aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/tools
diff options
context:
space:
mode:
Diffstat (limited to 'tools')
-rw-r--r--tools/arch/mips/include/uapi/asm/perf_regs.h40
-rw-r--r--tools/arch/x86/include/asm/asm.h193
-rw-r--r--tools/arch/x86/include/asm/disabled-features.h7
-rw-r--r--tools/arch/x86/include/asm/nops.h24
-rw-r--r--tools/bootconfig/include/linux/bootconfig.h4
-rw-r--r--tools/bootconfig/main.c1
-rw-r--r--tools/include/uapi/asm-generic/unistd.h3
-rw-r--r--tools/include/uapi/linux/in.h3
-rw-r--r--tools/include/uapi/linux/prctl.h8
-rw-r--r--tools/lib/bpf/xsk.c2
-rw-r--r--tools/objtool/arch/x86/decode.c6
-rw-r--r--tools/objtool/arch/x86/include/arch/special.h1
-rw-r--r--tools/objtool/check.c38
-rw-r--r--tools/objtool/elf.c135
-rw-r--r--tools/objtool/include/objtool/elf.h18
-rw-r--r--tools/objtool/include/objtool/objtool.h3
-rw-r--r--tools/objtool/include/objtool/special.h1
-rw-r--r--tools/objtool/special.c14
-rw-r--r--tools/perf/Makefile.config1
-rw-r--r--tools/perf/builtin-record.c6
-rwxr-xr-xtools/perf/check-headers.sh1
-rw-r--r--tools/perf/tests/attr/base-record2
-rwxr-xr-xtools/perf/tests/shell/stat_bpf_counters.sh4
-rw-r--r--tools/perf/trace/beauty/include/linux/socket.h2
-rw-r--r--tools/perf/util/bpf_counter.c6
-rw-r--r--tools/perf/util/dwarf-aux.c8
-rw-r--r--tools/perf/util/env.c1
-rw-r--r--tools/perf/util/evsel.c1
-rw-r--r--tools/perf/util/evsel.h4
-rw-r--r--tools/perf/util/machine.c3
-rw-r--r--tools/perf/util/metricgroup.c14
-rw-r--r--tools/perf/util/perf_api_probe.c10
-rw-r--r--tools/perf/util/perf_api_probe.h1
-rw-r--r--tools/perf/util/probe-finder.c3
-rw-r--r--tools/perf/util/session.c1
-rw-r--r--tools/perf/util/stat-display.c8
-rw-r--r--tools/perf/util/symbol-elf.c1
-rw-r--r--tools/testing/selftests/bpf/test_verifier.c2
-rw-r--r--tools/testing/selftests/bpf/verifier/and.c2
-rw-r--r--tools/testing/selftests/bpf/verifier/bounds.c14
-rw-r--r--tools/testing/selftests/bpf/verifier/dead_code.c2
-rw-r--r--tools/testing/selftests/bpf/verifier/jmp32.c22
-rw-r--r--tools/testing/selftests/bpf/verifier/jset.c10
-rw-r--r--tools/testing/selftests/bpf/verifier/unpriv.c2
-rw-r--r--tools/testing/selftests/bpf/verifier/value_ptr_arith.c7
-rw-r--r--tools/testing/selftests/futex/functional/.gitignore2
-rw-r--r--tools/testing/selftests/futex/functional/Makefile7
-rw-r--r--tools/testing/selftests/futex/functional/futex_requeue.c136
-rw-r--r--tools/testing/selftests/futex/functional/futex_wait.c171
-rw-r--r--tools/testing/selftests/futex/functional/futex_wait_timeout.c126
-rwxr-xr-xtools/testing/selftests/futex/functional/run.sh6
-rw-r--r--tools/testing/selftests/kvm/include/kvm_util.h10
-rw-r--r--tools/testing/selftests/kvm/kvm_page_table_test.c2
-rw-r--r--tools/testing/selftests/kvm/lib/kvm_util.c54
-rw-r--r--tools/testing/selftests/kvm/lib/perf_test_util.c2
-rw-r--r--tools/testing/selftests/kvm/lib/test_util.c38
-rw-r--r--tools/testing/selftests/kvm/memslot_perf_test.c2
-rw-r--r--tools/testing/selftests/kvm/set_memory_region_test.c4
-rwxr-xr-xtools/testing/selftests/net/fib_tests.sh25
-rwxr-xr-xtools/testing/selftests/net/icmp.sh74
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_connect.sh24
-rwxr-xr-xtools/testing/selftests/net/udpgro_fwd.sh2
-rwxr-xr-xtools/testing/selftests/net/veth.sh5
-rw-r--r--tools/testing/selftests/netfilter/Makefile2
-rwxr-xr-xtools/testing/selftests/netfilter/nft_fib.sh221
-rw-r--r--tools/testing/selftests/proc/.gitignore1
-rw-r--r--tools/testing/selftests/sched/.gitignore1
-rw-r--r--tools/testing/selftests/sched/Makefile14
-rw-r--r--tools/testing/selftests/sched/config1
-rw-r--r--tools/testing/selftests/sched/cs_prctl_test.c338
-rwxr-xr-xtools/testing/selftests/wireguard/netns.sh1
-rw-r--r--tools/testing/selftests/wireguard/qemu/kernel.config1
72 files changed, 1735 insertions, 174 deletions
diff --git a/tools/arch/mips/include/uapi/asm/perf_regs.h b/tools/arch/mips/include/uapi/asm/perf_regs.h
new file mode 100644
index 000000000000..d0f4ecd616cf
--- /dev/null
+++ b/tools/arch/mips/include/uapi/asm/perf_regs.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _ASM_MIPS_PERF_REGS_H
+#define _ASM_MIPS_PERF_REGS_H
+
+enum perf_event_mips_regs {
+ PERF_REG_MIPS_PC,
+ PERF_REG_MIPS_R1,
+ PERF_REG_MIPS_R2,
+ PERF_REG_MIPS_R3,
+ PERF_REG_MIPS_R4,
+ PERF_REG_MIPS_R5,
+ PERF_REG_MIPS_R6,
+ PERF_REG_MIPS_R7,
+ PERF_REG_MIPS_R8,
+ PERF_REG_MIPS_R9,
+ PERF_REG_MIPS_R10,
+ PERF_REG_MIPS_R11,
+ PERF_REG_MIPS_R12,
+ PERF_REG_MIPS_R13,
+ PERF_REG_MIPS_R14,
+ PERF_REG_MIPS_R15,
+ PERF_REG_MIPS_R16,
+ PERF_REG_MIPS_R17,
+ PERF_REG_MIPS_R18,
+ PERF_REG_MIPS_R19,
+ PERF_REG_MIPS_R20,
+ PERF_REG_MIPS_R21,
+ PERF_REG_MIPS_R22,
+ PERF_REG_MIPS_R23,
+ PERF_REG_MIPS_R24,
+ PERF_REG_MIPS_R25,
+ PERF_REG_MIPS_R26,
+ PERF_REG_MIPS_R27,
+ PERF_REG_MIPS_R28,
+ PERF_REG_MIPS_R29,
+ PERF_REG_MIPS_R30,
+ PERF_REG_MIPS_R31,
+ PERF_REG_MIPS_MAX = PERF_REG_MIPS_R31 + 1,
+};
+#endif /* _ASM_MIPS_PERF_REGS_H */
diff --git a/tools/arch/x86/include/asm/asm.h b/tools/arch/x86/include/asm/asm.h
new file mode 100644
index 000000000000..3ad3da9a7d97
--- /dev/null
+++ b/tools/arch/x86/include/asm/asm.h
@@ -0,0 +1,193 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_ASM_H
+#define _ASM_X86_ASM_H
+
+#ifdef __ASSEMBLY__
+# define __ASM_FORM(x, ...) x,## __VA_ARGS__
+# define __ASM_FORM_RAW(x, ...) x,## __VA_ARGS__
+# define __ASM_FORM_COMMA(x, ...) x,## __VA_ARGS__,
+#else
+#include <linux/stringify.h>
+# define __ASM_FORM(x, ...) " " __stringify(x,##__VA_ARGS__) " "
+# define __ASM_FORM_RAW(x, ...) __stringify(x,##__VA_ARGS__)
+# define __ASM_FORM_COMMA(x, ...) " " __stringify(x,##__VA_ARGS__) ","
+#endif
+
+#define _ASM_BYTES(x, ...) __ASM_FORM(.byte x,##__VA_ARGS__ ;)
+
+#ifndef __x86_64__
+/* 32 bit */
+# define __ASM_SEL(a,b) __ASM_FORM(a)
+# define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(a)
+#else
+/* 64 bit */
+# define __ASM_SEL(a,b) __ASM_FORM(b)
+# define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(b)
+#endif
+
+#define __ASM_SIZE(inst, ...) __ASM_SEL(inst##l##__VA_ARGS__, \
+ inst##q##__VA_ARGS__)
+#define __ASM_REG(reg) __ASM_SEL_RAW(e##reg, r##reg)
+
+#define _ASM_PTR __ASM_SEL(.long, .quad)
+#define _ASM_ALIGN __ASM_SEL(.balign 4, .balign 8)
+
+#define _ASM_MOV __ASM_SIZE(mov)
+#define _ASM_INC __ASM_SIZE(inc)
+#define _ASM_DEC __ASM_SIZE(dec)
+#define _ASM_ADD __ASM_SIZE(add)
+#define _ASM_SUB __ASM_SIZE(sub)
+#define _ASM_XADD __ASM_SIZE(xadd)
+#define _ASM_MUL __ASM_SIZE(mul)
+
+#define _ASM_AX __ASM_REG(ax)
+#define _ASM_BX __ASM_REG(bx)
+#define _ASM_CX __ASM_REG(cx)
+#define _ASM_DX __ASM_REG(dx)
+#define _ASM_SP __ASM_REG(sp)
+#define _ASM_BP __ASM_REG(bp)
+#define _ASM_SI __ASM_REG(si)
+#define _ASM_DI __ASM_REG(di)
+
+#ifndef __x86_64__
+/* 32 bit */
+
+#define _ASM_ARG1 _ASM_AX
+#define _ASM_ARG2 _ASM_DX
+#define _ASM_ARG3 _ASM_CX
+
+#define _ASM_ARG1L eax
+#define _ASM_ARG2L edx
+#define _ASM_ARG3L ecx
+
+#define _ASM_ARG1W ax
+#define _ASM_ARG2W dx
+#define _ASM_ARG3W cx
+
+#define _ASM_ARG1B al
+#define _ASM_ARG2B dl
+#define _ASM_ARG3B cl
+
+#else
+/* 64 bit */
+
+#define _ASM_ARG1 _ASM_DI
+#define _ASM_ARG2 _ASM_SI
+#define _ASM_ARG3 _ASM_DX
+#define _ASM_ARG4 _ASM_CX
+#define _ASM_ARG5 r8
+#define _ASM_ARG6 r9
+
+#define _ASM_ARG1Q rdi
+#define _ASM_ARG2Q rsi
+#define _ASM_ARG3Q rdx
+#define _ASM_ARG4Q rcx
+#define _ASM_ARG5Q r8
+#define _ASM_ARG6Q r9
+
+#define _ASM_ARG1L edi
+#define _ASM_ARG2L esi
+#define _ASM_ARG3L edx
+#define _ASM_ARG4L ecx
+#define _ASM_ARG5L r8d
+#define _ASM_ARG6L r9d
+
+#define _ASM_ARG1W di
+#define _ASM_ARG2W si
+#define _ASM_ARG3W dx
+#define _ASM_ARG4W cx
+#define _ASM_ARG5W r8w
+#define _ASM_ARG6W r9w
+
+#define _ASM_ARG1B dil
+#define _ASM_ARG2B sil
+#define _ASM_ARG3B dl
+#define _ASM_ARG4B cl
+#define _ASM_ARG5B r8b
+#define _ASM_ARG6B r9b
+
+#endif
+
+/*
+ * Macros to generate condition code outputs from inline assembly,
+ * The output operand must be type "bool".
+ */
+#ifdef __GCC_ASM_FLAG_OUTPUTS__
+# define CC_SET(c) "\n\t/* output condition code " #c "*/\n"
+# define CC_OUT(c) "=@cc" #c
+#else
+# define CC_SET(c) "\n\tset" #c " %[_cc_" #c "]\n"
+# define CC_OUT(c) [_cc_ ## c] "=qm"
+#endif
+
+#ifdef __KERNEL__
+
+/* Exception table entry */
+#ifdef __ASSEMBLY__
+# define _ASM_EXTABLE_HANDLE(from, to, handler) \
+ .pushsection "__ex_table","a" ; \
+ .balign 4 ; \
+ .long (from) - . ; \
+ .long (to) - . ; \
+ .long (handler) - . ; \
+ .popsection
+
+# define _ASM_EXTABLE(from, to) \
+ _ASM_EXTABLE_HANDLE(from, to, ex_handler_default)
+
+# define _ASM_EXTABLE_UA(from, to) \
+ _ASM_EXTABLE_HANDLE(from, to, ex_handler_uaccess)
+
+# define _ASM_EXTABLE_CPY(from, to) \
+ _ASM_EXTABLE_HANDLE(from, to, ex_handler_copy)
+
+# define _ASM_EXTABLE_FAULT(from, to) \
+ _ASM_EXTABLE_HANDLE(from, to, ex_handler_fault)
+
+# ifdef CONFIG_KPROBES
+# define _ASM_NOKPROBE(entry) \
+ .pushsection "_kprobe_blacklist","aw" ; \
+ _ASM_ALIGN ; \
+ _ASM_PTR (entry); \
+ .popsection
+# else
+# define _ASM_NOKPROBE(entry)
+# endif
+
+#else /* ! __ASSEMBLY__ */
+# define _EXPAND_EXTABLE_HANDLE(x) #x
+# define _ASM_EXTABLE_HANDLE(from, to, handler) \
+ " .pushsection \"__ex_table\",\"a\"\n" \
+ " .balign 4\n" \
+ " .long (" #from ") - .\n" \
+ " .long (" #to ") - .\n" \
+ " .long (" _EXPAND_EXTABLE_HANDLE(handler) ") - .\n" \
+ " .popsection\n"
+
+# define _ASM_EXTABLE(from, to) \
+ _ASM_EXTABLE_HANDLE(from, to, ex_handler_default)
+
+# define _ASM_EXTABLE_UA(from, to) \
+ _ASM_EXTABLE_HANDLE(from, to, ex_handler_uaccess)
+
+# define _ASM_EXTABLE_CPY(from, to) \
+ _ASM_EXTABLE_HANDLE(from, to, ex_handler_copy)
+
+# define _ASM_EXTABLE_FAULT(from, to) \
+ _ASM_EXTABLE_HANDLE(from, to, ex_handler_fault)
+
+/* For C file, we already have NOKPROBE_SYMBOL macro */
+
+/*
+ * This output constraint should be used for any inline asm which has a "call"
+ * instruction. Otherwise the asm may be inserted before the frame pointer
+ * gets set up by the containing function. If you forget to do this, objtool
+ * may print a "call without frame pointer save/setup" warning.
+ */
+register unsigned long current_stack_pointer asm(_ASM_SP);
+#define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer)
+#endif /* __ASSEMBLY__ */
+
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_X86_ASM_H */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index b7dd944dc867..8f28fafa98b3 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -56,11 +56,8 @@
# define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31))
#endif
-#ifdef CONFIG_IOMMU_SUPPORT
-# define DISABLE_ENQCMD 0
-#else
-# define DISABLE_ENQCMD (1 << (X86_FEATURE_ENQCMD & 31))
-#endif
+/* Force disable because it's broken beyond repair */
+#define DISABLE_ENQCMD (1 << (X86_FEATURE_ENQCMD & 31))
#ifdef CONFIG_X86_SGX
# define DISABLE_SGX 0
diff --git a/tools/arch/x86/include/asm/nops.h b/tools/arch/x86/include/asm/nops.h
index c1e5e818ba16..c5573eaa5bb9 100644
--- a/tools/arch/x86/include/asm/nops.h
+++ b/tools/arch/x86/include/asm/nops.h
@@ -2,6 +2,8 @@
#ifndef _ASM_X86_NOPS_H
#define _ASM_X86_NOPS_H
+#include <asm/asm.h>
+
/*
* Define nops for use with alternative() and for tracing.
*/
@@ -57,20 +59,14 @@
#endif /* CONFIG_64BIT */
-#ifdef __ASSEMBLY__
-#define _ASM_MK_NOP(x) .byte x
-#else
-#define _ASM_MK_NOP(x) ".byte " __stringify(x) "\n"
-#endif
-
-#define ASM_NOP1 _ASM_MK_NOP(BYTES_NOP1)
-#define ASM_NOP2 _ASM_MK_NOP(BYTES_NOP2)
-#define ASM_NOP3 _ASM_MK_NOP(BYTES_NOP3)
-#define ASM_NOP4 _ASM_MK_NOP(BYTES_NOP4)
-#define ASM_NOP5 _ASM_MK_NOP(BYTES_NOP5)
-#define ASM_NOP6 _ASM_MK_NOP(BYTES_NOP6)
-#define ASM_NOP7 _ASM_MK_NOP(BYTES_NOP7)
-#define ASM_NOP8 _ASM_MK_NOP(BYTES_NOP8)
+#define ASM_NOP1 _ASM_BYTES(BYTES_NOP1)
+#define ASM_NOP2 _ASM_BYTES(BYTES_NOP2)
+#define ASM_NOP3 _ASM_BYTES(BYTES_NOP3)
+#define ASM_NOP4 _ASM_BYTES(BYTES_NOP4)
+#define ASM_NOP5 _ASM_BYTES(BYTES_NOP5)
+#define ASM_NOP6 _ASM_BYTES(BYTES_NOP6)
+#define ASM_NOP7 _ASM_BYTES(BYTES_NOP7)
+#define ASM_NOP8 _ASM_BYTES(BYTES_NOP8)
#define ASM_NOP_MAX 8
diff --git a/tools/bootconfig/include/linux/bootconfig.h b/tools/bootconfig/include/linux/bootconfig.h
index 078cbd2ba651..de7f30f99af3 100644
--- a/tools/bootconfig/include/linux/bootconfig.h
+++ b/tools/bootconfig/include/linux/bootconfig.h
@@ -4,4 +4,8 @@
#include "../../../../include/linux/bootconfig.h"
+#ifndef fallthrough
+# define fallthrough
+#endif
+
#endif
diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c
index 7362bef1a368..6cd6080cac04 100644
--- a/tools/bootconfig/main.c
+++ b/tools/bootconfig/main.c
@@ -399,6 +399,7 @@ static int apply_xbc(const char *path, const char *xbc_path)
}
/* TODO: Ensure the @path is initramfs/initrd image */
if (fstat(fd, &stat) < 0) {
+ ret = -errno;
pr_err("Failed to get the size of %s\n", path);
goto out;
}
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 6de5a7fc066b..d2a942086fcb 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -863,8 +863,7 @@ __SYSCALL(__NR_process_madvise, sys_process_madvise)
__SC_COMP(__NR_epoll_pwait2, sys_epoll_pwait2, compat_sys_epoll_pwait2)
#define __NR_mount_setattr 442
__SYSCALL(__NR_mount_setattr, sys_mount_setattr)
-#define __NR_quotactl_path 443
-__SYSCALL(__NR_quotactl_path, sys_quotactl_path)
+/* 443 is reserved for quotactl_path */
#define __NR_landlock_create_ruleset 444
__SYSCALL(__NR_landlock_create_ruleset, sys_landlock_create_ruleset)
diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
index 7d6687618d80..d1b327036ae4 100644
--- a/tools/include/uapi/linux/in.h
+++ b/tools/include/uapi/linux/in.h
@@ -289,6 +289,9 @@ struct sockaddr_in {
/* Address indicating an error return. */
#define INADDR_NONE ((unsigned long int) 0xffffffff)
+/* Dummy address for src of ICMP replies if no real address is set (RFC7600). */
+#define INADDR_DUMMY ((unsigned long int) 0xc0000008)
+
/* Network number for local host loopback. */
#define IN_LOOPBACKNET 127
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index 18a9f59dc067..967d9c55323d 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -259,4 +259,12 @@ struct prctl_mm_map {
#define PR_PAC_SET_ENABLED_KEYS 60
#define PR_PAC_GET_ENABLED_KEYS 61
+/* Request the scheduler to share a core */
+#define PR_SCHED_CORE 62
+# define PR_SCHED_CORE_GET 0
+# define PR_SCHED_CORE_CREATE 1 /* create unique core_sched cookie */
+# define PR_SCHED_CORE_SHARE_TO 2 /* push core_sched cookie to pid */
+# define PR_SCHED_CORE_SHARE_FROM 3 /* pull core_sched cookie to pid */
+# define PR_SCHED_CORE_MAX 4
+
#endif /* _LINUX_PRCTL_H */
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 6061431ee04c..e9b619aa0cdf 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -1094,7 +1094,7 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
goto out_put_ctx;
}
if (xsk->fd == umem->fd)
- umem->rx_ring_setup_done = true;
+ umem->tx_ring_setup_done = true;
}
err = xsk_get_mmap_offsets(xsk->fd, &off);
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 24295d39713b..bc821056aba9 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -684,7 +684,7 @@ static int elf_add_alternative(struct elf *elf,
sec = find_section_by_name(elf, ".altinstructions");
if (!sec) {
sec = elf_create_section(elf, ".altinstructions",
- SHF_WRITE, size, 0);
+ SHF_ALLOC, size, 0);
if (!sec) {
WARN_ELF("elf_create_section");
@@ -747,6 +747,10 @@ int arch_rewrite_retpolines(struct objtool_file *file)
list_for_each_entry(insn, &file->retpoline_call_list, call_node) {
+ if (insn->type != INSN_JUMP_DYNAMIC &&
+ insn->type != INSN_CALL_DYNAMIC)
+ continue;
+
if (!strcmp(insn->sec->name, ".text.__x86.indirect_thunk"))
continue;
diff --git a/tools/objtool/arch/x86/include/arch/special.h b/tools/objtool/arch/x86/include/arch/special.h
index 14271cca0c74..f2918f789a0a 100644
--- a/tools/objtool/arch/x86/include/arch/special.h
+++ b/tools/objtool/arch/x86/include/arch/special.h
@@ -9,6 +9,7 @@
#define JUMP_ENTRY_SIZE 16
#define JUMP_ORIG_OFFSET 0
#define JUMP_NEW_OFFSET 4
+#define JUMP_KEY_OFFSET 8
#define ALT_ENTRY_SIZE 12
#define ALT_ORIG_OFFSET 0
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 9ed1a4cd00dc..e5947fbb9e7a 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -1225,15 +1225,41 @@ static int handle_jump_alt(struct objtool_file *file,
struct instruction *orig_insn,
struct instruction **new_insn)
{
- if (orig_insn->type == INSN_NOP)
- return 0;
+ if (orig_insn->type != INSN_JUMP_UNCONDITIONAL &&
+ orig_insn->type != INSN_NOP) {
- if (orig_insn->type != INSN_JUMP_UNCONDITIONAL) {
WARN_FUNC("unsupported instruction at jump label",
orig_insn->sec, orig_insn->offset);
return -1;
}
+ if (special_alt->key_addend & 2) {
+ struct reloc *reloc = insn_reloc(file, orig_insn);
+
+ if (reloc) {
+ reloc->type = R_NONE;
+ elf_write_reloc(file->elf, reloc);
+ }
+ elf_write_insn(file->elf, orig_insn->sec,
+ orig_insn->offset, orig_insn->len,
+ arch_nop_insn(orig_insn->len));
+ orig_insn->type = INSN_NOP;
+ }
+
+ if (orig_insn->type == INSN_NOP) {
+ if (orig_insn->len == 2)
+ file->jl_nop_short++;
+ else
+ file->jl_nop_long++;
+
+ return 0;
+ }
+
+ if (orig_insn->len == 2)
+ file->jl_short++;
+ else
+ file->jl_long++;
+
*new_insn = list_next_entry(orig_insn, list);
return 0;
}
@@ -1314,6 +1340,12 @@ static int add_special_section_alts(struct objtool_file *file)
free(special_alt);
}
+ if (stats) {
+ printf("jl\\\tNOP\tJMP\n");
+ printf("short:\t%ld\t%ld\n", file->jl_nop_short, file->jl_short);
+ printf("long:\t%ld\t%ld\n", file->jl_nop_long, file->jl_long);
+ }
+
out:
return ret;
}
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 743c2e9d0f56..8676c7598728 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -9,6 +9,7 @@
#include <sys/types.h>
#include <sys/stat.h>
+#include <sys/mman.h>
#include <fcntl.h>
#include <stdio.h>
#include <stdlib.h>
@@ -27,21 +28,27 @@ static inline u32 str_hash(const char *str)
return jhash(str, strlen(str), 0);
}
-static inline int elf_hash_bits(void)
-{
- return vmlinux ? ELF_HASH_BITS : 16;
-}
+#define __elf_table(name) (elf->name##_hash)
+#define __elf_bits(name) (elf->name##_bits)
-#define elf_hash_add(hashtable, node, key) \
- hlist_add_head(node, &hashtable[hash_min(key, elf_hash_bits())])
+#define elf_hash_add(name, node, key) \
+ hlist_add_head(node, &__elf_table(name)[hash_min(key, __elf_bits(name))])
-static void elf_hash_init(struct hlist_head *table)
-{
- __hash_init(table, 1U << elf_hash_bits());
-}
+#define elf_hash_for_each_possible(name, obj, member, key) \
+ hlist_for_each_entry(obj, &__elf_table(name)[hash_min(key, __elf_bits(name))], member)
-#define elf_hash_for_each_possible(name, obj, member, key) \
- hlist_for_each_entry(obj, &name[hash_min(key, elf_hash_bits())], member)
+#define elf_alloc_hash(name, size) \
+({ \
+ __elf_bits(name) = max(10, ilog2(size)); \
+ __elf_table(name) = mmap(NULL, sizeof(struct hlist_head) << __elf_bits(name), \
+ PROT_READ|PROT_WRITE, \
+ MAP_PRIVATE|MAP_ANON, -1, 0); \
+ if (__elf_table(name) == (void *)-1L) { \
+ WARN("mmap fail " #name); \
+ __elf_table(name) = NULL; \
+ } \
+ __elf_table(name); \
+})
static bool symbol_to_offset(struct rb_node *a, const struct rb_node *b)
{
@@ -80,9 +87,10 @@ struct section *find_section_by_name(const struct elf *elf, const char *name)
{
struct section *sec;
- elf_hash_for_each_possible(elf->section_name_hash, sec, name_hash, str_hash(name))
+ elf_hash_for_each_possible(section_name, sec, name_hash, str_hash(name)) {
if (!strcmp(sec->name, name))
return sec;
+ }
return NULL;
}
@@ -92,9 +100,10 @@ static struct section *find_section_by_index(struct elf *elf,
{
struct section *sec;
- elf_hash_for_each_possible(elf->section_hash, sec, hash, idx)
+ elf_hash_for_each_possible(section, sec, hash, idx) {
if (sec->idx == idx)
return sec;
+ }
return NULL;
}
@@ -103,9 +112,10 @@ static struct symbol *find_symbol_by_index(struct elf *elf, unsigned int idx)
{
struct symbol *sym;
- elf_hash_for_each_possible(elf->symbol_hash, sym, hash, idx)
+ elf_hash_for_each_possible(symbol, sym, hash, idx) {
if (sym->idx == idx)
return sym;
+ }
return NULL;
}
@@ -170,9 +180,10 @@ struct symbol *find_symbol_by_name(const struct elf *elf, const char *name)
{
struct symbol *sym;
- elf_hash_for_each_possible(elf->symbol_name_hash, sym, name_hash, str_hash(name))
+ elf_hash_for_each_possible(symbol_name, sym, name_hash, str_hash(name)) {
if (!strcmp(sym->name, name))
return sym;
+ }
return NULL;
}
@@ -189,8 +200,8 @@ struct reloc *find_reloc_by_dest_range(const struct elf *elf, struct section *se
sec = sec->reloc;
for_offset_range(o, offset, offset + len) {
- elf_hash_for_each_possible(elf->reloc_hash, reloc, hash,
- sec_offset_hash(sec, o)) {
+ elf_hash_for_each_possible(reloc, reloc, hash,
+ sec_offset_hash(sec, o)) {
if (reloc->sec != sec)
continue;
@@ -228,6 +239,10 @@ static int read_sections(struct elf *elf)
return -1;
}
+ if (!elf_alloc_hash(section, sections_nr) ||
+ !elf_alloc_hash(section_name, sections_nr))
+ return -1;
+
for (i = 0; i < sections_nr; i++) {
sec = malloc(sizeof(*sec));
if (!sec) {
@@ -273,13 +288,18 @@ static int read_sections(struct elf *elf)
}
sec->len = sec->sh.sh_size;
+ if (sec->sh.sh_flags & SHF_EXECINSTR)
+ elf->text_size += sec->len;
+
list_add_tail(&sec->list, &elf->sections);
- elf_hash_add(elf->section_hash, &sec->hash, sec->idx);
- elf_hash_add(elf->section_name_hash, &sec->name_hash, str_hash(sec->name));
+ elf_hash_add(section, &sec->hash, sec->idx);
+ elf_hash_add(section_name, &sec->name_hash, str_hash(sec->name));
}
- if (stats)
+ if (stats) {
printf("nr_sections: %lu\n", (unsigned long)sections_nr);
+ printf("section_bits: %d\n", elf->section_bits);
+ }
/* sanity check, one more call to elf_nextscn() should return NULL */
if (elf_nextscn(elf->elf, s)) {
@@ -308,8 +328,8 @@ static void elf_add_symbol(struct elf *elf, struct symbol *sym)
else
entry = &sym->sec->symbol_list;
list_add(&sym->list, entry);
- elf_hash_add(elf->symbol_hash, &sym->hash, sym->idx);
- elf_hash_add(elf->symbol_name_hash, &sym->name_hash, str_hash(sym->name));
+ elf_hash_add(symbol, &sym->hash, sym->idx);
+ elf_hash_add(symbol_name, &sym->name_hash, str_hash(sym->name));
/*
* Don't store empty STT_NOTYPE symbols in the rbtree. They
@@ -329,19 +349,25 @@ static int read_symbols(struct elf *elf)
Elf32_Word shndx;
symtab = find_section_by_name(elf, ".symtab");
- if (!symtab) {
+ if (symtab) {
+ symtab_shndx = find_section_by_name(elf, ".symtab_shndx");
+ if (symtab_shndx)
+ shndx_data = symtab_shndx->data;
+
+ symbols_nr = symtab->sh.sh_size / symtab->sh.sh_entsize;
+ } else {
/*
* A missing symbol table is actually possible if it's an empty
- * .o file. This can happen for thunk_64.o.
+ * .o file. This can happen for thunk_64.o. Make sure to at
+ * least allocate the symbol hash tables so we can do symbol
+ * lookups without crashing.
*/
- return 0;
+ symbols_nr = 0;
}
- symtab_shndx = find_section_by_name(elf, ".symtab_shndx");
- if (symtab_shndx)
- shndx_data = symtab_shndx->data;
-
- symbols_nr = symtab->sh.sh_size / symtab->sh.sh_entsize;
+ if (!elf_alloc_hash(symbol, symbols_nr) ||
+ !elf_alloc_hash(symbol_name, symbols_nr))
+ return -1;
for (i = 0; i < symbols_nr; i++) {
sym = malloc(sizeof(*sym));
@@ -389,8 +415,10 @@ static int read_symbols(struct elf *elf)
elf_add_symbol(elf, sym);
}
- if (stats)
+ if (stats) {
printf("nr_symbols: %lu\n", (unsigned long)symbols_nr);
+ printf("symbol_bits: %d\n", elf->symbol_bits);
+ }
/* Create parent/child links for any cold subfunctions */
list_for_each_entry(sec, &elf->sections, list) {
@@ -479,7 +507,7 @@ int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset,
reloc->addend = addend;
list_add_tail(&reloc->list, &sec->reloc->reloc_list);
- elf_hash_add(elf->reloc_hash, &reloc->hash, reloc_hash(reloc));
+ elf_hash_add(reloc, &reloc->hash, reloc_hash(reloc));
sec->reloc->changed = true;
@@ -556,6 +584,9 @@ static int read_relocs(struct elf *elf)
unsigned int symndx;
unsigned long nr_reloc, max_reloc = 0, tot_reloc = 0;
+ if (!elf_alloc_hash(reloc, elf->text_size / 16))
+ return -1;
+
list_for_each_entry(sec, &elf->sections, list) {
if ((sec->sh.sh_type != SHT_RELA) &&
(sec->sh.sh_type != SHT_REL))
@@ -600,7 +631,7 @@ static int read_relocs(struct elf *elf)
}
list_add_tail(&reloc->list, &sec->reloc_list);
- elf_hash_add(elf->reloc_hash, &reloc->hash, reloc_hash(reloc));
+ elf_hash_add(reloc, &reloc->hash, reloc_hash(reloc));
nr_reloc++;
}
@@ -611,6 +642,7 @@ static int read_relocs(struct elf *elf)
if (stats) {
printf("max_reloc: %lu\n", max_reloc);
printf("tot_reloc: %lu\n", tot_reloc);
+ printf("reloc_bits: %d\n", elf->reloc_bits);
}
return 0;
@@ -632,12 +664,6 @@ struct elf *elf_open_read(const char *name, int flags)
INIT_LIST_HEAD(&elf->sections);
- elf_hash_init(elf->symbol_hash);
- elf_hash_init(elf->symbol_name_hash);
- elf_hash_init(elf->section_hash);
- elf_hash_init(elf->section_name_hash);
- elf_hash_init(elf->reloc_hash);
-
elf->fd = open(name, flags);
if (elf->fd == -1) {
fprintf(stderr, "objtool: Can't open '%s': %s\n",
@@ -717,7 +743,7 @@ static int elf_add_string(struct elf *elf, struct section *strtab, char *str)
struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name)
{
- struct section *symtab;
+ struct section *symtab, *symtab_shndx;
struct symbol *sym;
Elf_Data *data;
Elf_Scn *s;
@@ -769,6 +795,29 @@ struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name)
symtab->len += data->d_size;
symtab->changed = true;
+ symtab_shndx = find_section_by_name(elf, ".symtab_shndx");
+ if (symtab_shndx) {
+ s = elf_getscn(elf->elf, symtab_shndx->idx);
+ if (!s) {
+ WARN_ELF("elf_getscn");
+ return NULL;
+ }
+
+ data = elf_newdata(s);
+ if (!data) {
+ WARN_ELF("elf_newdata");
+ return NULL;
+ }
+
+ data->d_buf = &sym->sym.st_size; /* conveniently 0 */
+ data->d_size = sizeof(Elf32_Word);
+ data->d_align = 4;
+ data->d_type = ELF_T_WORD;
+
+ symtab_shndx->len += 4;
+ symtab_shndx->changed = true;
+ }
+
sym->sec = find_section_by_index(elf, 0);
elf_add_symbol(elf, sym);
@@ -851,8 +900,8 @@ struct section *elf_create_section(struct elf *elf, const char *name,
return NULL;
list_add_tail(&sec->list, &elf->sections);
- elf_hash_add(elf->section_hash, &sec->hash, sec->idx);
- elf_hash_add(elf->section_name_hash, &sec->name_hash, str_hash(sec->name));
+ elf_hash_add(section, &sec->hash, sec->idx);
+ elf_hash_add(section_name, &sec->name_hash, str_hash(sec->name));
elf->changed = true;
diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h
index 45e5ede363b0..e34395047530 100644
--- a/tools/objtool/include/objtool/elf.h
+++ b/tools/objtool/include/objtool/elf.h
@@ -83,12 +83,20 @@ struct elf {
int fd;
bool changed;
char *name;
+ unsigned int text_size;
struct list_head sections;
- DECLARE_HASHTABLE(symbol_hash, ELF_HASH_BITS);
- DECLARE_HASHTABLE(symbol_name_hash, ELF_HASH_BITS);
- DECLARE_HASHTABLE(section_hash, ELF_HASH_BITS);
- DECLARE_HASHTABLE(section_name_hash, ELF_HASH_BITS);
- DECLARE_HASHTABLE(reloc_hash, ELF_HASH_BITS);
+
+ int symbol_bits;
+ int symbol_name_bits;
+ int section_bits;
+ int section_name_bits;
+ int reloc_bits;
+
+ struct hlist_head *symbol_hash;
+ struct hlist_head *symbol_name_hash;
+ struct hlist_head *section_hash;
+ struct hlist_head *section_name_hash;
+ struct hlist_head *reloc_hash;
};
#define OFFSET_STRIDE_BITS 4
diff --git a/tools/objtool/include/objtool/objtool.h b/tools/objtool/include/objtool/objtool.h
index e4084afb2304..24fa83634de4 100644
--- a/tools/objtool/include/objtool/objtool.h
+++ b/tools/objtool/include/objtool/objtool.h
@@ -22,6 +22,9 @@ struct objtool_file {
struct list_head static_call_list;
struct list_head mcount_loc_list;
bool ignore_unreachables, c_file, hints, rodata;
+
+ unsigned long jl_short, jl_long;
+ unsigned long jl_nop_short, jl_nop_long;
};
struct objtool_file *objtool_open_read(const char *_objname);
diff --git a/tools/objtool/include/objtool/special.h b/tools/objtool/include/objtool/special.h
index 8a09f4e9d480..dc4721e19002 100644
--- a/tools/objtool/include/objtool/special.h
+++ b/tools/objtool/include/objtool/special.h
@@ -27,6 +27,7 @@ struct special_alt {
unsigned long new_off;
unsigned int orig_len, new_len; /* group only */
+ u8 key_addend;
};
int special_get_alts(struct elf *elf, struct list_head *alts);
diff --git a/tools/objtool/special.c b/tools/objtool/special.c
index 07b21cfabf5c..bc925cf19e2d 100644
--- a/tools/objtool/special.c
+++ b/tools/objtool/special.c
@@ -23,6 +23,7 @@ struct special_entry {
unsigned char size, orig, new;
unsigned char orig_len, new_len; /* group only */
unsigned char feature; /* ALTERNATIVE macro CPU feature */
+ unsigned char key; /* jump_label key */
};
struct special_entry entries[] = {
@@ -42,6 +43,7 @@ struct special_entry entries[] = {
.size = JUMP_ENTRY_SIZE,
.orig = JUMP_ORIG_OFFSET,
.new = JUMP_NEW_OFFSET,
+ .key = JUMP_KEY_OFFSET,
},
{
.sec = "__ex_table",
@@ -122,6 +124,18 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry,
alt->new_off -= 0x7ffffff0;
}
+ if (entry->key) {
+ struct reloc *key_reloc;
+
+ key_reloc = find_reloc_by_dest(elf, sec, offset + entry->key);
+ if (!key_reloc) {
+ WARN_FUNC("can't find key reloc",
+ sec, offset + entry->key);
+ return -1;
+ }
+ alt->key_addend = key_reloc->addend;
+ }
+
return 0;
}
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 406a9519145e..73df23dd664c 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -90,7 +90,6 @@ endif
ifeq ($(ARCH),mips)
NO_PERF_REGS := 0
CFLAGS += -I$(OUTPUT)arch/mips/include/generated
- CFLAGS += -I../../arch/mips/include/uapi -I../../arch/mips/include/generated/uapi
LIBUNWIND_LIBS = -lunwind -lunwind-mips
endif
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 3337b5f93336..84803abeb942 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -2714,6 +2714,12 @@ int cmd_record(int argc, const char **argv)
rec->no_buildid = true;
}
+ if (rec->opts.record_cgroup && !perf_can_record_cgroup()) {
+ pr_err("Kernel has no cgroup sampling support.\n");
+ err = -EINVAL;
+ goto out_opts;
+ }
+
if (rec->opts.kcore)
rec->data.is_dir = true;
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index dd8ff287e930..c783558332b8 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -39,6 +39,7 @@ arch/x86/lib/x86-opcode-map.txt
arch/x86/tools/gen-insn-attr-x86.awk
arch/arm/include/uapi/asm/perf_regs.h
arch/arm64/include/uapi/asm/perf_regs.h
+arch/mips/include/uapi/asm/perf_regs.h
arch/powerpc/include/uapi/asm/perf_regs.h
arch/s390/include/uapi/asm/perf_regs.h
arch/x86/include/uapi/asm/perf_regs.h
diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record
index 4a7b8deef3fd..8c10955eff93 100644
--- a/tools/perf/tests/attr/base-record
+++ b/tools/perf/tests/attr/base-record
@@ -16,7 +16,7 @@ pinned=0
exclusive=0
exclude_user=0
exclude_kernel=0|1
-exclude_hv=0
+exclude_hv=0|1
exclude_idle=0
mmap=1
comm=1
diff --git a/tools/perf/tests/shell/stat_bpf_counters.sh b/tools/perf/tests/shell/stat_bpf_counters.sh
index 22eb31e48ca7..2f9948b3d943 100755
--- a/tools/perf/tests/shell/stat_bpf_counters.sh
+++ b/tools/perf/tests/shell/stat_bpf_counters.sh
@@ -11,9 +11,9 @@ compare_number()
second_num=$2
# upper bound is first_num * 110%
- upper=$(( $first_num + $first_num / 10 ))
+ upper=$(expr $first_num + $first_num / 10 )
# lower bound is first_num * 90%
- lower=$(( $first_num - $first_num / 10 ))
+ lower=$(expr $first_num - $first_num / 10 )
if [ $second_num -gt $upper ] || [ $second_num -lt $lower ]; then
echo "The difference between $first_num and $second_num are greater than 10%."
diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h
index b8fc5c53ba6f..0d8e3dcb7f88 100644
--- a/tools/perf/trace/beauty/include/linux/socket.h
+++ b/tools/perf/trace/beauty/include/linux/socket.h
@@ -438,6 +438,4 @@ extern int __sys_socketpair(int family, int type, int protocol,
int __user *usockvec);
extern int __sys_shutdown_sock(struct socket *sock, int how);
extern int __sys_shutdown(int fd, int how);
-
-extern struct ns_common *get_net_ns(struct ns_common *ns);
#endif /* _LINUX_SOCKET_H */
diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c
index 974f10e356f0..5ed674a2f55e 100644
--- a/tools/perf/util/bpf_counter.c
+++ b/tools/perf/util/bpf_counter.c
@@ -521,9 +521,10 @@ static int bperf__load(struct evsel *evsel, struct target *target)
evsel->bperf_leader_link_fd = bpf_link_get_fd_by_id(entry.link_id);
if (evsel->bperf_leader_link_fd < 0 &&
- bperf_reload_leader_program(evsel, attr_map_fd, &entry))
+ bperf_reload_leader_program(evsel, attr_map_fd, &entry)) {
+ err = -1;
goto out;
-
+ }
/*
* The bpf_link holds reference to the leader program, and the
* leader program holds reference to the maps. Therefore, if
@@ -550,6 +551,7 @@ static int bperf__load(struct evsel *evsel, struct target *target)
/* Step 2: load the follower skeleton */
evsel->follower_skel = bperf_follower_bpf__open();
if (!evsel->follower_skel) {
+ err = -1;
pr_err("Failed to open follower skeleton\n");
goto out;
}
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index b2f4920e19a6..7d2ba8419b0c 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -975,9 +975,13 @@ static int __die_find_variable_cb(Dwarf_Die *die_mem, void *data)
if ((tag == DW_TAG_formal_parameter ||
tag == DW_TAG_variable) &&
die_compare_name(die_mem, fvp->name) &&
- /* Does the DIE have location information or external instance? */
+ /*
+ * Does the DIE have location information or const value
+ * or external instance?
+ */
(dwarf_attr(die_mem, DW_AT_external, &attr) ||
- dwarf_attr(die_mem, DW_AT_location, &attr)))
+ dwarf_attr(die_mem, DW_AT_location, &attr) ||
+ dwarf_attr(die_mem, DW_AT_const_value, &attr)))
return DIE_FIND_CB_END;
if (dwarf_haspc(die_mem, fvp->addr))
return DIE_FIND_CB_CONTINUE;
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 9130f6fad8d5..bc5e4f294e9e 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -144,6 +144,7 @@ static void perf_env__purge_bpf(struct perf_env *env)
node = rb_entry(next, struct bpf_prog_info_node, rb_node);
next = rb_next(&node->rb_node);
rb_erase(&node->rb_node, root);
+ free(node->info_linear);
free(node);
}
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 4a3cd1b5bb33..a8d8463f8ee5 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -428,6 +428,7 @@ struct evsel *evsel__clone(struct evsel *orig)
evsel->auto_merge_stats = orig->auto_merge_stats;
evsel->collect_stat = orig->collect_stat;
evsel->weak_group = orig->weak_group;
+ evsel->use_config_name = orig->use_config_name;
if (evsel__copy_config_terms(evsel, orig) < 0)
goto out_err;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 75cf5dbfe208..bdad52a06438 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -83,8 +83,10 @@ struct evsel {
bool collect_stat;
bool weak_group;
bool bpf_counter;
+ bool use_config_name;
int bpf_fd;
struct bpf_object *bpf_obj;
+ struct list_head config_terms;
};
/*
@@ -116,10 +118,8 @@ struct evsel {
bool merged_stat;
bool reset_group;
bool errored;
- bool use_config_name;
struct hashmap *per_pkg_mask;
struct evsel *leader;
- struct list_head config_terms;
int err;
int cpu_iter;
struct {
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 3ff4936a15a4..da19be7da284 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -776,10 +776,10 @@ static int machine__process_ksymbol_register(struct machine *machine,
if (dso) {
dso->kernel = DSO_SPACE__KERNEL;
map = map__new2(0, dso);
+ dso__put(dso);
}
if (!dso || !map) {
- dso__put(dso);
return -ENOMEM;
}
@@ -792,6 +792,7 @@ static int machine__process_ksymbol_register(struct machine *machine,
map->start = event->ksymbol.addr;
map->end = map->start + event->ksymbol.len;
maps__insert(&machine->kmaps, map);
+ map__put(map);
dso__set_loaded(dso);
if (is_bpf_image(event->ksymbol.name)) {
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 8336dd8e8098..d3cf2dee36c8 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -162,10 +162,10 @@ static bool contains_event(struct evsel **metric_events, int num_events,
return false;
}
-static bool evsel_same_pmu(struct evsel *ev1, struct evsel *ev2)
+static bool evsel_same_pmu_or_none(struct evsel *ev1, struct evsel *ev2)
{
if (!ev1->pmu_name || !ev2->pmu_name)
- return false;
+ return true;
return !strcmp(ev1->pmu_name, ev2->pmu_name);
}
@@ -288,7 +288,7 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist,
*/
if (!has_constraint &&
ev->leader != metric_events[i]->leader &&
- evsel_same_pmu(ev->leader, metric_events[i]->leader))
+ evsel_same_pmu_or_none(ev->leader, metric_events[i]->leader))
break;
if (!strcmp(metric_events[i]->name, ev->name)) {
set_bit(ev->idx, evlist_used);
@@ -1073,16 +1073,18 @@ static int metricgroup__add_metric_sys_event_iter(struct pmu_event *pe,
ret = add_metric(d->metric_list, pe, d->metric_no_group, &m, NULL, d->ids);
if (ret)
- return ret;
+ goto out;
ret = resolve_metric(d->metric_no_group,
d->metric_list, NULL, d->ids);
if (ret)
- return ret;
+ goto out;
*(d->has_match) = true;
- return *d->ret;
+out:
+ *(d->ret) = ret;
+ return ret;
}
static int metricgroup__add_metric(const char *metric, bool metric_no_group,
diff --git a/tools/perf/util/perf_api_probe.c b/tools/perf/util/perf_api_probe.c
index 829af17a0867..020411682a3c 100644
--- a/tools/perf/util/perf_api_probe.c
+++ b/tools/perf/util/perf_api_probe.c
@@ -103,6 +103,11 @@ static void perf_probe_build_id(struct evsel *evsel)
evsel->core.attr.build_id = 1;
}
+static void perf_probe_cgroup(struct evsel *evsel)
+{
+ evsel->core.attr.cgroup = 1;
+}
+
bool perf_can_sample_identifier(void)
{
return perf_probe_api(perf_probe_sample_identifier);
@@ -182,3 +187,8 @@ bool perf_can_record_build_id(void)
{
return perf_probe_api(perf_probe_build_id);
}
+
+bool perf_can_record_cgroup(void)
+{
+ return perf_probe_api(perf_probe_cgroup);
+}
diff --git a/tools/perf/util/perf_api_probe.h b/tools/perf/util/perf_api_probe.h
index f12ca55f509a..b104168efb15 100644
--- a/tools/perf/util/perf_api_probe.h
+++ b/tools/perf/util/perf_api_probe.h
@@ -12,5 +12,6 @@ bool perf_can_record_switch_events(void);
bool perf_can_record_text_poke_events(void);
bool perf_can_sample_identifier(void);
bool perf_can_record_build_id(void);
+bool perf_can_record_cgroup(void);
#endif // __PERF_API_PROBE_H
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 866f2d514d72..b029c29ce227 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -190,6 +190,9 @@ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr,
immediate_value_is_supported()) {
Dwarf_Sword snum;
+ if (!tvar)
+ return 0;
+
dwarf_formsdata(&attr, &snum);
ret = asprintf(&tvar->value, "\\%ld", (long)snum);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 106b3d60881a..e59242c361ce 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1723,6 +1723,7 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset,
if (event->header.size < hdr_sz || event->header.size > buf_sz)
return -1;
+ buf += hdr_sz;
rest = event->header.size - hdr_sz;
if (readn(fd, buf, rest) != (ssize_t)rest)
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index a76fff5e7d83..ca326f98c7a2 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -541,7 +541,7 @@ static void uniquify_event_name(struct evsel *counter)
char *config;
int ret = 0;
- if (counter->uniquified_name ||
+ if (counter->uniquified_name || counter->use_config_name ||
!counter->pmu_name || !strncmp(counter->name, counter->pmu_name,
strlen(counter->pmu_name)))
return;
@@ -555,10 +555,8 @@ static void uniquify_event_name(struct evsel *counter)
}
} else {
if (perf_pmu__has_hybrid()) {
- if (!counter->use_config_name) {
- ret = asprintf(&new_name, "%s/%s/",
- counter->pmu_name, counter->name);
- }
+ ret = asprintf(&new_name, "%s/%s/",
+ counter->pmu_name, counter->name);
} else {
ret = asprintf(&new_name, "%s [%s]",
counter->name, counter->pmu_name);
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 4c56aa837434..a73345730ba9 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -2412,6 +2412,7 @@ int cleanup_sdt_note_list(struct list_head *sdt_notes)
list_for_each_entry_safe(pos, tmp, sdt_notes, note_list) {
list_del_init(&pos->note_list);
+ zfree(&pos->args);
zfree(&pos->name);
zfree(&pos->provider);
free(pos);
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 1512092e1e68..3a9e332c5e36 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -1147,7 +1147,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
}
}
- if (test->insn_processed) {
+ if (!unpriv && test->insn_processed) {
uint32_t insn_processed;
char *proc;
diff --git a/tools/testing/selftests/bpf/verifier/and.c b/tools/testing/selftests/bpf/verifier/and.c
index ca8fdb1b3f01..7d7ebee5cc7a 100644
--- a/tools/testing/selftests/bpf/verifier/and.c
+++ b/tools/testing/selftests/bpf/verifier/and.c
@@ -61,6 +61,8 @@
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R1 !read_ok",
+ .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 0
},
diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c
index 8a1caf46ffbc..e061e8799ce2 100644
--- a/tools/testing/selftests/bpf/verifier/bounds.c
+++ b/tools/testing/selftests/bpf/verifier/bounds.c
@@ -508,6 +508,8 @@
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, -1),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 invalid mem access 'inv'",
+ .result_unpriv = REJECT,
.result = ACCEPT
},
{
@@ -528,6 +530,8 @@
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, -1),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 invalid mem access 'inv'",
+ .result_unpriv = REJECT,
.result = ACCEPT
},
{
@@ -569,6 +573,8 @@
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 min value is outside of the allowed memory range",
+ .result_unpriv = REJECT,
.fixup_map_hash_8b = { 3 },
.result = ACCEPT,
},
@@ -589,6 +595,8 @@
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 min value is outside of the allowed memory range",
+ .result_unpriv = REJECT,
.fixup_map_hash_8b = { 3 },
.result = ACCEPT,
},
@@ -609,6 +617,8 @@
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 min value is outside of the allowed memory range",
+ .result_unpriv = REJECT,
.fixup_map_hash_8b = { 3 },
.result = ACCEPT,
},
@@ -674,6 +684,8 @@
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 min value is outside of the allowed memory range",
+ .result_unpriv = REJECT,
.fixup_map_hash_8b = { 3 },
.result = ACCEPT,
},
@@ -695,6 +707,8 @@
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 min value is outside of the allowed memory range",
+ .result_unpriv = REJECT,
.fixup_map_hash_8b = { 3 },
.result = ACCEPT,
},
diff --git a/tools/testing/selftests/bpf/verifier/dead_code.c b/tools/testing/selftests/bpf/verifier/dead_code.c
index 17fe33a75034..2c8935b3e65d 100644
--- a/tools/testing/selftests/bpf/verifier/dead_code.c
+++ b/tools/testing/selftests/bpf/verifier/dead_code.c
@@ -8,6 +8,8 @@
BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 10, -4),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R9 !read_ok",
+ .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 7,
},
diff --git a/tools/testing/selftests/bpf/verifier/jmp32.c b/tools/testing/selftests/bpf/verifier/jmp32.c
index bd5cae4a7f73..1c857b2fbdf0 100644
--- a/tools/testing/selftests/bpf/verifier/jmp32.c
+++ b/tools/testing/selftests/bpf/verifier/jmp32.c
@@ -87,6 +87,8 @@
BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R9 !read_ok",
+ .result_unpriv = REJECT,
.result = ACCEPT,
},
{
@@ -150,6 +152,8 @@
BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R9 !read_ok",
+ .result_unpriv = REJECT,
.result = ACCEPT,
},
{
@@ -213,6 +217,8 @@
BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R9 !read_ok",
+ .result_unpriv = REJECT,
.result = ACCEPT,
},
{
@@ -280,6 +286,8 @@
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 invalid mem access 'inv'",
+ .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 2,
},
@@ -348,6 +356,8 @@
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 invalid mem access 'inv'",
+ .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 2,
},
@@ -416,6 +426,8 @@
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 invalid mem access 'inv'",
+ .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 2,
},
@@ -484,6 +496,8 @@
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 invalid mem access 'inv'",
+ .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 2,
},
@@ -552,6 +566,8 @@
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 invalid mem access 'inv'",
+ .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 2,
},
@@ -620,6 +636,8 @@
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 invalid mem access 'inv'",
+ .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 2,
},
@@ -688,6 +706,8 @@
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 invalid mem access 'inv'",
+ .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 2,
},
@@ -756,6 +776,8 @@
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 invalid mem access 'inv'",
+ .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 2,
},
diff --git a/tools/testing/selftests/bpf/verifier/jset.c b/tools/testing/selftests/bpf/verifier/jset.c
index 8dcd4e0383d5..11fc68da735e 100644
--- a/tools/testing/selftests/bpf/verifier/jset.c
+++ b/tools/testing/selftests/bpf/verifier/jset.c
@@ -82,8 +82,8 @@
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
- .retval_unpriv = 1,
- .result_unpriv = ACCEPT,
+ .errstr_unpriv = "R9 !read_ok",
+ .result_unpriv = REJECT,
.retval = 1,
.result = ACCEPT,
},
@@ -141,7 +141,8 @@
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
- .result_unpriv = ACCEPT,
+ .errstr_unpriv = "R9 !read_ok",
+ .result_unpriv = REJECT,
.result = ACCEPT,
},
{
@@ -162,6 +163,7 @@
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
- .result_unpriv = ACCEPT,
+ .errstr_unpriv = "R9 !read_ok",
+ .result_unpriv = REJECT,
.result = ACCEPT,
},
diff --git a/tools/testing/selftests/bpf/verifier/unpriv.c b/tools/testing/selftests/bpf/verifier/unpriv.c
index bd436df5cc32..111801aea5e3 100644
--- a/tools/testing/selftests/bpf/verifier/unpriv.c
+++ b/tools/testing/selftests/bpf/verifier/unpriv.c
@@ -420,6 +420,8 @@
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R7 invalid mem access 'inv'",
+ .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 0,
},
diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
index 7ae2859d495c..a3e593ddfafc 100644
--- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
+++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
@@ -120,7 +120,7 @@
.fixup_map_array_48b = { 1 },
.result = ACCEPT,
.result_unpriv = REJECT,
- .errstr_unpriv = "R2 tried to add from different maps, paths or scalars",
+ .errstr_unpriv = "R2 pointer comparison prohibited",
.retval = 0,
},
{
@@ -159,7 +159,8 @@
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
// fake-dead code; targeted from branch A to
- // prevent dead code sanitization
+ // prevent dead code sanitization, rejected
+ // via branch B however
BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
@@ -167,7 +168,7 @@
.fixup_map_array_48b = { 1 },
.result = ACCEPT,
.result_unpriv = REJECT,
- .errstr_unpriv = "R2 tried to add from different maps, paths or scalars",
+ .errstr_unpriv = "R0 invalid mem access 'inv'",
.retval = 0,
},
{
diff --git a/tools/testing/selftests/futex/functional/.gitignore b/tools/testing/selftests/futex/functional/.gitignore
index 0efcd494daab..0e78b49d0f2f 100644
--- a/tools/testing/selftests/futex/functional/.gitignore
+++ b/tools/testing/selftests/futex/functional/.gitignore
@@ -6,3 +6,5 @@ futex_wait_private_mapped_file
futex_wait_timeout
futex_wait_uninitialized_heap
futex_wait_wouldblock
+futex_wait
+futex_requeue
diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile
index 23207829ec75..bd1fec59e010 100644
--- a/tools/testing/selftests/futex/functional/Makefile
+++ b/tools/testing/selftests/futex/functional/Makefile
@@ -1,5 +1,6 @@
# SPDX-License-Identifier: GPL-2.0
-INCLUDES := -I../include -I../../
+INCLUDES := -I../include -I../../ -I../../../../../usr/include/ \
+ -I$(KBUILD_OUTPUT)/kselftest/usr/include
CFLAGS := $(CFLAGS) -g -O2 -Wall -D_GNU_SOURCE -pthread $(INCLUDES)
LDLIBS := -lpthread -lrt
@@ -14,7 +15,9 @@ TEST_GEN_FILES := \
futex_requeue_pi_signal_restart \
futex_requeue_pi_mismatched_ops \
futex_wait_uninitialized_heap \
- futex_wait_private_mapped_file
+ futex_wait_private_mapped_file \
+ futex_wait \
+ futex_requeue
TEST_PROGS := run.sh
diff --git a/tools/testing/selftests/futex/functional/futex_requeue.c b/tools/testing/selftests/futex/functional/futex_requeue.c
new file mode 100644
index 000000000000..51485be6eb2f
--- /dev/null
+++ b/tools/testing/selftests/futex/functional/futex_requeue.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright Collabora Ltd., 2021
+ *
+ * futex cmp requeue test by André Almeida <andrealmeid@collabora.com>
+ */
+
+#include <pthread.h>
+#include <limits.h>
+#include "logging.h"
+#include "futextest.h"
+
+#define TEST_NAME "futex-requeue"
+#define timeout_ns 30000000
+#define WAKE_WAIT_US 10000
+
+volatile futex_t *f1;
+
+void usage(char *prog)
+{
+ printf("Usage: %s\n", prog);
+ printf(" -c Use color\n");
+ printf(" -h Display this help message\n");
+ printf(" -v L Verbosity level: %d=QUIET %d=CRITICAL %d=INFO\n",
+ VQUIET, VCRITICAL, VINFO);
+}
+
+void *waiterfn(void *arg)
+{
+ struct timespec to;
+
+ to.tv_sec = 0;
+ to.tv_nsec = timeout_ns;
+
+ if (futex_wait(f1, *f1, &to, 0))
+ printf("waiter failed errno %d\n", errno);
+
+ return NULL;
+}
+
+int main(int argc, char *argv[])
+{
+ pthread_t waiter[10];
+ int res, ret = RET_PASS;
+ int c, i;
+ volatile futex_t _f1 = 0;
+ volatile futex_t f2 = 0;
+
+ f1 = &_f1;
+
+ while ((c = getopt(argc, argv, "cht:v:")) != -1) {
+ switch (c) {
+ case 'c':
+ log_color(1);
+ break;
+ case 'h':
+ usage(basename(argv[0]));
+ exit(0);
+ case 'v':
+ log_verbosity(atoi(optarg));
+ break;
+ default:
+ usage(basename(argv[0]));
+ exit(1);
+ }
+ }
+
+ ksft_print_header();
+ ksft_set_plan(2);
+ ksft_print_msg("%s: Test futex_requeue\n",
+ basename(argv[0]));
+
+ /*
+ * Requeue a waiter from f1 to f2, and wake f2.
+ */
+ if (pthread_create(&waiter[0], NULL, waiterfn, NULL))
+ error("pthread_create failed\n", errno);
+
+ usleep(WAKE_WAIT_US);
+
+ info("Requeuing 1 futex from f1 to f2\n");
+ res = futex_cmp_requeue(f1, 0, &f2, 0, 1, 0);
+ if (res != 1) {
+ ksft_test_result_fail("futex_requeue simple returned: %d %s\n",
+ res ? errno : res,
+ res ? strerror(errno) : "");
+ ret = RET_FAIL;
+ }
+
+
+ info("Waking 1 futex at f2\n");
+ res = futex_wake(&f2, 1, 0);
+ if (res != 1) {
+ ksft_test_result_fail("futex_requeue simple returned: %d %s\n",
+ res ? errno : res,
+ res ? strerror(errno) : "");
+ ret = RET_FAIL;
+ } else {
+ ksft_test_result_pass("futex_requeue simple succeeds\n");
+ }
+
+
+ /*
+ * Create 10 waiters at f1. At futex_requeue, wake 3 and requeue 7.
+ * At futex_wake, wake INT_MAX (should be exactly 7).
+ */
+ for (i = 0; i < 10; i++) {
+ if (pthread_create(&waiter[i], NULL, waiterfn, NULL))
+ error("pthread_create failed\n", errno);
+ }
+
+ usleep(WAKE_WAIT_US);
+
+ info("Waking 3 futexes at f1 and requeuing 7 futexes from f1 to f2\n");
+ res = futex_cmp_requeue(f1, 0, &f2, 3, 7, 0);
+ if (res != 10) {
+ ksft_test_result_fail("futex_requeue many returned: %d %s\n",
+ res ? errno : res,
+ res ? strerror(errno) : "");
+ ret = RET_FAIL;
+ }
+
+ info("Waking INT_MAX futexes at f2\n");
+ res = futex_wake(&f2, INT_MAX, 0);
+ if (res != 7) {
+ ksft_test_result_fail("futex_requeue many returned: %d %s\n",
+ res ? errno : res,
+ res ? strerror(errno) : "");
+ ret = RET_FAIL;
+ } else {
+ ksft_test_result_pass("futex_requeue many succeeds\n");
+ }
+
+ ksft_print_cnts();
+ return ret;
+}
diff --git a/tools/testing/selftests/futex/functional/futex_wait.c b/tools/testing/selftests/futex/functional/futex_wait.c
new file mode 100644
index 000000000000..685140d9b93d
--- /dev/null
+++ b/tools/testing/selftests/futex/functional/futex_wait.c
@@ -0,0 +1,171 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright Collabora Ltd., 2021
+ *
+ * futex cmp requeue test by André Almeida <andrealmeid@collabora.com>
+ */
+
+#include <pthread.h>
+#include <sys/shm.h>
+#include <sys/mman.h>
+#include <fcntl.h>
+#include "logging.h"
+#include "futextest.h"
+
+#define TEST_NAME "futex-wait"
+#define timeout_ns 30000000
+#define WAKE_WAIT_US 10000
+#define SHM_PATH "futex_shm_file"
+
+void *futex;
+
+void usage(char *prog)
+{
+ printf("Usage: %s\n", prog);
+ printf(" -c Use color\n");
+ printf(" -h Display this help message\n");
+ printf(" -v L Verbosity level: %d=QUIET %d=CRITICAL %d=INFO\n",
+ VQUIET, VCRITICAL, VINFO);
+}
+
+static void *waiterfn(void *arg)
+{
+ struct timespec to;
+ unsigned int flags = 0;
+
+ if (arg)
+ flags = *((unsigned int *) arg);
+
+ to.tv_sec = 0;
+ to.tv_nsec = timeout_ns;
+
+ if (futex_wait(futex, 0, &to, flags))
+ printf("waiter failed errno %d\n", errno);
+
+ return NULL;
+}
+
+int main(int argc, char *argv[])
+{
+ int res, ret = RET_PASS, fd, c, shm_id;
+ u_int32_t f_private = 0, *shared_data;
+ unsigned int flags = FUTEX_PRIVATE_FLAG;
+ pthread_t waiter;
+ void *shm;
+
+ futex = &f_private;
+
+ while ((c = getopt(argc, argv, "cht:v:")) != -1) {
+ switch (c) {
+ case 'c':
+ log_color(1);
+ break;
+ case 'h':
+ usage(basename(argv[0]));
+ exit(0);
+ case 'v':
+ log_verbosity(atoi(optarg));
+ break;
+ default:
+ usage(basename(argv[0]));
+ exit(1);
+ }
+ }
+
+ ksft_print_header();
+ ksft_set_plan(3);
+ ksft_print_msg("%s: Test futex_wait\n", basename(argv[0]));
+
+ /* Testing a private futex */
+ info("Calling private futex_wait on futex: %p\n", futex);
+ if (pthread_create(&waiter, NULL, waiterfn, (void *) &flags))
+ error("pthread_create failed\n", errno);
+
+ usleep(WAKE_WAIT_US);
+
+ info("Calling private futex_wake on futex: %p\n", futex);
+ res = futex_wake(futex, 1, FUTEX_PRIVATE_FLAG);
+ if (res != 1) {
+ ksft_test_result_fail("futex_wake private returned: %d %s\n",
+ errno, strerror(errno));
+ ret = RET_FAIL;
+ } else {
+ ksft_test_result_pass("futex_wake private succeeds\n");
+ }
+
+ /* Testing an anon page shared memory */
+ shm_id = shmget(IPC_PRIVATE, 4096, IPC_CREAT | 0666);
+ if (shm_id < 0) {
+ perror("shmget");
+ exit(1);
+ }
+
+ shared_data = shmat(shm_id, NULL, 0);
+
+ *shared_data = 0;
+ futex = shared_data;
+
+ info("Calling shared (page anon) futex_wait on futex: %p\n", futex);
+ if (pthread_create(&waiter, NULL, waiterfn, NULL))
+ error("pthread_create failed\n", errno);
+
+ usleep(WAKE_WAIT_US);
+
+ info("Calling shared (page anon) futex_wake on futex: %p\n", futex);
+ res = futex_wake(futex, 1, 0);
+ if (res != 1) {
+ ksft_test_result_fail("futex_wake shared (page anon) returned: %d %s\n",
+ errno, strerror(errno));
+ ret = RET_FAIL;
+ } else {
+ ksft_test_result_pass("futex_wake shared (page anon) succeeds\n");
+ }
+
+
+ /* Testing a file backed shared memory */
+ fd = open(SHM_PATH, O_RDWR | O_CREAT, S_IRUSR | S_IWUSR);
+ if (fd < 0) {
+ perror("open");
+ exit(1);
+ }
+
+ if (ftruncate(fd, sizeof(f_private))) {
+ perror("ftruncate");
+ exit(1);
+ }
+
+ shm = mmap(NULL, sizeof(f_private), PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+ if (shm == MAP_FAILED) {
+ perror("mmap");
+ exit(1);
+ }
+
+ memcpy(shm, &f_private, sizeof(f_private));
+
+ futex = shm;
+
+ info("Calling shared (file backed) futex_wait on futex: %p\n", futex);
+ if (pthread_create(&waiter, NULL, waiterfn, NULL))
+ error("pthread_create failed\n", errno);
+
+ usleep(WAKE_WAIT_US);
+
+ info("Calling shared (file backed) futex_wake on futex: %p\n", futex);
+ res = futex_wake(shm, 1, 0);
+ if (res != 1) {
+ ksft_test_result_fail("futex_wake shared (file backed) returned: %d %s\n",
+ errno, strerror(errno));
+ ret = RET_FAIL;
+ } else {
+ ksft_test_result_pass("futex_wake shared (file backed) succeeds\n");
+ }
+
+ /* Freeing resources */
+ shmdt(shared_data);
+ munmap(shm, sizeof(f_private));
+ remove(SHM_PATH);
+ close(fd);
+
+ ksft_print_cnts();
+ return ret;
+}
diff --git a/tools/testing/selftests/futex/functional/futex_wait_timeout.c b/tools/testing/selftests/futex/functional/futex_wait_timeout.c
index ee55e6d389a3..1f8f6daaf1e7 100644
--- a/tools/testing/selftests/futex/functional/futex_wait_timeout.c
+++ b/tools/testing/selftests/futex/functional/futex_wait_timeout.c
@@ -11,21 +11,18 @@
*
* HISTORY
* 2009-Nov-6: Initial version by Darren Hart <dvhart@linux.intel.com>
+ * 2021-Apr-26: More test cases by André Almeida <andrealmeid@collabora.com>
*
*****************************************************************************/
-#include <errno.h>
-#include <getopt.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <time.h>
+#include <pthread.h>
#include "futextest.h"
#include "logging.h"
#define TEST_NAME "futex-wait-timeout"
static long timeout_ns = 100000; /* 100us default timeout */
+static futex_t futex_pi;
void usage(char *prog)
{
@@ -37,11 +34,67 @@ void usage(char *prog)
VQUIET, VCRITICAL, VINFO);
}
+/*
+ * Get a PI lock and hold it forever, so the main thread lock_pi will block
+ * and we can test the timeout
+ */
+void *get_pi_lock(void *arg)
+{
+ int ret;
+ volatile futex_t lock = 0;
+
+ ret = futex_lock_pi(&futex_pi, NULL, 0, 0);
+ if (ret != 0)
+ error("futex_lock_pi failed\n", ret);
+
+ /* Blocks forever */
+ ret = futex_wait(&lock, 0, NULL, 0);
+ error("futex_wait failed\n", ret);
+
+ return NULL;
+}
+
+/*
+ * Check if the function returned the expected error
+ */
+static void test_timeout(int res, int *ret, char *test_name, int err)
+{
+ if (!res || errno != err) {
+ ksft_test_result_fail("%s returned %d\n", test_name,
+ res < 0 ? errno : res);
+ *ret = RET_FAIL;
+ } else {
+ ksft_test_result_pass("%s succeeds\n", test_name);
+ }
+}
+
+/*
+ * Calculate absolute timeout and correct overflow
+ */
+static int futex_get_abs_timeout(clockid_t clockid, struct timespec *to,
+ long timeout_ns)
+{
+ if (clock_gettime(clockid, to)) {
+ error("clock_gettime failed\n", errno);
+ return errno;
+ }
+
+ to->tv_nsec += timeout_ns;
+
+ if (to->tv_nsec >= 1000000000) {
+ to->tv_sec++;
+ to->tv_nsec -= 1000000000;
+ }
+
+ return 0;
+}
+
int main(int argc, char *argv[])
{
futex_t f1 = FUTEX_INITIALIZER;
- struct timespec to;
int res, ret = RET_PASS;
+ struct timespec to;
+ pthread_t thread;
int c;
while ((c = getopt(argc, argv, "cht:v:")) != -1) {
@@ -65,22 +118,63 @@ int main(int argc, char *argv[])
}
ksft_print_header();
- ksft_set_plan(1);
+ ksft_set_plan(7);
ksft_print_msg("%s: Block on a futex and wait for timeout\n",
basename(argv[0]));
ksft_print_msg("\tArguments: timeout=%ldns\n", timeout_ns);
- /* initialize timeout */
+ pthread_create(&thread, NULL, get_pi_lock, NULL);
+
+ /* initialize relative timeout */
to.tv_sec = 0;
to.tv_nsec = timeout_ns;
- info("Calling futex_wait on f1: %u @ %p\n", f1, &f1);
- res = futex_wait(&f1, f1, &to, FUTEX_PRIVATE_FLAG);
- if (!res || errno != ETIMEDOUT) {
- fail("futex_wait returned %d\n", ret < 0 ? errno : ret);
- ret = RET_FAIL;
- }
+ res = futex_wait(&f1, f1, &to, 0);
+ test_timeout(res, &ret, "futex_wait relative", ETIMEDOUT);
+
+ /* FUTEX_WAIT_BITSET with CLOCK_REALTIME */
+ if (futex_get_abs_timeout(CLOCK_REALTIME, &to, timeout_ns))
+ return RET_FAIL;
+ res = futex_wait_bitset(&f1, f1, &to, 1, FUTEX_CLOCK_REALTIME);
+ test_timeout(res, &ret, "futex_wait_bitset realtime", ETIMEDOUT);
+
+ /* FUTEX_WAIT_BITSET with CLOCK_MONOTONIC */
+ if (futex_get_abs_timeout(CLOCK_MONOTONIC, &to, timeout_ns))
+ return RET_FAIL;
+ res = futex_wait_bitset(&f1, f1, &to, 1, 0);
+ test_timeout(res, &ret, "futex_wait_bitset monotonic", ETIMEDOUT);
+
+ /* FUTEX_WAIT_REQUEUE_PI with CLOCK_REALTIME */
+ if (futex_get_abs_timeout(CLOCK_REALTIME, &to, timeout_ns))
+ return RET_FAIL;
+ res = futex_wait_requeue_pi(&f1, f1, &futex_pi, &to, FUTEX_CLOCK_REALTIME);
+ test_timeout(res, &ret, "futex_wait_requeue_pi realtime", ETIMEDOUT);
+
+ /* FUTEX_WAIT_REQUEUE_PI with CLOCK_MONOTONIC */
+ if (futex_get_abs_timeout(CLOCK_MONOTONIC, &to, timeout_ns))
+ return RET_FAIL;
+ res = futex_wait_requeue_pi(&f1, f1, &futex_pi, &to, 0);
+ test_timeout(res, &ret, "futex_wait_requeue_pi monotonic", ETIMEDOUT);
+
+ /*
+ * FUTEX_LOCK_PI with CLOCK_REALTIME
+ * Due to historical reasons, FUTEX_LOCK_PI supports only realtime
+ * clock, but requires the caller to not set CLOCK_REALTIME flag.
+ *
+ * If you call FUTEX_LOCK_PI with a monotonic clock, it'll be
+ * interpreted as a realtime clock, and (unless you mess your machine's
+ * time or your time machine) the monotonic clock value is always
+ * smaller than realtime and the syscall will timeout immediately.
+ */
+ if (futex_get_abs_timeout(CLOCK_REALTIME, &to, timeout_ns))
+ return RET_FAIL;
+ res = futex_lock_pi(&futex_pi, &to, 0, 0);
+ test_timeout(res, &ret, "futex_lock_pi realtime", ETIMEDOUT);
+
+ /* Test operations that don't support FUTEX_CLOCK_REALTIME */
+ res = futex_lock_pi(&futex_pi, NULL, 0, FUTEX_CLOCK_REALTIME);
+ test_timeout(res, &ret, "futex_lock_pi invalid timeout flag", ENOSYS);
- print_result(TEST_NAME, ret);
+ ksft_print_cnts();
return ret;
}
diff --git a/tools/testing/selftests/futex/functional/run.sh b/tools/testing/selftests/futex/functional/run.sh
index 1acb6ace1680..11a9d62290f5 100755
--- a/tools/testing/selftests/futex/functional/run.sh
+++ b/tools/testing/selftests/futex/functional/run.sh
@@ -73,3 +73,9 @@ echo
echo
./futex_wait_uninitialized_heap $COLOR
./futex_wait_private_mapped_file $COLOR
+
+echo
+./futex_wait $COLOR
+
+echo
+./futex_requeue $COLOR
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index fcd8e3855111..35739567189e 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -43,6 +43,7 @@ enum vm_guest_mode {
VM_MODE_P40V48_4K,
VM_MODE_P40V48_64K,
VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */
+ VM_MODE_P47V64_4K,
NUM_VM_MODES,
};
@@ -60,7 +61,7 @@ enum vm_guest_mode {
#elif defined(__s390x__)
-#define VM_MODE_DEFAULT VM_MODE_P52V48_4K
+#define VM_MODE_DEFAULT VM_MODE_P47V64_4K
#define MIN_PAGE_SHIFT 12U
#define ptes_per_page(page_size) ((page_size) / 16)
@@ -285,10 +286,11 @@ struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_me
uint32_t num_percpu_pages, void *guest_code,
uint32_t vcpuids[]);
-/* Like vm_create_default_with_vcpus, but accepts mode as a parameter */
+/* Like vm_create_default_with_vcpus, but accepts mode and slot0 memory as a parameter */
struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus,
- uint64_t extra_mem_pages, uint32_t num_percpu_pages,
- void *guest_code, uint32_t vcpuids[]);
+ uint64_t slot0_mem_pages, uint64_t extra_mem_pages,
+ uint32_t num_percpu_pages, void *guest_code,
+ uint32_t vcpuids[]);
/*
* Adds a vCPU with reasonable defaults (e.g. a stack)
diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c
index 1c4753fff19e..82171f17c1d7 100644
--- a/tools/testing/selftests/kvm/kvm_page_table_test.c
+++ b/tools/testing/selftests/kvm/kvm_page_table_test.c
@@ -268,7 +268,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg)
/* Create a VM with enough guest pages */
guest_num_pages = test_mem_size / guest_page_size;
- vm = vm_create_with_vcpus(mode, nr_vcpus,
+ vm = vm_create_with_vcpus(mode, nr_vcpus, DEFAULT_GUEST_PHY_PAGES,
guest_num_pages, 0, guest_code, NULL);
/* Align down GPA of the testing memslot */
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 28e528c19d28..a2b732cf96ea 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -82,7 +82,7 @@ int kvm_check_cap(long cap)
kvm_fd = open_kvm_dev_path_or_exit();
ret = ioctl(kvm_fd, KVM_CHECK_EXTENSION, cap);
- TEST_ASSERT(ret != -1, "KVM_CHECK_EXTENSION IOCTL failed,\n"
+ TEST_ASSERT(ret >= 0, "KVM_CHECK_EXTENSION IOCTL failed,\n"
" rc: %i errno: %i", ret, errno);
close(kvm_fd);
@@ -175,6 +175,7 @@ const char *vm_guest_mode_string(uint32_t i)
[VM_MODE_P40V48_4K] = "PA-bits:40, VA-bits:48, 4K pages",
[VM_MODE_P40V48_64K] = "PA-bits:40, VA-bits:48, 64K pages",
[VM_MODE_PXXV48_4K] = "PA-bits:ANY, VA-bits:48, 4K pages",
+ [VM_MODE_P47V64_4K] = "PA-bits:47, VA-bits:64, 4K pages",
};
_Static_assert(sizeof(strings)/sizeof(char *) == NUM_VM_MODES,
"Missing new mode strings?");
@@ -192,6 +193,7 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = {
{ 40, 48, 0x1000, 12 },
{ 40, 48, 0x10000, 16 },
{ 0, 0, 0x1000, 12 },
+ { 47, 64, 0x1000, 12 },
};
_Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES,
"Missing new mode params?");
@@ -277,6 +279,9 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
TEST_FAIL("VM_MODE_PXXV48_4K not supported on non-x86 platforms");
#endif
break;
+ case VM_MODE_P47V64_4K:
+ vm->pgtable_levels = 5;
+ break;
default:
TEST_FAIL("Unknown guest mode, mode: 0x%x", mode);
}
@@ -308,21 +313,50 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
return vm;
}
+/*
+ * VM Create with customized parameters
+ *
+ * Input Args:
+ * mode - VM Mode (e.g. VM_MODE_P52V48_4K)
+ * nr_vcpus - VCPU count
+ * slot0_mem_pages - Slot0 physical memory size
+ * extra_mem_pages - Non-slot0 physical memory total size
+ * num_percpu_pages - Per-cpu physical memory pages
+ * guest_code - Guest entry point
+ * vcpuids - VCPU IDs
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Pointer to opaque structure that describes the created VM.
+ *
+ * Creates a VM with the mode specified by mode (e.g. VM_MODE_P52V48_4K),
+ * with customized slot0 memory size, at least 512 pages currently.
+ * extra_mem_pages is only used to calculate the maximum page table size,
+ * no real memory allocation for non-slot0 memory in this function.
+ */
struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus,
- uint64_t extra_mem_pages, uint32_t num_percpu_pages,
- void *guest_code, uint32_t vcpuids[])
+ uint64_t slot0_mem_pages, uint64_t extra_mem_pages,
+ uint32_t num_percpu_pages, void *guest_code,
+ uint32_t vcpuids[])
{
+ uint64_t vcpu_pages, extra_pg_pages, pages;
+ struct kvm_vm *vm;
+ int i;
+
+ /* Force slot0 memory size not small than DEFAULT_GUEST_PHY_PAGES */
+ if (slot0_mem_pages < DEFAULT_GUEST_PHY_PAGES)
+ slot0_mem_pages = DEFAULT_GUEST_PHY_PAGES;
+
/* The maximum page table size for a memory region will be when the
* smallest pages are used. Considering each page contains x page
* table descriptors, the total extra size for page tables (for extra
* N pages) will be: N/x+N/x^2+N/x^3+... which is definitely smaller
* than N/x*2.
*/
- uint64_t vcpu_pages = (DEFAULT_STACK_PGS + num_percpu_pages) * nr_vcpus;
- uint64_t extra_pg_pages = (extra_mem_pages + vcpu_pages) / PTES_PER_MIN_PAGE * 2;
- uint64_t pages = DEFAULT_GUEST_PHY_PAGES + extra_mem_pages + vcpu_pages + extra_pg_pages;
- struct kvm_vm *vm;
- int i;
+ vcpu_pages = (DEFAULT_STACK_PGS + num_percpu_pages) * nr_vcpus;
+ extra_pg_pages = (slot0_mem_pages + extra_mem_pages + vcpu_pages) / PTES_PER_MIN_PAGE * 2;
+ pages = slot0_mem_pages + vcpu_pages + extra_pg_pages;
TEST_ASSERT(nr_vcpus <= kvm_check_cap(KVM_CAP_MAX_VCPUS),
"nr_vcpus = %d too large for host, max-vcpus = %d",
@@ -354,8 +388,8 @@ struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_me
uint32_t num_percpu_pages, void *guest_code,
uint32_t vcpuids[])
{
- return vm_create_with_vcpus(VM_MODE_DEFAULT, nr_vcpus, extra_mem_pages,
- num_percpu_pages, guest_code, vcpuids);
+ return vm_create_with_vcpus(VM_MODE_DEFAULT, nr_vcpus, DEFAULT_GUEST_PHY_PAGES,
+ extra_mem_pages, num_percpu_pages, guest_code, vcpuids);
}
struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index abf381800a59..7397ca299835 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -69,7 +69,7 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0,
"Guest memory size is not guest page size aligned.");
- vm = vm_create_with_vcpus(mode, vcpus,
+ vm = vm_create_with_vcpus(mode, vcpus, DEFAULT_GUEST_PHY_PAGES,
(vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size,
0, guest_code, NULL);
diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c
index 6ad6c8276b2e..af1031fed97f 100644
--- a/tools/testing/selftests/kvm/lib/test_util.c
+++ b/tools/testing/selftests/kvm/lib/test_util.c
@@ -166,75 +166,75 @@ size_t get_def_hugetlb_pagesz(void)
return 0;
}
+#define ANON_FLAGS (MAP_PRIVATE | MAP_ANONYMOUS)
+#define ANON_HUGE_FLAGS (ANON_FLAGS | MAP_HUGETLB)
+
const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i)
{
- static const int anon_flags = MAP_PRIVATE | MAP_ANONYMOUS;
- static const int anon_huge_flags = anon_flags | MAP_HUGETLB;
-
static const struct vm_mem_backing_src_alias aliases[] = {
[VM_MEM_SRC_ANONYMOUS] = {
.name = "anonymous",
- .flag = anon_flags,
+ .flag = ANON_FLAGS,
},
[VM_MEM_SRC_ANONYMOUS_THP] = {
.name = "anonymous_thp",
- .flag = anon_flags,
+ .flag = ANON_FLAGS,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB] = {
.name = "anonymous_hugetlb",
- .flag = anon_huge_flags,
+ .flag = ANON_HUGE_FLAGS,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_16KB] = {
.name = "anonymous_hugetlb_16kb",
- .flag = anon_huge_flags | MAP_HUGE_16KB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_16KB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_64KB] = {
.name = "anonymous_hugetlb_64kb",
- .flag = anon_huge_flags | MAP_HUGE_64KB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_64KB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_512KB] = {
.name = "anonymous_hugetlb_512kb",
- .flag = anon_huge_flags | MAP_HUGE_512KB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_512KB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_1MB] = {
.name = "anonymous_hugetlb_1mb",
- .flag = anon_huge_flags | MAP_HUGE_1MB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_1MB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_2MB] = {
.name = "anonymous_hugetlb_2mb",
- .flag = anon_huge_flags | MAP_HUGE_2MB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_2MB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_8MB] = {
.name = "anonymous_hugetlb_8mb",
- .flag = anon_huge_flags | MAP_HUGE_8MB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_8MB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_16MB] = {
.name = "anonymous_hugetlb_16mb",
- .flag = anon_huge_flags | MAP_HUGE_16MB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_16MB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_32MB] = {
.name = "anonymous_hugetlb_32mb",
- .flag = anon_huge_flags | MAP_HUGE_32MB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_32MB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_256MB] = {
.name = "anonymous_hugetlb_256mb",
- .flag = anon_huge_flags | MAP_HUGE_256MB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_256MB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_512MB] = {
.name = "anonymous_hugetlb_512mb",
- .flag = anon_huge_flags | MAP_HUGE_512MB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_512MB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_1GB] = {
.name = "anonymous_hugetlb_1gb",
- .flag = anon_huge_flags | MAP_HUGE_1GB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_1GB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_2GB] = {
.name = "anonymous_hugetlb_2gb",
- .flag = anon_huge_flags | MAP_HUGE_2GB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_2GB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_16GB] = {
.name = "anonymous_hugetlb_16gb",
- .flag = anon_huge_flags | MAP_HUGE_16GB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_16GB,
},
[VM_MEM_SRC_SHMEM] = {
.name = "shmem",
diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c
index 9307f25d8130..11239652d805 100644
--- a/tools/testing/selftests/kvm/memslot_perf_test.c
+++ b/tools/testing/selftests/kvm/memslot_perf_test.c
@@ -267,7 +267,7 @@ static bool prepare_vm(struct vm_data *data, int nslots, uint64_t *maxslots,
data->hva_slots = malloc(sizeof(*data->hva_slots) * data->nslots);
TEST_ASSERT(data->hva_slots, "malloc() fail");
- data->vm = vm_create_default(VCPU_ID, 1024, guest_code);
+ data->vm = vm_create_default(VCPU_ID, mempages, guest_code);
pr_info_v("Adding slots 1..%i, each slot with %"PRIu64" pages + %"PRIu64" extra pages last\n",
max_mem_slots - 1, data->pages_per_slot, rempages);
diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c
index 978f5b5f4dc0..d8812f27648c 100644
--- a/tools/testing/selftests/kvm/set_memory_region_test.c
+++ b/tools/testing/selftests/kvm/set_memory_region_test.c
@@ -376,7 +376,7 @@ static void test_add_max_memory_regions(void)
pr_info("Adding slots 0..%i, each memory region with %dK size\n",
(max_mem_slots - 1), MEM_REGION_SIZE >> 10);
- mem = mmap(NULL, MEM_REGION_SIZE * max_mem_slots + alignment,
+ mem = mmap(NULL, (size_t)max_mem_slots * MEM_REGION_SIZE + alignment,
PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
TEST_ASSERT(mem != MAP_FAILED, "Failed to mmap() host");
mem_aligned = (void *)(((size_t) mem + alignment - 1) & ~(alignment - 1));
@@ -401,7 +401,7 @@ static void test_add_max_memory_regions(void)
TEST_ASSERT(ret == -1 && errno == EINVAL,
"Adding one more memory slot should fail with EINVAL");
- munmap(mem, MEM_REGION_SIZE * max_mem_slots + alignment);
+ munmap(mem, (size_t)max_mem_slots * MEM_REGION_SIZE + alignment);
munmap(mem_extra, MEM_REGION_SIZE);
kvm_vm_free(vm);
}
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 76d9487fb03c..5abe92d55b69 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -1384,12 +1384,37 @@ ipv4_rt_replace()
ipv4_rt_replace_mpath
}
+# checks that cached input route on VRF port is deleted
+# when VRF is deleted
+ipv4_local_rt_cache()
+{
+ run_cmd "ip addr add 10.0.0.1/32 dev lo"
+ run_cmd "ip netns add test-ns"
+ run_cmd "ip link add veth-outside type veth peer name veth-inside"
+ run_cmd "ip link add vrf-100 type vrf table 1100"
+ run_cmd "ip link set veth-outside master vrf-100"
+ run_cmd "ip link set veth-inside netns test-ns"
+ run_cmd "ip link set veth-outside up"
+ run_cmd "ip link set vrf-100 up"
+ run_cmd "ip route add 10.1.1.1/32 dev veth-outside table 1100"
+ run_cmd "ip netns exec test-ns ip link set veth-inside up"
+ run_cmd "ip netns exec test-ns ip addr add 10.1.1.1/32 dev veth-inside"
+ run_cmd "ip netns exec test-ns ip route add 10.0.0.1/32 dev veth-inside"
+ run_cmd "ip netns exec test-ns ip route add default via 10.0.0.1"
+ run_cmd "ip netns exec test-ns ping 10.0.0.1 -c 1 -i 1"
+ run_cmd "ip link delete vrf-100"
+
+ # if we do not hang test is a success
+ log_test $? 0 "Cached route removed from VRF port device"
+}
+
ipv4_route_test()
{
route_setup
ipv4_rt_add
ipv4_rt_replace
+ ipv4_local_rt_cache
route_cleanup
}
diff --git a/tools/testing/selftests/net/icmp.sh b/tools/testing/selftests/net/icmp.sh
new file mode 100755
index 000000000000..e4b04cd1644a
--- /dev/null
+++ b/tools/testing/selftests/net/icmp.sh
@@ -0,0 +1,74 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test for checking ICMP response with dummy address instead of 0.0.0.0.
+# Sets up two namespaces like:
+# +----------------------+ +--------------------+
+# | ns1 | v4-via-v6 routes: | ns2 |
+# | | ' | |
+# | +--------+ -> 172.16.1.0/24 -> +--------+ |
+# | | veth0 +--------------------------+ veth0 | |
+# | +--------+ <- 172.16.0.0/24 <- +--------+ |
+# | 172.16.0.1 | | 2001:db8:1::2/64 |
+# | 2001:db8:1::2/64 | | |
+# +----------------------+ +--------------------+
+#
+# And then tries to ping 172.16.1.1 from ns1. This results in a "net
+# unreachable" message being sent from ns2, but there is no IPv4 address set in
+# that address space, so the kernel should substitute the dummy address
+# 192.0.0.8 defined in RFC7600.
+
+NS1=ns1
+NS2=ns2
+H1_IP=172.16.0.1/32
+H1_IP6=2001:db8:1::1
+RT1=172.16.1.0/24
+PINGADDR=172.16.1.1
+RT2=172.16.0.0/24
+H2_IP6=2001:db8:1::2
+
+TMPFILE=$(mktemp)
+
+cleanup()
+{
+ rm -f "$TMPFILE"
+ ip netns del $NS1
+ ip netns del $NS2
+}
+
+trap cleanup EXIT
+
+# Namespaces
+ip netns add $NS1
+ip netns add $NS2
+
+# Connectivity
+ip -netns $NS1 link add veth0 type veth peer name veth0 netns $NS2
+ip -netns $NS1 link set dev veth0 up
+ip -netns $NS2 link set dev veth0 up
+ip -netns $NS1 addr add $H1_IP dev veth0
+ip -netns $NS1 addr add $H1_IP6/64 dev veth0 nodad
+ip -netns $NS2 addr add $H2_IP6/64 dev veth0 nodad
+ip -netns $NS1 route add $RT1 via inet6 $H2_IP6
+ip -netns $NS2 route add $RT2 via inet6 $H1_IP6
+
+# Make sure ns2 will respond with ICMP unreachable
+ip netns exec $NS2 sysctl -qw net.ipv4.icmp_ratelimit=0 net.ipv4.ip_forward=1
+
+# Run the test - a ping runs in the background, and we capture ICMP responses
+# with tcpdump; -c 1 means it should exit on the first ping, but add a timeout
+# in case something goes wrong
+ip netns exec $NS1 ping -w 3 -i 0.5 $PINGADDR >/dev/null &
+ip netns exec $NS1 timeout 10 tcpdump -tpni veth0 -c 1 'icmp and icmp[icmptype] != icmp-echo' > $TMPFILE 2>/dev/null
+
+# Parse response and check for dummy address
+# tcpdump output looks like:
+# IP 192.0.0.8 > 172.16.0.1: ICMP net 172.16.1.1 unreachable, length 92
+RESP_IP=$(awk '{print $2}' < $TMPFILE)
+if [[ "$RESP_IP" != "192.0.0.8" ]]; then
+ echo "FAIL - got ICMP response from $RESP_IP, should be 192.0.0.8"
+ exit 1
+else
+ echo "OK"
+ exit 0
+fi
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index 3c4cb72ed8a4..2b495dc8d78e 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -197,9 +197,6 @@ ip -net "$ns4" link set ns4eth3 up
ip -net "$ns4" route add default via 10.0.3.2
ip -net "$ns4" route add default via dead:beef:3::2
-# use TCP syn cookies, even if no flooding was detected.
-ip netns exec "$ns2" sysctl -q net.ipv4.tcp_syncookies=2
-
set_ethtool_flags() {
local ns="$1"
local dev="$2"
@@ -501,6 +498,7 @@ do_transfer()
local stat_ackrx_now_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableACKRX")
local stat_cookietx_now=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesSent")
local stat_cookierx_now=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesRecv")
+ local stat_ooo_now=$(get_mib_counter "${listener_ns}" "TcpExtTCPOFOQueue")
expect_synrx=$((stat_synrx_last_l))
expect_ackrx=$((stat_ackrx_last_l))
@@ -518,10 +516,14 @@ do_transfer()
"${stat_synrx_now_l}" "${expect_synrx}" 1>&2
retc=1
fi
- if [ ${stat_ackrx_now_l} -lt ${expect_ackrx} ]; then
- printf "[ FAIL ] lower MPC ACK rx (%d) than expected (%d)\n" \
- "${stat_ackrx_now_l}" "${expect_ackrx}" 1>&2
- rets=1
+ if [ ${stat_ackrx_now_l} -lt ${expect_ackrx} -a ${stat_ooo_now} -eq 0 ]; then
+ if [ ${stat_ooo_now} -eq 0 ]; then
+ printf "[ FAIL ] lower MPC ACK rx (%d) than expected (%d)\n" \
+ "${stat_ackrx_now_l}" "${expect_ackrx}" 1>&2
+ rets=1
+ else
+ printf "[ Note ] fallback due to TCP OoO"
+ fi
fi
if [ $retc -eq 0 ] && [ $rets -eq 0 ]; then
@@ -732,6 +734,14 @@ for sender in $ns1 $ns2 $ns3 $ns4;do
exit $ret
fi
+ # ns1<->ns2 is not subject to reordering/tc delays. Use it to test
+ # mptcp syncookie support.
+ if [ $sender = $ns1 ]; then
+ ip netns exec "$ns2" sysctl -q net.ipv4.tcp_syncookies=2
+ else
+ ip netns exec "$ns2" sysctl -q net.ipv4.tcp_syncookies=1
+ fi
+
run_tests "$ns2" $sender 10.0.1.2
run_tests "$ns2" $sender dead:beef:1::2
run_tests "$ns2" $sender 10.0.2.1
diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh
index a8fa64136282..7f26591f236b 100755
--- a/tools/testing/selftests/net/udpgro_fwd.sh
+++ b/tools/testing/selftests/net/udpgro_fwd.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
readonly BASE="ns-$(mktemp -u XXXXXX)"
diff --git a/tools/testing/selftests/net/veth.sh b/tools/testing/selftests/net/veth.sh
index 2fedc0781ce8..11d7cdb898c0 100755
--- a/tools/testing/selftests/net/veth.sh
+++ b/tools/testing/selftests/net/veth.sh
@@ -18,7 +18,8 @@ ret=0
cleanup() {
local ns
- local -r jobs="$(jobs -p)"
+ local jobs
+ readonly jobs="$(jobs -p)"
[ -n "${jobs}" ] && kill -1 ${jobs} 2>/dev/null
rm -f $STATS
@@ -108,7 +109,7 @@ chk_gro() {
if [ ! -f ../bpf/xdp_dummy.o ]; then
echo "Missing xdp_dummy helper. Build bpf selftest first"
- exit -1
+ exit 1
fi
create_ns
diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
index 3171069a6b46..cd6430b39982 100644
--- a/tools/testing/selftests/netfilter/Makefile
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
# Makefile for netfilter selftests
-TEST_PROGS := nft_trans_stress.sh nft_nat.sh bridge_brouter.sh \
+TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \
conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \
nft_concat_range.sh nft_conntrack_helper.sh \
nft_queue.sh nft_meta.sh nf_nat_edemux.sh \
diff --git a/tools/testing/selftests/netfilter/nft_fib.sh b/tools/testing/selftests/netfilter/nft_fib.sh
new file mode 100755
index 000000000000..6caf6ac8c285
--- /dev/null
+++ b/tools/testing/selftests/netfilter/nft_fib.sh
@@ -0,0 +1,221 @@
+#!/bin/bash
+#
+# This tests the fib expression.
+#
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+ret=0
+
+sfx=$(mktemp -u "XXXXXXXX")
+ns1="ns1-$sfx"
+ns2="ns2-$sfx"
+nsrouter="nsrouter-$sfx"
+timeout=4
+
+log_netns=$(sysctl -n net.netfilter.nf_log_all_netns)
+
+cleanup()
+{
+ ip netns del ${ns1}
+ ip netns del ${ns2}
+ ip netns del ${nsrouter}
+
+ [ $log_netns -eq 0 ] && sysctl -q net.netfilter.nf_log_all_netns=$log_netns
+}
+
+nft --version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without nft tool"
+ exit $ksft_skip
+fi
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without ip tool"
+ exit $ksft_skip
+fi
+
+ip netns add ${nsrouter}
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not create net namespace"
+ exit $ksft_skip
+fi
+
+trap cleanup EXIT
+
+dmesg | grep -q ' nft_rpfilter: '
+if [ $? -eq 0 ]; then
+ dmesg -c | grep ' nft_rpfilter: '
+ echo "WARN: a previous test run has failed" 1>&2
+fi
+
+sysctl -q net.netfilter.nf_log_all_netns=1
+ip netns add ${ns1}
+ip netns add ${ns2}
+
+load_ruleset() {
+ local netns=$1
+
+ip netns exec ${netns} nft -f /dev/stdin <<EOF
+table inet filter {
+ chain prerouting {
+ type filter hook prerouting priority 0; policy accept;
+ fib saddr . iif oif missing counter log prefix "$netns nft_rpfilter: " drop
+ }
+}
+EOF
+}
+
+load_ruleset_count() {
+ local netns=$1
+
+ip netns exec ${netns} nft -f /dev/stdin <<EOF
+table inet filter {
+ chain prerouting {
+ type filter hook prerouting priority 0; policy accept;
+ ip daddr 1.1.1.1 fib saddr . iif oif missing counter drop
+ ip6 daddr 1c3::c01d fib saddr . iif oif missing counter drop
+ }
+}
+EOF
+}
+
+check_drops() {
+ dmesg | grep -q ' nft_rpfilter: '
+ if [ $? -eq 0 ]; then
+ dmesg | grep ' nft_rpfilter: '
+ echo "FAIL: rpfilter did drop packets"
+ return 1
+ fi
+
+ return 0
+}
+
+check_fib_counter() {
+ local want=$1
+ local ns=$2
+ local address=$3
+
+ line=$(ip netns exec ${ns} nft list table inet filter | grep 'fib saddr . iif' | grep $address | grep "packets $want" )
+ ret=$?
+
+ if [ $ret -ne 0 ];then
+ echo "Netns $ns fib counter doesn't match expected packet count of $want for $address" 1>&2
+ ip netns exec ${ns} nft list table inet filter
+ return 1
+ fi
+
+ if [ $want -gt 0 ]; then
+ echo "PASS: fib expression did drop packets for $address"
+ fi
+
+ return 0
+}
+
+load_ruleset ${nsrouter}
+load_ruleset ${ns1}
+load_ruleset ${ns2}
+
+ip link add veth0 netns ${nsrouter} type veth peer name eth0 netns ${ns1} > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: No virtual ethernet pair device support in kernel"
+ exit $ksft_skip
+fi
+ip link add veth1 netns ${nsrouter} type veth peer name eth0 netns ${ns2}
+
+ip -net ${nsrouter} link set lo up
+ip -net ${nsrouter} link set veth0 up
+ip -net ${nsrouter} addr add 10.0.1.1/24 dev veth0
+ip -net ${nsrouter} addr add dead:1::1/64 dev veth0
+
+ip -net ${nsrouter} link set veth1 up
+ip -net ${nsrouter} addr add 10.0.2.1/24 dev veth1
+ip -net ${nsrouter} addr add dead:2::1/64 dev veth1
+
+ip -net ${ns1} link set lo up
+ip -net ${ns1} link set eth0 up
+
+ip -net ${ns2} link set lo up
+ip -net ${ns2} link set eth0 up
+
+ip -net ${ns1} addr add 10.0.1.99/24 dev eth0
+ip -net ${ns1} addr add dead:1::99/64 dev eth0
+ip -net ${ns1} route add default via 10.0.1.1
+ip -net ${ns1} route add default via dead:1::1
+
+ip -net ${ns2} addr add 10.0.2.99/24 dev eth0
+ip -net ${ns2} addr add dead:2::99/64 dev eth0
+ip -net ${ns2} route add default via 10.0.2.1
+ip -net ${ns2} route add default via dead:2::1
+
+test_ping() {
+ local daddr4=$1
+ local daddr6=$2
+
+ ip netns exec ${ns1} ping -c 1 -q $daddr4 > /dev/null
+ ret=$?
+ if [ $ret -ne 0 ];then
+ check_drops
+ echo "FAIL: ${ns1} cannot reach $daddr4, ret $ret" 1>&2
+ return 1
+ fi
+
+ ip netns exec ${ns1} ping -c 3 -q $daddr6 > /dev/null
+ ret=$?
+ if [ $ret -ne 0 ];then
+ check_drops
+ echo "FAIL: ${ns1} cannot reach $daddr6, ret $ret" 1>&2
+ return 1
+ fi
+
+ return 0
+}
+
+ip netns exec ${nsrouter} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
+ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
+ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
+
+sleep 3
+
+test_ping 10.0.2.1 dead:2::1 || exit 1
+check_drops || exit 1
+
+test_ping 10.0.2.99 dead:2::99 || exit 1
+check_drops || exit 1
+
+echo "PASS: fib expression did not cause unwanted packet drops"
+
+ip netns exec ${nsrouter} nft flush table inet filter
+
+ip -net ${ns1} route del default
+ip -net ${ns1} -6 route del default
+
+ip -net ${ns1} addr del 10.0.1.99/24 dev eth0
+ip -net ${ns1} addr del dead:1::99/64 dev eth0
+
+ip -net ${ns1} addr add 10.0.2.99/24 dev eth0
+ip -net ${ns1} addr add dead:2::99/64 dev eth0
+
+ip -net ${ns1} route add default via 10.0.2.1
+ip -net ${ns1} -6 route add default via dead:2::1
+
+ip -net ${nsrouter} addr add dead:2::1/64 dev veth0
+
+# switch to ruleset that doesn't log, this time
+# its expected that this does drop the packets.
+load_ruleset_count ${nsrouter}
+
+# ns1 has a default route, but nsrouter does not.
+# must not check return value, ping to 1.1.1.1 will
+# fail.
+check_fib_counter 0 ${nsrouter} 1.1.1.1 || exit 1
+check_fib_counter 0 ${nsrouter} 1c3::c01d || exit 1
+
+ip netns exec ${ns1} ping -c 1 -W 1 -q 1.1.1.1 > /dev/null
+check_fib_counter 1 ${nsrouter} 1.1.1.1 || exit 1
+
+sleep 2
+ip netns exec ${ns1} ping -c 3 -q 1c3::c01d > /dev/null
+check_fib_counter 3 ${nsrouter} 1c3::c01d || exit 1
+
+exit 0
diff --git a/tools/testing/selftests/proc/.gitignore b/tools/testing/selftests/proc/.gitignore
index bed4b5318a86..8f3e72e626fa 100644
--- a/tools/testing/selftests/proc/.gitignore
+++ b/tools/testing/selftests/proc/.gitignore
@@ -10,6 +10,7 @@
/proc-self-map-files-002
/proc-self-syscall
/proc-self-wchan
+/proc-subset-pid
/proc-uptime-001
/proc-uptime-002
/read
diff --git a/tools/testing/selftests/sched/.gitignore b/tools/testing/selftests/sched/.gitignore
new file mode 100644
index 000000000000..6996d4654d92
--- /dev/null
+++ b/tools/testing/selftests/sched/.gitignore
@@ -0,0 +1 @@
+cs_prctl_test
diff --git a/tools/testing/selftests/sched/Makefile b/tools/testing/selftests/sched/Makefile
new file mode 100644
index 000000000000..10c72f14fea9
--- /dev/null
+++ b/tools/testing/selftests/sched/Makefile
@@ -0,0 +1,14 @@
+# SPDX-License-Identifier: GPL-2.0+
+
+ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep clang),)
+CLANG_FLAGS += -no-integrated-as
+endif
+
+CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -Wl,-rpath=./ \
+ $(CLANG_FLAGS)
+LDLIBS += -lpthread
+
+TEST_GEN_FILES := cs_prctl_test
+TEST_PROGS := cs_prctl_test
+
+include ../lib.mk
diff --git a/tools/testing/selftests/sched/config b/tools/testing/selftests/sched/config
new file mode 100644
index 000000000000..e8b09aa7c0c4
--- /dev/null
+++ b/tools/testing/selftests/sched/config
@@ -0,0 +1 @@
+CONFIG_SCHED_DEBUG=y
diff --git a/tools/testing/selftests/sched/cs_prctl_test.c b/tools/testing/selftests/sched/cs_prctl_test.c
new file mode 100644
index 000000000000..63fe6521c56d
--- /dev/null
+++ b/tools/testing/selftests/sched/cs_prctl_test.c
@@ -0,0 +1,338 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Use the core scheduling prctl() to test core scheduling cookies control.
+ *
+ * Copyright (c) 2021 Oracle and/or its affiliates.
+ * Author: Chris Hyser <chris.hyser@oracle.com>
+ *
+ *
+ * This library is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU Lesser General Public License
+ * along with this library; if not, see <http://www.gnu.org/licenses>.
+ */
+
+#define _GNU_SOURCE
+#include <sys/eventfd.h>
+#include <sys/wait.h>
+#include <sys/types.h>
+#include <sched.h>
+#include <sys/prctl.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <time.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#if __GLIBC_PREREQ(2, 30) == 0
+#include <sys/syscall.h>
+static pid_t gettid(void)
+{
+ return syscall(SYS_gettid);
+}
+#endif
+
+#ifndef PR_SCHED_CORE
+#define PR_SCHED_CORE 62
+# define PR_SCHED_CORE_GET 0
+# define PR_SCHED_CORE_CREATE 1 /* create unique core_sched cookie */
+# define PR_SCHED_CORE_SHARE_TO 2 /* push core_sched cookie to pid */
+# define PR_SCHED_CORE_SHARE_FROM 3 /* pull core_sched cookie to pid */
+# define PR_SCHED_CORE_MAX 4
+#endif
+
+#define MAX_PROCESSES 128
+#define MAX_THREADS 128
+
+static const char USAGE[] = "cs_prctl_test [options]\n"
+" options:\n"
+" -P : number of processes to create.\n"
+" -T : number of threads per process to create.\n"
+" -d : delay time to keep tasks alive.\n"
+" -k : keep tasks alive until keypress.\n";
+
+enum pid_type {PIDTYPE_PID = 0, PIDTYPE_TGID, PIDTYPE_PGID};
+
+const int THREAD_CLONE_FLAGS = CLONE_THREAD | CLONE_SIGHAND | CLONE_FS | CLONE_VM | CLONE_FILES;
+
+static int _prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4,
+ unsigned long arg5)
+{
+ int res;
+
+ res = prctl(option, arg2, arg3, arg4, arg5);
+ printf("%d = prctl(%d, %ld, %ld, %ld, %lx)\n", res, option, (long)arg2, (long)arg3,
+ (long)arg4, arg5);
+ return res;
+}
+
+#define STACK_SIZE (1024 * 1024)
+
+#define handle_error(msg) __handle_error(__FILE__, __LINE__, msg)
+static void __handle_error(char *fn, int ln, char *msg)
+{
+ printf("(%s:%d) - ", fn, ln);
+ perror(msg);
+ exit(EXIT_FAILURE);
+}
+
+static void handle_usage(int rc, char *msg)
+{
+ puts(USAGE);
+ puts(msg);
+ putchar('\n');
+ exit(rc);
+}
+
+static unsigned long get_cs_cookie(int pid)
+{
+ unsigned long long cookie;
+ int ret;
+
+ ret = prctl(PR_SCHED_CORE, PR_SCHED_CORE_GET, pid, PIDTYPE_PID,
+ (unsigned long)&cookie);
+ if (ret) {
+ printf("Not a core sched system\n");
+ return -1UL;
+ }
+
+ return cookie;
+}
+
+struct child_args {
+ int num_threads;
+ int pfd[2];
+ int cpid;
+ int thr_tids[MAX_THREADS];
+};
+
+static int child_func_thread(void __attribute__((unused))*arg)
+{
+ while (1)
+ usleep(20000);
+ return 0;
+}
+
+static void create_threads(int num_threads, int thr_tids[])
+{
+ void *child_stack;
+ pid_t tid;
+ int i;
+
+ for (i = 0; i < num_threads; ++i) {
+ child_stack = malloc(STACK_SIZE);
+ if (!child_stack)
+ handle_error("child stack allocate");
+
+ tid = clone(child_func_thread, child_stack + STACK_SIZE, THREAD_CLONE_FLAGS, NULL);
+ if (tid == -1)
+ handle_error("clone thread");
+ thr_tids[i] = tid;
+ }
+}
+
+static int child_func_process(void *arg)
+{
+ struct child_args *ca = (struct child_args *)arg;
+
+ close(ca->pfd[0]);
+
+ create_threads(ca->num_threads, ca->thr_tids);
+
+ write(ca->pfd[1], &ca->thr_tids, sizeof(int) * ca->num_threads);
+ close(ca->pfd[1]);
+
+ while (1)
+ usleep(20000);
+ return 0;
+}
+
+static unsigned char child_func_process_stack[STACK_SIZE];
+
+void create_processes(int num_processes, int num_threads, struct child_args proc[])
+{
+ pid_t cpid;
+ int i;
+
+ for (i = 0; i < num_processes; ++i) {
+ proc[i].num_threads = num_threads;
+
+ if (pipe(proc[i].pfd) == -1)
+ handle_error("pipe() failed");
+
+ cpid = clone(child_func_process, child_func_process_stack + STACK_SIZE,
+ SIGCHLD, &proc[i]);
+ proc[i].cpid = cpid;
+ close(proc[i].pfd[1]);
+ }
+
+ for (i = 0; i < num_processes; ++i) {
+ read(proc[i].pfd[0], &proc[i].thr_tids, sizeof(int) * proc[i].num_threads);
+ close(proc[i].pfd[0]);
+ }
+}
+
+void disp_processes(int num_processes, struct child_args proc[])
+{
+ int i, j;
+
+ printf("tid=%d, / tgid=%d / pgid=%d: %lx\n", gettid(), getpid(), getpgid(0),
+ get_cs_cookie(getpid()));
+
+ for (i = 0; i < num_processes; ++i) {
+ printf(" tid=%d, / tgid=%d / pgid=%d: %lx\n", proc[i].cpid, proc[i].cpid,
+ getpgid(proc[i].cpid), get_cs_cookie(proc[i].cpid));
+ for (j = 0; j < proc[i].num_threads; ++j) {
+ printf(" tid=%d, / tgid=%d / pgid=%d: %lx\n", proc[i].thr_tids[j],
+ proc[i].cpid, getpgid(0), get_cs_cookie(proc[i].thr_tids[j]));
+ }
+ }
+ puts("\n");
+}
+
+static int errors;
+
+#define validate(v) _validate(__LINE__, v, #v)
+void _validate(int line, int val, char *msg)
+{
+ if (!val) {
+ ++errors;
+ printf("(%d) FAILED: %s\n", line, msg);
+ } else {
+ printf("(%d) PASSED: %s\n", line, msg);
+ }
+}
+
+int main(int argc, char *argv[])
+{
+ struct child_args procs[MAX_PROCESSES];
+
+ int keypress = 0;
+ int num_processes = 2;
+ int num_threads = 3;
+ int delay = 0;
+ int res = 0;
+ int pidx;
+ int pid;
+ int opt;
+
+ while ((opt = getopt(argc, argv, ":hkT:P:d:")) != -1) {
+ switch (opt) {
+ case 'P':
+ num_processes = (int)strtol(optarg, NULL, 10);
+ break;
+ case 'T':
+ num_threads = (int)strtoul(optarg, NULL, 10);
+ break;
+ case 'd':
+ delay = (int)strtol(optarg, NULL, 10);
+ break;
+ case 'k':
+ keypress = 1;
+ break;
+ case 'h':
+ printf(USAGE);
+ exit(EXIT_SUCCESS);
+ default:
+ handle_usage(20, "unknown option");
+ }
+ }
+
+ if (num_processes < 1 || num_processes > MAX_PROCESSES)
+ handle_usage(1, "Bad processes value");
+
+ if (num_threads < 1 || num_threads > MAX_THREADS)
+ handle_usage(2, "Bad thread value");
+
+ if (keypress)
+ delay = -1;
+
+ srand(time(NULL));
+
+ /* put into separate process group */
+ if (setpgid(0, 0) != 0)
+ handle_error("process group");
+
+ printf("\n## Create a thread/process/process group hiearchy\n");
+ create_processes(num_processes, num_threads, procs);
+ disp_processes(num_processes, procs);
+ validate(get_cs_cookie(0) == 0);
+
+ printf("\n## Set a cookie on entire process group\n");
+ if (_prctl(PR_SCHED_CORE, PR_SCHED_CORE_CREATE, 0, PIDTYPE_PGID, 0) < 0)
+ handle_error("core_sched create failed -- PGID");
+ disp_processes(num_processes, procs);
+
+ validate(get_cs_cookie(0) != 0);
+
+ /* get a random process pid */
+ pidx = rand() % num_processes;
+ pid = procs[pidx].cpid;
+
+ validate(get_cs_cookie(0) == get_cs_cookie(pid));
+ validate(get_cs_cookie(0) == get_cs_cookie(procs[pidx].thr_tids[0]));
+
+ printf("\n## Set a new cookie on entire process/TGID [%d]\n", pid);
+ if (_prctl(PR_SCHED_CORE, PR_SCHED_CORE_CREATE, pid, PIDTYPE_TGID, 0) < 0)
+ handle_error("core_sched create failed -- TGID");
+ disp_processes(num_processes, procs);
+
+ validate(get_cs_cookie(0) != get_cs_cookie(pid));
+ validate(get_cs_cookie(pid) != 0);
+ validate(get_cs_cookie(pid) == get_cs_cookie(procs[pidx].thr_tids[0]));
+
+ printf("\n## Copy the cookie of current/PGID[%d], to pid [%d] as PIDTYPE_PID\n",
+ getpid(), pid);
+ if (_prctl(PR_SCHED_CORE, PR_SCHED_CORE_SHARE_TO, pid, PIDTYPE_PID, 0) < 0)
+ handle_error("core_sched share to itself failed -- PID");
+ disp_processes(num_processes, procs);
+
+ validate(get_cs_cookie(0) == get_cs_cookie(pid));
+ validate(get_cs_cookie(pid) != 0);
+ validate(get_cs_cookie(pid) != get_cs_cookie(procs[pidx].thr_tids[0]));
+
+ printf("\n## Copy cookie from a thread [%d] to current/PGID [%d] as PIDTYPE_PID\n",
+ procs[pidx].thr_tids[0], getpid());
+ if (_prctl(PR_SCHED_CORE, PR_SCHED_CORE_SHARE_FROM, procs[pidx].thr_tids[0],
+ PIDTYPE_PID, 0) < 0)
+ handle_error("core_sched share from thread failed -- PID");
+ disp_processes(num_processes, procs);
+
+ validate(get_cs_cookie(0) == get_cs_cookie(procs[pidx].thr_tids[0]));
+ validate(get_cs_cookie(pid) != get_cs_cookie(procs[pidx].thr_tids[0]));
+
+ printf("\n## Copy cookie from current [%d] to current as pidtype PGID\n", getpid());
+ if (_prctl(PR_SCHED_CORE, PR_SCHED_CORE_SHARE_TO, 0, PIDTYPE_PGID, 0) < 0)
+ handle_error("core_sched share to self failed -- PGID");
+ disp_processes(num_processes, procs);
+
+ validate(get_cs_cookie(0) == get_cs_cookie(pid));
+ validate(get_cs_cookie(pid) != 0);
+ validate(get_cs_cookie(pid) == get_cs_cookie(procs[pidx].thr_tids[0]));
+
+ if (errors) {
+ printf("TESTS FAILED. errors: %d\n", errors);
+ res = 10;
+ } else {
+ printf("SUCCESS !!!\n");
+ }
+
+ if (keypress)
+ getchar();
+ else
+ sleep(delay);
+
+ for (pidx = 0; pidx < num_processes; ++pidx)
+ kill(procs[pidx].cpid, 15);
+
+ return res;
+}
diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh
index 7ed7cd95e58f..ebc4ee0fe179 100755
--- a/tools/testing/selftests/wireguard/netns.sh
+++ b/tools/testing/selftests/wireguard/netns.sh
@@ -363,6 +363,7 @@ ip1 -6 rule add table main suppress_prefixlength 0
ip1 -4 route add default dev wg0 table 51820
ip1 -4 rule add not fwmark 51820 table 51820
ip1 -4 rule add table main suppress_prefixlength 0
+n1 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/vethc/rp_filter'
# Flood the pings instead of sending just one, to trigger routing table reference counting bugs.
n1 ping -W 1 -c 100 -f 192.168.99.7
n1 ping -W 1 -c 100 -f abab::1111
diff --git a/tools/testing/selftests/wireguard/qemu/kernel.config b/tools/testing/selftests/wireguard/qemu/kernel.config
index 4eecb432a66c..74db83a0aedd 100644
--- a/tools/testing/selftests/wireguard/qemu/kernel.config
+++ b/tools/testing/selftests/wireguard/qemu/kernel.config
@@ -19,7 +19,6 @@ CONFIG_NETFILTER_XTABLES=y
CONFIG_NETFILTER_XT_NAT=y
CONFIG_NETFILTER_XT_MATCH_LENGTH=y
CONFIG_NETFILTER_XT_MARK=y
-CONFIG_NF_CONNTRACK_IPV4=y
CONFIG_NF_NAT_IPV4=y
CONFIG_IP_NF_IPTABLES=y
CONFIG_IP_NF_FILTER=y