2016-02-18 11:58:58 +08:00
|
|
|
/* Copyright (c) 2016 Facebook
|
|
|
|
|
*
|
|
|
|
|
* This program is free software; you can redistribute it and/or
|
|
|
|
|
* modify it under the terms of version 2 of the GNU General Public
|
|
|
|
|
* License as published by the Free Software Foundation.
|
|
|
|
|
*/
|
|
|
|
|
#include <linux/bpf.h>
|
|
|
|
|
#include <linux/jhash.h>
|
|
|
|
|
#include <linux/filter.h>
|
|
|
|
|
#include <linux/stacktrace.h>
|
|
|
|
|
#include <linux/perf_event.h>
|
bpf: extend stackmap to save binary_build_id+offset instead of address
Currently, bpf stackmap store address for each entry in the call trace.
To map these addresses to user space files, it is necessary to maintain
the mapping from these virtual address to symbols in the binary. Usually,
the user space profiler (such as perf) has to scan /proc/pid/maps at the
beginning of profiling, and monitor mmap2() calls afterwards. Given the
cost of maintaining the address map, this solution is not practical for
system wide profiling that is always on.
This patch tries to solve this problem with a variation of stackmap. This
variation is enabled by flag BPF_F_STACK_BUILD_ID. Instead of storing
addresses, the variation stores ELF file build_id + offset.
Build ID is a 20-byte unique identifier for ELF files. The following
command shows the Build ID of /bin/bash:
[user@]$ readelf -n /bin/bash
...
Build ID: XXXXXXXXXX
...
With BPF_F_STACK_BUILD_ID, bpf_get_stackid() tries to parse Build ID
for each entry in the call trace, and translate it into the following
struct:
struct bpf_stack_build_id_offset {
__s32 status;
unsigned char build_id[BPF_BUILD_ID_SIZE];
union {
__u64 offset;
__u64 ip;
};
};
The search of build_id is limited to the first page of the file, and this
page should be in page cache. Otherwise, we fallback to store ip for this
entry (ip field in struct bpf_stack_build_id_offset). This requires the
build_id to be stored in the first page. A quick survey of binary and
dynamic library files in a few different systems shows that almost all
binary and dynamic library files have build_id in the first page.
Build_id is only meaningful for user stack. If a kernel stack is added to
a stackmap with BPF_F_STACK_BUILD_ID, it will automatically fallback to
only store ip (status == BPF_STACK_BUILD_ID_IP). Similarly, if build_id
lookup failed for some reason, it will also fallback to store ip.
User space can access struct bpf_stack_build_id_offset with bpf
syscall BPF_MAP_LOOKUP_ELEM. It is necessary for user space to
maintain mapping from build id to binary files. This mostly static
mapping is much easier to maintain than per process address maps.
Note: Stackmap with build_id only works in non-nmi context at this time.
This is because we need to take mm->mmap_sem for find_vma(). If this
changes, we would like to allow build_id lookup in nmi context.
Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-03-15 01:23:21 +08:00
|
|
|
#include <linux/elf.h>
|
|
|
|
|
#include <linux/pagemap.h>
|
2016-03-08 13:57:17 +08:00
|
|
|
#include "percpu_freelist.h"
|
2016-02-18 11:58:58 +08:00
|
|
|
|
bpf: extend stackmap to save binary_build_id+offset instead of address
Currently, bpf stackmap store address for each entry in the call trace.
To map these addresses to user space files, it is necessary to maintain
the mapping from these virtual address to symbols in the binary. Usually,
the user space profiler (such as perf) has to scan /proc/pid/maps at the
beginning of profiling, and monitor mmap2() calls afterwards. Given the
cost of maintaining the address map, this solution is not practical for
system wide profiling that is always on.
This patch tries to solve this problem with a variation of stackmap. This
variation is enabled by flag BPF_F_STACK_BUILD_ID. Instead of storing
addresses, the variation stores ELF file build_id + offset.
Build ID is a 20-byte unique identifier for ELF files. The following
command shows the Build ID of /bin/bash:
[user@]$ readelf -n /bin/bash
...
Build ID: XXXXXXXXXX
...
With BPF_F_STACK_BUILD_ID, bpf_get_stackid() tries to parse Build ID
for each entry in the call trace, and translate it into the following
struct:
struct bpf_stack_build_id_offset {
__s32 status;
unsigned char build_id[BPF_BUILD_ID_SIZE];
union {
__u64 offset;
__u64 ip;
};
};
The search of build_id is limited to the first page of the file, and this
page should be in page cache. Otherwise, we fallback to store ip for this
entry (ip field in struct bpf_stack_build_id_offset). This requires the
build_id to be stored in the first page. A quick survey of binary and
dynamic library files in a few different systems shows that almost all
binary and dynamic library files have build_id in the first page.
Build_id is only meaningful for user stack. If a kernel stack is added to
a stackmap with BPF_F_STACK_BUILD_ID, it will automatically fallback to
only store ip (status == BPF_STACK_BUILD_ID_IP). Similarly, if build_id
lookup failed for some reason, it will also fallback to store ip.
User space can access struct bpf_stack_build_id_offset with bpf
syscall BPF_MAP_LOOKUP_ELEM. It is necessary for user space to
maintain mapping from build id to binary files. This mostly static
mapping is much easier to maintain than per process address maps.
Note: Stackmap with build_id only works in non-nmi context at this time.
This is because we need to take mm->mmap_sem for find_vma(). If this
changes, we would like to allow build_id lookup in nmi context.
Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-03-15 01:23:21 +08:00
|
|
|
#define STACK_CREATE_FLAG_MASK \
|
|
|
|
|
(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY | \
|
|
|
|
|
BPF_F_STACK_BUILD_ID)
|
2017-10-19 04:00:22 +08:00
|
|
|
|
2016-02-18 11:58:58 +08:00
|
|
|
struct stack_map_bucket {
|
2016-03-08 13:57:17 +08:00
|
|
|
struct pcpu_freelist_node fnode;
|
2016-02-18 11:58:58 +08:00
|
|
|
u32 hash;
|
|
|
|
|
u32 nr;
|
bpf: extend stackmap to save binary_build_id+offset instead of address
Currently, bpf stackmap store address for each entry in the call trace.
To map these addresses to user space files, it is necessary to maintain
the mapping from these virtual address to symbols in the binary. Usually,
the user space profiler (such as perf) has to scan /proc/pid/maps at the
beginning of profiling, and monitor mmap2() calls afterwards. Given the
cost of maintaining the address map, this solution is not practical for
system wide profiling that is always on.
This patch tries to solve this problem with a variation of stackmap. This
variation is enabled by flag BPF_F_STACK_BUILD_ID. Instead of storing
addresses, the variation stores ELF file build_id + offset.
Build ID is a 20-byte unique identifier for ELF files. The following
command shows the Build ID of /bin/bash:
[user@]$ readelf -n /bin/bash
...
Build ID: XXXXXXXXXX
...
With BPF_F_STACK_BUILD_ID, bpf_get_stackid() tries to parse Build ID
for each entry in the call trace, and translate it into the following
struct:
struct bpf_stack_build_id_offset {
__s32 status;
unsigned char build_id[BPF_BUILD_ID_SIZE];
union {
__u64 offset;
__u64 ip;
};
};
The search of build_id is limited to the first page of the file, and this
page should be in page cache. Otherwise, we fallback to store ip for this
entry (ip field in struct bpf_stack_build_id_offset). This requires the
build_id to be stored in the first page. A quick survey of binary and
dynamic library files in a few different systems shows that almost all
binary and dynamic library files have build_id in the first page.
Build_id is only meaningful for user stack. If a kernel stack is added to
a stackmap with BPF_F_STACK_BUILD_ID, it will automatically fallback to
only store ip (status == BPF_STACK_BUILD_ID_IP). Similarly, if build_id
lookup failed for some reason, it will also fallback to store ip.
User space can access struct bpf_stack_build_id_offset with bpf
syscall BPF_MAP_LOOKUP_ELEM. It is necessary for user space to
maintain mapping from build id to binary files. This mostly static
mapping is much easier to maintain than per process address maps.
Note: Stackmap with build_id only works in non-nmi context at this time.
This is because we need to take mm->mmap_sem for find_vma(). If this
changes, we would like to allow build_id lookup in nmi context.
Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-03-15 01:23:21 +08:00
|
|
|
u64 data[];
|
2016-02-18 11:58:58 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct bpf_stack_map {
|
|
|
|
|
struct bpf_map map;
|
2016-03-08 13:57:17 +08:00
|
|
|
void *elems;
|
|
|
|
|
struct pcpu_freelist freelist;
|
2016-02-18 11:58:58 +08:00
|
|
|
u32 n_buckets;
|
2016-03-08 13:57:17 +08:00
|
|
|
struct stack_map_bucket *buckets[];
|
2016-02-18 11:58:58 +08:00
|
|
|
};
|
|
|
|
|
|
bpf: extend stackmap to save binary_build_id+offset instead of address
Currently, bpf stackmap store address for each entry in the call trace.
To map these addresses to user space files, it is necessary to maintain
the mapping from these virtual address to symbols in the binary. Usually,
the user space profiler (such as perf) has to scan /proc/pid/maps at the
beginning of profiling, and monitor mmap2() calls afterwards. Given the
cost of maintaining the address map, this solution is not practical for
system wide profiling that is always on.
This patch tries to solve this problem with a variation of stackmap. This
variation is enabled by flag BPF_F_STACK_BUILD_ID. Instead of storing
addresses, the variation stores ELF file build_id + offset.
Build ID is a 20-byte unique identifier for ELF files. The following
command shows the Build ID of /bin/bash:
[user@]$ readelf -n /bin/bash
...
Build ID: XXXXXXXXXX
...
With BPF_F_STACK_BUILD_ID, bpf_get_stackid() tries to parse Build ID
for each entry in the call trace, and translate it into the following
struct:
struct bpf_stack_build_id_offset {
__s32 status;
unsigned char build_id[BPF_BUILD_ID_SIZE];
union {
__u64 offset;
__u64 ip;
};
};
The search of build_id is limited to the first page of the file, and this
page should be in page cache. Otherwise, we fallback to store ip for this
entry (ip field in struct bpf_stack_build_id_offset). This requires the
build_id to be stored in the first page. A quick survey of binary and
dynamic library files in a few different systems shows that almost all
binary and dynamic library files have build_id in the first page.
Build_id is only meaningful for user stack. If a kernel stack is added to
a stackmap with BPF_F_STACK_BUILD_ID, it will automatically fallback to
only store ip (status == BPF_STACK_BUILD_ID_IP). Similarly, if build_id
lookup failed for some reason, it will also fallback to store ip.
User space can access struct bpf_stack_build_id_offset with bpf
syscall BPF_MAP_LOOKUP_ELEM. It is necessary for user space to
maintain mapping from build id to binary files. This mostly static
mapping is much easier to maintain than per process address maps.
Note: Stackmap with build_id only works in non-nmi context at this time.
This is because we need to take mm->mmap_sem for find_vma(). If this
changes, we would like to allow build_id lookup in nmi context.
Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-03-15 01:23:21 +08:00
|
|
|
static inline bool stack_map_use_build_id(struct bpf_map *map)
|
|
|
|
|
{
|
|
|
|
|
return (map->map_flags & BPF_F_STACK_BUILD_ID);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline int stack_map_data_size(struct bpf_map *map)
|
|
|
|
|
{
|
|
|
|
|
return stack_map_use_build_id(map) ?
|
|
|
|
|
sizeof(struct bpf_stack_build_id) : sizeof(u64);
|
|
|
|
|
}
|
|
|
|
|
|
2016-03-08 13:57:17 +08:00
|
|
|
static int prealloc_elems_and_freelist(struct bpf_stack_map *smap)
|
|
|
|
|
{
|
|
|
|
|
u32 elem_size = sizeof(struct stack_map_bucket) + smap->map.value_size;
|
|
|
|
|
int err;
|
|
|
|
|
|
2017-08-19 02:28:00 +08:00
|
|
|
smap->elems = bpf_map_area_alloc(elem_size * smap->map.max_entries,
|
|
|
|
|
smap->map.numa_node);
|
2016-03-08 13:57:17 +08:00
|
|
|
if (!smap->elems)
|
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
|
|
err = pcpu_freelist_init(&smap->freelist);
|
|
|
|
|
if (err)
|
|
|
|
|
goto free_elems;
|
|
|
|
|
|
|
|
|
|
pcpu_freelist_populate(&smap->freelist, smap->elems, elem_size,
|
|
|
|
|
smap->map.max_entries);
|
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
|
|
free_elems:
|
bpf: don't trigger OOM killer under pressure with map alloc
This patch adds two helpers, bpf_map_area_alloc() and bpf_map_area_free(),
that are to be used for map allocations. Using kmalloc() for very large
allocations can cause excessive work within the page allocator, so i) fall
back earlier to vmalloc() when the attempt is considered costly anyway,
and even more importantly ii) don't trigger OOM killer with any of the
allocators.
Since this is based on a user space request, for example, when creating
maps with element pre-allocation, we really want such requests to fail
instead of killing other user space processes.
Also, don't spam the kernel log with warnings should any of the allocations
fail under pressure. Given that, we can make backend selection in
bpf_map_area_alloc() generic, and convert all maps over to use this API
for spots with potentially large allocation requests.
Note, replacing the one kmalloc_array() is fine as overflow checks happen
earlier in htab_map_alloc(), since it must also protect the multiplication
for vmalloc() should kmalloc_array() fail.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-18 22:14:17 +08:00
|
|
|
bpf_map_area_free(smap->elems);
|
2016-03-08 13:57:17 +08:00
|
|
|
return err;
|
|
|
|
|
}
|
|
|
|
|
|
2016-02-18 11:58:58 +08:00
|
|
|
/* Called from syscall */
|
|
|
|
|
static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
|
|
|
|
|
{
|
|
|
|
|
u32 value_size = attr->value_size;
|
|
|
|
|
struct bpf_stack_map *smap;
|
|
|
|
|
u64 cost, n_buckets;
|
|
|
|
|
int err;
|
|
|
|
|
|
|
|
|
|
if (!capable(CAP_SYS_ADMIN))
|
|
|
|
|
return ERR_PTR(-EPERM);
|
|
|
|
|
|
2017-10-19 04:00:22 +08:00
|
|
|
if (attr->map_flags & ~STACK_CREATE_FLAG_MASK)
|
2016-03-08 13:57:16 +08:00
|
|
|
return ERR_PTR(-EINVAL);
|
|
|
|
|
|
2016-02-18 11:58:58 +08:00
|
|
|
/* check sanity of attributes */
|
|
|
|
|
if (attr->max_entries == 0 || attr->key_size != 4 ||
|
bpf: extend stackmap to save binary_build_id+offset instead of address
Currently, bpf stackmap store address for each entry in the call trace.
To map these addresses to user space files, it is necessary to maintain
the mapping from these virtual address to symbols in the binary. Usually,
the user space profiler (such as perf) has to scan /proc/pid/maps at the
beginning of profiling, and monitor mmap2() calls afterwards. Given the
cost of maintaining the address map, this solution is not practical for
system wide profiling that is always on.
This patch tries to solve this problem with a variation of stackmap. This
variation is enabled by flag BPF_F_STACK_BUILD_ID. Instead of storing
addresses, the variation stores ELF file build_id + offset.
Build ID is a 20-byte unique identifier for ELF files. The following
command shows the Build ID of /bin/bash:
[user@]$ readelf -n /bin/bash
...
Build ID: XXXXXXXXXX
...
With BPF_F_STACK_BUILD_ID, bpf_get_stackid() tries to parse Build ID
for each entry in the call trace, and translate it into the following
struct:
struct bpf_stack_build_id_offset {
__s32 status;
unsigned char build_id[BPF_BUILD_ID_SIZE];
union {
__u64 offset;
__u64 ip;
};
};
The search of build_id is limited to the first page of the file, and this
page should be in page cache. Otherwise, we fallback to store ip for this
entry (ip field in struct bpf_stack_build_id_offset). This requires the
build_id to be stored in the first page. A quick survey of binary and
dynamic library files in a few different systems shows that almost all
binary and dynamic library files have build_id in the first page.
Build_id is only meaningful for user stack. If a kernel stack is added to
a stackmap with BPF_F_STACK_BUILD_ID, it will automatically fallback to
only store ip (status == BPF_STACK_BUILD_ID_IP). Similarly, if build_id
lookup failed for some reason, it will also fallback to store ip.
User space can access struct bpf_stack_build_id_offset with bpf
syscall BPF_MAP_LOOKUP_ELEM. It is necessary for user space to
maintain mapping from build id to binary files. This mostly static
mapping is much easier to maintain than per process address maps.
Note: Stackmap with build_id only works in non-nmi context at this time.
This is because we need to take mm->mmap_sem for find_vma(). If this
changes, we would like to allow build_id lookup in nmi context.
Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-03-15 01:23:21 +08:00
|
|
|
value_size < 8 || value_size % 8)
|
|
|
|
|
return ERR_PTR(-EINVAL);
|
|
|
|
|
|
|
|
|
|
BUILD_BUG_ON(sizeof(struct bpf_stack_build_id) % sizeof(u64));
|
|
|
|
|
if (attr->map_flags & BPF_F_STACK_BUILD_ID) {
|
|
|
|
|
if (value_size % sizeof(struct bpf_stack_build_id) ||
|
|
|
|
|
value_size / sizeof(struct bpf_stack_build_id)
|
|
|
|
|
> sysctl_perf_event_max_stack)
|
|
|
|
|
return ERR_PTR(-EINVAL);
|
|
|
|
|
} else if (value_size / 8 > sysctl_perf_event_max_stack)
|
2016-02-18 11:58:58 +08:00
|
|
|
return ERR_PTR(-EINVAL);
|
|
|
|
|
|
|
|
|
|
/* hash table size must be power of 2 */
|
|
|
|
|
n_buckets = roundup_pow_of_two(attr->max_entries);
|
|
|
|
|
|
|
|
|
|
cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap);
|
|
|
|
|
if (cost >= U32_MAX - PAGE_SIZE)
|
|
|
|
|
return ERR_PTR(-E2BIG);
|
|
|
|
|
|
2017-08-19 02:28:00 +08:00
|
|
|
smap = bpf_map_area_alloc(cost, bpf_map_attr_numa_node(attr));
|
bpf: don't trigger OOM killer under pressure with map alloc
This patch adds two helpers, bpf_map_area_alloc() and bpf_map_area_free(),
that are to be used for map allocations. Using kmalloc() for very large
allocations can cause excessive work within the page allocator, so i) fall
back earlier to vmalloc() when the attempt is considered costly anyway,
and even more importantly ii) don't trigger OOM killer with any of the
allocators.
Since this is based on a user space request, for example, when creating
maps with element pre-allocation, we really want such requests to fail
instead of killing other user space processes.
Also, don't spam the kernel log with warnings should any of the allocations
fail under pressure. Given that, we can make backend selection in
bpf_map_area_alloc() generic, and convert all maps over to use this API
for spots with potentially large allocation requests.
Note, replacing the one kmalloc_array() is fine as overflow checks happen
earlier in htab_map_alloc(), since it must also protect the multiplication
for vmalloc() should kmalloc_array() fail.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-18 22:14:17 +08:00
|
|
|
if (!smap)
|
|
|
|
|
return ERR_PTR(-ENOMEM);
|
2016-02-18 11:58:58 +08:00
|
|
|
|
|
|
|
|
err = -E2BIG;
|
|
|
|
|
cost += n_buckets * (value_size + sizeof(struct stack_map_bucket));
|
|
|
|
|
if (cost >= U32_MAX - PAGE_SIZE)
|
|
|
|
|
goto free_smap;
|
|
|
|
|
|
2018-01-12 12:29:06 +08:00
|
|
|
bpf_map_init_from_attr(&smap->map, attr);
|
2016-02-18 11:58:58 +08:00
|
|
|
smap->map.value_size = value_size;
|
|
|
|
|
smap->n_buckets = n_buckets;
|
|
|
|
|
smap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
|
|
|
|
|
|
2016-03-08 13:57:17 +08:00
|
|
|
err = bpf_map_precharge_memlock(smap->map.pages);
|
|
|
|
|
if (err)
|
|
|
|
|
goto free_smap;
|
|
|
|
|
|
2016-04-29 00:16:33 +08:00
|
|
|
err = get_callchain_buffers(sysctl_perf_event_max_stack);
|
2016-02-18 11:58:58 +08:00
|
|
|
if (err)
|
|
|
|
|
goto free_smap;
|
|
|
|
|
|
2016-03-08 13:57:17 +08:00
|
|
|
err = prealloc_elems_and_freelist(smap);
|
|
|
|
|
if (err)
|
|
|
|
|
goto put_buffers;
|
|
|
|
|
|
2016-02-18 11:58:58 +08:00
|
|
|
return &smap->map;
|
|
|
|
|
|
2016-03-08 13:57:17 +08:00
|
|
|
put_buffers:
|
|
|
|
|
put_callchain_buffers();
|
2016-02-18 11:58:58 +08:00
|
|
|
free_smap:
|
bpf: don't trigger OOM killer under pressure with map alloc
This patch adds two helpers, bpf_map_area_alloc() and bpf_map_area_free(),
that are to be used for map allocations. Using kmalloc() for very large
allocations can cause excessive work within the page allocator, so i) fall
back earlier to vmalloc() when the attempt is considered costly anyway,
and even more importantly ii) don't trigger OOM killer with any of the
allocators.
Since this is based on a user space request, for example, when creating
maps with element pre-allocation, we really want such requests to fail
instead of killing other user space processes.
Also, don't spam the kernel log with warnings should any of the allocations
fail under pressure. Given that, we can make backend selection in
bpf_map_area_alloc() generic, and convert all maps over to use this API
for spots with potentially large allocation requests.
Note, replacing the one kmalloc_array() is fine as overflow checks happen
earlier in htab_map_alloc(), since it must also protect the multiplication
for vmalloc() should kmalloc_array() fail.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-18 22:14:17 +08:00
|
|
|
bpf_map_area_free(smap);
|
2016-02-18 11:58:58 +08:00
|
|
|
return ERR_PTR(err);
|
|
|
|
|
}
|
|
|
|
|
|
bpf: extend stackmap to save binary_build_id+offset instead of address
Currently, bpf stackmap store address for each entry in the call trace.
To map these addresses to user space files, it is necessary to maintain
the mapping from these virtual address to symbols in the binary. Usually,
the user space profiler (such as perf) has to scan /proc/pid/maps at the
beginning of profiling, and monitor mmap2() calls afterwards. Given the
cost of maintaining the address map, this solution is not practical for
system wide profiling that is always on.
This patch tries to solve this problem with a variation of stackmap. This
variation is enabled by flag BPF_F_STACK_BUILD_ID. Instead of storing
addresses, the variation stores ELF file build_id + offset.
Build ID is a 20-byte unique identifier for ELF files. The following
command shows the Build ID of /bin/bash:
[user@]$ readelf -n /bin/bash
...
Build ID: XXXXXXXXXX
...
With BPF_F_STACK_BUILD_ID, bpf_get_stackid() tries to parse Build ID
for each entry in the call trace, and translate it into the following
struct:
struct bpf_stack_build_id_offset {
__s32 status;
unsigned char build_id[BPF_BUILD_ID_SIZE];
union {
__u64 offset;
__u64 ip;
};
};
The search of build_id is limited to the first page of the file, and this
page should be in page cache. Otherwise, we fallback to store ip for this
entry (ip field in struct bpf_stack_build_id_offset). This requires the
build_id to be stored in the first page. A quick survey of binary and
dynamic library files in a few different systems shows that almost all
binary and dynamic library files have build_id in the first page.
Build_id is only meaningful for user stack. If a kernel stack is added to
a stackmap with BPF_F_STACK_BUILD_ID, it will automatically fallback to
only store ip (status == BPF_STACK_BUILD_ID_IP). Similarly, if build_id
lookup failed for some reason, it will also fallback to store ip.
User space can access struct bpf_stack_build_id_offset with bpf
syscall BPF_MAP_LOOKUP_ELEM. It is necessary for user space to
maintain mapping from build id to binary files. This mostly static
mapping is much easier to maintain than per process address maps.
Note: Stackmap with build_id only works in non-nmi context at this time.
This is because we need to take mm->mmap_sem for find_vma(). If this
changes, we would like to allow build_id lookup in nmi context.
Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-03-15 01:23:21 +08:00
|
|
|
#define BPF_BUILD_ID 3
|
|
|
|
|
/*
|
|
|
|
|
* Parse build id from the note segment. This logic can be shared between
|
|
|
|
|
* 32-bit and 64-bit system, because Elf32_Nhdr and Elf64_Nhdr are
|
|
|
|
|
* identical.
|
|
|
|
|
*/
|
|
|
|
|
static inline int stack_map_parse_build_id(void *page_addr,
|
|
|
|
|
unsigned char *build_id,
|
|
|
|
|
void *note_start,
|
|
|
|
|
Elf32_Word note_size)
|
|
|
|
|
{
|
|
|
|
|
Elf32_Word note_offs = 0, new_offs;
|
|
|
|
|
|
|
|
|
|
/* check for overflow */
|
|
|
|
|
if (note_start < page_addr || note_start + note_size < note_start)
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
|
|
/* only supports note that fits in the first page */
|
|
|
|
|
if (note_start + note_size > page_addr + PAGE_SIZE)
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
|
|
while (note_offs + sizeof(Elf32_Nhdr) < note_size) {
|
|
|
|
|
Elf32_Nhdr *nhdr = (Elf32_Nhdr *)(note_start + note_offs);
|
|
|
|
|
|
|
|
|
|
if (nhdr->n_type == BPF_BUILD_ID &&
|
|
|
|
|
nhdr->n_namesz == sizeof("GNU") &&
|
|
|
|
|
nhdr->n_descsz == BPF_BUILD_ID_SIZE) {
|
|
|
|
|
memcpy(build_id,
|
|
|
|
|
note_start + note_offs +
|
|
|
|
|
ALIGN(sizeof("GNU"), 4) + sizeof(Elf32_Nhdr),
|
|
|
|
|
BPF_BUILD_ID_SIZE);
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
new_offs = note_offs + sizeof(Elf32_Nhdr) +
|
|
|
|
|
ALIGN(nhdr->n_namesz, 4) + ALIGN(nhdr->n_descsz, 4);
|
|
|
|
|
if (new_offs <= note_offs) /* overflow */
|
|
|
|
|
break;
|
|
|
|
|
note_offs = new_offs;
|
|
|
|
|
}
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Parse build ID from 32-bit ELF */
|
|
|
|
|
static int stack_map_get_build_id_32(void *page_addr,
|
|
|
|
|
unsigned char *build_id)
|
|
|
|
|
{
|
|
|
|
|
Elf32_Ehdr *ehdr = (Elf32_Ehdr *)page_addr;
|
|
|
|
|
Elf32_Phdr *phdr;
|
|
|
|
|
int i;
|
|
|
|
|
|
|
|
|
|
/* only supports phdr that fits in one page */
|
|
|
|
|
if (ehdr->e_phnum >
|
|
|
|
|
(PAGE_SIZE - sizeof(Elf32_Ehdr)) / sizeof(Elf32_Phdr))
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
|
|
phdr = (Elf32_Phdr *)(page_addr + sizeof(Elf32_Ehdr));
|
|
|
|
|
|
|
|
|
|
for (i = 0; i < ehdr->e_phnum; ++i)
|
|
|
|
|
if (phdr[i].p_type == PT_NOTE)
|
|
|
|
|
return stack_map_parse_build_id(page_addr, build_id,
|
|
|
|
|
page_addr + phdr[i].p_offset,
|
|
|
|
|
phdr[i].p_filesz);
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Parse build ID from 64-bit ELF */
|
|
|
|
|
static int stack_map_get_build_id_64(void *page_addr,
|
|
|
|
|
unsigned char *build_id)
|
|
|
|
|
{
|
|
|
|
|
Elf64_Ehdr *ehdr = (Elf64_Ehdr *)page_addr;
|
|
|
|
|
Elf64_Phdr *phdr;
|
|
|
|
|
int i;
|
|
|
|
|
|
|
|
|
|
/* only supports phdr that fits in one page */
|
|
|
|
|
if (ehdr->e_phnum >
|
|
|
|
|
(PAGE_SIZE - sizeof(Elf64_Ehdr)) / sizeof(Elf64_Phdr))
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
|
|
phdr = (Elf64_Phdr *)(page_addr + sizeof(Elf64_Ehdr));
|
|
|
|
|
|
|
|
|
|
for (i = 0; i < ehdr->e_phnum; ++i)
|
|
|
|
|
if (phdr[i].p_type == PT_NOTE)
|
|
|
|
|
return stack_map_parse_build_id(page_addr, build_id,
|
|
|
|
|
page_addr + phdr[i].p_offset,
|
|
|
|
|
phdr[i].p_filesz);
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Parse build ID of ELF file mapped to vma */
|
|
|
|
|
static int stack_map_get_build_id(struct vm_area_struct *vma,
|
|
|
|
|
unsigned char *build_id)
|
|
|
|
|
{
|
|
|
|
|
Elf32_Ehdr *ehdr;
|
|
|
|
|
struct page *page;
|
|
|
|
|
void *page_addr;
|
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
|
|
/* only works for page backed storage */
|
|
|
|
|
if (!vma->vm_file)
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
|
|
page = find_get_page(vma->vm_file->f_mapping, 0);
|
|
|
|
|
if (!page)
|
|
|
|
|
return -EFAULT; /* page not mapped */
|
|
|
|
|
|
|
|
|
|
ret = -EINVAL;
|
|
|
|
|
page_addr = page_address(page);
|
|
|
|
|
ehdr = (Elf32_Ehdr *)page_addr;
|
|
|
|
|
|
|
|
|
|
/* compare magic x7f "ELF" */
|
|
|
|
|
if (memcmp(ehdr->e_ident, ELFMAG, SELFMAG) != 0)
|
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
|
|
/* only support executable file and shared object file */
|
|
|
|
|
if (ehdr->e_type != ET_EXEC && ehdr->e_type != ET_DYN)
|
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
|
|
if (ehdr->e_ident[EI_CLASS] == ELFCLASS32)
|
|
|
|
|
ret = stack_map_get_build_id_32(page_addr, build_id);
|
|
|
|
|
else if (ehdr->e_ident[EI_CLASS] == ELFCLASS64)
|
|
|
|
|
ret = stack_map_get_build_id_64(page_addr, build_id);
|
|
|
|
|
out:
|
|
|
|
|
put_page(page);
|
|
|
|
|
return ret;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void stack_map_get_build_id_offset(struct bpf_map *map,
|
|
|
|
|
struct stack_map_bucket *bucket,
|
|
|
|
|
u64 *ips, u32 trace_nr, bool user)
|
|
|
|
|
{
|
|
|
|
|
int i;
|
|
|
|
|
struct vm_area_struct *vma;
|
|
|
|
|
struct bpf_stack_build_id *id_offs;
|
|
|
|
|
|
|
|
|
|
bucket->nr = trace_nr;
|
|
|
|
|
id_offs = (struct bpf_stack_build_id *)bucket->data;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* We cannot do up_read() in nmi context, so build_id lookup is
|
|
|
|
|
* only supported for non-nmi events. If at some point, it is
|
|
|
|
|
* possible to run find_vma() without taking the semaphore, we
|
|
|
|
|
* would like to allow build_id lookup in nmi context.
|
|
|
|
|
*
|
|
|
|
|
* Same fallback is used for kernel stack (!user) on a stackmap
|
|
|
|
|
* with build_id.
|
|
|
|
|
*/
|
|
|
|
|
if (!user || !current || !current->mm || in_nmi() ||
|
|
|
|
|
down_read_trylock(¤t->mm->mmap_sem) == 0) {
|
|
|
|
|
/* cannot access current->mm, fall back to ips */
|
|
|
|
|
for (i = 0; i < trace_nr; i++) {
|
|
|
|
|
id_offs[i].status = BPF_STACK_BUILD_ID_IP;
|
|
|
|
|
id_offs[i].ip = ips[i];
|
|
|
|
|
}
|
|
|
|
|
return;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
for (i = 0; i < trace_nr; i++) {
|
|
|
|
|
vma = find_vma(current->mm, ips[i]);
|
|
|
|
|
if (!vma || stack_map_get_build_id(vma, id_offs[i].build_id)) {
|
|
|
|
|
/* per entry fall back to ips */
|
|
|
|
|
id_offs[i].status = BPF_STACK_BUILD_ID_IP;
|
|
|
|
|
id_offs[i].ip = ips[i];
|
|
|
|
|
continue;
|
|
|
|
|
}
|
|
|
|
|
id_offs[i].offset = (vma->vm_pgoff << PAGE_SHIFT) + ips[i]
|
|
|
|
|
- vma->vm_start;
|
|
|
|
|
id_offs[i].status = BPF_STACK_BUILD_ID_VALID;
|
|
|
|
|
}
|
|
|
|
|
up_read(¤t->mm->mmap_sem);
|
|
|
|
|
}
|
|
|
|
|
|
bpf: add BPF_CALL_x macros for declaring helpers
This work adds BPF_CALL_<n>() macros and converts all the eBPF helper functions
to use them, in a similar fashion like we do with SYSCALL_DEFINE<n>() macros
that are used today. Motivation for this is to hide all the register handling
and all necessary casts from the user, so that it is done automatically in the
background when adding a BPF_CALL_<n>() call.
This makes current helpers easier to review, eases to write future helpers,
avoids getting the casting mess wrong, and allows for extending all helpers at
once (f.e. build time checks, etc). It also helps detecting more easily in
code reviews that unused registers are not instrumented in the code by accident,
breaking compatibility with existing programs.
BPF_CALL_<n>() internals are quite similar to SYSCALL_DEFINE<n>() ones with some
fundamental differences, for example, for generating the actual helper function
that carries all u64 regs, we need to fill unused regs, so that we always end up
with 5 u64 regs as an argument.
I reviewed several 0-5 generated BPF_CALL_<n>() variants of the .i results and
they look all as expected. No sparse issue spotted. We let this also sit for a
few days with Fengguang's kbuild test robot, and there were no issues seen. On
s390, it barked on the "uses dynamic stack allocation" notice, which is an old
one from bpf_perf_event_output{,_tp}() reappearing here due to the conversion
to the call wrapper, just telling that the perf raw record/frag sits on stack
(gcc with s390's -mwarn-dynamicstack), but that's all. Did various runtime tests
and they were fine as well. All eBPF helpers are now converted to use these
macros, getting rid of a good chunk of all the raw castings.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-09-09 08:45:31 +08:00
|
|
|
BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
|
|
|
|
|
u64, flags)
|
2016-02-18 11:58:58 +08:00
|
|
|
{
|
|
|
|
|
struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
|
|
|
|
|
struct perf_callchain_entry *trace;
|
|
|
|
|
struct stack_map_bucket *bucket, *new_bucket, *old_bucket;
|
bpf: extend stackmap to save binary_build_id+offset instead of address
Currently, bpf stackmap store address for each entry in the call trace.
To map these addresses to user space files, it is necessary to maintain
the mapping from these virtual address to symbols in the binary. Usually,
the user space profiler (such as perf) has to scan /proc/pid/maps at the
beginning of profiling, and monitor mmap2() calls afterwards. Given the
cost of maintaining the address map, this solution is not practical for
system wide profiling that is always on.
This patch tries to solve this problem with a variation of stackmap. This
variation is enabled by flag BPF_F_STACK_BUILD_ID. Instead of storing
addresses, the variation stores ELF file build_id + offset.
Build ID is a 20-byte unique identifier for ELF files. The following
command shows the Build ID of /bin/bash:
[user@]$ readelf -n /bin/bash
...
Build ID: XXXXXXXXXX
...
With BPF_F_STACK_BUILD_ID, bpf_get_stackid() tries to parse Build ID
for each entry in the call trace, and translate it into the following
struct:
struct bpf_stack_build_id_offset {
__s32 status;
unsigned char build_id[BPF_BUILD_ID_SIZE];
union {
__u64 offset;
__u64 ip;
};
};
The search of build_id is limited to the first page of the file, and this
page should be in page cache. Otherwise, we fallback to store ip for this
entry (ip field in struct bpf_stack_build_id_offset). This requires the
build_id to be stored in the first page. A quick survey of binary and
dynamic library files in a few different systems shows that almost all
binary and dynamic library files have build_id in the first page.
Build_id is only meaningful for user stack. If a kernel stack is added to
a stackmap with BPF_F_STACK_BUILD_ID, it will automatically fallback to
only store ip (status == BPF_STACK_BUILD_ID_IP). Similarly, if build_id
lookup failed for some reason, it will also fallback to store ip.
User space can access struct bpf_stack_build_id_offset with bpf
syscall BPF_MAP_LOOKUP_ELEM. It is necessary for user space to
maintain mapping from build id to binary files. This mostly static
mapping is much easier to maintain than per process address maps.
Note: Stackmap with build_id only works in non-nmi context at this time.
This is because we need to take mm->mmap_sem for find_vma(). If this
changes, we would like to allow build_id lookup in nmi context.
Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-03-15 01:23:21 +08:00
|
|
|
u32 max_depth = map->value_size / stack_map_data_size(map);
|
2016-04-21 23:28:50 +08:00
|
|
|
/* stack_map_alloc() checks that max_depth <= sysctl_perf_event_max_stack */
|
|
|
|
|
u32 init_nr = sysctl_perf_event_max_stack - max_depth;
|
2016-02-18 11:58:58 +08:00
|
|
|
u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
|
|
|
|
|
u32 hash, id, trace_nr, trace_len;
|
|
|
|
|
bool user = flags & BPF_F_USER_STACK;
|
|
|
|
|
bool kernel = !user;
|
|
|
|
|
u64 *ips;
|
bpf: extend stackmap to save binary_build_id+offset instead of address
Currently, bpf stackmap store address for each entry in the call trace.
To map these addresses to user space files, it is necessary to maintain
the mapping from these virtual address to symbols in the binary. Usually,
the user space profiler (such as perf) has to scan /proc/pid/maps at the
beginning of profiling, and monitor mmap2() calls afterwards. Given the
cost of maintaining the address map, this solution is not practical for
system wide profiling that is always on.
This patch tries to solve this problem with a variation of stackmap. This
variation is enabled by flag BPF_F_STACK_BUILD_ID. Instead of storing
addresses, the variation stores ELF file build_id + offset.
Build ID is a 20-byte unique identifier for ELF files. The following
command shows the Build ID of /bin/bash:
[user@]$ readelf -n /bin/bash
...
Build ID: XXXXXXXXXX
...
With BPF_F_STACK_BUILD_ID, bpf_get_stackid() tries to parse Build ID
for each entry in the call trace, and translate it into the following
struct:
struct bpf_stack_build_id_offset {
__s32 status;
unsigned char build_id[BPF_BUILD_ID_SIZE];
union {
__u64 offset;
__u64 ip;
};
};
The search of build_id is limited to the first page of the file, and this
page should be in page cache. Otherwise, we fallback to store ip for this
entry (ip field in struct bpf_stack_build_id_offset). This requires the
build_id to be stored in the first page. A quick survey of binary and
dynamic library files in a few different systems shows that almost all
binary and dynamic library files have build_id in the first page.
Build_id is only meaningful for user stack. If a kernel stack is added to
a stackmap with BPF_F_STACK_BUILD_ID, it will automatically fallback to
only store ip (status == BPF_STACK_BUILD_ID_IP). Similarly, if build_id
lookup failed for some reason, it will also fallback to store ip.
User space can access struct bpf_stack_build_id_offset with bpf
syscall BPF_MAP_LOOKUP_ELEM. It is necessary for user space to
maintain mapping from build id to binary files. This mostly static
mapping is much easier to maintain than per process address maps.
Note: Stackmap with build_id only works in non-nmi context at this time.
This is because we need to take mm->mmap_sem for find_vma(). If this
changes, we would like to allow build_id lookup in nmi context.
Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-03-15 01:23:21 +08:00
|
|
|
bool hash_matches;
|
2016-02-18 11:58:58 +08:00
|
|
|
|
|
|
|
|
if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
|
|
|
|
|
BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID)))
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
2016-04-28 23:30:53 +08:00
|
|
|
trace = get_perf_callchain(regs, init_nr, kernel, user,
|
|
|
|
|
sysctl_perf_event_max_stack, false, false);
|
2016-02-18 11:58:58 +08:00
|
|
|
|
|
|
|
|
if (unlikely(!trace))
|
|
|
|
|
/* couldn't fetch the stack trace */
|
|
|
|
|
return -EFAULT;
|
|
|
|
|
|
|
|
|
|
/* get_perf_callchain() guarantees that trace->nr >= init_nr
|
2016-04-21 23:28:50 +08:00
|
|
|
* and trace-nr <= sysctl_perf_event_max_stack, so trace_nr <= max_depth
|
2016-02-18 11:58:58 +08:00
|
|
|
*/
|
|
|
|
|
trace_nr = trace->nr - init_nr;
|
|
|
|
|
|
|
|
|
|
if (trace_nr <= skip)
|
|
|
|
|
/* skipping more than usable stack trace */
|
|
|
|
|
return -EFAULT;
|
|
|
|
|
|
|
|
|
|
trace_nr -= skip;
|
|
|
|
|
trace_len = trace_nr * sizeof(u64);
|
|
|
|
|
ips = trace->ip + skip + init_nr;
|
|
|
|
|
hash = jhash2((u32 *)ips, trace_len / sizeof(u32), 0);
|
|
|
|
|
id = hash & (smap->n_buckets - 1);
|
2016-03-08 13:57:17 +08:00
|
|
|
bucket = READ_ONCE(smap->buckets[id]);
|
2016-02-18 11:58:58 +08:00
|
|
|
|
bpf: extend stackmap to save binary_build_id+offset instead of address
Currently, bpf stackmap store address for each entry in the call trace.
To map these addresses to user space files, it is necessary to maintain
the mapping from these virtual address to symbols in the binary. Usually,
the user space profiler (such as perf) has to scan /proc/pid/maps at the
beginning of profiling, and monitor mmap2() calls afterwards. Given the
cost of maintaining the address map, this solution is not practical for
system wide profiling that is always on.
This patch tries to solve this problem with a variation of stackmap. This
variation is enabled by flag BPF_F_STACK_BUILD_ID. Instead of storing
addresses, the variation stores ELF file build_id + offset.
Build ID is a 20-byte unique identifier for ELF files. The following
command shows the Build ID of /bin/bash:
[user@]$ readelf -n /bin/bash
...
Build ID: XXXXXXXXXX
...
With BPF_F_STACK_BUILD_ID, bpf_get_stackid() tries to parse Build ID
for each entry in the call trace, and translate it into the following
struct:
struct bpf_stack_build_id_offset {
__s32 status;
unsigned char build_id[BPF_BUILD_ID_SIZE];
union {
__u64 offset;
__u64 ip;
};
};
The search of build_id is limited to the first page of the file, and this
page should be in page cache. Otherwise, we fallback to store ip for this
entry (ip field in struct bpf_stack_build_id_offset). This requires the
build_id to be stored in the first page. A quick survey of binary and
dynamic library files in a few different systems shows that almost all
binary and dynamic library files have build_id in the first page.
Build_id is only meaningful for user stack. If a kernel stack is added to
a stackmap with BPF_F_STACK_BUILD_ID, it will automatically fallback to
only store ip (status == BPF_STACK_BUILD_ID_IP). Similarly, if build_id
lookup failed for some reason, it will also fallback to store ip.
User space can access struct bpf_stack_build_id_offset with bpf
syscall BPF_MAP_LOOKUP_ELEM. It is necessary for user space to
maintain mapping from build id to binary files. This mostly static
mapping is much easier to maintain than per process address maps.
Note: Stackmap with build_id only works in non-nmi context at this time.
This is because we need to take mm->mmap_sem for find_vma(). If this
changes, we would like to allow build_id lookup in nmi context.
Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-03-15 01:23:21 +08:00
|
|
|
hash_matches = bucket && bucket->hash == hash;
|
|
|
|
|
/* fast cmp */
|
|
|
|
|
if (hash_matches && flags & BPF_F_FAST_STACK_CMP)
|
|
|
|
|
return id;
|
|
|
|
|
|
|
|
|
|
if (stack_map_use_build_id(map)) {
|
|
|
|
|
/* for build_id+offset, pop a bucket before slow cmp */
|
|
|
|
|
new_bucket = (struct stack_map_bucket *)
|
|
|
|
|
pcpu_freelist_pop(&smap->freelist);
|
|
|
|
|
if (unlikely(!new_bucket))
|
|
|
|
|
return -ENOMEM;
|
|
|
|
|
stack_map_get_build_id_offset(map, new_bucket, ips,
|
|
|
|
|
trace_nr, user);
|
|
|
|
|
trace_len = trace_nr * sizeof(struct bpf_stack_build_id);
|
|
|
|
|
if (hash_matches && bucket->nr == trace_nr &&
|
|
|
|
|
memcmp(bucket->data, new_bucket->data, trace_len) == 0) {
|
|
|
|
|
pcpu_freelist_push(&smap->freelist, &new_bucket->fnode);
|
2016-02-18 11:58:58 +08:00
|
|
|
return id;
|
bpf: extend stackmap to save binary_build_id+offset instead of address
Currently, bpf stackmap store address for each entry in the call trace.
To map these addresses to user space files, it is necessary to maintain
the mapping from these virtual address to symbols in the binary. Usually,
the user space profiler (such as perf) has to scan /proc/pid/maps at the
beginning of profiling, and monitor mmap2() calls afterwards. Given the
cost of maintaining the address map, this solution is not practical for
system wide profiling that is always on.
This patch tries to solve this problem with a variation of stackmap. This
variation is enabled by flag BPF_F_STACK_BUILD_ID. Instead of storing
addresses, the variation stores ELF file build_id + offset.
Build ID is a 20-byte unique identifier for ELF files. The following
command shows the Build ID of /bin/bash:
[user@]$ readelf -n /bin/bash
...
Build ID: XXXXXXXXXX
...
With BPF_F_STACK_BUILD_ID, bpf_get_stackid() tries to parse Build ID
for each entry in the call trace, and translate it into the following
struct:
struct bpf_stack_build_id_offset {
__s32 status;
unsigned char build_id[BPF_BUILD_ID_SIZE];
union {
__u64 offset;
__u64 ip;
};
};
The search of build_id is limited to the first page of the file, and this
page should be in page cache. Otherwise, we fallback to store ip for this
entry (ip field in struct bpf_stack_build_id_offset). This requires the
build_id to be stored in the first page. A quick survey of binary and
dynamic library files in a few different systems shows that almost all
binary and dynamic library files have build_id in the first page.
Build_id is only meaningful for user stack. If a kernel stack is added to
a stackmap with BPF_F_STACK_BUILD_ID, it will automatically fallback to
only store ip (status == BPF_STACK_BUILD_ID_IP). Similarly, if build_id
lookup failed for some reason, it will also fallback to store ip.
User space can access struct bpf_stack_build_id_offset with bpf
syscall BPF_MAP_LOOKUP_ELEM. It is necessary for user space to
maintain mapping from build id to binary files. This mostly static
mapping is much easier to maintain than per process address maps.
Note: Stackmap with build_id only works in non-nmi context at this time.
This is because we need to take mm->mmap_sem for find_vma(). If this
changes, we would like to allow build_id lookup in nmi context.
Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-03-15 01:23:21 +08:00
|
|
|
}
|
|
|
|
|
if (bucket && !(flags & BPF_F_REUSE_STACKID)) {
|
|
|
|
|
pcpu_freelist_push(&smap->freelist, &new_bucket->fnode);
|
|
|
|
|
return -EEXIST;
|
|
|
|
|
}
|
|
|
|
|
} else {
|
|
|
|
|
if (hash_matches && bucket->nr == trace_nr &&
|
|
|
|
|
memcmp(bucket->data, ips, trace_len) == 0)
|
2016-02-18 11:58:58 +08:00
|
|
|
return id;
|
bpf: extend stackmap to save binary_build_id+offset instead of address
Currently, bpf stackmap store address for each entry in the call trace.
To map these addresses to user space files, it is necessary to maintain
the mapping from these virtual address to symbols in the binary. Usually,
the user space profiler (such as perf) has to scan /proc/pid/maps at the
beginning of profiling, and monitor mmap2() calls afterwards. Given the
cost of maintaining the address map, this solution is not practical for
system wide profiling that is always on.
This patch tries to solve this problem with a variation of stackmap. This
variation is enabled by flag BPF_F_STACK_BUILD_ID. Instead of storing
addresses, the variation stores ELF file build_id + offset.
Build ID is a 20-byte unique identifier for ELF files. The following
command shows the Build ID of /bin/bash:
[user@]$ readelf -n /bin/bash
...
Build ID: XXXXXXXXXX
...
With BPF_F_STACK_BUILD_ID, bpf_get_stackid() tries to parse Build ID
for each entry in the call trace, and translate it into the following
struct:
struct bpf_stack_build_id_offset {
__s32 status;
unsigned char build_id[BPF_BUILD_ID_SIZE];
union {
__u64 offset;
__u64 ip;
};
};
The search of build_id is limited to the first page of the file, and this
page should be in page cache. Otherwise, we fallback to store ip for this
entry (ip field in struct bpf_stack_build_id_offset). This requires the
build_id to be stored in the first page. A quick survey of binary and
dynamic library files in a few different systems shows that almost all
binary and dynamic library files have build_id in the first page.
Build_id is only meaningful for user stack. If a kernel stack is added to
a stackmap with BPF_F_STACK_BUILD_ID, it will automatically fallback to
only store ip (status == BPF_STACK_BUILD_ID_IP). Similarly, if build_id
lookup failed for some reason, it will also fallback to store ip.
User space can access struct bpf_stack_build_id_offset with bpf
syscall BPF_MAP_LOOKUP_ELEM. It is necessary for user space to
maintain mapping from build id to binary files. This mostly static
mapping is much easier to maintain than per process address maps.
Note: Stackmap with build_id only works in non-nmi context at this time.
This is because we need to take mm->mmap_sem for find_vma(). If this
changes, we would like to allow build_id lookup in nmi context.
Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-03-15 01:23:21 +08:00
|
|
|
if (bucket && !(flags & BPF_F_REUSE_STACKID))
|
|
|
|
|
return -EEXIST;
|
|
|
|
|
|
|
|
|
|
new_bucket = (struct stack_map_bucket *)
|
|
|
|
|
pcpu_freelist_pop(&smap->freelist);
|
|
|
|
|
if (unlikely(!new_bucket))
|
|
|
|
|
return -ENOMEM;
|
|
|
|
|
memcpy(new_bucket->data, ips, trace_len);
|
2016-02-18 11:58:58 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
new_bucket->hash = hash;
|
|
|
|
|
new_bucket->nr = trace_nr;
|
|
|
|
|
|
|
|
|
|
old_bucket = xchg(&smap->buckets[id], new_bucket);
|
|
|
|
|
if (old_bucket)
|
2016-03-08 13:57:17 +08:00
|
|
|
pcpu_freelist_push(&smap->freelist, &old_bucket->fnode);
|
2016-02-18 11:58:58 +08:00
|
|
|
return id;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
const struct bpf_func_proto bpf_get_stackid_proto = {
|
|
|
|
|
.func = bpf_get_stackid,
|
|
|
|
|
.gpl_only = true,
|
|
|
|
|
.ret_type = RET_INTEGER,
|
|
|
|
|
.arg1_type = ARG_PTR_TO_CTX,
|
|
|
|
|
.arg2_type = ARG_CONST_MAP_PTR,
|
|
|
|
|
.arg3_type = ARG_ANYTHING,
|
|
|
|
|
};
|
|
|
|
|
|
2016-03-08 13:57:17 +08:00
|
|
|
/* Called from eBPF program */
|
2016-02-18 11:58:58 +08:00
|
|
|
static void *stack_map_lookup_elem(struct bpf_map *map, void *key)
|
2016-03-08 13:57:17 +08:00
|
|
|
{
|
|
|
|
|
return NULL;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Called from syscall */
|
|
|
|
|
int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value)
|
2016-02-18 11:58:58 +08:00
|
|
|
{
|
|
|
|
|
struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
|
2016-03-08 13:57:17 +08:00
|
|
|
struct stack_map_bucket *bucket, *old_bucket;
|
|
|
|
|
u32 id = *(u32 *)key, trace_len;
|
2016-02-18 11:58:58 +08:00
|
|
|
|
|
|
|
|
if (unlikely(id >= smap->n_buckets))
|
2016-03-08 13:57:17 +08:00
|
|
|
return -ENOENT;
|
|
|
|
|
|
|
|
|
|
bucket = xchg(&smap->buckets[id], NULL);
|
|
|
|
|
if (!bucket)
|
|
|
|
|
return -ENOENT;
|
|
|
|
|
|
bpf: extend stackmap to save binary_build_id+offset instead of address
Currently, bpf stackmap store address for each entry in the call trace.
To map these addresses to user space files, it is necessary to maintain
the mapping from these virtual address to symbols in the binary. Usually,
the user space profiler (such as perf) has to scan /proc/pid/maps at the
beginning of profiling, and monitor mmap2() calls afterwards. Given the
cost of maintaining the address map, this solution is not practical for
system wide profiling that is always on.
This patch tries to solve this problem with a variation of stackmap. This
variation is enabled by flag BPF_F_STACK_BUILD_ID. Instead of storing
addresses, the variation stores ELF file build_id + offset.
Build ID is a 20-byte unique identifier for ELF files. The following
command shows the Build ID of /bin/bash:
[user@]$ readelf -n /bin/bash
...
Build ID: XXXXXXXXXX
...
With BPF_F_STACK_BUILD_ID, bpf_get_stackid() tries to parse Build ID
for each entry in the call trace, and translate it into the following
struct:
struct bpf_stack_build_id_offset {
__s32 status;
unsigned char build_id[BPF_BUILD_ID_SIZE];
union {
__u64 offset;
__u64 ip;
};
};
The search of build_id is limited to the first page of the file, and this
page should be in page cache. Otherwise, we fallback to store ip for this
entry (ip field in struct bpf_stack_build_id_offset). This requires the
build_id to be stored in the first page. A quick survey of binary and
dynamic library files in a few different systems shows that almost all
binary and dynamic library files have build_id in the first page.
Build_id is only meaningful for user stack. If a kernel stack is added to
a stackmap with BPF_F_STACK_BUILD_ID, it will automatically fallback to
only store ip (status == BPF_STACK_BUILD_ID_IP). Similarly, if build_id
lookup failed for some reason, it will also fallback to store ip.
User space can access struct bpf_stack_build_id_offset with bpf
syscall BPF_MAP_LOOKUP_ELEM. It is necessary for user space to
maintain mapping from build id to binary files. This mostly static
mapping is much easier to maintain than per process address maps.
Note: Stackmap with build_id only works in non-nmi context at this time.
This is because we need to take mm->mmap_sem for find_vma(). If this
changes, we would like to allow build_id lookup in nmi context.
Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-03-15 01:23:21 +08:00
|
|
|
trace_len = bucket->nr * stack_map_data_size(map);
|
|
|
|
|
memcpy(value, bucket->data, trace_len);
|
2016-03-08 13:57:17 +08:00
|
|
|
memset(value + trace_len, 0, map->value_size - trace_len);
|
|
|
|
|
|
|
|
|
|
old_bucket = xchg(&smap->buckets[id], bucket);
|
|
|
|
|
if (old_bucket)
|
|
|
|
|
pcpu_freelist_push(&smap->freelist, &old_bucket->fnode);
|
|
|
|
|
return 0;
|
2016-02-18 11:58:58 +08:00
|
|
|
}
|
|
|
|
|
|
2018-01-05 05:55:03 +08:00
|
|
|
static int stack_map_get_next_key(struct bpf_map *map, void *key,
|
|
|
|
|
void *next_key)
|
2016-02-18 11:58:58 +08:00
|
|
|
{
|
2018-01-05 05:55:03 +08:00
|
|
|
struct bpf_stack_map *smap = container_of(map,
|
|
|
|
|
struct bpf_stack_map, map);
|
|
|
|
|
u32 id;
|
|
|
|
|
|
|
|
|
|
WARN_ON_ONCE(!rcu_read_lock_held());
|
|
|
|
|
|
|
|
|
|
if (!key) {
|
|
|
|
|
id = 0;
|
|
|
|
|
} else {
|
|
|
|
|
id = *(u32 *)key;
|
|
|
|
|
if (id >= smap->n_buckets || !smap->buckets[id])
|
|
|
|
|
id = 0;
|
|
|
|
|
else
|
|
|
|
|
id++;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
while (id < smap->n_buckets && !smap->buckets[id])
|
|
|
|
|
id++;
|
|
|
|
|
|
|
|
|
|
if (id >= smap->n_buckets)
|
|
|
|
|
return -ENOENT;
|
|
|
|
|
|
|
|
|
|
*(u32 *)next_key = id;
|
|
|
|
|
return 0;
|
2016-02-18 11:58:58 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int stack_map_update_elem(struct bpf_map *map, void *key, void *value,
|
|
|
|
|
u64 map_flags)
|
|
|
|
|
{
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Called from syscall or from eBPF program */
|
|
|
|
|
static int stack_map_delete_elem(struct bpf_map *map, void *key)
|
|
|
|
|
{
|
|
|
|
|
struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
|
|
|
|
|
struct stack_map_bucket *old_bucket;
|
|
|
|
|
u32 id = *(u32 *)key;
|
|
|
|
|
|
|
|
|
|
if (unlikely(id >= smap->n_buckets))
|
|
|
|
|
return -E2BIG;
|
|
|
|
|
|
|
|
|
|
old_bucket = xchg(&smap->buckets[id], NULL);
|
|
|
|
|
if (old_bucket) {
|
2016-03-08 13:57:17 +08:00
|
|
|
pcpu_freelist_push(&smap->freelist, &old_bucket->fnode);
|
2016-02-18 11:58:58 +08:00
|
|
|
return 0;
|
|
|
|
|
} else {
|
|
|
|
|
return -ENOENT;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Called when map->refcnt goes to zero, either from workqueue or from syscall */
|
|
|
|
|
static void stack_map_free(struct bpf_map *map)
|
|
|
|
|
{
|
|
|
|
|
struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
|
|
|
|
|
|
2016-03-08 13:57:17 +08:00
|
|
|
/* wait for bpf programs to complete before freeing stack map */
|
2016-02-18 11:58:58 +08:00
|
|
|
synchronize_rcu();
|
|
|
|
|
|
bpf: don't trigger OOM killer under pressure with map alloc
This patch adds two helpers, bpf_map_area_alloc() and bpf_map_area_free(),
that are to be used for map allocations. Using kmalloc() for very large
allocations can cause excessive work within the page allocator, so i) fall
back earlier to vmalloc() when the attempt is considered costly anyway,
and even more importantly ii) don't trigger OOM killer with any of the
allocators.
Since this is based on a user space request, for example, when creating
maps with element pre-allocation, we really want such requests to fail
instead of killing other user space processes.
Also, don't spam the kernel log with warnings should any of the allocations
fail under pressure. Given that, we can make backend selection in
bpf_map_area_alloc() generic, and convert all maps over to use this API
for spots with potentially large allocation requests.
Note, replacing the one kmalloc_array() is fine as overflow checks happen
earlier in htab_map_alloc(), since it must also protect the multiplication
for vmalloc() should kmalloc_array() fail.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-18 22:14:17 +08:00
|
|
|
bpf_map_area_free(smap->elems);
|
2016-03-08 13:57:17 +08:00
|
|
|
pcpu_freelist_destroy(&smap->freelist);
|
bpf: don't trigger OOM killer under pressure with map alloc
This patch adds two helpers, bpf_map_area_alloc() and bpf_map_area_free(),
that are to be used for map allocations. Using kmalloc() for very large
allocations can cause excessive work within the page allocator, so i) fall
back earlier to vmalloc() when the attempt is considered costly anyway,
and even more importantly ii) don't trigger OOM killer with any of the
allocators.
Since this is based on a user space request, for example, when creating
maps with element pre-allocation, we really want such requests to fail
instead of killing other user space processes.
Also, don't spam the kernel log with warnings should any of the allocations
fail under pressure. Given that, we can make backend selection in
bpf_map_area_alloc() generic, and convert all maps over to use this API
for spots with potentially large allocation requests.
Note, replacing the one kmalloc_array() is fine as overflow checks happen
earlier in htab_map_alloc(), since it must also protect the multiplication
for vmalloc() should kmalloc_array() fail.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-18 22:14:17 +08:00
|
|
|
bpf_map_area_free(smap);
|
2016-02-18 11:58:58 +08:00
|
|
|
put_callchain_buffers();
|
|
|
|
|
}
|
|
|
|
|
|
2017-04-11 21:34:58 +08:00
|
|
|
const struct bpf_map_ops stack_map_ops = {
|
2016-02-18 11:58:58 +08:00
|
|
|
.map_alloc = stack_map_alloc,
|
|
|
|
|
.map_free = stack_map_free,
|
|
|
|
|
.map_get_next_key = stack_map_get_next_key,
|
|
|
|
|
.map_lookup_elem = stack_map_lookup_elem,
|
|
|
|
|
.map_update_elem = stack_map_update_elem,
|
|
|
|
|
.map_delete_elem = stack_map_delete_elem,
|
|
|
|
|
};
|
