summaryrefslogtreecommitdiff
path: root/tools/include
diff options
context:
space:
mode:
authorArnaldo Carvalho de Melo <acme@redhat.com>2022-01-13 16:20:59 +0300
committerArnaldo Carvalho de Melo <acme@redhat.com>2022-01-13 16:20:59 +0300
commit1aa77e716c6f2332f2d4664f747ff4eba731825b (patch)
treebffb043cec73da6c79d4ec652e531f86344b160b /tools/include
parentc0dd94558d0e473aa92254e1c48a47900c911e69 (diff)
parent455e73a07f6e288b0061dfcf4fcf54fa9fe06458 (diff)
downloadlinux-1aa77e716c6f2332f2d4664f747ff4eba731825b.tar.xz
Merge remote-tracking branch 'torvalds/master' into perf/core
To pick up fixes and get in line with other trees, powerpc kernel mostly this time, but BPF as well. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Diffstat (limited to 'tools/include')
-rw-r--r--tools/include/linux/kernel.h2
-rw-r--r--tools/include/nolibc/nolibc.h86
-rw-r--r--tools/include/uapi/linux/bpf.h165
-rw-r--r--tools/include/uapi/linux/btf.h3
-rw-r--r--tools/include/uapi/linux/if_link.h2
5 files changed, 229 insertions, 29 deletions
diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h
index 3e8df500cfbd..9701e8307db0 100644
--- a/tools/include/linux/kernel.h
+++ b/tools/include/linux/kernel.h
@@ -92,7 +92,9 @@ int vscnprintf(char *buf, size_t size, const char *fmt, va_list args);
int scnprintf(char * buf, size_t size, const char * fmt, ...);
int scnprintf_pad(char * buf, size_t size, const char * fmt, ...);
+#ifndef ARRAY_SIZE
#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr))
+#endif
#define current_gfp_context(k) 0
#define synchronize_rcu()
diff --git a/tools/include/nolibc/nolibc.h b/tools/include/nolibc/nolibc.h
index 3430667b0d24..c1c285fe494a 100644
--- a/tools/include/nolibc/nolibc.h
+++ b/tools/include/nolibc/nolibc.h
@@ -265,12 +265,17 @@ struct stat {
* - arguments are in rdi, rsi, rdx, r10, r8, r9 respectively
* - the system call is performed by calling the syscall instruction
* - syscall return comes in rax
- * - rcx and r8..r11 may be clobbered, others are preserved.
+ * - rcx and r11 are clobbered, others are preserved.
* - the arguments are cast to long and assigned into the target registers
* which are then simply passed as registers to the asm code, so that we
* don't have to experience issues with register constraints.
* - the syscall number is always specified last in order to allow to force
* some registers before (gcc refuses a %-register at the last position).
+ * - see also x86-64 ABI section A.2 AMD64 Linux Kernel Conventions, A.2.1
+ * Calling Conventions.
+ *
+ * Link x86-64 ABI: https://gitlab.com/x86-psABIs/x86-64-ABI/-/wikis/x86-64-psABI
+ *
*/
#define my_syscall0(num) \
@@ -280,9 +285,9 @@ struct stat {
\
asm volatile ( \
"syscall\n" \
- : "=a" (_ret) \
+ : "=a"(_ret) \
: "0"(_num) \
- : "rcx", "r8", "r9", "r10", "r11", "memory", "cc" \
+ : "rcx", "r11", "memory", "cc" \
); \
_ret; \
})
@@ -295,10 +300,10 @@ struct stat {
\
asm volatile ( \
"syscall\n" \
- : "=a" (_ret) \
+ : "=a"(_ret) \
: "r"(_arg1), \
"0"(_num) \
- : "rcx", "r8", "r9", "r10", "r11", "memory", "cc" \
+ : "rcx", "r11", "memory", "cc" \
); \
_ret; \
})
@@ -312,10 +317,10 @@ struct stat {
\
asm volatile ( \
"syscall\n" \
- : "=a" (_ret) \
+ : "=a"(_ret) \
: "r"(_arg1), "r"(_arg2), \
"0"(_num) \
- : "rcx", "r8", "r9", "r10", "r11", "memory", "cc" \
+ : "rcx", "r11", "memory", "cc" \
); \
_ret; \
})
@@ -330,10 +335,10 @@ struct stat {
\
asm volatile ( \
"syscall\n" \
- : "=a" (_ret) \
+ : "=a"(_ret) \
: "r"(_arg1), "r"(_arg2), "r"(_arg3), \
"0"(_num) \
- : "rcx", "r8", "r9", "r10", "r11", "memory", "cc" \
+ : "rcx", "r11", "memory", "cc" \
); \
_ret; \
})
@@ -349,10 +354,10 @@ struct stat {
\
asm volatile ( \
"syscall\n" \
- : "=a" (_ret), "=r"(_arg4) \
+ : "=a"(_ret) \
: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \
"0"(_num) \
- : "rcx", "r8", "r9", "r11", "memory", "cc" \
+ : "rcx", "r11", "memory", "cc" \
); \
_ret; \
})
@@ -369,10 +374,10 @@ struct stat {
\
asm volatile ( \
"syscall\n" \
- : "=a" (_ret), "=r"(_arg4), "=r"(_arg5) \
+ : "=a"(_ret) \
: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
"0"(_num) \
- : "rcx", "r9", "r11", "memory", "cc" \
+ : "rcx", "r11", "memory", "cc" \
); \
_ret; \
})
@@ -390,7 +395,7 @@ struct stat {
\
asm volatile ( \
"syscall\n" \
- : "=a" (_ret), "=r"(_arg4), "=r"(_arg5) \
+ : "=a"(_ret) \
: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
"r"(_arg6), "0"(_num) \
: "rcx", "r11", "memory", "cc" \
@@ -399,17 +404,23 @@ struct stat {
})
/* startup code */
+/*
+ * x86-64 System V ABI mandates:
+ * 1) %rsp must be 16-byte aligned right before the function call.
+ * 2) The deepest stack frame should be zero (the %rbp).
+ *
+ */
asm(".section .text\n"
".global _start\n"
"_start:\n"
"pop %rdi\n" // argc (first arg, %rdi)
"mov %rsp, %rsi\n" // argv[] (second arg, %rsi)
"lea 8(%rsi,%rdi,8),%rdx\n" // then a NULL then envp (third arg, %rdx)
- "and $-16, %rsp\n" // x86 ABI : esp must be 16-byte aligned when
- "sub $8, %rsp\n" // entering the callee
+ "xor %ebp, %ebp\n" // zero the stack frame
+ "and $-16, %rsp\n" // x86 ABI : esp must be 16-byte aligned before call
"call main\n" // main() returns the status code, we'll exit with it.
- "movzb %al, %rdi\n" // retrieve exit code from 8 lower bits
- "mov $60, %rax\n" // NR_exit == 60
+ "mov %eax, %edi\n" // retrieve exit code (32 bit)
+ "mov $60, %eax\n" // NR_exit == 60
"syscall\n" // really exit
"hlt\n" // ensure it does not return
"");
@@ -577,20 +588,28 @@ struct sys_stat_struct {
})
/* startup code */
+/*
+ * i386 System V ABI mandates:
+ * 1) last pushed argument must be 16-byte aligned.
+ * 2) The deepest stack frame should be set to zero
+ *
+ */
asm(".section .text\n"
".global _start\n"
"_start:\n"
"pop %eax\n" // argc (first arg, %eax)
"mov %esp, %ebx\n" // argv[] (second arg, %ebx)
"lea 4(%ebx,%eax,4),%ecx\n" // then a NULL then envp (third arg, %ecx)
- "and $-16, %esp\n" // x86 ABI : esp must be 16-byte aligned when
+ "xor %ebp, %ebp\n" // zero the stack frame
+ "and $-16, %esp\n" // x86 ABI : esp must be 16-byte aligned before
+ "sub $4, %esp\n" // the call instruction (args are aligned)
"push %ecx\n" // push all registers on the stack so that we
"push %ebx\n" // support both regparm and plain stack modes
"push %eax\n"
"call main\n" // main() returns the status code in %eax
- "movzbl %al, %ebx\n" // retrieve exit code from lower 8 bits
- "movl $1, %eax\n" // NR_exit == 1
- "int $0x80\n" // exit now
+ "mov %eax, %ebx\n" // retrieve exit code (32-bit int)
+ "movl $1, %eax\n" // NR_exit == 1
+ "int $0x80\n" // exit now
"hlt\n" // ensure it does not
"");
@@ -774,7 +793,6 @@ asm(".section .text\n"
"and %r3, %r1, $-8\n" // AAPCS : sp must be 8-byte aligned in the
"mov %sp, %r3\n" // callee, an bl doesn't push (lr=pc)
"bl main\n" // main() returns the status code, we'll exit with it.
- "and %r0, %r0, $0xff\n" // limit exit code to 8 bits
"movs r7, $1\n" // NR_exit == 1
"svc $0x00\n"
"");
@@ -971,7 +989,6 @@ asm(".section .text\n"
"add x2, x2, x1\n" // + argv
"and sp, x1, -16\n" // sp must be 16-byte aligned in the callee
"bl main\n" // main() returns the status code, we'll exit with it.
- "and x0, x0, 0xff\n" // limit exit code to 8 bits
"mov x8, 93\n" // NR_exit == 93
"svc #0\n"
"");
@@ -1176,7 +1193,7 @@ asm(".section .text\n"
"addiu $sp,$sp,-16\n" // the callee expects to save a0..a3 there!
"jal main\n" // main() returns the status code, we'll exit with it.
"nop\n" // delayed slot
- "and $a0, $v0, 0xff\n" // limit exit code to 8 bits
+ "move $a0, $v0\n" // retrieve 32-bit exit code from v0
"li $v0, 4001\n" // NR_exit == 4001
"syscall\n"
".end __start\n"
@@ -1374,7 +1391,6 @@ asm(".section .text\n"
"add a2,a2,a1\n" // + argv
"andi sp,a1,-16\n" // sp must be 16-byte aligned
"call main\n" // main() returns the status code, we'll exit with it.
- "andi a0, a0, 0xff\n" // limit exit code to 8 bits
"li a7, 93\n" // NR_exit == 93
"ecall\n"
"");
@@ -1556,6 +1572,12 @@ pid_t sys_getpid(void)
}
static __attribute__((unused))
+pid_t sys_gettid(void)
+{
+ return my_syscall0(__NR_gettid);
+}
+
+static __attribute__((unused))
int sys_gettimeofday(struct timeval *tv, struct timezone *tz)
{
return my_syscall2(__NR_gettimeofday, tv, tz);
@@ -2014,6 +2036,18 @@ pid_t getpid(void)
}
static __attribute__((unused))
+pid_t gettid(void)
+{
+ pid_t ret = sys_gettid();
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
int gettimeofday(struct timeval *tv, struct timezone *tz)
{
int ret = sys_gettimeofday(tv, tz);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index ba5af15e25f5..b0383d371b9a 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1342,8 +1342,10 @@ union bpf_attr {
/* or valid module BTF object fd or 0 to attach to vmlinux */
__u32 attach_btf_obj_fd;
};
- __u32 :32; /* pad */
+ __u32 core_relo_cnt; /* number of bpf_core_relo */
__aligned_u64 fd_array; /* array of FDs */
+ __aligned_u64 core_relos;
+ __u32 core_relo_rec_size; /* sizeof(struct bpf_core_relo) */
};
struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -1744,7 +1746,7 @@ union bpf_attr {
* if the maximum number of tail calls has been reached for this
* chain of programs. This limit is defined in the kernel by the
* macro **MAX_TAIL_CALL_CNT** (not accessible to user space),
- * which is currently set to 32.
+ * which is currently set to 33.
* Return
* 0 on success, or a negative error in case of failure.
*
@@ -4938,6 +4940,84 @@ union bpf_attr {
* **-ENOENT** if symbol is not found.
*
* **-EPERM** if caller does not have permission to obtain kernel address.
+ *
+ * long bpf_find_vma(struct task_struct *task, u64 addr, void *callback_fn, void *callback_ctx, u64 flags)
+ * Description
+ * Find vma of *task* that contains *addr*, call *callback_fn*
+ * function with *task*, *vma*, and *callback_ctx*.
+ * The *callback_fn* should be a static function and
+ * the *callback_ctx* should be a pointer to the stack.
+ * The *flags* is used to control certain aspects of the helper.
+ * Currently, the *flags* must be 0.
+ *
+ * The expected callback signature is
+ *
+ * long (\*callback_fn)(struct task_struct \*task, struct vm_area_struct \*vma, void \*callback_ctx);
+ *
+ * Return
+ * 0 on success.
+ * **-ENOENT** if *task->mm* is NULL, or no vma contains *addr*.
+ * **-EBUSY** if failed to try lock mmap_lock.
+ * **-EINVAL** for invalid **flags**.
+ *
+ * long bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, u64 flags)
+ * Description
+ * For **nr_loops**, call **callback_fn** function
+ * with **callback_ctx** as the context parameter.
+ * The **callback_fn** should be a static function and
+ * the **callback_ctx** should be a pointer to the stack.
+ * The **flags** is used to control certain aspects of the helper.
+ * Currently, the **flags** must be 0. Currently, nr_loops is
+ * limited to 1 << 23 (~8 million) loops.
+ *
+ * long (\*callback_fn)(u32 index, void \*ctx);
+ *
+ * where **index** is the current index in the loop. The index
+ * is zero-indexed.
+ *
+ * If **callback_fn** returns 0, the helper will continue to the next
+ * loop. If return value is 1, the helper will skip the rest of
+ * the loops and return. Other return values are not used now,
+ * and will be rejected by the verifier.
+ *
+ * Return
+ * The number of loops performed, **-EINVAL** for invalid **flags**,
+ * **-E2BIG** if **nr_loops** exceeds the maximum number of loops.
+ *
+ * long bpf_strncmp(const char *s1, u32 s1_sz, const char *s2)
+ * Description
+ * Do strncmp() between **s1** and **s2**. **s1** doesn't need
+ * to be null-terminated and **s1_sz** is the maximum storage
+ * size of **s1**. **s2** must be a read-only string.
+ * Return
+ * An integer less than, equal to, or greater than zero
+ * if the first **s1_sz** bytes of **s1** is found to be
+ * less than, to match, or be greater than **s2**.
+ *
+ * long bpf_get_func_arg(void *ctx, u32 n, u64 *value)
+ * Description
+ * Get **n**-th argument (zero based) of the traced function (for tracing programs)
+ * returned in **value**.
+ *
+ * Return
+ * 0 on success.
+ * **-EINVAL** if n >= arguments count of traced function.
+ *
+ * long bpf_get_func_ret(void *ctx, u64 *value)
+ * Description
+ * Get return value of the traced function (for tracing programs)
+ * in **value**.
+ *
+ * Return
+ * 0 on success.
+ * **-EOPNOTSUPP** for tracing programs other than BPF_TRACE_FEXIT or BPF_MODIFY_RETURN.
+ *
+ * long bpf_get_func_arg_cnt(void *ctx)
+ * Description
+ * Get number of arguments of the traced function (for tracing programs).
+ *
+ * Return
+ * The number of arguments of the traced function.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -5120,6 +5200,12 @@ union bpf_attr {
FN(trace_vprintk), \
FN(skc_to_unix_sock), \
FN(kallsyms_lookup_name), \
+ FN(find_vma), \
+ FN(loop), \
+ FN(strncmp), \
+ FN(get_func_arg), \
+ FN(get_func_ret), \
+ FN(get_func_arg_cnt), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -6296,6 +6382,7 @@ struct bpf_sk_lookup {
__u32 local_ip4; /* Network byte order */
__u32 local_ip6[4]; /* Network byte order */
__u32 local_port; /* Host byte order */
+ __u32 ingress_ifindex; /* The arriving interface. Determined by inet_iif. */
};
/*
@@ -6328,4 +6415,78 @@ enum {
BTF_F_ZERO = (1ULL << 3),
};
+/* bpf_core_relo_kind encodes which aspect of captured field/type/enum value
+ * has to be adjusted by relocations. It is emitted by llvm and passed to
+ * libbpf and later to the kernel.
+ */
+enum bpf_core_relo_kind {
+ BPF_CORE_FIELD_BYTE_OFFSET = 0, /* field byte offset */
+ BPF_CORE_FIELD_BYTE_SIZE = 1, /* field size in bytes */
+ BPF_CORE_FIELD_EXISTS = 2, /* field existence in target kernel */
+ BPF_CORE_FIELD_SIGNED = 3, /* field signedness (0 - unsigned, 1 - signed) */
+ BPF_CORE_FIELD_LSHIFT_U64 = 4, /* bitfield-specific left bitshift */
+ BPF_CORE_FIELD_RSHIFT_U64 = 5, /* bitfield-specific right bitshift */
+ BPF_CORE_TYPE_ID_LOCAL = 6, /* type ID in local BPF object */
+ BPF_CORE_TYPE_ID_TARGET = 7, /* type ID in target kernel */
+ BPF_CORE_TYPE_EXISTS = 8, /* type existence in target kernel */
+ BPF_CORE_TYPE_SIZE = 9, /* type size in bytes */
+ BPF_CORE_ENUMVAL_EXISTS = 10, /* enum value existence in target kernel */
+ BPF_CORE_ENUMVAL_VALUE = 11, /* enum value integer value */
+};
+
+/*
+ * "struct bpf_core_relo" is used to pass relocation data form LLVM to libbpf
+ * and from libbpf to the kernel.
+ *
+ * CO-RE relocation captures the following data:
+ * - insn_off - instruction offset (in bytes) within a BPF program that needs
+ * its insn->imm field to be relocated with actual field info;
+ * - type_id - BTF type ID of the "root" (containing) entity of a relocatable
+ * type or field;
+ * - access_str_off - offset into corresponding .BTF string section. String
+ * interpretation depends on specific relocation kind:
+ * - for field-based relocations, string encodes an accessed field using
+ * a sequence of field and array indices, separated by colon (:). It's
+ * conceptually very close to LLVM's getelementptr ([0]) instruction's
+ * arguments for identifying offset to a field.
+ * - for type-based relocations, strings is expected to be just "0";
+ * - for enum value-based relocations, string contains an index of enum
+ * value within its enum type;
+ * - kind - one of enum bpf_core_relo_kind;
+ *
+ * Example:
+ * struct sample {
+ * int a;
+ * struct {
+ * int b[10];
+ * };
+ * };
+ *
+ * struct sample *s = ...;
+ * int *x = &s->a; // encoded as "0:0" (a is field #0)
+ * int *y = &s->b[5]; // encoded as "0:1:0:5" (anon struct is field #1,
+ * // b is field #0 inside anon struct, accessing elem #5)
+ * int *z = &s[10]->b; // encoded as "10:1" (ptr is used as an array)
+ *
+ * type_id for all relocs in this example will capture BTF type id of
+ * `struct sample`.
+ *
+ * Such relocation is emitted when using __builtin_preserve_access_index()
+ * Clang built-in, passing expression that captures field address, e.g.:
+ *
+ * bpf_probe_read(&dst, sizeof(dst),
+ * __builtin_preserve_access_index(&src->a.b.c));
+ *
+ * In this case Clang will emit field relocation recording necessary data to
+ * be able to find offset of embedded `a.b.c` field within `src` struct.
+ *
+ * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction
+ */
+struct bpf_core_relo {
+ __u32 insn_off;
+ __u32 type_id;
+ __u32 access_str_off;
+ enum bpf_core_relo_kind kind;
+};
+
#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h
index deb12f755f0f..b0d8fea1951d 100644
--- a/tools/include/uapi/linux/btf.h
+++ b/tools/include/uapi/linux/btf.h
@@ -43,7 +43,7 @@ struct btf_type {
* "size" tells the size of the type it is describing.
*
* "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
- * FUNC, FUNC_PROTO, VAR and DECL_TAG.
+ * FUNC, FUNC_PROTO, VAR, DECL_TAG and TYPE_TAG.
* "type" is a type_id referring to another type.
*/
union {
@@ -75,6 +75,7 @@ enum {
BTF_KIND_DATASEC = 15, /* Section */
BTF_KIND_FLOAT = 16, /* Floating point */
BTF_KIND_DECL_TAG = 17, /* Decl Tag */
+ BTF_KIND_TYPE_TAG = 18, /* Type Tag */
NR_BTF_KINDS,
BTF_KIND_MAX = NR_BTF_KINDS - 1,
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index eebd3894fe89..6218f93f5c1a 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -347,6 +347,7 @@ enum {
*/
IFLA_PARENT_DEV_NAME,
IFLA_PARENT_DEV_BUS_NAME,
+ IFLA_GRO_MAX_SIZE,
__IFLA_MAX
};
@@ -858,6 +859,7 @@ enum {
IFLA_BOND_TLB_DYNAMIC_LB,
IFLA_BOND_PEER_NOTIF_DELAY,
IFLA_BOND_AD_LACP_ACTIVE,
+ IFLA_BOND_MISSED_MAX,
__IFLA_BOND_MAX,
};