diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-01-20 09:57:05 +0100 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-01-20 09:57:05 +0100 |
commit | fa2e1ba3e9e39072fa7a6a9d11ac432c505b4ac7 (patch) | |
tree | 9a8eb0d867559af3a55a88856d23036dabdf3f1c /kernel/bpf | |
parent | Merge branch 'akpm' (patches from Andrew) (diff) | |
parent | Merge branch 'ipv4-avoid-pathological-hash-tables' (diff) | |
download | linux-fa2e1ba3e9e39072fa7a6a9d11ac432c505b4ac7.tar.xz linux-fa2e1ba3e9e39072fa7a6a9d11ac432c505b4ac7.zip |
Merge tag 'net-5.17-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski:
"Including fixes from netfilter, bpf.
Quite a handful of old regression fixes but most of those are
pre-5.16.
Current release - regressions:
- fix memory leaks in the skb free deferral scheme if upper layer
protocols are used, i.e. in-kernel TCP readers like TLS
Current release - new code bugs:
- nf_tables: fix NULL check typo in _clone() functions
- change the default to y for Vertexcom vendor Kconfig
- a couple of fixes to incorrect uses of ref tracking
- two fixes for constifying netdev->dev_addr
Previous releases - regressions:
- bpf:
- various verifier fixes mainly around register offset handling
when passed to helper functions
- fix mount source displayed for bpffs (none -> bpffs)
- bonding:
- fix extraction of ports for connection hash calculation
- fix bond_xmit_broadcast return value when some devices are down
- phy: marvell: add Marvell specific PHY loopback
- sch_api: don't skip qdisc attach on ingress, prevent ref leak
- htb: restore minimal packet size handling in rate control
- sfp: fix high power modules without diagnostic monitoring
- mscc: ocelot:
- don't let phylink re-enable TX PAUSE on the NPI port
- don't dereference NULL pointers with shared tc filters
- smsc95xx: correct reset handling for LAN9514
- cpsw: avoid alignment faults by taking NET_IP_ALIGN into account
- phy: micrel: use kszphy_suspend/_resume for irq aware devices,
avoid races with the interrupt
Previous releases - always broken:
- xdp: check prog type before updating BPF link
- smc: resolve various races around abnormal connection termination
- sit: allow encapsulated IPv6 traffic to be delivered locally
- axienet: fix init/reset handling, add missing barriers, read the
right status words, stop queues correctly
- add missing dev_put() in sock_timestamping_bind_phc()
Misc:
- ipv4: prevent accidentally passing RTO_ONLINK to
ip_route_output_key_hash() by sanitizing flags
- ipv4: avoid quadratic behavior in netns dismantle
- stmmac: dwmac-oxnas: add support for OX810SE
- fsl: xgmac_mdio: add workaround for erratum A-009885"
* tag 'net-5.17-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (92 commits)
ipv4: add net_hash_mix() dispersion to fib_info_laddrhash keys
ipv4: avoid quadratic behavior in netns dismantle
net/fsl: xgmac_mdio: Fix incorrect iounmap when removing module
powerpc/fsl/dts: Enable WA for erratum A-009885 on fman3l MDIO buses
dt-bindings: net: Document fsl,erratum-a009885
net/fsl: xgmac_mdio: Add workaround for erratum A-009885
net: mscc: ocelot: fix using match before it is set
net: phy: micrel: use kszphy_suspend()/kszphy_resume for irq aware devices
net: cpsw: avoid alignment faults by taking NET_IP_ALIGN into account
nfc: llcp: fix NULL error pointer dereference on sendmsg() after failed bind()
net: axienet: increase default TX ring size to 128
net: axienet: fix for TX busy handling
net: axienet: fix number of TX ring slots for available check
net: axienet: Fix TX ring slot available check
net: axienet: limit minimum TX ring size
net: axienet: add missing memory barriers
net: axienet: reset core on initialization prior to MDIO access
net: axienet: Wait for PhyRstCmplt after core reset
net: axienet: increase reset timeout
bpf, selftests: Add ringbuf memory type confusion test
...
Diffstat (limited to 'kernel/bpf')
-rw-r--r-- | kernel/bpf/btf.c | 2 | ||||
-rw-r--r-- | kernel/bpf/inode.c | 14 | ||||
-rw-r--r-- | kernel/bpf/verifier.c | 81 |
3 files changed, 69 insertions, 28 deletions
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 33bb8ae4a804..e16dafeb2450 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -5686,7 +5686,7 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, i, btf_type_str(t)); return -EINVAL; } - if (check_ctx_reg(env, reg, regno)) + if (check_ptr_off_reg(env, reg, regno)) return -EINVAL; } else if (is_kfunc && (reg->type == PTR_TO_BTF_ID || reg2btf_ids[reg->type])) { const struct btf_type *reg_ref_t; diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 80da1db47c68..5a8d9f7467bf 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -648,12 +648,22 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) int opt; opt = fs_parse(fc, bpf_fs_parameters, param, &result); - if (opt < 0) + if (opt < 0) { /* We might like to report bad mount options here, but * traditionally we've ignored all mount options, so we'd * better continue to ignore non-existing options for bpf. */ - return opt == -ENOPARAM ? 0 : opt; + if (opt == -ENOPARAM) { + opt = vfs_parse_fs_param_source(fc, param); + if (opt != -ENOPARAM) + return opt; + + return 0; + } + + if (opt < 0) + return opt; + } switch (opt) { case OPT_MODE: diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index bfb45381fb3f..a39eedecc93a 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -570,6 +570,8 @@ static const char *reg_type_str(struct bpf_verifier_env *env, if (type & MEM_RDONLY) strncpy(prefix, "rdonly_", 16); + if (type & MEM_ALLOC) + strncpy(prefix, "alloc_", 16); snprintf(env->type_str_buf, TYPE_STR_BUF_LEN, "%s%s%s", prefix, str[base_type(type)], postfix); @@ -616,7 +618,7 @@ static void mark_reg_scratched(struct bpf_verifier_env *env, u32 regno) static void mark_stack_slot_scratched(struct bpf_verifier_env *env, u32 spi) { - env->scratched_stack_slots |= 1UL << spi; + env->scratched_stack_slots |= 1ULL << spi; } static bool reg_scratched(const struct bpf_verifier_env *env, u32 regno) @@ -637,14 +639,14 @@ static bool verifier_state_scratched(const struct bpf_verifier_env *env) static void mark_verifier_state_clean(struct bpf_verifier_env *env) { env->scratched_regs = 0U; - env->scratched_stack_slots = 0UL; + env->scratched_stack_slots = 0ULL; } /* Used for printing the entire verifier state. */ static void mark_verifier_state_scratched(struct bpf_verifier_env *env) { env->scratched_regs = ~0U; - env->scratched_stack_slots = ~0UL; + env->scratched_stack_slots = ~0ULL; } /* The reg state of a pointer or a bounded scalar was saved when @@ -3969,16 +3971,17 @@ static int get_callee_stack_depth(struct bpf_verifier_env *env, } #endif -int check_ctx_reg(struct bpf_verifier_env *env, - const struct bpf_reg_state *reg, int regno) +static int __check_ptr_off_reg(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int regno, + bool fixed_off_ok) { - /* Access to ctx or passing it to a helper is only allowed in - * its original, unmodified form. + /* Access to this pointer-typed register or passing it to a helper + * is only allowed in its original, unmodified form. */ - if (reg->off) { - verbose(env, "dereference of modified ctx ptr R%d off=%d disallowed\n", - regno, reg->off); + if (!fixed_off_ok && reg->off) { + verbose(env, "dereference of modified %s ptr R%d off=%d disallowed\n", + reg_type_str(env, reg->type), regno, reg->off); return -EACCES; } @@ -3986,13 +3989,20 @@ int check_ctx_reg(struct bpf_verifier_env *env, char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(env, "variable ctx access var_off=%s disallowed\n", tn_buf); + verbose(env, "variable %s access var_off=%s disallowed\n", + reg_type_str(env, reg->type), tn_buf); return -EACCES; } return 0; } +int check_ptr_off_reg(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int regno) +{ + return __check_ptr_off_reg(env, reg, regno, false); +} + static int __check_buffer_access(struct bpf_verifier_env *env, const char *buf_info, const struct bpf_reg_state *reg, @@ -4437,7 +4447,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn return -EACCES; } - err = check_ctx_reg(env, reg, regno); + err = check_ptr_off_reg(env, reg, regno); if (err < 0) return err; @@ -5127,6 +5137,7 @@ static const struct bpf_reg_types mem_types = { PTR_TO_MAP_KEY, PTR_TO_MAP_VALUE, PTR_TO_MEM, + PTR_TO_MEM | MEM_ALLOC, PTR_TO_BUF, }, }; @@ -5144,7 +5155,7 @@ static const struct bpf_reg_types int_ptr_types = { static const struct bpf_reg_types fullsock_types = { .types = { PTR_TO_SOCKET } }; static const struct bpf_reg_types scalar_types = { .types = { SCALAR_VALUE } }; static const struct bpf_reg_types context_types = { .types = { PTR_TO_CTX } }; -static const struct bpf_reg_types alloc_mem_types = { .types = { PTR_TO_MEM } }; +static const struct bpf_reg_types alloc_mem_types = { .types = { PTR_TO_MEM | MEM_ALLOC } }; static const struct bpf_reg_types const_map_ptr_types = { .types = { CONST_PTR_TO_MAP } }; static const struct bpf_reg_types btf_ptr_types = { .types = { PTR_TO_BTF_ID } }; static const struct bpf_reg_types spin_lock_types = { .types = { PTR_TO_MAP_VALUE } }; @@ -5244,12 +5255,6 @@ found: kernel_type_name(btf_vmlinux, *arg_btf_id)); return -EACCES; } - - if (!tnum_is_const(reg->var_off) || reg->var_off.value) { - verbose(env, "R%d is a pointer to in-kernel struct with non-zero offset\n", - regno); - return -EACCES; - } } return 0; @@ -5304,10 +5309,33 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg, if (err) return err; - if (type == PTR_TO_CTX) { - err = check_ctx_reg(env, reg, regno); + switch ((u32)type) { + case SCALAR_VALUE: + /* Pointer types where reg offset is explicitly allowed: */ + case PTR_TO_PACKET: + case PTR_TO_PACKET_META: + case PTR_TO_MAP_KEY: + case PTR_TO_MAP_VALUE: + case PTR_TO_MEM: + case PTR_TO_MEM | MEM_RDONLY: + case PTR_TO_MEM | MEM_ALLOC: + case PTR_TO_BUF: + case PTR_TO_BUF | MEM_RDONLY: + case PTR_TO_STACK: + /* Some of the argument types nevertheless require a + * zero register offset. + */ + if (arg_type == ARG_PTR_TO_ALLOC_MEM) + goto force_off_check; + break; + /* All the rest must be rejected: */ + default: +force_off_check: + err = __check_ptr_off_reg(env, reg, regno, + type == PTR_TO_BTF_ID); if (err < 0) return err; + break; } skip_type_check: @@ -9507,9 +9535,13 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) return 0; } - if (insn->src_reg == BPF_PSEUDO_BTF_ID) { - mark_reg_known_zero(env, regs, insn->dst_reg); + /* All special src_reg cases are listed below. From this point onwards + * we either succeed and assign a corresponding dst_reg->type after + * zeroing the offset, or fail and reject the program. + */ + mark_reg_known_zero(env, regs, insn->dst_reg); + if (insn->src_reg == BPF_PSEUDO_BTF_ID) { dst_reg->type = aux->btf_var.reg_type; switch (base_type(dst_reg->type)) { case PTR_TO_MEM: @@ -9547,7 +9579,6 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) } map = env->used_maps[aux->map_index]; - mark_reg_known_zero(env, regs, insn->dst_reg); dst_reg->map_ptr = map; if (insn->src_reg == BPF_PSEUDO_MAP_VALUE || @@ -9651,7 +9682,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; } - err = check_ctx_reg(env, ®s[ctx_reg], ctx_reg); + err = check_ptr_off_reg(env, ®s[ctx_reg], ctx_reg); if (err < 0) return err; |