From e5c7bd4e5ca0f549108a7013ba77885926c6a56b Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 22 May 2024 13:40:19 -0300 Subject: tools include UAPI: Sync linux/stat.h with the kernel sources To get the changes in: 2a82bb02941fb53d ("statx: stx_subvol") To pick up this change and support it: $ tools/perf/trace/beauty/statx_mask.sh > before $ cp include/uapi/linux/stat.h tools/perf/trace/beauty/include/uapi/linux/stat.h $ tools/perf/trace/beauty/statx_mask.sh > after $ diff -u before after --- before 2024-05-22 13:39:49.742470571 -0300 +++ after 2024-05-22 13:39:59.157883101 -0300 @@ -14,4 +14,5 @@ [ilog2(0x00001000) + 1] = "MNT_ID", [ilog2(0x00002000) + 1] = "DIOALIGN", [ilog2(0x00004000) + 1] = "MNT_ID_UNIQUE", + [ilog2(0x00008000) + 1] = "SUBVOL", }; $ Now we'll see it like we see these: # perf trace -e statx 0.000 ( 0.015 ms): systemd-userwo/3982299 statx(dfd: 6, filename: ".", mask: TYPE|INO|MNT_ID, buffer: 0x7ffd8945e850) = 0 180.559 ( 0.007 ms): (ostnamed)/3982957 statx(dfd: 4, filename: "sys", flags: SYMLINK_NOFOLLOW|NO_AUTOMOUNT|STATX_DONT_SYNC, mask: TYPE, buffer: 0x7fff13161190) = 0 180.918 ( 0.011 ms): (ostnamed)/3982957 statx(dfd: CWD, filename: "/run/systemd/mount-rootfs/sys/kernel/security", flags: SYMLINK_NOFOLLOW|NO_AUTOMOUNT|STATX_DONT_SYNC, mask: MNT_ID, buffer: 0x7fff13161120) = 0 180.956 ( 0.010 ms): (ostnamed)/3982957 statx(dfd: CWD, filename: "/run/systemd/mount-rootfs/sys/fs/cgroup", flags: SYMLINK_NOFOLLOW|NO_AUTOMOUNT|STATX_DONT_SYNC, mask: MNT_ID, buffer: 0x7fff13161120) = 0 Cc: Adrian Hunter Cc: Christian Brauner Cc: Ian Rogers Cc: Jiri Olsa Cc: Kan Liang Cc: Kent Overstreet Cc: Namhyung Kim Link: https://lore.kernel.org/lkml/Zk5nO9yT0oPezUoo@x1 Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/trace/beauty/include/uapi/linux/stat.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/trace/beauty/include/uapi/linux/stat.h b/tools/perf/trace/beauty/include/uapi/linux/stat.h index 2f2ee82d5517..67626d535316 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/stat.h +++ b/tools/perf/trace/beauty/include/uapi/linux/stat.h @@ -126,8 +126,9 @@ struct statx { __u64 stx_mnt_id; __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */ __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */ + __u64 stx_subvol; /* Subvolume identifier */ /* 0xa0 */ - __u64 __spare3[12]; /* Spare space for future expansion */ + __u64 __spare3[11]; /* Spare space for future expansion */ /* 0x100 */ }; @@ -155,6 +156,7 @@ struct statx { #define STATX_MNT_ID 0x00001000U /* Got stx_mnt_id */ #define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */ #define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */ +#define STATX_SUBVOL 0x00008000U /* Want/got stx_subvol */ #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ -- cgit v1.2.3 From 0efc88e444d9d74f220f60a3e37143c8decf1bea Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 27 May 2024 12:15:27 -0300 Subject: tools headers UAPI: Sync linux/prctl.h with the kernel sources To pick the changes in: 628d701f2de5b9a1 ("powerpc/dexcr: Add DEXCR prctl interface") 6b9391b581fddd85 ("riscv: Include riscv_set_icache_flush_ctx prctl") That adds some PowerPC and a RISC-V specific prctl options: $ tools/perf/trace/beauty/prctl_option.sh > before $ cp include/uapi/linux/prctl.h tools/perf/trace/beauty/include/uapi/linux/prctl.h $ tools/perf/trace/beauty/prctl_option.sh > after $ diff -u before after --- before 2024-05-27 12:14:21.358032781 -0300 +++ after 2024-05-27 12:14:32.364530185 -0300 @@ -65,6 +65,9 @@ [68] = "GET_MEMORY_MERGE", [69] = "RISCV_V_SET_CONTROL", [70] = "RISCV_V_GET_CONTROL", + [71] = "RISCV_SET_ICACHE_FLUSH_CTX", + [72] = "PPC_GET_DEXCR", + [73] = "PPC_SET_DEXCR", }; static const char *prctl_set_mm_options[] = { [1] = "START_CODE", $ That now will be used to decode the syscall option and also to compose filters, for instance: [root@five ~]# perf trace -e syscalls:sys_enter_prctl --filter option==SET_NAME 0.000 Isolated Servi/3474327 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23f13b7aee) 0.032 DOM Worker/3474327 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23deb25670) 7.920 :3474328/3474328 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23e24fbb10) 7.935 StreamT~s #374/3474328 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23e24fb970) 8.400 Isolated Servi/3474329 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23e24bab10) 8.418 StreamT~s #374/3474329 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23e24ba970) ^C[root@five ~]# This addresses this perf build warning: Warning: Kernel ABI header differences: diff -u tools/include/uapi/linux/prctl.h include/uapi/linux/prctl.h Cc: Adrian Hunter Cc: Benjamin Gray Cc: Charlie Jenkins Cc: Ian Rogers Cc: Jiri Olsa Cc: Kan Liang Cc: Michael Ellerman Cc: Namhyung Kim Cc: Palmer Dabbelt Link: https://lore.kernel.org/lkml/ZlSklGWp--v_Ije7@x1 Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/trace/beauty/include/uapi/linux/prctl.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'tools') diff --git a/tools/perf/trace/beauty/include/uapi/linux/prctl.h b/tools/perf/trace/beauty/include/uapi/linux/prctl.h index 370ed14b1ae0..35791791a879 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/prctl.h +++ b/tools/perf/trace/beauty/include/uapi/linux/prctl.h @@ -306,4 +306,26 @@ struct prctl_mm_map { # define PR_RISCV_V_VSTATE_CTRL_NEXT_MASK 0xc # define PR_RISCV_V_VSTATE_CTRL_MASK 0x1f +#define PR_RISCV_SET_ICACHE_FLUSH_CTX 71 +# define PR_RISCV_CTX_SW_FENCEI_ON 0 +# define PR_RISCV_CTX_SW_FENCEI_OFF 1 +# define PR_RISCV_SCOPE_PER_PROCESS 0 +# define PR_RISCV_SCOPE_PER_THREAD 1 + +/* PowerPC Dynamic Execution Control Register (DEXCR) controls */ +#define PR_PPC_GET_DEXCR 72 +#define PR_PPC_SET_DEXCR 73 +/* DEXCR aspect to act on */ +# define PR_PPC_DEXCR_SBHE 0 /* Speculative branch hint enable */ +# define PR_PPC_DEXCR_IBRTPD 1 /* Indirect branch recurrent target prediction disable */ +# define PR_PPC_DEXCR_SRAPD 2 /* Subroutine return address prediction disable */ +# define PR_PPC_DEXCR_NPHIE 3 /* Non-privileged hash instruction enable */ +/* Action to apply / return */ +# define PR_PPC_DEXCR_CTRL_EDITABLE 0x1 /* Aspect can be modified with PR_PPC_SET_DEXCR */ +# define PR_PPC_DEXCR_CTRL_SET 0x2 /* Set the aspect for this process */ +# define PR_PPC_DEXCR_CTRL_CLEAR 0x4 /* Clear the aspect for this process */ +# define PR_PPC_DEXCR_CTRL_SET_ONEXEC 0x8 /* Set the aspect on exec */ +# define PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC 0x10 /* Clear the aspect on exec */ +# define PR_PPC_DEXCR_CTRL_MASK 0x1f + #endif /* _LINUX_PRCTL_H */ -- cgit v1.2.3 From 1437a9f06f740cc2950d9b6ac23fad838ff023a3 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 27 May 2024 12:34:20 -0300 Subject: tools headers UAPI: Sync fcntl.h with the kernel sources to pick F_DUPFD_QUERY There is no scrape script yet for those, but the warning pointed out we need to update the array with the F_LINUX_SPECIFIC_BASE entries, do it. Now 'perf trace' can decode that cmd and also use it in filter, as in: root@number:~# perf trace -e syscalls:*enter_fcntl --filter 'cmd != SETFL && cmd != GETFL' 0.000 sssd_kcm/303828 syscalls:sys_enter_fcntl(fd: 13, cmd: SETLK, arg: 0x7fffdc6a8a50) 0.013 sssd_kcm/303828 syscalls:sys_enter_fcntl(fd: 13, cmd: SETLKW, arg: 0x7fffdc6a8aa0) 0.090 sssd_kcm/303828 syscalls:sys_enter_fcntl(fd: 13, cmd: SETLKW, arg: 0x7fffdc6a88e0) ^Croot@number:~# This picks up the changes in: c62b758bae6af16f ("fcntl: add F_DUPFD_QUERY fcntl()") Addressing this perf tools build warning: Warning: Kernel ABI header differences: diff -u tools/perf/trace/beauty/include/uapi/linux/fcntl.h include/uapi/linux/fcntl.h Cc: Adrian Hunter Cc: Christian Brauner Cc: Ian Rogers Cc: Jiri Olsa Cc: Kan Liang Cc: Linus Torvalds Cc: Namhyung Kim Link: https://lore.kernel.org/lkml/ZlSqNQH9mFw2bmjq@x1 Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 2 +- tools/perf/trace/beauty/include/uapi/linux/fcntl.h | 14 ++++++++------ 2 files changed, 9 insertions(+), 7 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 51eca671c797..08a3a6effac1 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -765,7 +765,7 @@ static const char *fcntl_cmds[] = { static DEFINE_STRARRAY(fcntl_cmds, "F_"); static const char *fcntl_linux_specific_cmds[] = { - "SETLEASE", "GETLEASE", "NOTIFY", [5] = "CANCELLK", "DUPFD_CLOEXEC", + "SETLEASE", "GETLEASE", "NOTIFY", "DUPFD_QUERY", [5] = "CANCELLK", "DUPFD_CLOEXEC", "SETPIPE_SZ", "GETPIPE_SZ", "ADD_SEALS", "GET_SEALS", "GET_RW_HINT", "SET_RW_HINT", "GET_FILE_RW_HINT", "SET_FILE_RW_HINT", }; diff --git a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h index 282e90aeb163..c0bcc185fa48 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h +++ b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h @@ -8,6 +8,14 @@ #define F_SETLEASE (F_LINUX_SPECIFIC_BASE + 0) #define F_GETLEASE (F_LINUX_SPECIFIC_BASE + 1) +/* + * Request nofications on a directory. + * See below for events that may be notified. + */ +#define F_NOTIFY (F_LINUX_SPECIFIC_BASE + 2) + +#define F_DUPFD_QUERY (F_LINUX_SPECIFIC_BASE + 3) + /* * Cancel a blocking posix lock; internal use only until we expose an * asynchronous lock api to userspace: @@ -17,12 +25,6 @@ /* Create a file descriptor with FD_CLOEXEC set. */ #define F_DUPFD_CLOEXEC (F_LINUX_SPECIFIC_BASE + 6) -/* - * Request nofications on a directory. - * See below for events that may be notified. - */ -#define F_NOTIFY (F_LINUX_SPECIFIC_BASE+2) - /* * Set and get of pipe page size array */ -- cgit v1.2.3 From a3eed53beec4a7bac8acd109abcb187df2577781 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 27 May 2024 12:45:33 -0300 Subject: perf beauty: Update copy of linux/socket.h with the kernel sources To pick up the fixes in: 0645fbe760afcc53 ("net: have do_accept() take a struct proto_accept_arg argument") That just changes a function prototype, not touching things used by the perf scrape scripts such as: $ tools/perf/trace/beauty/sockaddr.sh | head -5 static const char *socket_families[] = { [0] = "UNSPEC", [1] = "LOCAL", [2] = "INET", [3] = "AX25", $ This addresses this perf tools build warning: Warning: Kernel ABI header differences: diff -u tools/perf/trace/beauty/include/linux/socket.h include/linux/socket.h Cc: Adrian Hunter Cc: Ian Rogers Cc: Jens Axboe Cc: Jiri Olsa Cc: Kan Liang Cc: Namhyung Kim Link: https://lore.kernel.org/lkml/ZlSrceExgjrUiDb5@x1 Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/trace/beauty/include/linux/socket.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h index 139c330ccf2c..89d16b90370b 100644 --- a/tools/perf/trace/beauty/include/linux/socket.h +++ b/tools/perf/trace/beauty/include/linux/socket.h @@ -16,6 +16,7 @@ struct cred; struct socket; struct sock; struct sk_buff; +struct proto_accept_arg; #define __sockaddr_check_size(size) \ BUILD_BUG_ON(((size) > sizeof(struct __kernel_sockaddr_storage))) @@ -433,7 +434,7 @@ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size, extern int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, struct sockaddr __user *addr, int addr_len); -extern struct file *do_accept(struct file *file, unsigned file_flags, +extern struct file *do_accept(struct file *file, struct proto_accept_arg *arg, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, -- cgit v1.2.3 From 001821b0e79716c4e17c71d8e053a23599a7a508 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 27 May 2024 12:51:30 -0300 Subject: perf trace beauty: Update the arch/x86/include/asm/irq_vectors.h copy with the kernel sources to pick POSTED_MSI_NOTIFICATION To pick up the change in: f5a3562ec9dd29e6 ("x86/irq: Reserve a per CPU IDT vector for posted MSIs") That picks up this new vector: $ cp arch/x86/include/asm/irq_vectors.h tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h $ tools/perf/trace/beauty/tracepoints/x86_irq_vectors.sh > after $ diff -u before after --- before 2024-05-27 12:50:47.708863932 -0300 +++ after 2024-05-27 12:51:15.335113123 -0300 @@ -1,6 +1,7 @@ static const char *x86_irq_vectors[] = { [0x02] = "NMI", [0x80] = "IA32_SYSCALL", + [0xeb] = "POSTED_MSI_NOTIFICATION", [0xec] = "LOCAL_TIMER", [0xed] = "HYPERV_STIMER0", [0xee] = "HYPERV_REENLIGHTENMENT", $ Now those will be known when pretty printing the irq_vectors:* tracepoints. Cc: Adrian Hunter Cc: Ian Rogers Cc: Jacob Pan Cc: Jiri Olsa Cc: Kan Liang Cc: Namhyung Kim Cc: Thomas Gleixner Link: https://lore.kernel.org/lkml/ZlS34M0x30EFVhbg@x1 Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h b/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h index d18bfb238f66..13aea8fc3d45 100644 --- a/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h +++ b/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h @@ -97,10 +97,16 @@ #define LOCAL_TIMER_VECTOR 0xec +/* + * Posted interrupt notification vector for all device MSIs delivered to + * the host kernel. + */ +#define POSTED_MSI_NOTIFICATION_VECTOR 0xeb + #define NR_VECTORS 256 #ifdef CONFIG_X86_LOCAL_APIC -#define FIRST_SYSTEM_VECTOR LOCAL_TIMER_VECTOR +#define FIRST_SYSTEM_VECTOR POSTED_MSI_NOTIFICATION_VECTOR #else #define FIRST_SYSTEM_VECTOR NR_VECTORS #endif -- cgit v1.2.3 From da42b5229b27bb5c0eff3408c92f025e6041dad3 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 28 May 2024 11:01:20 -0300 Subject: tools headers: Update the syscall tables and unistd.h, mostly to support the new 'mseal' syscall But also to wire up shadow stacks on 32-bit x86, picking up those changes from these csets: ff388fe5c481d39c ("mseal: wire up mseal syscall") 2883f01ec37dd866 ("x86/shstk: Enable shadow stacks for x32") This makes 'perf trace' support it, now its possible, for instance to do: # perf trace -e mseal --max-stack=16 Here is an example with the 'sendmmsg' syscall: root@x1:~# perf trace -e sendmmsg --max-stack 16 --max-events=1 0.000 ( 0.062 ms): dbus-broker/1012 sendmmsg(fd: 150, mmsg: 0x7ffef57cca50, vlen: 1, flags: DONTWAIT|NOSIGNAL) = 1 syscall_exit_to_user_mode_prepare ([kernel.kallsyms]) syscall_exit_to_user_mode_prepare ([kernel.kallsyms]) syscall_exit_to_user_mode ([kernel.kallsyms]) do_syscall_64 ([kernel.kallsyms]) entry_SYSCALL_64 ([kernel.kallsyms]) [0x117ce7] (/usr/lib64/libc.so.6 (deleted)) root@x1:~# To do a system wide tracing of the new 'mseal' syscall with a backtrace of at most 16 entries. This addresses these perf tools build warnings: Warning: Kernel ABI header differences: diff -u tools/include/uapi/asm-generic/unistd.h include/uapi/asm-generic/unistd.h diff -u tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl diff -u tools/perf/arch/powerpc/entry/syscalls/syscall.tbl arch/powerpc/kernel/syscalls/syscall.tbl diff -u tools/perf/arch/s390/entry/syscalls/syscall.tbl arch/s390/kernel/syscalls/syscall.tbl diff -u tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl arch/mips/kernel/syscalls/syscall_n64.tbl Cc: Adrian Hunter Cc: Andrew Morton Cc: H J Lu Cc: Ian Rogers Cc: Ingo Molnar Cc: Jeff Xu Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lore.kernel.org/lkml/ZlXlo4TNcba4wnVZ@x1 Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/asm-generic/unistd.h | 5 ++++- tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl | 1 + tools/perf/arch/powerpc/entry/syscalls/syscall.tbl | 1 + tools/perf/arch/s390/entry/syscalls/syscall.tbl | 1 + tools/perf/arch/x86/entry/syscalls/syscall_64.tbl | 3 ++- 5 files changed, 9 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index 75f00965ab15..d983c48a3b6a 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -842,8 +842,11 @@ __SYSCALL(__NR_lsm_set_self_attr, sys_lsm_set_self_attr) #define __NR_lsm_list_modules 461 __SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules) +#define __NR_mseal 462 +__SYSCALL(__NR_mseal, sys_mseal) + #undef __NR_syscalls -#define __NR_syscalls 462 +#define __NR_syscalls 463 /* * 32 bit systems traditionally used different diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl index 532b855df589..1464c6be6eb3 100644 --- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl +++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl @@ -376,3 +376,4 @@ 459 n64 lsm_get_self_attr sys_lsm_get_self_attr 460 n64 lsm_set_self_attr sys_lsm_set_self_attr 461 n64 lsm_list_modules sys_lsm_list_modules +462 n64 mseal sys_mseal diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index 17173b82ca21..3656f1ca7a21 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -548,3 +548,4 @@ 459 common lsm_get_self_attr sys_lsm_get_self_attr 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index 095bb86339a7..bd0fee24ad10 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -464,3 +464,4 @@ 459 common lsm_get_self_attr sys_lsm_get_self_attr sys_lsm_get_self_attr 460 common lsm_set_self_attr sys_lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal sys_mseal diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 7e8d46f4147f..a396f6e6ab5b 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -374,7 +374,7 @@ 450 common set_mempolicy_home_node sys_set_mempolicy_home_node 451 common cachestat sys_cachestat 452 common fchmodat2 sys_fchmodat2 -453 64 map_shadow_stack sys_map_shadow_stack +453 common map_shadow_stack sys_map_shadow_stack 454 common futex_wake sys_futex_wake 455 common futex_wait sys_futex_wait 456 common futex_requeue sys_futex_requeue @@ -383,6 +383,7 @@ 459 common lsm_get_self_attr sys_lsm_get_self_attr 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal # # Due to a historical design error, certain syscalls are numbered differently -- cgit v1.2.3 From ac4b069035783f7a54b3ab841119f4b6bf435f98 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 28 May 2024 15:10:28 -0300 Subject: tools arch x86: Sync the msr-index.h copy with the kernel sources To pick up the changes from these csets: 53bc516ade85a764 ("x86/msr: Move ARCH_CAP_XAPIC_DISABLE bit definition to its rightful place") That patch just move definitions around, so this just silences this perf build warning: Warning: Kernel ABI header differences: diff -u tools/arch/x86/include/asm/msr-index.h arch/x86/include/asm/msr-index. Cc: Adrian Hunter Cc: Borislav Petkov (AMD) Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Cc: Pawan Gupta Link: https://lore.kernel.org/lkml/ZlYe8jOzd1_DyA7X@x1 Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/asm/msr-index.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'tools') diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index e72c2b872957..e022e6eb766c 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -170,6 +170,10 @@ * CPU is not affected by Branch * History Injection. */ +#define ARCH_CAP_XAPIC_DISABLE BIT(21) /* + * IA32_XAPIC_DISABLE_STATUS MSR + * supported + */ #define ARCH_CAP_PBRSB_NO BIT(24) /* * Not susceptible to Post-Barrier * Return Stack Buffer Predictions. @@ -192,11 +196,6 @@ * File. */ -#define ARCH_CAP_XAPIC_DISABLE BIT(21) /* - * IA32_XAPIC_DISABLE_STATUS MSR - * supported - */ - #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* * Writeback and invalidate the -- cgit v1.2.3 From 88e520512a68b4e724cb0f4281c79ae28673ccb1 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 28 May 2024 16:24:15 -0300 Subject: tools headers UAPI: Sync kvm headers with the kernel sources To pick the changes in: 4af663c2f64a8d25 ("KVM: SEV: Allow per-guest configuration of GHCB protocol version") 4f5defae708992dd ("KVM: SEV: introduce KVM_SEV_INIT2 operation") 26c44aa9e076ed83 ("KVM: SEV: define VM types for SEV and SEV-ES") ac5c48027bacb1b5 ("KVM: SEV: publish supported VMSA features") 651d61bc8b7d8bb6 ("KVM: PPC: Fix documentation for ppc mmu caps") That don't change functionality in tools/perf, as no new ioctl is added for the 'perf trace' scripts to harvest. This addresses these perf build warnings: Warning: Kernel ABI header differences: diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h diff -u tools/arch/x86/include/uapi/asm/kvm.h arch/x86/include/uapi/asm/kvm.h Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Joel Stanley Cc: Michael Ellerman Cc: Michael Roth Cc: Namhyung Kim Cc: Paolo Bonzini Link: https://lore.kernel.org/lkml/ZlYxAdHjyAkvGtMW@x1 Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/uapi/asm/kvm.h | 22 ++++++++++++++++++++-- tools/include/uapi/linux/kvm.h | 4 ++-- 2 files changed, 22 insertions(+), 4 deletions(-) (limited to 'tools') diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index ef11aa4cab42..9fae1b73b529 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -457,8 +457,13 @@ struct kvm_sync_regs { #define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE 0x00000001 -/* attributes for system fd (group 0) */ -#define KVM_X86_XCOMP_GUEST_SUPP 0 +/* vendor-independent attributes for system fd (group 0) */ +#define KVM_X86_GRP_SYSTEM 0 +# define KVM_X86_XCOMP_GUEST_SUPP 0 + +/* vendor-specific groups and attributes for system fd */ +#define KVM_X86_GRP_SEV 1 +# define KVM_X86_SEV_VMSA_FEATURES 0 struct kvm_vmx_nested_state_data { __u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; @@ -689,6 +694,9 @@ enum sev_cmd_id { /* Guest Migration Extension */ KVM_SEV_SEND_CANCEL, + /* Second time is the charm; improved versions of the above ioctls. */ + KVM_SEV_INIT2, + KVM_SEV_NR_MAX, }; @@ -700,6 +708,14 @@ struct kvm_sev_cmd { __u32 sev_fd; }; +struct kvm_sev_init { + __u64 vmsa_features; + __u32 flags; + __u16 ghcb_version; + __u16 pad1; + __u32 pad2[8]; +}; + struct kvm_sev_launch_start { __u32 handle; __u32 policy; @@ -856,5 +872,7 @@ struct kvm_hyperv_eventfd { #define KVM_X86_DEFAULT_VM 0 #define KVM_X86_SW_PROTECTED_VM 1 +#define KVM_X86_SEV_VM 2 +#define KVM_X86_SEV_ES_VM 3 #endif /* _ASM_X86_KVM_H */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index ea32b101b999..d03842abae57 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1221,9 +1221,9 @@ struct kvm_vfio_spapr_tce { /* Available with KVM_CAP_SPAPR_RESIZE_HPT */ #define KVM_PPC_RESIZE_HPT_PREPARE _IOR(KVMIO, 0xad, struct kvm_ppc_resize_hpt) #define KVM_PPC_RESIZE_HPT_COMMIT _IOR(KVMIO, 0xae, struct kvm_ppc_resize_hpt) -/* Available with KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_MMU_HASH_V3 */ +/* Available with KVM_CAP_PPC_MMU_RADIX or KVM_CAP_PPC_MMU_HASH_V3 */ #define KVM_PPC_CONFIGURE_V3_MMU _IOW(KVMIO, 0xaf, struct kvm_ppc_mmuv3_cfg) -/* Available with KVM_CAP_PPC_RADIX_MMU */ +/* Available with KVM_CAP_PPC_MMU_RADIX */ #define KVM_PPC_GET_RMMU_INFO _IOW(KVMIO, 0xb0, struct kvm_ppc_rmmu_info) /* Available with KVM_CAP_PPC_GET_CPU_CHAR */ #define KVM_PPC_GET_CPU_CHAR _IOR(KVMIO, 0xb1, struct kvm_ppc_cpu_char) -- cgit v1.2.3 From 2f523f29d3b19a668b8d4ce6f768d8faff976b3a Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 28 May 2024 16:54:31 -0300 Subject: tools headers UAPI: Update i915_drm.h with the kernel sources Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Kan Liang Cc: Namhyung Kim Link: https://lore.kernel.org/lkml/ Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/drm/i915_drm.h | 31 ++++++++++++++++++++++++++++--- 1 file changed, 28 insertions(+), 3 deletions(-) (limited to 'tools') diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 2ee338860b7e..d4d86e566e07 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -806,6 +806,12 @@ typedef struct drm_i915_irq_wait { */ #define I915_PARAM_PXP_STATUS 58 +/* + * Query if kernel allows marking a context to send a Freq hint to SLPC. This + * will enable use of the strategies allowed by the SLPC algorithm. + */ +#define I915_PARAM_HAS_CONTEXT_FREQ_HINT 59 + /* Must be kept compact -- no holes and well documented */ /** @@ -2148,6 +2154,15 @@ struct drm_i915_gem_context_param { * -EIO: The firmware did not succeed in creating the protected context. */ #define I915_CONTEXT_PARAM_PROTECTED_CONTENT 0xd + +/* + * I915_CONTEXT_PARAM_LOW_LATENCY: + * + * Mark this context as a low latency workload which requires aggressive GT + * frequency scaling. Use I915_PARAM_HAS_CONTEXT_FREQ_HINT to check if the kernel + * supports this per context flag. + */ +#define I915_CONTEXT_PARAM_LOW_LATENCY 0xe /* Must be kept compact -- no holes and well documented */ /** @value: Context parameter value to be set or queried */ @@ -2623,19 +2638,29 @@ struct drm_i915_reg_read { * */ +/* + * struct drm_i915_reset_stats - Return global reset and other context stats + * + * Driver keeps few stats for each contexts and also global reset count. + * This struct can be used to query those stats. + */ struct drm_i915_reset_stats { + /** @ctx_id: ID of the requested context */ __u32 ctx_id; + + /** @flags: MBZ */ __u32 flags; - /* All resets since boot/module reload, for all contexts */ + /** @reset_count: All resets since boot/module reload, for all contexts */ __u32 reset_count; - /* Number of batches lost when active in GPU, for this context */ + /** @batch_active: Number of batches lost when active in GPU, for this context */ __u32 batch_active; - /* Number of batches lost pending for execution, for this context */ + /** @batch_pending: Number of batches lost pending for execution, for this context */ __u32 batch_pending; + /** @pad: MBZ */ __u32 pad; }; -- cgit v1.2.3 From d6283b160a12010b2113cc64726a3c9eda13dc5f Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 29 May 2024 10:38:04 -0300 Subject: tools headers uapi: Sync linux/stat.h with the kernel sources to pick STATX_SUBVOL To pick the changes from: 2a82bb02941fb53d ("statx: stx_subvol") This silences this perf build warning: Warning: Kernel ABI header differences: diff -u tools/include/uapi/linux/stat.h include/uapi/linux/stat.h Cc: Adrian Hunter Cc: Christian Brauner Cc: Ian Rogers Cc: Jiri Olsa Cc: Kan Liang Cc: Kent Overstreet Cc: Namhyung Kim Link: https://lore.kernel.org/lkml/ZlnK2Fmx_gahzwZI@x1 Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/stat.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h index 2f2ee82d5517..67626d535316 100644 --- a/tools/include/uapi/linux/stat.h +++ b/tools/include/uapi/linux/stat.h @@ -126,8 +126,9 @@ struct statx { __u64 stx_mnt_id; __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */ __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */ + __u64 stx_subvol; /* Subvolume identifier */ /* 0xa0 */ - __u64 __spare3[12]; /* Spare space for future expansion */ + __u64 __spare3[11]; /* Spare space for future expansion */ /* 0x100 */ }; @@ -155,6 +156,7 @@ struct statx { #define STATX_MNT_ID 0x00001000U /* Got stx_mnt_id */ #define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */ #define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */ +#define STATX_SUBVOL 0x00008000U /* Want/got stx_subvol */ #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ -- cgit v1.2.3 From dc6abbbde4b099e936cd5428e196d86a5e119aae Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 3 Jun 2024 15:25:23 -0300 Subject: tools headers arm64: Sync arm64's cputype.h with the kernel sources To get the changes in: 0ce85db6c2141b7f ("arm64: cputype: Add Neoverse-V3 definitions") 02a0a04676fa7796 ("arm64: cputype: Add Cortex-X4 definitions") f4d9d9dcc70b96b5 ("arm64: Add Neoverse-V2 part") That makes this perf source code to be rebuilt: CC /tmp/build/perf-tools/util/arm-spe.o The changes in the above patch add MIDR_NEOVERSE_V[23] and MIDR_NEOVERSE_V1 is used in arm-spe.c, so probably we need to add those and perhaps MIDR_CORTEX_X4 to that array? Or maybe we need to leave this for later when this is all tested on those machines? static const struct midr_range neoverse_spe[] = { MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1), MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V1), {}, }; Mark Rutland recommended about arm-spe.c: "I would not touch this for now -- someone would have to go audit the TRMs to check that those other cores have the same encoding, and I think it'd be better to do that as a follow-up." That addresses this perf build warning: Warning: Kernel ABI header differences: diff -u tools/arch/arm64/include/asm/cputype.h arch/arm64/include/asm/cputype.h Acked-by: Mark Rutland Cc: Adrian Hunter Cc: Besar Wicaksono Cc: Ian Rogers Cc: Jiri Olsa Cc: Kan Liang Cc: Namhyung Kim Cc: Will Deacon Link: https://lore.kernel.org/lkml/Zl8cYk0Tai2fs7aM@x1 Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/arm64/include/asm/cputype.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'tools') diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h index 52f076afeb96..7b32b99023a2 100644 --- a/tools/arch/arm64/include/asm/cputype.h +++ b/tools/arch/arm64/include/asm/cputype.h @@ -86,6 +86,9 @@ #define ARM_CPU_PART_CORTEX_X2 0xD48 #define ARM_CPU_PART_NEOVERSE_N2 0xD49 #define ARM_CPU_PART_CORTEX_A78C 0xD4B +#define ARM_CPU_PART_NEOVERSE_V2 0xD4F +#define ARM_CPU_PART_CORTEX_X4 0xD82 +#define ARM_CPU_PART_NEOVERSE_V3 0xD84 #define APM_CPU_PART_XGENE 0x000 #define APM_CPU_VAR_POTENZA 0x00 @@ -159,6 +162,9 @@ #define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2) #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2) #define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C) +#define MIDR_NEOVERSE_V2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V2) +#define MIDR_CORTEX_X4 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X4) +#define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) -- cgit v1.2.3 From 5b3cde198878b2f3269d5e7efbc0d514899b1fd8 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 4 Jun 2024 11:00:22 -0300 Subject: Revert "perf record: Reduce memory for recording PERF_RECORD_LOST_SAMPLES event" This reverts commit 7d1405c71df21f6c394b8a885aa8a133f749fa22. This causes segfaults in some cases, as reported by Milian: ``` sudo /usr/bin/perf record -z --call-graph dwarf -e cycles -e raw_syscalls:sys_enter ls ... [ perf record: Woken up 3 times to write data ] malloc(): invalid next size (unsorted) Aborted ``` Backtrace with GDB + debuginfod: ``` malloc(): invalid next size (unsorted) Thread 1 "perf" received signal SIGABRT, Aborted. __pthread_kill_implementation (threadid=, signo=signo@entry=6, no_tid=no_tid@entry=0) at pthread_kill.c:44 Downloading source file /usr/src/debug/glibc/glibc/nptl/pthread_kill.c 44 return INTERNAL_SYSCALL_ERROR_P (ret) ? INTERNAL_SYSCALL_ERRNO (ret) : 0; (gdb) bt #0 __pthread_kill_implementation (threadid=, signo=signo@entry=6, no_tid=no_tid@entry=0) at pthread_kill.c:44 #1 0x00007ffff6ea8eb3 in __pthread_kill_internal (threadid=, signo=6) at pthread_kill.c:78 #2 0x00007ffff6e50a30 in __GI_raise (sig=sig@entry=6) at ../sysdeps/posix/ raise.c:26 #3 0x00007ffff6e384c3 in __GI_abort () at abort.c:79 #4 0x00007ffff6e39354 in __libc_message_impl (fmt=fmt@entry=0x7ffff6fc22ea "%s\n") at ../sysdeps/posix/libc_fatal.c:132 #5 0x00007ffff6eb3085 in malloc_printerr (str=str@entry=0x7ffff6fc5850 "malloc(): invalid next size (unsorted)") at malloc.c:5772 #6 0x00007ffff6eb657c in _int_malloc (av=av@entry=0x7ffff6ff6ac0 , bytes=bytes@entry=368) at malloc.c:4081 #7 0x00007ffff6eb877e in __libc_calloc (n=, elem_size=) at malloc.c:3754 #8 0x000055555569bdb6 in perf_session.do_write_header () #9 0x00005555555a373a in __cmd_record.constprop.0 () #10 0x00005555555a6846 in cmd_record () #11 0x000055555564db7f in run_builtin () #12 0x000055555558ed77 in main () ``` Valgrind memcheck: ``` ==45136== Invalid write of size 8 ==45136== at 0x2B38A5: perf_event__synthesize_id_sample (in /usr/bin/perf) ==45136== by 0x157069: __cmd_record.constprop.0 (in /usr/bin/perf) ==45136== by 0x15A845: cmd_record (in /usr/bin/perf) ==45136== by 0x201B7E: run_builtin (in /usr/bin/perf) ==45136== by 0x142D76: main (in /usr/bin/perf) ==45136== Address 0x6a866a8 is 0 bytes after a block of size 40 alloc'd ==45136== at 0x4849BF3: calloc (vg_replace_malloc.c:1675) ==45136== by 0x3574AB: zalloc (in /usr/bin/perf) ==45136== by 0x1570E0: __cmd_record.constprop.0 (in /usr/bin/perf) ==45136== by 0x15A845: cmd_record (in /usr/bin/perf) ==45136== by 0x201B7E: run_builtin (in /usr/bin/perf) ==45136== by 0x142D76: main (in /usr/bin/perf) ==45136== ==45136== Syscall param write(buf) points to unaddressable byte(s) ==45136== at 0x575953D: __libc_write (write.c:26) ==45136== by 0x575953D: write (write.c:24) ==45136== by 0x35761F: ion (in /usr/bin/perf) ==45136== by 0x357778: writen (in /usr/bin/perf) ==45136== by 0x1548F7: record__write (in /usr/bin/perf) ==45136== by 0x15708A: __cmd_record.constprop.0 (in /usr/bin/perf) ==45136== by 0x15A845: cmd_record (in /usr/bin/perf) ==45136== by 0x201B7E: run_builtin (in /usr/bin/perf) ==45136== by 0x142D76: main (in /usr/bin/perf) ==45136== Address 0x6a866a8 is 0 bytes after a block of size 40 alloc'd ==45136== at 0x4849BF3: calloc (vg_replace_malloc.c:1675) ==45136== by 0x3574AB: zalloc (in /usr/bin/perf) ==45136== by 0x1570E0: __cmd_record.constprop.0 (in /usr/bin/perf) ==45136== by 0x15A845: cmd_record (in /usr/bin/perf) ==45136== by 0x201B7E: run_builtin (in /usr/bin/perf) ==45136== by 0x142D76: main (in /usr/bin/perf) ==45136== ----- Closes: https://lore.kernel.org/linux-perf-users/23879991.0LEYPuXRzz@milian-workstation/ Reported-by: Milian Wolff Tested-by: Milian Wolff Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Kan Liang Cc: Namhyung Kim Cc: stable@kernel.org # 6.8+ Link: https://lore.kernel.org/lkml/Zl9ksOlHJHnKM70p@x1 Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 66a3de8ac661..0a8ba1323d64 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1956,8 +1956,7 @@ static void record__read_lost_samples(struct record *rec) if (count.lost) { if (!lost) { - lost = zalloc(sizeof(*lost) + - session->machines.host.id_hdr_size); + lost = zalloc(PERF_SAMPLE_MAX_SIZE); if (!lost) { pr_debug("Memory allocation failed\n"); return; @@ -1973,8 +1972,7 @@ static void record__read_lost_samples(struct record *rec) lost_count = perf_bpf_filter__lost_count(evsel); if (lost_count) { if (!lost) { - lost = zalloc(sizeof(*lost) + - session->machines.host.id_hdr_size); + lost = zalloc(PERF_SAMPLE_MAX_SIZE); if (!lost) { pr_debug("Memory allocation failed\n"); return; -- cgit v1.2.3 From ca9680821dfec73c9100860bda4fab1f1309722e Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 21 May 2024 10:07:40 -0700 Subject: perf bpf: Fix handling of minimal vmlinux.h file when interrupting the build Ingo reported that he was seeing these when hitting Control+C during a perf tools build: Makefile.perf:1149: *** Missing bpftool input for generating vmlinux.h. Stop. The failure happens when you don't have vmlinux.h or vmlinux with BTF. ifeq ($(VMLINUX_H),) ifeq ($(VMLINUX_BTF),) $(error Missing bpftool input for generating vmlinux.h) endif endif VMLINUX_BTF can be empty if you didn't build a kernel or it doesn't have a BTF section and the current kernel also has no BTF. This is totally ok. But VMLINUX_H should be set to the minimal version in the source tree (unless you overwrite it manually) when you don't pass GEN_VMLINUX_H=1 (which requires VMLINUX_BTF should not be empty). The problem is that it's defined in Makefile.config which is not included for `make clean`. Reported-by: Ingo Molnar Signed-off-by: Namhyung Kim Tested-by: Ingo Molnar Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Kan Liang Link: http://lore.kernel.org/lkml/CAM9d7ch5HTr+k+_GpbMrX0HUo5BZ11byh1xq0Two7B7RQACuNw@mail.gmail.com Link: http://lore.kernel.org/lkml/ZjssGrj+abyC6mYP@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.perf | 1 + 1 file changed, 1 insertion(+) (limited to 'tools') diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 5c35c0d89306..e6d56b555369 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -214,6 +214,7 @@ NON_CONFIG_TARGETS := clean python-clean TAGS tags cscope help ifdef MAKECMDGOALS ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),) + VMLINUX_H=$(src-perf)/util/bpf_skel/vmlinux/vmlinux.h config := 0 endif endif -- cgit v1.2.3 From 01c51a32dc18f128d2e55a7b2128b77fc01a2285 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 12 Apr 2024 10:43:29 +0200 Subject: KVM: s390x: selftests: Add shared zeropage test Let's test that we can have shared zeropages in our process as long as storage keys are not getting used, that shared zeropages are properly unshared (replaced by anonymous pages) once storage keys are enabled, and that no new shared zeropages are populated after storage keys were enabled. We require the new pagemap interface to detect the shared zeropage. On an old kernel (zeropages always disabled): # ./s390x/shared_zeropage_test TAP version 13 1..3 not ok 1 Shared zeropages should be enabled ok 2 Shared zeropage should be gone ok 3 Shared zeropages should be disabled # Totals: pass:2 fail:1 xfail:0 xpass:0 skip:0 error:0 On a fixed kernel: # ./s390x/shared_zeropage_test TAP version 13 1..3 ok 1 Shared zeropages should be enabled ok 2 Shared zeropage should be gone ok 3 Shared zeropages should be disabled # Totals: pass:3 fail:0 xfail:0 xpass:0 skip:0 error:0 Testing of UFFDIO_ZEROPAGE can be added later. [ agordeev: Fixed checkpatch complaint, added ucall_common.h include ] Cc: Christian Borntraeger Cc: Janosch Frank Cc: Claudio Imbrenda Cc: Thomas Huth Cc: Alexander Gordeev Cc: Paolo Bonzini Cc: Shuah Khan Signed-off-by: David Hildenbrand Acked-by: Christian Borntraeger Acked-by: Muhammad Usama Anjum Tested-by: Alexander Gordeev Link: https://lore.kernel.org/r/20240412084329.30315-1-david@redhat.com Signed-off-by: Alexander Gordeev --- tools/testing/selftests/kvm/Makefile | 1 + .../selftests/kvm/s390x/shared_zeropage_test.c | 111 +++++++++++++++++++++ 2 files changed, 112 insertions(+) create mode 100644 tools/testing/selftests/kvm/s390x/shared_zeropage_test.c (limited to 'tools') diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index ce8ff8e8ce3a..ac280dcba996 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -183,6 +183,7 @@ TEST_GEN_PROGS_s390x += s390x/sync_regs_test TEST_GEN_PROGS_s390x += s390x/tprot TEST_GEN_PROGS_s390x += s390x/cmma_test TEST_GEN_PROGS_s390x += s390x/debug_test +TEST_GEN_PROGS_s390x += s390x/shared_zeropage_test TEST_GEN_PROGS_s390x += demand_paging_test TEST_GEN_PROGS_s390x += dirty_log_test TEST_GEN_PROGS_s390x += guest_print_test diff --git a/tools/testing/selftests/kvm/s390x/shared_zeropage_test.c b/tools/testing/selftests/kvm/s390x/shared_zeropage_test.c new file mode 100644 index 000000000000..bba0d9a6dcc8 --- /dev/null +++ b/tools/testing/selftests/kvm/s390x/shared_zeropage_test.c @@ -0,0 +1,111 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Test shared zeropage handling (with/without storage keys) + * + * Copyright (C) 2024, Red Hat, Inc. + */ +#include + +#include + +#include "test_util.h" +#include "kvm_util.h" +#include "kselftest.h" +#include "ucall_common.h" + +static void set_storage_key(void *addr, uint8_t skey) +{ + asm volatile("sske %0,%1" : : "d" (skey), "a" (addr)); +} + +static void guest_code(void) +{ + /* Issue some storage key instruction. */ + set_storage_key((void *)0, 0x98); + GUEST_DONE(); +} + +/* + * Returns 1 if the shared zeropage is mapped, 0 if something else is mapped. + * Returns < 0 on error or if nothing is mapped. + */ +static int maps_shared_zeropage(int pagemap_fd, void *addr) +{ + struct page_region region; + struct pm_scan_arg arg = { + .start = (uintptr_t)addr, + .end = (uintptr_t)addr + 4096, + .vec = (uintptr_t)®ion, + .vec_len = 1, + .size = sizeof(struct pm_scan_arg), + .category_mask = PAGE_IS_PFNZERO, + .category_anyof_mask = PAGE_IS_PRESENT, + .return_mask = PAGE_IS_PFNZERO, + }; + return ioctl(pagemap_fd, PAGEMAP_SCAN, &arg); +} + +int main(int argc, char *argv[]) +{ + char *mem, *page0, *page1, *page2, tmp; + const size_t pagesize = getpagesize(); + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + struct ucall uc; + int pagemap_fd; + + ksft_print_header(); + ksft_set_plan(3); + + /* + * We'll use memory that is not mapped into the VM for simplicity. + * Shared zeropages are enabled/disabled per-process. + */ + mem = mmap(0, 3 * pagesize, PROT_READ, MAP_PRIVATE | MAP_ANON, -1, 0); + TEST_ASSERT(mem != MAP_FAILED, "mmap() failed"); + + /* Disable THP. Ignore errors on older kernels. */ + madvise(mem, 3 * pagesize, MADV_NOHUGEPAGE); + + page0 = mem; + page1 = page0 + pagesize; + page2 = page1 + pagesize; + + /* Can we even detect shared zeropages? */ + pagemap_fd = open("/proc/self/pagemap", O_RDONLY); + TEST_REQUIRE(pagemap_fd >= 0); + + tmp = *page0; + asm volatile("" : "+r" (tmp)); + TEST_REQUIRE(maps_shared_zeropage(pagemap_fd, page0) == 1); + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + + /* Verify that we get the shared zeropage after VM creation. */ + tmp = *page1; + asm volatile("" : "+r" (tmp)); + ksft_test_result(maps_shared_zeropage(pagemap_fd, page1) == 1, + "Shared zeropages should be enabled\n"); + + /* + * Let our VM execute a storage key instruction that should + * unshare all shared zeropages. + */ + vcpu_run(vcpu); + get_ucall(vcpu, &uc); + TEST_ASSERT_EQ(uc.cmd, UCALL_DONE); + + /* Verify that we don't have a shared zeropage anymore. */ + ksft_test_result(!maps_shared_zeropage(pagemap_fd, page1), + "Shared zeropage should be gone\n"); + + /* Verify that we don't get any new shared zeropages. */ + tmp = *page2; + asm volatile("" : "+r" (tmp)); + ksft_test_result(!maps_shared_zeropage(pagemap_fd, page2), + "Shared zeropages should be disabled\n"); + + kvm_vm_free(vm); + + ksft_finished(); +} -- cgit v1.2.3 From 6a09788c1a66e3d8b04b3b3e7618cc817bb60ae9 Mon Sep 17 00:00:00 2001 From: YonglongLi Date: Fri, 7 Jun 2024 17:01:49 +0200 Subject: mptcp: pm: inc RmAddr MIB counter once per RM_ADDR ID The RmAddr MIB counter is supposed to be incremented once when a valid RM_ADDR has been received. Before this patch, it could have been incremented as many times as the number of subflows connected to the linked address ID, so it could have been 0, 1 or more than 1. The "RmSubflow" is incremented after a local operation. In this case, it is normal to tied it with the number of subflows that have been actually removed. The "remove invalid addresses" MP Join subtest has been modified to validate this case. A broadcast IP address is now used instead: the client will not be able to create a subflow to this address. The consequence is that when receiving the RM_ADDR with the ID attached to this broadcast IP address, no subflow linked to this ID will be found. Fixes: 7a7e52e38a40 ("mptcp: add RM_ADDR related mibs") Cc: stable@vger.kernel.org Co-developed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: YonglongLi Signed-off-by: Matthieu Baerts (NGI0) Link: https://lore.kernel.org/r/20240607-upstream-net-20240607-misc-fixes-v1-2-1ab9ddfa3d00@kernel.org Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 2b66c5fa71eb..aea314d140c9 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -2250,7 +2250,8 @@ remove_tests() pm_nl_set_limits $ns1 3 3 pm_nl_add_endpoint $ns1 10.0.12.1 flags signal pm_nl_add_endpoint $ns1 10.0.3.1 flags signal - pm_nl_add_endpoint $ns1 10.0.14.1 flags signal + # broadcast IP: no packet for this address will be received on ns1 + pm_nl_add_endpoint $ns1 224.0.0.1 flags signal pm_nl_set_limits $ns2 3 3 addr_nr_ns1=-3 speed=10 \ run_tests $ns1 $ns2 10.0.1.1 -- cgit v1.2.3 From 40eec1795cc27b076d49236649a29507c7ed8c2d Mon Sep 17 00:00:00 2001 From: YonglongLi Date: Fri, 7 Jun 2024 17:01:50 +0200 Subject: mptcp: pm: update add_addr counters after connect The creation of new subflows can fail for different reasons. If no subflow have been created using the received ADD_ADDR, the related counters should not be updated, otherwise they will never be decremented for events related to this ID later on. For the moment, the number of accepted ADD_ADDR is only decremented upon the reception of a related RM_ADDR, and only if the remote address ID is currently being used by at least one subflow. In other words, if no subflow can be created with the received address, the counter will not be decremented. In this case, it is then important not to increment pm.add_addr_accepted counter, and not to modify pm.accept_addr bit. Note that this patch does not modify the behaviour in case of failures later on, e.g. if the MP Join is dropped or rejected. The "remove invalid addresses" MP Join subtest has been modified to validate this case. The broadcast IP address is added before the "valid" address that will be used to successfully create a subflow, and the limit is decreased by one: without this patch, it was not possible to create the last subflow, because: - the broadcast address would have been accepted even if it was not usable: the creation of a subflow to this address results in an error, - the limit of 2 accepted ADD_ADDR would have then been reached. Fixes: 01cacb00b35c ("mptcp: add netlink-based PM") Cc: stable@vger.kernel.org Co-developed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: YonglongLi Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://lore.kernel.org/r/20240607-upstream-net-20240607-misc-fixes-v1-3-1ab9ddfa3d00@kernel.org Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index aea314d140c9..108aeeb84ef1 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -2249,10 +2249,10 @@ remove_tests() if reset "remove invalid addresses"; then pm_nl_set_limits $ns1 3 3 pm_nl_add_endpoint $ns1 10.0.12.1 flags signal - pm_nl_add_endpoint $ns1 10.0.3.1 flags signal # broadcast IP: no packet for this address will be received on ns1 pm_nl_add_endpoint $ns1 224.0.0.1 flags signal - pm_nl_set_limits $ns2 3 3 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_set_limits $ns2 2 2 addr_nr_ns1=-3 speed=10 \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 -- cgit v1.2.3