INJECT_ASM(n) \ + "lea asm_loop_cnt_" #n "(%%rip), %%" INJECT_ASM_REG "\n\t" \ + "mov (%%" INJECT_ASM_REG "), %%" INJECT_ASM_REG "\n\t" \ + "test %%" INJECT_ASM_REG ",%%" INJECT_ASM_REG "\n\t" \ + "jz 333f\n\t" \ + "222:\n\t" \ + "dec %%" INJECT_ASM_REG "\n\t" \ + "jnz 222b\n\t" \ + "333:\n\t" + +#else +#error "Unsupported architecture" +#endif + +#elif defined(__ARMEL__) + +#define RSEQ_INJECT_INPUT \ + , [loop_cnt_1]"m"(loop_cnt[1]) \ + , [loop_cnt_2]"m"(loop_cnt[2]) \ + , [loop_cnt_3]"m"(loop_cnt[3]) \ + , [loop_cnt_4]"m"(loop_cnt[4]) \ + , [loop_cnt_5]"m"(loop_cnt[5]) \ + , [loop_cnt_6]"m"(loop_cnt[6]) + +#define INJECT_ASM_REG "r4" + +#define RSEQ_INJECT_CLOBBER \ + , INJECT_ASM_REG + +#define RSEQ_INJECT_ASM(n) \ + "ldr " INJECT_ASM_REG ", %[loop_cnt_" #n "]\n\t" \ + "cmp " INJECT_ASM_REG ", #0\n\t" \ + "beq 333f\n\t" \ + "222:\n\t" \ + "subs " INJECT_ASM_REG ", #1\n\t" \ + "bne 222b\n\t" \ + "333:\n\t" + +#elif __PPC__ + +#define RSEQ_INJECT_INPUT \ + , [loop_cnt_1]"m"(loop_cnt[1]) \ + , [loop_cnt_2]"m"(loop_cnt[2]) \ + , [loop_cnt_3]"m"(loop_cnt[3]) \ + , [loop_cnt_4]"m"(loop_cnt[4]) \ + , [loop_cnt_5]"m"(loop_cnt[5]) \ + , [loop_cnt_6]"m"(loop_cnt[6]) + +#define INJECT_ASM_REG "r18" + +#define RSEQ_INJECT_CLOBBER \ + , INJECT_ASM_REG + +#define RSEQ_INJECT_ASM(n) \ + "lwz %%" INJECT_ASM_REG ", %[loop_cnt_" #n "]\n\t" \ + "cmpwi %%" INJECT_ASM_REG ", 0\n\t" \ + "beq 333f\n\t" \ + "222:\n\t" \ + "subic. %%" INJECT_ASM_REG ", %%" INJECT_ASM_REG ", 1\n\t" \ + "bne 222b\n\t" \ + "333:\n\t" +#else +#error unsupported target +#endif + +#define RSEQ_INJECT_FAILED \ + nr_abort++; + +#define RSEQ_INJECT_C(n) \ +{ \ + int loc_i, loc_nr_loops = loop_cnt[n]; \ + \ + for (loc_i = 0; loc_i < loc_nr_loops; loc_i++) { \ + rseq_barrier(); \ + } \ + if (loc_nr_loops == -1 && opt_modulo) { \ + if (yield_mod_cnt == opt_modulo - 1) { \ + if (opt_sleep > 0) \ + poll(NULL, 0, opt_sleep); \ + if (opt_yield) \ + sched_yield(); \ + if (opt_signal) \ + raise(SIGUSR1); \ + yield_mod_cnt = 0; \ + } else { \ + yield_mod_cnt++; \ + } \ + } \ +} + +#else + +#define printf_verbose(fmt, ...) + +#endif /* BENCHMARK */ + +#include "rseq.h" + +struct percpu_lock_entry { + intptr_t v; +} __attribute__((aligned(128))); + +struct percpu_lock { + struct percpu_lock_entry c[CPU_SETSIZE]; +}; + +struct test_data_entry { + intptr_t count; +} __attribute__((aligned(128))); + +struct spinlock_test_data { + struct percpu_lock lock; + struct test_data_entry c[CPU_SETSIZE]; +}; + +struct spinlock_thread_test_data { + struct spinlock_test_data *data; + long long reps; + int reg; +}; + +struct inc_test_data { + struct test_data_entry c[CPU_SETSIZE]; +}; + +struct inc_thread_test_data { + struct inc_test_data *data; + long long reps; + int reg; +}; + +struct percpu_list_node { + intptr_t data; + struct percpu_list_node *next; +}; + +struct percpu_list_entry { + struct percpu_list_node *head; +} __attribute__((aligned(128))); + +struct percpu_list { + struct percpu_list_entry c[CPU_SETSIZE]; +}; + +#define BUFFER_ITEM_PER_CPU 100 + +struct percpu_buffer_node { + intptr_t data; +}; + +struct percpu_buffer_entry { + intptr_t offset; + intptr_t buflen; + struct percpu_buffer_node **array; +} __attribute__((aligned(128))); + +struct percpu_buffer { + struct percpu_buffer_entry c[CPU_SETSIZE]; +}; + +#define MEMCPY_BUFFER_ITEM_PER_CPU 100 + +struct percpu_memcpy_buffer_node { + intptr_t data1; + uint64_t data2; +}; + +struct percpu_memcpy_buffer_entry { + intptr_t offset; + intptr_t buflen; + struct percpu_memcpy_buffer_node *array; +} __attribute__((aligned(128))); + +struct percpu_memcpy_buffer { + struct percpu_memcpy_buffer_entry c[CPU_SETSIZE]; +}; + +/* A simple percpu spinlock. Grabs lock on current cpu. */ +static int rseq_this_cpu_lock(struct percpu_lock *lock) +{ + int cpu; + + for (;;) { + int ret; + + cpu = rseq_cpu_start(); + ret = rseq_cmpeqv_storev(&lock->c[cpu].v, + 0, 1, cpu); + if (rseq_likely(!ret)) + break; + /* Retry if comparison fails or rseq aborts. */ + } + /* + * Acquire semantic when taking lock after control dependency. + * Matches rseq_smp_store_release(). + */ + rseq_smp_acquire__after_ctrl_dep(); + return cpu; +} + +static void rseq_percpu_unlock(struct percpu_lock *lock, int cpu) +{ + assert(lock->c[cpu].v == 1); + /* + * Release lock, with release semantic. Matches + * rseq_smp_acquire__after_ctrl_dep(). + */ + rseq_smp_store_release(&lock->c[cpu].v, 0); +} + +void *test_percpu_spinlock_thread(void *arg) +{ + struct spinlock_thread_test_data *thread_data = arg; + struct spinlock_test_data *data = thread_data->data; + long long i, reps; + + if (!opt_disable_rseq && thread_data->reg && + rseq_register_current_thread()) + abort(); + reps = thread_data->reps; + for (i = 0; i < reps; i++) { + int cpu = rseq_cpu_start(); + + cpu = rseq_this_cpu_lock(&data->lock); + data->c[cpu].count++; + rseq_percpu_unlock(&data->lock, cpu); +#ifndef BENCHMARK + if (i != 0 && !(i % (reps / 10))) + printf_verbose("tid %d: count %lld\n", (int) gettid(), i); +#endif + } + printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n", + (int) gettid(), nr_abort, signals_delivered); + if (!opt_disable_rseq && thread_data->reg && + rseq_unregister_current_thread()) + abort(); + return NULL; +} + +/* + * A simple test which implements a sharded counter using a per-cpu + * lock. Obviously real applications might prefer to simply use a + * per-cpu increment; however, this is reasonable for a test and the + * lock can be extended to synchronize more complicated operations. + */ +void test_percpu_spinlock(void) +{ + const int num_threads = opt_threads; + int i, ret; + uint64_t sum; + pthread_t test_threads[num_threads]; + struct spinlock_test_data data; + struct spinlock_thread_test_data thread_data[num_threads]; + + memset(&data, 0, sizeof(data)); + for (i = 0; i < num_threads; i++) { + thread_data[i].reps = opt_reps; + if (opt_disable_mod <= 0 || (i % opt_disable_mod)) + thread_data[i].reg = 1; + else + thread_data[i].reg = 0; + thread_data[i].data = &data; + ret = pthread_create(&test_threads[i], NULL, + test_percpu_spinlock_thread, + &thread_data[i]); + if (ret) { + errno = ret; + perror("pthread_create"); + abort(); + } + } + + for (i = 0; i < num_threads; i++) { + ret = pthread_join(test_threads[i], NULL); + if (ret) { + errno = ret; + perror("pthread_join"); + abort(); + } + } + + sum = 0; + for (i = 0; i < CPU_SETSIZE; i++) + sum += data.c[i].count; + + assert(sum == (uint64_t)opt_reps * num_threads); +} + +void *test_percpu_inc_thread(void *arg) +{ + struct inc_thread_test_data *thread_data = arg; + struct inc_test_data *data = thread_data->data; + long long i, reps; + + if (!opt_disable_rseq && thread_data->reg && + rseq_register_current_thread()) + abort(); + reps = thread_data->reps; + for (i = 0; i < reps; i++) { + int ret; + + do { + int cpu; + + cpu = rseq_cpu_start(); + ret = rseq_addv(&data->c[cpu].count, 1, cpu); + } while (rseq_unlikely(ret)); +#ifndef BENCHMARK + if (i != 0 && !(i % (reps / 10))) + printf_verbose("tid %d: count %lld\n", (int) gettid(), i); +#endif + } + printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n", + (int) gettid(), nr_abort, signals_delivered); + if (!opt_disable_rseq && thread_data->reg && + rseq_unregister_current_thread()) + abort(); + return NULL; +} + +void test_percpu_inc(void) +{ + const int num_threads = opt_threads; + int i, ret; + uint64_t sum; + pthread_t test_threads[num_threads]; + struct inc_test_data data; + struct inc_thread_test_data thread_data[num_threads]; + + memset(&data, 0, sizeof(data)); + for (i = 0; i < num_threads; i++) { + thread_data[i].reps = opt_reps; + if (opt_disable_mod <= 0 || (i % opt_disable_mod)) + thread_data[i].reg = 1; + else + thread_data[i].reg = 0; + thread_data[i].data = &data; + ret = pthread_create(&test_threads[i], NULL, + test_percpu_inc_thread, + &thread_data[i]); + if (ret) { + errno = ret; + perror("pthread_create"); + abort(); + } + } + + for (i = 0; i < num_threads; i++) { + ret = pthread_join(test_threads[i], NULL); + if (ret) { + errno = ret; + perror("pthread_join"); + abort(); + } + } + + sum = 0; + for (i = 0; i < CPU_SETSIZE; i++) + sum += data.c[i].count; + + assert(sum == (uint64_t)opt_reps * num_threads); +} + +void this_cpu_list_push(struct percpu_list *list, + struct percpu_list_node *node, + int *_cpu) +{ + int cpu; + + for (;;) { + intptr_t *targetptr, newval, expect; + int ret; + + cpu = rseq_cpu_start(); + /* Load list->c[cpu].head with single-copy atomicity. */ + expect = (intptr_t)RSEQ_READ_ONCE(list->c[cpu].head); + newval = (intptr_t)node; + targetptr = (intptr_t *)&list->c[cpu].head; + node->next = (struct percpu_list_node *)expect; + ret = rseq_cmpeqv_storev(targetptr, expect, newval, cpu); + if (rseq_likely(!ret)) + break; + /* Retry if comparison fails or rseq aborts. */ + } + if (_cpu) + *_cpu = cpu; +} + +/* + * Unlike a traditional lock-less linked list; the availability of a + * rseq primitive allows us to implement pop without concerns over + * ABA-type races. + */ +struct percpu_list_node *this_cpu_list_pop(struct percpu_list *list, + int *_cpu) +{ + struct percpu_list_node *node = NULL; + int cpu; + + for (;;) { + struct percpu_list_node *head; + intptr_t *targetptr, expectnot, *load; + off_t offset; + int ret; + + cpu = rseq_cpu_start(); + targetptr = (intptr_t *)&list->c[cpu].head; + expectnot = (intptr_t)NULL; + offset = offsetof(struct percpu_list_node, next); + load = (intptr_t *)&head; + ret = rseq_cmpnev_storeoffp_load(targetptr, expectnot, + offset, load, cpu); + if (rseq_likely(!ret)) { + node = head; + break; + } + if (ret > 0) + break; + /* Retry if rseq aborts. */ + } + if (_cpu) + *_cpu = cpu; + return node; +} + +/* + * __percpu_list_pop is not safe against concurrent accesses. Should + * only be used on lists that are not concurrently modified. + */ +struct percpu_list_node *__percpu_list_pop(struct percpu_list *list, int cpu) +{ + struct percpu_list_node *node; + + node = list->c[cpu].head; + if (!node) + return NULL; + list->c[cpu].head = node->next; + return node; +} + +void *test_percpu_list_thread(void *arg) +{ + long long i, reps; + struct percpu_list *list = (struct percpu_list *)arg; + + if (!opt_disable_rseq && rseq_register_current_thread()) + abort(); + + reps = opt_reps; + for (i = 0; i < reps; i++) { + struct percpu_list_node *node; + + node = this_cpu_list_pop(list, NULL); + if (opt_yield) + sched_yield(); /* encourage shuffling */ + if (node) + this_cpu_list_push(list, node, NULL); + } + + printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n", + (int) gettid(), nr_abort, signals_delivered); + if (!opt_disable_rseq && rseq_unregister_current_thread()) + abort(); + + return NULL; +} + +/* Simultaneous modification to a per-cpu linked list from many threads. */ +void test_percpu_list(void) +{ + const int num_threads = opt_threads; + int i, j, ret; + uint64_t sum = 0, expected_sum = 0; + struct percpu_list list; + pthread_t test_threads[num_threads]; + cpu_set_t allowed_cpus; + + memset(&list, 0, sizeof(list)); + + /* Generate list entries for every usable cpu. */ + sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus); + for (i = 0; i < CPU_SETSIZE; i++) { + if (!CPU_ISSET(i, &allowed_cpus)) + continue; + for (j = 1; j <= 100; j++) { + struct percpu_list_node *node; + + expected_sum += j; + + node = malloc(sizeof(*node)); + assert(node); + node->data = j; + node->next = list.c[i].head; + list.c[i].head = node; + } + } + + for (i = 0; i < num_threads; i++) { + ret = pthread_create(&test_threads[i], NULL, + test_percpu_list_thread, &list); + if (ret) { + errno = ret; + perror("pthread_create"); + abort(); + } + } + + for (i = 0; i < num_threads; i++) { + ret = pthread_join(test_threads[i], NULL); + if (ret) { + errno = ret; + perror("pthread_join"); + abort(); + } + } + + for (i = 0; i < CPU_SETSIZE; i++) { + struct percpu_list_node *node; + + if (!CPU_ISSET(i, &allowed_cpus)) + continue; + + while ((node = __percpu_list_pop(&list, i))) { + sum += node->data; + free(node); + } + } + + /* + * All entries should now be accounted for (unless some external + * actor is interfering with our allowed affinity while this + * test is running). + */ + assert(sum == expected_sum); +} + +bool this_cpu_buffer_push(struct percpu_buffer *buffer, + struct percpu_buffer_node *node, + int *_cpu) +{ + bool result = false; + int cpu; + + for (;;) { + intptr_t *targetptr_spec, newval_spec; + intptr_t *targetptr_final, newval_final; + intptr_t offset; + int ret; + + cpu = rseq_cpu_start(); + offset = RSEQ_READ_ONCE(buffer->c[cpu].offset); + if (offset == buffer->c[cpu].buflen) + break; + newval_spec = (intptr_t)node; + targetptr_spec = (intptr_t *)&buffer->c[cpu].array[offset]; + newval_final = offset + 1; + targetptr_final = &buffer->c[cpu].offset; + if (opt_mb) + ret = rseq_cmpeqv_trystorev_storev_release( + targetptr_final, offset, targetptr_spec, + newval_spec, newval_final, cpu); + else + ret = rseq_cmpeqv_trystorev_storev(targetptr_final, + offset, targetptr_spec, newval_spec, + newval_final, cpu); + if (rseq_likely(!ret)) { + result = true; + break; + } + /* Retry if comparison fails or rseq aborts. */ + } + if (_cpu) + *_cpu = cpu; + return result; +} + +struct percpu_buffer_node *this_cpu_buffer_pop(struct percpu_buffer *buffer, + int *_cpu) +{ + struct percpu_buffer_node *head; + int cpu; + + for (;;) { + intptr_t *targetptr, newval; + intptr_t offset; + int ret; + + cpu = rseq_cpu_start(); + /* Load offset with single-copy atomicity. */ + offset = RSEQ_READ_ONCE(buffer->c[cpu].offset); + if (offset == 0) { + head = NULL; + break; + } + head = RSEQ_READ_ONCE(buffer->c[cpu].array[offset - 1]); + newval = offset - 1; + targetptr = (intptr_t *)&buffer->c[cpu].offset; + ret = rseq_cmpeqv_cmpeqv_storev(targetptr, offset, + (intptr_t *)&buffer->c[cpu].array[offset - 1], + (intptr_t)head, newval, cpu); + if (rseq_likely(!ret)) + break; + /* Retry if comparison fails or rseq aborts. */ + } + if (_cpu) + *_cpu = cpu; + return head; +} + +/* + * __percpu_buffer_pop is not safe against concurrent accesses. Should + * only be used on buffers that are not concurrently modified. + */ +struct percpu_buffer_node *__percpu_buffer_pop(struct percpu_buffer *buffer, + int cpu) +{ + struct percpu_buffer_node *head; + intptr_t offset; + + offset = buffer->c[cpu].offset; + if (offset == 0) + return NULL; + head = buffer->c[cpu].array[offset - 1]; + buffer->c[cpu].offset = offset - 1; + return head; +} + +void *test_percpu_buffer_thread(void *arg) +{ + long long i, reps; + struct percpu_buffer *buffer = (struct percpu_buffer *)arg; + + if (!opt_disable_rseq && rseq_register_current_thread()) + abort(); + + reps = opt_reps; + for (i = 0; i < reps; i++) { + struct percpu_buffer_node *node; + + node = this_cpu_buffer_pop(buffer, NULL); + if (opt_yield) + sched_yield(); /* encourage shuffling */ + if (node) { + if (!this_cpu_buffer_push(buffer, node, NULL)) { + /* Should increase buffer size. */ + abort(); + } + } + } + + printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n", + (int) gettid(), nr_abort, signals_delivered); + if (!opt_disable_rseq && rseq_unregister_current_thread()) + abort(); + + return NULL; +} + +/* Simultaneous modification to a per-cpu buffer from many threads. */ +void test_percpu_buffer(void) +{ + const int num_threads = opt_threads; + int i, j, ret; + uint64_t sum = 0, expected_sum = 0; + struct percpu_buffer buffer; + pthread_t test_threads[num_threads]; + cpu_set_t allowed_cpus; + + memset(&buffer, 0, sizeof(buffer)); + + /* Generate list entries for every usable cpu. */ + sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus); + for (i = 0; i < CPU_SETSIZE; i++) { + if (!CPU_ISSET(i, &allowed_cpus)) + continue; + /* Worse-case is every item in same CPU. */ + buffer.c[i].array = + malloc(sizeof(*buffer.c[i].array) * CPU_SETSIZE * + BUFFER_ITEM_PER_CPU); + assert(buffer.c[i].array); + buffer.c[i].buflen = CPU_SETSIZE * BUFFER_ITEM_PER_CPU; + for (j = 1; j <= BUFFER_ITEM_PER_CPU; j++) { + struct percpu_buffer_node *node; + + expected_sum += j; + + /* + * We could theoretically put the word-sized + * "data" directly in the buffer. However, we + * want to model objects that would not fit + * within a single word, so allocate an object + * for each node. + */ + node = malloc(sizeof(*node)); + assert(node); + node->data = j; + buffer.c[i].array[j - 1] = node; + buffer.c[i].offset++; + } + } + + for (i = 0; i < num_threads; i++) { + ret = pthread_create(&test_threads[i], NULL, + test_percpu_buffer_thread, &buffer); + if (ret) { + errno = ret; + perror("pthread_create"); + abort(); + } + } + + for (i = 0; i < num_threads; i++) { + ret = pthread_join(test_threads[i], NULL); + if (ret) { + errno = ret; + perror("pthread_join"); + abort(); + } + } + + for (i = 0; i < CPU_SETSIZE; i++) { + struct percpu_buffer_node *node; + + if (!CPU_ISSET(i, &allowed_cpus)) + continue; + + while ((node = __percpu_buffer_pop(&buffer, i))) { + sum += node->data; + free(node); + } + free(buffer.c[i].array); + } + + /* + * All entries should now be accounted for (unless some external + * actor is interfering with our allowed affinity while this + * test is running). + */ + assert(sum == expected_sum); +} + +bool this_cpu_memcpy_buffer_push(struct percpu_memcpy_buffer *buffer, + struct percpu_memcpy_buffer_node item, + int *_cpu) +{ + bool result = false; + int cpu; + + for (;;) { + intptr_t *targetptr_final, newval_final, offset; + char *destptr, *srcptr; + size_t copylen; + int ret; + + cpu = rseq_cpu_start(); + /* Load offset with single-copy atomicity. */ + offset = RSEQ_READ_ONCE(buffer->c[cpu].offset); + if (offset == buffer->c[cpu].buflen) + break; + destptr = (char *)&buffer->c[cpu].array[offset]; + srcptr = (char *)&item; + /* copylen must be <= 4kB. */ + copylen = sizeof(item); + newval_final = offset + 1; + targetptr_final = &buffer->c[cpu].offset; + if (opt_mb) + ret = rseq_cmpeqv_trymemcpy_storev_release( + targetptr_final, offset, + destptr, srcptr, copylen, + newval_final, cpu); + else + ret = rseq_cmpeqv_trymemcpy_storev(targetptr_final, + offset, destptr, srcptr, copylen, + newval_final, cpu); + if (rseq_likely(!ret)) { + result = true; + break; + } + /* Retry if comparison fails or rseq aborts. */ + } + if (_cpu) + *_cpu = cpu; + return result; +} + +bool this_cpu_memcpy_buffer_pop(struct percpu_memcpy_buffer *buffer, + struct percpu_memcpy_buffer_node *item, + int *_cpu) +{ + bool result = false; + int cpu; + + for (;;) { + intptr_t *targetptr_final, newval_final, offset; + char *destptr, *srcptr; + size_t copylen; + int ret; + + cpu = rseq_cpu_start(); + /* Load offset with single-copy atomicity. */ + offset = RSEQ_READ_ONCE(buffer->c[cpu].offset); + if (offset == 0) + break; + destptr = (char *)item; + srcptr = (char *)&buffer->c[cpu].array[offset - 1]; + /* copylen must be <= 4kB. */ + copylen = sizeof(*item); + newval_final = offset - 1; + targetptr_final = &buffer->c[cpu].offset; + ret = rseq_cmpeqv_trymemcpy_storev(targetptr_final, + offset, destptr, srcptr, copylen, + newval_final, cpu); + if (rseq_likely(!ret)) { + result = true; + break; + } + /* Retry if comparison fails or rseq aborts. */ + } + if (_cpu) + *_cpu = cpu; + return result; +} + +/* + * __percpu_memcpy_buffer_pop is not safe against concurrent accesses. Should + * only be used on buffers that are not concurrently modified. + */ +bool __percpu_memcpy_buffer_pop(struct percpu_memcpy_buffer *buffer, + struct percpu_memcpy_buffer_node *item, + int cpu) +{ + intptr_t offset; + + offset = buffer->c[cpu].offset; + if (offset == 0) + return false; + memcpy(item, &buffer->c[cpu].array[offset - 1], sizeof(*item)); + buffer->c[cpu].offset = offset - 1; + return true; +} + +void *test_percpu_memcpy_buffer_thread(void *arg) +{ + long long i, reps; + struct percpu_memcpy_buffer *buffer = (struct percpu_memcpy_buffer *)arg; + + if (!opt_disable_rseq && rseq_register_current_thread()) + abort(); + + reps = opt_reps; + for (i = 0; i < reps; i++) { + struct percpu_memcpy_buffer_node item; + bool result; + + result = this_cpu_memcpy_buffer_pop(buffer, &item, NULL); + if (opt_yield) + sched_yield(); /* encourage shuffling */ + if (result) { + if (!this_cpu_memcpy_buffer_push(buffer, item, NULL)) { + /* Should increase buffer size. */ + abort(); + } + } + } + + printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n", + (int) gettid(), nr_abort, signals_delivered); + if (!opt_disable_rseq && rseq_unregister_current_thread()) + abort(); + + return NULL; +} + +/* Simultaneous modification to a per-cpu buffer from many threads. */ +void test_percpu_memcpy_buffer(void) +{ + const int num_threads = opt_threads; + int i, j, ret; + uint64_t sum = 0, expected_sum = 0; + struct percpu_memcpy_buffer buffer; + pthread_t test_threads[num_threads]; + cpu_set_t allowed_cpus; + + memset(&buffer, 0, sizeof(buffer)); + + /* Generate list entries for every usable cpu. */ + sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus); + for (i = 0; i < CPU_SETSIZE; i++) { + if (!CPU_ISSET(i, &allowed_cpus)) + continue; + /* Worse-case is every item in same CPU. */ + buffer.c[i].array = + malloc(sizeof(*buffer.c[i].array) * CPU_SETSIZE * + MEMCPY_BUFFER_ITEM_PER_CPU); + assert(buffer.c[i].array); + buffer.c[i].buflen = CPU_SETSIZE * MEMCPY_BUFFER_ITEM_PER_CPU; + for (j = 1; j <= MEMCPY_BUFFER_ITEM_PER_CPU; j++) { + expected_sum += 2 * j + 1; + + /* + * We could theoretically put the word-sized + * "data" directly in the buffer. However, we + * want to model objects that would not fit + * within a single word, so allocate an object + * for each node. + */ + buffer.c[i].array[j - 1].data1 = j; + buffer.c[i].array[j - 1].data2 = j + 1; + buffer.c[i].offset++; + } + } + + for (i = 0; i < num_threads; i++) { + ret = pthread_create(&test_threads[i], NULL, + test_percpu_memcpy_buffer_thread, + &buffer); + if (ret) { + errno = ret; + perror("pthread_create"); + abort(); + } + } + + for (i = 0; i < num_threads; i++) { + ret = pthread_join(test_threads[i], NULL); + if (ret) { + errno = ret; + perror("pthread_join"); + abort(); + } + } + + for (i = 0; i < CPU_SETSIZE; i++) { + struct percpu_memcpy_buffer_node item; + + if (!CPU_ISSET(i, &allowed_cpus)) + continue; + + while (__percpu_memcpy_buffer_pop(&buffer, &item, i)) { + sum += item.data1; + sum += item.data2; + } + free(buffer.c[i].array); + } + + /* + * All entries should now be accounted for (unless some external + * actor is interfering with our allowed affinity while this + * test is running). + */ + assert(sum == expected_sum); +} + +static void test_signal_interrupt_handler(int signo) +{ + signals_delivered++; +} + +static int set_signal_handler(void) +{ + int ret = 0; + struct sigaction sa; + sigset_t sigset; + + ret = sigemptyset(&sigset); + if (ret < 0) { + perror("sigemptyset"); + return ret; + } + + sa.sa_handler = test_signal_interrupt_handler; + sa.sa_mask = sigset; + sa.sa_flags = 0; + ret = sigaction(SIGUSR1, &sa, NULL); + if (ret < 0) { + perror("sigaction"); + return ret; + } + + printf_verbose("Signal handler set for SIGUSR1\n"); + + return ret; +} + +static void show_usage(int argc, char **argv) +{ + printf("Usage : %s <OPTIONS>\n", + argv[0]); + printf("OPTIONS:\n"); + printf(" [-1 loops] Number of loops for delay injection 1\n"); + printf(" [-2 loops] Number of loops for delay injection 2\n"); + printf(" [-3 loops] Number of loops for delay injection 3\n"); + printf(" [-4 loops] Number of loops for delay injection 4\n"); + printf(" [-5 loops] Number of loops for delay injection 5\n"); + printf(" [-6 loops] Number of loops for delay injection 6\n"); + printf(" [-7 loops] Number of loops for delay injection 7 (-1 to enable -m)\n"); + printf(" [-8 loops] Number of loops for delay injection 8 (-1 to enable -m)\n"); + printf(" [-9 loops] Number of loops for delay injection 9 (-1 to enable -m)\n"); + printf(" [-m N] Yield/sleep/kill every modulo N (default 0: disabled) (>= 0)\n"); + printf(" [-y] Yield\n"); + printf(" [-k] Kill thread with signal\n"); + printf(" [-s S] S: =0: disabled (default), >0: sleep time (ms)\n"); + printf(" [-t N] Number of threads (default 200)\n"); + printf(" [-r N] Number of repetitions per thread (default 5000)\n"); + printf(" [-d] Disable rseq system call (no initialization)\n"); + printf(" [-D M] Disable rseq for each M threads\n"); + printf(" [-T test] Choose test: (s)pinlock, (l)ist, (b)uffer, (m)emcpy, (i)ncrement\n"); + printf(" [-M] Push into buffer and memcpy buffer with memory barriers.\n"); + printf(" [-v] Verbose output.\n"); + printf(" [-h] Show this help.\n"); + printf("\n"); +} + +int main(int argc, char **argv) +{ + int i; + + for (i = 1; i < argc; i++) { + if (argv[i][0] != '-') + continue; + switch (argv[i][1]) { + case '1': + case '2': + case '3': + case '4': + case '5': + case '6': + case '7': + case '8': + case '9': + if (argc < i + 2) { + show_usage(argc, argv); + goto error; + } + loop_cnt[argv[i][1] - '0'] = atol(argv[i + 1]); + i++; + break; + case 'm': + if (argc < i + 2) { + show_usage(argc, argv); + goto error; + } + opt_modulo = atol(argv[i + 1]); + if (opt_modulo < 0) { + show_usage(argc, argv); + goto error; + } + i++; + break; + case 's': + if (argc < i + 2) { + show_usage(argc, argv); + goto error; + } + opt_sleep = atol(argv[i + 1]); + if (opt_sleep < 0) { + show_usage(argc, argv); + goto error; + } + i++; + break; + case 'y': + opt_yield = 1; + break; + case 'k': + opt_signal = 1; + break; + case 'd': + opt_disable_rseq = 1; + break; + case 'D': + if (argc < i + 2) { + show_usage(argc, argv); + goto error; + } + opt_disable_mod = atol(argv[i + 1]); + if (opt_disable_mod < 0) { + show_usage(argc, argv); + goto error; + } + i++; + break; + case 't': + if (argc < i + 2) { + show_usage(argc, argv); + goto error; + } + opt_threads = atol(argv[i + 1]); + if (opt_threads < 0) { + show_usage(argc, argv); + goto error; + } + i++; + break; + case 'r': + if (argc < i + 2) { + show_usage(argc, argv); + goto error; + } + opt_reps = atoll(argv[i + 1]); + if (opt_reps < 0) { + show_usage(argc, argv); + goto error; + } + i++; + break; + case 'h': + show_usage(argc, argv); + goto end; + case 'T': + if (argc < i + 2) { + show_usage(argc, argv); + goto error; + } + opt_test = *argv[i + 1]; + switch (opt_test) { + case 's': + case 'l': + case 'i': + case 'b': + case 'm': + break; + default: + show_usage(argc, argv); + goto error; + } + i++; + break; + case 'v': + verbose = 1; + break; + case 'M': + opt_mb = 1; + break; + default: + show_usage(argc, argv); + goto error; + } + } + + loop_cnt_1 = loop_cnt[1]; + loop_cnt_2 = loop_cnt[2]; + loop_cnt_3 = loop_cnt[3]; + loop_cnt_4 = loop_cnt[4]; + loop_cnt_5 = loop_cnt[5]; + loop_cnt_6 = loop_cnt[6]; + + if (set_signal_handler()) + goto error; + + if (!opt_disable_rseq && rseq_register_current_thread()) + goto error; + switch (opt_test) { + case 's': + printf_verbose("spinlock\n"); + test_percpu_spinlock(); + break; + case 'l': + printf_verbose("linked list\n"); + test_percpu_list(); + break; + case 'b': + printf_verbose("buffer\n"); + test_percpu_buffer(); + break; + case 'm': + printf_verbose("memcpy buffer\n"); + test_percpu_memcpy_buffer(); + break; + case 'i': + printf_verbose("counter increment\n"); + test_percpu_inc(); + break; + } + if (!opt_disable_rseq && rseq_unregister_current_thread()) + abort(); +end: + return 0; + +error: + return -1; +} diff --git a/tools/testing/selftests/rseq/rseq-arm.h b/tools/testing/selftests/rseq/rseq-arm.h new file mode 100644 index 0000000..3b055f9 --- /dev/null +++ b/tools/testing/selftests/rseq/rseq-arm.h @@ -0,0 +1,715 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * rseq-arm.h + * + * (C) Copyright 2016-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com> + */ + +#define RSEQ_SIG 0x53053053 + +#define rseq_smp_mb() __asm__ __volatile__ ("dmb" ::: "memory", "cc") +#define rseq_smp_rmb() __asm__ __volatile__ ("dmb" ::: "memory", "cc") +#define rseq_smp_wmb() __asm__ __volatile__ ("dmb" ::: "memory", "cc") + +#define rseq_smp_load_acquire(p) \ +__extension__ ({ \ + __typeof(*p) ____p1 = RSEQ_READ_ONCE(*p); \ + rseq_smp_mb(); \ + ____p1; \ +}) + +#define rseq_smp_acquire__after_ctrl_dep() rseq_smp_rmb() + +#define rseq_smp_store_release(p, v) \ +do { \ + rseq_smp_mb(); \ + RSEQ_WRITE_ONCE(*p, v); \ +} while (0) + +#ifdef RSEQ_SKIP_FASTPATH +#include "rseq-skip.h" +#else /* !RSEQ_SKIP_FASTPATH */ + +#define __RSEQ_ASM_DEFINE_TABLE(version, flags, start_ip, \ + post_commit_offset, abort_ip) \ + ".pushsection __rseq_table, \"aw\"\n\t" \ + ".balign 32\n\t" \ + ".word " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \ + ".word " __rseq_str(start_ip) ", 0x0, " __rseq_str(post_commit_offset) ", 0x0, " __rseq_str(abort_ip) ", 0x0\n\t" \ + ".popsection\n\t" + +#define RSEQ_ASM_DEFINE_TABLE(start_ip, post_commit_ip, abort_ip) \ + __RSEQ_ASM_DEFINE_TABLE(0x0, 0x0, start_ip, \ + (post_commit_ip - start_ip), abort_ip) + +#define RSEQ_ASM_STORE_RSEQ_CS(label, cs_label, rseq_cs) \ + RSEQ_INJECT_ASM(1) \ + "adr r0, " __rseq_str(cs_label) "\n\t" \ + "str r0, %[" __rseq_str(rseq_cs) "]\n\t" \ + __rseq_str(label) ":\n\t" + +#define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label) \ + RSEQ_INJECT_ASM(2) \ + "ldr r0, %[" __rseq_str(current_cpu_id) "]\n\t" \ + "cmp %[" __rseq_str(cpu_id) "], r0\n\t" \ + "bne " __rseq_str(label) "\n\t" + +#define __RSEQ_ASM_DEFINE_ABORT(table_label, label, teardown, \ + abort_label, version, flags, \ + start_ip, post_commit_offset, abort_ip) \ + __rseq_str(table_label) ":\n\t" \ + ".word " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \ + ".word " __rseq_str(start_ip) ", 0x0, " __rseq_str(post_commit_offset) ", 0x0, " __rseq_str(abort_ip) ", 0x0\n\t" \ + ".word " __rseq_str(RSEQ_SIG) "\n\t" \ + __rseq_str(label) ":\n\t" \ + teardown \ + "b %l[" __rseq_str(abort_label) "]\n\t" + +#define RSEQ_ASM_DEFINE_ABORT(table_label, label, teardown, abort_label, \ + start_ip, post_commit_ip, abort_ip) \ + __RSEQ_ASM_DEFINE_ABORT(table_label, label, teardown, \ + abort_label, 0x0, 0x0, start_ip, \ + (post_commit_ip - start_ip), abort_ip) + +#define RSEQ_ASM_DEFINE_CMPFAIL(label, teardown, cmpfail_label) \ + __rseq_str(label) ":\n\t" \ + teardown \ + "b %l[" __rseq_str(cmpfail_label) "]\n\t" + +#define rseq_workaround_gcc_asm_size_guess() __asm__ __volatile__("") + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + rseq_workaround_gcc_asm_size_guess(); + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + "ldr r0, %[v]\n\t" + "cmp %[expect], r0\n\t" + "bne %l[cmpfail]\n\t" + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) + "ldr r0, %[v]\n\t" + "cmp %[expect], r0\n\t" + "bne %l[error2]\n\t" +#endif + /* final store */ + "str %[newv], %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(5) + "b 5f\n\t" + RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f) + "5:\n\t" + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + [v] "m" (*v), + [expect] "r" (expect), + [newv] "r" (newv) + RSEQ_INJECT_INPUT + : "r0", "memory", "cc" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + rseq_workaround_gcc_asm_size_guess(); + return 0; +abort: + rseq_workaround_gcc_asm_size_guess(); + RSEQ_INJECT_FAILED + return -1; +cmpfail: + rseq_workaround_gcc_asm_size_guess(); + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __attribute__((always_inline)) +int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, + off_t voffp, intptr_t *load, int cpu) +{ + RSEQ_INJECT_C(9) + + rseq_workaround_gcc_asm_size_guess(); + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + "ldr r0, %[v]\n\t" + "cmp %[expectnot], r0\n\t" + "beq %l[cmpfail]\n\t" + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) + "ldr r0, %[v]\n\t" + "cmp %[expectnot], r0\n\t" + "beq %l[error2]\n\t" +#endif + "str r0, %[load]\n\t" + "add r0, %[voffp]\n\t" + "ldr r0, [r0]\n\t" + /* final store */ + "str r0, %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(5) + "b 5f\n\t" + RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f) + "5:\n\t" + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* final store input */ + [v] "m" (*v), + [expectnot] "r" (expectnot), + [voffp] "Ir" (voffp), + [load] "m" (*load) + RSEQ_INJECT_INPUT + : "r0", "memory", "cc" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + rseq_workaround_gcc_asm_size_guess(); + return 0; +abort: + rseq_workaround_gcc_asm_size_guess(); + RSEQ_INJECT_FAILED + return -1; +cmpfail: + rseq_workaround_gcc_asm_size_guess(); + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __attribute__((always_inline)) +int rseq_addv(intptr_t *v, intptr_t count, int cpu) +{ + RSEQ_INJECT_C(9) + + rseq_workaround_gcc_asm_size_guess(); + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) +#endif + "ldr r0, %[v]\n\t" + "add r0, %[count]\n\t" + /* final store */ + "str r0, %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(4) + "b 5f\n\t" + RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f) + "5:\n\t" + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + [v] "m" (*v), + [count] "Ir" (count) + RSEQ_INJECT_INPUT + : "r0", "memory", "cc" + RSEQ_INJECT_CLOBBER + : abort +#ifdef RSEQ_COMPARE_TWICE + , error1 +#endif + ); + rseq_workaround_gcc_asm_size_guess(); + return 0; +abort: + rseq_workaround_gcc_asm_size_guess(); + RSEQ_INJECT_FAILED + return -1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +#endif +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t newv2, + intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + rseq_workaround_gcc_asm_size_guess(); + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + "ldr r0, %[v]\n\t" + "cmp %[expect], r0\n\t" + "bne %l[cmpfail]\n\t" + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) + "ldr r0, %[v]\n\t" + "cmp %[expect], r0\n\t" + "bne %l[error2]\n\t" +#endif + /* try store */ + "str %[newv2], %[v2]\n\t" + RSEQ_INJECT_ASM(5) + /* final store */ + "str %[newv], %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(6) + "b 5f\n\t" + RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f) + "5:\n\t" + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* try store input */ + [v2] "m" (*v2), + [newv2] "r" (newv2), + /* final store input */ + [v] "m" (*v), + [expect] "r" (expect), + [newv] "r" (newv) + RSEQ_INJECT_INPUT + : "r0", "memory", "cc" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + rseq_workaround_gcc_asm_size_guess(); + return 0; +abort: + rseq_workaround_gcc_asm_size_guess(); + RSEQ_INJECT_FAILED + return -1; +cmpfail: + rseq_workaround_gcc_asm_size_guess(); + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t newv2, + intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + rseq_workaround_gcc_asm_size_guess(); + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + "ldr r0, %[v]\n\t" + "cmp %[expect], r0\n\t" + "bne %l[cmpfail]\n\t" + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) + "ldr r0, %[v]\n\t" + "cmp %[expect], r0\n\t" + "bne %l[error2]\n\t" +#endif + /* try store */ + "str %[newv2], %[v2]\n\t" + RSEQ_INJECT_ASM(5) + "dmb\n\t" /* full mb provides store-release */ + /* final store */ + "str %[newv], %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(6) + "b 5f\n\t" + RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f) + "5:\n\t" + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* try store input */ + [v2] "m" (*v2), + [newv2] "r" (newv2), + /* final store input */ + [v] "m" (*v), + [expect] "r" (expect), + [newv] "r" (newv) + RSEQ_INJECT_INPUT + : "r0", "memory", "cc" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + rseq_workaround_gcc_asm_size_guess(); + return 0; +abort: + rseq_workaround_gcc_asm_size_guess(); + RSEQ_INJECT_FAILED + return -1; +cmpfail: + rseq_workaround_gcc_asm_size_guess(); + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t expect2, + intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + rseq_workaround_gcc_asm_size_guess(); + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + "ldr r0, %[v]\n\t" + "cmp %[expect], r0\n\t" + "bne %l[cmpfail]\n\t" + RSEQ_INJECT_ASM(4) + "ldr r0, %[v2]\n\t" + "cmp %[expect2], r0\n\t" + "bne %l[cmpfail]\n\t" + RSEQ_INJECT_ASM(5) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) + "ldr r0, %[v]\n\t" + "cmp %[expect], r0\n\t" + "bne %l[error2]\n\t" + "ldr r0, %[v2]\n\t" + "cmp %[expect2], r0\n\t" + "bne %l[error3]\n\t" +#endif + /* final store */ + "str %[newv], %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(6) + "b 5f\n\t" + RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f) + "5:\n\t" + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* cmp2 input */ + [v2] "m" (*v2), + [expect2] "r" (expect2), + /* final store input */ + [v] "m" (*v), + [expect] "r" (expect), + [newv] "r" (newv) + RSEQ_INJECT_INPUT + : "r0", "memory", "cc" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2, error3 +#endif + ); + rseq_workaround_gcc_asm_size_guess(); + return 0; +abort: + rseq_workaround_gcc_asm_size_guess(); + RSEQ_INJECT_FAILED + return -1; +cmpfail: + rseq_workaround_gcc_asm_size_guess(); + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("1st expected value comparison failed"); +error3: + rseq_bug("2nd expected value comparison failed"); +#endif +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, + void *dst, void *src, size_t len, + intptr_t newv, int cpu) +{ + uint32_t rseq_scratch[3]; + + RSEQ_INJECT_C(9) + + rseq_workaround_gcc_asm_size_guess(); + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */ + "str %[src], %[rseq_scratch0]\n\t" + "str %[dst], %[rseq_scratch1]\n\t" + "str %[len], %[rseq_scratch2]\n\t" + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + "ldr r0, %[v]\n\t" + "cmp %[expect], r0\n\t" + "bne 5f\n\t" + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 6f) + "ldr r0, %[v]\n\t" + "cmp %[expect], r0\n\t" + "bne 7f\n\t" +#endif + /* try memcpy */ + "cmp %[len], #0\n\t" \ + "beq 333f\n\t" \ + "222:\n\t" \ + "ldrb %%r0, [%[src]]\n\t" \ + "strb %%r0, [%[dst]]\n\t" \ + "adds %[src], #1\n\t" \ + "adds %[dst], #1\n\t" \ + "subs %[len], #1\n\t" \ + "bne 222b\n\t" \ + "333:\n\t" \ + RSEQ_INJECT_ASM(5) + /* final store */ + "str %[newv], %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(6) + /* teardown */ + "ldr %[len], %[rseq_scratch2]\n\t" + "ldr %[dst], %[rseq_scratch1]\n\t" + "ldr %[src], %[rseq_scratch0]\n\t" + "b 8f\n\t" + RSEQ_ASM_DEFINE_ABORT(3, 4, + /* teardown */ + "ldr %[len], %[rseq_scratch2]\n\t" + "ldr %[dst], %[rseq_scratch1]\n\t" + "ldr %[src], %[rseq_scratch0]\n\t", + abort, 1b, 2b, 4f) + RSEQ_ASM_DEFINE_CMPFAIL(5, + /* teardown */ + "ldr %[len], %[rseq_scratch2]\n\t" + "ldr %[dst], %[rseq_scratch1]\n\t" + "ldr %[src], %[rseq_scratch0]\n\t", + cmpfail) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_CMPFAIL(6, + /* teardown */ + "ldr %[len], %[rseq_scratch2]\n\t" + "ldr %[dst], %[rseq_scratch1]\n\t" + "ldr %[src], %[rseq_scratch0]\n\t", + error1) + RSEQ_ASM_DEFINE_CMPFAIL(7, + /* teardown */ + "ldr %[len], %[rseq_scratch2]\n\t" + "ldr %[dst], %[rseq_scratch1]\n\t" + "ldr %[src], %[rseq_scratch0]\n\t", + error2) +#endif + "8:\n\t" + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* final store input */ + [v] "m" (*v), + [expect] "r" (expect), + [newv] "r" (newv), + /* try memcpy input */ + [dst] "r" (dst), + [src] "r" (src), + [len] "r" (len), + [rseq_scratch0] "m" (rseq_scratch[0]), + [rseq_scratch1] "m" (rseq_scratch[1]), + [rseq_scratch2] "m" (rseq_scratch[2]) + RSEQ_INJECT_INPUT + : "r0", "memory", "cc" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + rseq_workaround_gcc_asm_size_guess(); + return 0; +abort: + rseq_workaround_gcc_asm_size_guess(); + RSEQ_INJECT_FAILED + return -1; +cmpfail: + rseq_workaround_gcc_asm_size_guess(); + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_workaround_gcc_asm_size_guess(); + rseq_bug("cpu_id comparison failed"); +error2: + rseq_workaround_gcc_asm_size_guess(); + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, + void *dst, void *src, size_t len, + intptr_t newv, int cpu) +{ + uint32_t rseq_scratch[3]; + + RSEQ_INJECT_C(9) + + rseq_workaround_gcc_asm_size_guess(); + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */ + "str %[src], %[rseq_scratch0]\n\t" + "str %[dst], %[rseq_scratch1]\n\t" + "str %[len], %[rseq_scratch2]\n\t" + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + "ldr r0, %[v]\n\t" + "cmp %[expect], r0\n\t" + "bne 5f\n\t" + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 6f) + "ldr r0, %[v]\n\t" + "cmp %[expect], r0\n\t" + "bne 7f\n\t" +#endif + /* try memcpy */ + "cmp %[len], #0\n\t" \ + "beq 333f\n\t" \ + "222:\n\t" \ + "ldrb %%r0, [%[src]]\n\t" \ + "strb %%r0, [%[dst]]\n\t" \ + "adds %[src], #1\n\t" \ + "adds %[dst], #1\n\t" \ + "subs %[len], #1\n\t" \ + "bne 222b\n\t" \ + "333:\n\t" \ + RSEQ_INJECT_ASM(5) + "dmb\n\t" /* full mb provides store-release */ + /* final store */ + "str %[newv], %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(6) + /* teardown */ + "ldr %[len], %[rseq_scratch2]\n\t" + "ldr %[dst], %[rseq_scratch1]\n\t" + "ldr %[src], %[rseq_scratch0]\n\t" + "b 8f\n\t" + RSEQ_ASM_DEFINE_ABORT(3, 4, + /* teardown */ + "ldr %[len], %[rseq_scratch2]\n\t" + "ldr %[dst], %[rseq_scratch1]\n\t" + "ldr %[src], %[rseq_scratch0]\n\t", + abort, 1b, 2b, 4f) + RSEQ_ASM_DEFINE_CMPFAIL(5, + /* teardown */ + "ldr %[len], %[rseq_scratch2]\n\t" + "ldr %[dst], %[rseq_scratch1]\n\t" + "ldr %[src], %[rseq_scratch0]\n\t", + cmpfail) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_CMPFAIL(6, + /* teardown */ + "ldr %[len], %[rseq_scratch2]\n\t" + "ldr %[dst], %[rseq_scratch1]\n\t" + "ldr %[src], %[rseq_scratch0]\n\t", + error1) + RSEQ_ASM_DEFINE_CMPFAIL(7, + /* teardown */ + "ldr %[len], %[rseq_scratch2]\n\t" + "ldr %[dst], %[rseq_scratch1]\n\t" + "ldr %[src], %[rseq_scratch0]\n\t", + error2) +#endif + "8:\n\t" + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* final store input */ + [v] "m" (*v), + [expect] "r" (expect), + [newv] "r" (newv), + /* try memcpy input */ + [dst] "r" (dst), + [src] "r" (src), + [len] "r" (len), + [rseq_scratch0] "m" (rseq_scratch[0]), + [rseq_scratch1] "m" (rseq_scratch[1]), + [rseq_scratch2] "m" (rseq_scratch[2]) + RSEQ_INJECT_INPUT + : "r0", "memory", "cc" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + rseq_workaround_gcc_asm_size_guess(); + return 0; +abort: + rseq_workaround_gcc_asm_size_guess(); + RSEQ_INJECT_FAILED + return -1; +cmpfail: + rseq_workaround_gcc_asm_size_guess(); + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_workaround_gcc_asm_size_guess(); + rseq_bug("cpu_id comparison failed"); +error2: + rseq_workaround_gcc_asm_size_guess(); + rseq_bug("expected value comparison failed"); +#endif +} + +#endif /* !RSEQ_SKIP_FASTPATH */ diff --git a/tools/testing/selftests/rseq/rseq-ppc.h b/tools/testing/selftests/rseq/rseq-ppc.h new file mode 100644 index 0000000..52630c9 --- /dev/null +++ b/tools/testing/selftests/rseq/rseq-ppc.h @@ -0,0 +1,671 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * rseq-ppc.h + * + * (C) Copyright 2016-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com> + * (C) Copyright 2016-2018 - Boqun Feng <boqun.feng@gmail.com> + */ + +#define RSEQ_SIG 0x53053053 + +#define rseq_smp_mb() __asm__ __volatile__ ("sync" ::: "memory", "cc") +#define rseq_smp_lwsync() __asm__ __volatile__ ("lwsync" ::: "memory", "cc") +#define rseq_smp_rmb() rseq_smp_lwsync() +#define rseq_smp_wmb() rseq_smp_lwsync() + +#define rseq_smp_load_acquire(p) \ +__extension__ ({ \ + __typeof(*p) ____p1 = RSEQ_READ_ONCE(*p); \ + rseq_smp_lwsync(); \ + ____p1; \ +}) + +#define rseq_smp_acquire__after_ctrl_dep() rseq_smp_lwsync() + +#define rseq_smp_store_release(p, v) \ +do { \ + rseq_smp_lwsync(); \ + RSEQ_WRITE_ONCE(*p, v); \ +} while (0) + +#ifdef RSEQ_SKIP_FASTPATH +#include "rseq-skip.h" +#else /* !RSEQ_SKIP_FASTPATH */ + +/* + * The __rseq_table section can be used by debuggers to better handle + * single-stepping through the restartable critical sections. + */ + +#ifdef __PPC64__ + +#define STORE_WORD "std " +#define LOAD_WORD "ld " +#define LOADX_WORD "ldx " +#define CMP_WORD "cmpd " + +#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, \ + start_ip, post_commit_offset, abort_ip) \ + ".pushsection __rseq_table, \"aw\"\n\t" \ + ".balign 32\n\t" \ + __rseq_str(label) ":\n\t" \ + ".long " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \ + ".quad " __rseq_str(start_ip) ", " __rseq_str(post_commit_offset) ", " __rseq_str(abort_ip) "\n\t" \ + ".popsection\n\t" + +#define RSEQ_ASM_STORE_RSEQ_CS(label, cs_label, rseq_cs) \ + RSEQ_INJECT_ASM(1) \ + "lis %%r17, (" __rseq_str(cs_label) ")@highest\n\t" \ + "ori %%r17, %%r17, (" __rseq_str(cs_label) ")@higher\n\t" \ + "rldicr %%r17, %%r17, 32, 31\n\t" \ + "oris %%r17, %%r17, (" __rseq_str(cs_label) ")@high\n\t" \ + "ori %%r17, %%r17, (" __rseq_str(cs_label) ")@l\n\t" \ + "std %%r17, %[" __rseq_str(rseq_cs) "]\n\t" \ + __rseq_str(label) ":\n\t" + +#else /* #ifdef __PPC64__ */ + +#define STORE_WORD "stw " +#define LOAD_WORD "lwz " +#define LOADX_WORD "lwzx " +#define CMP_WORD "cmpw " + +#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, \ + start_ip, post_commit_offset, abort_ip) \ + ".pushsection __rseq_table, \"aw\"\n\t" \ + ".balign 32\n\t" \ + __rseq_str(label) ":\n\t" \ + ".long " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \ + /* 32-bit only supported on BE */ \ + ".long 0x0, " __rseq_str(start_ip) ", 0x0, " __rseq_str(post_commit_offset) ", 0x0, " __rseq_str(abort_ip) "\n\t" \ + ".popsection\n\t" + +#define RSEQ_ASM_STORE_RSEQ_CS(label, cs_label, rseq_cs) \ + RSEQ_INJECT_ASM(1) \ + "lis %%r17, (" __rseq_str(cs_label) ")@ha\n\t" \ + "addi %%r17, %%r17, (" __rseq_str(cs_label) ")@l\n\t" \ + "stw %%r17, %[" __rseq_str(rseq_cs) "]\n\t" \ + __rseq_str(label) ":\n\t" + +#endif /* #ifdef __PPC64__ */ + +#define RSEQ_ASM_DEFINE_TABLE(label, start_ip, post_commit_ip, abort_ip) \ + __RSEQ_ASM_DEFINE_TABLE(label, 0x0, 0x0, start_ip, \ + (post_commit_ip - start_ip), abort_ip) + +#define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label) \ + RSEQ_INJECT_ASM(2) \ + "lwz %%r17, %[" __rseq_str(current_cpu_id) "]\n\t" \ + "cmpw cr7, %[" __rseq_str(cpu_id) "], %%r17\n\t" \ + "bne- cr7, " __rseq_str(label) "\n\t" + +#define RSEQ_ASM_DEFINE_ABORT(label, abort_label) \ + ".pushsection __rseq_failure, \"ax\"\n\t" \ + ".long " __rseq_str(RSEQ_SIG) "\n\t" \ + __rseq_str(label) ":\n\t" \ + "b %l[" __rseq_str(abort_label) "]\n\t" \ + ".popsection\n\t" + +/* + * RSEQ_ASM_OPs: asm operations for rseq + * RSEQ_ASM_OP_R_*: has hard-code registers in it + * RSEQ_ASM_OP_* (else): doesn't have hard-code registers(unless cr7) + */ +#define RSEQ_ASM_OP_CMPEQ(var, expect, label) \ + LOAD_WORD "%%r17, %[" __rseq_str(var) "]\n\t" \ + CMP_WORD "cr7, %%r17, %[" __rseq_str(expect) "]\n\t" \ + "bne- cr7, " __rseq_str(label) "\n\t" + +#define RSEQ_ASM_OP_CMPNE(var, expectnot, label) \ + LOAD_WORD "%%r17, %[" __rseq_str(var) "]\n\t" \ + CMP_WORD "cr7, %%r17, %[" __rseq_str(expectnot) "]\n\t" \ + "beq- cr7, " __rseq_str(label) "\n\t" + +#define RSEQ_ASM_OP_STORE(value, var) \ + STORE_WORD "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t" + +/* Load @var to r17 */ +#define RSEQ_ASM_OP_R_LOAD(var) \ + LOAD_WORD "%%r17, %[" __rseq_str(var) "]\n\t" + +/* Store r17 to @var */ +#define RSEQ_ASM_OP_R_STORE(var) \ + STORE_WORD "%%r17, %[" __rseq_str(var) "]\n\t" + +/* Add @count to r17 */ +#define RSEQ_ASM_OP_R_ADD(count) \ + "add %%r17, %[" __rseq_str(count) "], %%r17\n\t" + +/* Load (r17 + voffp) to r17 */ +#define RSEQ_ASM_OP_R_LOADX(voffp) \ + LOADX_WORD "%%r17, %[" __rseq_str(voffp) "], %%r17\n\t" + +/* TODO: implement a faster memcpy. */ +#define RSEQ_ASM_OP_R_MEMCPY() \ + "cmpdi %%r19, 0\n\t" \ + "beq 333f\n\t" \ + "addi %%r20, %%r20, -1\n\t" \ + "addi %%r21, %%r21, -1\n\t" \ + "222:\n\t" \ + "lbzu %%r18, 1(%%r20)\n\t" \ + "stbu %%r18, 1(%%r21)\n\t" \ + "addi %%r19, %%r19, -1\n\t" \ + "cmpdi %%r19, 0\n\t" \ + "bne 222b\n\t" \ + "333:\n\t" \ + +#define RSEQ_ASM_OP_R_FINAL_STORE(var, post_commit_label) \ + STORE_WORD "%%r17, %[" __rseq_str(var) "]\n\t" \ + __rseq_str(post_commit_label) ":\n\t" + +#define RSEQ_ASM_OP_FINAL_STORE(value, var, post_commit_label) \ + STORE_WORD "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t" \ + __rseq_str(post_commit_label) ":\n\t" + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs) + /* cmp cpuid */ + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + /* cmp @v equal to @expect */ + RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail]) + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + /* cmp cpuid */ + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) + /* cmp @v equal to @expect */ + RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2]) +#endif + /* final store */ + RSEQ_ASM_OP_FINAL_STORE(newv, v, 2) + RSEQ_INJECT_ASM(5) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + [v] "m" (*v), + [expect] "r" (expect), + [newv] "r" (newv) + RSEQ_INJECT_INPUT + : "memory", "cc", "r17" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __attribute__((always_inline)) +int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, + off_t voffp, intptr_t *load, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs) + /* cmp cpuid */ + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + /* cmp @v not equal to @expectnot */ + RSEQ_ASM_OP_CMPNE(v, expectnot, %l[cmpfail]) + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + /* cmp cpuid */ + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) + /* cmp @v not equal to @expectnot */ + RSEQ_ASM_OP_CMPNE(v, expectnot, %l[error2]) +#endif + /* load the value of @v */ + RSEQ_ASM_OP_R_LOAD(v) + /* store it in @load */ + RSEQ_ASM_OP_R_STORE(load) + /* dereference voffp(v) */ + RSEQ_ASM_OP_R_LOADX(voffp) + /* final store the value at voffp(v) */ + RSEQ_ASM_OP_R_FINAL_STORE(v, 2) + RSEQ_INJECT_ASM(5) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* final store input */ + [v] "m" (*v), + [expectnot] "r" (expectnot), + [voffp] "b" (voffp), + [load] "m" (*load) + RSEQ_INJECT_INPUT + : "memory", "cc", "r17" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __attribute__((always_inline)) +int rseq_addv(intptr_t *v, intptr_t count, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs) + /* cmp cpuid */ + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) +#ifdef RSEQ_COMPARE_TWICE + /* cmp cpuid */ + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) +#endif + /* load the value of @v */ + RSEQ_ASM_OP_R_LOAD(v) + /* add @count to it */ + RSEQ_ASM_OP_R_ADD(count) + /* final store */ + RSEQ_ASM_OP_R_FINAL_STORE(v, 2) + RSEQ_INJECT_ASM(4) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* final store input */ + [v] "m" (*v), + [count] "r" (count) + RSEQ_INJECT_INPUT + : "memory", "cc", "r17" + RSEQ_INJECT_CLOBBER + : abort +#ifdef RSEQ_COMPARE_TWICE + , error1 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +#endif +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t newv2, + intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs) + /* cmp cpuid */ + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + /* cmp @v equal to @expect */ + RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail]) + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + /* cmp cpuid */ + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) + /* cmp @v equal to @expect */ + RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2]) +#endif + /* try store */ + RSEQ_ASM_OP_STORE(newv2, v2) + RSEQ_INJECT_ASM(5) + /* final store */ + RSEQ_ASM_OP_FINAL_STORE(newv, v, 2) + RSEQ_INJECT_ASM(6) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* try store input */ + [v2] "m" (*v2), + [newv2] "r" (newv2), + /* final store input */ + [v] "m" (*v), + [expect] "r" (expect), + [newv] "r" (newv) + RSEQ_INJECT_INPUT + : "memory", "cc", "r17" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t newv2, + intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs) + /* cmp cpuid */ + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + /* cmp @v equal to @expect */ + RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail]) + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + /* cmp cpuid */ + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) + /* cmp @v equal to @expect */ + RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2]) +#endif + /* try store */ + RSEQ_ASM_OP_STORE(newv2, v2) + RSEQ_INJECT_ASM(5) + /* for 'release' */ + "lwsync\n\t" + /* final store */ + RSEQ_ASM_OP_FINAL_STORE(newv, v, 2) + RSEQ_INJECT_ASM(6) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* try store input */ + [v2] "m" (*v2), + [newv2] "r" (newv2), + /* final store input */ + [v] "m" (*v), + [expect] "r" (expect), + [newv] "r" (newv) + RSEQ_INJECT_INPUT + : "memory", "cc", "r17" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t expect2, + intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs) + /* cmp cpuid */ + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + /* cmp @v equal to @expect */ + RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail]) + RSEQ_INJECT_ASM(4) + /* cmp @v2 equal to @expct2 */ + RSEQ_ASM_OP_CMPEQ(v2, expect2, %l[cmpfail]) + RSEQ_INJECT_ASM(5) +#ifdef RSEQ_COMPARE_TWICE + /* cmp cpuid */ + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) + /* cmp @v equal to @expect */ + RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2]) + /* cmp @v2 equal to @expct2 */ + RSEQ_ASM_OP_CMPEQ(v2, expect2, %l[error3]) +#endif + /* final store */ + RSEQ_ASM_OP_FINAL_STORE(newv, v, 2) + RSEQ_INJECT_ASM(6) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* cmp2 input */ + [v2] "m" (*v2), + [expect2] "r" (expect2), + /* final store input */ + [v] "m" (*v), + [expect] "r" (expect), + [newv] "r" (newv) + RSEQ_INJECT_INPUT + : "memory", "cc", "r17" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2, error3 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("1st expected value comparison failed"); +error3: + rseq_bug("2nd expected value comparison failed"); +#endif +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, + void *dst, void *src, size_t len, + intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */ + /* setup for mempcy */ + "mr %%r19, %[len]\n\t" + "mr %%r20, %[src]\n\t" + "mr %%r21, %[dst]\n\t" + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs) + /* cmp cpuid */ + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + /* cmp @v equal to @expect */ + RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail]) + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + /* cmp cpuid */ + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) + /* cmp @v equal to @expect */ + RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2]) +#endif + /* try memcpy */ + RSEQ_ASM_OP_R_MEMCPY() + RSEQ_INJECT_ASM(5) + /* final store */ + RSEQ_ASM_OP_FINAL_STORE(newv, v, 2) + RSEQ_INJECT_ASM(6) + /* teardown */ + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* final store input */ + [v] "m" (*v), + [expect] "r" (expect), + [newv] "r" (newv), + /* try memcpy input */ + [dst] "r" (dst), + [src] "r" (src), + [len] "r" (len) + RSEQ_INJECT_INPUT + : "memory", "cc", "r17", "r18", "r19", "r20", "r21" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, + void *dst, void *src, size_t len, + intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */ + /* setup for mempcy */ + "mr %%r19, %[len]\n\t" + "mr %%r20, %[src]\n\t" + "mr %%r21, %[dst]\n\t" + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs) + /* cmp cpuid */ + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + /* cmp @v equal to @expect */ + RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail]) + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + /* cmp cpuid */ + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) + /* cmp @v equal to @expect */ + RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2]) +#endif + /* try memcpy */ + RSEQ_ASM_OP_R_MEMCPY() + RSEQ_INJECT_ASM(5) + /* for 'release' */ + "lwsync\n\t" + /* final store */ + RSEQ_ASM_OP_FINAL_STORE(newv, v, 2) + RSEQ_INJECT_ASM(6) + /* teardown */ + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* final store input */ + [v] "m" (*v), + [expect] "r" (expect), + [newv] "r" (newv), + /* try memcpy input */ + [dst] "r" (dst), + [src] "r" (src), + [len] "r" (len) + RSEQ_INJECT_INPUT + : "memory", "cc", "r17", "r18", "r19", "r20", "r21" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +#undef STORE_WORD +#undef LOAD_WORD +#undef LOADX_WORD +#undef CMP_WORD + +#endif /* !RSEQ_SKIP_FASTPATH */ diff --git a/tools/testing/selftests/rseq/rseq-skip.h b/tools/testing/selftests/rseq/rseq-skip.h new file mode 100644 index 0000000..72750b5 --- /dev/null +++ b/tools/testing/selftests/rseq/rseq-skip.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * rseq-skip.h + * + * (C) Copyright 2017-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com> + */ + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) +{ + return -1; +} + +static inline __attribute__((always_inline)) +int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, + off_t voffp, intptr_t *load, int cpu) +{ + return -1; +} + +static inline __attribute__((always_inline)) +int rseq_addv(intptr_t *v, intptr_t count, int cpu) +{ + return -1; +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t newv2, + intptr_t newv, int cpu) +{ + return -1; +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t newv2, + intptr_t newv, int cpu) +{ + return -1; +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t expect2, + intptr_t newv, int cpu) +{ + return -1; +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, + void *dst, void *src, size_t len, + intptr_t newv, int cpu) +{ + return -1; +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, + void *dst, void *src, size_t len, + intptr_t newv, int cpu) +{ + return -1; +} diff --git a/tools/testing/selftests/rseq/rseq-x86.h b/tools/testing/selftests/rseq/rseq-x86.h new file mode 100644 index 0000000..089410a --- /dev/null +++ b/tools/testing/selftests/rseq/rseq-x86.h @@ -0,0 +1,1132 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * rseq-x86.h + * + * (C) Copyright 2016-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com> + */ + +#include <stdint.h> + +#define RSEQ_SIG 0x53053053 + +#ifdef __x86_64__ + +#define rseq_smp_mb() \ + __asm__ __volatile__ ("lock; addl $0,-128(%%rsp)" ::: "memory", "cc") +#define rseq_smp_rmb() rseq_barrier() +#define rseq_smp_wmb() rseq_barrier() + +#define rseq_smp_load_acquire(p) \ +__extension__ ({ \ + __typeof(*p) ____p1 = RSEQ_READ_ONCE(*p); \ + rseq_barrier(); \ + ____p1; \ +}) + +#define rseq_smp_acquire__after_ctrl_dep() rseq_smp_rmb() + +#define rseq_smp_store_release(p, v) \ +do { \ + rseq_barrier(); \ + RSEQ_WRITE_ONCE(*p, v); \ +} while (0) + +#ifdef RSEQ_SKIP_FASTPATH +#include "rseq-skip.h" +#else /* !RSEQ_SKIP_FASTPATH */ + +#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, \ + start_ip, post_commit_offset, abort_ip) \ + ".pushsection __rseq_table, \"aw\"\n\t" \ + ".balign 32\n\t" \ + __rseq_str(label) ":\n\t" \ + ".long " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \ + ".quad " __rseq_str(start_ip) ", " __rseq_str(post_commit_offset) ", " __rseq_str(abort_ip) "\n\t" \ + ".popsection\n\t" + +#define RSEQ_ASM_DEFINE_TABLE(label, start_ip, post_commit_ip, abort_ip) \ + __RSEQ_ASM_DEFINE_TABLE(label, 0x0, 0x0, start_ip, \ + (post_commit_ip - start_ip), abort_ip) + +#define RSEQ_ASM_STORE_RSEQ_CS(label, cs_label, rseq_cs) \ + RSEQ_INJECT_ASM(1) \ + "leaq " __rseq_str(cs_label) "(%%rip), %%rax\n\t" \ + "movq %%rax, %[" __rseq_str(rseq_cs) "]\n\t" \ + __rseq_str(label) ":\n\t" + +#define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label) \ + RSEQ_INJECT_ASM(2) \ + "cmpl %[" __rseq_str(cpu_id) "], %[" __rseq_str(current_cpu_id) "]\n\t" \ + "jnz " __rseq_str(label) "\n\t" + +#define RSEQ_ASM_DEFINE_ABORT(label, teardown, abort_label) \ + ".pushsection __rseq_failure, \"ax\"\n\t" \ + /* Disassembler-friendly signature: nopl <sig>(%rip). */\ + ".byte 0x0f, 0x1f, 0x05\n\t" \ + ".long " __rseq_str(RSEQ_SIG) "\n\t" \ + __rseq_str(label) ":\n\t" \ + teardown \ + "jmp %l[" __rseq_str(abort_label) "]\n\t" \ + ".popsection\n\t" + +#define RSEQ_ASM_DEFINE_CMPFAIL(label, teardown, cmpfail_label) \ + ".pushsection __rseq_failure, \"ax\"\n\t" \ + __rseq_str(label) ":\n\t" \ + teardown \ + "jmp %l[" __rseq_str(cmpfail_label) "]\n\t" \ + ".popsection\n\t" + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + "cmpq %[v], %[expect]\n\t" + "jnz %l[cmpfail]\n\t" + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) + "cmpq %[v], %[expect]\n\t" + "jnz %l[error2]\n\t" +#endif + /* final store */ + "movq %[newv], %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(5) + RSEQ_ASM_DEFINE_ABORT(4, "", abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + [v] "m" (*v), + [expect] "r" (expect), + [newv] "r" (newv) + : "memory", "cc", "rax" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +/* + * Compare @v against @expectnot. When it does _not_ match, load @v + * into @load, and store the content of *@v + voffp into @v. + */ +static inline __attribute__((always_inline)) +int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, + off_t voffp, intptr_t *load, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + "movq %[v], %%rbx\n\t" + "cmpq %%rbx, %[expectnot]\n\t" + "je %l[cmpfail]\n\t" + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) + "movq %[v], %%rbx\n\t" + "cmpq %%rbx, %[expectnot]\n\t" + "je %l[error2]\n\t" +#endif + "movq %%rbx, %[load]\n\t" + "addq %[voffp], %%rbx\n\t" + "movq (%%rbx), %%rbx\n\t" + /* final store */ + "movq %%rbx, %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(5) + RSEQ_ASM_DEFINE_ABORT(4, "", abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* final store input */ + [v] "m" (*v), + [expectnot] "r" (expectnot), + [voffp] "er" (voffp), + [load] "m" (*load) + : "memory", "cc", "rax", "rbx" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __attribute__((always_inline)) +int rseq_addv(intptr_t *v, intptr_t count, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) +#endif + /* final store */ + "addq %[count], %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(4) + RSEQ_ASM_DEFINE_ABORT(4, "", abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* final store input */ + [v] "m" (*v), + [count] "er" (count) + : "memory", "cc", "rax" + RSEQ_INJECT_CLOBBER + : abort +#ifdef RSEQ_COMPARE_TWICE + , error1 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +#endif +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t newv2, + intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + "cmpq %[v], %[expect]\n\t" + "jnz %l[cmpfail]\n\t" + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) + "cmpq %[v], %[expect]\n\t" + "jnz %l[error2]\n\t" +#endif + /* try store */ + "movq %[newv2], %[v2]\n\t" + RSEQ_INJECT_ASM(5) + /* final store */ + "movq %[newv], %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(6) + RSEQ_ASM_DEFINE_ABORT(4, "", abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* try store input */ + [v2] "m" (*v2), + [newv2] "r" (newv2), + /* final store input */ + [v] "m" (*v), + [expect] "r" (expect), + [newv] "r" (newv) + : "memory", "cc", "rax" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +/* x86-64 is TSO. */ +static inline __attribute__((always_inline)) +int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t newv2, + intptr_t newv, int cpu) +{ + return rseq_cmpeqv_trystorev_storev(v, expect, v2, newv2, newv, cpu); +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t expect2, + intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + "cmpq %[v], %[expect]\n\t" + "jnz %l[cmpfail]\n\t" + RSEQ_INJECT_ASM(4) + "cmpq %[v2], %[expect2]\n\t" + "jnz %l[cmpfail]\n\t" + RSEQ_INJECT_ASM(5) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) + "cmpq %[v], %[expect]\n\t" + "jnz %l[error2]\n\t" + "cmpq %[v2], %[expect2]\n\t" + "jnz %l[error3]\n\t" +#endif + /* final store */ + "movq %[newv], %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(6) + RSEQ_ASM_DEFINE_ABORT(4, "", abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* cmp2 input */ + [v2] "m" (*v2), + [expect2] "r" (expect2), + /* final store input */ + [v] "m" (*v), + [expect] "r" (expect), + [newv] "r" (newv) + : "memory", "cc", "rax" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2, error3 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("1st expected value comparison failed"); +error3: + rseq_bug("2nd expected value comparison failed"); +#endif +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, + void *dst, void *src, size_t len, + intptr_t newv, int cpu) +{ + uint64_t rseq_scratch[3]; + + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */ + "movq %[src], %[rseq_scratch0]\n\t" + "movq %[dst], %[rseq_scratch1]\n\t" + "movq %[len], %[rseq_scratch2]\n\t" + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + "cmpq %[v], %[expect]\n\t" + "jnz 5f\n\t" + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 6f) + "cmpq %[v], %[expect]\n\t" + "jnz 7f\n\t" +#endif + /* try memcpy */ + "test %[len], %[len]\n\t" \ + "jz 333f\n\t" \ + "222:\n\t" \ + "movb (%[src]), %%al\n\t" \ + "movb %%al, (%[dst])\n\t" \ + "inc %[src]\n\t" \ + "inc %[dst]\n\t" \ + "dec %[len]\n\t" \ + "jnz 222b\n\t" \ + "333:\n\t" \ + RSEQ_INJECT_ASM(5) + /* final store */ + "movq %[newv], %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(6) + /* teardown */ + "movq %[rseq_scratch2], %[len]\n\t" + "movq %[rseq_scratch1], %[dst]\n\t" + "movq %[rseq_scratch0], %[src]\n\t" + RSEQ_ASM_DEFINE_ABORT(4, + "movq %[rseq_scratch2], %[len]\n\t" + "movq %[rseq_scratch1], %[dst]\n\t" + "movq %[rseq_scratch0], %[src]\n\t", + abort) + RSEQ_ASM_DEFINE_CMPFAIL(5, + "movq %[rseq_scratch2], %[len]\n\t" + "movq %[rseq_scratch1], %[dst]\n\t" + "movq %[rseq_scratch0], %[src]\n\t", + cmpfail) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_CMPFAIL(6, + "movq %[rseq_scratch2], %[len]\n\t" + "movq %[rseq_scratch1], %[dst]\n\t" + "movq %[rseq_scratch0], %[src]\n\t", + error1) + RSEQ_ASM_DEFINE_CMPFAIL(7, + "movq %[rseq_scratch2], %[len]\n\t" + "movq %[rseq_scratch1], %[dst]\n\t" + "movq %[rseq_scratch0], %[src]\n\t", + error2) +#endif + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* final store input */ + [v] "m" (*v), + [expect] "r" (expect), + [newv] "r" (newv), + /* try memcpy input */ + [dst] "r" (dst), + [src] "r" (src), + [len] "r" (len), + [rseq_scratch0] "m" (rseq_scratch[0]), + [rseq_scratch1] "m" (rseq_scratch[1]), + [rseq_scratch2] "m" (rseq_scratch[2]) + : "memory", "cc", "rax" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +/* x86-64 is TSO. */ +static inline __attribute__((always_inline)) +int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, + void *dst, void *src, size_t len, + intptr_t newv, int cpu) +{ + return rseq_cmpeqv_trymemcpy_storev(v, expect, dst, src, len, + newv, cpu); +} + +#endif /* !RSEQ_SKIP_FASTPATH */ + +#elif __i386__ + +#define rseq_smp_mb() \ + __asm__ __volatile__ ("lock; addl $0,-128(%%esp)" ::: "memory", "cc") +#define rseq_smp_rmb() \ + __asm__ __volatile__ ("lock; addl $0,-128(%%esp)" ::: "memory", "cc") +#define rseq_smp_wmb() \ + __asm__ __volatile__ ("lock; addl $0,-128(%%esp)" ::: "memory", "cc") + +#define rseq_smp_load_acquire(p) \ +__extension__ ({ \ + __typeof(*p) ____p1 = RSEQ_READ_ONCE(*p); \ + rseq_smp_mb(); \ + ____p1; \ +}) + +#define rseq_smp_acquire__after_ctrl_dep() rseq_smp_rmb() + +#define rseq_smp_store_release(p, v) \ +do { \ + rseq_smp_mb(); \ + RSEQ_WRITE_ONCE(*p, v); \ +} while (0) + +#ifdef RSEQ_SKIP_FASTPATH +#include "rseq-skip.h" +#else /* !RSEQ_SKIP_FASTPATH */ + +/* + * Use eax as scratch register and take memory operands as input to + * lessen register pressure. Especially needed when compiling in O0. + */ +#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, \ + start_ip, post_commit_offset, abort_ip) \ + ".pushsection __rseq_table, \"aw\"\n\t" \ + ".balign 32\n\t" \ + __rseq_str(label) ":\n\t" \ + ".long " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \ + ".long " __rseq_str(start_ip) ", 0x0, " __rseq_str(post_commit_offset) ", 0x0, " __rseq_str(abort_ip) ", 0x0\n\t" \ + ".popsection\n\t" + +#define RSEQ_ASM_DEFINE_TABLE(label, start_ip, post_commit_ip, abort_ip) \ + __RSEQ_ASM_DEFINE_TABLE(label, 0x0, 0x0, start_ip, \ + (post_commit_ip - start_ip), abort_ip) + +#define RSEQ_ASM_STORE_RSEQ_CS(label, cs_label, rseq_cs) \ + RSEQ_INJECT_ASM(1) \ + "movl $" __rseq_str(cs_label) ", %[rseq_cs]\n\t" \ + __rseq_str(label) ":\n\t" + +#define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label) \ + RSEQ_INJECT_ASM(2) \ + "cmpl %[" __rseq_str(cpu_id) "], %[" __rseq_str(current_cpu_id) "]\n\t" \ + "jnz " __rseq_str(label) "\n\t" + +#define RSEQ_ASM_DEFINE_ABORT(label, teardown, abort_label) \ + ".pushsection __rseq_failure, \"ax\"\n\t" \ + /* Disassembler-friendly signature: nopl <sig>. */ \ + ".byte 0x0f, 0x1f, 0x05\n\t" \ + ".long " __rseq_str(RSEQ_SIG) "\n\t" \ + __rseq_str(label) ":\n\t" \ + teardown \ + "jmp %l[" __rseq_str(abort_label) "]\n\t" \ + ".popsection\n\t" + +#define RSEQ_ASM_DEFINE_CMPFAIL(label, teardown, cmpfail_label) \ + ".pushsection __rseq_failure, \"ax\"\n\t" \ + __rseq_str(label) ":\n\t" \ + teardown \ + "jmp %l[" __rseq_str(cmpfail_label) "]\n\t" \ + ".popsection\n\t" + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + "cmpl %[v], %[expect]\n\t" + "jnz %l[cmpfail]\n\t" + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) + "cmpl %[v], %[expect]\n\t" + "jnz %l[error2]\n\t" +#endif + /* final store */ + "movl %[newv], %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(5) + RSEQ_ASM_DEFINE_ABORT(4, "", abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + [v] "m" (*v), + [expect] "r" (expect), + [newv] "r" (newv) + : "memory", "cc", "eax" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +/* + * Compare @v against @expectnot. When it does _not_ match, load @v + * into @load, and store the content of *@v + voffp into @v. + */ +static inline __attribute__((always_inline)) +int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, + off_t voffp, intptr_t *load, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + "movl %[v], %%ebx\n\t" + "cmpl %%ebx, %[expectnot]\n\t" + "je %l[cmpfail]\n\t" + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) + "movl %[v], %%ebx\n\t" + "cmpl %%ebx, %[expectnot]\n\t" + "je %l[error2]\n\t" +#endif + "movl %%ebx, %[load]\n\t" + "addl %[voffp], %%ebx\n\t" + "movl (%%ebx), %%ebx\n\t" + /* final store */ + "movl %%ebx, %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(5) + RSEQ_ASM_DEFINE_ABORT(4, "", abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* final store input */ + [v] "m" (*v), + [expectnot] "r" (expectnot), + [voffp] "ir" (voffp), + [load] "m" (*load) + : "memory", "cc", "eax", "ebx" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __attribute__((always_inline)) +int rseq_addv(intptr_t *v, intptr_t count, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) +#endif + /* final store */ + "addl %[count], %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(4) + RSEQ_ASM_DEFINE_ABORT(4, "", abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* final store input */ + [v] "m" (*v), + [count] "ir" (count) + : "memory", "cc", "eax" + RSEQ_INJECT_CLOBBER + : abort +#ifdef RSEQ_COMPARE_TWICE + , error1 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +#endif +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t newv2, + intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + "cmpl %[v], %[expect]\n\t" + "jnz %l[cmpfail]\n\t" + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) + "cmpl %[v], %[expect]\n\t" + "jnz %l[error2]\n\t" +#endif + /* try store */ + "movl %[newv2], %%eax\n\t" + "movl %%eax, %[v2]\n\t" + RSEQ_INJECT_ASM(5) + /* final store */ + "movl %[newv], %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(6) + RSEQ_ASM_DEFINE_ABORT(4, "", abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* try store input */ + [v2] "m" (*v2), + [newv2] "m" (newv2), + /* final store input */ + [v] "m" (*v), + [expect] "r" (expect), + [newv] "r" (newv) + : "memory", "cc", "eax" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t newv2, + intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + "movl %[expect], %%eax\n\t" + "cmpl %[v], %%eax\n\t" + "jnz %l[cmpfail]\n\t" + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) + "movl %[expect], %%eax\n\t" + "cmpl %[v], %%eax\n\t" + "jnz %l[error2]\n\t" +#endif + /* try store */ + "movl %[newv2], %[v2]\n\t" + RSEQ_INJECT_ASM(5) + "lock; addl $0,-128(%%esp)\n\t" + /* final store */ + "movl %[newv], %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(6) + RSEQ_ASM_DEFINE_ABORT(4, "", abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* try store input */ + [v2] "m" (*v2), + [newv2] "r" (newv2), + /* final store input */ + [v] "m" (*v), + [expect] "m" (expect), + [newv] "r" (newv) + : "memory", "cc", "eax" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif + +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t expect2, + intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + "cmpl %[v], %[expect]\n\t" + "jnz %l[cmpfail]\n\t" + RSEQ_INJECT_ASM(4) + "cmpl %[expect2], %[v2]\n\t" + "jnz %l[cmpfail]\n\t" + RSEQ_INJECT_ASM(5) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) + "cmpl %[v], %[expect]\n\t" + "jnz %l[error2]\n\t" + "cmpl %[expect2], %[v2]\n\t" + "jnz %l[error3]\n\t" +#endif + "movl %[newv], %%eax\n\t" + /* final store */ + "movl %%eax, %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(6) + RSEQ_ASM_DEFINE_ABORT(4, "", abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* cmp2 input */ + [v2] "m" (*v2), + [expect2] "r" (expect2), + /* final store input */ + [v] "m" (*v), + [expect] "r" (expect), + [newv] "m" (newv) + : "memory", "cc", "eax" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2, error3 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("1st expected value comparison failed"); +error3: + rseq_bug("2nd expected value comparison failed"); +#endif +} + +/* TODO: implement a faster memcpy. */ +static inline __attribute__((always_inline)) +int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, + void *dst, void *src, size_t len, + intptr_t newv, int cpu) +{ + uint32_t rseq_scratch[3]; + + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */ + "movl %[src], %[rseq_scratch0]\n\t" + "movl %[dst], %[rseq_scratch1]\n\t" + "movl %[len], %[rseq_scratch2]\n\t" + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + "movl %[expect], %%eax\n\t" + "cmpl %%eax, %[v]\n\t" + "jnz 5f\n\t" + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 6f) + "movl %[expect], %%eax\n\t" + "cmpl %%eax, %[v]\n\t" + "jnz 7f\n\t" +#endif + /* try memcpy */ + "test %[len], %[len]\n\t" \ + "jz 333f\n\t" \ + "222:\n\t" \ + "movb (%[src]), %%al\n\t" \ + "movb %%al, (%[dst])\n\t" \ + "inc %[src]\n\t" \ + "inc %[dst]\n\t" \ + "dec %[len]\n\t" \ + "jnz 222b\n\t" \ + "333:\n\t" \ + RSEQ_INJECT_ASM(5) + "movl %[newv], %%eax\n\t" + /* final store */ + "movl %%eax, %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(6) + /* teardown */ + "movl %[rseq_scratch2], %[len]\n\t" + "movl %[rseq_scratch1], %[dst]\n\t" + "movl %[rseq_scratch0], %[src]\n\t" + RSEQ_ASM_DEFINE_ABORT(4, + "movl %[rseq_scratch2], %[len]\n\t" + "movl %[rseq_scratch1], %[dst]\n\t" + "movl %[rseq_scratch0], %[src]\n\t", + abort) + RSEQ_ASM_DEFINE_CMPFAIL(5, + "movl %[rseq_scratch2], %[len]\n\t" + "movl %[rseq_scratch1], %[dst]\n\t" + "movl %[rseq_scratch0], %[src]\n\t", + cmpfail) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_CMPFAIL(6, + "movl %[rseq_scratch2], %[len]\n\t" + "movl %[rseq_scratch1], %[dst]\n\t" + "movl %[rseq_scratch0], %[src]\n\t", + error1) + RSEQ_ASM_DEFINE_CMPFAIL(7, + "movl %[rseq_scratch2], %[len]\n\t" + "movl %[rseq_scratch1], %[dst]\n\t" + "movl %[rseq_scratch0], %[src]\n\t", + error2) +#endif + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* final store input */ + [v] "m" (*v), + [expect] "m" (expect), + [newv] "m" (newv), + /* try memcpy input */ + [dst] "r" (dst), + [src] "r" (src), + [len] "r" (len), + [rseq_scratch0] "m" (rseq_scratch[0]), + [rseq_scratch1] "m" (rseq_scratch[1]), + [rseq_scratch2] "m" (rseq_scratch[2]) + : "memory", "cc", "eax" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +/* TODO: implement a faster memcpy. */ +static inline __attribute__((always_inline)) +int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, + void *dst, void *src, size_t len, + intptr_t newv, int cpu) +{ + uint32_t rseq_scratch[3]; + + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */ + "movl %[src], %[rseq_scratch0]\n\t" + "movl %[dst], %[rseq_scratch1]\n\t" + "movl %[len], %[rseq_scratch2]\n\t" + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + "movl %[expect], %%eax\n\t" + "cmpl %%eax, %[v]\n\t" + "jnz 5f\n\t" + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 6f) + "movl %[expect], %%eax\n\t" + "cmpl %%eax, %[v]\n\t" + "jnz 7f\n\t" +#endif + /* try memcpy */ + "test %[len], %[len]\n\t" \ + "jz 333f\n\t" \ + "222:\n\t" \ + "movb (%[src]), %%al\n\t" \ + "movb %%al, (%[dst])\n\t" \ + "inc %[src]\n\t" \ + "inc %[dst]\n\t" \ + "dec %[len]\n\t" \ + "jnz 222b\n\t" \ + "333:\n\t" \ + RSEQ_INJECT_ASM(5) + "lock; addl $0,-128(%%esp)\n\t" + "movl %[newv], %%eax\n\t" + /* final store */ + "movl %%eax, %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(6) + /* teardown */ + "movl %[rseq_scratch2], %[len]\n\t" + "movl %[rseq_scratch1], %[dst]\n\t" + "movl %[rseq_scratch0], %[src]\n\t" + RSEQ_ASM_DEFINE_ABORT(4, + "movl %[rseq_scratch2], %[len]\n\t" + "movl %[rseq_scratch1], %[dst]\n\t" + "movl %[rseq_scratch0], %[src]\n\t", + abort) + RSEQ_ASM_DEFINE_CMPFAIL(5, + "movl %[rseq_scratch2], %[len]\n\t" + "movl %[rseq_scratch1], %[dst]\n\t" + "movl %[rseq_scratch0], %[src]\n\t", + cmpfail) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_CMPFAIL(6, + "movl %[rseq_scratch2], %[len]\n\t" + "movl %[rseq_scratch1], %[dst]\n\t" + "movl %[rseq_scratch0], %[src]\n\t", + error1) + RSEQ_ASM_DEFINE_CMPFAIL(7, + "movl %[rseq_scratch2], %[len]\n\t" + "movl %[rseq_scratch1], %[dst]\n\t" + "movl %[rseq_scratch0], %[src]\n\t", + error2) +#endif + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* final store input */ + [v] "m" (*v), + [expect] "m" (expect), + [newv] "m" (newv), + /* try memcpy input */ + [dst] "r" (dst), + [src] "r" (src), + [len] "r" (len), + [rseq_scratch0] "m" (rseq_scratch[0]), + [rseq_scratch1] "m" (rseq_scratch[1]), + [rseq_scratch2] "m" (rseq_scratch[2]) + : "memory", "cc", "eax" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +#endif /* !RSEQ_SKIP_FASTPATH */ + +#endif diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c new file mode 100644 index 0000000..4847e97 --- /dev/null +++ b/tools/testing/selftests/rseq/rseq.c @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: LGPL-2.1 +/* + * rseq.c + * + * Copyright (C) 2016 Mathieu Desnoyers <mathieu.desnoyers@efficios.com> + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; only + * version 2.1 of the License. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + */ + +#define _GNU_SOURCE +#include <errno.h> +#include <sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <syscall.h> +#include <assert.h> +#include <signal.h> + +#include "rseq.h" + +#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) + +__attribute__((tls_model("initial-exec"))) __thread +volatile struct rseq __rseq_abi = { + .cpu_id = RSEQ_CPU_ID_UNINITIALIZED, +}; + +static __attribute__((tls_model("initial-exec"))) __thread +volatile int refcount; + +static void signal_off_save(sigset_t *oldset) +{ + sigset_t set; + int ret; + + sigfillset(&set); + ret = pthread_sigmask(SIG_BLOCK, &set, oldset); + if (ret) + abort(); +} + +static void signal_restore(sigset_t oldset) +{ + int ret; + + ret = pthread_sigmask(SIG_SETMASK, &oldset, NULL); + if (ret) + abort(); +} + +static int sys_rseq(volatile struct rseq *rseq_abi, uint32_t rseq_len, + int flags, uint32_t sig) +{ + return syscall(__NR_rseq, rseq_abi, rseq_len, flags, sig); +} + +int rseq_register_current_thread(void) +{ + int rc, ret = 0; + sigset_t oldset; + + signal_off_save(&oldset); + if (refcount++) + goto end; + rc = sys_rseq(&__rseq_abi, sizeof(struct rseq), 0, RSEQ_SIG); + if (!rc) { + assert(rseq_current_cpu_raw() >= 0); + goto end; + } + if (errno != EBUSY) + __rseq_abi.cpu_id = -2; + ret = -1; + refcount--; +end: + signal_restore(oldset); + return ret; +} + +int rseq_unregister_current_thread(void) +{ + int rc, ret = 0; + sigset_t oldset; + + signal_off_save(&oldset); + if (--refcount) + goto end; + rc = sys_rseq(&__rseq_abi, sizeof(struct rseq), + RSEQ_FLAG_UNREGISTER, RSEQ_SIG); + if (!rc) + goto end; + ret = -1; +end: + signal_restore(oldset); + return ret; +} + +int32_t rseq_fallback_current_cpu(void) +{ + int32_t cpu; + + cpu = sched_getcpu(); + if (cpu < 0) { + perror("sched_getcpu()"); + abort(); + } + return cpu; +} diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h new file mode 100644 index 0000000..0a80857 --- /dev/null +++ b/tools/testing/selftests/rseq/rseq.h @@ -0,0 +1,147 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * rseq.h + * + * (C) Copyright 2016-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com> + */ + +#ifndef RSEQ_H +#define RSEQ_H + +#include <stdint.h> +#include <stdbool.h> +#include <pthread.h> +#include <signal.h> +#include <sched.h> +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <sched.h> +#include <linux/rseq.h> + +/* + * Empty code injection macros, override when testing. + * It is important to consider that the ASM injection macros need to be + * fully reentrant (e.g. do not modify the stack). + */ +#ifndef RSEQ_INJECT_ASM +#define RSEQ_INJECT_ASM(n) +#endif + +#ifndef RSEQ_INJECT_C +#define RSEQ_INJECT_C(n) +#endif + +#ifndef RSEQ_INJECT_INPUT +#define RSEQ_INJECT_INPUT +#endif + +#ifndef RSEQ_INJECT_CLOBBER +#define RSEQ_INJECT_CLOBBER +#endif + +#ifndef RSEQ_INJECT_FAILED +#define RSEQ_INJECT_FAILED +#endif + +extern __thread volatile struct rseq __rseq_abi; + +#define rseq_likely(x) __builtin_expect(!!(x), 1) +#define rseq_unlikely(x) __builtin_expect(!!(x), 0) +#define rseq_barrier() __asm__ __volatile__("" : : : "memory") + +#define RSEQ_ACCESS_ONCE(x) (*(__volatile__ __typeof__(x) *)&(x)) +#define RSEQ_WRITE_ONCE(x, v) __extension__ ({ RSEQ_ACCESS_ONCE(x) = (v); }) +#define RSEQ_READ_ONCE(x) RSEQ_ACCESS_ONCE(x) + +#define __rseq_str_1(x) #x +#define __rseq_str(x) __rseq_str_1(x) + +#define rseq_log(fmt, args...) \ + fprintf(stderr, fmt "(in %s() at " __FILE__ ":" __rseq_str(__LINE__)"\n", \ + ## args, __func__) + +#define rseq_bug(fmt, args...) \ + do { \ + rseq_log(fmt, ##args); \ + abort(); \ + } while (0) + +#if defined(__x86_64__) || defined(__i386__) +#include <rseq-x86.h> +#elif defined(__ARMEL__) +#include <rseq-arm.h> +#elif defined(__PPC__) +#include <rseq-ppc.h> +#else +#error unsupported target +#endif + +/* + * Register rseq for the current thread. This needs to be called once + * by any thread which uses restartable sequences, before they start + * using restartable sequences, to ensure restartable sequences + * succeed. A restartable sequence executed from a non-registered + * thread will always fail. + */ +int rseq_register_current_thread(void); + +/* + * Unregister rseq for current thread. + */ +int rseq_unregister_current_thread(void); + +/* + * Restartable sequence fallback for reading the current CPU number. + */ +int32_t rseq_fallback_current_cpu(void); + +/* + * Values returned can be either the current CPU number, -1 (rseq is + * uninitialized), or -2 (rseq initialization has failed). + */ +static inline int32_t rseq_current_cpu_raw(void) +{ + return RSEQ_ACCESS_ONCE(__rseq_abi.cpu_id); +} + +/* + * Returns a possible CPU number, which is typically the current CPU. + * The returned CPU number can be used to prepare for an rseq critical + * section, which will confirm whether the cpu number is indeed the + * current one, and whether rseq is initialized. + * + * The CPU number returned by rseq_cpu_start should always be validated + * by passing it to a rseq asm sequence, or by comparing it to the + * return value of rseq_current_cpu_raw() if the rseq asm sequence + * does not need to be invoked. + */ +static inline uint32_t rseq_cpu_start(void) +{ + return RSEQ_ACCESS_ONCE(__rseq_abi.cpu_id_start); +} + +static inline uint32_t rseq_current_cpu(void) +{ + int32_t cpu; + + cpu = rseq_current_cpu_raw(); + if (rseq_unlikely(cpu < 0)) + cpu = rseq_fallback_current_cpu(); + return cpu; +} + +/* + * rseq_prepare_unload() should be invoked by each thread using rseq_finish*() + * at least once between their last rseq_finish*() and library unload of the + * library defining the rseq critical section (struct rseq_cs). This also + * applies to use of rseq in code generated by JIT: rseq_prepare_unload() + * should be invoked at least once by each thread using rseq_finish*() before + * reclaim of the memory holding the struct rseq_cs. + */ +static inline void rseq_prepare_unload(void) +{ + __rseq_abi.rseq_cs = 0; +} + +#endif /* RSEQ_H_ */ diff --git a/tools/testing/selftests/rseq/run_param_test.sh b/tools/testing/selftests/rseq/run_param_test.sh new file mode 100644 index 0000000..3acd6d7 --- /dev/null +++ b/tools/testing/selftests/rseq/run_param_test.sh @@ -0,0 +1,121 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ or MIT + +EXTRA_ARGS=${@} + +OLDIFS="$IFS" +IFS=$'\n' +TEST_LIST=( + "-T s" + "-T l" + "-T b" + "-T b -M" + "-T m" + "-T m -M" + "-T i" +) + +TEST_NAME=( + "spinlock" + "list" + "buffer" + "buffer with barrier" + "memcpy" + "memcpy with barrier" + "increment" +) +IFS="$OLDIFS" + +REPS=1000 +SLOW_REPS=100 + +function do_tests() +{ + local i=0 + while [ "$i" -lt "${#TEST_LIST[@]}" ]; do + echo "Running test ${TEST_NAME[$i]}" + ./param_test ${TEST_LIST[$i]} -r ${REPS} ${@} ${EXTRA_ARGS} || exit 1 + echo "Running compare-twice test ${TEST_NAME[$i]}" + ./param_test_compare_twice ${TEST_LIST[$i]} -r ${REPS} ${@} ${EXTRA_ARGS} || exit 1 + let "i++" + done +} + +echo "Default parameters" +do_tests + +echo "Loop injection: 10000 loops" + +OLDIFS="$IFS" +IFS=$'\n' +INJECT_LIST=( + "1" + "2" + "3" + "4" + "5" + "6" + "7" + "8" + "9" +) +IFS="$OLDIFS" + +NR_LOOPS=10000 + +i=0 +while [ "$i" -lt "${#INJECT_LIST[@]}" ]; do + echo "Injecting at <${INJECT_LIST[$i]}>" + do_tests -${INJECT_LIST[i]} ${NR_LOOPS} + let "i++" +done +NR_LOOPS= + +function inject_blocking() +{ + OLDIFS="$IFS" + IFS=$'\n' + INJECT_LIST=( + "7" + "8" + "9" + ) + IFS="$OLDIFS" + + NR_LOOPS=-1 + + i=0 + while [ "$i" -lt "${#INJECT_LIST[@]}" ]; do + echo "Injecting at <${INJECT_LIST[$i]}>" + do_tests -${INJECT_LIST[i]} -1 ${@} + let "i++" + done + NR_LOOPS= +} + +echo "Yield injection (25%)" +inject_blocking -m 4 -y + +echo "Yield injection (50%)" +inject_blocking -m 2 -y + +echo "Yield injection (100%)" +inject_blocking -m 1 -y + +echo "Kill injection (25%)" +inject_blocking -m 4 -k + +echo "Kill injection (50%)" +inject_blocking -m 2 -k + +echo "Kill injection (100%)" +inject_blocking -m 1 -k + +echo "Sleep injection (1ms, 25%)" +inject_blocking -m 4 -s 1 + +echo "Sleep injection (1ms, 50%)" +inject_blocking -m 2 -s 1 + +echo "Sleep injection (1ms, 100%)" +inject_blocking -m 1 -s 1 diff --git a/tools/testing/selftests/sparc64/Makefile b/tools/testing/selftests/sparc64/Makefile new file mode 100644 index 0000000..2082eef --- /dev/null +++ b/tools/testing/selftests/sparc64/Makefile @@ -0,0 +1,46 @@ +SUBDIRS := drivers + +TEST_PROGS := run.sh + +.PHONY: all clean + +include ../lib.mk + +all: + @for DIR in $(SUBDIRS); do \ + BUILD_TARGET=$(OUTPUT)/$$DIR; \ + mkdir $$BUILD_TARGET -p; \ + make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ + #SUBDIR test prog name should be in the form: SUBDIR_test.sh \ + TEST=$$DIR"_test.sh"; \ + if [ -e $$DIR/$$TEST ]; then \ + rsync -a $$DIR/$$TEST $$BUILD_TARGET/; \ + fi \ + done + +override define RUN_TESTS + @cd $(OUTPUT); ./run.sh +endef + +override define INSTALL_RULE + mkdir -p $(INSTALL_PATH) + install -t $(INSTALL_PATH) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) + + @for SUBDIR in $(SUBDIRS); do \ + BUILD_TARGET=$(OUTPUT)/$$SUBDIR; \ + mkdir $$BUILD_TARGET -p; \ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$SUBDIR INSTALL_PATH=$(INSTALL_PATH)/$$SUBDIR install; \ + done; +endef + +override define EMIT_TESTS + echo "./run.sh" +endef + +override define CLEAN + @for DIR in $(SUBDIRS); do \ + BUILD_TARGET=$(OUTPUT)/$$DIR; \ + mkdir $$BUILD_TARGET -p; \ + make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ + done +endef diff --git a/tools/testing/selftests/sparc64/drivers/.gitignore b/tools/testing/selftests/sparc64/drivers/.gitignore new file mode 100644 index 0000000..90e835e --- /dev/null +++ b/tools/testing/selftests/sparc64/drivers/.gitignore @@ -0,0 +1 @@ +adi-test diff --git a/tools/testing/selftests/sparc64/drivers/Makefile b/tools/testing/selftests/sparc64/drivers/Makefile new file mode 100644 index 0000000..6264f40 --- /dev/null +++ b/tools/testing/selftests/sparc64/drivers/Makefile @@ -0,0 +1,15 @@ + +INCLUDEDIR := -I. +CFLAGS := $(CFLAGS) $(INCLUDEDIR) -Wall -O2 -g + +TEST_GEN_FILES := adi-test + +all: $(TEST_GEN_FILES) + +$(TEST_GEN_FILES): adi-test.c + +TEST_PROGS := drivers_test.sh + +include ../../lib.mk + +$(OUTPUT)/adi-test: adi-test.c diff --git a/tools/testing/selftests/sparc64/drivers/adi-test.c b/tools/testing/selftests/sparc64/drivers/adi-test.c new file mode 100644 index 0000000..95d93c6 --- /dev/null +++ b/tools/testing/selftests/sparc64/drivers/adi-test.c @@ -0,0 +1,721 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * selftest for sparc64's privileged ADI driver + * + * Author: Tom Hromatka <tom.hromatka@oracle.com> + */ +#include <linux/kernel.h> +#include <errno.h> +#include <fcntl.h> +#include <stdarg.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/syscall.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> + +#include "../../kselftest.h" + +#define DEBUG_LEVEL_1_BIT (0x0001) +#define DEBUG_LEVEL_2_BIT (0x0002) +#define DEBUG_LEVEL_3_BIT (0x0004) +#define DEBUG_LEVEL_4_BIT (0x0008) +#define DEBUG_TIMING_BIT (0x1000) + +#ifndef ARRAY_SIZE +# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +/* bit mask of enabled bits to print */ +#define DEBUG 0x0001 + +#define DEBUG_PRINT_L1(...) debug_print(DEBUG_LEVEL_1_BIT, __VA_ARGS__) +#define DEBUG_PRINT_L2(...) debug_print(DEBUG_LEVEL_2_BIT, __VA_ARGS__) +#define DEBUG_PRINT_L3(...) debug_print(DEBUG_LEVEL_3_BIT, __VA_ARGS__) +#define DEBUG_PRINT_L4(...) debug_print(DEBUG_LEVEL_4_BIT, __VA_ARGS__) +#define DEBUG_PRINT_T(...) debug_print(DEBUG_TIMING_BIT, __VA_ARGS__) + +static void debug_print(int level, const char *s, ...) +{ + va_list args; + + va_start(args, s); + + if (DEBUG & level) + vfprintf(stdout, s, args); + va_end(args); +} + +#ifndef min +#define min(x, y) ((x) < (y) ? x : y) +#endif + +#define RETURN_FROM_TEST(_ret) \ + do { \ + DEBUG_PRINT_L1( \ + "\tTest %s returned %d\n", __func__, _ret); \ + return _ret; \ + } while (0) + +#define ADI_BLKSZ 64 +#define ADI_MAX_VERSION 15 + +#define TEST_STEP_FAILURE(_ret) \ + do { \ + fprintf(stderr, "\tTest step failure: %d at %s:%d\n", \ + _ret, __func__, __LINE__); \ + goto out; \ + } while (0) + +#define RDTICK(_x) \ + asm volatile(" rd %%tick, %0\n" : "=r" (_x)) + +static int random_version(void) +{ + long tick; + + RDTICK(tick); + + return tick % (ADI_MAX_VERSION + 1); +} + +#define MAX_RANGES_SUPPORTED 5 +static const char system_ram_str[] = "System RAM\n"; +static int range_count; +static unsigned long long int start_addr[MAX_RANGES_SUPPORTED]; +static unsigned long long int end_addr[MAX_RANGES_SUPPORTED]; + +struct stats { + char name[16]; + unsigned long total; + unsigned long count; + unsigned long bytes; +}; + +static struct stats read_stats = { + .name = "read", .total = 0, .count = 0, .bytes = 0}; +static struct stats pread_stats = { + .name = "pread", .total = 0, .count = 0, .bytes = 0}; +static struct stats write_stats = { + .name = "write", .total = 0, .count = 0, .bytes = 0}; +static struct stats pwrite_stats = { + .name = "pwrite", .total = 0, .count = 0, .bytes = 0}; +static struct stats seek_stats = { + .name = "seek", .total = 0, .count = 0, .bytes = 0}; + +static void update_stats(struct stats * const ustats, + unsigned long measurement, unsigned long bytes) +{ + ustats->total += measurement; + ustats->bytes += bytes; + ustats->count++; +} + +static void print_ustats(const struct stats * const ustats) +{ + DEBUG_PRINT_L1("%s\t%7d\t%7.0f\t%7.0f\n", + ustats->name, ustats->count, + (float)ustats->total / (float)ustats->count, + (float)ustats->bytes / (float)ustats->count); +} + +static void print_stats(void) +{ + DEBUG_PRINT_L1("\nSyscall\tCall\tAvgTime\tAvgSize\n" + "\tCount\t(ticks)\t(bytes)\n" + "-------------------------------\n"); + + print_ustats(&read_stats); + print_ustats(&pread_stats); + print_ustats(&write_stats); + print_ustats(&pwrite_stats); + print_ustats(&seek_stats); +} + +static int build_memory_map(void) +{ + char line[256]; + FILE *fp; + int i; + + range_count = 0; + + fp = fopen("/proc/iomem", "r"); + if (!fp) { + fprintf(stderr, "/proc/iomem: error %d: %s\n", + errno, strerror(errno)); + return -errno; + } + + while (fgets(line, sizeof(line), fp) != 0) { + if (strstr(line, system_ram_str)) { + char *dash, *end_ptr; + + /* Given a line like this: + * d0400000-10ffaffff : System RAM + * replace the "-" with a space + */ + dash = strstr(line, "-"); + dash[0] = 0x20; + + start_addr[range_count] = strtoull(line, &end_ptr, 16); + end_addr[range_count] = strtoull(end_ptr, NULL, 16); + range_count++; + } + } + + fclose(fp); + + DEBUG_PRINT_L1("RAM Ranges\n"); + for (i = 0; i < range_count; i++) + DEBUG_PRINT_L1("\trange %d: 0x%llx\t- 0x%llx\n", + i, start_addr[i], end_addr[i]); + + if (range_count == 0) { + fprintf(stderr, "No valid address ranges found. Error.\n"); + return -1; + } + + return 0; +} + +static int read_adi(int fd, unsigned char *buf, int buf_sz) +{ + int ret, bytes_read = 0; + long start, end, elapsed_time = 0; + + do { + RDTICK(start); + ret = read(fd, buf + bytes_read, buf_sz - bytes_read); + RDTICK(end); + if (ret < 0) + return -errno; + + elapsed_time += end - start; + update_stats(&read_stats, elapsed_time, buf_sz); + bytes_read += ret; + + } while (bytes_read < buf_sz); + + DEBUG_PRINT_T("\tread elapsed timed = %ld\n", elapsed_time); + DEBUG_PRINT_L3("\tRead %d bytes\n", bytes_read); + + return bytes_read; +} + +static int pread_adi(int fd, unsigned char *buf, + int buf_sz, unsigned long offset) +{ + int ret, i, bytes_read = 0; + unsigned long cur_offset; + long start, end, elapsed_time = 0; + + cur_offset = offset; + do { + RDTICK(start); + ret = pread(fd, buf + bytes_read, buf_sz - bytes_read, + cur_offset); + RDTICK(end); + if (ret < 0) + return -errno; + + elapsed_time += end - start; + update_stats(&pread_stats, elapsed_time, buf_sz); + bytes_read += ret; + cur_offset += ret; + + } while (bytes_read < buf_sz); + + DEBUG_PRINT_T("\tpread elapsed timed = %ld\n", elapsed_time); + DEBUG_PRINT_L3("\tRead %d bytes starting at offset 0x%lx\n", + bytes_read, offset); + for (i = 0; i < bytes_read; i++) + DEBUG_PRINT_L4("\t\t0x%lx\t%d\n", offset + i, buf[i]); + + return bytes_read; +} + +static int write_adi(int fd, const unsigned char * const buf, int buf_sz) +{ + int ret, bytes_written = 0; + long start, end, elapsed_time = 0; + + do { + RDTICK(start); + ret = write(fd, buf + bytes_written, buf_sz - bytes_written); + RDTICK(end); + if (ret < 0) + return -errno; + + elapsed_time += (end - start); + update_stats(&write_stats, elapsed_time, buf_sz); + bytes_written += ret; + } while (bytes_written < buf_sz); + + DEBUG_PRINT_T("\twrite elapsed timed = %ld\n", elapsed_time); + DEBUG_PRINT_L3("\tWrote %d of %d bytes\n", bytes_written, buf_sz); + + return bytes_written; +} + +static int pwrite_adi(int fd, const unsigned char * const buf, + int buf_sz, unsigned long offset) +{ + int ret, bytes_written = 0; + unsigned long cur_offset; + long start, end, elapsed_time = 0; + + cur_offset = offset; + + do { + RDTICK(start); + ret = pwrite(fd, buf + bytes_written, + buf_sz - bytes_written, cur_offset); + RDTICK(end); + if (ret < 0) { + fprintf(stderr, "pwrite(): error %d: %s\n", + errno, strerror(errno)); + return -errno; + } + + elapsed_time += (end - start); + update_stats(&pwrite_stats, elapsed_time, buf_sz); + bytes_written += ret; + cur_offset += ret; + + } while (bytes_written < buf_sz); + + DEBUG_PRINT_T("\tpwrite elapsed timed = %ld\n", elapsed_time); + DEBUG_PRINT_L3("\tWrote %d of %d bytes starting at address 0x%lx\n", + bytes_written, buf_sz, offset); + + return bytes_written; +} + +static off_t seek_adi(int fd, off_t offset, int whence) +{ + long start, end; + off_t ret; + + RDTICK(start); + ret = lseek(fd, offset, whence); + RDTICK(end); + DEBUG_PRINT_L2("\tlseek ret = 0x%llx\n", ret); + if (ret < 0) + goto out; + + DEBUG_PRINT_T("\tlseek elapsed timed = %ld\n", end - start); + update_stats(&seek_stats, end - start, 0); + +out: + (void)lseek(fd, 0, SEEK_END); + return ret; +} + +static int test0_prpw_aligned_1byte(int fd) +{ + /* somewhat arbitrarily chosen address */ + unsigned long paddr = + (end_addr[range_count - 1] - 0x1000) & ~(ADI_BLKSZ - 1); + unsigned char version[1], expected_version; + loff_t offset; + int ret; + + version[0] = random_version(); + expected_version = version[0]; + + offset = paddr / ADI_BLKSZ; + + ret = pwrite_adi(fd, version, sizeof(version), offset); + if (ret != sizeof(version)) + TEST_STEP_FAILURE(ret); + + ret = pread_adi(fd, version, sizeof(version), offset); + if (ret != sizeof(version)) + TEST_STEP_FAILURE(ret); + + if (expected_version != version[0]) { + DEBUG_PRINT_L2("\tExpected version %d but read version %d\n", + expected_version, version[0]); + TEST_STEP_FAILURE(-expected_version); + } + + ret = 0; +out: + RETURN_FROM_TEST(ret); +} + +#define TEST1_VERSION_SZ 4096 +static int test1_prpw_aligned_4096bytes(int fd) +{ + /* somewhat arbitrarily chosen address */ + unsigned long paddr = + (end_addr[range_count - 1] - 0x6000) & ~(ADI_BLKSZ - 1); + unsigned char version[TEST1_VERSION_SZ], + expected_version[TEST1_VERSION_SZ]; + loff_t offset; + int ret, i; + + for (i = 0; i < TEST1_VERSION_SZ; i++) { + version[i] = random_version(); + expected_version[i] = version[i]; + } + + offset = paddr / ADI_BLKSZ; + + ret = pwrite_adi(fd, version, sizeof(version), offset); + if (ret != sizeof(version)) + TEST_STEP_FAILURE(ret); + + ret = pread_adi(fd, version, sizeof(version), offset); + if (ret != sizeof(version)) + TEST_STEP_FAILURE(ret); + + for (i = 0; i < TEST1_VERSION_SZ; i++) { + if (expected_version[i] != version[i]) { + DEBUG_PRINT_L2( + "\tExpected version %d but read version %d\n", + expected_version, version[0]); + TEST_STEP_FAILURE(-expected_version[i]); + } + } + + ret = 0; +out: + RETURN_FROM_TEST(ret); +} + +#define TEST2_VERSION_SZ 10327 +static int test2_prpw_aligned_10327bytes(int fd) +{ + /* somewhat arbitrarily chosen address */ + unsigned long paddr = + (start_addr[0] + 0x6000) & ~(ADI_BLKSZ - 1); + unsigned char version[TEST2_VERSION_SZ], + expected_version[TEST2_VERSION_SZ]; + loff_t offset; + int ret, i; + + for (i = 0; i < TEST2_VERSION_SZ; i++) { + version[i] = random_version(); + expected_version[i] = version[i]; + } + + offset = paddr / ADI_BLKSZ; + + ret = pwrite_adi(fd, version, sizeof(version), offset); + if (ret != sizeof(version)) + TEST_STEP_FAILURE(ret); + + ret = pread_adi(fd, version, sizeof(version), offset); + if (ret != sizeof(version)) + TEST_STEP_FAILURE(ret); + + for (i = 0; i < TEST2_VERSION_SZ; i++) { + if (expected_version[i] != version[i]) { + DEBUG_PRINT_L2( + "\tExpected version %d but read version %d\n", + expected_version, version[0]); + TEST_STEP_FAILURE(-expected_version[i]); + } + } + + ret = 0; +out: + RETURN_FROM_TEST(ret); +} + +#define TEST3_VERSION_SZ 12541 +static int test3_prpw_unaligned_12541bytes(int fd) +{ + /* somewhat arbitrarily chosen address */ + unsigned long paddr = + ((start_addr[0] + 0xC000) & ~(ADI_BLKSZ - 1)) + 17; + unsigned char version[TEST3_VERSION_SZ], + expected_version[TEST3_VERSION_SZ]; + loff_t offset; + int ret, i; + + for (i = 0; i < TEST3_VERSION_SZ; i++) { + version[i] = random_version(); + expected_version[i] = version[i]; + } + + offset = paddr / ADI_BLKSZ; + + ret = pwrite_adi(fd, version, sizeof(version), offset); + if (ret != sizeof(version)) + TEST_STEP_FAILURE(ret); + + ret = pread_adi(fd, version, sizeof(version), offset); + if (ret != sizeof(version)) + TEST_STEP_FAILURE(ret); + + for (i = 0; i < TEST3_VERSION_SZ; i++) { + if (expected_version[i] != version[i]) { + DEBUG_PRINT_L2( + "\tExpected version %d but read version %d\n", + expected_version, version[0]); + TEST_STEP_FAILURE(-expected_version[i]); + } + } + + ret = 0; +out: + RETURN_FROM_TEST(ret); +} + +static int test4_lseek(int fd) +{ +#define OFFSET_ADD (0x100) +#define OFFSET_SUBTRACT (0xFFFFFFF000000000) + + off_t offset_out, offset_in; + int ret; + + + offset_in = 0x123456789abcdef0; + offset_out = seek_adi(fd, offset_in, SEEK_SET); + if (offset_out != offset_in) { + ret = -1; + TEST_STEP_FAILURE(ret); + } + + /* seek to the current offset. this should return EINVAL */ + offset_out = seek_adi(fd, offset_in, SEEK_SET); + if (offset_out < 0 && errno == EINVAL) + DEBUG_PRINT_L2( + "\tSEEK_SET failed as designed. Not an error\n"); + else { + ret = -2; + TEST_STEP_FAILURE(ret); + } + + offset_out = seek_adi(fd, 0, SEEK_CUR); + if (offset_out != offset_in) { + ret = -3; + TEST_STEP_FAILURE(ret); + } + + offset_out = seek_adi(fd, OFFSET_ADD, SEEK_CUR); + if (offset_out != (offset_in + OFFSET_ADD)) { + ret = -4; + TEST_STEP_FAILURE(ret); + } + + offset_out = seek_adi(fd, OFFSET_SUBTRACT, SEEK_CUR); + if (offset_out != (offset_in + OFFSET_ADD + OFFSET_SUBTRACT)) { + ret = -5; + TEST_STEP_FAILURE(ret); + } + + ret = 0; +out: + RETURN_FROM_TEST(ret); +} + +static int test5_rw_aligned_1byte(int fd) +{ + /* somewhat arbitrarily chosen address */ + unsigned long paddr = + (end_addr[range_count - 1] - 0xF000) & ~(ADI_BLKSZ - 1); + unsigned char version, expected_version; + loff_t offset; + off_t oret; + int ret; + + offset = paddr / ADI_BLKSZ; + version = expected_version = random_version(); + + oret = seek_adi(fd, offset, SEEK_SET); + if (oret != offset) { + ret = -1; + TEST_STEP_FAILURE(ret); + } + + ret = write_adi(fd, &version, sizeof(version)); + if (ret != sizeof(version)) + TEST_STEP_FAILURE(ret); + + oret = seek_adi(fd, offset, SEEK_SET); + if (oret != offset) { + ret = -1; + TEST_STEP_FAILURE(ret); + } + + ret = read_adi(fd, &version, sizeof(version)); + if (ret != sizeof(version)) + TEST_STEP_FAILURE(ret); + + if (expected_version != version) { + DEBUG_PRINT_L2("\tExpected version %d but read version %d\n", + expected_version, version); + TEST_STEP_FAILURE(-expected_version); + } + + ret = 0; +out: + RETURN_FROM_TEST(ret); +} + +#define TEST6_VERSION_SZ 9434 +static int test6_rw_aligned_9434bytes(int fd) +{ + /* somewhat arbitrarily chosen address */ + unsigned long paddr = + (end_addr[range_count - 1] - 0x5F000) & ~(ADI_BLKSZ - 1); + unsigned char version[TEST6_VERSION_SZ], + expected_version[TEST6_VERSION_SZ]; + loff_t offset; + off_t oret; + int ret, i; + + offset = paddr / ADI_BLKSZ; + for (i = 0; i < TEST6_VERSION_SZ; i++) + version[i] = expected_version[i] = random_version(); + + oret = seek_adi(fd, offset, SEEK_SET); + if (oret != offset) { + ret = -1; + TEST_STEP_FAILURE(ret); + } + + ret = write_adi(fd, version, sizeof(version)); + if (ret != sizeof(version)) + TEST_STEP_FAILURE(ret); + + memset(version, 0, TEST6_VERSION_SZ); + + oret = seek_adi(fd, offset, SEEK_SET); + if (oret != offset) { + ret = -1; + TEST_STEP_FAILURE(ret); + } + + ret = read_adi(fd, version, sizeof(version)); + if (ret != sizeof(version)) + TEST_STEP_FAILURE(ret); + + for (i = 0; i < TEST6_VERSION_SZ; i++) { + if (expected_version[i] != version[i]) { + DEBUG_PRINT_L2( + "\tExpected version %d but read version %d\n", + expected_version[i], version[i]); + TEST_STEP_FAILURE(-expected_version[i]); + } + } + + ret = 0; +out: + RETURN_FROM_TEST(ret); +} + +#define TEST7_VERSION_SZ 14963 +static int test7_rw_aligned_14963bytes(int fd) +{ + /* somewhat arbitrarily chosen address */ + unsigned long paddr = + ((start_addr[range_count - 1] + 0xF000) & ~(ADI_BLKSZ - 1)) + 39; + unsigned char version[TEST7_VERSION_SZ], + expected_version[TEST7_VERSION_SZ]; + loff_t offset; + off_t oret; + int ret, i; + + offset = paddr / ADI_BLKSZ; + for (i = 0; i < TEST7_VERSION_SZ; i++) { + version[i] = random_version(); + expected_version[i] = version[i]; + } + + oret = seek_adi(fd, offset, SEEK_SET); + if (oret != offset) { + ret = -1; + TEST_STEP_FAILURE(ret); + } + + ret = write_adi(fd, version, sizeof(version)); + if (ret != sizeof(version)) + TEST_STEP_FAILURE(ret); + + memset(version, 0, TEST7_VERSION_SZ); + + oret = seek_adi(fd, offset, SEEK_SET); + if (oret != offset) { + ret = -1; + TEST_STEP_FAILURE(ret); + } + + ret = read_adi(fd, version, sizeof(version)); + if (ret != sizeof(version)) + TEST_STEP_FAILURE(ret); + + for (i = 0; i < TEST7_VERSION_SZ; i++) { + if (expected_version[i] != version[i]) { + DEBUG_PRINT_L2( + "\tExpected version %d but read version %d\n", + expected_version[i], version[i]); + TEST_STEP_FAILURE(-expected_version[i]); + } + + paddr += ADI_BLKSZ; + } + + ret = 0; +out: + RETURN_FROM_TEST(ret); +} + +static int (*tests[])(int fd) = { + test0_prpw_aligned_1byte, + test1_prpw_aligned_4096bytes, + test2_prpw_aligned_10327bytes, + test3_prpw_unaligned_12541bytes, + test4_lseek, + test5_rw_aligned_1byte, + test6_rw_aligned_9434bytes, + test7_rw_aligned_14963bytes, +}; +#define TEST_COUNT ARRAY_SIZE(tests) + +int main(int argc, char *argv[]) +{ + int fd, ret, test; + + ret = build_memory_map(); + if (ret < 0) + return ret; + + fd = open("/dev/adi", O_RDWR); + if (fd < 0) { + fprintf(stderr, "open: error %d: %s\n", + errno, strerror(errno)); + return -errno; + } + + for (test = 0; test < TEST_COUNT; test++) { + DEBUG_PRINT_L1("Running test #%d\n", test); + + ret = (*tests[test])(fd); + if (ret != 0) + ksft_test_result_fail("Test #%d failed: error %d\n", + test, ret); + else + ksft_test_result_pass("Test #%d passed\n", test); + } + + print_stats(); + close(fd); + + if (ksft_get_fail_cnt() > 0) + ksft_exit_fail(); + else + ksft_exit_pass(); + + /* it's impossible to get here, but the compiler throws a warning + * about control reaching the end of non-void function. bah. + */ + return 0; +} diff --git a/tools/testing/selftests/sparc64/drivers/drivers_test.sh b/tools/testing/selftests/sparc64/drivers/drivers_test.sh new file mode 100755 index 0000000..6d08273 --- /dev/null +++ b/tools/testing/selftests/sparc64/drivers/drivers_test.sh @@ -0,0 +1,30 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +SRC_TREE=../../../../ + +test_run() +{ + if [ -f ${SRC_TREE}/drivers/char/adi.ko ]; then + insmod ${SRC_TREE}/drivers/char/adi.ko 2> /dev/null + if [ $? -ne 0 ]; then + rc=1 + fi + else + # Use modprobe dry run to check for missing adi module + if ! /sbin/modprobe -q -n adi; then + echo "adi: [SKIP]" + elif /sbin/modprobe -q adi; then + echo "adi: ok" + else + echo "adi: [FAIL]" + rc=1 + fi + fi + ./adi-test + rmmod adi 2> /dev/null +} + +rc=0 +test_run +exit $rc diff --git a/tools/testing/selftests/sparc64/run.sh b/tools/testing/selftests/sparc64/run.sh new file mode 100755 index 0000000..38ad61f --- /dev/null +++ b/tools/testing/selftests/sparc64/run.sh @@ -0,0 +1,3 @@ +#!/bin/sh + +(cd drivers; ./drivers_test.sh) diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json b/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json index 93cf8fe..3a2f51f 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json @@ -398,13 +398,83 @@ 255 ] ], - "cmdUnderTest": "for i in `seq 1 32`; do cmd=\"action csum tcp continue index $i \"; args=\"$args$cmd\"; done && $TC actions add $args", - "expExitCode": "255", + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum tcp continue index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"", + "expExitCode": "0", "verifyCmd": "$TC actions ls action csum", "matchPattern": "^[ \t]+index [0-9]* ref", "matchCount": "32", "teardown": [ "$TC actions flush action csum" ] + }, + { + "id": "b4e9", + "name": "Delete batch of 32 csum actions", + "category": [ + "actions", + "csum" + ], + "setup": [ + [ + "$TC actions flush action csum", + 0, + 1, + 255 + ], + "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum tcp continue index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"" + ], + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions del \\$args\"", + "expExitCode": "0", + "verifyCmd": "$TC actions list action csum", + "matchPattern": "^[ \t]+index [0-9]+ ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "0015", + "name": "Add batch of 32 csum tcp actions with large cookies", + "category": [ + "actions", + "csum" + ], + "setup": [ + [ + "$TC actions flush action csum", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum tcp continue index \\$i cookie aaabbbcccdddeee \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action csum", + "matchPattern": "^[ \t]+index [0-9]* ref", + "matchCount": "32", + "teardown": [ + "$TC actions flush action csum" + ] + }, + { + "id": "989e", + "name": "Delete batch of 32 csum actions with large cookies", + "category": [ + "actions", + "csum" + ], + "setup": [ + [ + "$TC actions flush action csum", + 0, + 1, + 255 + ], + "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum tcp continue index \\$i cookie aaabbbcccdddeee \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"" + ], + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions del \\$args\"", + "expExitCode": "0", + "verifyCmd": "$TC actions list action csum", + "matchPattern": "^[ \t]+index [0-9]+ ref", + "matchCount": "0", + "teardown": [] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json index 9f34f07..de97e4f 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json @@ -1,7 +1,7 @@ [ { - "id": "a568", - "name": "Add action with ife type", + "id": "7682", + "name": "Create valid ife encode action with mark and pass control", "category": [ "actions", "ife" @@ -12,21 +12,782 @@ 0, 1, 255 - ], - "$TC actions add action ife encode type 0xDEAD index 1" + ] ], - "cmdUnderTest": "$TC actions get action ife index 1", + "cmdUnderTest": "$TC actions add action ife encode allow mark pass index 2", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 2", + "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*allow mark.*index 2", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "ef47", + "name": "Create valid ife encode action with mark and pipe control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use mark 10 pipe index 2", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 2", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*use mark.*index 2", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "df43", + "name": "Create valid ife encode action with mark and continue control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow mark continue index 2", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 2", + "matchPattern": "action order [0-9]*: ife encode action continue.*type 0xED3E.*allow mark.*index 2", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "e4cf", + "name": "Create valid ife encode action with mark and drop control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use mark 789 drop index 2", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 2", + "matchPattern": "action order [0-9]*: ife encode action drop.*type 0xED3E.*use mark 789.*index 2", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "ccba", + "name": "Create valid ife encode action with mark and reclassify control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use mark 656768 reclassify index 2", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 2", + "matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xED3E.*use mark 656768.*index 2", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "a1cf", + "name": "Create valid ife encode action with mark and jump control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use mark 65 jump 1 index 2", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 2", + "matchPattern": "action order [0-9]*: ife encode action jump 1.*type 0xED3E.*use mark 65.*index 2", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "cb3d", + "name": "Create valid ife encode action with mark value at 32-bit maximum", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use mark 4294967295 reclassify index 90", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 90", + "matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xED3E.*use mark 4294967295.*index 90", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "1efb", + "name": "Create ife encode action with mark value exceeding 32-bit maximum", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use mark 4294967295999 pipe index 90", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 90", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*use mark 4294967295999.*index 90", + "matchCount": "0", + "teardown": [] + }, + { + "id": "95ed", + "name": "Create valid ife encode action with prio and pass control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow prio pass index 9", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 9", + "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*allow prio.*index 9", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "aa17", + "name": "Create valid ife encode action with prio and pipe control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use prio 7 pipe index 9", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 9", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*use prio 7.*index 9", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "74c7", + "name": "Create valid ife encode action with prio and continue control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use prio 3 continue index 9", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 9", + "matchPattern": "action order [0-9]*: ife encode action continue.*type 0xED3E.*use prio 3.*index 9", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "7a97", + "name": "Create valid ife encode action with prio and drop control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow prio drop index 9", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 9", + "matchPattern": "action order [0-9]*: ife encode action drop.*type 0xED3E.*allow prio.*index 9", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "f66b", + "name": "Create valid ife encode action with prio and reclassify control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use prio 998877 reclassify index 9", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 9", + "matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xED3E.*use prio 998877.*index 9", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "3056", + "name": "Create valid ife encode action with prio and jump control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use prio 998877 jump 10 index 9", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 9", + "matchPattern": "action order [0-9]*: ife encode action jump 10.*type 0xED3E.*use prio 998877.*index 9", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "7dd3", + "name": "Create valid ife encode action with prio value at 32-bit maximum", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use prio 4294967295 reclassify index 99", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 99", + "matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xED3E.*use prio 4294967295.*index 99", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "2ca1", + "name": "Create ife encode action with prio value exceeding 32-bit maximum", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use prio 4294967298 pipe index 99", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 99", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*use prio 4294967298.*index 99", + "matchCount": "0", + "teardown": [] + }, + { + "id": "05bb", + "name": "Create valid ife encode action with tcindex and pass control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow tcindex pass index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*allow tcindex.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "ce65", + "name": "Create valid ife encode action with tcindex and pipe control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use tcindex 111 pipe index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*use tcindex 111.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "09cd", + "name": "Create valid ife encode action with tcindex and continue control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use tcindex 1 continue index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife encode action continue.*type 0xED3E.*use tcindex 1.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "8eb5", + "name": "Create valid ife encode action with tcindex and continue control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use tcindex 1 continue index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife encode action continue.*type 0xED3E.*use tcindex 1.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "451a", + "name": "Create valid ife encode action with tcindex and drop control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow tcindex drop index 77", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 77", + "matchPattern": "action order [0-9]*: ife encode action drop.*type 0xED3E.*allow tcindex.*index 77", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "d76c", + "name": "Create valid ife encode action with tcindex and reclassify control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow tcindex reclassify index 77", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 77", + "matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xED3E.*allow tcindex.*index 77", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "e731", + "name": "Create valid ife encode action with tcindex and jump control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow tcindex jump 999 index 77", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 77", + "matchPattern": "action order [0-9]*: ife encode action jump 999.*type 0xED3E.*allow tcindex.*index 77", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "b7b8", + "name": "Create valid ife encode action with tcindex value at 16-bit maximum", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use tcindex 65535 pass index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*use tcindex 65535.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "d0d8", + "name": "Create ife encode action with tcindex value exceeding 16-bit maximum", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use tcindex 65539 pipe index 1", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*use tcindex 65539.*index 1", + "matchCount": "0", + "teardown": [] + }, + { + "id": "2a9c", + "name": "Create valid ife encode action with mac src parameter", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow mark src 00:11:22:33:44:55 pipe index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*allow mark src 00:11:22:33:44:55.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "cf5c", + "name": "Create valid ife encode action with mac dst parameter", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use prio 9876 dst 00:11:22:33:44:55 reclassify index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xED3E.*use prio 9876 dst 00:11:22:33:44:55.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "2353", + "name": "Create valid ife encode action with mac src and mac dst parameters", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow tcindex src 00:aa:bb:cc:dd:ee dst 00:11:22:33:44:55 pass index 11", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 11", + "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*allow tcindex dst 00:11:22:33:44:55 src 00:aa:bb:cc:dd:ee .*index 11", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "552c", + "name": "Create valid ife encode action with mark and type parameters", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use mark 7 type 0xfefe pass index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xFEFE.*use mark 7.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "0421", + "name": "Create valid ife encode action with prio and type parameters", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use prio 444 type 0xabba pipe index 21", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 21", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xABBA.*use prio 444.*index 21", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "4017", + "name": "Create valid ife encode action with tcindex and type parameters", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use tcindex 5000 type 0xabcd reclassify index 21", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 21", + "matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xABCD.*use tcindex 5000.*index 21", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "fac3", + "name": "Create valid ife encode action with index at 32-bit maximnum", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow mark pass index 4294967295", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 4294967295", + "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*allow mark.*index 4294967295", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "7c25", + "name": "Create valid ife decode action with pass control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife decode pass index 1", "expExitCode": "0", "verifyCmd": "$TC actions get action ife index 1", - "matchPattern": "type 0xDEAD", + "matchPattern": "action order [0-9]*: ife decode action pass.*type 0x0.*allow mark allow tcindex allow prio.*index 1", "matchCount": "1", "teardown": [ "$TC actions flush action ife" ] }, { - "id": "b983", - "name": "Add action without ife type", + "id": "dccb", + "name": "Create valid ife decode action with pipe control", "category": [ "actions", "ife" @@ -37,16 +798,267 @@ 0, 1, 255 - ], - "$TC actions add action ife encode index 1" + ] ], - "cmdUnderTest": "$TC actions get action ife index 1", + "cmdUnderTest": "$TC actions add action ife decode pipe index 1", "expExitCode": "0", "verifyCmd": "$TC actions get action ife index 1", - "matchPattern": "type 0xED3E", + "matchPattern": "action order [0-9]*: ife decode action pipe.*type 0x0.*allow mark allow tcindex allow prio.*index 1", "matchCount": "1", "teardown": [ "$TC actions flush action ife" ] + }, + { + "id": "7bb9", + "name": "Create valid ife decode action with continue control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife decode continue index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife decode action continue.*type 0x0.*allow mark allow tcindex allow prio.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "d9ad", + "name": "Create valid ife decode action with drop control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife decode drop index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife decode action drop.*type 0x0.*allow mark allow tcindex allow prio.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "219f", + "name": "Create valid ife decode action with reclassify control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife decode reclassify index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife decode action reclassify.*type 0x0.*allow mark allow tcindex allow prio.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "8f44", + "name": "Create valid ife decode action with jump control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife decode jump 10 index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife decode action jump 10.*type 0x0.*allow mark allow tcindex allow prio.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "56cf", + "name": "Create ife encode action with index exceeding 32-bit maximum", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow mark pass index 4294967295999", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 4294967295999", + "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*allow mark.*index 4294967295999", + "matchCount": "0", + "teardown": [] + }, + { + "id": "ee94", + "name": "Create ife encode action with invalid control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow mark kuka index 4", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 4", + "matchPattern": "action order [0-9]*: ife encode action kuka.*type 0xED3E.*allow mark.*index 4", + "matchCount": "0", + "teardown": [] + }, + { + "id": "b330", + "name": "Create ife encode action with cookie", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow prio pipe index 4 cookie aabbccddeeff112233445566778800a1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 4", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*allow prio.*index 4.*cookie aabbccddeeff112233445566778800a1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "bbc0", + "name": "Create ife encode action with invalid argument", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow foo pipe index 4", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 4", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*allow foo.*index 4", + "matchCount": "0", + "teardown": [] + }, + { + "id": "d54a", + "name": "Create ife encode action with invalid type argument", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow prio type 70000 pipe index 4", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 4", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0x11170.*allow prio.*index 4", + "matchCount": "0", + "teardown": [] + }, + { + "id": "7ee0", + "name": "Create ife encode action with invalid mac src argument", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow prio src 00:11:22:33:44:pp pipe index 4", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 4", + "matchPattern": "action order [0-9]*: ife encode action pipe.*allow prio.*index 4", + "matchCount": "0", + "teardown": [] + }, + { + "id": "0a7d", + "name": "Create ife encode action with invalid mac dst argument", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow prio dst 00.111-22:33:44:aa pipe index 4", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 4", + "matchPattern": "action order [0-9]*: ife encode action pipe.*allow prio.*index 4", + "matchCount": "0", + "teardown": [] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json index 443c9b3..6e4edfa 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json @@ -340,7 +340,7 @@ }, { "id": "8b69", - "name": "Add mirred mirror action with maximum index", + "name": "Add mirred mirror action with index at 32-bit maximum", "category": [ "actions", "mirred" @@ -363,6 +363,28 @@ ] }, { + "id": "3f66", + "name": "Add mirred mirror action with index exceeding 32-bit maximum", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action mirred ingress mirror dev lo pipe index 429496729555", + "expExitCode": "255", + "verifyCmd": "$TC actions get action mirred index 429496729555", + "matchPattern": "action order [0-9]*: mirred \\(Ingress Mirror to device lo\\) pipe.*index 429496729555", + "matchCount": "0", + "teardown": [] + }, + { "id": "a70e", "name": "Delete mirred mirror action", "category": [ diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json index 38d85a1..f03763d 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json @@ -401,11 +401,11 @@ ], "cmdUnderTest": "$TC actions add action police rate 10mbit burst 10k index 4294967295", "expExitCode": "0", - "verifyCmd": "$TC actions get action mirred index 4294967295", + "verifyCmd": "$TC actions get action police index 4294967295", "matchPattern": "action order [0-9]*: police 0xffffffff rate 10Mbit burst 10Kb mtu 2Kb", "matchCount": "1", "teardown": [ - "$TC actions flush action mirred" + "$TC actions flush action police" ] }, { diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json b/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json new file mode 100644 index 0000000..3aca33c --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json @@ -0,0 +1,588 @@ +[ + { + "id": "9784", + "name": "Add valid sample action with mandatory arguments", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 10 group 1 index 2", + "expExitCode": "0", + "verifyCmd": "$TC actions get action sample index 2", + "matchPattern": "action order [0-9]+: sample rate 1/10 group 1.*index 2 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "5c91", + "name": "Add valid sample action with mandatory arguments and continue control action", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 700 group 2 continue index 2", + "expExitCode": "0", + "verifyCmd": "$TC actions get action sample index 2", + "matchPattern": "action order [0-9]+: sample rate 1/700 group 2 continue.*index 2 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "334b", + "name": "Add valid sample action with mandatory arguments and drop control action", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 10000 group 11 drop index 22", + "expExitCode": "0", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample rate 1/10000 group 11 drop.*index 22 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "da69", + "name": "Add valid sample action with mandatory arguments and reclassify control action", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 20000 group 72 reclassify index 100", + "expExitCode": "0", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample rate 1/20000 group 72 reclassify.*index 100 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "13ce", + "name": "Add valid sample action with mandatory arguments and pipe control action", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 20 group 2 pipe index 100", + "expExitCode": "0", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample rate 1/20 group 2 pipe.*index 100 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "1886", + "name": "Add valid sample action with mandatory arguments and jump control action", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 700 group 25 jump 4 index 200", + "expExitCode": "0", + "verifyCmd": "$TC actions get action sample index 200", + "matchPattern": "action order [0-9]+: sample rate 1/700 group 25 jump 4.*index 200 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "b6d4", + "name": "Add sample action with mandatory arguments and invalid control action", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 200000 group 52 foo index 1", + "expExitCode": "255", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample rate 1/200000 group 52 foo.*index 1 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "a874", + "name": "Add invalid sample action without mandatory arguments", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample index 1", + "expExitCode": "255", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample.*index 1 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "ac01", + "name": "Add invalid sample action without mandatory argument rate", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample group 10 index 1", + "expExitCode": "255", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample.*group 10.*index 1 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "4203", + "name": "Add invalid sample action without mandatory argument group", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 100 index 10", + "expExitCode": "255", + "verifyCmd": "$TC actions get action sample index 10", + "matchPattern": "action order [0-9]+: sample rate 1/100.*index 10 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "14a7", + "name": "Add invalid sample action without mandatory argument group", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 100 index 10", + "expExitCode": "255", + "verifyCmd": "$TC actions get action sample index 10", + "matchPattern": "action order [0-9]+: sample rate 1/100.*index 10 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "8f2e", + "name": "Add valid sample action with trunc argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 1024 group 4 trunc 1024 index 10", + "expExitCode": "0", + "verifyCmd": "$TC actions get action sample index 10", + "matchPattern": "action order [0-9]+: sample rate 1/1024 group 4 trunc_size 1024 pipe.*index 10 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "45f8", + "name": "Add sample action with maximum rate argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 4294967295 group 4 index 10", + "expExitCode": "0", + "verifyCmd": "$TC actions get action sample index 10", + "matchPattern": "action order [0-9]+: sample rate 1/4294967295 group 4 pipe.*index 10 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "ad0c", + "name": "Add sample action with maximum trunc argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 16000 group 4 trunc 4294967295 index 10", + "expExitCode": "0", + "verifyCmd": "$TC actions get action sample index 10", + "matchPattern": "action order [0-9]+: sample rate 1/16000 group 4 trunc_size 4294967295 pipe.*index 10 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "83a9", + "name": "Add sample action with maximum group argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 4294 group 4294967295 index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action sample index 1", + "matchPattern": "action order [0-9]+: sample rate 1/4294 group 4294967295 pipe.*index 1 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "ed27", + "name": "Add sample action with invalid rate argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 4294967296 group 4 index 10", + "expExitCode": "255", + "verifyCmd": "$TC actions get action sample index 10", + "matchPattern": "action order [0-9]+: sample rate 1/4294967296 group 4 pipe.*index 10 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "2eae", + "name": "Add sample action with invalid group argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 4098 group 5294967299 continue index 1", + "expExitCode": "255", + "verifyCmd": "$TC actions get action sample index 1", + "matchPattern": "action order [0-9]+: sample rate 1/4098 group 5294967299 continue.*index 1 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "6ff3", + "name": "Add sample action with invalid trunc size", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 1024 group 4 trunc 112233445566 index 11", + "expExitCode": "255", + "verifyCmd": "$TC actions get action sample index 11", + "matchPattern": "action order [0-9]+: sample rate 1/1024 group 4 trunc_size 112233445566.*index 11 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "2b2a", + "name": "Add sample action with invalid index", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 1024 group 4 index 5294967299", + "expExitCode": "255", + "verifyCmd": "$TC actions get action sample index 5294967299", + "matchPattern": "action order [0-9]+: sample rate 1/1024 group 4 pipe.*index 5294967299 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "dee2", + "name": "Add sample action with maximum allowed index", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 1024 group 4 index 4294967295", + "expExitCode": "0", + "verifyCmd": "$TC actions get action sample index 4294967295", + "matchPattern": "action order [0-9]+: sample rate 1/1024 group 4 pipe.*index 4294967295 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "560e", + "name": "Add sample action with cookie", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 1024 group 4 index 45 cookie aabbccdd", + "expExitCode": "0", + "verifyCmd": "$TC actions get action sample index 45", + "matchPattern": "action order [0-9]+: sample rate 1/1024 group 4 pipe.*index 45.*cookie aabbccdd", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "704a", + "name": "Replace existing sample action with new rate argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ], + "$TC actions add action sample rate 1024 group 4 index 4" + ], + "cmdUnderTest": "$TC actions replace action sample rate 2048 group 4 index 4", + "expExitCode": "0", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample rate 1/2048 group 4 pipe.*index 4", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "60eb", + "name": "Replace existing sample action with new group argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ], + "$TC actions add action sample rate 1024 group 4 index 4" + ], + "cmdUnderTest": "$TC actions replace action sample rate 1024 group 7 index 4", + "expExitCode": "0", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample rate 1/1024 group 7 pipe.*index 4", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "2cce", + "name": "Replace existing sample action with new trunc argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ], + "$TC actions add action sample rate 1024 group 4 trunc 48 index 4" + ], + "cmdUnderTest": "$TC actions replace action sample rate 1024 group 7 trunc 64 index 4", + "expExitCode": "0", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample rate 1/1024 group 7 trunc_size 64 pipe.*index 4", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "59d1", + "name": "Replace existing sample action with new control argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ], + "$TC actions add action sample rate 1024 group 4 reclassify index 4" + ], + "cmdUnderTest": "$TC actions replace action sample rate 1024 group 7 pipe index 4", + "expExitCode": "0", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample rate 1/1024 group 7 pipe.*index 4", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + } +] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json b/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json index 4510ddf..69ea09e 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json @@ -1,7 +1,7 @@ [ { "id": "6f5a", - "name": "Add vlan pop action", + "name": "Add vlan pop action with pipe opcode", "category": [ "actions", "vlan" @@ -14,18 +14,18 @@ 255 ] ], - "cmdUnderTest": "$TC actions add action vlan pop index 8", + "cmdUnderTest": "$TC actions add action vlan pop pipe index 8", "expExitCode": "0", "verifyCmd": "$TC actions list action vlan", - "matchPattern": "action order [0-9]+: vlan.*pop.*index 8 ref", + "matchPattern": "action order [0-9]+: vlan.*pop.*pipe.*index 8 ref", "matchCount": "1", "teardown": [ "$TC actions flush action vlan" ] }, { - "id": "ee6f", - "name": "Add vlan pop action with large index", + "id": "df35", + "name": "Add vlan pop action with pass opcode", "category": [ "actions", "vlan" @@ -38,10 +38,82 @@ 255 ] ], - "cmdUnderTest": "$TC actions add action vlan pop index 4294967295", + "cmdUnderTest": "$TC actions add action vlan pop pass index 8", "expExitCode": "0", - "verifyCmd": "$TC actions list action vlan", - "matchPattern": "action order [0-9]+: vlan.*pop.*index 4294967295 ref", + "verifyCmd": "$TC actions get action vlan index 8", + "matchPattern": "action order [0-9]+: vlan.*pop.*pass.*index 8 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action vlan" + ] + }, + { + "id": "b0d4", + "name": "Add vlan pop action with drop opcode", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action vlan pop drop index 8", + "expExitCode": "0", + "verifyCmd": "$TC actions get action vlan index 8", + "matchPattern": "action order [0-9]+: vlan.*pop.*drop.*index 8 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action vlan" + ] + }, + { + "id": "95ee", + "name": "Add vlan pop action with reclassify opcode", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action vlan pop reclassify index 8", + "expExitCode": "0", + "verifyCmd": "$TC actions get action vlan index 8", + "matchPattern": "action order [0-9]+: vlan.*pop.*reclassify.*index 8 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action vlan" + ] + }, + { + "id": "0283", + "name": "Add vlan pop action with continue opcode", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action vlan pop continue index 8", + "expExitCode": "0", + "verifyCmd": "$TC actions get action vlan index 8", + "matchPattern": "action order [0-9]+: vlan.*pop.*continue.*index 8 ref", "matchCount": "1", "teardown": [ "$TC actions flush action vlan" @@ -96,6 +168,74 @@ ] }, { + "id": "a178", + "name": "Add vlan pop action with invalid opcode", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action vlan pop foo index 8", + "expExitCode": "255", + "verifyCmd": "$TC actions list action vlan", + "matchPattern": "action order [0-9]+: vlan.*pop.*foo.*index 8 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "ee6f", + "name": "Add vlan pop action with index at 32-bit maximum", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action vlan pop index 4294967295", + "expExitCode": "0", + "verifyCmd": "$TC actions list action vlan", + "matchPattern": "action order [0-9]+: vlan.*pop.*index 4294967295 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action vlan" + ] + }, + { + "id": "0dfa", + "name": "Add vlan pop action with index exceeding 32-bit maximum", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action vlan pop reclassify index 429496729599", + "expExitCode": "255", + "verifyCmd": "$TC actions get action vlan index 429496729599", + "matchPattern": "action order [0-9]+: vlan.*pop.reclassify.*index 429496729599", + "matchCount": "0", + "teardown": [] + }, + { "id": "2b91", "name": "Add vlan invalid action", "category": [ @@ -115,13 +255,11 @@ "verifyCmd": "$TC actions list action vlan", "matchPattern": "action order [0-9]+: vlan.*bad_mode", "matchCount": "0", - "teardown": [ - "$TC actions flush action vlan" - ] + "teardown": [] }, { "id": "57fc", - "name": "Add vlan action with invalid protocol type", + "name": "Add vlan push action with invalid protocol type", "category": [ "actions", "vlan" @@ -139,9 +277,7 @@ "verifyCmd": "$TC actions list action vlan", "matchPattern": "action order [0-9]+: vlan.*push", "matchCount": "0", - "teardown": [ - "$TC actions flush action vlan" - ] + "teardown": [] }, { "id": "3989", @@ -216,6 +352,30 @@ ] }, { + "id": "1f4b", + "name": "Add vlan push action with maximum 12-bit vlan ID", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action vlan push id 4094 index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action vlan index 1", + "matchPattern": "action order [0-9]+: vlan.*push id 4094.*protocol 802.1Q.*priority 0.*index 1 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action vlan" + ] + }, + { "id": "1f7b", "name": "Add vlan push action with invalid vlan ID", "category": [ @@ -240,6 +400,30 @@ ] }, { + "id": "fe40", + "name": "Add vlan push action with maximum 3-bit IEEE 802.1p priority", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action vlan push id 4 priority 7 reclassify index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action vlan index 1", + "matchPattern": "action order [0-9]+: vlan.*push id 4.*protocol 802.1Q.*priority 7.*reclassify.*index 1 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action vlan" + ] + }, + { "id": "5d02", "name": "Add vlan push action with invalid IEEE 802.1p priority", "category": [ @@ -259,9 +443,7 @@ "verifyCmd": "$TC actions list action vlan", "matchPattern": "action order [0-9]+: vlan.*push id 5.*index 1 ref", "matchCount": "0", - "teardown": [ - "$TC actions flush action vlan" - ] + "teardown": [] }, { "id": "6812", @@ -312,6 +494,106 @@ ] }, { + "id": "3deb", + "name": "Replace existing vlan push action with new ID", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ], + "$TC actions add action vlan push id 500 pipe index 12" + ], + "cmdUnderTest": "$TC actions replace action vlan push id 700 pipe index 12", + "expExitCode": "0", + "verifyCmd": "$TC actions get action vlan index 12", + "matchPattern": "action order [0-9]+: vlan.*push id 700 protocol 802.1Q priority 0 pipe.*index 12 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action vlan" + ] + }, + { + "id": "9e76", + "name": "Replace existing vlan push action with new protocol", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ], + "$TC actions add action vlan push id 1 protocol 802.1Q pipe index 1" + ], + "cmdUnderTest": "$TC actions replace action vlan push id 1 protocol 802.1ad pipe index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action vlan index 1", + "matchPattern": "action order [0-9]+: vlan.*push id 1 protocol 802.1ad priority 0 pipe.*index 1 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action vlan" + ] + }, + { + "id": "ede4", + "name": "Replace existing vlan push action with new priority", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ], + "$TC actions add action vlan push id 1 protocol 802.1Q priority 3 reclassify index 1" + ], + "cmdUnderTest": "$TC actions replace action vlan push id 1 priority 4 reclassify index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action vlan index 1", + "matchPattern": "action order [0-9]+: vlan.*push id 1 protocol 802.1Q priority 4 reclassify.*index 1 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action vlan" + ] + }, + { + "id": "d413", + "name": "Replace existing vlan pop action with new cookie", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ], + "$TC actions add action vlan pop continue index 1 cookie 22334455" + ], + "cmdUnderTest": "$TC actions replace action vlan pop continue index 1 cookie a1b1c2d1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action vlan index 1", + "matchPattern": "action order [0-9]+: vlan.*pop continue.*index 1 ref.*cookie a1b1c2d1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action vlan" + ] + }, + { "id": "83a4", "name": "Delete vlan pop action", "category": [ @@ -385,7 +667,7 @@ }, { "id": "1d78", - "name": "Add vlan action with cookie", + "name": "Add vlan push action with cookie", "category": [ "actions", "vlan" diff --git a/tools/testing/selftests/uevent/Makefile b/tools/testing/selftests/uevent/Makefile new file mode 100644 index 0000000..f7baa9a --- /dev/null +++ b/tools/testing/selftests/uevent/Makefile @@ -0,0 +1,17 @@ +# SPDX-License-Identifier: GPL-2.0 +all: + +include ../lib.mk + +.PHONY: all clean + +BINARIES := uevent_filtering +CFLAGS += -Wl,-no-as-needed -Wall + +uevent_filtering: uevent_filtering.c ../kselftest.h ../kselftest_harness.h + $(CC) $(CFLAGS) $< -o $@ + +TEST_PROGS += $(BINARIES) +EXTRA_CLEAN := $(BINARIES) + +all: $(BINARIES) diff --git a/tools/testing/selftests/uevent/config b/tools/testing/selftests/uevent/config new file mode 100644 index 0000000..1038f45 --- /dev/null +++ b/tools/testing/selftests/uevent/config @@ -0,0 +1,2 @@ +CONFIG_USER_NS=y +CONFIG_NET=y diff --git a/tools/testing/selftests/uevent/uevent_filtering.c b/tools/testing/selftests/uevent/uevent_filtering.c new file mode 100644 index 0000000..f83391a --- /dev/null +++ b/tools/testing/selftests/uevent/uevent_filtering.c @@ -0,0 +1,486 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <linux/netlink.h> +#include <signal.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/prctl.h> +#include <sys/socket.h> +#include <sched.h> +#include <sys/eventfd.h> +#include <sys/stat.h> +#include <sys/syscall.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "../kselftest.h" +#include "../kselftest_harness.h" + +#define __DEV_FULL "/sys/devices/virtual/mem/full/uevent" +#define __UEVENT_BUFFER_SIZE (2048 * 2) +#define __UEVENT_HEADER "add@/devices/virtual/mem/full" +#define __UEVENT_HEADER_LEN sizeof("add@/devices/virtual/mem/full") +#define __UEVENT_LISTEN_ALL -1 + +ssize_t read_nointr(int fd, void *buf, size_t count) +{ + ssize_t ret; + +again: + ret = read(fd, buf, count); + if (ret < 0 && errno == EINTR) + goto again; + + return ret; +} + +ssize_t write_nointr(int fd, const void *buf, size_t count) +{ + ssize_t ret; + +again: + ret = write(fd, buf, count); + if (ret < 0 && errno == EINTR) + goto again; + + return ret; +} + +int wait_for_pid(pid_t pid) +{ + int status, ret; + +again: + ret = waitpid(pid, &status, 0); + if (ret == -1) { + if (errno == EINTR) + goto again; + + return -1; + } + + if (ret != pid) + goto again; + + if (!WIFEXITED(status) || WEXITSTATUS(status) != 0) + return -1; + + return 0; +} + +static int uevent_listener(unsigned long post_flags, bool expect_uevent, + int sync_fd) +{ + int sk_fd, ret; + socklen_t sk_addr_len; + int fret = -1, rcv_buf_sz = __UEVENT_BUFFER_SIZE; + uint64_t sync_add = 1; + struct sockaddr_nl sk_addr = { 0 }, rcv_addr = { 0 }; + char buf[__UEVENT_BUFFER_SIZE] = { 0 }; + struct iovec iov = { buf, __UEVENT_BUFFER_SIZE }; + char control[CMSG_SPACE(sizeof(struct ucred))]; + struct msghdr hdr = { + &rcv_addr, sizeof(rcv_addr), &iov, 1, + control, sizeof(control), 0, + }; + + sk_fd = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, + NETLINK_KOBJECT_UEVENT); + if (sk_fd < 0) { + fprintf(stderr, "%s - Failed to open uevent socket\n", strerror(errno)); + return -1; + } + + ret = setsockopt(sk_fd, SOL_SOCKET, SO_RCVBUF, &rcv_buf_sz, + sizeof(rcv_buf_sz)); + if (ret < 0) { + fprintf(stderr, "%s - Failed to set socket options\n", strerror(errno)); + goto on_error; + } + + sk_addr.nl_family = AF_NETLINK; + sk_addr.nl_groups = __UEVENT_LISTEN_ALL; + + sk_addr_len = sizeof(sk_addr); + ret = bind(sk_fd, (struct sockaddr *)&sk_addr, sk_addr_len); + if (ret < 0) { + fprintf(stderr, "%s - Failed to bind socket\n", strerror(errno)); + goto on_error; + } + + ret = getsockname(sk_fd, (struct sockaddr *)&sk_addr, &sk_addr_len); + if (ret < 0) { + fprintf(stderr, "%s - Failed to retrieve socket name\n", strerror(errno)); + goto on_error; + } + + if ((size_t)sk_addr_len != sizeof(sk_addr)) { + fprintf(stderr, "Invalid socket address size\n"); + goto on_error; + } + + if (post_flags & CLONE_NEWUSER) { + ret = unshare(CLONE_NEWUSER); + if (ret < 0) { + fprintf(stderr, + "%s - Failed to unshare user namespace\n", + strerror(errno)); + goto on_error; + } + } + + if (post_flags & CLONE_NEWNET) { + ret = unshare(CLONE_NEWNET); + if (ret < 0) { + fprintf(stderr, + "%s - Failed to unshare network namespace\n", + strerror(errno)); + goto on_error; + } + } + + ret = write_nointr(sync_fd, &sync_add, sizeof(sync_add)); + close(sync_fd); + if (ret != sizeof(sync_add)) { + fprintf(stderr, "Failed to synchronize with parent process\n"); + goto on_error; + } + + fret = 0; + for (;;) { + ssize_t r; + + r = recvmsg(sk_fd, &hdr, 0); + if (r <= 0) { + fprintf(stderr, "%s - Failed to receive uevent\n", strerror(errno)); + ret = -1; + break; + } + + /* ignore libudev messages */ + if (memcmp(buf, "libudev", 8) == 0) + continue; + + /* ignore uevents we didn't trigger */ + if (memcmp(buf, __UEVENT_HEADER, __UEVENT_HEADER_LEN) != 0) + continue; + + if (!expect_uevent) { + fprintf(stderr, "Received unexpected uevent:\n"); + ret = -1; + } + + if (TH_LOG_ENABLED) { + /* If logging is enabled dump the received uevent. */ + (void)write_nointr(STDERR_FILENO, buf, r); + (void)write_nointr(STDERR_FILENO, "\n", 1); + } + + break; + } + +on_error: + close(sk_fd); + + return fret; +} + +int trigger_uevent(unsigned int times) +{ + int fd, ret; + unsigned int i; + + fd = open(__DEV_FULL, O_RDWR | O_CLOEXEC); + if (fd < 0) { + if (errno != ENOENT) + return -EINVAL; + + return -1; + } + + for (i = 0; i < times; i++) { + ret = write_nointr(fd, "add\n", sizeof("add\n") - 1); + if (ret < 0) { + fprintf(stderr, "Failed to trigger uevent\n"); + break; + } + } + close(fd); + + return ret; +} + +int set_death_signal(void) +{ + int ret; + pid_t ppid; + + ret = prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0); + + /* Check whether we have been orphaned. */ + ppid = getppid(); + if (ppid == 1) { + pid_t self; + + self = getpid(); + ret = kill(self, SIGKILL); + } + + if (ret < 0) + return -1; + + return 0; +} + +static int do_test(unsigned long pre_flags, unsigned long post_flags, + bool expect_uevent, int sync_fd) +{ + int ret; + uint64_t wait_val; + pid_t pid; + sigset_t mask; + sigset_t orig_mask; + struct timespec timeout; + + sigemptyset(&mask); + sigaddset(&mask, SIGCHLD); + + ret = sigprocmask(SIG_BLOCK, &mask, &orig_mask); + if (ret < 0) { + fprintf(stderr, "%s- Failed to block SIGCHLD\n", strerror(errno)); + return -1; + } + + pid = fork(); + if (pid < 0) { + fprintf(stderr, "%s - Failed to fork() new process\n", strerror(errno)); + return -1; + } + + if (pid == 0) { + /* Make sure that we go away when our parent dies. */ + ret = set_death_signal(); + if (ret < 0) { + fprintf(stderr, "Failed to set PR_SET_PDEATHSIG to SIGKILL\n"); + _exit(EXIT_FAILURE); + } + + if (pre_flags & CLONE_NEWUSER) { + ret = unshare(CLONE_NEWUSER); + if (ret < 0) { + fprintf(stderr, + "%s - Failed to unshare user namespace\n", + strerror(errno)); + _exit(EXIT_FAILURE); + } + } + + if (pre_flags & CLONE_NEWNET) { + ret = unshare(CLONE_NEWNET); + if (ret < 0) { + fprintf(stderr, + "%s - Failed to unshare network namespace\n", + strerror(errno)); + _exit(EXIT_FAILURE); + } + } + + if (uevent_listener(post_flags, expect_uevent, sync_fd) < 0) + _exit(EXIT_FAILURE); + + _exit(EXIT_SUCCESS); + } + + ret = read_nointr(sync_fd, &wait_val, sizeof(wait_val)); + if (ret != sizeof(wait_val)) { + fprintf(stderr, "Failed to synchronize with child process\n"); + _exit(EXIT_FAILURE); + } + + /* Trigger 10 uevents to account for the case where the kernel might + * drop some. + */ + ret = trigger_uevent(10); + if (ret < 0) + fprintf(stderr, "Failed triggering uevents\n"); + + /* Wait for 2 seconds before considering this failed. This should be + * plenty of time for the kernel to deliver the uevent even under heavy + * load. + */ + timeout.tv_sec = 2; + timeout.tv_nsec = 0; + +again: + ret = sigtimedwait(&mask, NULL, &timeout); + if (ret < 0) { + if (errno == EINTR) + goto again; + + if (!expect_uevent) + ret = kill(pid, SIGTERM); /* success */ + else + ret = kill(pid, SIGUSR1); /* error */ + if (ret < 0) + return -1; + } + + ret = wait_for_pid(pid); + if (ret < 0) + return -1; + + return ret; +} + +static void signal_handler(int sig) +{ + if (sig == SIGTERM) + _exit(EXIT_SUCCESS); + + _exit(EXIT_FAILURE); +} + +TEST(uevent_filtering) +{ + int ret, sync_fd; + struct sigaction act; + + if (geteuid()) { + TH_LOG("Uevent filtering tests require root privileges. Skipping test"); + _exit(KSFT_SKIP); + } + + ret = access(__DEV_FULL, F_OK); + EXPECT_EQ(0, ret) { + if (errno == ENOENT) { + TH_LOG(__DEV_FULL " does not exist. Skipping test"); + _exit(KSFT_SKIP); + } + + _exit(KSFT_FAIL); + } + + act.sa_handler = signal_handler; + act.sa_flags = 0; + sigemptyset(&act.sa_mask); + + ret = sigaction(SIGTERM, &act, NULL); + ASSERT_EQ(0, ret); + + sync_fd = eventfd(0, EFD_CLOEXEC); + ASSERT_GE(sync_fd, 0); + + /* + * Setup: + * - Open uevent listening socket in initial network namespace owned by + * initial user namespace. + * - Trigger uevent in initial network namespace owned by initial user + * namespace. + * Expected Result: + * - uevent listening socket receives uevent + */ + ret = do_test(0, 0, true, sync_fd); + ASSERT_EQ(0, ret) { + goto do_cleanup; + } + + /* + * Setup: + * - Open uevent listening socket in non-initial network namespace + * owned by initial user namespace. + * - Trigger uevent in initial network namespace owned by initial user + * namespace. + * Expected Result: + * - uevent listening socket receives uevent + */ + ret = do_test(CLONE_NEWNET, 0, true, sync_fd); + ASSERT_EQ(0, ret) { + goto do_cleanup; + } + + /* + * Setup: + * - unshare user namespace + * - Open uevent listening socket in initial network namespace + * owned by initial user namespace. + * - Trigger uevent in initial network namespace owned by initial user + * namespace. + * Expected Result: + * - uevent listening socket receives uevent + */ + ret = do_test(CLONE_NEWUSER, 0, true, sync_fd); + ASSERT_EQ(0, ret) { + goto do_cleanup; + } + + /* + * Setup: + * - Open uevent listening socket in non-initial network namespace + * owned by non-initial user namespace. + * - Trigger uevent in initial network namespace owned by initial user + * namespace. + * Expected Result: + * - uevent listening socket receives no uevent + */ + ret = do_test(CLONE_NEWUSER | CLONE_NEWNET, 0, false, sync_fd); + ASSERT_EQ(0, ret) { + goto do_cleanup; + } + + /* + * Setup: + * - Open uevent listening socket in initial network namespace + * owned by initial user namespace. + * - unshare network namespace + * - Trigger uevent in initial network namespace owned by initial user + * namespace. + * Expected Result: + * - uevent listening socket receives uevent + */ + ret = do_test(0, CLONE_NEWNET, true, sync_fd); + ASSERT_EQ(0, ret) { + goto do_cleanup; + } + + /* + * Setup: + * - Open uevent listening socket in initial network namespace + * owned by initial user namespace. + * - unshare user namespace + * - Trigger uevent in initial network namespace owned by initial user + * namespace. + * Expected Result: + * - uevent listening socket receives uevent + */ + ret = do_test(0, CLONE_NEWUSER, true, sync_fd); + ASSERT_EQ(0, ret) { + goto do_cleanup; + } + + /* + * Setup: + * - Open uevent listening socket in initial network namespace + * owned by initial user namespace. + * - unshare user namespace + * - unshare network namespace + * - Trigger uevent in initial network namespace owned by initial user + * namespace. + * Expected Result: + * - uevent listening socket receives uevent + */ + ret = do_test(0, CLONE_NEWUSER | CLONE_NEWNET, true, sync_fd); + ASSERT_EQ(0, ret) { + goto do_cleanup; + } + +do_cleanup: + close(sync_fd); +} + +TEST_HARNESS_MAIN diff --git a/tools/usb/usbip/libsrc/vhci_driver.c b/tools/usb/usbip/libsrc/vhci_driver.c index c9c8161..4204359 100644 --- a/tools/usb/usbip/libsrc/vhci_driver.c +++ b/tools/usb/usbip/libsrc/vhci_driver.c @@ -135,11 +135,11 @@ static int refresh_imported_device_list(void) return 0; } -static int get_nports(void) +static int get_nports(struct udev_device *hc_device) { const char *attr_nports; - attr_nports = udev_device_get_sysattr_value(vhci_driver->hc_device, "nports"); + attr_nports = udev_device_get_sysattr_value(hc_device, "nports"); if (!attr_nports) { err("udev_device_get_sysattr_value nports failed"); return -1; @@ -242,35 +242,41 @@ static int read_record(int rhport, char *host, unsigned long host_len, int usbip_vhci_driver_open(void) { + int nports; + struct udev_device *hc_device; + udev_context = udev_new(); if (!udev_context) { err("udev_new failed"); return -1; } - vhci_driver = calloc(1, sizeof(struct usbip_vhci_driver)); - /* will be freed in usbip_driver_close() */ - vhci_driver->hc_device = + hc_device = udev_device_new_from_subsystem_sysname(udev_context, USBIP_VHCI_BUS_TYPE, USBIP_VHCI_DEVICE_NAME); - if (!vhci_driver->hc_device) { + if (!hc_device) { err("udev_device_new_from_subsystem_sysname failed"); goto err; } - vhci_driver->nports = get_nports(); - dbg("available ports: %d", vhci_driver->nports); - - if (vhci_driver->nports <= 0) { + nports = get_nports(hc_device); + if (nports <= 0) { err("no available ports"); goto err; - } else if (vhci_driver->nports > MAXNPORT) { - err("port number exceeds %d", MAXNPORT); + } + dbg("available ports: %d", nports); + + vhci_driver = calloc(1, sizeof(struct usbip_vhci_driver) + + nports * sizeof(struct usbip_imported_device)); + if (!vhci_driver) { + err("vhci_driver allocation failed"); goto err; } + vhci_driver->nports = nports; + vhci_driver->hc_device = hc_device; vhci_driver->ncontrollers = get_ncontrollers(); dbg("available controllers: %d", vhci_driver->ncontrollers); @@ -285,7 +291,7 @@ int usbip_vhci_driver_open(void) return 0; err: - udev_device_unref(vhci_driver->hc_device); + udev_device_unref(hc_device); if (vhci_driver) free(vhci_driver); diff --git a/tools/usb/usbip/libsrc/vhci_driver.h b/tools/usb/usbip/libsrc/vhci_driver.h index 418b404..6c9aca2 100644 --- a/tools/usb/usbip/libsrc/vhci_driver.h +++ b/tools/usb/usbip/libsrc/vhci_driver.h @@ -13,7 +13,6 @@ #define USBIP_VHCI_BUS_TYPE "platform" #define USBIP_VHCI_DEVICE_NAME "vhci_hcd.0" -#define MAXNPORT 128 enum hub_speed { HUB_SPEED_HIGH = 0, @@ -41,7 +40,7 @@ struct usbip_vhci_driver { int ncontrollers; int nports; - struct usbip_imported_device idev[MAXNPORT]; + struct usbip_imported_device idev[]; }; diff --git a/tools/usb/usbip/src/usbip_detach.c b/tools/usb/usbip/src/usbip_detach.c index 9db9d21..777f728 100644 --- a/tools/usb/usbip/src/usbip_detach.c +++ b/tools/usb/usbip/src/usbip_detach.c @@ -43,9 +43,12 @@ void usbip_detach_usage(void) static int detach_port(char *port) { - int ret; + int ret = 0; uint8_t portnum; char path[PATH_MAX+1]; + int i; + struct usbip_imported_device *idev; + int found = 0; unsigned int port_len = strlen(port); @@ -55,27 +58,48 @@ static int detach_port(char *port) return -1; } - /* check max port */ - portnum = atoi(port); - /* remove the port state file */ + ret = usbip_vhci_driver_open(); + if (ret < 0) { + err("open vhci_driver"); + return -1; + } + + /* check for invalid port */ + for (i = 0; i < vhci_driver->nports; i++) { + idev = &vhci_driver->idev[i]; + + if (idev->port == portnum) { + found = 1; + if (idev->status != VDEV_ST_NULL) + break; + info("Port %d is already detached!\n", idev->port); + goto call_driver_close; + } + } + if (!found) { + err("Invalid port %s > maxports %d", + port, vhci_driver->nports); + goto call_driver_close; + } + + /* remove the port state file */ snprintf(path, PATH_MAX, VHCI_STATE_PATH"/port%d", portnum); remove(path); rmdir(VHCI_STATE_PATH); - ret = usbip_vhci_driver_open(); + ret = usbip_vhci_detach_device(portnum); if (ret < 0) { - err("open vhci_driver"); - return -1; + ret = -1; + err("Port %d detach request failed!\n", portnum); + goto call_driver_close; } + info("Port %d is now detached!\n", portnum); - ret = usbip_vhci_detach_device(portnum); - if (ret < 0) - return -1; - +call_driver_close: usbip_vhci_driver_close(); return ret; diff --git a/tools/virtio/linux/dma-mapping.h b/tools/virtio/linux/dma-mapping.h index 1571e24..f91aeb5f 100644 --- a/tools/virtio/linux/dma-mapping.h +++ b/tools/virtio/linux/dma-mapping.h @@ -6,8 +6,6 @@ # error Virtio userspace code does not support CONFIG_HAS_DMA #endif -#define PCI_DMA_BUS_IS_PHYS 1 - enum dma_data_direction { DMA_BIDIRECTIONAL = 0, DMA_TO_DEVICE = 1, diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c index a8783f4..cce853d 100644 --- a/tools/vm/page-types.c +++ b/tools/vm/page-types.c @@ -131,6 +131,7 @@ static const char * const page_flag_names[] = { [KPF_KSM] = "x:ksm", [KPF_THP] = "t:thp", [KPF_BALLOON] = "o:balloon", + [KPF_PGTABLE] = "g:pgtable", [KPF_ZERO_PAGE] = "z:zero_page", [KPF_IDLE] = "i:idle_page", |
