summaryrefslogtreecommitdiff
path: root/tools/lib/bpf/libbpf_internal.h
diff options
context:
space:
mode:
Diffstat (limited to 'tools/lib/bpf/libbpf_internal.h')
-rw-r--r--tools/lib/bpf/libbpf_internal.h147
1 files changed, 116 insertions, 31 deletions
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 50d70e90d5f1..d99bc847bf84 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -9,6 +9,15 @@
#ifndef __LIBBPF_LIBBPF_INTERNAL_H
#define __LIBBPF_LIBBPF_INTERNAL_H
+#include <stdlib.h>
+#include <limits.h>
+
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
+/* prevent accidental re-addition of reallocarray() */
+#pragma GCC poison reallocarray
+
#include "libbpf.h"
#define BTF_INFO_ENC(kind, kind_flag, vlen) \
@@ -23,6 +32,12 @@
#define BTF_PARAM_ENC(name, type) (name), (type)
#define BTF_VAR_SECINFO_ENC(type, offset, size) (type), (offset), (size)
+#ifndef likely
+#define likely(x) __builtin_expect(!!(x), 1)
+#endif
+#ifndef unlikely
+#define unlikely(x) __builtin_expect(!!(x), 0)
+#endif
#ifndef min
# define min(x, y) ((x) < (y) ? (x) : (y))
#endif
@@ -63,6 +78,37 @@ do { \
#define pr_info(fmt, ...) __pr(LIBBPF_INFO, fmt, ##__VA_ARGS__)
#define pr_debug(fmt, ...) __pr(LIBBPF_DEBUG, fmt, ##__VA_ARGS__)
+#ifndef __has_builtin
+#define __has_builtin(x) 0
+#endif
+/*
+ * Re-implement glibc's reallocarray() for libbpf internal-only use.
+ * reallocarray(), unfortunately, is not available in all versions of glibc,
+ * so requires extra feature detection and using reallocarray() stub from
+ * <tools/libc_compat.h> and COMPAT_NEED_REALLOCARRAY. All this complicates
+ * build of libbpf unnecessarily and is just a maintenance burden. Instead,
+ * it's trivial to implement libbpf-specific internal version and use it
+ * throughout libbpf.
+ */
+static inline void *libbpf_reallocarray(void *ptr, size_t nmemb, size_t size)
+{
+ size_t total;
+
+#if __has_builtin(__builtin_mul_overflow)
+ if (unlikely(__builtin_mul_overflow(nmemb, size, &total)))
+ return NULL;
+#else
+ if (size == 0 || nmemb > ULONG_MAX / size)
+ return NULL;
+ total = nmemb * size;
+#endif
+ return realloc(ptr, total);
+}
+
+void *btf_add_mem(void **data, size_t *cap_cnt, size_t elem_sz,
+ size_t cur_cnt, size_t max_cnt, size_t add_cnt);
+int btf_ensure_mem(void **data, size_t *cap_cnt, size_t elem_sz, size_t need_cnt);
+
static inline bool libbpf_validate_opts(const char *opts,
size_t opts_sz, size_t user_sz,
const char *type_name)
@@ -94,6 +140,11 @@ static inline bool libbpf_validate_opts(const char *opts,
((opts) && opts->sz >= offsetofend(typeof(*(opts)), field))
#define OPTS_GET(opts, field, fallback_value) \
(OPTS_HAS(opts, field) ? (opts)->field : fallback_value)
+#define OPTS_SET(opts, field, value) \
+ do { \
+ if (OPTS_HAS(opts, field)) \
+ (opts)->field = value; \
+ } while (0)
int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz);
int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz);
@@ -105,18 +156,6 @@ int bpf_object__section_size(const struct bpf_object *obj, const char *name,
int bpf_object__variable_offset(const struct bpf_object *obj, const char *name,
__u32 *off);
-struct nlattr;
-typedef int (*libbpf_dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb);
-int libbpf_netlink_open(unsigned int *nl_pid);
-int libbpf_nl_get_link(int sock, unsigned int nl_pid,
- libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie);
-int libbpf_nl_get_class(int sock, unsigned int nl_pid, int ifindex,
- libbpf_dump_nlmsg_t dump_class_nlmsg, void *cookie);
-int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
- libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie);
-int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle,
- libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie);
-
struct btf_ext_info {
/*
* info points to the individual info section (e.g. func_info and
@@ -138,6 +177,44 @@ struct btf_ext_info {
i < (sec)->num_info; \
i++, rec = (void *)rec + (seg)->rec_size)
+/*
+ * The .BTF.ext ELF section layout defined as
+ * struct btf_ext_header
+ * func_info subsection
+ *
+ * The func_info subsection layout:
+ * record size for struct bpf_func_info in the func_info subsection
+ * struct btf_sec_func_info for section #1
+ * a list of bpf_func_info records for section #1
+ * where struct bpf_func_info mimics one in include/uapi/linux/bpf.h
+ * but may not be identical
+ * struct btf_sec_func_info for section #2
+ * a list of bpf_func_info records for section #2
+ * ......
+ *
+ * Note that the bpf_func_info record size in .BTF.ext may not
+ * be the same as the one defined in include/uapi/linux/bpf.h.
+ * The loader should ensure that record_size meets minimum
+ * requirement and pass the record as is to the kernel. The
+ * kernel will handle the func_info properly based on its contents.
+ */
+struct btf_ext_header {
+ __u16 magic;
+ __u8 version;
+ __u8 flags;
+ __u32 hdr_len;
+
+ /* All offsets are in bytes relative to the end of this header */
+ __u32 func_info_off;
+ __u32 func_info_len;
+ __u32 line_info_off;
+ __u32 line_info_len;
+
+ /* optional part of .BTF.ext header */
+ __u32 core_relo_off;
+ __u32 core_relo_len;
+};
+
struct btf_ext {
union {
struct btf_ext_header *hdr;
@@ -145,7 +222,7 @@ struct btf_ext {
};
struct btf_ext_info func_info;
struct btf_ext_info line_info;
- struct btf_ext_info field_reloc_info;
+ struct btf_ext_info core_relo_info;
__u32 data_size;
};
@@ -170,32 +247,40 @@ struct bpf_line_info_min {
__u32 line_col;
};
-/* bpf_field_info_kind encodes which aspect of captured field has to be
- * adjusted by relocations. Currently supported values are:
- * - BPF_FIELD_BYTE_OFFSET: field offset (in bytes);
- * - BPF_FIELD_EXISTS: field existence (1, if field exists; 0, otherwise);
+/* bpf_core_relo_kind encodes which aspect of captured field/type/enum value
+ * has to be adjusted by relocations.
*/
-enum bpf_field_info_kind {
+enum bpf_core_relo_kind {
BPF_FIELD_BYTE_OFFSET = 0, /* field byte offset */
- BPF_FIELD_BYTE_SIZE = 1,
+ BPF_FIELD_BYTE_SIZE = 1, /* field size in bytes */
BPF_FIELD_EXISTS = 2, /* field existence in target kernel */
- BPF_FIELD_SIGNED = 3,
- BPF_FIELD_LSHIFT_U64 = 4,
- BPF_FIELD_RSHIFT_U64 = 5,
+ BPF_FIELD_SIGNED = 3, /* field signedness (0 - unsigned, 1 - signed) */
+ BPF_FIELD_LSHIFT_U64 = 4, /* bitfield-specific left bitshift */
+ BPF_FIELD_RSHIFT_U64 = 5, /* bitfield-specific right bitshift */
+ BPF_TYPE_ID_LOCAL = 6, /* type ID in local BPF object */
+ BPF_TYPE_ID_TARGET = 7, /* type ID in target kernel */
+ BPF_TYPE_EXISTS = 8, /* type existence in target kernel */
+ BPF_TYPE_SIZE = 9, /* type size in bytes */
+ BPF_ENUMVAL_EXISTS = 10, /* enum value existence in target kernel */
+ BPF_ENUMVAL_VALUE = 11, /* enum value integer value */
};
-/* The minimum bpf_field_reloc checked by the loader
+/* The minimum bpf_core_relo checked by the loader
*
- * Field relocation captures the following data:
+ * 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
- * field;
+ * type or field;
* - access_str_off - offset into corresponding .BTF string section. String
- * itself encodes an accessed field using a sequence of field and array
- * indicies, separated by colon (:). It's conceptually very close to LLVM's
- * getelementptr ([0]) instruction's arguments for identifying offset to
- * a field.
+ * 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;
*
* Example to provide a better feel.
*
@@ -226,11 +311,11 @@ enum bpf_field_info_kind {
*
* [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction
*/
-struct bpf_field_reloc {
+struct bpf_core_relo {
__u32 insn_off;
__u32 type_id;
__u32 access_str_off;
- enum bpf_field_info_kind kind;
+ enum bpf_core_relo_kind kind;
};
#endif /* __LIBBPF_LIBBPF_INTERNAL_H */
?id=fab1adcf9503ccf191aec9ee42580f7dc1eb6237'>ps3disk: convert to blk-mqJens Axboe Convert from the old request_fn style driver to blk-mq. Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Tested-by: Geoff Levand <geoff@infradead.org> Signed-off-by: Jens Axboe <axboe@kernel.dk> 2018-09-28block: genhd: add 'groups' argument to device_add_diskHannes Reinecke Update device_add_disk() to take an 'groups' argument so that individual drivers can register a device with additional sysfs attributes. This avoids race condition the driver would otherwise have if these groups were to be created with sysfs_add_groups(). Signed-off-by: Martin Wilck <martin.wilck@suse.com> Signed-off-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Bart Van Assche <bvanassche@acm.org> Signed-off-by: Jens Axboe <axboe@kernel.dk> 2018-05-11ps3disk: handle highmem pagesChristoph Hellwig The ps3disk driver already kmaps all pages when copying from/to the internal bounce buffer, so it can accept highmem pages just fine. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@kernel.dk> 2017-06-09block: introduce new block status code typeChristoph Hellwig Currently we use nornal Linux errno values in the block layer, and while we accept any error a few have overloaded magic meanings. This patch instead introduces a new blk_status_t value that holds block layer specific status codes and explicitly explains their meaning. Helpers to convert from and to the previous special meanings are provided for now, but I suspect we want to get rid of them in the long run - those drivers that have a errno input (e.g. networking) usually get errnos that don't know about the special block layer overloads, and similarly returning them to userspace will usually return somethings that strictly speaking isn't correct for file system operations, but that's left as an exercise for later. For now the set of errors is a very limited set that closely corresponds to the previous overloaded errno values, but there is some low hanging fruite to improve it. blk_status_t (ab)uses the sparse __bitwise annotations to allow for sparse typechecking, so that we can easily catch places passing the wrong values. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com> 2017-01-31block: fold cmd_type into the REQ_OP_ spaceChristoph Hellwig Instead of keeping two levels of indirection for requests types, fold it all into the operations. The little caveat here is that previously cmd_type only applied to struct request, while the request and bio op fields were set to plain REQ_OP_READ/WRITE even for passthrough operations. Instead this patch adds new REQ_OP_* for SCSI passthrough and driver private requests, althought it has to add two for each so that we can communicate the data in/out nature of the request. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com> 2016-06-27block: convert to device_add_disk()Dan Williams For block drivers that specify a parent device, convert them to use device_add_disk(). This conversion was done with the following semantic patch: @@ struct gendisk *disk; expression E; @@ - disk->driverfs_dev = E; ... - add_disk(disk); + device_add_disk(E, disk); @@ struct gendisk *disk; expression E1, E2; @@ - disk->driverfs_dev = E1; ... E2 = disk; ... - add_disk(E2); + device_add_disk(E1, E2); ...plus some manual fixups for a few missed conversions. Cc: Jens Axboe <axboe@fb.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Michael S. Tsirkin <mst@redhat.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: David S. Miller <davem@davemloft.net> Cc: James Bottomley <James.Bottomley@hansenpartnership.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de> Signed-off-by: Dan Williams <dan.j.williams@intel.com> 2016-06-07block, drivers: add REQ_OP_FLUSH operationMike Christie This adds a REQ_OP_FLUSH operation that is sent to request_fn based drivers by the block layer's flush code, instead of sending requests with the request->cmd_flags REQ_FLUSH bit set. Signed-off-by: Mike Christie <mchristi@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Hannes Reinecke <hare@suse.com> Signed-off-by: Jens Axboe <axboe@fb.com> 2016-04-12ps3disk: switch to using blk_queue_write_cache()Jens Axboe Signed-off-by: Jens Axboe <axboe@fb.com> Reviewed-by: Christoph Hellwig <hch@lst.de>