UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity
OpenCloudOS-Kernel/kernel/bpf/queue_stack_maps.c

290 lines
6.8 KiB
C
Raw Normal View History

bpf: add queue and stack maps Queue/stack maps implement a FIFO/LIFO data storage for ebpf programs. These maps support peek, pop and push operations that are exposed to eBPF programs through the new bpf_map[peek/pop/push] helpers. Those operations are exposed to userspace applications through the already existing syscalls in the following way: BPF_MAP_LOOKUP_ELEM -> peek BPF_MAP_LOOKUP_AND_DELETE_ELEM -> pop BPF_MAP_UPDATE_ELEM -> push Queue/stack maps are implemented using a buffer, tail and head indexes, hence BPF_F_NO_PREALLOC is not supported. As opposite to other maps, queue and stack do not use RCU for protecting maps values, the bpf_map[peek/pop] have a ARG_PTR_TO_UNINIT_MAP_VALUE argument that is a pointer to a memory zone where to save the value of a map. Basically the same as ARG_PTR_TO_UNINIT_MEM, but the size has not be passed as an extra argument. Our main motivation for implementing queue/stack maps was to keep track of a pool of elements, like network ports in a SNAT, however we forsee other use cases, like for exampling saving last N kernel events in a map and then analysing from userspace. Signed-off-by: Mauricio Vasquez B <mauricio.vasquez@polito.it> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-18 21:16:25 +08:00
// SPDX-License-Identifier: GPL-2.0
/*
* queue_stack_maps.c: BPF queue and stack maps
*
* Copyright (c) 2018 Politecnico di Torino
*/
#include <linux/bpf.h>
#include <linux/list.h>
#include <linux/slab.h>
bpf: fix integer overflow in queue_stack_map Fix the following issues: - allow queue_stack_map for root only - fix u32 max_entries overflow - disallow value_size == 0 Fixes: f1a2e44a3aec ("bpf: add queue and stack maps") Reported-by: Wei Wu <ww9210@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Cc: Mauricio Vasquez B <mauricio.vasquez@polito.it> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-11-23 02:49:56 +08:00
#include <linux/capability.h>
bpf: add queue and stack maps Queue/stack maps implement a FIFO/LIFO data storage for ebpf programs. These maps support peek, pop and push operations that are exposed to eBPF programs through the new bpf_map[peek/pop/push] helpers. Those operations are exposed to userspace applications through the already existing syscalls in the following way: BPF_MAP_LOOKUP_ELEM -> peek BPF_MAP_LOOKUP_AND_DELETE_ELEM -> pop BPF_MAP_UPDATE_ELEM -> push Queue/stack maps are implemented using a buffer, tail and head indexes, hence BPF_F_NO_PREALLOC is not supported. As opposite to other maps, queue and stack do not use RCU for protecting maps values, the bpf_map[peek/pop] have a ARG_PTR_TO_UNINIT_MAP_VALUE argument that is a pointer to a memory zone where to save the value of a map. Basically the same as ARG_PTR_TO_UNINIT_MEM, but the size has not be passed as an extra argument. Our main motivation for implementing queue/stack maps was to keep track of a pool of elements, like network ports in a SNAT, however we forsee other use cases, like for exampling saving last N kernel events in a map and then analysing from userspace. Signed-off-by: Mauricio Vasquez B <mauricio.vasquez@polito.it> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-18 21:16:25 +08:00
#include "percpu_freelist.h"
#define QUEUE_STACK_CREATE_FLAG_MASK \
bpf: add program side {rd, wr}only support for maps This work adds two new map creation flags BPF_F_RDONLY_PROG and BPF_F_WRONLY_PROG in order to allow for read-only or write-only BPF maps from a BPF program side. Today we have BPF_F_RDONLY and BPF_F_WRONLY, but this only applies to system call side, meaning the BPF program has full read/write access to the map as usual while bpf(2) calls with map fd can either only read or write into the map depending on the flags. BPF_F_RDONLY_PROG and BPF_F_WRONLY_PROG allows for the exact opposite such that verifier is going to reject program loads if write into a read-only map or a read into a write-only map is detected. For read-only map case also some helpers are forbidden for programs that would alter the map state such as map deletion, update, etc. As opposed to the two BPF_F_RDONLY / BPF_F_WRONLY flags, BPF_F_RDONLY_PROG as well as BPF_F_WRONLY_PROG really do correspond to the map lifetime. We've enabled this generic map extension to various non-special maps holding normal user data: array, hash, lru, lpm, local storage, queue and stack. Further generic map types could be followed up in future depending on use-case. Main use case here is to forbid writes into .rodata map values from verifier side. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-04-10 05:20:05 +08:00
(BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK)
bpf: add queue and stack maps Queue/stack maps implement a FIFO/LIFO data storage for ebpf programs. These maps support peek, pop and push operations that are exposed to eBPF programs through the new bpf_map[peek/pop/push] helpers. Those operations are exposed to userspace applications through the already existing syscalls in the following way: BPF_MAP_LOOKUP_ELEM -> peek BPF_MAP_LOOKUP_AND_DELETE_ELEM -> pop BPF_MAP_UPDATE_ELEM -> push Queue/stack maps are implemented using a buffer, tail and head indexes, hence BPF_F_NO_PREALLOC is not supported. As opposite to other maps, queue and stack do not use RCU for protecting maps values, the bpf_map[peek/pop] have a ARG_PTR_TO_UNINIT_MAP_VALUE argument that is a pointer to a memory zone where to save the value of a map. Basically the same as ARG_PTR_TO_UNINIT_MEM, but the size has not be passed as an extra argument. Our main motivation for implementing queue/stack maps was to keep track of a pool of elements, like network ports in a SNAT, however we forsee other use cases, like for exampling saving last N kernel events in a map and then analysing from userspace. Signed-off-by: Mauricio Vasquez B <mauricio.vasquez@polito.it> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-18 21:16:25 +08:00
struct bpf_queue_stack {
struct bpf_map map;
raw_spinlock_t lock;
u32 head, tail;
u32 size; /* max_entries + 1 */
char elements[0] __aligned(8);
};
static struct bpf_queue_stack *bpf_queue_stack(struct bpf_map *map)
{
return container_of(map, struct bpf_queue_stack, map);
}
static bool queue_stack_map_is_empty(struct bpf_queue_stack *qs)
{
return qs->head == qs->tail;
}
static bool queue_stack_map_is_full(struct bpf_queue_stack *qs)
{
u32 head = qs->head + 1;
if (unlikely(head >= qs->size))
head = 0;
return head == qs->tail;
}
/* Called from syscall */
static int queue_stack_map_alloc_check(union bpf_attr *attr)
{
bpf: fix integer overflow in queue_stack_map Fix the following issues: - allow queue_stack_map for root only - fix u32 max_entries overflow - disallow value_size == 0 Fixes: f1a2e44a3aec ("bpf: add queue and stack maps") Reported-by: Wei Wu <ww9210@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Cc: Mauricio Vasquez B <mauricio.vasquez@polito.it> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-11-23 02:49:56 +08:00
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
bpf: add queue and stack maps Queue/stack maps implement a FIFO/LIFO data storage for ebpf programs. These maps support peek, pop and push operations that are exposed to eBPF programs through the new bpf_map[peek/pop/push] helpers. Those operations are exposed to userspace applications through the already existing syscalls in the following way: BPF_MAP_LOOKUP_ELEM -> peek BPF_MAP_LOOKUP_AND_DELETE_ELEM -> pop BPF_MAP_UPDATE_ELEM -> push Queue/stack maps are implemented using a buffer, tail and head indexes, hence BPF_F_NO_PREALLOC is not supported. As opposite to other maps, queue and stack do not use RCU for protecting maps values, the bpf_map[peek/pop] have a ARG_PTR_TO_UNINIT_MAP_VALUE argument that is a pointer to a memory zone where to save the value of a map. Basically the same as ARG_PTR_TO_UNINIT_MEM, but the size has not be passed as an extra argument. Our main motivation for implementing queue/stack maps was to keep track of a pool of elements, like network ports in a SNAT, however we forsee other use cases, like for exampling saving last N kernel events in a map and then analysing from userspace. Signed-off-by: Mauricio Vasquez B <mauricio.vasquez@polito.it> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-18 21:16:25 +08:00
/* check sanity of attributes */
if (attr->max_entries == 0 || attr->key_size != 0 ||
bpf: fix integer overflow in queue_stack_map Fix the following issues: - allow queue_stack_map for root only - fix u32 max_entries overflow - disallow value_size == 0 Fixes: f1a2e44a3aec ("bpf: add queue and stack maps") Reported-by: Wei Wu <ww9210@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Cc: Mauricio Vasquez B <mauricio.vasquez@polito.it> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-11-23 02:49:56 +08:00
attr->value_size == 0 ||
bpf: add program side {rd, wr}only support for maps This work adds two new map creation flags BPF_F_RDONLY_PROG and BPF_F_WRONLY_PROG in order to allow for read-only or write-only BPF maps from a BPF program side. Today we have BPF_F_RDONLY and BPF_F_WRONLY, but this only applies to system call side, meaning the BPF program has full read/write access to the map as usual while bpf(2) calls with map fd can either only read or write into the map depending on the flags. BPF_F_RDONLY_PROG and BPF_F_WRONLY_PROG allows for the exact opposite such that verifier is going to reject program loads if write into a read-only map or a read into a write-only map is detected. For read-only map case also some helpers are forbidden for programs that would alter the map state such as map deletion, update, etc. As opposed to the two BPF_F_RDONLY / BPF_F_WRONLY flags, BPF_F_RDONLY_PROG as well as BPF_F_WRONLY_PROG really do correspond to the map lifetime. We've enabled this generic map extension to various non-special maps holding normal user data: array, hash, lru, lpm, local storage, queue and stack. Further generic map types could be followed up in future depending on use-case. Main use case here is to forbid writes into .rodata map values from verifier side. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-04-10 05:20:05 +08:00
attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK ||
!bpf_map_flags_access_ok(attr->map_flags))
bpf: add queue and stack maps Queue/stack maps implement a FIFO/LIFO data storage for ebpf programs. These maps support peek, pop and push operations that are exposed to eBPF programs through the new bpf_map[peek/pop/push] helpers. Those operations are exposed to userspace applications through the already existing syscalls in the following way: BPF_MAP_LOOKUP_ELEM -> peek BPF_MAP_LOOKUP_AND_DELETE_ELEM -> pop BPF_MAP_UPDATE_ELEM -> push Queue/stack maps are implemented using a buffer, tail and head indexes, hence BPF_F_NO_PREALLOC is not supported. As opposite to other maps, queue and stack do not use RCU for protecting maps values, the bpf_map[peek/pop] have a ARG_PTR_TO_UNINIT_MAP_VALUE argument that is a pointer to a memory zone where to save the value of a map. Basically the same as ARG_PTR_TO_UNINIT_MEM, but the size has not be passed as an extra argument. Our main motivation for implementing queue/stack maps was to keep track of a pool of elements, like network ports in a SNAT, however we forsee other use cases, like for exampling saving last N kernel events in a map and then analysing from userspace. Signed-off-by: Mauricio Vasquez B <mauricio.vasquez@polito.it> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-18 21:16:25 +08:00
return -EINVAL;
if (attr->value_size > KMALLOC_MAX_SIZE)
/* if value_size is bigger, the user space won't be able to
* access the elements.
*/
return -E2BIG;
return 0;
}
static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr)
{
int ret, numa_node = bpf_map_attr_numa_node(attr);
bpf: rework memlock-based memory accounting for maps In order to unify the existing memlock charging code with the memcg-based memory accounting, which will be added later, let's rework the current scheme. Currently the following design is used: 1) .alloc() callback optionally checks if the allocation will likely succeed using bpf_map_precharge_memlock() 2) .alloc() performs actual allocations 3) .alloc() callback calculates map cost and sets map.memory.pages 4) map_create() calls bpf_map_init_memlock() which sets map.memory.user and performs actual charging; in case of failure the map is destroyed <map is in use> 1) bpf_map_free_deferred() calls bpf_map_release_memlock(), which performs uncharge and releases the user 2) .map_free() callback releases the memory The scheme can be simplified and made more robust: 1) .alloc() calculates map cost and calls bpf_map_charge_init() 2) bpf_map_charge_init() sets map.memory.user and performs actual charge 3) .alloc() performs actual allocations <map is in use> 1) .map_free() callback releases the memory 2) bpf_map_charge_finish() performs uncharge and releases the user The new scheme also allows to reuse bpf_map_charge_init()/finish() functions for memcg-based accounting. Because charges are performed before actual allocations and uncharges after freeing the memory, no bogus memory pressure can be created. In cases when the map structure is not available (e.g. it's not created yet, or is already destroyed), on-stack bpf_map_memory structure is used. The charge can be transferred with the bpf_map_charge_move() function. Signed-off-by: Roman Gushchin <guro@fb.com> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-05-30 09:03:58 +08:00
struct bpf_map_memory mem = {0};
bpf: add queue and stack maps Queue/stack maps implement a FIFO/LIFO data storage for ebpf programs. These maps support peek, pop and push operations that are exposed to eBPF programs through the new bpf_map[peek/pop/push] helpers. Those operations are exposed to userspace applications through the already existing syscalls in the following way: BPF_MAP_LOOKUP_ELEM -> peek BPF_MAP_LOOKUP_AND_DELETE_ELEM -> pop BPF_MAP_UPDATE_ELEM -> push Queue/stack maps are implemented using a buffer, tail and head indexes, hence BPF_F_NO_PREALLOC is not supported. As opposite to other maps, queue and stack do not use RCU for protecting maps values, the bpf_map[peek/pop] have a ARG_PTR_TO_UNINIT_MAP_VALUE argument that is a pointer to a memory zone where to save the value of a map. Basically the same as ARG_PTR_TO_UNINIT_MEM, but the size has not be passed as an extra argument. Our main motivation for implementing queue/stack maps was to keep track of a pool of elements, like network ports in a SNAT, however we forsee other use cases, like for exampling saving last N kernel events in a map and then analysing from userspace. Signed-off-by: Mauricio Vasquez B <mauricio.vasquez@polito.it> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-18 21:16:25 +08:00
struct bpf_queue_stack *qs;
bpf: fix integer overflow in queue_stack_map Fix the following issues: - allow queue_stack_map for root only - fix u32 max_entries overflow - disallow value_size == 0 Fixes: f1a2e44a3aec ("bpf: add queue and stack maps") Reported-by: Wei Wu <ww9210@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Cc: Mauricio Vasquez B <mauricio.vasquez@polito.it> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-11-23 02:49:56 +08:00
u64 size, queue_size, cost;
bpf: add queue and stack maps Queue/stack maps implement a FIFO/LIFO data storage for ebpf programs. These maps support peek, pop and push operations that are exposed to eBPF programs through the new bpf_map[peek/pop/push] helpers. Those operations are exposed to userspace applications through the already existing syscalls in the following way: BPF_MAP_LOOKUP_ELEM -> peek BPF_MAP_LOOKUP_AND_DELETE_ELEM -> pop BPF_MAP_UPDATE_ELEM -> push Queue/stack maps are implemented using a buffer, tail and head indexes, hence BPF_F_NO_PREALLOC is not supported. As opposite to other maps, queue and stack do not use RCU for protecting maps values, the bpf_map[peek/pop] have a ARG_PTR_TO_UNINIT_MAP_VALUE argument that is a pointer to a memory zone where to save the value of a map. Basically the same as ARG_PTR_TO_UNINIT_MEM, but the size has not be passed as an extra argument. Our main motivation for implementing queue/stack maps was to keep track of a pool of elements, like network ports in a SNAT, however we forsee other use cases, like for exampling saving last N kernel events in a map and then analysing from userspace. Signed-off-by: Mauricio Vasquez B <mauricio.vasquez@polito.it> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-18 21:16:25 +08:00
bpf: fix integer overflow in queue_stack_map Fix the following issues: - allow queue_stack_map for root only - fix u32 max_entries overflow - disallow value_size == 0 Fixes: f1a2e44a3aec ("bpf: add queue and stack maps") Reported-by: Wei Wu <ww9210@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Cc: Mauricio Vasquez B <mauricio.vasquez@polito.it> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-11-23 02:49:56 +08:00
size = (u64) attr->max_entries + 1;
cost = queue_size = sizeof(*qs) + size * attr->value_size;
bpf: add queue and stack maps Queue/stack maps implement a FIFO/LIFO data storage for ebpf programs. These maps support peek, pop and push operations that are exposed to eBPF programs through the new bpf_map[peek/pop/push] helpers. Those operations are exposed to userspace applications through the already existing syscalls in the following way: BPF_MAP_LOOKUP_ELEM -> peek BPF_MAP_LOOKUP_AND_DELETE_ELEM -> pop BPF_MAP_UPDATE_ELEM -> push Queue/stack maps are implemented using a buffer, tail and head indexes, hence BPF_F_NO_PREALLOC is not supported. As opposite to other maps, queue and stack do not use RCU for protecting maps values, the bpf_map[peek/pop] have a ARG_PTR_TO_UNINIT_MAP_VALUE argument that is a pointer to a memory zone where to save the value of a map. Basically the same as ARG_PTR_TO_UNINIT_MEM, but the size has not be passed as an extra argument. Our main motivation for implementing queue/stack maps was to keep track of a pool of elements, like network ports in a SNAT, however we forsee other use cases, like for exampling saving last N kernel events in a map and then analysing from userspace. Signed-off-by: Mauricio Vasquez B <mauricio.vasquez@polito.it> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-18 21:16:25 +08:00
bpf: rework memlock-based memory accounting for maps In order to unify the existing memlock charging code with the memcg-based memory accounting, which will be added later, let's rework the current scheme. Currently the following design is used: 1) .alloc() callback optionally checks if the allocation will likely succeed using bpf_map_precharge_memlock() 2) .alloc() performs actual allocations 3) .alloc() callback calculates map cost and sets map.memory.pages 4) map_create() calls bpf_map_init_memlock() which sets map.memory.user and performs actual charging; in case of failure the map is destroyed <map is in use> 1) bpf_map_free_deferred() calls bpf_map_release_memlock(), which performs uncharge and releases the user 2) .map_free() callback releases the memory The scheme can be simplified and made more robust: 1) .alloc() calculates map cost and calls bpf_map_charge_init() 2) bpf_map_charge_init() sets map.memory.user and performs actual charge 3) .alloc() performs actual allocations <map is in use> 1) .map_free() callback releases the memory 2) bpf_map_charge_finish() performs uncharge and releases the user The new scheme also allows to reuse bpf_map_charge_init()/finish() functions for memcg-based accounting. Because charges are performed before actual allocations and uncharges after freeing the memory, no bogus memory pressure can be created. In cases when the map structure is not available (e.g. it's not created yet, or is already destroyed), on-stack bpf_map_memory structure is used. The charge can be transferred with the bpf_map_charge_move() function. Signed-off-by: Roman Gushchin <guro@fb.com> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-05-30 09:03:58 +08:00
ret = bpf_map_charge_init(&mem, cost);
bpf: add queue and stack maps Queue/stack maps implement a FIFO/LIFO data storage for ebpf programs. These maps support peek, pop and push operations that are exposed to eBPF programs through the new bpf_map[peek/pop/push] helpers. Those operations are exposed to userspace applications through the already existing syscalls in the following way: BPF_MAP_LOOKUP_ELEM -> peek BPF_MAP_LOOKUP_AND_DELETE_ELEM -> pop BPF_MAP_UPDATE_ELEM -> push Queue/stack maps are implemented using a buffer, tail and head indexes, hence BPF_F_NO_PREALLOC is not supported. As opposite to other maps, queue and stack do not use RCU for protecting maps values, the bpf_map[peek/pop] have a ARG_PTR_TO_UNINIT_MAP_VALUE argument that is a pointer to a memory zone where to save the value of a map. Basically the same as ARG_PTR_TO_UNINIT_MEM, but the size has not be passed as an extra argument. Our main motivation for implementing queue/stack maps was to keep track of a pool of elements, like network ports in a SNAT, however we forsee other use cases, like for exampling saving last N kernel events in a map and then analysing from userspace. Signed-off-by: Mauricio Vasquez B <mauricio.vasquez@polito.it> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-18 21:16:25 +08:00
if (ret < 0)
return ERR_PTR(ret);
qs = bpf_map_area_alloc(queue_size, numa_node);
bpf: rework memlock-based memory accounting for maps In order to unify the existing memlock charging code with the memcg-based memory accounting, which will be added later, let's rework the current scheme. Currently the following design is used: 1) .alloc() callback optionally checks if the allocation will likely succeed using bpf_map_precharge_memlock() 2) .alloc() performs actual allocations 3) .alloc() callback calculates map cost and sets map.memory.pages 4) map_create() calls bpf_map_init_memlock() which sets map.memory.user and performs actual charging; in case of failure the map is destroyed <map is in use> 1) bpf_map_free_deferred() calls bpf_map_release_memlock(), which performs uncharge and releases the user 2) .map_free() callback releases the memory The scheme can be simplified and made more robust: 1) .alloc() calculates map cost and calls bpf_map_charge_init() 2) bpf_map_charge_init() sets map.memory.user and performs actual charge 3) .alloc() performs actual allocations <map is in use> 1) .map_free() callback releases the memory 2) bpf_map_charge_finish() performs uncharge and releases the user The new scheme also allows to reuse bpf_map_charge_init()/finish() functions for memcg-based accounting. Because charges are performed before actual allocations and uncharges after freeing the memory, no bogus memory pressure can be created. In cases when the map structure is not available (e.g. it's not created yet, or is already destroyed), on-stack bpf_map_memory structure is used. The charge can be transferred with the bpf_map_charge_move() function. Signed-off-by: Roman Gushchin <guro@fb.com> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-05-30 09:03:58 +08:00
if (!qs) {
bpf_map_charge_finish(&mem);
bpf: add queue and stack maps Queue/stack maps implement a FIFO/LIFO data storage for ebpf programs. These maps support peek, pop and push operations that are exposed to eBPF programs through the new bpf_map[peek/pop/push] helpers. Those operations are exposed to userspace applications through the already existing syscalls in the following way: BPF_MAP_LOOKUP_ELEM -> peek BPF_MAP_LOOKUP_AND_DELETE_ELEM -> pop BPF_MAP_UPDATE_ELEM -> push Queue/stack maps are implemented using a buffer, tail and head indexes, hence BPF_F_NO_PREALLOC is not supported. As opposite to other maps, queue and stack do not use RCU for protecting maps values, the bpf_map[peek/pop] have a ARG_PTR_TO_UNINIT_MAP_VALUE argument that is a pointer to a memory zone where to save the value of a map. Basically the same as ARG_PTR_TO_UNINIT_MEM, but the size has not be passed as an extra argument. Our main motivation for implementing queue/stack maps was to keep track of a pool of elements, like network ports in a SNAT, however we forsee other use cases, like for exampling saving last N kernel events in a map and then analysing from userspace. Signed-off-by: Mauricio Vasquez B <mauricio.vasquez@polito.it> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-18 21:16:25 +08:00
return ERR_PTR(-ENOMEM);
bpf: rework memlock-based memory accounting for maps In order to unify the existing memlock charging code with the memcg-based memory accounting, which will be added later, let's rework the current scheme. Currently the following design is used: 1) .alloc() callback optionally checks if the allocation will likely succeed using bpf_map_precharge_memlock() 2) .alloc() performs actual allocations 3) .alloc() callback calculates map cost and sets map.memory.pages 4) map_create() calls bpf_map_init_memlock() which sets map.memory.user and performs actual charging; in case of failure the map is destroyed <map is in use> 1) bpf_map_free_deferred() calls bpf_map_release_memlock(), which performs uncharge and releases the user 2) .map_free() callback releases the memory The scheme can be simplified and made more robust: 1) .alloc() calculates map cost and calls bpf_map_charge_init() 2) bpf_map_charge_init() sets map.memory.user and performs actual charge 3) .alloc() performs actual allocations <map is in use> 1) .map_free() callback releases the memory 2) bpf_map_charge_finish() performs uncharge and releases the user The new scheme also allows to reuse bpf_map_charge_init()/finish() functions for memcg-based accounting. Because charges are performed before actual allocations and uncharges after freeing the memory, no bogus memory pressure can be created. In cases when the map structure is not available (e.g. it's not created yet, or is already destroyed), on-stack bpf_map_memory structure is used. The charge can be transferred with the bpf_map_charge_move() function. Signed-off-by: Roman Gushchin <guro@fb.com> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-05-30 09:03:58 +08:00
}
bpf: add queue and stack maps Queue/stack maps implement a FIFO/LIFO data storage for ebpf programs. These maps support peek, pop and push operations that are exposed to eBPF programs through the new bpf_map[peek/pop/push] helpers. Those operations are exposed to userspace applications through the already existing syscalls in the following way: BPF_MAP_LOOKUP_ELEM -> peek BPF_MAP_LOOKUP_AND_DELETE_ELEM -> pop BPF_MAP_UPDATE_ELEM -> push Queue/stack maps are implemented using a buffer, tail and head indexes, hence BPF_F_NO_PREALLOC is not supported. As opposite to other maps, queue and stack do not use RCU for protecting maps values, the bpf_map[peek/pop] have a ARG_PTR_TO_UNINIT_MAP_VALUE argument that is a pointer to a memory zone where to save the value of a map. Basically the same as ARG_PTR_TO_UNINIT_MEM, but the size has not be passed as an extra argument. Our main motivation for implementing queue/stack maps was to keep track of a pool of elements, like network ports in a SNAT, however we forsee other use cases, like for exampling saving last N kernel events in a map and then analysing from userspace. Signed-off-by: Mauricio Vasquez B <mauricio.vasquez@polito.it> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-18 21:16:25 +08:00
memset(qs, 0, sizeof(*qs));
bpf_map_init_from_attr(&qs->map, attr);
bpf: rework memlock-based memory accounting for maps In order to unify the existing memlock charging code with the memcg-based memory accounting, which will be added later, let's rework the current scheme. Currently the following design is used: 1) .alloc() callback optionally checks if the allocation will likely succeed using bpf_map_precharge_memlock() 2) .alloc() performs actual allocations 3) .alloc() callback calculates map cost and sets map.memory.pages 4) map_create() calls bpf_map_init_memlock() which sets map.memory.user and performs actual charging; in case of failure the map is destroyed <map is in use> 1) bpf_map_free_deferred() calls bpf_map_release_memlock(), which performs uncharge and releases the user 2) .map_free() callback releases the memory The scheme can be simplified and made more robust: 1) .alloc() calculates map cost and calls bpf_map_charge_init() 2) bpf_map_charge_init() sets map.memory.user and performs actual charge 3) .alloc() performs actual allocations <map is in use> 1) .map_free() callback releases the memory 2) bpf_map_charge_finish() performs uncharge and releases the user The new scheme also allows to reuse bpf_map_charge_init()/finish() functions for memcg-based accounting. Because charges are performed before actual allocations and uncharges after freeing the memory, no bogus memory pressure can be created. In cases when the map structure is not available (e.g. it's not created yet, or is already destroyed), on-stack bpf_map_memory structure is used. The charge can be transferred with the bpf_map_charge_move() function. Signed-off-by: Roman Gushchin <guro@fb.com> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-05-30 09:03:58 +08:00
bpf_map_charge_move(&qs->map.memory, &mem);
bpf: add queue and stack maps Queue/stack maps implement a FIFO/LIFO data storage for ebpf programs. These maps support peek, pop and push operations that are exposed to eBPF programs through the new bpf_map[peek/pop/push] helpers. Those operations are exposed to userspace applications through the already existing syscalls in the following way: BPF_MAP_LOOKUP_ELEM -> peek BPF_MAP_LOOKUP_AND_DELETE_ELEM -> pop BPF_MAP_UPDATE_ELEM -> push Queue/stack maps are implemented using a buffer, tail and head indexes, hence BPF_F_NO_PREALLOC is not supported. As opposite to other maps, queue and stack do not use RCU for protecting maps values, the bpf_map[peek/pop] have a ARG_PTR_TO_UNINIT_MAP_VALUE argument that is a pointer to a memory zone where to save the value of a map. Basically the same as ARG_PTR_TO_UNINIT_MEM, but the size has not be passed as an extra argument. Our main motivation for implementing queue/stack maps was to keep track of a pool of elements, like network ports in a SNAT, however we forsee other use cases, like for exampling saving last N kernel events in a map and then analysing from userspace. Signed-off-by: Mauricio Vasquez B <mauricio.vasquez@polito.it> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-18 21:16:25 +08:00
qs->size = size;
raw_spin_lock_init(&qs->lock);
return &qs->map;
}
/* Called when map->refcnt goes to zero, either from workqueue or from syscall */
static void queue_stack_map_free(struct bpf_map *map)
{
struct bpf_queue_stack *qs = bpf_queue_stack(map);
/* at this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
* so the programs (can be more than one that used this map) were
* disconnected from events. Wait for outstanding critical sections in
* these programs to complete
*/
synchronize_rcu();
bpf_map_area_free(qs);
}
static int __queue_map_get(struct bpf_map *map, void *value, bool delete)
{
struct bpf_queue_stack *qs = bpf_queue_stack(map);
unsigned long flags;
int err = 0;
void *ptr;
raw_spin_lock_irqsave(&qs->lock, flags);
if (queue_stack_map_is_empty(qs)) {
bpf: fix leaking uninitialized memory on pop/peek helpers Commit f1a2e44a3aec ("bpf: add queue and stack maps") added helpers with ARG_PTR_TO_UNINIT_MAP_VALUE. Meaning, the helper is supposed to fill the map value buffer with data instead of reading from it like in other helpers such as map update. However, given the buffer is allowed to be uninitialized (since we fill it in the helper anyway), it also means that the helper is obliged to wipe the memory in case of an error in order to not allow for leaking uninitialized memory. Given pop/peek is both handled inside __{stack,queue}_map_get(), lets wipe it there on error case, that is, empty stack/queue. Fixes: f1a2e44a3aec ("bpf: add queue and stack maps") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Cc: Mauricio Vasquez B <mauricio.vasquez@polito.it> Acked-by: Mauricio Vasquez B<mauricio.vasquez@polito.it> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-25 04:05:48 +08:00
memset(value, 0, qs->map.value_size);
bpf: add queue and stack maps Queue/stack maps implement a FIFO/LIFO data storage for ebpf programs. These maps support peek, pop and push operations that are exposed to eBPF programs through the new bpf_map[peek/pop/push] helpers. Those operations are exposed to userspace applications through the already existing syscalls in the following way: BPF_MAP_LOOKUP_ELEM -> peek BPF_MAP_LOOKUP_AND_DELETE_ELEM -> pop BPF_MAP_UPDATE_ELEM -> push Queue/stack maps are implemented using a buffer, tail and head indexes, hence BPF_F_NO_PREALLOC is not supported. As opposite to other maps, queue and stack do not use RCU for protecting maps values, the bpf_map[peek/pop] have a ARG_PTR_TO_UNINIT_MAP_VALUE argument that is a pointer to a memory zone where to save the value of a map. Basically the same as ARG_PTR_TO_UNINIT_MEM, but the size has not be passed as an extra argument. Our main motivation for implementing queue/stack maps was to keep track of a pool of elements, like network ports in a SNAT, however we forsee other use cases, like for exampling saving last N kernel events in a map and then analysing from userspace. Signed-off-by: Mauricio Vasquez B <mauricio.vasquez@polito.it> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-18 21:16:25 +08:00
err = -ENOENT;
goto out;
}
ptr = &qs->elements[qs->tail * qs->map.value_size];
memcpy(value, ptr, qs->map.value_size);
if (delete) {
if (unlikely(++qs->tail >= qs->size))
qs->tail = 0;
}
out:
raw_spin_unlock_irqrestore(&qs->lock, flags);
return err;
}
static int __stack_map_get(struct bpf_map *map, void *value, bool delete)
{
struct bpf_queue_stack *qs = bpf_queue_stack(map);
unsigned long flags;
int err = 0;
void *ptr;
u32 index;
raw_spin_lock_irqsave(&qs->lock, flags);
if (queue_stack_map_is_empty(qs)) {
bpf: fix leaking uninitialized memory on pop/peek helpers Commit f1a2e44a3aec ("bpf: add queue and stack maps") added helpers with ARG_PTR_TO_UNINIT_MAP_VALUE. Meaning, the helper is supposed to fill the map value buffer with data instead of reading from it like in other helpers such as map update. However, given the buffer is allowed to be uninitialized (since we fill it in the helper anyway), it also means that the helper is obliged to wipe the memory in case of an error in order to not allow for leaking uninitialized memory. Given pop/peek is both handled inside __{stack,queue}_map_get(), lets wipe it there on error case, that is, empty stack/queue. Fixes: f1a2e44a3aec ("bpf: add queue and stack maps") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Cc: Mauricio Vasquez B <mauricio.vasquez@polito.it> Acked-by: Mauricio Vasquez B<mauricio.vasquez@polito.it> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-25 04:05:48 +08:00
memset(value, 0, qs->map.value_size);
bpf: add queue and stack maps Queue/stack maps implement a FIFO/LIFO data storage for ebpf programs. These maps support peek, pop and push operations that are exposed to eBPF programs through the new bpf_map[peek/pop/push] helpers. Those operations are exposed to userspace applications through the already existing syscalls in the following way: BPF_MAP_LOOKUP_ELEM -> peek BPF_MAP_LOOKUP_AND_DELETE_ELEM -> pop BPF_MAP_UPDATE_ELEM -> push Queue/stack maps are implemented using a buffer, tail and head indexes, hence BPF_F_NO_PREALLOC is not supported. As opposite to other maps, queue and stack do not use RCU for protecting maps values, the bpf_map[peek/pop] have a ARG_PTR_TO_UNINIT_MAP_VALUE argument that is a pointer to a memory zone where to save the value of a map. Basically the same as ARG_PTR_TO_UNINIT_MEM, but the size has not be passed as an extra argument. Our main motivation for implementing queue/stack maps was to keep track of a pool of elements, like network ports in a SNAT, however we forsee other use cases, like for exampling saving last N kernel events in a map and then analysing from userspace. Signed-off-by: Mauricio Vasquez B <mauricio.vasquez@polito.it> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-18 21:16:25 +08:00
err = -ENOENT;
goto out;
}
index = qs->head - 1;
if (unlikely(index >= qs->size))
index = qs->size - 1;
ptr = &qs->elements[index * qs->map.value_size];
memcpy(value, ptr, qs->map.value_size);
if (delete)
qs->head = index;
out:
raw_spin_unlock_irqrestore(&qs->lock, flags);
return err;
}
/* Called from syscall or from eBPF program */
static int queue_map_peek_elem(struct bpf_map *map, void *value)
{
return __queue_map_get(map, value, false);
}
/* Called from syscall or from eBPF program */
static int stack_map_peek_elem(struct bpf_map *map, void *value)
{
return __stack_map_get(map, value, false);
}
/* Called from syscall or from eBPF program */
static int queue_map_pop_elem(struct bpf_map *map, void *value)
{
return __queue_map_get(map, value, true);
}
/* Called from syscall or from eBPF program */
static int stack_map_pop_elem(struct bpf_map *map, void *value)
{
return __stack_map_get(map, value, true);
}
/* Called from syscall or from eBPF program */
static int queue_stack_map_push_elem(struct bpf_map *map, void *value,
u64 flags)
{
struct bpf_queue_stack *qs = bpf_queue_stack(map);
unsigned long irq_flags;
int err = 0;
void *dst;
/* BPF_EXIST is used to force making room for a new element in case the
* map is full
*/
bool replace = (flags & BPF_EXIST);
/* Check supported flags for queue and stack maps */
if (flags & BPF_NOEXIST || flags > BPF_EXIST)
return -EINVAL;
raw_spin_lock_irqsave(&qs->lock, irq_flags);
if (queue_stack_map_is_full(qs)) {
if (!replace) {
err = -E2BIG;
goto out;
}
/* advance tail pointer to overwrite oldest element */
if (unlikely(++qs->tail >= qs->size))
qs->tail = 0;
}
dst = &qs->elements[qs->head * qs->map.value_size];
memcpy(dst, value, qs->map.value_size);
if (unlikely(++qs->head >= qs->size))
qs->head = 0;
out:
raw_spin_unlock_irqrestore(&qs->lock, irq_flags);
return err;
}
/* Called from syscall or from eBPF program */
static void *queue_stack_map_lookup_elem(struct bpf_map *map, void *key)
{
return NULL;
}
/* Called from syscall or from eBPF program */
static int queue_stack_map_update_elem(struct bpf_map *map, void *key,
void *value, u64 flags)
{
return -EINVAL;
}
/* Called from syscall or from eBPF program */
static int queue_stack_map_delete_elem(struct bpf_map *map, void *key)
{
return -EINVAL;
}
/* Called from syscall */
static int queue_stack_map_get_next_key(struct bpf_map *map, void *key,
void *next_key)
{
return -EINVAL;
}
const struct bpf_map_ops queue_map_ops = {
.map_alloc_check = queue_stack_map_alloc_check,
.map_alloc = queue_stack_map_alloc,
.map_free = queue_stack_map_free,
.map_lookup_elem = queue_stack_map_lookup_elem,
.map_update_elem = queue_stack_map_update_elem,
.map_delete_elem = queue_stack_map_delete_elem,
.map_push_elem = queue_stack_map_push_elem,
.map_pop_elem = queue_map_pop_elem,
.map_peek_elem = queue_map_peek_elem,
.map_get_next_key = queue_stack_map_get_next_key,
};
const struct bpf_map_ops stack_map_ops = {
.map_alloc_check = queue_stack_map_alloc_check,
.map_alloc = queue_stack_map_alloc,
.map_free = queue_stack_map_free,
.map_lookup_elem = queue_stack_map_lookup_elem,
.map_update_elem = queue_stack_map_update_elem,
.map_delete_elem = queue_stack_map_delete_elem,
.map_push_elem = queue_stack_map_push_elem,
.map_pop_elem = stack_map_pop_elem,
.map_peek_elem = stack_map_peek_elem,
.map_get_next_key = queue_stack_map_get_next_key,
};