summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2021-07-01 01:51:09 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2021-07-01 01:51:09 +0300
commitdbe69e43372212527abf48609aba7fc39a6daa27 (patch)
tree96cfafdf70f5325ceeac1054daf7deca339c9730 /kernel
parenta6eaf3850cb171c328a8b0db6d3c79286a1eba9d (diff)
parentb6df00789e2831fff7a2c65aa7164b2a4dcbe599 (diff)
downloadlinux-dbe69e43372212527abf48609aba7fc39a6daa27.tar.xz
Merge tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski: "Core: - BPF: - add syscall program type and libbpf support for generating instructions and bindings for in-kernel BPF loaders (BPF loaders for BPF), this is a stepping stone for signed BPF programs - infrastructure to migrate TCP child sockets from one listener to another in the same reuseport group/map to improve flexibility of service hand-off/restart - add broadcast support to XDP redirect - allow bypass of the lockless qdisc to improving performance (for pktgen: +23% with one thread, +44% with 2 threads) - add a simpler version of "DO_ONCE()" which does not require jump labels, intended for slow-path usage - virtio/vsock: introduce SOCK_SEQPACKET support - add getsocketopt to retrieve netns cookie - ip: treat lowest address of a IPv4 subnet as ordinary unicast address allowing reclaiming of precious IPv4 addresses - ipv6: use prandom_u32() for ID generation - ip: add support for more flexible field selection for hashing across multi-path routes (w/ offload to mlxsw) - icmp: add support for extended RFC 8335 PROBE (ping) - seg6: add support for SRv6 End.DT46 behavior - mptcp: - DSS checksum support (RFC 8684) to detect middlebox meddling - support Connection-time 'C' flag - time stamping support - sctp: packetization Layer Path MTU Discovery (RFC 8899) - xfrm: speed up state addition with seq set - WiFi: - hidden AP discovery on 6 GHz and other HE 6 GHz improvements - aggregation handling improvements for some drivers - minstrel improvements for no-ack frames - deferred rate control for TXQs to improve reaction times - switch from round robin to virtual time-based airtime scheduler - add trace points: - tcp checksum errors - openvswitch - action execution, upcalls - socket errors via sk_error_report Device APIs: - devlink: add rate API for hierarchical control of max egress rate of virtual devices (VFs, SFs etc.) - don't require RCU read lock to be held around BPF hooks in NAPI context - page_pool: generic buffer recycling New hardware/drivers: - mobile: - iosm: PCIe Driver for Intel M.2 Modem - support for Qualcomm MSM8998 (ipa) - WiFi: Qualcomm QCN9074 and WCN6855 PCI devices - sparx5: Microchip SparX-5 family of Enterprise Ethernet switches - Mellanox BlueField Gigabit Ethernet (control NIC of the DPU) - NXP SJA1110 Automotive Ethernet 10-port switch - Qualcomm QCA8327 switch support (qca8k) - Mikrotik 10/25G NIC (atl1c) Driver changes: - ACPI support for some MDIO, MAC and PHY devices from Marvell and NXP (our first foray into MAC/PHY description via ACPI) - HW timestamping (PTP) support: bnxt_en, ice, sja1105, hns3, tja11xx - Mellanox/Nvidia NIC (mlx5) - NIC VF offload of L2 bridging - support IRQ distribution to Sub-functions - Marvell (prestera): - add flower and match all - devlink trap - link aggregation - Netronome (nfp): connection tracking offload - Intel 1GE (igc): add AF_XDP support - Marvell DPU (octeontx2): ingress ratelimit offload - Google vNIC (gve): new ring/descriptor format support - Qualcomm mobile (rmnet & ipa): inline checksum offload support - MediaTek WiFi (mt76) - mt7915 MSI support - mt7915 Tx status reporting - mt7915 thermal sensors support - mt7921 decapsulation offload - mt7921 enable runtime pm and deep sleep - Realtek WiFi (rtw88) - beacon filter support - Tx antenna path diversity support - firmware crash information via devcoredump - Qualcomm WiFi (wcn36xx) - Wake-on-WLAN support with magic packets and GTK rekeying - Micrel PHY (ksz886x/ksz8081): add cable test support" * tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2168 commits) tcp: change ICSK_CA_PRIV_SIZE definition tcp_yeah: check struct yeah size at compile time gve: DQO: Fix off by one in gve_rx_dqo() stmmac: intel: set PCI_D3hot in suspend stmmac: intel: Enable PHY WOL option in EHL net: stmmac: option to enable PHY WOL with PMT enabled net: say "local" instead of "static" addresses in ndo_dflt_fdb_{add,del} net: use netdev_info in ndo_dflt_fdb_{add,del} ptp: Set lookup cookie when creating a PTP PPS source. net: sock: add trace for socket errors net: sock: introduce sk_error_report net: dsa: replay the local bridge FDB entries pointing to the bridge dev too net: dsa: ensure during dsa_fdb_offload_notify that dev_hold and dev_put are on the same dev net: dsa: include fdb entries pointing to bridge in the host fdb list net: dsa: include bridge addresses which are local in the host fdb list net: dsa: sync static FDB entries on foreign interfaces to hardware net: dsa: install the host MDB and FDB entries in the master's RX filter net: dsa: reference count the FDB addresses at the cross-chip notifier level net: dsa: introduce a separate cross-chip notifier type for host FDBs net: dsa: reference count the MDB entries at the cross-chip notifier level ...
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/bpf_inode_storage.c2
-rw-r--r--kernel/bpf/bpf_iter.c13
-rw-r--r--kernel/bpf/bpf_lsm.c2
-rw-r--r--kernel/bpf/btf.c76
-rw-r--r--kernel/bpf/core.c61
-rw-r--r--kernel/bpf/cpumap.c16
-rw-r--r--kernel/bpf/devmap.c358
-rw-r--r--kernel/bpf/hashtab.c123
-rw-r--r--kernel/bpf/helpers.c6
-rw-r--r--kernel/bpf/inode.c2
-rw-r--r--kernel/bpf/lpm_trie.c6
-rw-r--r--kernel/bpf/preload/iterators/iterators.bpf.c1
-rw-r--r--kernel/bpf/reuseport_array.c2
-rw-r--r--kernel/bpf/ringbuf.c2
-rw-r--r--kernel/bpf/syscall.c241
-rw-r--r--kernel/bpf/tnum.c41
-rw-r--r--kernel/bpf/trampoline.c2
-rw-r--r--kernel/bpf/verifier.c363
-rw-r--r--kernel/trace/bpf_trace.c2
-rw-r--r--kernel/trace/trace.h13
20 files changed, 950 insertions, 382 deletions
diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c
index 2921ca39a93e..96ceed0e0fb5 100644
--- a/kernel/bpf/bpf_inode_storage.c
+++ b/kernel/bpf/bpf_inode_storage.c
@@ -72,7 +72,7 @@ void bpf_inode_storage_free(struct inode *inode)
return;
}
- /* Netiher the bpf_prog nor the bpf-map's syscall
+ /* Neither the bpf_prog nor the bpf-map's syscall
* could be modifying the local_storage->list now.
* Thus, no elem can be added-to or deleted-from the
* local_storage->list by the bpf_prog or by the bpf-map's syscall.
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index 931870f9cf56..2d4fbdbb194e 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -473,15 +473,16 @@ bool bpf_link_is_iter(struct bpf_link *link)
return link->ops == &bpf_iter_link_lops;
}
-int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr,
+ struct bpf_prog *prog)
{
- union bpf_iter_link_info __user *ulinfo;
struct bpf_link_primer link_primer;
struct bpf_iter_target_info *tinfo;
union bpf_iter_link_info linfo;
struct bpf_iter_link *link;
u32 prog_btf_id, linfo_len;
bool existed = false;
+ bpfptr_t ulinfo;
int err;
if (attr->link_create.target_fd || attr->link_create.flags)
@@ -489,18 +490,18 @@ int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
memset(&linfo, 0, sizeof(union bpf_iter_link_info));
- ulinfo = u64_to_user_ptr(attr->link_create.iter_info);
+ ulinfo = make_bpfptr(attr->link_create.iter_info, uattr.is_kernel);
linfo_len = attr->link_create.iter_info_len;
- if (!ulinfo ^ !linfo_len)
+ if (bpfptr_is_null(ulinfo) ^ !linfo_len)
return -EINVAL;
- if (ulinfo) {
+ if (!bpfptr_is_null(ulinfo)) {
err = bpf_check_uarg_tail_zero(ulinfo, sizeof(linfo),
linfo_len);
if (err)
return err;
linfo_len = min_t(u32, linfo_len, sizeof(linfo));
- if (copy_from_user(&linfo, ulinfo, linfo_len))
+ if (copy_from_bpfptr(&linfo, ulinfo, linfo_len))
return -EFAULT;
}
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index da471bf01b97..06062370c3b8 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -127,7 +127,7 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
}
/* The set of hooks which are called without pagefaults disabled and are allowed
- * to "sleep" and thus can be used for sleeable BPF programs.
+ * to "sleep" and thus can be used for sleepable BPF programs.
*/
BTF_SET_START(sleepable_lsm_hooks)
BTF_ID(func, bpf_lsm_bpf)
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index f982a9f0dbc4..cb4b72997d9b 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -51,7 +51,7 @@
* The BTF type section contains a list of 'struct btf_type' objects.
* Each one describes a C type. Recall from the above section
* that a 'struct btf_type' object could be immediately followed by extra
- * data in order to desribe some particular C types.
+ * data in order to describe some particular C types.
*
* type_id:
* ~~~~~~~
@@ -1143,7 +1143,7 @@ static void *btf_show_obj_safe(struct btf_show *show,
/*
* We need a new copy to our safe object, either because we haven't
- * yet copied and are intializing safe data, or because the data
+ * yet copied and are initializing safe data, or because the data
* we want falls outside the boundaries of the safe object.
*/
if (!safe) {
@@ -3417,7 +3417,7 @@ static struct btf_kind_operations func_proto_ops = {
* BTF_KIND_FUNC_PROTO cannot be directly referred by
* a struct's member.
*
- * It should be a funciton pointer instead.
+ * It should be a function pointer instead.
* (i.e. struct's member -> BTF_KIND_PTR -> BTF_KIND_FUNC_PROTO)
*
* Hence, there is no btf_func_check_member().
@@ -4257,7 +4257,7 @@ static int btf_parse_hdr(struct btf_verifier_env *env)
return 0;
}
-static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size,
+static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size,
u32 log_level, char __user *log_ubuf, u32 log_size)
{
struct btf_verifier_env *env = NULL;
@@ -4306,7 +4306,7 @@ static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size,
btf->data = data;
btf->data_size = btf_data_size;
- if (copy_from_user(data, btf_data, btf_data_size)) {
+ if (copy_from_bpfptr(data, btf_data, btf_data_size)) {
err = -EFAULT;
goto errout;
}
@@ -5792,12 +5792,12 @@ static int __btf_new_fd(struct btf *btf)
return anon_inode_getfd("btf", &btf_fops, btf, O_RDONLY | O_CLOEXEC);
}
-int btf_new_fd(const union bpf_attr *attr)
+int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr)
{
struct btf *btf;
int ret;
- btf = btf_parse(u64_to_user_ptr(attr->btf),
+ btf = btf_parse(make_bpfptr(attr->btf, uattr.is_kernel),
attr->btf_size, attr->btf_log_level,
u64_to_user_ptr(attr->btf_log_buf),
attr->btf_log_size);
@@ -6097,3 +6097,65 @@ struct module *btf_try_get_module(const struct btf *btf)
return res;
}
+
+BPF_CALL_4(bpf_btf_find_by_name_kind, char *, name, int, name_sz, u32, kind, int, flags)
+{
+ struct btf *btf;
+ long ret;
+
+ if (flags)
+ return -EINVAL;
+
+ if (name_sz <= 1 || name[name_sz - 1])
+ return -EINVAL;
+
+ btf = bpf_get_btf_vmlinux();
+ if (IS_ERR(btf))
+ return PTR_ERR(btf);
+
+ ret = btf_find_by_name_kind(btf, name, kind);
+ /* ret is never zero, since btf_find_by_name_kind returns
+ * positive btf_id or negative error.
+ */
+ if (ret < 0) {
+ struct btf *mod_btf;
+ int id;
+
+ /* If name is not found in vmlinux's BTF then search in module's BTFs */
+ spin_lock_bh(&btf_idr_lock);
+ idr_for_each_entry(&btf_idr, mod_btf, id) {
+ if (!btf_is_module(mod_btf))
+ continue;
+ /* linear search could be slow hence unlock/lock
+ * the IDR to avoiding holding it for too long
+ */
+ btf_get(mod_btf);
+ spin_unlock_bh(&btf_idr_lock);
+ ret = btf_find_by_name_kind(mod_btf, name, kind);
+ if (ret > 0) {
+ int btf_obj_fd;
+
+ btf_obj_fd = __btf_new_fd(mod_btf);
+ if (btf_obj_fd < 0) {
+ btf_put(mod_btf);
+ return btf_obj_fd;
+ }
+ return ret | (((u64)btf_obj_fd) << 32);
+ }
+ spin_lock_bh(&btf_idr_lock);
+ btf_put(mod_btf);
+ }
+ spin_unlock_bh(&btf_idr_lock);
+ }
+ return ret;
+}
+
+const struct bpf_func_proto bpf_btf_find_by_name_kind_proto = {
+ .func = bpf_btf_find_by_name_kind,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_CONST_SIZE,
+ .arg3_type = ARG_ANYTHING,
+ .arg4_type = ARG_ANYTHING,
+};
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 5e31ee9f7512..034ad93a1ad7 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1392,29 +1392,54 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn)
select_insn:
goto *jumptable[insn->code];
- /* ALU */
-#define ALU(OPCODE, OP) \
- ALU64_##OPCODE##_X: \
- DST = DST OP SRC; \
- CONT; \
- ALU_##OPCODE##_X: \
- DST = (u32) DST OP (u32) SRC; \
- CONT; \
- ALU64_##OPCODE##_K: \
- DST = DST OP IMM; \
- CONT; \
- ALU_##OPCODE##_K: \
- DST = (u32) DST OP (u32) IMM; \
+ /* Explicitly mask the register-based shift amounts with 63 or 31
+ * to avoid undefined behavior. Normally this won't affect the
+ * generated code, for example, in case of native 64 bit archs such
+ * as x86-64 or arm64, the compiler is optimizing the AND away for
+ * the interpreter. In case of JITs, each of the JIT backends compiles
+ * the BPF shift operations to machine instructions which produce
+ * implementation-defined results in such a case; the resulting
+ * contents of the register may be arbitrary, but program behaviour
+ * as a whole remains defined. In other words, in case of JIT backends,
+ * the AND must /not/ be added to the emitted LSH/RSH/ARSH translation.
+ */
+ /* ALU (shifts) */
+#define SHT(OPCODE, OP) \
+ ALU64_##OPCODE##_X: \
+ DST = DST OP (SRC & 63); \
+ CONT; \
+ ALU_##OPCODE##_X: \
+ DST = (u32) DST OP ((u32) SRC & 31); \
+ CONT; \
+ ALU64_##OPCODE##_K: \
+ DST = DST OP IMM; \
+ CONT; \
+ ALU_##OPCODE##_K: \
+ DST = (u32) DST OP (u32) IMM; \
+ CONT;
+ /* ALU (rest) */
+#define ALU(OPCODE, OP) \
+ ALU64_##OPCODE##_X: \
+ DST = DST OP SRC; \
+ CONT; \
+ ALU_##OPCODE##_X: \
+ DST = (u32) DST OP (u32) SRC; \
+ CONT; \
+ ALU64_##OPCODE##_K: \
+ DST = DST OP IMM; \
+ CONT; \
+ ALU_##OPCODE##_K: \
+ DST = (u32) DST OP (u32) IMM; \
CONT;
-
ALU(ADD, +)
ALU(SUB, -)
ALU(AND, &)
ALU(OR, |)
- ALU(LSH, <<)
- ALU(RSH, >>)
ALU(XOR, ^)
ALU(MUL, *)
+ SHT(LSH, <<)
+ SHT(RSH, >>)
+#undef SHT
#undef ALU
ALU_NEG:
DST = (u32) -DST;
@@ -1439,13 +1464,13 @@ select_insn:
insn++;
CONT;
ALU_ARSH_X:
- DST = (u64) (u32) (((s32) DST) >> SRC);
+ DST = (u64) (u32) (((s32) DST) >> (SRC & 31));
CONT;
ALU_ARSH_K:
DST = (u64) (u32) (((s32) DST) >> IMM);
CONT;
ALU64_ARSH_X:
- (*(s64 *) &DST) >>= SRC;
+ (*(s64 *) &DST) >>= (SRC & 63);
CONT;
ALU64_ARSH_K:
(*(s64 *) &DST) >>= IMM;
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 5dd3e866599a..480e936c54d0 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -74,7 +74,7 @@ struct bpf_cpu_map_entry {
struct bpf_cpu_map {
struct bpf_map map;
/* Below members specific for map type */
- struct bpf_cpu_map_entry **cpu_map;
+ struct bpf_cpu_map_entry __rcu **cpu_map;
};
static DEFINE_PER_CPU(struct list_head, cpu_map_flush_list);
@@ -469,7 +469,7 @@ static void __cpu_map_entry_replace(struct bpf_cpu_map *cmap,
{
struct bpf_cpu_map_entry *old_rcpu;
- old_rcpu = xchg(&cmap->cpu_map[key_cpu], rcpu);
+ old_rcpu = unrcu_pointer(xchg(&cmap->cpu_map[key_cpu], RCU_INITIALIZER(rcpu)));
if (old_rcpu) {
call_rcu(&old_rcpu->rcu, __cpu_map_entry_free);
INIT_WORK(&old_rcpu->kthread_stop_wq, cpu_map_kthread_stop);
@@ -551,7 +551,7 @@ static void cpu_map_free(struct bpf_map *map)
for (i = 0; i < cmap->map.max_entries; i++) {
struct bpf_cpu_map_entry *rcpu;
- rcpu = READ_ONCE(cmap->cpu_map[i]);
+ rcpu = rcu_dereference_raw(cmap->cpu_map[i]);
if (!rcpu)
continue;
@@ -562,6 +562,10 @@ static void cpu_map_free(struct bpf_map *map)
kfree(cmap);
}
+/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or
+ * by local_bh_disable() (from XDP calls inside NAPI). The
+ * rcu_read_lock_bh_held() below makes lockdep accept both.
+ */
static void *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
{
struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
@@ -570,7 +574,8 @@ static void *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
if (key >= map->max_entries)
return NULL;
- rcpu = READ_ONCE(cmap->cpu_map[key]);
+ rcpu = rcu_dereference_check(cmap->cpu_map[key],
+ rcu_read_lock_bh_held());
return rcpu;
}
@@ -601,7 +606,8 @@ static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
static int cpu_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
{
- return __bpf_xdp_redirect_map(map, ifindex, flags, __cpu_map_lookup_elem);
+ return __bpf_xdp_redirect_map(map, ifindex, flags, 0,
+ __cpu_map_lookup_elem);
}
static int cpu_map_btf_id;
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index aa516472ce46..2546dafd6672 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -57,6 +57,7 @@ struct xdp_dev_bulk_queue {
struct list_head flush_node;
struct net_device *dev;
struct net_device *dev_rx;
+ struct bpf_prog *xdp_prog;
unsigned int count;
};
@@ -72,7 +73,7 @@ struct bpf_dtab_netdev {
struct bpf_dtab {
struct bpf_map map;
- struct bpf_dtab_netdev **netdev_map; /* DEVMAP type only */
+ struct bpf_dtab_netdev __rcu **netdev_map; /* DEVMAP type only */
struct list_head list;
/* these are only used for DEVMAP_HASH type maps */
@@ -92,7 +93,7 @@ static struct hlist_head *dev_map_create_hash(unsigned int entries,
int i;
struct hlist_head *hash;
- hash = bpf_map_area_alloc(entries * sizeof(*hash), numa_node);
+ hash = bpf_map_area_alloc((u64) entries * sizeof(*hash), numa_node);
if (hash != NULL)
for (i = 0; i < entries; i++)
INIT_HLIST_HEAD(&hash[i]);
@@ -143,7 +144,7 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr)
spin_lock_init(&dtab->index_lock);
} else {
- dtab->netdev_map = bpf_map_area_alloc(dtab->map.max_entries *
+ dtab->netdev_map = bpf_map_area_alloc((u64) dtab->map.max_entries *
sizeof(struct bpf_dtab_netdev *),
dtab->map.numa_node);
if (!dtab->netdev_map)
@@ -197,6 +198,7 @@ static void dev_map_free(struct bpf_map *map)
list_del_rcu(&dtab->list);
spin_unlock(&dev_map_lock);
+ bpf_clear_redirect_map(map);
synchronize_rcu();
/* Make sure prior __dev_map_entry_free() have completed. */
@@ -224,7 +226,7 @@ static void dev_map_free(struct bpf_map *map)
for (i = 0; i < dtab->map.max_entries; i++) {
struct bpf_dtab_netdev *dev;
- dev = dtab->netdev_map[i];
+ dev = rcu_dereference_raw(dtab->netdev_map[i]);
if (!dev)
continue;
@@ -257,6 +259,10 @@ static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
return 0;
}
+/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or
+ * by local_bh_disable() (from XDP calls inside NAPI). The
+ * rcu_read_lock_bh_held() below makes lockdep accept both.
+ */
static void *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key)
{
struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
@@ -326,22 +332,69 @@ bool dev_map_can_have_prog(struct bpf_map *map)
return false;
}
+static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog,
+ struct xdp_frame **frames, int n,
+ struct net_device *dev)
+{
+ struct xdp_txq_info txq = { .dev = dev };
+ struct xdp_buff xdp;
+ int i, nframes = 0;
+
+ for (i = 0; i < n; i++) {
+ struct xdp_frame *xdpf = frames[i];
+ u32 act;
+ int err;
+
+ xdp_convert_frame_to_buff(xdpf, &xdp);
+ xdp.txq = &txq;
+
+ act = bpf_prog_run_xdp(xdp_prog, &xdp);
+ switch (act) {
+ case XDP_PASS:
+ err = xdp_update_frame_from_buff(&xdp, xdpf);
+ if (unlikely(err < 0))
+ xdp_return_frame_rx_napi(xdpf);
+ else
+ frames[nframes++] = xdpf;
+ break;
+ default:
+ bpf_warn_invalid_xdp_action(act);
+ fallthrough;
+ case XDP_ABORTED:
+ trace_xdp_exception(dev, xdp_prog, act);
+ fallthrough;
+ case XDP_DROP:
+ xdp_return_frame_rx_napi(xdpf);
+ break;
+ }
+ }
+ return nframes; /* sent frames count */
+}
+
static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags)
{
struct net_device *dev = bq->dev;
+ unsigned int cnt = bq->count;
int sent = 0, err = 0;
+ int to_send = cnt;
int i;
- if (unlikely(!bq->count))
+ if (unlikely(!cnt))
return;
- for (i = 0; i < bq->count; i++) {
+ for (i = 0; i < cnt; i++) {
struct xdp_frame *xdpf = bq->q[i];
prefetch(xdpf);
}
- sent = dev->netdev_ops->ndo_xdp_xmit(dev, bq->count, bq->q, flags);
+ if (bq->xdp_prog) {
+ to_send = dev_map_bpf_prog_run(bq->xdp_prog, bq->q, cnt, dev);
+ if (!to_send)
+ goto out;
+ }
+
+ sent = dev->netdev_ops->ndo_xdp_xmit(dev, to_send, bq->q, flags);
if (sent < 0) {
/* If ndo_xdp_xmit fails with an errno, no frames have
* been xmit'ed.
@@ -353,37 +406,34 @@ static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags)
/* If not all frames have been transmitted, it is our
* responsibility to free them
*/
- for (i = sent; unlikely(i < bq->count); i++)
+ for (i = sent; unlikely(i < to_send); i++)
xdp_return_frame_rx_napi(bq->q[i]);
- trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, bq->count - sent, err);
- bq->dev_rx = NULL;
+out:
bq->count = 0;
- __list_del_clearprev(&bq->flush_node);
-}
-
-/* __dev_flush is called from xdp_do_flush() which _must_ be signaled
- * from the driver before returning from its napi->poll() routine. The poll()
- * routine is called either from busy_poll context or net_rx_action signaled
- * from NET_RX_SOFTIRQ. Either way the poll routine must complete before the
- * net device can be torn down. On devmap tear down we ensure the flush list
- * is empty before completing to ensure all flush operations have completed.
- * When drivers update the bpf program they may need to ensure any flush ops
- * are also complete. Using synchronize_rcu or call_rcu will suffice for this
- * because both wait for napi context to exit.
+ trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, cnt - sent, err);
+}
+
+/* __dev_flush is called from xdp_do_flush() which _must_ be signalled from the
+ * driver before returning from its napi->poll() routine. See the comment above
+ * xdp_do_flush() in filter.c.
*/
void __dev_flush(void)
{
struct list_head *flush_list = this_cpu_ptr(&dev_flush_list);
struct xdp_dev_bulk_queue *bq, *tmp;
- list_for_each_entry_safe(bq, tmp, flush_list, flush_node)
+ list_for_each_entry_safe(bq, tmp, flush_list, flush_node) {
bq_xmit_all(bq, XDP_XMIT_FLUSH);
+ bq->dev_rx = NULL;
+ bq->xdp_prog = NULL;
+ __list_del_clearprev(&bq->flush_node);
+ }
}
-/* rcu_read_lock (from syscall and BPF contexts) ensures that if a delete and/or
- * update happens in parallel here a dev_put wont happen until after reading the
- * ifindex.
+/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or
+ * by local_bh_disable() (from XDP calls inside NAPI). The
+ * rcu_read_lock_bh_held() below makes lockdep accept both.
*/
static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
{
@@ -393,15 +443,17 @@ static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
if (key >= map->max_entries)
return NULL;
- obj = READ_ONCE(dtab->netdev_map[key]);
+ obj = rcu_dereference_check(dtab->netdev_map[key],
+ rcu_read_lock_bh_held());
return obj;
}
-/* Runs under RCU-read-side, plus in softirq under NAPI protection.
- * Thus, safe percpu variable access.
+/* Runs in NAPI, i.e., softirq under local_bh_disable(). Thus, safe percpu
+ * variable access, and map elements stick around. See comment above
+ * xdp_do_flush() in filter.c.
*/
static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
- struct net_device *dev_rx)
+ struct net_device *dev_rx, struct bpf_prog *xdp_prog)
{
struct list_head *flush_list = this_cpu_ptr(&dev_flush_list);
struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq);
@@ -412,18 +464,22 @@ static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
/* Ingress dev_rx will be the same for all xdp_frame's in
* bulk_queue, because bq stored per-CPU and must be flushed
* from net_device drivers NAPI func end.
+ *
+ * Do the same with xdp_prog and flush_list since these fields
+ * are only ever modified together.
*/
- if (!bq->dev_rx)
+ if (!bq->dev_rx) {
bq->dev_rx = dev_rx;
+ bq->xdp_prog = xdp_prog;
+ list_add(&bq->flush_node, flush_list);
+ }
bq->q[bq->count++] = xdpf;
-
- if (!bq->flush_node.prev)
- list_add(&bq->flush_node, flush_list);
}
static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
- struct net_device *dev_rx)
+ struct net_device *dev_rx,
+ struct bpf_prog *xdp_prog)
{
struct xdp_frame *xdpf;
int err;
@@ -439,55 +495,115 @@ static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
if (unlikely(!xdpf))
return -EOVERFLOW;
- bq_enqueue(dev, xdpf, dev_rx);
+ bq_enqueue(dev, xdpf, dev_rx, xdp_prog);
return 0;
}
-static struct xdp_buff *dev_map_run_prog(struct net_device *dev,
- struct xdp_buff *xdp,
- struct bpf_prog *xdp_prog)
+int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
+ struct net_device *dev_rx)
{
- struct xdp_txq_info txq = { .dev = dev };
- u32 act;
+ return __xdp_enqueue(dev, xdp, dev_rx, NULL);
+}
- xdp_set_data_meta_invalid(xdp);
- xdp->txq = &txq;
+int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
+ struct net_device *dev_rx)
+{
+ struct net_device *dev = dst->dev;
- act = bpf_prog_run_xdp(xdp_prog, xdp);
- switch (act) {
- case XDP_PASS:
- return xdp;
- case XDP_DROP:
- break;
- default:
- bpf_warn_invalid_xdp_action(act);
- fallthrough;
- case XDP_ABORTED:
- trace_xdp_exception(dev, xdp_prog, act);
- break;
- }
+ return __xdp_enqueue(dev, xdp, dev_rx, dst->xdp_prog);
+}
- xdp_return_buff(xdp);
- return NULL;
+static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_buff *xdp,
+ int exclude_ifindex)
+{
+ if (!obj || obj->dev->ifindex == exclude_ifindex ||
+ !obj->dev->netdev_ops->ndo_xdp_xmit)
+ return false;
+
+ if (xdp_ok_fwd_dev(obj->dev, xdp->data_end - xdp->data))
+ return false;
+
+ return true;
}
-int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
- struct net_device *dev_rx)
+static int dev_map_enqueue_clone(struct bpf_dtab_netdev *obj,
+ struct net_device *dev_rx,
+ struct xdp_frame *xdpf)
{
- return __xdp_enqueue(dev, xdp, dev_rx);
+ struct xdp_frame *nxdpf;
+
+ nxdpf = xdpf_clone(xdpf);
+ if (!nxdpf)
+ return -ENOMEM;
+
+ bq_enqueue(obj->dev, nxdpf, dev_rx, obj->xdp_prog);
+
+ return 0;
}
-int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
- struct net_device *dev_rx)
+int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx,
+ struct bpf_map *map, bool exclude_ingress)
{
- struct net_device *dev = dst->dev;
+ struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
+ int exclude_ifindex = exclude_ingress ? dev_rx->ifindex : 0;
+ struct bpf_dtab_netdev *dst, *last_dst = NULL;
+ struct hlist_head *head;
+ struct xdp_frame *xdpf;
+ unsigned int i;
+ int err;
- if (dst->xdp_prog) {
- xdp = dev_map_run_prog(dev, xdp, dst->xdp_prog);
- if (!xdp)
- return 0;
+ xdpf = xdp_convert_buff_to_frame(xdp);
+ if (unlikely(!xdpf))
+ return -EOVERFLOW;
+
+ if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
+ for (i = 0; i < map->max_entries; i++) {
+ dst = READ_ONCE(dtab->netdev_map[i]);
+ if (!is_valid_dst(dst, xdp, exclude_ifindex))
+ continue;
+
+ /* we only need n-1 clones; last_dst enqueued below */
+ if (!last_dst) {
+ last_dst = dst;
+ continue;
+ }
+
+ err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf);
+ if (err)
+ return err;
+
+ last_dst = dst;
+ }
+ } else { /* BPF_MAP_TYPE_DEVMAP_HASH */
+ for (i = 0; i < dtab->n_buckets; i++) {
+ head = dev_map_index_hash(dtab, i);
+ hlist_for_each_entry_rcu(dst, head, index_hlist,
+ lockdep_is_held(&dtab->index_lock)) {
+ if (!is_valid_dst(dst, xdp, exclude_ifindex))
+ continue;
+
+ /* we only need n-1 clones; last_dst enqueued below */
+ if (!last_dst) {
+ last_dst = dst;
+ continue;
+ }
+
+ err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf);
+ if (err)
+ return err;
+
+ last_dst = dst;
+ }
+ }
}
- return __xdp_enqueue(dev, xdp, dev_rx);
+
+ /* consume the last copy of the frame */
+ if (last_dst)
+ bq_enqueue(last_dst->dev, xdpf, dev_rx, last_dst->xdp_prog);
+ else
+ xdp_return_frame_rx_napi(xdpf); /* dtab is empty */
+
+ return 0;
}
int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
@@ -504,6 +620,87 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
return 0;
}
+static int dev_map_redirect_clone(struct bpf_dtab_netdev *dst,
+ struct sk_buff *skb,
+ struct bpf_prog *xdp_prog)
+{
+ struct sk_buff *nskb;
+ int err;
+
+ nskb = skb_clone(skb, GFP_ATOMIC);
+ if (!nskb)
+ return -ENOMEM;
+
+ err = dev_map_generic_redirect(dst, nskb, xdp_prog);
+ if (unlikely(err)) {
+ consume_skb(nskb);
+ return err;
+ }
+
+ return 0;
+}
+
+int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb,
+ struct bpf_prog *xdp_prog, struct bpf_map *map,
+ bool exclude_ingress)
+{
+ struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
+ int exclude_ifindex = exclude_ingress ? dev->ifindex : 0;
+ struct bpf_dtab_netdev *dst, *last_dst = NULL;
+ struct hlist_head *head;
+ struct hlist_node *next;
+ unsigned int i;
+ int err;
+
+ if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
+ for (i = 0; i < map->max_entries; i++) {
+ dst = READ_ONCE(dtab->netdev_map[i]);
+ if (!dst || dst->dev->ifindex == exclude_ifindex)
+ continue;
+
+ /* we only need n-1 clones; last_dst enqueued below */
+ if (!last_dst) {
+ last_dst = dst;
+ continue;
+ }
+
+ err = dev_map_redirect_clone(last_dst, skb, xdp_prog);
+ if (err)
+ return err;
+
+ last_dst = dst;
+ }
+ } else { /* BPF_MAP_TYPE_DEVMAP_HASH */
+ for (i = 0; i < dtab->n_buckets; i++) {
+ head = dev_map_index_hash(dtab, i);
+ hlist_for_each_entry_safe(dst, next, head, index_hlist) {
+ if (!dst || dst->dev->ifindex == exclude_ifindex)
+ continue;
+
+ /* we only need n-1 clones; last_dst enqueued below */
+ if (!last_dst) {
+ last_dst = dst;
+ continue;
+ }
+
+ err = dev_map_redirect_clone(last_dst, skb, xdp_prog);
+ if (err)
+ return err;
+
+ last_dst = dst;
+ }
+ }
+ }
+
+ /* consume the first skb and return */
+ if (last_dst)
+ return dev_map_generic_redirect(last_dst, skb, xdp_prog);
+
+ /* dtab is empty */
+ consume_skb(skb);
+ return 0;
+}
+
static void *dev_map_lookup_elem(struct bpf_map *map, void *key)
{
struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key);
@@ -538,14 +735,7 @@ static int dev_map_delete_elem(struct bpf_map *map, void *key)
if (k >= map->max_entries)
return -EINVAL;
- /* Use call_rcu() here to ensure any rcu critical sections have
- * completed as well as any flush operations because call_rcu
- * will wait for preempt-disable region to complete, NAPI in this
- * context. And additionally, the driver tear down ensures all
- * soft irqs are complete before removing the net device in the
- * case of dev_put equals zero.
- */
- old_dev = xchg(&dtab->netdev_map[k], NULL);
+ old_dev = unrcu_pointer(xchg(&dtab->netdev_map[k], NULL));
if (old_dev)
call_rcu(&old_dev->rcu, __dev_map_entry_free);
return 0;
@@ -654,7 +844,7 @@ static int __dev_map_update_elem(struct net *net, struct bpf_map *map,
* Remembering the driver side flush operation will happen before the
* net device is removed.
*/
- old_dev = xchg(&dtab->netdev_map[i], dev);
+ old_dev = unrcu_pointer(xchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev)));
if (old_dev)
call_rcu(&old_dev->rcu, __dev_map_entry_free);
@@ -730,12 +920,16 @@ static int dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value,
static int dev_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
{
- return __bpf_xdp_redirect_map(map, ifindex, flags, __dev_map_lookup_elem);
+ return __bpf_xdp_redirect_map(map, ifindex, flags,
+ BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS,
+ __dev_map_lookup_elem);
}
static int dev_hash_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
{
- return __bpf_xdp_redirect_map(map, ifindex, flags, __dev_map_hash_lookup_elem);
+ return __bpf_xdp_redirect_map(map, ifindex, flags,
+ BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS,
+ __dev_map_hash_lookup_elem);
}
static int dev_map_btf_id;
@@ -830,10 +1024,10 @@ static int dev_map_notification(struct notifier_block *notifier,
for (i = 0; i < dtab->map.max_entries; i++) {
struct bpf_dtab_netdev *dev, *odev;
- dev = READ_ONCE(dtab->netdev_map[i]);
+ dev = rcu_dereference(dtab->netdev_map[i]);
if (!dev || netdev != dev->dev)
continue;
- odev = cmpxchg(&dtab->netdev_map[i], dev, NULL);
+ odev = unrcu_pointer(cmpxchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev), NULL));
if (dev == odev)
call_rcu(&dev->rcu,
__dev_map_entry_free);
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index d7ebb12ffffc..72c58cc516a3 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -46,12 +46,12 @@
* events, kprobes and tracing to be invoked before the prior invocation
* from one of these contexts completed. sys_bpf() uses the same mechanism
* by pinning the task to the current CPU and incrementing the recursion
- * protection accross the map operation.
+ * protection across the map operation.
*
* This has subtle implications on PREEMPT_RT. PREEMPT_RT forbids certain
* operations like memory allocations (even with GFP_ATOMIC) from atomic
* contexts. This is required because even with GFP_ATOMIC the memory
- * allocator calls into code pathes which acquire locks with long held lock
+ * allocator calls into code paths which acquire locks with long held lock
* sections. To ensure the deterministic behaviour these locks are regular
* spinlocks, which are converted to 'sleepable' spinlocks on RT. The only
* true atomic contexts on an RT kernel are the low level hardware
@@ -596,7 +596,8 @@ static void *__htab_map_lookup_elem(struct bpf_map *map, void *key)
struct htab_elem *l;
u32 hash, key_size;
- WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
+ WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+ !rcu_read_lock_bh_held());
key_size = map->key_size;
@@ -989,7 +990,8 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
/* unknown flags */
return -EINVAL;
- WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
+ WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+ !rcu_read_lock_bh_held());
key_size = map->key_size;
@@ -1082,7 +1084,8 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value,
/* unknown flags */
return -EINVAL;
- WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
+ WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+ !rcu_read_lock_bh_held());
key_size = map->key_size;
@@ -1148,7 +1151,8 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
/* unknown flags */
return -EINVAL;
- WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
+ WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+ !rcu_read_lock_bh_held());
key_size = map->key_size;
@@ -1202,7 +1206,8 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
/* unknown flags */
return -EINVAL;
- WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
+ WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+ !rcu_read_lock_bh_held());
key_size = map->key_size;
@@ -1276,7 +1281,8 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key)
u32 hash, key_size;
int ret;
- WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
+ WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+ !rcu_read_lock_bh_held());
key_size = map->key_size;
@@ -1311,7 +1317,8 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key)
u32 hash, key_size;
int ret;
- WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
+ WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+ !rcu_read_lock_bh_held());
key_size = map->key_size;
@@ -1401,6 +1408,100 @@ static void htab_map_seq_show_elem(struct bpf_map *map, void *key,
rcu_read_unlock();
}
+static int __htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key,
+ void *value, bool is_lru_map,
+ bool is_percpu, u64 flags)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ struct hlist_nulls_head *head;
+ unsigned long bflags;
+ struct htab_elem *l;
+ u32 hash, key_size;
+ struct bucket *b;
+ int ret;
+
+ key_size = map->key_size;
+
+ hash = htab_map_hash(key, key_size, htab->hashrnd);
+ b = __select_bucket(htab, hash);
+ head = &b->head;
+
+ ret = htab_lock_bucket(htab, b, hash, &bflags);
+ if (ret)
+ return ret;
+
+ l = lookup_elem_raw(head, hash, key, key_size);
+ if (!l) {
+ ret = -ENOENT;
+ } else {
+ if (is_percpu) {
+ u32 roundup_value_size = round_up(map->value_size, 8);
+ void __percpu *pptr;
+ int off = 0, cpu;
+
+ pptr = htab_elem_get_ptr(l, key_size);
+ for_each_possible_cpu(cpu) {
+ bpf_long_memcpy(value + off,
+ per_cpu_ptr(pptr, cpu),
+ roundup_value_size);
+ off += roundup_value_size;
+ }
+ } else {
+ u32 roundup_key_size = round_up(map->key_size, 8);
+
+ if (flags & BPF_F_LOCK)
+ copy_map_value_locked(map, value, l->key +
+ roundup_key_size,
+ true);
+ else
+ copy_map_value(map, value, l->key +
+ roundup_key_size);
+ check_and_init_map_lock(map, value);
+ }
+
+ hlist_nulls_del_rcu(&l->hash_node);
+ if (!is_lru_map)
+ free_htab_elem(htab, l);
+ }
+
+ htab_unlock_bucket(htab, b, hash, bflags);
+
+ if (is_lru_map && l)
+ bpf_lru_push_free(&htab->lru, &l->lru_node);
+
+ return ret;
+}
+
+static int htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key,
+ void *value, u64 flags)
+{
+ return __htab_map_lookup_and_delete_elem(map, key, value, false, false,
+ flags);
+}
+
+static int htab_percpu_map_lookup_and_delete_elem(struct bpf_map *map,
+ void *key, void *value,
+ u64 flags)
+{
+ return __htab_map_lookup_and_delete_elem(map, key, value, false, true,
+ flags);
+}
+
+static int htab_lru_map_lookup_and_delete_elem(struct bpf_map *map, void *key,
+ void *value, u64 flags)
+{
+ return __htab_map_lookup_and_delete_elem(map, key, value, true, false,
+ flags);
+}
+
+static int htab_lru_percpu_map_lookup_and_delete_elem(struct bpf_map *map,
+ void *key, void *value,
+ u64 flags)
+{
+ return __htab_map_lookup_and_delete_elem(map, key, value, true, true,
+ flags);
+}
+
static int
__htab_map_lookup_and_delete_batch(struct bpf_map *map,
const union bpf_attr *attr,
@@ -1934,6 +2035,7 @@ const struct bpf_map_ops htab_map_ops = {
.map_free = htab_map_free,
.map_get_next_key = htab_map_get_next_key,
.map_lookup_elem = htab_map_lookup_elem,
+ .map_lookup_and_delete_elem = htab_map_lookup_and_delete_elem,
.map_update_elem = htab_map_update_elem,
.map_delete_elem = htab_map_delete_elem,
.map_gen_lookup = htab_map_gen_lookup,
@@ -1954,6 +2056,7 @@ const struct bpf_map_ops htab_lru_map_ops = {
.map_free = htab_map_free,
.map_get_next_key = htab_map_get_next_key,
.map_lookup_elem = htab_lru_map_lookup_elem,
+ .map_lookup_and_delete_elem = htab_lru_map_lookup_and_delete_elem,
.map_lookup_elem_sys_only = htab_lru_map_lookup_elem_sys,
.map_update_elem = htab_lru_map_update_elem,
.map_delete_elem = htab_lru_map_delete_elem,
@@ -2077,6 +2180,7 @@ const struct bpf_map_ops htab_percpu_map_ops = {
.map_free = htab_map_free,
.map_get_next_key = htab_map_get_next_key,
.map_lookup_elem = htab_percpu_map_lookup_elem,
+ .map_lookup_and_delete_elem = htab_percpu_map_lookup_and_delete_elem,
.map_update_elem = htab_percpu_map_update_elem,
.map_delete_elem = htab_map_delete_elem,
.map_seq_show_elem = htab_percpu_map_seq_show_elem,
@@ -2096,6 +2200,7 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = {
.map_free = htab_map_free,
.map_get_next_key = htab_map_get_next_key,
.map_lookup_elem = htab_lru_percpu_map_lookup_elem,
+ .map_lookup_and_delete_elem = htab_lru_percpu_map_lookup_and_delete_elem,
.map_update_elem = htab_lru_percpu_map_update_elem,
.map_delete_elem = htab_lru_map_delete_elem,
.map_seq_show_elem = htab_percpu_map_seq_show_elem,
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index a2f1f15ce432..62cf00383910 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -29,7 +29,7 @@
*/
BPF_CALL_2(bpf_map_lookup_elem, struct bpf_map *, map, void *, key)
{
- WARN_ON_ONCE(!rcu_read_lock_held());
+ WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
return (unsigned long) map->ops->map_lookup_elem(map, key);
}
@@ -45,7 +45,7 @@ const struct bpf_func_proto bpf_map_lookup_elem_proto = {
BPF_CALL_4(bpf_map_update_elem, struct bpf_map *, map, void *, key,
void *, value, u64, flags)
{
- WARN_ON_ONCE(!rcu_read_lock_held());
+ WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
return map->ops->map_update_elem(map, key, value, flags);
}
@@ -62,7 +62,7 @@ const struct bpf_func_proto bpf_map_update_elem_proto = {
BPF_CALL_2(bpf_map_delete_elem, struct bpf_map *, map, void *, key)
{
- WARN_ON_ONCE(!rcu_read_lock_held());
+ WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
return map->ops->map_delete_elem(map, key);
}
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index b4ebd60a6c16..80da1db47c68 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -543,7 +543,7 @@ int bpf_obj_get_user(const char __user *pathname, int flags)
return PTR_ERR(raw);
if (type == BPF_TYPE_PROG)
- ret = (f_flags != O_RDWR) ? -EINVAL : bpf_prog_new_fd(raw);
+ ret = bpf_prog_new_fd(raw);
else if (type == BPF_TYPE_MAP)
ret = bpf_map_new_fd(raw, f_flags);
else if (type == BPF_TYPE_LINK)
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 1b7b8a6f34ee..423549d2c52e 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -232,7 +232,8 @@ static void *trie_lookup_elem(struct bpf_map *map, void *_key)
/* Start walking the trie from the root node ... */
- for (node = rcu_dereference(trie->root); node;) {
+ for (node = rcu_dereference_check(trie->root, rcu_read_lock_bh_held());
+ node;) {
unsigned int next_bit;
size_t matchlen;
@@ -264,7 +265,8 @@ static void *trie_lookup_elem(struct bpf_map *map, void *_key)
* traverse down.
*/
next_bit = extract_bit(key->data, node->prefixlen);
- node = rcu_dereference(node->child[next_bit]);
+ node = rcu_dereference_check(node->child[next_bit],
+ rcu_read_lock_bh_held());
}
if (!found)
diff --git a/kernel/bpf/preload/iterators/iterators.bpf.c b/kernel/bpf/preload/iterators/iterators.bpf.c
index 52aa7b38e8b8..03af863314ea 100644
--- a/kernel/bpf/preload/iterators/iterators.bpf.c
+++ b/kernel/bpf/preload/iterators/iterators.bpf.c
@@ -2,7 +2,6 @@
/* Copyright (c) 2020 Facebook */
#include <linux/bpf.h>
#include <bpf/bpf_helpers.h>
-#include <bpf/bpf_tracing.h>
#include <bpf/bpf_core_read.h>
#pragma clang attribute push (__attribute__((preserve_access_index)), apply_to = record)
diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c
index 4838922f723d..93a55391791a 100644
--- a/kernel/bpf/reuseport_array.c
+++ b/kernel/bpf/reuseport_array.c
@@ -102,7 +102,7 @@ static void reuseport_array_free(struct bpf_map *map)
/*
* ops->map_*_elem() will not be able to access this
* array now. Hence, this function only races with
- * bpf_sk_reuseport_detach() which was triggerred by
+ * bpf_sk_reuseport_detach() which was triggered by
* close() or disconnect().
*
* This function and bpf_sk_reuseport_detach() are
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index 84b3b35fc0d0..9e0c10c6892a 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -8,6 +8,7 @@
#include <linux/vmalloc.h>
#include <linux/wait.h>
#include <linux/poll.h>
+#include <linux/kmemleak.h>
#include <uapi/linux/btf.h>
#define RINGBUF_CREATE_FLAG_MASK (BPF_F_NUMA_NODE)
@@ -105,6 +106,7 @@ static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node)
rb = vmap(pages, nr_meta_pages + 2 * nr_data_pages,
VM_ALLOC | VM_USERMAP, PAGE_KERNEL);
if (rb) {
+ kmemleak_not_leak(pages);
rb->pages = pages;
rb->nr_pages = nr_pages;
return rb;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index ea04b0deb5ce..e343f158e556 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -73,11 +73,10 @@ static const struct bpf_map_ops * const bpf_map_types[] = {
* copy_from_user() call. However, this is not a concern since this function is
* meant to be a future-proofing of bits.
*/
-int bpf_check_uarg_tail_zero(void __user *uaddr,
+int bpf_check_uarg_tail_zero(bpfptr_t uaddr,
size_t expected_size,
size_t actual_size)
{
- unsigned char __user *addr = uaddr + expected_size;
int res;
if (unlikely(actual_size > PAGE_SIZE)) /* silly large */
@@ -86,7 +85,12 @@ int bpf_check_uarg_tail_zero(void __user *uaddr,
if (actual_size <= expected_size)
return 0;
- res = check_zeroed_user(addr, actual_size - expected_size);
+ if (uaddr.is_kernel)
+ res = memchr_inv(uaddr.kernel + expected_size, 0,
+ actual_size - expected_size) == NULL;
+ else
+ res = check_zeroed_user(uaddr.user + expected_size,
+ actual_size - expected_size);
if (res < 0)
return res;
return res ? 0 : -E2BIG;
@@ -1005,6 +1009,17 @@ static void *__bpf_copy_key(void __user *ukey, u64 key_size)
return NULL;
}
+static void *___bpf_copy_key(bpfptr_t ukey, u64 key_size)
+{
+ if (key_size)
+ return memdup_bpfptr(ukey, key_size);
+
+ if (!bpfptr_is_null(ukey))
+ return ERR_PTR(-EINVAL);
+
+ return NULL;
+}
+
/* last field in 'union bpf_attr' used by this command */
#define BPF_MAP_LOOKUP_ELEM_LAST_FIELD flags
@@ -1075,10 +1090,10 @@ err_put:
#define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags
-static int map_update_elem(union bpf_attr *attr)
+static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr)
{
- void __user *ukey = u64_to_user_ptr(attr->key);
- void __user *uvalue = u64_to_user_ptr(attr->value);
+ bpfptr_t ukey = make_bpfptr(attr->key, uattr.is_kernel);
+ bpfptr_t uvalue = make_bpfptr(attr->value, uattr.is_kernel);
int ufd = attr->map_fd;
struct bpf_map *map;
void *key, *value;
@@ -1104,7 +1119,7 @@ static int map_update_elem(union bpf_attr *attr)
goto err_put;
}
- key = __bpf_copy_key(ukey, map->key_size);
+ key = ___bpf_copy_key(ukey, map->key_size);
if (IS_ERR(key)) {
err = PTR_ERR(key);
goto err_put;
@@ -1124,7 +1139,7 @@ static int map_update_elem(union bpf_attr *attr)
goto free_key;
err = -EFAULT;
- if (copy_from_user(value, uvalue, value_size) != 0)
+ if (copy_from_bpfptr(value, uvalue, value_size) != 0)
goto free_value;
err = bpf_map_update_value(map, f, key, value, attr->flags);
@@ -1469,7 +1484,7 @@ free_buf:
return err;
}
-#define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD value
+#define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD flags
static int map_lookup_and_delete_elem(union bpf_attr *attr)
{
@@ -1485,6 +1500,9 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
if (CHECK_ATTR(BPF_MAP_LOOKUP_AND_DELETE_ELEM))
return -EINVAL;
+ if (attr->flags & ~BPF_F_LOCK)
+ return -EINVAL;
+
f = fdget(ufd);
map = __bpf_map_get(f);
if (IS_ERR(map))
@@ -1495,24 +1513,47 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
goto err_put;
}
+ if (attr->flags &&
+ (map->map_type == BPF_MAP_TYPE_QUEUE ||
+ map->map_type == BPF_MAP_TYPE_STACK)) {
+ err = -EINVAL;
+ goto err_put;
+ }
+
+ if ((attr->flags & BPF_F_LOCK) &&
+ !map_value_has_spin_lock(map)) {
+ err = -EINVAL;
+ goto err_put;
+ }
+
key = __bpf_copy_key(ukey, map->key_size);
if (IS_ERR(key)) {
err = PTR_ERR(key);
goto err_put;
}
- value_size = map->value_size;
+ value_size = bpf_map_value_size(map);
err = -ENOMEM;
value = kmalloc(value_size, GFP_USER | __GFP_NOWARN);
if (!value)
goto free_key;
+ err = -ENOTSUPP;
if (map->map_type == BPF_MAP_TYPE_QUEUE ||
map->map_type == BPF_MAP_TYPE_STACK) {
err = map->ops->map_pop_elem(map, value);
- } else {
- err = -ENOTSUPP;
+ } else if (map->map_type == BPF_MAP_TYPE_HASH ||
+ map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+ map->map_type == BPF_MAP_TYPE_LRU_HASH ||
+ map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
+ if (!bpf_map_is_dev_bound(map)) {
+ bpf_disable_instrumentation();
+ rcu_read_lock();
+ err = map->ops->map_lookup_and_delete_elem(map, key, value, attr->flags);
+ rcu_read_unlock();
+ bpf_enable_instrumentation();
+ }
}
if (err)
@@ -1932,6 +1973,11 @@ static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr)
attr->expected_attach_type =
BPF_CGROUP_INET_SOCK_CREATE;
break;
+ case BPF_PROG_TYPE_SK_REUSEPORT:
+ if (!attr->expected_attach_type)
+ attr->expected_attach_type =
+ BPF_SK_REUSEPORT_SELECT;
+ break;
}
}
@@ -2015,6 +2061,15 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
if (expected_attach_type == BPF_SK_LOOKUP)
return 0;
return -EINVAL;
+ case BPF_PROG_TYPE_SK_REUSEPORT:
+ switch (expected_attach_type) {
+ case BPF_SK_REUSEPORT_SELECT:
+ case BPF_SK_REUSEPORT_SELECT_OR_MIGRATE:
+ return 0;
+ default:
+ return -EINVAL;
+ }
+ case BPF_PROG_TYPE_SYSCALL:
case BPF_PROG_TYPE_EXT:
if (expected_attach_type)
return -EINVAL;
@@ -2074,9 +2129,9 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type)
}
/* last field in 'union bpf_attr' used by this command */
-#define BPF_PROG_LOAD_LAST_FIELD attach_prog_fd
+#define BPF_PROG_LOAD_LAST_FIELD fd_array
-static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
+static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr)
{
enum bpf_prog_type type = attr->prog_type;
struct bpf_prog *prog, *dst_prog = NULL;
@@ -2101,8 +2156,9 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
return -EPERM;
/* copy eBPF program license from user space */
- if (strncpy_from_user(license, u64_to_user_ptr(attr->license),
- sizeof(license) - 1) < 0)
+ if (strncpy_from_bpfptr(license,
+ make_bpfptr(attr->license, uattr.is_kernel),
+ sizeof(license) - 1) < 0)
return -EFAULT;
license[sizeof(license) - 1] = 0;
@@ -2186,8 +2242,9 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
prog->len = attr->insn_cnt;
err = -EFAULT;
- if (copy_from_user(prog->insns, u64_to_user_ptr(attr->insns),
- bpf_prog_insn_size(prog)) != 0)
+ if (copy_from_bpfptr(prog->insns,
+ make_bpfptr(attr->insns, uattr.is_kernel),
+ bpf_prog_insn_size(prog)) != 0)
goto free_prog_sec;
prog->orig_prog = NULL;
@@ -3423,7 +3480,7 @@ static int bpf_prog_get_info_by_fd(struct file *file,
u32 ulen;
int err;
- err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len);
+ err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len);
if (err)
return err;
info_len = min_t(u32, sizeof(info), info_len);
@@ -3702,7 +3759,7 @@ static int bpf_map_get_info_by_fd(struct file *file,
u32 info_len = attr->info.info_len;
int err;
- err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len);
+ err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len);
if (err)
return err;
info_len = min_t(u32, sizeof(info), info_len);
@@ -3745,7 +3802,7 @@ static int bpf_btf_get_info_by_fd(struct file *file,
u32 info_len = attr->info.info_len;
int err;
- err = bpf_check_uarg_tail_zero(uinfo, sizeof(*uinfo), info_len);
+ err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(*uinfo), info_len);
if (err)
return err;
@@ -3762,7 +3819,7 @@ static int bpf_link_get_info_by_fd(struct file *file,
u32 info_len = attr->info.info_len;
int err;
- err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len);
+ err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len);
if (err)
return err;
info_len = min_t(u32, sizeof(info), info_len);
@@ -3825,7 +3882,7 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
#define BPF_BTF_LOAD_LAST_FIELD btf_log_level
-static int bpf_btf_load(const union bpf_attr *attr)
+static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr)
{
if (CHECK_ATTR(BPF_BTF_LOAD))
return -EINVAL;
@@ -3833,7 +3890,7 @@ static int bpf_btf_load(const union bpf_attr *attr)
if (!bpf_capable())
return -EPERM;
- return btf_new_fd(attr);
+ return btf_new_fd(attr, uattr);
}
#define BPF_BTF_GET_FD_BY_ID_LAST_FIELD btf_id
@@ -4023,13 +4080,14 @@ err_put:
return err;
}
-static int tracing_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+static int tracing_bpf_link_attach(const union bpf_attr *attr, bpfptr_t uattr,
+ struct bpf_prog *prog)
{
if (attr->link_create.attach_type != prog->expected_attach_type)
return -EINVAL;
if (prog->expected_attach_type == BPF_TRACE_ITER)
- return bpf_iter_link_attach(attr, prog);
+ return bpf_iter_link_attach(attr, uattr, prog);
else if (prog->type == BPF_PROG_TYPE_EXT)
return bpf_tracing_prog_attach(prog,
attr->link_create.target_fd,
@@ -4038,7 +4096,7 @@ static int tracing_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *
}
#define BPF_LINK_CREATE_LAST_FIELD link_create.iter_info_len
-static int link_create(union bpf_attr *attr)
+static int link_create(union bpf_attr *attr, bpfptr_t uattr)
{
enum bpf_prog_type ptype;
struct bpf_prog *prog;
@@ -4057,7 +4115,7 @@ static int link_create(union bpf_attr *attr)
goto out;
if (prog->type == BPF_PROG_TYPE_EXT) {
- ret = tracing_bpf_link_attach(attr, prog);
+ ret = tracing_bpf_link_attach(attr, uattr, prog);
goto out;
}
@@ -4078,7 +4136,7 @@ static int link_create(union bpf_attr *attr)
ret = cgroup_bpf_link_attach(attr, prog);
break;
case BPF_PROG_TYPE_TRACING:
- ret = tracing_bpf_link_attach(attr, prog);
+ ret = tracing_bpf_link_attach(attr, uattr, prog);
break;
case BPF_PROG_TYPE_FLOW_DISSECTOR:
case BPF_PROG_TYPE_SK_LOOKUP:
@@ -4366,7 +4424,7 @@ out_prog_put:
return ret;
}
-SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
+static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size)
{
union bpf_attr attr;
int err;
@@ -4381,7 +4439,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
/* copy attributes from user space, may be less than sizeof(bpf_attr) */
memset(&attr, 0, sizeof(attr));
- if (copy_from_user(&attr, uattr, size) != 0)
+ if (copy_from_bpfptr(&attr, uattr, size) != 0)
return -EFAULT;
err = security_bpf(cmd, &attr, size);
@@ -4396,7 +4454,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
err = map_lookup_elem(&attr);
break;
case BPF_MAP_UPDATE_ELEM:
- err = map_update_elem(&attr);
+ err = map_update_elem(&attr, uattr);
break;
case BPF_MAP_DELETE_ELEM:
err = map_delete_elem(&attr);
@@ -4423,21 +4481,21 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
err = bpf_prog_detach(&attr);
break;
case BPF_PROG_QUERY:
- err = bpf_prog_query(&attr, uattr);
+ err = bpf_prog_query(&attr, uattr.user);
break;
case BPF_PROG_TEST_RUN:
- err = bpf_prog_test_run(&attr, uattr);
+ err = bpf_prog_test_run(&attr, uattr.user);
break;
case BPF_PROG_GET_NEXT_ID:
- err = bpf_obj_get_next_id(&attr, uattr,
+ err = bpf_obj_get_next_id(&attr, uattr.user,
&prog_idr, &prog_idr_lock);
break;
case BPF_MAP_GET_NEXT_ID:
- err = bpf_obj_get_next_id(&attr, uattr,
+ err = bpf_obj_get_next_id(&attr, uattr.user,
&map_idr, &map_idr_lock);
break;
case BPF_BTF_GET_NEXT_ID:
- err = bpf_obj_get_next_id(&attr, uattr,
+ err = bpf_obj_get_next_id(&attr, uattr.user,
&btf_idr, &btf_idr_lock);
break;
case BPF_PROG_GET_FD_BY_ID:
@@ -4447,38 +4505,38 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
err = bpf_map_get_fd_by_id(&attr);
break;
case BPF_OBJ_GET_INFO_BY_FD:
- err = bpf_obj_get_info_by_fd(&attr, uattr);
+ err = bpf_obj_get_info_by_fd(&attr, uattr.user);
break;
case BPF_RAW_TRACEPOINT_OPEN:
err = bpf_raw_tracepoint_open(&attr);
break;
case BPF_BTF_LOAD:
- err = bpf_btf_load(&attr);
+ err = bpf_btf_load(&attr, uattr);
break;
case BPF_BTF_GET_FD_BY_ID:
err = bpf_btf_get_fd_by_id(&attr);
break;
case BPF_TASK_FD_QUERY:
- err = bpf_task_fd_query(&attr, uattr);
+ err = bpf_task_fd_query(&attr, uattr.user);
break;
case BPF_MAP_LOOKUP_AND_DELETE_ELEM:
err = map_lookup_and_delete_elem(&attr);
break;
case BPF_MAP_LOOKUP_BATCH:
- err = bpf_map_do_batch(&attr, uattr, BPF_MAP_LOOKUP_BATCH);
+ err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_LOOKUP_BATCH);
break;
case BPF_MAP_LOOKUP_AND_DELETE_BATCH:
- err = bpf_map_do_batch(&attr, uattr,
+ err = bpf_map_do_batch(&attr, uattr.user,
BPF_MAP_LOOKUP_AND_DELETE_BATCH);
break;
case BPF_MAP_UPDATE_BATCH:
- err = bpf_map_do_batch(&attr, uattr, BPF_MAP_UPDATE_BATCH);
+ err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_UPDATE_BATCH);
break;
case BPF_MAP_DELETE_BATCH:
- err = bpf_map_do_batch(&attr, uattr, BPF_MAP_DELETE_BATCH);
+ err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_DELETE_BATCH);
break;
case BPF_LINK_CREATE:
- err = link_create(&attr);
+ err = link_create(&attr, uattr);
break;
case BPF_LINK_UPDATE:
err = link_update(&attr);
@@ -4487,7 +4545,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
err = bpf_link_get_fd_by_id(&attr);
break;
case BPF_LINK_GET_NEXT_ID:
- err = bpf_obj_get_next_id(&attr, uattr,
+ err = bpf_obj_get_next_id(&attr, uattr.user,
&link_idr, &link_idr_lock);
break;
case BPF_ENABLE_STATS:
@@ -4509,3 +4567,94 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
return err;
}
+
+SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
+{
+ return __sys_bpf(cmd, USER_BPFPTR(uattr), size);
+}
+
+static bool syscall_prog_is_valid_access(int off, int size,
+ enum bpf_access_type type,
+ const struct bpf_prog *prog,
+ struct bpf_insn_access_aux *info)
+{
+ if (off < 0 || off >= U16_MAX)
+ return false;
+ if (off % size != 0)
+ return false;
+ return true;
+}
+
+BPF_CALL_3(bpf_sys_bpf, int, cmd, void *, attr, u32, attr_size)
+{
+ switch (cmd) {
+ case BPF_MAP_CREATE:
+ case BPF_MAP_UPDATE_ELEM:
+ case BPF_MAP_FREEZE:
+ case BPF_PROG_LOAD:
+ case BPF_BTF_LOAD:
+ break;
+ /* case BPF_PROG_TEST_RUN:
+ * is not part of this list to prevent recursive test_run
+ */
+ default:
+ return -EINVAL;
+ }
+ return __sys_bpf(cmd, KERNEL_BPFPTR(attr), attr_size);
+}
+
+static const struct bpf_func_proto bpf_sys_bpf_proto = {
+ .func = bpf_sys_bpf,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_ANYTHING,
+ .arg2_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_CONST_SIZE,
+};
+
+const struct bpf_func_proto * __weak
+tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+ return bpf_base_func_proto(func_id);
+}
+
+BPF_CALL_1(bpf_sys_close, u32, fd)
+{
+ /* When bpf program calls this helper there should not be
+ * an fdget() without matching completed fdput().
+ * This helper is allowed in the following callchain only:
+ * sys_bpf->prog_test_run->bpf_prog->bpf_sys_close
+ */
+ return close_fd(fd);
+}
+
+static const struct bpf_func_proto bpf_sys_close_proto = {
+ .func = bpf_sys_close,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_ANYTHING,
+};
+
+static const struct bpf_func_proto *
+syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+ switch (func_id) {
+ case BPF_FUNC_sys_bpf:
+ return &bpf_sys_bpf_proto;
+ case BPF_FUNC_btf_find_by_name_kind:
+ return &bpf_btf_find_by_name_kind_proto;
+ case BPF_FUNC_sys_close:
+ return &bpf_sys_close_proto;
+ default:
+ return tracing_prog_func_proto(func_id, prog);
+ }
+}
+
+const struct bpf_verifier_ops bpf_syscall_verifier_ops = {
+ .get_func_proto = syscall_prog_func_proto,
+ .is_valid_access = syscall_prog_is_valid_access,
+};
+
+const struct bpf_prog_ops bpf_syscall_prog_ops = {
+ .test_run = bpf_prog_test_run_syscall,
+};
diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c
index ceac5281bd31..3d7127f439a1 100644
--- a/kernel/bpf/tnum.c
+++ b/kernel/bpf/tnum.c
@@ -111,28 +111,31 @@ struct tnum tnum_xor(struct tnum a, struct tnum b)
return TNUM(v & ~mu, mu);
}
-/* half-multiply add: acc += (unknown * mask * value).
- * An intermediate step in the multiply algorithm.
+/* Generate partial products by multiplying each bit in the multiplier (tnum a)
+ * with the multiplicand (tnum b), and add the partial products after
+ * appropriately bit-shifting them. Instead of directly performing tnum addition
+ * on the generated partial products, equivalenty, decompose each partial
+ * product into two tnums, consisting of the value-sum (acc_v) and the
+ * mask-sum (acc_m) and then perform tnum addition on them. The following paper
+ * explains the algorithm in more detail: https://arxiv.org/abs/2105.05398.
*/
-static struct tnum hma(struct tnum acc, u64 value, u64 mask)
-{
- while (mask) {
- if (mask & 1)
- acc = tnum_add(acc, TNUM(0, value));
- mask >>= 1;
- value <<= 1;
- }
- return acc;
-}
-
struct tnum tnum_mul(struct tnum a, struct tnum b)
{
- struct tnum acc;
- u64 pi;
-
- pi = a.value * b.value;
- acc = hma(TNUM(pi, 0), a.mask, b.mask | b.value);
- return hma(acc, b.mask, a.value);
+ u64 acc_v = a.value * b.value;
+ struct tnum acc_m = TNUM(0, 0);
+
+ while (a.value || a.mask) {
+ /* LSB of tnum a is a certain 1 */
+ if (a.value & 1)
+ acc_m = tnum_add(acc_m, TNUM(0, b.mask));
+ /* LSB of tnum a is uncertain */
+ else if (a.mask & 1)
+ acc_m = tnum_add(acc_m, TNUM(0, b.value | b.mask));
+ /* Note: no case for LSB is certain 0 */
+ a = tnum_rshift(a, 1);
+ b = tnum_lshift(b, 1);
+ }
+ return tnum_add(TNUM(acc_v, 0), acc_m);
}
/* Note that if a and b disagree - i.e. one has a 'known 1' where the other has
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 2d44b5aa0057..28a3630c48ee 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -552,7 +552,7 @@ static void notrace inc_misses_counter(struct bpf_prog *prog)
* __bpf_prog_enter returns:
* 0 - skip execution of the bpf prog
* 1 - execute bpf prog
- * [2..MAX_U64] - excute bpf prog and record execution time.
+ * [2..MAX_U64] - execute bpf prog and record execution time.
* This is start time.
*/
u64 notrace __bpf_prog_enter(struct bpf_prog *prog)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c6a27574242d..be38bb930bf1 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -47,7 +47,7 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = {
* - unreachable insns exist (shouldn't be a forest. program = one function)
* - out of bounds or malformed jumps
* The second pass is all possible path descent from the 1st insn.
- * Since it's analyzing all pathes through the program, the length of the
+ * Since it's analyzing all paths through the program, the length of the
* analysis is limited to 64k insn, which may be hit even if total number of
* insn is less then 4K, but there are too many branches that change stack/regs.
* Number of 'branches to be analyzed' is limited to 1k
@@ -132,7 +132,7 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = {
* If it's ok, then verifier allows this BPF_CALL insn and looks at
* .ret_type which is RET_PTR_TO_MAP_VALUE_OR_NULL, so it sets
* R0->type = PTR_TO_MAP_VALUE_OR_NULL which means bpf_map_lookup_elem() function
- * returns ether pointer to map value or NULL.
+ * returns either pointer to map value or NULL.
*
* When type PTR_TO_MAP_VALUE_OR_NULL passes through 'if (reg != 0) goto +off'
* insn, the register holding that pointer in the true branch changes state to
@@ -737,81 +737,104 @@ static void print_verifier_state(struct bpf_verifier_env *env,
verbose(env, "\n");
}
-#define COPY_STATE_FN(NAME, COUNT, FIELD, SIZE) \
-static int copy_##NAME##_state(struct bpf_func_state *dst, \
- const struct bpf_func_state *src) \
-{ \
- if (!src->FIELD) \
- return 0; \
- if (WARN_ON_ONCE(dst->COUNT < src->COUNT)) { \
- /* internal bug, make state invalid to reject the program */ \
- memset(dst, 0, sizeof(*dst)); \
- return -EFAULT; \
- } \
- memcpy(dst->FIELD, src->FIELD, \
- sizeof(*src->FIELD) * (src->COUNT / SIZE)); \
- return 0; \
-}
-/* copy_reference_state() */
-COPY_STATE_FN(reference, acquired_refs, refs, 1)
-/* copy_stack_state() */
-COPY_STATE_FN(stack, allocated_stack, stack, BPF_REG_SIZE)
-#undef COPY_STATE_FN
-
-#define REALLOC_STATE_FN(NAME, COUNT, FIELD, SIZE) \
-static int realloc_##NAME##_state(struct bpf_func_state *state, int size, \
- bool copy_old) \
-{ \
- u32 old_size = state->COUNT; \
- struct bpf_##NAME##_state *new_##FIELD; \
- int slot = size / SIZE; \
- \
- if (size <= old_size || !size) { \
- if (copy_old) \
- return 0; \
- state->COUNT = slot * SIZE; \
- if (!size && old_size) { \
- kfree(state->FIELD); \
- state->FIELD = NULL; \
- } \
- return 0; \
- } \
- new_##FIELD = kmalloc_array(slot, sizeof(struct bpf_##NAME##_state), \
- GFP_KERNEL); \
- if (!new_##FIELD) \
- return -ENOMEM; \
- if (copy_old) { \
- if (state->FIELD) \
- memcpy(new_##FIELD, state->FIELD, \
- sizeof(*new_##FIELD) * (old_size / SIZE)); \
- memset(new_##FIELD + old_size / SIZE, 0, \
- sizeof(*new_##FIELD) * (size - old_size) / SIZE); \
- } \
- state->COUNT = slot * SIZE; \
- kfree(state->FIELD); \
- state->FIELD = new_##FIELD; \
- return 0; \
-}
-/* realloc_reference_state() */
-REALLOC_STATE_FN(reference, acquired_refs, refs, 1)
-/* realloc_stack_state() */
-REALLOC_STATE_FN(stack, allocated_stack, stack, BPF_REG_SIZE)
-#undef REALLOC_STATE_FN
-
-/* do_check() starts with zero-sized stack in struct bpf_verifier_state to
- * make it consume minimal amount of memory. check_stack_write() access from
- * the program calls into realloc_func_state() to grow the stack size.
- * Note there is a non-zero 'parent' pointer inside bpf_verifier_state
- * which realloc_stack_state() copies over. It points to previous
- * bpf_verifier_state which is never reallocated.
+/* copy array src of length n * size bytes to dst. dst is reallocated if it's too
+ * small to hold src. This is different from krealloc since we don't want to preserve
+ * the contents of dst.
+ *
+ * Leaves dst untouched if src is NULL or length is zero. Returns NULL if memory could
+ * not be allocated.
*/
-static int realloc_func_state(struct bpf_func_state *state, int stack_size,
- int refs_size, bool copy_old)
+static void *copy_array(void *dst, const void *src, size_t n, size_t size, gfp_t flags)
{
- int err = realloc_reference_state(state, refs_size, copy_old);
- if (err)
- return err;
- return realloc_stack_state(state, stack_size, copy_old);
+ size_t bytes;
+
+ if (ZERO_OR_NULL_PTR(src))
+ goto out;
+
+ if (unlikely(check_mul_overflow(n, size, &bytes)))
+ return NULL;
+
+ if (ksize(dst) < bytes) {
+ kfree(dst);
+ dst = kmalloc_track_caller(bytes, flags);
+ if (!dst)
+ return NULL;
+ }
+
+ memcpy(dst, src, bytes);
+out:
+ return dst ? dst : ZERO_SIZE_PTR;
+}
+
+/* resize an array from old_n items to new_n items. the array is reallocated if it's too
+ * small to hold new_n items. new items are zeroed out if the array grows.
+ *
+ * Contrary to krealloc_array, does not free arr if new_n is zero.
+ */
+static void *realloc_array(void *arr, size_t old_n, size_t new_n, size_t size)
+{
+ if (!new_n || old_n == new_n)
+ goto out;
+
+ arr = krealloc_array(arr, new_n, size, GFP_KERNEL);
+ if (!arr)
+ return NULL;
+
+ if (new_n > old_n)
+ memset(arr + old_n * size, 0, (new_n - old_n) * size);
+
+out:
+ return arr ? arr : ZERO_SIZE_PTR;
+}
+
+static int copy_reference_state(struct bpf_func_state *dst, const struct bpf_func_state *src)
+{
+ dst->refs = copy_array(dst->refs, src->refs, src->acquired_refs,
+ sizeof(struct bpf_reference_state), GFP_KERNEL);
+ if (!dst->refs)
+ return -ENOMEM;
+
+ dst->acquired_refs = src->acquired_refs;
+ return 0;
+}
+
+static int copy_stack_state(struct bpf_func_state *dst, const struct bpf_func_state *src)
+{
+ size_t n = src->allocated_stack / BPF_REG_SIZE;
+
+ dst->stack = copy_array(dst->stack, src->stack, n, sizeof(struct bpf_stack_state),
+ GFP_KERNEL);
+ if (!dst->stack)
+ return -ENOMEM;
+
+ dst->allocated_stack = src->allocated_stack;
+ return 0;
+}
+
+static int resize_reference_state(struct bpf_func_state *state, size_t n)
+{
+ state->refs = realloc_array(state->refs, state->acquired_refs, n,
+ sizeof(struct bpf_reference_state));
+ if (!state->refs)
+ return -ENOMEM;
+
+ state->acquired_refs = n;
+ return 0;
+}
+
+static int grow_stack_state(struct bpf_func_state *state, int size)
+{
+ size_t old_n = state->allocated_stack / BPF_REG_SIZE, n = size / BPF_REG_SIZE;
+
+ if (old_n >= n)
+ return 0;
+
+ state->stack = realloc_array(state->stack, old_n, n, sizeof(struct bpf_stack_state));
+ if (!state->stack)
+ return -ENOMEM;
+
+ state->allocated_stack = size;
+ return 0;
}
/* Acquire a pointer id from the env and update the state->refs to include
@@ -825,7 +848,7 @@ static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx)
int new_ofs = state->acquired_refs;
int id, err;
- err = realloc_reference_state(state, state->acquired_refs + 1, true);
+ err = resize_reference_state(state, state->acquired_refs + 1);
if (err)
return err;
id = ++env->id_gen;
@@ -854,18 +877,6 @@ static int release_reference_state(struct bpf_func_state *state, int ptr_id)
return -EINVAL;
}
-static int transfer_reference_state(struct bpf_func_state *dst,
- struct bpf_func_state *src)
-{
- int err = realloc_reference_state(dst, src->acquired_refs, false);
- if (err)
- return err;
- err = copy_reference_state(dst, src);
- if (err)
- return err;
- return 0;
-}
-
static void free_func_state(struct bpf_func_state *state)
{
if (!state)
@@ -904,10 +915,6 @@ static int copy_func_state(struct bpf_func_state *dst,
{
int err;
- err = realloc_func_state(dst, src->allocated_stack, src->acquired_refs,
- false);
- if (err)
- return err;
memcpy(dst, src, offsetof(struct bpf_func_state, acquired_refs));
err = copy_reference_state(dst, src);
if (err)
@@ -919,16 +926,13 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
const struct bpf_verifier_state *src)
{
struct bpf_func_state *dst;
- u32 jmp_sz = sizeof(struct bpf_idx_pair) * src->jmp_history_cnt;
int i, err;
- if (dst_state->jmp_history_cnt < src->jmp_history_cnt) {
- kfree(dst_state->jmp_history);
- dst_state->jmp_history = kmalloc(jmp_sz, GFP_USER);
- if (!dst_state->jmp_history)
- return -ENOMEM;
- }
- memcpy(dst_state->jmp_history, src->jmp_history, jmp_sz);
+ dst_state->jmp_history = copy_array(dst_state->jmp_history, src->jmp_history,
+ src->jmp_history_cnt, sizeof(struct bpf_idx_pair),
+ GFP_USER);
+ if (!dst_state->jmp_history)
+ return -ENOMEM;
dst_state->jmp_history_cnt = src->jmp_history_cnt;
/* if dst has more stack frames then src frame, free them */
@@ -2590,8 +2594,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
u32 dst_reg = env->prog->insnsi[insn_idx].dst_reg;
struct bpf_reg_state *reg = NULL;
- err = realloc_func_state(state, round_up(slot + 1, BPF_REG_SIZE),
- state->acquired_refs, true);
+ err = grow_stack_state(state, round_up(slot + 1, BPF_REG_SIZE));
if (err)
return err;
/* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0,
@@ -2613,7 +2616,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
if (dst_reg != BPF_REG_FP) {
/* The backtracking logic can only recognize explicit
* stack slot address like [fp - 8]. Other spill of
- * scalar via different register has to be conervative.
+ * scalar via different register has to be conservative.
* Backtrack from here and mark all registers as precise
* that contributed into 'reg' being a constant.
*/
@@ -2753,8 +2756,7 @@ static int check_stack_write_var_off(struct bpf_verifier_env *env,
if (value_reg && register_is_null(value_reg))
writing_zero = true;
- err = realloc_func_state(state, round_up(-min_off, BPF_REG_SIZE),
- state->acquired_refs, true);
+ err = grow_stack_state(state, round_up(-min_off, BPF_REG_SIZE));
if (err)
return err;
@@ -5629,7 +5631,7 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn
subprog /* subprog number within this prog */);
/* Transfer references to the callee */
- err = transfer_reference_state(callee, caller);
+ err = copy_reference_state(callee, caller);
if (err)
return err;
@@ -5780,7 +5782,7 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
}
/* Transfer references to the caller */
- err = transfer_reference_state(caller, callee);
+ err = copy_reference_state(caller, callee);
if (err)
return err;
@@ -8968,12 +8970,14 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
mark_reg_known_zero(env, regs, insn->dst_reg);
dst_reg->map_ptr = map;
- if (insn->src_reg == BPF_PSEUDO_MAP_VALUE) {
+ if (insn->src_reg == BPF_PSEUDO_MAP_VALUE ||
+ insn->src_reg == BPF_PSEUDO_MAP_IDX_VALUE) {
dst_reg->type = PTR_TO_MAP_VALUE;
dst_reg->off = aux->map_off;
if (map_value_has_spin_lock(map))
dst_reg->id = ++env->id_gen;
- } else if (insn->src_reg == BPF_PSEUDO_MAP_FD) {
+ } else if (insn->src_reg == BPF_PSEUDO_MAP_FD ||
+ insn->src_reg == BPF_PSEUDO_MAP_IDX) {
dst_reg->type = CONST_PTR_TO_MAP;
} else {
verbose(env, "bpf verifier is misconfigured\n");
@@ -9104,7 +9108,7 @@ static int check_return_code(struct bpf_verifier_env *env)
!prog->aux->attach_func_proto->type)
return 0;
- /* eBPF calling convetion is such that R0 is used
+ /* eBPF calling convention is such that R0 is used
* to return the value from eBPF program.
* Make sure that it's readable at this time
* of bpf_exit, which means that program wrote
@@ -9489,7 +9493,7 @@ static int check_abnormal_return(struct bpf_verifier_env *env)
static int check_btf_func(struct bpf_verifier_env *env,
const union bpf_attr *attr,
- union bpf_attr __user *uattr)
+ bpfptr_t uattr)
{
const struct btf_type *type, *func_proto, *ret_type;
u32 i, nfuncs, urec_size, min_size;
@@ -9498,7 +9502,7 @@ static int check_btf_func(struct bpf_verifier_env *env,
struct bpf_func_info_aux *info_aux = NULL;
struct bpf_prog *prog;
const struct btf *btf;
- void __user *urecord;
+ bpfptr_t urecord;
u32 prev_offset = 0;
bool scalar_return;
int ret = -ENOMEM;
@@ -9526,7 +9530,7 @@ static int check_btf_func(struct bpf_verifier_env *env,
prog = env->prog;
btf = prog->aux->btf;
- urecord = u64_to_user_ptr(attr->func_info);
+ urecord = make_bpfptr(attr->func_info, uattr.is_kernel);
min_size = min_t(u32, krec_size, urec_size);
krecord = kvcalloc(nfuncs, krec_size, GFP_KERNEL | __GFP_NOWARN);
@@ -9544,13 +9548,15 @@ static int check_btf_func(struct bpf_verifier_env *env,
/* set the size kernel expects so loader can zero
* out the rest of the record.
*/
- if (put_user(min_size, &uattr->func_info_rec_size))
+ if (copy_to_bpfptr_offset(uattr,
+ offsetof(union bpf_attr, func_info_rec_size),
+ &min_size, sizeof(min_size)))
ret = -EFAULT;
}
goto err_free;
}
- if (copy_from_user(&krecord[i], urecord, min_size)) {
+ if (copy_from_bpfptr(&krecord[i], urecord, min_size)) {
ret = -EFAULT;
goto err_free;
}
@@ -9602,7 +9608,7 @@ static int check_btf_func(struct bpf_verifier_env *env,
}
prev_offset = krecord[i].insn_off;
- urecord += urec_size;
+ bpfptr_add(&urecord, urec_size);
}
prog->aux->func_info = krecord;
@@ -9634,14 +9640,14 @@ static void adjust_btf_func(struct bpf_verifier_env *env)
static int check_btf_line(struct bpf_verifier_env *env,
const union bpf_attr *attr,
- union bpf_attr __user *uattr)
+ bpfptr_t uattr)
{
u32 i, s, nr_linfo, ncopy, expected_size, rec_size, prev_offset = 0;
struct bpf_subprog_info *sub;
struct bpf_line_info *linfo;
struct bpf_prog *prog;
const struct btf *btf;
- void __user *ulinfo;
+ bpfptr_t ulinfo;
int err;
nr_linfo = attr->line_info_cnt;
@@ -9667,7 +9673,7 @@ static int check_btf_line(struct bpf_verifier_env *env,
s = 0;
sub = env->subprog_info;
- ulinfo = u64_to_user_ptr(attr->line_info);
+ ulinfo = make_bpfptr(attr->line_info, uattr.is_kernel);
expected_size = sizeof(struct bpf_line_info);
ncopy = min_t(u32, expected_size, rec_size);
for (i = 0; i < nr_linfo; i++) {
@@ -9675,14 +9681,15 @@ static int check_btf_line(struct bpf_verifier_env *env,
if (err) {
if (err == -E2BIG) {
verbose(env, "nonzero tailing record in line_info");
- if (put_user(expected_size,
- &uattr->line_info_rec_size))
+ if (copy_to_bpfptr_offset(uattr,
+ offsetof(union bpf_attr, line_info_rec_size),
+ &expected_size, sizeof(expected_size)))
err = -EFAULT;
}
goto err_free;
}
- if (copy_from_user(&linfo[i], ulinfo, ncopy)) {
+ if (copy_from_bpfptr(&linfo[i], ulinfo, ncopy)) {
err = -EFAULT;
goto err_free;
}
@@ -9734,7 +9741,7 @@ static int check_btf_line(struct bpf_verifier_env *env,
}
prev_offset = linfo[i].insn_off;
- ulinfo += rec_size;
+ bpfptr_add(&ulinfo, rec_size);
}
if (s != env->subprog_cnt) {
@@ -9756,7 +9763,7 @@ err_free:
static int check_btf_info(struct bpf_verifier_env *env,
const union bpf_attr *attr,
- union bpf_attr __user *uattr)
+ bpfptr_t uattr)
{
struct btf *btf;
int err;
@@ -9801,13 +9808,6 @@ static bool range_within(struct bpf_reg_state *old,
old->s32_max_value >= cur->s32_max_value;
}
-/* Maximum number of register states that can exist at once */
-#define ID_MAP_SIZE (MAX_BPF_REG + MAX_BPF_STACK / BPF_REG_SIZE)
-struct idpair {
- u32 old;
- u32 cur;
-};
-
/* If in the old state two registers had the same id, then they need to have
* the same id in the new state as well. But that id could be different from
* the old state, so we need to track the mapping from old to new ids.
@@ -9818,11 +9818,11 @@ struct idpair {
* So we look through our idmap to see if this old id has been seen before. If
* so, we require the new id to match; otherwise, we add the id pair to the map.
*/
-static bool check_ids(u32 old_id, u32 cur_id, struct idpair *idmap)
+static bool check_ids(u32 old_id, u32 cur_id, struct bpf_id_pair *idmap)
{
unsigned int i;
- for (i = 0; i < ID_MAP_SIZE; i++) {
+ for (i = 0; i < BPF_ID_MAP_SIZE; i++) {
if (!idmap[i].old) {
/* Reached an empty slot; haven't seen this id before */
idmap[i].old = old_id;
@@ -9899,7 +9899,7 @@ static void clean_verifier_state(struct bpf_verifier_env *env,
* Since the verifier pushes the branch states as it sees them while exploring
* the program the condition of walking the branch instruction for the second
* time means that all states below this branch were already explored and
- * their final liveness markes are already propagated.
+ * their final liveness marks are already propagated.
* Hence when the verifier completes the search of state list in is_state_visited()
* we can call this clean_live_states() function to mark all liveness states
* as REG_LIVE_DONE to indicate that 'parent' pointers of 'struct bpf_reg_state'
@@ -9935,7 +9935,7 @@ next:
/* Returns true if (rold safe implies rcur safe) */
static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
- struct idpair *idmap)
+ struct bpf_id_pair *idmap)
{
bool equal;
@@ -10053,7 +10053,7 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
static bool stacksafe(struct bpf_func_state *old,
struct bpf_func_state *cur,
- struct idpair *idmap)
+ struct bpf_id_pair *idmap)
{
int i, spi;
@@ -10150,32 +10150,23 @@ static bool refsafe(struct bpf_func_state *old, struct bpf_func_state *cur)
* whereas register type in current state is meaningful, it means that
* the current state will reach 'bpf_exit' instruction safely
*/
-static bool func_states_equal(struct bpf_func_state *old,
+static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_state *old,
struct bpf_func_state *cur)
{
- struct idpair *idmap;
- bool ret = false;
int i;
- idmap = kcalloc(ID_MAP_SIZE, sizeof(struct idpair), GFP_KERNEL);
- /* If we failed to allocate the idmap, just say it's not safe */
- if (!idmap)
- return false;
-
- for (i = 0; i < MAX_BPF_REG; i++) {
- if (!regsafe(&old->regs[i], &cur->regs[i], idmap))
- goto out_free;
- }
+ memset(env->idmap_scratch, 0, sizeof(env->idmap_scratch));
+ for (i = 0; i < MAX_BPF_REG; i++)
+ if (!regsafe(&old->regs[i], &cur->regs[i], env->idmap_scratch))
+ return false;
- if (!stacksafe(old, cur, idmap))
- goto out_free;
+ if (!stacksafe(old, cur, env->idmap_scratch))
+ return false;
if (!refsafe(old, cur))
- goto out_free;
- ret = true;
-out_free:
- kfree(idmap);
- return ret;
+ return false;
+
+ return true;
}
static bool states_equal(struct bpf_verifier_env *env,
@@ -10202,7 +10193,7 @@ static bool states_equal(struct bpf_verifier_env *env,
for (i = 0; i <= old->curframe; i++) {
if (old->frame[i]->callsite != cur->frame[i]->callsite)
return false;
- if (!func_states_equal(old->frame[i], cur->frame[i]))
+ if (!func_states_equal(env, old->frame[i], cur->frame[i]))
return false;
}
return true;
@@ -11239,6 +11230,7 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
struct bpf_map *map;
struct fd f;
u64 addr;
+ u32 fd;
if (i == insn_cnt - 1 || insn[1].code != 0 ||
insn[1].dst_reg != 0 || insn[1].src_reg != 0 ||
@@ -11268,16 +11260,38 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
/* In final convert_pseudo_ld_imm64() step, this is
* converted into regular 64-bit imm load insn.
*/
- if ((insn[0].src_reg != BPF_PSEUDO_MAP_FD &&
- insn[0].src_reg != BPF_PSEUDO_MAP_VALUE) ||
- (insn[0].src_reg == BPF_PSEUDO_MAP_FD &&
- insn[1].imm != 0)) {
- verbose(env,
- "unrecognized bpf_ld_imm64 insn\n");
+ switch (insn[0].src_reg) {
+ case BPF_PSEUDO_MAP_VALUE:
+ case BPF_PSEUDO_MAP_IDX_VALUE:
+ break;
+ case BPF_PSEUDO_MAP_FD:
+ case BPF_PSEUDO_MAP_IDX:
+ if (insn[1].imm == 0)
+ break;
+ fallthrough;
+ default:
+ verbose(env, "unrecognized bpf_ld_imm64 insn\n");
return -EINVAL;
}
- f = fdget(insn[0].imm);
+ switch (insn[0].src_reg) {
+ case BPF_PSEUDO_MAP_IDX_VALUE:
+ case BPF_PSEUDO_MAP_IDX:
+ if (bpfptr_is_null(env->fd_array)) {
+ verbose(env, "fd_idx without fd_array is invalid\n");
+ return -EPROTO;
+ }
+ if (copy_from_bpfptr_offset(&fd, env->fd_array,
+ insn[0].imm * sizeof(fd),
+ sizeof(fd)))
+ return -EFAULT;
+ break;
+ default:
+ fd = insn[0].imm;
+ break;
+ }
+
+ f = fdget(fd);
map = __bpf_map_get(f);
if (IS_ERR(map)) {
verbose(env, "fd %d is not pointing to valid bpf_map\n",
@@ -11292,7 +11306,8 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
}
aux = &env->insn_aux_data[i];
- if (insn->src_reg == BPF_PSEUDO_MAP_FD) {
+ if (insn[0].src_reg == BPF_PSEUDO_MAP_FD ||
+ insn[0].src_reg == BPF_PSEUDO_MAP_IDX) {
addr = (unsigned long)map;
} else {
u32 off = insn[1].imm;
@@ -11459,7 +11474,7 @@ static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len
}
}
-static void adjust_poke_descs(struct bpf_prog *prog, u32 len)
+static void adjust_poke_descs(struct bpf_prog *prog, u32 off, u32 len)
{
struct bpf_jit_poke_descriptor *tab = prog->aux->poke_tab;
int i, sz = prog->aux->size_poke_tab;
@@ -11467,6 +11482,8 @@ static void adjust_poke_descs(struct bpf_prog *prog, u32 len)
for (i = 0; i < sz; i++) {
desc = &tab[i];
+ if (desc->insn_idx <= off)
+ continue;
desc->insn_idx += len - 1;
}
}
@@ -11487,7 +11504,7 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of
if (adjust_insn_aux_data(env, new_prog, off, len))
return NULL;
adjust_subprog_starts(env, off, len);
- adjust_poke_descs(new_prog, len);
+ adjust_poke_descs(new_prog, off, len);
return new_prog;
}
@@ -12506,7 +12523,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
prog->aux->max_pkt_offset = MAX_PACKET_OFF;
/* mark bpf_tail_call as different opcode to avoid
- * conditional branch in the interpeter for every normal
+ * conditional branch in the interpreter for every normal
* call and to prevent accidental JITing by JIT compiler
* that doesn't support bpf_tail_call yet
*/
@@ -13281,6 +13298,14 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
int ret;
u64 key;
+ if (prog->type == BPF_PROG_TYPE_SYSCALL) {
+ if (prog->aux->sleepable)
+ /* attach_btf_id checked to be zero already */
+ return 0;
+ verbose(env, "Syscall programs can only be sleepable\n");
+ return -EINVAL;
+ }
+
if (prog->aux->sleepable && prog->type != BPF_PROG_TYPE_TRACING &&
prog->type != BPF_PROG_TYPE_LSM) {
verbose(env, "Only fentry/fexit/fmod_ret and lsm programs can be sleepable\n");
@@ -13355,8 +13380,7 @@ struct btf *bpf_get_btf_vmlinux(void)
return btf_vmlinux;
}
-int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
- union bpf_attr __user *uattr)
+int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr)
{
u64 start_time = ktime_get_ns();
struct bpf_verifier_env *env;
@@ -13386,6 +13410,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
env->insn_aux_data[i].orig_idx = i;
env->prog = *prog;
env->ops = bpf_verifier_ops[env->prog->type];
+ env->fd_array = make_bpfptr(attr->fd_array, uattr.is_kernel);
is_priv = bpf_capable();
bpf_get_btf_vmlinux();
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 7a52bc172841..64bd2d84367f 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1017,6 +1017,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
#ifdef CONFIG_CGROUPS
case BPF_FUNC_get_current_cgroup_id:
return &bpf_get_current_cgroup_id_proto;
+ case BPF_FUNC_get_current_ancestor_cgroup_id:
+ return &bpf_get_current_ancestor_cgroup_id_proto;
#endif
case BPF_FUNC_send_signal:
return &bpf_send_signal_proto;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index cd80d046c7a5..d5d8c088a55d 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -20,6 +20,7 @@
#include <linux/irq_work.h>
#include <linux/workqueue.h>
#include <linux/ctype.h>
+#include <linux/once_lite.h>
#ifdef CONFIG_FTRACE_SYSCALLS
#include <asm/unistd.h> /* For NR_SYSCALLS */
@@ -99,16 +100,8 @@ enum trace_type {
#include "trace_entries.h"
/* Use this for memory failure errors */
-#define MEM_FAIL(condition, fmt, ...) ({ \
- static bool __section(".data.once") __warned; \
- int __ret_warn_once = !!(condition); \
- \
- if (unlikely(__ret_warn_once && !__warned)) { \
- __warned = true; \
- pr_err("ERROR: " fmt, ##__VA_ARGS__); \
- } \
- unlikely(__ret_warn_once); \
-})
+#define MEM_FAIL(condition, fmt, ...) \
+ DO_ONCE_LITE_IF(condition, pr_err, "ERROR: " fmt, ##__VA_ARGS__)
/*
* syscalls are special, and need special handling, this is why