- Kernel - mailweb.openeuler.org

[PATCH OLK-5.10] bpf: Fix incorrect verifier pruning due to missing register precision taints
by Pu Lehui 06 Jul '23

06 Jul '23

stable inclusion from stable-v5.10.179 commit b1281d008845ae9a4de9ef7510dcc1667557a67a category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7J5UK CVE: CVE-2023-2163 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 71b547f561247897a0a14f3082730156c0533fed ] Juan Jose et al reported an issue found via fuzzing where the verifier's pruning logic prematurely marks a program path as safe. Consider the following program: 0: (b7) r6 = 1024 1: (b7) r7 = 0 2: (b7) r8 = 0 3: (b7) r9 = -2147483648 4: (97) r6 %= 1025 5: (05) goto pc+0 6: (bd) if r6 <= r9 goto pc+2 7: (97) r6 %= 1 8: (b7) r9 = 0 9: (bd) if r6 <= r9 goto pc+1 10: (b7) r6 = 0 11: (b7) r0 = 0 12: (63) *(u32 *)(r10 -4) = r0 13: (18) r4 = 0xffff888103693400 // map_ptr(ks=4,vs=48) 15: (bf) r1 = r4 16: (bf) r2 = r10 17: (07) r2 += -4 18: (85) call bpf_map_lookup_elem#1 19: (55) if r0 != 0x0 goto pc+1 20: (95) exit 21: (77) r6 >>= 10 22: (27) r6 *= 8192 23: (bf) r1 = r0 24: (0f) r0 += r6 25: (79) r3 = *(u64 *)(r0 +0) 26: (7b) *(u64 *)(r1 +0) = r3 27: (95) exit The verifier treats this as safe, leading to oob read/write access due to an incorrect verifier conclusion: func#0 @0 0: R1=ctx(off=0,imm=0) R10=fp0 0: (b7) r6 = 1024 ; R6_w=1024 1: (b7) r7 = 0 ; R7_w=0 2: (b7) r8 = 0 ; R8_w=0 3: (b7) r9 = -2147483648 ; R9_w=-2147483648 4: (97) r6 %= 1025 ; R6_w=scalar() 5: (05) goto pc+0 6: (bd) if r6 <= r9 goto pc+2 ; R6_w=scalar(umin=18446744071562067969,var_off=(0xffffffff00000000; 0xffffffff)) R9_w=-2147483648 7: (97) r6 %= 1 ; R6_w=scalar() 8: (b7) r9 = 0 ; R9=0 9: (bd) if r6 <= r9 goto pc+1 ; R6=scalar(umin=1) R9=0 10: (b7) r6 = 0 ; R6_w=0 11: (b7) r0 = 0 ; R0_w=0 12: (63) *(u32 *)(r10 -4) = r0 last_idx 12 first_idx 9 regs=1 stack=0 before 11: (b7) r0 = 0 13: R0_w=0 R10=fp0 fp-8=0000???? 13: (18) r4 = 0xffff8ad3886c2a00 ; R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 15: (bf) r1 = r4 ; R1_w=map_ptr(off=0,ks=4,vs=48,imm=0) R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 16: (bf) r2 = r10 ; R2_w=fp0 R10=fp0 17: (07) r2 += -4 ; R2_w=fp-4 18: (85) call bpf_map_lookup_elem#1 ; R0=map_value_or_null(id=1,off=0,ks=4,vs=48,imm=0) 19: (55) if r0 != 0x0 goto pc+1 ; R0=0 20: (95) exit from 19 to 21: R0=map_value(off=0,ks=4,vs=48,imm=0) R6=0 R7=0 R8=0 R9=0 R10=fp0 fp-8=mmmm???? 21: (77) r6 >>= 10 ; R6_w=0 22: (27) r6 *= 8192 ; R6_w=0 23: (bf) r1 = r0 ; R0=map_value(off=0,ks=4,vs=48,imm=0) R1_w=map_value(off=0,ks=4,vs=48,imm=0) 24: (0f) r0 += r6 last_idx 24 first_idx 19 regs=40 stack=0 before 23: (bf) r1 = r0 regs=40 stack=0 before 22: (27) r6 *= 8192 regs=40 stack=0 before 21: (77) r6 >>= 10 regs=40 stack=0 before 19: (55) if r0 != 0x0 goto pc+1 parent didn't have regs=40 stack=0 marks: R0_rw=map_value_or_null(id=1,off=0,ks=4,vs=48,imm=0) R6_rw=P0 R7=0 R8=0 R9=0 R10=fp0 fp-8=mmmm???? last_idx 18 first_idx 9 regs=40 stack=0 before 18: (85) call bpf_map_lookup_elem#1 regs=40 stack=0 before 17: (07) r2 += -4 regs=40 stack=0 before 16: (bf) r2 = r10 regs=40 stack=0 before 15: (bf) r1 = r4 regs=40 stack=0 before 13: (18) r4 = 0xffff8ad3886c2a00 regs=40 stack=0 before 12: (63) *(u32 *)(r10 -4) = r0 regs=40 stack=0 before 11: (b7) r0 = 0 regs=40 stack=0 before 10: (b7) r6 = 0 25: (79) r3 = *(u64 *)(r0 +0) ; R0_w=map_value(off=0,ks=4,vs=48,imm=0) R3_w=scalar() 26: (7b) *(u64 *)(r1 +0) = r3 ; R1_w=map_value(off=0,ks=4,vs=48,imm=0) R3_w=scalar() 27: (95) exit from 9 to 11: R1=ctx(off=0,imm=0) R6=0 R7=0 R8=0 R9=0 R10=fp0 11: (b7) r0 = 0 ; R0_w=0 12: (63) *(u32 *)(r10 -4) = r0 last_idx 12 first_idx 11 regs=1 stack=0 before 11: (b7) r0 = 0 13: R0_w=0 R10=fp0 fp-8=0000???? 13: (18) r4 = 0xffff8ad3886c2a00 ; R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 15: (bf) r1 = r4 ; R1_w=map_ptr(off=0,ks=4,vs=48,imm=0) R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 16: (bf) r2 = r10 ; R2_w=fp0 R10=fp0 17: (07) r2 += -4 ; R2_w=fp-4 18: (85) call bpf_map_lookup_elem#1 frame 0: propagating r6 last_idx 19 first_idx 11 regs=40 stack=0 before 18: (85) call bpf_map_lookup_elem#1 regs=40 stack=0 before 17: (07) r2 += -4 regs=40 stack=0 before 16: (bf) r2 = r10 regs=40 stack=0 before 15: (bf) r1 = r4 regs=40 stack=0 before 13: (18) r4 = 0xffff8ad3886c2a00 regs=40 stack=0 before 12: (63) *(u32 *)(r10 -4) = r0 regs=40 stack=0 before 11: (b7) r0 = 0 parent didn't have regs=40 stack=0 marks: R1=ctx(off=0,imm=0) R6_r=P0 R7=0 R8=0 R9=0 R10=fp0 last_idx 9 first_idx 9 regs=40 stack=0 before 9: (bd) if r6 <= r9 goto pc+1 parent didn't have regs=40 stack=0 marks: R1=ctx(off=0,imm=0) R6_rw=Pscalar() R7_w=0 R8_w=0 R9_rw=0 R10=fp0 last_idx 8 first_idx 0 regs=40 stack=0 before 8: (b7) r9 = 0 regs=40 stack=0 before 7: (97) r6 %= 1 regs=40 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 regs=40 stack=0 before 5: (05) goto pc+0 regs=40 stack=0 before 4: (97) r6 %= 1025 regs=40 stack=0 before 3: (b7) r9 = -2147483648 regs=40 stack=0 before 2: (b7) r8 = 0 regs=40 stack=0 before 1: (b7) r7 = 0 regs=40 stack=0 before 0: (b7) r6 = 1024 19: safe frame 0: propagating r6 last_idx 9 first_idx 0 regs=40 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 regs=40 stack=0 before 5: (05) goto pc+0 regs=40 stack=0 before 4: (97) r6 %= 1025 regs=40 stack=0 before 3: (b7) r9 = -2147483648 regs=40 stack=0 before 2: (b7) r8 = 0 regs=40 stack=0 before 1: (b7) r7 = 0 regs=40 stack=0 before 0: (b7) r6 = 1024 from 6 to 9: safe verification time 110 usec stack depth 4 processed 36 insns (limit 1000000) max_states_per_insn 0 total_states 3 peak_states 3 mark_read 2 The verifier considers this program as safe by mistakenly pruning unsafe code paths. In the above func#0, code lines 0-10 are of interest. In line 0-3 registers r6 to r9 are initialized with known scalar values. In line 4 the register r6 is reset to an unknown scalar given the verifier does not track modulo operations. Due to this, the verifier can also not determine precisely which branches in line 6 and 9 are taken, therefore it needs to explore them both. As can be seen, the verifier starts with exploring the false/fall-through paths first. The 'from 19 to 21' path has both r6=0 and r9=0 and the pointer arithmetic on r0 += r6 is therefore considered safe. Given the arithmetic, r6 is correctly marked for precision tracking where backtracking kicks in where it walks back the current path all the way where r6 was set to 0 in the fall-through branch. Next, the pruning logics pops the path 'from 9 to 11' from the stack. Also here, the state of the registers is the same, that is, r6=0 and r9=0, so that at line 19 the path can be pruned as it is considered safe. It is interesting to note that the conditional in line 9 turned r6 into a more precise state, that is, in the fall-through path at the beginning of line 10, it is R6=scalar(umin=1), and in the branch-taken path (which is analyzed here) at the beginning of line 11, r6 turned into a known const r6=0 as r9=0 prior to that and therefore (unsigned) r6 <= 0 concludes that r6 must be 0 (**): [...] ; R6_w=scalar() 9: (bd) if r6 <= r9 goto pc+1 ; R6=scalar(umin=1) R9=0 [...] from 9 to 11: R1=ctx(off=0,imm=0) R6=0 R7=0 R8=0 R9=0 R10=fp0 [...] The next path is 'from 6 to 9'. The verifier considers the old and current state equivalent, and therefore prunes the search incorrectly. Looking into the two states which are being compared by the pruning logic at line 9, the old state consists of R6_rwD=Pscalar() R9_rwD=0 R10=fp0 and the new state consists of R1=ctx(off=0,imm=0) R6_w=scalar(umax=18446744071562067968) R7_w=0 R8_w=0 R9_w=-2147483648 R10=fp0. While r6 had the reg->precise flag correctly set in the old state, r9 did not. Both r6'es are considered as equivalent given the old one is a superset of the current, more precise one, however, r9's actual values (0 vs 0x80000000) mismatch. Given the old r9 did not have reg->precise flag set, the verifier does not consider the register as contributing to the precision state of r6, and therefore it considered both r9 states as equivalent. However, for this specific pruned path (which is also the actual path taken at runtime), register r6 will be 0x400 and r9 0x80000000 when reaching line 21, thus oob-accessing the map. The purpose of precision tracking is to initially mark registers (including spilled ones) as imprecise to help verifier's pruning logic finding equivalent states it can then prune if they don't contribute to the program's safety aspects. For example, if registers are used for pointer arithmetic or to pass constant length to a helper, then the verifier sets reg->precise flag and backtracks the BPF program instruction sequence and chain of verifier states to ensure that the given register or stack slot including their dependencies are marked as precisely tracked scalar. This also includes any other registers and slots that contribute to a tracked state of given registers/stack slot. This backtracking relies on recorded jmp_history and is able to traverse entire chain of parent states. This process ends only when all the necessary registers/slots and their transitive dependencies are marked as precise. The backtrack_insn() is called from the current instruction up to the first instruction, and its purpose is to compute a bitmask of registers and stack slots that need precision tracking in the parent's verifier state. For example, if a current instruction is r6 = r7, then r6 needs precision after this instruction and r7 needs precision before this instruction, that is, in the parent state. Hence for the latter r7 is marked and r6 unmarked. For the class of jmp/jmp32 instructions, backtrack_insn() today only looks at call and exit instructions and for all other conditionals the masks remain as-is. However, in the given situation register r6 has a dependency on r9 (as described above in **), so also that one needs to be marked for precision tracking. In other words, if an imprecise register influences a precise one, then the imprecise register should also be marked precise. Meaning, in the parent state both dest and src register need to be tracked for precision and therefore the marking must be more conservative by setting reg->precise flag for both. The precision propagation needs to cover both for the conditional: if the src reg was marked but not the dst reg and vice versa. After the fix the program is correctly rejected: func#0 @0 0: R1=ctx(off=0,imm=0) R10=fp0 0: (b7) r6 = 1024 ; R6_w=1024 1: (b7) r7 = 0 ; R7_w=0 2: (b7) r8 = 0 ; R8_w=0 3: (b7) r9 = -2147483648 ; R9_w=-2147483648 4: (97) r6 %= 1025 ; R6_w=scalar() 5: (05) goto pc+0 6: (bd) if r6 <= r9 goto pc+2 ; R6_w=scalar(umin=18446744071562067969,var_off=(0xffffffff80000000; 0x7fffffff),u32_min=-2147483648) R9_w=-2147483648 7: (97) r6 %= 1 ; R6_w=scalar() 8: (b7) r9 = 0 ; R9=0 9: (bd) if r6 <= r9 goto pc+1 ; R6=scalar(umin=1) R9=0 10: (b7) r6 = 0 ; R6_w=0 11: (b7) r0 = 0 ; R0_w=0 12: (63) *(u32 *)(r10 -4) = r0 last_idx 12 first_idx 9 regs=1 stack=0 before 11: (b7) r0 = 0 13: R0_w=0 R10=fp0 fp-8=0000???? 13: (18) r4 = 0xffff9290dc5bfe00 ; R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 15: (bf) r1 = r4 ; R1_w=map_ptr(off=0,ks=4,vs=48,imm=0) R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 16: (bf) r2 = r10 ; R2_w=fp0 R10=fp0 17: (07) r2 += -4 ; R2_w=fp-4 18: (85) call bpf_map_lookup_elem#1 ; R0=map_value_or_null(id=1,off=0,ks=4,vs=48,imm=0) 19: (55) if r0 != 0x0 goto pc+1 ; R0=0 20: (95) exit from 19 to 21: R0=map_value(off=0,ks=4,vs=48,imm=0) R6=0 R7=0 R8=0 R9=0 R10=fp0 fp-8=mmmm???? 21: (77) r6 >>= 10 ; R6_w=0 22: (27) r6 *= 8192 ; R6_w=0 23: (bf) r1 = r0 ; R0=map_value(off=0,ks=4,vs=48,imm=0) R1_w=map_value(off=0,ks=4,vs=48,imm=0) 24: (0f) r0 += r6 last_idx 24 first_idx 19 regs=40 stack=0 before 23: (bf) r1 = r0 regs=40 stack=0 before 22: (27) r6 *= 8192 regs=40 stack=0 before 21: (77) r6 >>= 10 regs=40 stack=0 before 19: (55) if r0 != 0x0 goto pc+1 parent didn't have regs=40 stack=0 marks: R0_rw=map_value_or_null(id=1,off=0,ks=4,vs=48,imm=0) R6_rw=P0 R7=0 R8=0 R9=0 R10=fp0 fp-8=mmmm???? last_idx 18 first_idx 9 regs=40 stack=0 before 18: (85) call bpf_map_lookup_elem#1 regs=40 stack=0 before 17: (07) r2 += -4 regs=40 stack=0 before 16: (bf) r2 = r10 regs=40 stack=0 before 15: (bf) r1 = r4 regs=40 stack=0 before 13: (18) r4 = 0xffff9290dc5bfe00 regs=40 stack=0 before 12: (63) *(u32 *)(r10 -4) = r0 regs=40 stack=0 before 11: (b7) r0 = 0 regs=40 stack=0 before 10: (b7) r6 = 0 25: (79) r3 = *(u64 *)(r0 +0) ; R0_w=map_value(off=0,ks=4,vs=48,imm=0) R3_w=scalar() 26: (7b) *(u64 *)(r1 +0) = r3 ; R1_w=map_value(off=0,ks=4,vs=48,imm=0) R3_w=scalar() 27: (95) exit from 9 to 11: R1=ctx(off=0,imm=0) R6=0 R7=0 R8=0 R9=0 R10=fp0 11: (b7) r0 = 0 ; R0_w=0 12: (63) *(u32 *)(r10 -4) = r0 last_idx 12 first_idx 11 regs=1 stack=0 before 11: (b7) r0 = 0 13: R0_w=0 R10=fp0 fp-8=0000???? 13: (18) r4 = 0xffff9290dc5bfe00 ; R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 15: (bf) r1 = r4 ; R1_w=map_ptr(off=0,ks=4,vs=48,imm=0) R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 16: (bf) r2 = r10 ; R2_w=fp0 R10=fp0 17: (07) r2 += -4 ; R2_w=fp-4 18: (85) call bpf_map_lookup_elem#1 frame 0: propagating r6 last_idx 19 first_idx 11 regs=40 stack=0 before 18: (85) call bpf_map_lookup_elem#1 regs=40 stack=0 before 17: (07) r2 += -4 regs=40 stack=0 before 16: (bf) r2 = r10 regs=40 stack=0 before 15: (bf) r1 = r4 regs=40 stack=0 before 13: (18) r4 = 0xffff9290dc5bfe00 regs=40 stack=0 before 12: (63) *(u32 *)(r10 -4) = r0 regs=40 stack=0 before 11: (b7) r0 = 0 parent didn't have regs=40 stack=0 marks: R1=ctx(off=0,imm=0) R6_r=P0 R7=0 R8=0 R9=0 R10=fp0 last_idx 9 first_idx 9 regs=40 stack=0 before 9: (bd) if r6 <= r9 goto pc+1 parent didn't have regs=240 stack=0 marks: R1=ctx(off=0,imm=0) R6_rw=Pscalar() R7_w=0 R8_w=0 R9_rw=P0 R10=fp0 last_idx 8 first_idx 0 regs=240 stack=0 before 8: (b7) r9 = 0 regs=40 stack=0 before 7: (97) r6 %= 1 regs=40 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 regs=240 stack=0 before 5: (05) goto pc+0 regs=240 stack=0 before 4: (97) r6 %= 1025 regs=240 stack=0 before 3: (b7) r9 = -2147483648 regs=40 stack=0 before 2: (b7) r8 = 0 regs=40 stack=0 before 1: (b7) r7 = 0 regs=40 stack=0 before 0: (b7) r6 = 1024 19: safe from 6 to 9: R1=ctx(off=0,imm=0) R6_w=scalar(umax=18446744071562067968) R7_w=0 R8_w=0 R9_w=-2147483648 R10=fp0 9: (bd) if r6 <= r9 goto pc+1 last_idx 9 first_idx 0 regs=40 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 regs=240 stack=0 before 5: (05) goto pc+0 regs=240 stack=0 before 4: (97) r6 %= 1025 regs=240 stack=0 before 3: (b7) r9 = -2147483648 regs=40 stack=0 before 2: (b7) r8 = 0 regs=40 stack=0 before 1: (b7) r7 = 0 regs=40 stack=0 before 0: (b7) r6 = 1024 last_idx 9 first_idx 0 regs=200 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 regs=240 stack=0 before 5: (05) goto pc+0 regs=240 stack=0 before 4: (97) r6 %= 1025 regs=240 stack=0 before 3: (b7) r9 = -2147483648 regs=40 stack=0 before 2: (b7) r8 = 0 regs=40 stack=0 before 1: (b7) r7 = 0 regs=40 stack=0 before 0: (b7) r6 = 1024 11: R6=scalar(umax=18446744071562067968) R9=-2147483648 11: (b7) r0 = 0 ; R0_w=0 12: (63) *(u32 *)(r10 -4) = r0 last_idx 12 first_idx 11 regs=1 stack=0 before 11: (b7) r0 = 0 13: R0_w=0 R10=fp0 fp-8=0000???? 13: (18) r4 = 0xffff9290dc5bfe00 ; R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 15: (bf) r1 = r4 ; R1_w=map_ptr(off=0,ks=4,vs=48,imm=0) R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 16: (bf) r2 = r10 ; R2_w=fp0 R10=fp0 17: (07) r2 += -4 ; R2_w=fp-4 18: (85) call bpf_map_lookup_elem#1 ; R0_w=map_value_or_null(id=3,off=0,ks=4,vs=48,imm=0) 19: (55) if r0 != 0x0 goto pc+1 ; R0_w=0 20: (95) exit from 19 to 21: R0=map_value(off=0,ks=4,vs=48,imm=0) R6=scalar(umax=18446744071562067968) R7=0 R8=0 R9=-2147483648 R10=fp0 fp-8=mmmm???? 21: (77) r6 >>= 10 ; R6_w=scalar(umax=18014398507384832,var_off=(0x0; 0x3fffffffffffff)) 22: (27) r6 *= 8192 ; R6_w=scalar(smax=9223372036854767616,umax=18446744073709543424,var_off=(0x0; 0xffffffffffffe000),s32_max=2147475456,u32_max=-8192) 23: (bf) r1 = r0 ; R0=map_value(off=0,ks=4,vs=48,imm=0) R1_w=map_value(off=0,ks=4,vs=48,imm=0) 24: (0f) r0 += r6 last_idx 24 first_idx 21 regs=40 stack=0 before 23: (bf) r1 = r0 regs=40 stack=0 before 22: (27) r6 *= 8192 regs=40 stack=0 before 21: (77) r6 >>= 10 parent didn't have regs=40 stack=0 marks: R0_rw=map_value(off=0,ks=4,vs=48,imm=0) R6_r=Pscalar(umax=18446744071562067968) R7=0 R8=0 R9=-2147483648 R10=fp0 fp-8=mmmm???? last_idx 19 first_idx 11 regs=40 stack=0 before 19: (55) if r0 != 0x0 goto pc+1 regs=40 stack=0 before 18: (85) call bpf_map_lookup_elem#1 regs=40 stack=0 before 17: (07) r2 += -4 regs=40 stack=0 before 16: (bf) r2 = r10 regs=40 stack=0 before 15: (bf) r1 = r4 regs=40 stack=0 before 13: (18) r4 = 0xffff9290dc5bfe00 regs=40 stack=0 before 12: (63) *(u32 *)(r10 -4) = r0 regs=40 stack=0 before 11: (b7) r0 = 0 parent didn't have regs=40 stack=0 marks: R1=ctx(off=0,imm=0) R6_rw=Pscalar(umax=18446744071562067968) R7_w=0 R8_w=0 R9_w=-2147483648 R10=fp0 last_idx 9 first_idx 0 regs=40 stack=0 before 9: (bd) if r6 <= r9 goto pc+1 regs=240 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 regs=240 stack=0 before 5: (05) goto pc+0 regs=240 stack=0 before 4: (97) r6 %= 1025 regs=240 stack=0 before 3: (b7) r9 = -2147483648 regs=40 stack=0 before 2: (b7) r8 = 0 regs=40 stack=0 before 1: (b7) r7 = 0 regs=40 stack=0 before 0: (b7) r6 = 1024 math between map_value pointer and register with unbounded min value is not allowed verification time 886 usec stack depth 4 processed 49 insns (limit 1000000) max_states_per_insn 1 total_states 5 peak_states 5 mark_read 2 Fixes: b5dc0163d8fd ("bpf: precise scalar_value tracking") Reported-by: Juan Jose Lopez Jaimez <jjlopezjaimez(a)google.com> Reported-by: Meador Inge <meadori(a)google.com> Reported-by: Simon Scannell <simonscannell(a)google.com> Reported-by: Nenad Stojanovski <thenenadx(a)google.com> Signed-off-by: Daniel Borkmann <daniel(a)iogearbox.net> Co-developed-by: Andrii Nakryiko <andrii(a)kernel.org> Signed-off-by: Andrii Nakryiko <andrii(a)kernel.org> Reviewed-by: John Fastabend <john.fastabend(a)gmail.com> Reviewed-by: Juan Jose Lopez Jaimez <jjlopezjaimez(a)google.com> Reviewed-by: Meador Inge <meadori(a)google.com> Reviewed-by: Simon Scannell <simonscannell(a)google.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Pu Lehui <pulehui(a)huawei.com> Reviewed-by: Xu Kuohai <xukuohai(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> --- kernel/bpf/verifier.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c91533a54121..407f2263216d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1923,6 +1923,21 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, } } else if (opcode == BPF_EXIT) { return -ENOTSUPP; + } else if (BPF_SRC(insn->code) == BPF_X) { + if (!(*reg_mask & (dreg | sreg))) + return 0; + /* dreg <cond> sreg + * Both dreg and sreg need precision before + * this insn. If only sreg was marked precise + * before it would be equally necessary to + * propagate it to dreg. + */ + *reg_mask |= (sreg | dreg); + /* else dreg <cond> K + * Only dreg still needs precision before + * this insn, so for the K-based conditional + * there is nothing new to be marked. + */ } } else if (class == BPF_LD) { if (!(*reg_mask & dreg)) -- 2.25.1

2 1

[PATCH OLK-5.10] bpf: Fix incorrect verifier pruning due to missing register precision taints
by Pu Lehui 06 Jul '23

06 Jul '23

From: Pu Lehui <pulehui(a)huawei.com> stable inclusion from stable-v5.10.179 commit b1281d008845ae9a4de9ef7510dcc1667557a67a category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7J5UK CVE: CVE-2023-2163 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 71b547f561247897a0a14f3082730156c0533fed ] Juan Jose et al reported an issue found via fuzzing where the verifier's pruning logic prematurely marks a program path as safe. Consider the following program: 0: (b7) r6 = 1024 1: (b7) r7 = 0 2: (b7) r8 = 0 3: (b7) r9 = -2147483648 4: (97) r6 %= 1025 5: (05) goto pc+0 6: (bd) if r6 <= r9 goto pc+2 7: (97) r6 %= 1 8: (b7) r9 = 0 9: (bd) if r6 <= r9 goto pc+1 10: (b7) r6 = 0 11: (b7) r0 = 0 12: (63) *(u32 *)(r10 -4) = r0 13: (18) r4 = 0xffff888103693400 // map_ptr(ks=4,vs=48) 15: (bf) r1 = r4 16: (bf) r2 = r10 17: (07) r2 += -4 18: (85) call bpf_map_lookup_elem#1 19: (55) if r0 != 0x0 goto pc+1 20: (95) exit 21: (77) r6 >>= 10 22: (27) r6 *= 8192 23: (bf) r1 = r0 24: (0f) r0 += r6 25: (79) r3 = *(u64 *)(r0 +0) 26: (7b) *(u64 *)(r1 +0) = r3 27: (95) exit The verifier treats this as safe, leading to oob read/write access due to an incorrect verifier conclusion: func#0 @0 0: R1=ctx(off=0,imm=0) R10=fp0 0: (b7) r6 = 1024 ; R6_w=1024 1: (b7) r7 = 0 ; R7_w=0 2: (b7) r8 = 0 ; R8_w=0 3: (b7) r9 = -2147483648 ; R9_w=-2147483648 4: (97) r6 %= 1025 ; R6_w=scalar() 5: (05) goto pc+0 6: (bd) if r6 <= r9 goto pc+2 ; R6_w=scalar(umin=18446744071562067969,var_off=(0xffffffff00000000; 0xffffffff)) R9_w=-2147483648 7: (97) r6 %= 1 ; R6_w=scalar() 8: (b7) r9 = 0 ; R9=0 9: (bd) if r6 <= r9 goto pc+1 ; R6=scalar(umin=1) R9=0 10: (b7) r6 = 0 ; R6_w=0 11: (b7) r0 = 0 ; R0_w=0 12: (63) *(u32 *)(r10 -4) = r0 last_idx 12 first_idx 9 regs=1 stack=0 before 11: (b7) r0 = 0 13: R0_w=0 R10=fp0 fp-8=0000???? 13: (18) r4 = 0xffff8ad3886c2a00 ; R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 15: (bf) r1 = r4 ; R1_w=map_ptr(off=0,ks=4,vs=48,imm=0) R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 16: (bf) r2 = r10 ; R2_w=fp0 R10=fp0 17: (07) r2 += -4 ; R2_w=fp-4 18: (85) call bpf_map_lookup_elem#1 ; R0=map_value_or_null(id=1,off=0,ks=4,vs=48,imm=0) 19: (55) if r0 != 0x0 goto pc+1 ; R0=0 20: (95) exit from 19 to 21: R0=map_value(off=0,ks=4,vs=48,imm=0) R6=0 R7=0 R8=0 R9=0 R10=fp0 fp-8=mmmm???? 21: (77) r6 >>= 10 ; R6_w=0 22: (27) r6 *= 8192 ; R6_w=0 23: (bf) r1 = r0 ; R0=map_value(off=0,ks=4,vs=48,imm=0) R1_w=map_value(off=0,ks=4,vs=48,imm=0) 24: (0f) r0 += r6 last_idx 24 first_idx 19 regs=40 stack=0 before 23: (bf) r1 = r0 regs=40 stack=0 before 22: (27) r6 *= 8192 regs=40 stack=0 before 21: (77) r6 >>= 10 regs=40 stack=0 before 19: (55) if r0 != 0x0 goto pc+1 parent didn't have regs=40 stack=0 marks: R0_rw=map_value_or_null(id=1,off=0,ks=4,vs=48,imm=0) R6_rw=P0 R7=0 R8=0 R9=0 R10=fp0 fp-8=mmmm???? last_idx 18 first_idx 9 regs=40 stack=0 before 18: (85) call bpf_map_lookup_elem#1 regs=40 stack=0 before 17: (07) r2 += -4 regs=40 stack=0 before 16: (bf) r2 = r10 regs=40 stack=0 before 15: (bf) r1 = r4 regs=40 stack=0 before 13: (18) r4 = 0xffff8ad3886c2a00 regs=40 stack=0 before 12: (63) *(u32 *)(r10 -4) = r0 regs=40 stack=0 before 11: (b7) r0 = 0 regs=40 stack=0 before 10: (b7) r6 = 0 25: (79) r3 = *(u64 *)(r0 +0) ; R0_w=map_value(off=0,ks=4,vs=48,imm=0) R3_w=scalar() 26: (7b) *(u64 *)(r1 +0) = r3 ; R1_w=map_value(off=0,ks=4,vs=48,imm=0) R3_w=scalar() 27: (95) exit from 9 to 11: R1=ctx(off=0,imm=0) R6=0 R7=0 R8=0 R9=0 R10=fp0 11: (b7) r0 = 0 ; R0_w=0 12: (63) *(u32 *)(r10 -4) = r0 last_idx 12 first_idx 11 regs=1 stack=0 before 11: (b7) r0 = 0 13: R0_w=0 R10=fp0 fp-8=0000???? 13: (18) r4 = 0xffff8ad3886c2a00 ; R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 15: (bf) r1 = r4 ; R1_w=map_ptr(off=0,ks=4,vs=48,imm=0) R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 16: (bf) r2 = r10 ; R2_w=fp0 R10=fp0 17: (07) r2 += -4 ; R2_w=fp-4 18: (85) call bpf_map_lookup_elem#1 frame 0: propagating r6 last_idx 19 first_idx 11 regs=40 stack=0 before 18: (85) call bpf_map_lookup_elem#1 regs=40 stack=0 before 17: (07) r2 += -4 regs=40 stack=0 before 16: (bf) r2 = r10 regs=40 stack=0 before 15: (bf) r1 = r4 regs=40 stack=0 before 13: (18) r4 = 0xffff8ad3886c2a00 regs=40 stack=0 before 12: (63) *(u32 *)(r10 -4) = r0 regs=40 stack=0 before 11: (b7) r0 = 0 parent didn't have regs=40 stack=0 marks: R1=ctx(off=0,imm=0) R6_r=P0 R7=0 R8=0 R9=0 R10=fp0 last_idx 9 first_idx 9 regs=40 stack=0 before 9: (bd) if r6 <= r9 goto pc+1 parent didn't have regs=40 stack=0 marks: R1=ctx(off=0,imm=0) R6_rw=Pscalar() R7_w=0 R8_w=0 R9_rw=0 R10=fp0 last_idx 8 first_idx 0 regs=40 stack=0 before 8: (b7) r9 = 0 regs=40 stack=0 before 7: (97) r6 %= 1 regs=40 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 regs=40 stack=0 before 5: (05) goto pc+0 regs=40 stack=0 before 4: (97) r6 %= 1025 regs=40 stack=0 before 3: (b7) r9 = -2147483648 regs=40 stack=0 before 2: (b7) r8 = 0 regs=40 stack=0 before 1: (b7) r7 = 0 regs=40 stack=0 before 0: (b7) r6 = 1024 19: safe frame 0: propagating r6 last_idx 9 first_idx 0 regs=40 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 regs=40 stack=0 before 5: (05) goto pc+0 regs=40 stack=0 before 4: (97) r6 %= 1025 regs=40 stack=0 before 3: (b7) r9 = -2147483648 regs=40 stack=0 before 2: (b7) r8 = 0 regs=40 stack=0 before 1: (b7) r7 = 0 regs=40 stack=0 before 0: (b7) r6 = 1024 from 6 to 9: safe verification time 110 usec stack depth 4 processed 36 insns (limit 1000000) max_states_per_insn 0 total_states 3 peak_states 3 mark_read 2 The verifier considers this program as safe by mistakenly pruning unsafe code paths. In the above func#0, code lines 0-10 are of interest. In line 0-3 registers r6 to r9 are initialized with known scalar values. In line 4 the register r6 is reset to an unknown scalar given the verifier does not track modulo operations. Due to this, the verifier can also not determine precisely which branches in line 6 and 9 are taken, therefore it needs to explore them both. As can be seen, the verifier starts with exploring the false/fall-through paths first. The 'from 19 to 21' path has both r6=0 and r9=0 and the pointer arithmetic on r0 += r6 is therefore considered safe. Given the arithmetic, r6 is correctly marked for precision tracking where backtracking kicks in where it walks back the current path all the way where r6 was set to 0 in the fall-through branch. Next, the pruning logics pops the path 'from 9 to 11' from the stack. Also here, the state of the registers is the same, that is, r6=0 and r9=0, so that at line 19 the path can be pruned as it is considered safe. It is interesting to note that the conditional in line 9 turned r6 into a more precise state, that is, in the fall-through path at the beginning of line 10, it is R6=scalar(umin=1), and in the branch-taken path (which is analyzed here) at the beginning of line 11, r6 turned into a known const r6=0 as r9=0 prior to that and therefore (unsigned) r6 <= 0 concludes that r6 must be 0 (**): [...] ; R6_w=scalar() 9: (bd) if r6 <= r9 goto pc+1 ; R6=scalar(umin=1) R9=0 [...] from 9 to 11: R1=ctx(off=0,imm=0) R6=0 R7=0 R8=0 R9=0 R10=fp0 [...] The next path is 'from 6 to 9'. The verifier considers the old and current state equivalent, and therefore prunes the search incorrectly. Looking into the two states which are being compared by the pruning logic at line 9, the old state consists of R6_rwD=Pscalar() R9_rwD=0 R10=fp0 and the new state consists of R1=ctx(off=0,imm=0) R6_w=scalar(umax=18446744071562067968) R7_w=0 R8_w=0 R9_w=-2147483648 R10=fp0. While r6 had the reg->precise flag correctly set in the old state, r9 did not. Both r6'es are considered as equivalent given the old one is a superset of the current, more precise one, however, r9's actual values (0 vs 0x80000000) mismatch. Given the old r9 did not have reg->precise flag set, the verifier does not consider the register as contributing to the precision state of r6, and therefore it considered both r9 states as equivalent. However, for this specific pruned path (which is also the actual path taken at runtime), register r6 will be 0x400 and r9 0x80000000 when reaching line 21, thus oob-accessing the map. The purpose of precision tracking is to initially mark registers (including spilled ones) as imprecise to help verifier's pruning logic finding equivalent states it can then prune if they don't contribute to the program's safety aspects. For example, if registers are used for pointer arithmetic or to pass constant length to a helper, then the verifier sets reg->precise flag and backtracks the BPF program instruction sequence and chain of verifier states to ensure that the given register or stack slot including their dependencies are marked as precisely tracked scalar. This also includes any other registers and slots that contribute to a tracked state of given registers/stack slot. This backtracking relies on recorded jmp_history and is able to traverse entire chain of parent states. This process ends only when all the necessary registers/slots and their transitive dependencies are marked as precise. The backtrack_insn() is called from the current instruction up to the first instruction, and its purpose is to compute a bitmask of registers and stack slots that need precision tracking in the parent's verifier state. For example, if a current instruction is r6 = r7, then r6 needs precision after this instruction and r7 needs precision before this instruction, that is, in the parent state. Hence for the latter r7 is marked and r6 unmarked. For the class of jmp/jmp32 instructions, backtrack_insn() today only looks at call and exit instructions and for all other conditionals the masks remain as-is. However, in the given situation register r6 has a dependency on r9 (as described above in **), so also that one needs to be marked for precision tracking. In other words, if an imprecise register influences a precise one, then the imprecise register should also be marked precise. Meaning, in the parent state both dest and src register need to be tracked for precision and therefore the marking must be more conservative by setting reg->precise flag for both. The precision propagation needs to cover both for the conditional: if the src reg was marked but not the dst reg and vice versa. After the fix the program is correctly rejected: func#0 @0 0: R1=ctx(off=0,imm=0) R10=fp0 0: (b7) r6 = 1024 ; R6_w=1024 1: (b7) r7 = 0 ; R7_w=0 2: (b7) r8 = 0 ; R8_w=0 3: (b7) r9 = -2147483648 ; R9_w=-2147483648 4: (97) r6 %= 1025 ; R6_w=scalar() 5: (05) goto pc+0 6: (bd) if r6 <= r9 goto pc+2 ; R6_w=scalar(umin=18446744071562067969,var_off=(0xffffffff80000000; 0x7fffffff),u32_min=-2147483648) R9_w=-2147483648 7: (97) r6 %= 1 ; R6_w=scalar() 8: (b7) r9 = 0 ; R9=0 9: (bd) if r6 <= r9 goto pc+1 ; R6=scalar(umin=1) R9=0 10: (b7) r6 = 0 ; R6_w=0 11: (b7) r0 = 0 ; R0_w=0 12: (63) *(u32 *)(r10 -4) = r0 last_idx 12 first_idx 9 regs=1 stack=0 before 11: (b7) r0 = 0 13: R0_w=0 R10=fp0 fp-8=0000???? 13: (18) r4 = 0xffff9290dc5bfe00 ; R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 15: (bf) r1 = r4 ; R1_w=map_ptr(off=0,ks=4,vs=48,imm=0) R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 16: (bf) r2 = r10 ; R2_w=fp0 R10=fp0 17: (07) r2 += -4 ; R2_w=fp-4 18: (85) call bpf_map_lookup_elem#1 ; R0=map_value_or_null(id=1,off=0,ks=4,vs=48,imm=0) 19: (55) if r0 != 0x0 goto pc+1 ; R0=0 20: (95) exit from 19 to 21: R0=map_value(off=0,ks=4,vs=48,imm=0) R6=0 R7=0 R8=0 R9=0 R10=fp0 fp-8=mmmm???? 21: (77) r6 >>= 10 ; R6_w=0 22: (27) r6 *= 8192 ; R6_w=0 23: (bf) r1 = r0 ; R0=map_value(off=0,ks=4,vs=48,imm=0) R1_w=map_value(off=0,ks=4,vs=48,imm=0) 24: (0f) r0 += r6 last_idx 24 first_idx 19 regs=40 stack=0 before 23: (bf) r1 = r0 regs=40 stack=0 before 22: (27) r6 *= 8192 regs=40 stack=0 before 21: (77) r6 >>= 10 regs=40 stack=0 before 19: (55) if r0 != 0x0 goto pc+1 parent didn't have regs=40 stack=0 marks: R0_rw=map_value_or_null(id=1,off=0,ks=4,vs=48,imm=0) R6_rw=P0 R7=0 R8=0 R9=0 R10=fp0 fp-8=mmmm???? last_idx 18 first_idx 9 regs=40 stack=0 before 18: (85) call bpf_map_lookup_elem#1 regs=40 stack=0 before 17: (07) r2 += -4 regs=40 stack=0 before 16: (bf) r2 = r10 regs=40 stack=0 before 15: (bf) r1 = r4 regs=40 stack=0 before 13: (18) r4 = 0xffff9290dc5bfe00 regs=40 stack=0 before 12: (63) *(u32 *)(r10 -4) = r0 regs=40 stack=0 before 11: (b7) r0 = 0 regs=40 stack=0 before 10: (b7) r6 = 0 25: (79) r3 = *(u64 *)(r0 +0) ; R0_w=map_value(off=0,ks=4,vs=48,imm=0) R3_w=scalar() 26: (7b) *(u64 *)(r1 +0) = r3 ; R1_w=map_value(off=0,ks=4,vs=48,imm=0) R3_w=scalar() 27: (95) exit from 9 to 11: R1=ctx(off=0,imm=0) R6=0 R7=0 R8=0 R9=0 R10=fp0 11: (b7) r0 = 0 ; R0_w=0 12: (63) *(u32 *)(r10 -4) = r0 last_idx 12 first_idx 11 regs=1 stack=0 before 11: (b7) r0 = 0 13: R0_w=0 R10=fp0 fp-8=0000???? 13: (18) r4 = 0xffff9290dc5bfe00 ; R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 15: (bf) r1 = r4 ; R1_w=map_ptr(off=0,ks=4,vs=48,imm=0) R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 16: (bf) r2 = r10 ; R2_w=fp0 R10=fp0 17: (07) r2 += -4 ; R2_w=fp-4 18: (85) call bpf_map_lookup_elem#1 frame 0: propagating r6 last_idx 19 first_idx 11 regs=40 stack=0 before 18: (85) call bpf_map_lookup_elem#1 regs=40 stack=0 before 17: (07) r2 += -4 regs=40 stack=0 before 16: (bf) r2 = r10 regs=40 stack=0 before 15: (bf) r1 = r4 regs=40 stack=0 before 13: (18) r4 = 0xffff9290dc5bfe00 regs=40 stack=0 before 12: (63) *(u32 *)(r10 -4) = r0 regs=40 stack=0 before 11: (b7) r0 = 0 parent didn't have regs=40 stack=0 marks: R1=ctx(off=0,imm=0) R6_r=P0 R7=0 R8=0 R9=0 R10=fp0 last_idx 9 first_idx 9 regs=40 stack=0 before 9: (bd) if r6 <= r9 goto pc+1 parent didn't have regs=240 stack=0 marks: R1=ctx(off=0,imm=0) R6_rw=Pscalar() R7_w=0 R8_w=0 R9_rw=P0 R10=fp0 last_idx 8 first_idx 0 regs=240 stack=0 before 8: (b7) r9 = 0 regs=40 stack=0 before 7: (97) r6 %= 1 regs=40 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 regs=240 stack=0 before 5: (05) goto pc+0 regs=240 stack=0 before 4: (97) r6 %= 1025 regs=240 stack=0 before 3: (b7) r9 = -2147483648 regs=40 stack=0 before 2: (b7) r8 = 0 regs=40 stack=0 before 1: (b7) r7 = 0 regs=40 stack=0 before 0: (b7) r6 = 1024 19: safe from 6 to 9: R1=ctx(off=0,imm=0) R6_w=scalar(umax=18446744071562067968) R7_w=0 R8_w=0 R9_w=-2147483648 R10=fp0 9: (bd) if r6 <= r9 goto pc+1 last_idx 9 first_idx 0 regs=40 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 regs=240 stack=0 before 5: (05) goto pc+0 regs=240 stack=0 before 4: (97) r6 %= 1025 regs=240 stack=0 before 3: (b7) r9 = -2147483648 regs=40 stack=0 before 2: (b7) r8 = 0 regs=40 stack=0 before 1: (b7) r7 = 0 regs=40 stack=0 before 0: (b7) r6 = 1024 last_idx 9 first_idx 0 regs=200 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 regs=240 stack=0 before 5: (05) goto pc+0 regs=240 stack=0 before 4: (97) r6 %= 1025 regs=240 stack=0 before 3: (b7) r9 = -2147483648 regs=40 stack=0 before 2: (b7) r8 = 0 regs=40 stack=0 before 1: (b7) r7 = 0 regs=40 stack=0 before 0: (b7) r6 = 1024 11: R6=scalar(umax=18446744071562067968) R9=-2147483648 11: (b7) r0 = 0 ; R0_w=0 12: (63) *(u32 *)(r10 -4) = r0 last_idx 12 first_idx 11 regs=1 stack=0 before 11: (b7) r0 = 0 13: R0_w=0 R10=fp0 fp-8=0000???? 13: (18) r4 = 0xffff9290dc5bfe00 ; R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 15: (bf) r1 = r4 ; R1_w=map_ptr(off=0,ks=4,vs=48,imm=0) R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 16: (bf) r2 = r10 ; R2_w=fp0 R10=fp0 17: (07) r2 += -4 ; R2_w=fp-4 18: (85) call bpf_map_lookup_elem#1 ; R0_w=map_value_or_null(id=3,off=0,ks=4,vs=48,imm=0) 19: (55) if r0 != 0x0 goto pc+1 ; R0_w=0 20: (95) exit from 19 to 21: R0=map_value(off=0,ks=4,vs=48,imm=0) R6=scalar(umax=18446744071562067968) R7=0 R8=0 R9=-2147483648 R10=fp0 fp-8=mmmm???? 21: (77) r6 >>= 10 ; R6_w=scalar(umax=18014398507384832,var_off=(0x0; 0x3fffffffffffff)) 22: (27) r6 *= 8192 ; R6_w=scalar(smax=9223372036854767616,umax=18446744073709543424,var_off=(0x0; 0xffffffffffffe000),s32_max=2147475456,u32_max=-8192) 23: (bf) r1 = r0 ; R0=map_value(off=0,ks=4,vs=48,imm=0) R1_w=map_value(off=0,ks=4,vs=48,imm=0) 24: (0f) r0 += r6 last_idx 24 first_idx 21 regs=40 stack=0 before 23: (bf) r1 = r0 regs=40 stack=0 before 22: (27) r6 *= 8192 regs=40 stack=0 before 21: (77) r6 >>= 10 parent didn't have regs=40 stack=0 marks: R0_rw=map_value(off=0,ks=4,vs=48,imm=0) R6_r=Pscalar(umax=18446744071562067968) R7=0 R8=0 R9=-2147483648 R10=fp0 fp-8=mmmm???? last_idx 19 first_idx 11 regs=40 stack=0 before 19: (55) if r0 != 0x0 goto pc+1 regs=40 stack=0 before 18: (85) call bpf_map_lookup_elem#1 regs=40 stack=0 before 17: (07) r2 += -4 regs=40 stack=0 before 16: (bf) r2 = r10 regs=40 stack=0 before 15: (bf) r1 = r4 regs=40 stack=0 before 13: (18) r4 = 0xffff9290dc5bfe00 regs=40 stack=0 before 12: (63) *(u32 *)(r10 -4) = r0 regs=40 stack=0 before 11: (b7) r0 = 0 parent didn't have regs=40 stack=0 marks: R1=ctx(off=0,imm=0) R6_rw=Pscalar(umax=18446744071562067968) R7_w=0 R8_w=0 R9_w=-2147483648 R10=fp0 last_idx 9 first_idx 0 regs=40 stack=0 before 9: (bd) if r6 <= r9 goto pc+1 regs=240 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 regs=240 stack=0 before 5: (05) goto pc+0 regs=240 stack=0 before 4: (97) r6 %= 1025 regs=240 stack=0 before 3: (b7) r9 = -2147483648 regs=40 stack=0 before 2: (b7) r8 = 0 regs=40 stack=0 before 1: (b7) r7 = 0 regs=40 stack=0 before 0: (b7) r6 = 1024 math between map_value pointer and register with unbounded min value is not allowed verification time 886 usec stack depth 4 processed 49 insns (limit 1000000) max_states_per_insn 1 total_states 5 peak_states 5 mark_read 2 Fixes: b5dc0163d8fd ("bpf: precise scalar_value tracking") Reported-by: Juan Jose Lopez Jaimez <jjlopezjaimez(a)google.com> Reported-by: Meador Inge <meadori(a)google.com> Reported-by: Simon Scannell <simonscannell(a)google.com> Reported-by: Nenad Stojanovski <thenenadx(a)google.com> Signed-off-by: Daniel Borkmann <daniel(a)iogearbox.net> Co-developed-by: Andrii Nakryiko <andrii(a)kernel.org> Signed-off-by: Andrii Nakryiko <andrii(a)kernel.org> Reviewed-by: John Fastabend <john.fastabend(a)gmail.com> Reviewed-by: Juan Jose Lopez Jaimez <jjlopezjaimez(a)google.com> Reviewed-by: Meador Inge <meadori(a)google.com> Reviewed-by: Simon Scannell <simonscannell(a)google.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Pu Lehui <pulehui(a)huawei.com> Reviewed-by: Xu Kuohai <xukuohai(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> --- kernel/bpf/verifier.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c91533a54121..407f2263216d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1923,6 +1923,21 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, } } else if (opcode == BPF_EXIT) { return -ENOTSUPP; + } else if (BPF_SRC(insn->code) == BPF_X) { + if (!(*reg_mask & (dreg | sreg))) + return 0; + /* dreg <cond> sreg + * Both dreg and sreg need precision before + * this insn. If only sreg was marked precise + * before it would be equally necessary to + * propagate it to dreg. + */ + *reg_mask |= (sreg | dreg); + /* else dreg <cond> K + * Only dreg still needs precision before + * this insn, so for the K-based conditional + * there is nothing new to be marked. + */ } } else if (class == BPF_LD) { if (!(*reg_mask & dreg)) -- 2.25.1

2 1

[PATCH 4.19 1/3] net: tap: check vlan with eth_type_vlan() method
by Yongqiang Liu 06 Jul '23

06 Jul '23

From: Menglong Dong <dong.menglong(a)zte.com.cn> mainline inclusion from mainline-v5.12-rc1-dontuse commit b69df2608281b71575fbb3b9f426dbcc4be8a700 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7IIRH CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- Replace some checks for ETH_P_8021Q and ETH_P_8021AD in drivers/net/tap.c with eth_type_vlan. Signed-off-by: Menglong Dong <dong.menglong(a)zte.com.cn> Link: https://lore.kernel.org/r/20210115023238.4681-1-dong.menglong@zte.com.cn Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Liu Jian <liujian56(a)huawei.com> Conflicts: drivers/net/tap.c Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/net/tap.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/tap.c b/drivers/net/tap.c index 43012a195b71..bea824a92974 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -715,8 +715,7 @@ static ssize_t tap_get_user(struct tap_queue *q, struct msghdr *m, skb_probe_transport_header(skb, ETH_HLEN); /* Move network header to the right position for VLAN tagged packets */ - if ((skb->protocol == htons(ETH_P_8021Q) || - skb->protocol == htons(ETH_P_8021AD)) && + if (eth_type_vlan(skb->protocol) && __vlan_get_protocol(skb, skb->protocol, &depth) != 0) skb_set_network_header(skb, depth); -- 2.25.1

1 2

[PATCH OLK-5.10] Huawei BMA: To fix the bug in the iBMA driver code
by Jialin Zhang 06 Jul '23

06 Jul '23

From: Huajingjing <huajingjing1(a)huawei.com> driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7FQ05 CVE: NA ----------------------------------------- 1. a low probability that iBMA cdev_veth driver causes softlockup problem 2. a low probability that iBMA veth driver causes soft interrupt loops 3. Change the iBMA driver version. Signed-off-by: Huajingjing <huajingjing1(a)huawei.com> Reviewed-by: Chenjiesong <chenjiesong(a)huawei.com> Reviewed-by: Huangjunhua <huangjunhua14(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- .../net/ethernet/huawei/bma/cdev_drv/bma_cdev.c | 2 +- .../bma/cdev_veth_drv/virtual_cdev_eth_net.c | 14 ++++++++------ drivers/net/ethernet/huawei/bma/edma_drv/bma_pci.h | 2 +- .../ethernet/huawei/bma/kbox_drv/kbox_include.h | 2 +- drivers/net/ethernet/huawei/bma/veth_drv/veth_hb.c | 10 +++++++++- drivers/net/ethernet/huawei/bma/veth_drv/veth_hb.h | 2 +- 6 files changed, 21 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/huawei/bma/cdev_drv/bma_cdev.c b/drivers/net/ethernet/huawei/bma/cdev_drv/bma_cdev.c index 9468a5a0c768..9022ceaa8f47 100644 --- a/drivers/net/ethernet/huawei/bma/cdev_drv/bma_cdev.c +++ b/drivers/net/ethernet/huawei/bma/cdev_drv/bma_cdev.c @@ -28,7 +28,7 @@ #ifdef DRV_VERSION #define CDEV_VERSION MICRO_TO_STR(DRV_VERSION) #else -#define CDEV_VERSION "0.3.5" +#define CDEV_VERSION "0.3.6" #endif #define CDEV_DEFAULT_NUM 4 diff --git a/drivers/net/ethernet/huawei/bma/cdev_veth_drv/virtual_cdev_eth_net.c b/drivers/net/ethernet/huawei/bma/cdev_veth_drv/virtual_cdev_eth_net.c index d8c3ab655566..e6dbec7073e4 100644 --- a/drivers/net/ethernet/huawei/bma/cdev_veth_drv/virtual_cdev_eth_net.c +++ b/drivers/net/ethernet/huawei/bma/cdev_veth_drv/virtual_cdev_eth_net.c @@ -667,6 +667,7 @@ static int edma_veth_copy_full_packet(struct edma_eth_dev_s *eth_dev, u8 *packet, u32 len) { unsigned int count = 0; + unsigned long flags = 0; u8 *ptr = NULL; LOG(DLOG_DEBUG, "Recv full packet, len %u.", len); @@ -674,14 +675,14 @@ static int edma_veth_copy_full_packet(struct edma_eth_dev_s *eth_dev, ptr = kmalloc(len, GFP_ATOMIC); if (ptr) { /* lock the queue. */ - spin_lock(&eth_dev->rx_queue_lock); + spin_lock_irqsave(&eth_dev->rx_queue_lock, flags); count = edma_veth_get_ring_buf_count(eth_dev->rx_packet_head, eth_dev->rx_packet_tail, MAX_RXTX_PACKET_LEN); if (count >= (MAX_RXTX_PACKET_LEN - 1)) { LOG(DLOG_DEBUG, "The rx queue is full."); - spin_unlock(&eth_dev->rx_queue_lock); + spin_unlock_irqrestore(&eth_dev->rx_queue_lock, flags); kfree(ptr); return -EBUSY; } @@ -692,7 +693,7 @@ static int edma_veth_copy_full_packet(struct edma_eth_dev_s *eth_dev, eth_dev->rx_packet_tail = (eth_dev->rx_packet_tail + 1) % MAX_RXTX_PACKET_LEN; - spin_unlock(&eth_dev->rx_queue_lock); + spin_unlock_irqrestore(&eth_dev->rx_queue_lock, flags); return 0; } @@ -1672,16 +1673,17 @@ static ssize_t cdev_copy_packet_to_user(struct edma_eth_dev_s *dev, unsigned char *packet = NULL; unsigned char *start = NULL; unsigned int free_packet = 0; + unsigned long flags = 0; ssize_t length = (ssize_t)count; ssize_t left; LOG(DLOG_DEBUG, "rx_packet_head:%u, rx_packet_tail: %u", dev->rx_packet_head, dev->rx_packet_tail); - spin_lock(&dev->rx_queue_lock); + spin_lock_irqsave(&dev->rx_queue_lock, flags); if (!cdev_check_ring_recv()) { - spin_unlock(&dev->rx_queue_lock); + spin_unlock_irqrestore(&dev->rx_queue_lock, flags); return -EAGAIN; } @@ -1712,7 +1714,7 @@ static ssize_t cdev_copy_packet_to_user(struct edma_eth_dev_s *dev, MAX_RXTX_PACKET_LEN; } - spin_unlock(&dev->rx_queue_lock); + spin_unlock_irqrestore(&dev->rx_queue_lock, flags); if (length > 0 && copy_to_user(data, start, length)) { LOG(DLOG_DEBUG, "Failed to copy to user, skip this message."); diff --git a/drivers/net/ethernet/huawei/bma/edma_drv/bma_pci.h b/drivers/net/ethernet/huawei/bma/edma_drv/bma_pci.h index 639ed4e58a8b..9eca34e6d47d 100644 --- a/drivers/net/ethernet/huawei/bma/edma_drv/bma_pci.h +++ b/drivers/net/ethernet/huawei/bma/edma_drv/bma_pci.h @@ -71,7 +71,7 @@ struct bma_pci_dev_s { #ifdef DRV_VERSION #define BMA_VERSION MICRO_TO_STR(DRV_VERSION) #else -#define BMA_VERSION "0.3.5" +#define BMA_VERSION "0.3.6" #endif #ifdef CONFIG_ARM64 diff --git a/drivers/net/ethernet/huawei/bma/kbox_drv/kbox_include.h b/drivers/net/ethernet/huawei/bma/kbox_drv/kbox_include.h index b027306e52c1..5406246ef548 100644 --- a/drivers/net/ethernet/huawei/bma/kbox_drv/kbox_include.h +++ b/drivers/net/ethernet/huawei/bma/kbox_drv/kbox_include.h @@ -23,7 +23,7 @@ #ifdef DRV_VERSION #define KBOX_VERSION MICRO_TO_STR(DRV_VERSION) #else -#define KBOX_VERSION "0.3.5" +#define KBOX_VERSION "0.3.6" #endif #define UNUSED(x) (x = x) diff --git a/drivers/net/ethernet/huawei/bma/veth_drv/veth_hb.c b/drivers/net/ethernet/huawei/bma/veth_drv/veth_hb.c index 7705bb919ead..6a7175c6206c 100644 --- a/drivers/net/ethernet/huawei/bma/veth_drv/veth_hb.c +++ b/drivers/net/ethernet/huawei/bma/veth_drv/veth_hb.c @@ -87,6 +87,12 @@ u32 g_testlbk; struct bspveth_device g_bspveth_dev = {}; +/* g_shutdown_flag is used to prevent veth_shutdown_task + * from being preempted by veth_dma_tx_timer_do_H. + * The default value is 0.The value 1 indicates that veth_shutdown_flag cannot be preempted, + * and the value 0 indicates that veth_shutdown_task can be preempted. + */ +static int g_shutdown_flag; static int veth_int_handler(struct notifier_block *pthis, unsigned long ev, void *unuse); @@ -1607,6 +1613,7 @@ void veth_netdev_exit(void) static void veth_shutdown_task(struct work_struct *work) { struct net_device *netdev = g_bspveth_dev.pnetdev; + g_shutdown_flag = 1; VETH_LOG(DLOG_ERROR, "veth is going down, please restart it manual\n"); @@ -1626,6 +1633,7 @@ static void veth_shutdown_task(struct work_struct *work) (void)veth_dmatimer_close_H(); } + g_shutdown_flag = 0; } s32 veth_netdev_init(void) @@ -1728,7 +1736,7 @@ void veth_dma_tx_timer_do_H(unsigned long data) rxret = veth_dma_task_H(BSPVETH_RX); - if (txret == BSP_ERR_AGAIN || rxret == BSP_ERR_AGAIN) { + if ((txret == BSP_ERR_AGAIN || rxret == BSP_ERR_AGAIN) && (g_shutdown_flag == 0)) { #ifndef USE_TASKLET (void)mod_timer(&g_bspveth_dev.dmatimer, jiffies_64); #else diff --git a/drivers/net/ethernet/huawei/bma/veth_drv/veth_hb.h b/drivers/net/ethernet/huawei/bma/veth_drv/veth_hb.h index 503636549320..777a9bbc4ac1 100644 --- a/drivers/net/ethernet/huawei/bma/veth_drv/veth_hb.h +++ b/drivers/net/ethernet/huawei/bma/veth_drv/veth_hb.h @@ -31,7 +31,7 @@ extern "C" { #ifdef DRV_VERSION #define VETH_VERSION MICRO_TO_STR(DRV_VERSION) #else -#define VETH_VERSION "0.3.5" +#define VETH_VERSION "0.3.6" #endif #define MODULE_NAME "veth" -- 2.25.1

2 1

[PATCH OLK-5.10 v2 0/5] jbd2: fix several checkpoint
by Zhihao Cheng 05 Jul '23

05 Jul '23

Zhang Yi (4): jbd2: remove journal_clean_one_cp_list() jbd2: fix a race when checking checkpoint buffer busy jbd2: remove __journal_try_to_free_buffer() jbd2: fix checkpoint cleanup performance regression Zhihao Cheng (1): jbd2: Fix wrongly judgement for buffer head removing while doing checkpoint fs/jbd2/checkpoint.c | 147 ++++++++++++++++++------------------ fs/jbd2/transaction.c | 40 ++-------- include/linux/jbd2.h | 1 + include/trace/events/jbd2.h | 12 +-- 4 files changed, 87 insertions(+), 113 deletions(-) -- 2.31.1

2 6

[PATCH OLK-5.10 v2] io_uring: hold uring mutex around poll removal
by Zhong Jinghua 05 Jul '23

05 Jul '23

From: Jens Axboe <axboe(a)kernel.dk> stable inclusion from stable-v5.10.185 commit 4716c73b188566865bdd79c3a6709696a224ac04 category: bugfix bugzilla: 188954, https://gitee.com/src-openeuler/kernel/issues/I7GVI5?from=project-issue CVE: CVE-2023-3389 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ---------------------------------------- Snipped from commit 9ca9fb24d5febccea354089c41f96a8ad0d853f8 upstream. While reworking the poll hashing in the v6.0 kernel, we ended up grabbing the ctx->uring_lock in poll update/removal. This also fixed a bug with linked timeouts racing with timeout expiry and poll removal. Bring back just the locking fix for that. Reported-and-tested-by: Querijn Voet <querijnqyn(a)gmail.com> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Zhong Jinghua <zhongjinghua(a)huawei.com> --- v2: cve number modify. io_uring/io_uring.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 67cb9d6ec4ac..f6af5ceb517e 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -5811,6 +5811,8 @@ static int io_poll_update(struct io_kiocb *req, unsigned int issue_flags) struct io_kiocb *preq; int ret2, ret = 0; + io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + spin_lock(&ctx->completion_lock); preq = io_poll_find(ctx, req->poll_update.old_user_data, true); if (!preq || !io_poll_disarm(preq)) { @@ -5842,6 +5844,7 @@ static int io_poll_update(struct io_kiocb *req, unsigned int issue_flags) req_set_fail(req); /* complete update request, we're done with it */ io_req_complete(req, ret); + io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); return 0; } -- 2.31.1

2 1

[PATCH openEuler-1.0-LTS 0/5] jbd2: fix several checkpoint
by Zhihao Cheng 05 Jul '23

05 Jul '23

Zhang Yi (4): jbd2: remove journal_clean_one_cp_list() jbd2: fix a race when checking checkpoint buffer busy jbd2: remove __journal_try_to_free_buffer() jbd2: fix checkpoint cleanup performance regression Zhihao Cheng (1): jbd2: Fix wrongly judgement for buffer head removing while doing checkpoint fs/jbd2/checkpoint.c | 147 ++++++++++++++++++------------------ fs/jbd2/transaction.c | 40 ++-------- include/linux/jbd2.h | 1 + include/trace/events/jbd2.h | 12 +-- 4 files changed, 87 insertions(+), 113 deletions(-) -- 2.31.1

2 6

[PATCH OLK-5.10] io_uring: hold uring mutex around poll removal
by Zhong Jinghua 05 Jul '23

05 Jul '23

From: Jens Axboe <axboe(a)kernel.dk> stable inclusion from stable-v5.10.185 commit 4716c73b188566865bdd79c3a6709696a224ac04 category: bugfix bugzilla: 188954, https://gitee.com/src-openeuler/kernel/issues/I5X879?from=project-issue CVE: CVE-2022-3238 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ---------------------------------------- Snipped from commit 9ca9fb24d5febccea354089c41f96a8ad0d853f8 upstream. While reworking the poll hashing in the v6.0 kernel, we ended up grabbing the ctx->uring_lock in poll update/removal. This also fixed a bug with linked timeouts racing with timeout expiry and poll removal. Bring back just the locking fix for that. Reported-and-tested-by: Querijn Voet <querijnqyn(a)gmail.com> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Zhong Jinghua <zhongjinghua(a)huawei.com> --- io_uring/io_uring.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 67cb9d6ec4ac..f6af5ceb517e 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -5811,6 +5811,8 @@ static int io_poll_update(struct io_kiocb *req, unsigned int issue_flags) struct io_kiocb *preq; int ret2, ret = 0; + io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + spin_lock(&ctx->completion_lock); preq = io_poll_find(ctx, req->poll_update.old_user_data, true); if (!preq || !io_poll_disarm(preq)) { @@ -5842,6 +5844,7 @@ static int io_poll_update(struct io_kiocb *req, unsigned int issue_flags) req_set_fail(req); /* complete update request, we're done with it */ io_req_complete(req, ret); + io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); return 0; } -- 2.31.1

2 1

[PATCH OLK-5.10] io_uring: hold uring mutex around poll removal
by Zhong Jinghua 05 Jul '23

05 Jul '23

From: Jens Axboe <axboe(a)kernel.dk> stable inclusion from stable-v5.10.185 commit 4716c73b188566865bdd79c3a6709696a224ac04 category: bugfix bugzilla: 188954, https://gitee.com/src-openeuler/kernel/issues/I5X879?from=project-issue CVE: CVE-2022-3238 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ---------------------------------------- Snipped from commit 9ca9fb24d5febccea354089c41f96a8ad0d853f8 upstream. While reworking the poll hashing in the v6.0 kernel, we ended up grabbing the ctx->uring_lock in poll update/removal. This also fixed a bug with linked timeouts racing with timeout expiry and poll removal. Bring back just the locking fix for that. Reported-and-tested-by: Querijn Voet <querijnqyn(a)gmail.com> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Zhong Jinghua <zhongjinghua(a)huawei.com> --- io_uring/io_uring.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 67cb9d6ec4ac..f6af5ceb517e 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -5811,6 +5811,8 @@ static int io_poll_update(struct io_kiocb *req, unsigned int issue_flags) struct io_kiocb *preq; int ret2, ret = 0; + io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + spin_lock(&ctx->completion_lock); preq = io_poll_find(ctx, req->poll_update.old_user_data, true); if (!preq || !io_poll_disarm(preq)) { @@ -5842,6 +5844,7 @@ static int io_poll_update(struct io_kiocb *req, unsigned int issue_flags) req_set_fail(req); /* complete update request, we're done with it */ io_req_complete(req, ret); + io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); return 0; } -- 2.31.1

2 1

[PATCH openEuler-1.0-LTS 1/3] nbd: fold nbd config initialization into nbd_alloc_config()
by Yongqiang Liu 05 Jul '23

05 Jul '23

From: Yu Kuai <yukuai3(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7EENU CVE: NA ---------------------------------------- There are no functional changes, make the code cleaner and prepare to fix null-ptr-dereference while accessing 'nbd->config'. Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> conflict: drivers/block/nbd.c Signed-off-by: Zhong Jinghua <zhongjinghua(a)huawei.com> Reviewed-by: Yu Kuai <yukuai3(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/block/nbd.c | 41 +++++++++++++++++++---------------------- 1 file changed, 19 insertions(+), 22 deletions(-) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index c306e9ffdd08..602679ce390f 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1469,17 +1469,20 @@ static int nbd_ioctl(struct block_device *bdev, fmode_t mode, return error; } -static struct nbd_config *nbd_alloc_config(void) +static int nbd_alloc_and_init_config(struct nbd_device *nbd) { struct nbd_config *config; + if (WARN_ON(nbd->config)) + return -EINVAL; + if (!try_module_get(THIS_MODULE)) - return ERR_PTR(-ENODEV); + return -ENODEV; config = kzalloc(sizeof(struct nbd_config), GFP_NOFS); if (!config) { module_put(THIS_MODULE); - return ERR_PTR(-ENOMEM); + return -ENOMEM; } atomic_set(&config->recv_threads, 0); @@ -1487,7 +1490,10 @@ static struct nbd_config *nbd_alloc_config(void) init_waitqueue_head(&config->conn_wait); config->blksize = NBD_DEF_BLKSIZE; atomic_set(&config->live_connections, 0); - return config; + nbd->config = config; + refcount_set(&nbd->config_refs, 1); + + return 0; } static int nbd_open(struct block_device *bdev, fmode_t mode) @@ -1506,21 +1512,17 @@ static int nbd_open(struct block_device *bdev, fmode_t mode) goto out; } if (!refcount_inc_not_zero(&nbd->config_refs)) { - struct nbd_config *config; - mutex_lock(&nbd->config_lock); if (refcount_inc_not_zero(&nbd->config_refs)) { mutex_unlock(&nbd->config_lock); goto out; } - config = nbd_alloc_config(); - if (IS_ERR(config)) { - ret = PTR_ERR(config); + ret = nbd_alloc_and_init_config(nbd); + if (ret) { mutex_unlock(&nbd->config_lock); goto out; } - nbd->config = config; - refcount_set(&nbd->config_refs, 1); + refcount_inc(&nbd->refs); mutex_unlock(&nbd->config_lock); bdev->bd_invalidated = 1; @@ -1924,22 +1926,17 @@ static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info) printk(KERN_ERR "nbd: nbd%d already in use\n", index); return -EBUSY; } - if (WARN_ON(nbd->config)) { - mutex_unlock(&nbd->config_lock); - nbd_put(nbd); - return -EINVAL; - } - config = nbd_alloc_config(); - if (IS_ERR(config)) { + + ret = nbd_alloc_and_init_config(nbd); + if (ret) { mutex_unlock(&nbd->config_lock); nbd_put(nbd); printk(KERN_ERR "nbd: couldn't allocate config\n"); - return PTR_ERR(config); + return ret; } - nbd->config = config; - refcount_set(&nbd->config_refs, 1); - set_bit(NBD_RT_BOUND, &config->runtime_flags); + config = nbd->config; + set_bit(NBD_RT_BOUND, &config->runtime_flags); if (info->attrs[NBD_ATTR_SIZE_BYTES]) { u64 bytes = nla_get_u64(info->attrs[NBD_ATTR_SIZE_BYTES]); ret = nbd_set_size(nbd, bytes, config->blksize); -- 2.25.1

1 2