From 711aef1bbf88212a21f7103e88f397b47a528805 Mon Sep 17 00:00:00 2001 From: Wang YanQing Date: Sat, 27 Apr 2019 16:28:26 +0800 Subject: [PATCH 01/29] bpf, x32: Fix bug for BPF_JMP | {BPF_JSGT, BPF_JSLE, BPF_JSLT, BPF_JSGE} The current method to compare 64-bit numbers for conditional jump is: 1) Compare the high 32-bit first. 2) If the high 32-bit isn't the same, then goto step 4. 3) Compare the low 32-bit. 4) Check the desired condition. This method is right for unsigned comparison, but it is buggy for signed comparison, because it does signed comparison for low 32-bit too. There is only one sign bit in 64-bit number, that is the MSB in the 64-bit number, it is wrong to treat low 32-bit as signed number and do the signed comparison for it. This patch fixes the bug and adds a testcase in selftests/bpf for such bug. Signed-off-by: Wang YanQing Signed-off-by: Daniel Borkmann --- arch/x86/net/bpf_jit_comp32.c | 217 ++++++++++++++++----- tools/testing/selftests/bpf/verifier/jit.c | 19 ++ 2 files changed, 185 insertions(+), 51 deletions(-) diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index 0d9cdffce6ac..8097b88d744f 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -117,6 +117,8 @@ static bool is_simm32(s64 value) #define IA32_JLE 0x7E #define IA32_JG 0x7F +#define COND_JMP_OPCODE_INVALID (0xFF) + /* * Map eBPF registers to IA32 32bit registers or stack scratch space. * @@ -1613,6 +1615,75 @@ static inline void emit_push_r64(const u8 src[], u8 **pprog) *pprog = prog; } +static u8 get_cond_jmp_opcode(const u8 op, bool is_cmp_lo) +{ + u8 jmp_cond; + + /* Convert BPF opcode to x86 */ + switch (op) { + case BPF_JEQ: + jmp_cond = IA32_JE; + break; + case BPF_JSET: + case BPF_JNE: + jmp_cond = IA32_JNE; + break; + case BPF_JGT: + /* GT is unsigned '>', JA in x86 */ + jmp_cond = IA32_JA; + break; + case BPF_JLT: + /* LT is unsigned '<', JB in x86 */ + jmp_cond = IA32_JB; + break; + case BPF_JGE: + /* GE is unsigned '>=', JAE in x86 */ + jmp_cond = IA32_JAE; + break; + case BPF_JLE: + /* LE is unsigned '<=', JBE in x86 */ + jmp_cond = IA32_JBE; + break; + case BPF_JSGT: + if (!is_cmp_lo) + /* Signed '>', GT in x86 */ + jmp_cond = IA32_JG; + else + /* GT is unsigned '>', JA in x86 */ + jmp_cond = IA32_JA; + break; + case BPF_JSLT: + if (!is_cmp_lo) + /* Signed '<', LT in x86 */ + jmp_cond = IA32_JL; + else + /* LT is unsigned '<', JB in x86 */ + jmp_cond = IA32_JB; + break; + case BPF_JSGE: + if (!is_cmp_lo) + /* Signed '>=', GE in x86 */ + jmp_cond = IA32_JGE; + else + /* GE is unsigned '>=', JAE in x86 */ + jmp_cond = IA32_JAE; + break; + case BPF_JSLE: + if (!is_cmp_lo) + /* Signed '<=', LE in x86 */ + jmp_cond = IA32_JLE; + else + /* LE is unsigned '<=', JBE in x86 */ + jmp_cond = IA32_JBE; + break; + default: /* to silence GCC warning */ + jmp_cond = COND_JMP_OPCODE_INVALID; + break; + } + + return jmp_cond; +} + static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, int oldproglen, struct jit_context *ctx) { @@ -2069,10 +2140,6 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, case BPF_JMP | BPF_JLT | BPF_X: case BPF_JMP | BPF_JGE | BPF_X: case BPF_JMP | BPF_JLE | BPF_X: - case BPF_JMP | BPF_JSGT | BPF_X: - case BPF_JMP | BPF_JSLE | BPF_X: - case BPF_JMP | BPF_JSLT | BPF_X: - case BPF_JMP | BPF_JSGE | BPF_X: case BPF_JMP32 | BPF_JEQ | BPF_X: case BPF_JMP32 | BPF_JNE | BPF_X: case BPF_JMP32 | BPF_JGT | BPF_X: @@ -2118,6 +2185,40 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, EMIT2(0x39, add_2reg(0xC0, dreg_lo, sreg_lo)); goto emit_cond_jmp; } + case BPF_JMP | BPF_JSGT | BPF_X: + case BPF_JMP | BPF_JSLE | BPF_X: + case BPF_JMP | BPF_JSLT | BPF_X: + case BPF_JMP | BPF_JSGE | BPF_X: { + u8 dreg_lo = dstk ? IA32_EAX : dst_lo; + u8 dreg_hi = dstk ? IA32_EDX : dst_hi; + u8 sreg_lo = sstk ? IA32_ECX : src_lo; + u8 sreg_hi = sstk ? IA32_EBX : src_hi; + + if (dstk) { + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(dst_lo)); + EMIT3(0x8B, + add_2reg(0x40, IA32_EBP, + IA32_EDX), + STACK_VAR(dst_hi)); + } + + if (sstk) { + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX), + STACK_VAR(src_lo)); + EMIT3(0x8B, + add_2reg(0x40, IA32_EBP, + IA32_EBX), + STACK_VAR(src_hi)); + } + + /* cmp dreg_hi,sreg_hi */ + EMIT2(0x39, add_2reg(0xC0, dreg_hi, sreg_hi)); + EMIT2(IA32_JNE, 10); + /* cmp dreg_lo,sreg_lo */ + EMIT2(0x39, add_2reg(0xC0, dreg_lo, sreg_lo)); + goto emit_cond_jmp_signed; + } case BPF_JMP | BPF_JSET | BPF_X: case BPF_JMP32 | BPF_JSET | BPF_X: { bool is_jmp64 = BPF_CLASS(insn->code) == BPF_JMP; @@ -2194,10 +2295,6 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, case BPF_JMP | BPF_JLT | BPF_K: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JLE | BPF_K: - case BPF_JMP | BPF_JSGT | BPF_K: - case BPF_JMP | BPF_JSLE | BPF_K: - case BPF_JMP | BPF_JSLT | BPF_K: - case BPF_JMP | BPF_JSGE | BPF_K: case BPF_JMP32 | BPF_JEQ | BPF_K: case BPF_JMP32 | BPF_JNE | BPF_K: case BPF_JMP32 | BPF_JGT | BPF_K: @@ -2238,50 +2335,9 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, /* cmp dreg_lo,sreg_lo */ EMIT2(0x39, add_2reg(0xC0, dreg_lo, sreg_lo)); -emit_cond_jmp: /* Convert BPF opcode to x86 */ - switch (BPF_OP(code)) { - case BPF_JEQ: - jmp_cond = IA32_JE; - break; - case BPF_JSET: - case BPF_JNE: - jmp_cond = IA32_JNE; - break; - case BPF_JGT: - /* GT is unsigned '>', JA in x86 */ - jmp_cond = IA32_JA; - break; - case BPF_JLT: - /* LT is unsigned '<', JB in x86 */ - jmp_cond = IA32_JB; - break; - case BPF_JGE: - /* GE is unsigned '>=', JAE in x86 */ - jmp_cond = IA32_JAE; - break; - case BPF_JLE: - /* LE is unsigned '<=', JBE in x86 */ - jmp_cond = IA32_JBE; - break; - case BPF_JSGT: - /* Signed '>', GT in x86 */ - jmp_cond = IA32_JG; - break; - case BPF_JSLT: - /* Signed '<', LT in x86 */ - jmp_cond = IA32_JL; - break; - case BPF_JSGE: - /* Signed '>=', GE in x86 */ - jmp_cond = IA32_JGE; - break; - case BPF_JSLE: - /* Signed '<=', LE in x86 */ - jmp_cond = IA32_JLE; - break; - default: /* to silence GCC warning */ +emit_cond_jmp: jmp_cond = get_cond_jmp_opcode(BPF_OP(code), false); + if (jmp_cond == COND_JMP_OPCODE_INVALID) return -EFAULT; - } jmp_offset = addrs[i + insn->off] - addrs[i]; if (is_imm8(jmp_offset)) { EMIT2(jmp_cond, jmp_offset); @@ -2291,7 +2347,66 @@ emit_cond_jmp: /* Convert BPF opcode to x86 */ pr_err("cond_jmp gen bug %llx\n", jmp_offset); return -EFAULT; } + break; + } + case BPF_JMP | BPF_JSGT | BPF_K: + case BPF_JMP | BPF_JSLE | BPF_K: + case BPF_JMP | BPF_JSLT | BPF_K: + case BPF_JMP | BPF_JSGE | BPF_K: { + u8 dreg_lo = dstk ? IA32_EAX : dst_lo; + u8 dreg_hi = dstk ? IA32_EDX : dst_hi; + u8 sreg_lo = IA32_ECX; + u8 sreg_hi = IA32_EBX; + u32 hi; + if (dstk) { + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(dst_lo)); + EMIT3(0x8B, + add_2reg(0x40, IA32_EBP, + IA32_EDX), + STACK_VAR(dst_hi)); + } + + /* mov ecx,imm32 */ + EMIT2_off32(0xC7, add_1reg(0xC0, IA32_ECX), imm32); + hi = imm32 & (1 << 31) ? (u32)~0 : 0; + /* mov ebx,imm32 */ + EMIT2_off32(0xC7, add_1reg(0xC0, IA32_EBX), hi); + /* cmp dreg_hi,sreg_hi */ + EMIT2(0x39, add_2reg(0xC0, dreg_hi, sreg_hi)); + EMIT2(IA32_JNE, 10); + /* cmp dreg_lo,sreg_lo */ + EMIT2(0x39, add_2reg(0xC0, dreg_lo, sreg_lo)); + + /* + * For simplicity of branch offset computation, + * let's use fixed jump coding here. + */ +emit_cond_jmp_signed: /* Check the condition for low 32-bit comparison */ + jmp_cond = get_cond_jmp_opcode(BPF_OP(code), true); + if (jmp_cond == COND_JMP_OPCODE_INVALID) + return -EFAULT; + jmp_offset = addrs[i + insn->off] - addrs[i] + 8; + if (is_simm32(jmp_offset)) { + EMIT2_off32(0x0F, jmp_cond + 0x10, jmp_offset); + } else { + pr_err("cond_jmp gen bug %llx\n", jmp_offset); + return -EFAULT; + } + EMIT2(0xEB, 6); + + /* Check the condition for high 32-bit comparison */ + jmp_cond = get_cond_jmp_opcode(BPF_OP(code), false); + if (jmp_cond == COND_JMP_OPCODE_INVALID) + return -EFAULT; + jmp_offset = addrs[i + insn->off] - addrs[i]; + if (is_simm32(jmp_offset)) { + EMIT2_off32(0x0F, jmp_cond + 0x10, jmp_offset); + } else { + pr_err("cond_jmp gen bug %llx\n", jmp_offset); + return -EFAULT; + } break; } case BPF_JMP | BPF_JA: diff --git a/tools/testing/selftests/bpf/verifier/jit.c b/tools/testing/selftests/bpf/verifier/jit.c index be488b4495a3..c33adf344fae 100644 --- a/tools/testing/selftests/bpf/verifier/jit.c +++ b/tools/testing/selftests/bpf/verifier/jit.c @@ -86,3 +86,22 @@ .result = ACCEPT, .retval = 2, }, +{ + "jit: jsgt, jslt", + .insns = { + BPF_LD_IMM64(BPF_REG_1, 0x80000000ULL), + BPF_LD_IMM64(BPF_REG_2, 0x0ULL), + BPF_JMP_REG(BPF_JSGT, BPF_REG_1, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + + BPF_JMP_REG(BPF_JSLT, BPF_REG_2, BPF_REG_1, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 2, +}, From b9aa0b35d878dff9ed19f94101fe353a4de00cc4 Mon Sep 17 00:00:00 2001 From: Wang YanQing Date: Sun, 28 Apr 2019 10:33:02 +0800 Subject: [PATCH 02/29] bpf, x32: Fix bug for BPF_ALU64 | BPF_NEG The current implementation has two errors: 1: The second xor instruction will clear carry flag which is necessary for following sbb instruction. 2: The select coding for sbb instruction is wrong, the coding is "sbb dreg_hi,ecx", but what we need is "sbb ecx,dreg_hi". This patch rewrites the implementation and fixes the errors. This patch fixes below errors reported by bpf/test_verifier in x32 platform when the jit is enabled: " 0: (b4) w1 = 4 1: (b4) w2 = 4 2: (1f) r2 -= r1 3: (4f) r2 |= r1 4: (87) r2 = -r2 5: (c7) r2 s>>= 63 6: (5f) r1 &= r2 7: (bf) r0 = r1 8: (95) exit processed 9 insns (limit 131072), stack depth 0 0: (b4) w1 = 4 1: (b4) w2 = 4 2: (1f) r2 -= r1 3: (4f) r2 |= r1 4: (87) r2 = -r2 5: (c7) r2 s>>= 63 6: (5f) r1 &= r2 7: (bf) r0 = r1 8: (95) exit processed 9 insns (limit 131072), stack depth 0 ...... Summary: 1189 PASSED, 125 SKIPPED, 15 FAILED " Signed-off-by: Wang YanQing Signed-off-by: Daniel Borkmann --- arch/x86/net/bpf_jit_comp32.c | 19 ++++++------------- 1 file changed, 6 insertions(+), 13 deletions(-) diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index 8097b88d744f..b29e82f190c7 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -700,19 +700,12 @@ static inline void emit_ia32_neg64(const u8 dst[], bool dstk, u8 **pprog) STACK_VAR(dst_hi)); } - /* xor ecx,ecx */ - EMIT2(0x31, add_2reg(0xC0, IA32_ECX, IA32_ECX)); - /* sub dreg_lo,ecx */ - EMIT2(0x2B, add_2reg(0xC0, dreg_lo, IA32_ECX)); - /* mov dreg_lo,ecx */ - EMIT2(0x89, add_2reg(0xC0, dreg_lo, IA32_ECX)); - - /* xor ecx,ecx */ - EMIT2(0x31, add_2reg(0xC0, IA32_ECX, IA32_ECX)); - /* sbb dreg_hi,ecx */ - EMIT2(0x19, add_2reg(0xC0, dreg_hi, IA32_ECX)); - /* mov dreg_hi,ecx */ - EMIT2(0x89, add_2reg(0xC0, dreg_hi, IA32_ECX)); + /* neg dreg_lo */ + EMIT2(0xF7, add_1reg(0xD8, dreg_lo)); + /* adc dreg_hi,0x0 */ + EMIT3(0x83, add_1reg(0xD0, dreg_hi), 0x00); + /* neg dreg_hi */ + EMIT2(0xF7, add_1reg(0xD8, dreg_hi)); if (dstk) { /* mov dword ptr [ebp+off],dreg_lo */ From 93aa4792c3908eac87ddd368ee0fe0564148232b Mon Sep 17 00:00:00 2001 From: Haiyang Zhang Date: Tue, 30 Apr 2019 19:29:07 +0000 Subject: [PATCH 03/29] hv_netvsc: fix race that may miss tx queue wakeup When the ring buffer is almost full due to RX completion messages, a TX packet may reach the "low watermark" and cause the queue stopped. If the TX completion arrives earlier than queue stopping, the wakeup may be missed. This patch moves the check for the last pending packet to cover both EAGAIN and success cases, so the queue will be reliably waked up when necessary. Reported-and-tested-by: Stephan Klein Signed-off-by: Haiyang Zhang Signed-off-by: David S. Miller --- drivers/net/hyperv/netvsc.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index e0dce373cdd9..3d4a166a49d5 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -875,12 +875,6 @@ static inline int netvsc_send_pkt( } else if (ret == -EAGAIN) { netif_tx_stop_queue(txq); ndev_ctx->eth_stats.stop_queue++; - if (atomic_read(&nvchan->queue_sends) < 1 && - !net_device->tx_disable) { - netif_tx_wake_queue(txq); - ndev_ctx->eth_stats.wake_queue++; - ret = -ENOSPC; - } } else { netdev_err(ndev, "Unable to send packet pages %u len %u, ret %d\n", @@ -888,6 +882,15 @@ static inline int netvsc_send_pkt( ret); } + if (netif_tx_queue_stopped(txq) && + atomic_read(&nvchan->queue_sends) < 1 && + !net_device->tx_disable) { + netif_tx_wake_queue(txq); + ndev_ctx->eth_stats.wake_queue++; + if (ret == -EAGAIN) + ret = -ENOSPC; + } + return ret; } From 3c6eeff295f01bdf1c6c3addcb0a04c0c6c029e9 Mon Sep 17 00:00:00 2001 From: Sameeh Jubran Date: Wed, 1 May 2019 16:47:03 +0300 Subject: [PATCH 04/29] net: ena: fix swapped parameters when calling ena_com_indirect_table_fill_entry second parameter should be the index of the table rather than the value. Fixes: 1738cd3ed342 ("net: ena: Add a driver for Amazon Elastic Network Adapters (ENA)") Signed-off-by: Saeed Bshara Signed-off-by: Sameeh Jubran Signed-off-by: David S. Miller --- drivers/net/ethernet/amazon/ena/ena_ethtool.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c index f3a5a384e6e8..fe596bc30a96 100644 --- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c +++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c @@ -697,8 +697,8 @@ static int ena_set_rxfh(struct net_device *netdev, const u32 *indir, if (indir) { for (i = 0; i < ENA_RX_RSS_TABLE_SIZE; i++) { rc = ena_com_indirect_table_fill_entry(ena_dev, - ENA_IO_RXQ_IDX(indir[i]), - i); + i, + ENA_IO_RXQ_IDX(indir[i])); if (unlikely(rc)) { netif_err(adapter, drv, netdev, "Cannot fill indirect table (index is too large)\n"); From 8ee8ee7fe87bf64738ab4e31be036a7165608b27 Mon Sep 17 00:00:00 2001 From: Sameeh Jubran Date: Wed, 1 May 2019 16:47:04 +0300 Subject: [PATCH 05/29] net: ena: fix: set freed objects to NULL to avoid failing future allocations In some cases when a queue related allocation fails, successful past allocations are freed but the pointer that pointed to them is not set to NULL. This is a problem for 2 reasons: 1. This is generally a bad practice since this pointer might be accidentally accessed in the future. 2. Future allocations using the same pointer check if the pointer is NULL and fail if it is not. Fixed this by setting such pointers to NULL in the allocation of queue related objects. Also refactored the code of ena_setup_tx_resources() to goto-style error handling to avoid code duplication of resource freeing. Fixes: 1738cd3ed342 ("net: ena: Add a driver for Amazon Elastic Network Adapters (ENA)") Signed-off-by: Arthur Kiyanovski Signed-off-by: Sameeh Jubran Signed-off-by: David S. Miller --- drivers/net/ethernet/amazon/ena/ena_netdev.c | 25 ++++++++++++-------- 1 file changed, 15 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index a6eacf2099c3..dbcd58ebd0a9 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -224,28 +224,23 @@ static int ena_setup_tx_resources(struct ena_adapter *adapter, int qid) if (!tx_ring->tx_buffer_info) { tx_ring->tx_buffer_info = vzalloc(size); if (!tx_ring->tx_buffer_info) - return -ENOMEM; + goto err_tx_buffer_info; } size = sizeof(u16) * tx_ring->ring_size; tx_ring->free_tx_ids = vzalloc_node(size, node); if (!tx_ring->free_tx_ids) { tx_ring->free_tx_ids = vzalloc(size); - if (!tx_ring->free_tx_ids) { - vfree(tx_ring->tx_buffer_info); - return -ENOMEM; - } + if (!tx_ring->free_tx_ids) + goto err_free_tx_ids; } size = tx_ring->tx_max_header_size; tx_ring->push_buf_intermediate_buf = vzalloc_node(size, node); if (!tx_ring->push_buf_intermediate_buf) { tx_ring->push_buf_intermediate_buf = vzalloc(size); - if (!tx_ring->push_buf_intermediate_buf) { - vfree(tx_ring->tx_buffer_info); - vfree(tx_ring->free_tx_ids); - return -ENOMEM; - } + if (!tx_ring->push_buf_intermediate_buf) + goto err_push_buf_intermediate_buf; } /* Req id ring for TX out of order completions */ @@ -259,6 +254,15 @@ static int ena_setup_tx_resources(struct ena_adapter *adapter, int qid) tx_ring->next_to_clean = 0; tx_ring->cpu = ena_irq->cpu; return 0; + +err_push_buf_intermediate_buf: + vfree(tx_ring->free_tx_ids); + tx_ring->free_tx_ids = NULL; +err_free_tx_ids: + vfree(tx_ring->tx_buffer_info); + tx_ring->tx_buffer_info = NULL; +err_tx_buffer_info: + return -ENOMEM; } /* ena_free_tx_resources - Free I/O Tx Resources per Queue @@ -378,6 +382,7 @@ static int ena_setup_rx_resources(struct ena_adapter *adapter, rx_ring->free_rx_ids = vzalloc(size); if (!rx_ring->free_rx_ids) { vfree(rx_ring->rx_buffer_info); + rx_ring->rx_buffer_info = NULL; return -ENOMEM; } } From b287cdbd1cedfc9606682c6e02b58d00ff3a33ae Mon Sep 17 00:00:00 2001 From: Sameeh Jubran Date: Wed, 1 May 2019 16:47:05 +0300 Subject: [PATCH 06/29] net: ena: fix: Free napi resources when ena_up() fails ena_up() calls ena_init_napi() but does not call ena_del_napi() in case of failure. This causes a segmentation fault upon rmmod when netif_napi_del() is called. Fix this bug by calling ena_del_napi() before returning error from ena_up(). Fixes: 1738cd3ed342 ("net: ena: Add a driver for Amazon Elastic Network Adapters (ENA)") Signed-off-by: Arthur Kiyanovski Signed-off-by: Sameeh Jubran Signed-off-by: David S. Miller --- drivers/net/ethernet/amazon/ena/ena_netdev.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index dbcd58ebd0a9..03244155f74c 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -1825,6 +1825,7 @@ err_setup_rx: err_setup_tx: ena_free_io_irq(adapter); err_req_irq: + ena_del_napi(adapter); return rc; } From d3cfe7ddbc3dfbb9b201615b7fef8fd66d1b5fe8 Mon Sep 17 00:00:00 2001 From: Sameeh Jubran Date: Wed, 1 May 2019 16:47:06 +0300 Subject: [PATCH 07/29] net: ena: fix incorrect test of supported hash function ena_com_set_hash_function() tests if a hash function is supported by the device before setting it. The test returns the opposite result than needed. Reverse the condition to return the correct value. Also use the BIT macro instead of inline shift. Fixes: 1738cd3ed342 ("net: ena: Add a driver for Amazon Elastic Network Adapters (ENA)") Signed-off-by: Arthur Kiyanovski Signed-off-by: Sameeh Jubran Signed-off-by: David S. Miller --- drivers/net/ethernet/amazon/ena/ena_com.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index b17d435de09f..f9bc0b831a1a 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -2195,7 +2195,7 @@ int ena_com_set_hash_function(struct ena_com_dev *ena_dev) if (unlikely(ret)) return ret; - if (get_resp.u.flow_hash_func.supported_func & (1 << rss->hash_func)) { + if (!(get_resp.u.flow_hash_func.supported_func & BIT(rss->hash_func))) { pr_err("Func hash %d isn't supported by device, abort\n", rss->hash_func); return -EOPNOTSUPP; From 9a27de0c6ba10fe1af74d16d3524425e52c1ba3e Mon Sep 17 00:00:00 2001 From: Sameeh Jubran Date: Wed, 1 May 2019 16:47:07 +0300 Subject: [PATCH 08/29] net: ena: fix return value of ena_com_config_llq_info() ena_com_config_llq_info() returns 0 even if ena_com_set_llq() fails. Return the failure code of ena_com_set_llq() in case it fails. fixes: 689b2bdaaa14 ("net: ena: add functions for handling Low Latency Queues in ena_com") Signed-off-by: Arthur Kiyanovski Signed-off-by: Sameeh Jubran Signed-off-by: David S. Miller --- drivers/net/ethernet/amazon/ena/ena_com.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index f9bc0b831a1a..4fe437fe771b 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -731,7 +731,7 @@ static int ena_com_config_llq_info(struct ena_com_dev *ena_dev, if (rc) pr_err("Cannot set LLQ configuration: %d\n", rc); - return 0; + return rc; } static int ena_com_wait_and_process_admin_cq_interrupts(struct ena_comp_ctx *comp_ctx, From 78cb421d185cfb4fcea94e7c3ff6e6ea77bb8c11 Mon Sep 17 00:00:00 2001 From: Sameeh Jubran Date: Wed, 1 May 2019 16:47:08 +0300 Subject: [PATCH 09/29] net: ena: improve latency by disabling adaptive interrupt moderation by default Adaptive interrupt moderation was erroneously enabled by default in the driver. In case the device supports adaptive interrupt moderation it will be automatically used, which may potentially increase latency. The adaptive moderation can be enabled from ethtool command in case the feature is supported by the device. Fixes: 1738cd3ed342 ("net: ena: Add a driver for Amazon Elastic Network Adapters (ENA)") Signed-off-by: Guy Tzalik Signed-off-by: Sameeh Jubran Signed-off-by: David S. Miller --- drivers/net/ethernet/amazon/ena/ena_com.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index 4fe437fe771b..677d31abf214 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -2802,7 +2802,11 @@ int ena_com_init_interrupt_moderation(struct ena_com_dev *ena_dev) /* if moderation is supported by device we set adaptive moderation */ delay_resolution = get_resp.u.intr_moderation.intr_delay_resolution; ena_com_update_intr_delay_resolution(ena_dev, delay_resolution); - ena_com_enable_adaptive_moderation(ena_dev); + + /* Disable adaptive moderation by default - can be enabled from + * ethtool + */ + ena_com_disable_adaptive_moderation(ena_dev); return 0; err: From 11bd7a00c0d8ffe33d1e926f8e789b4aea787186 Mon Sep 17 00:00:00 2001 From: Sameeh Jubran Date: Wed, 1 May 2019 16:47:09 +0300 Subject: [PATCH 10/29] net: ena: fix ena_com_fill_hash_function() implementation ena_com_fill_hash_function() didn't configure the rss->hash_func. Fixes: 1738cd3ed342 ("net: ena: Add a driver for Amazon Elastic Network Adapters (ENA)") Signed-off-by: Netanel Belgazal Signed-off-by: Sameeh Jubran Signed-off-by: David S. Miller --- drivers/net/ethernet/amazon/ena/ena_com.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index 677d31abf214..4cdd8459c37e 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -2280,6 +2280,7 @@ int ena_com_fill_hash_function(struct ena_com_dev *ena_dev, return -EINVAL; } + rss->hash_func = func; rc = ena_com_set_hash_function(ena_dev); /* Restore the old function */ From f913308879bc6ae437ce64d878c7b05643ddea44 Mon Sep 17 00:00:00 2001 From: Sameeh Jubran Date: Wed, 1 May 2019 16:47:10 +0300 Subject: [PATCH 11/29] net: ena: gcc 8: fix compilation warning GCC 8 contains a number of new warnings as well as enhancements to existing checkers. The warning - Wstringop-truncation - warns for calls to bounded string manipulation functions such as strncat, strncpy, and stpncpy that may either truncate the copied string or leave the destination unchanged. In our case the destination string length (32 bytes) is much shorter than the source string (64 bytes) which causes this warning to show up. In general the destination has to be at least a byte larger than the length of the source string with strncpy for this warning not to showup. This can be easily fixed by using strlcpy instead which already does the truncation to the string. Documentation for this function can be found here: https://elixir.bootlin.com/linux/latest/source/lib/string.c#L141 Fixes: 1738cd3ed342 ("net: ena: Add a driver for Amazon Elastic Network Adapters (ENA)") Signed-off-by: Sameeh Jubran Signed-off-by: David S. Miller --- drivers/net/ethernet/amazon/ena/ena_netdev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 03244155f74c..bc5997a5f809 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -2298,7 +2298,7 @@ static void ena_config_host_info(struct ena_com_dev *ena_dev, host_info->bdf = (pdev->bus->number << 8) | pdev->devfn; host_info->os_type = ENA_ADMIN_OS_LINUX; host_info->kernel_ver = LINUX_VERSION_CODE; - strncpy(host_info->kernel_ver_str, utsname()->version, + strlcpy(host_info->kernel_ver_str, utsname()->version, sizeof(host_info->kernel_ver_str) - 1); host_info->os_dist = 0; strncpy(host_info->os_dist_str, utsname()->release, From 64c6f4bbca748c3b2101469a76d88b7cd1c00476 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 1 May 2019 18:08:34 -0700 Subject: [PATCH 12/29] neighbor: Reset gc_entries counter if new entry is released before insert Ian and Alan both reported seeing overflows after upgrades to 5.x kernels: neighbour: arp_cache: neighbor table overflow! Alan's mpls script helped get to the bottom of this bug. When a new entry is created the gc_entries counter is bumped in neigh_alloc to check if a new one is allowed to be created. ___neigh_create then searches for an existing entry before inserting the just allocated one. If an entry already exists, the new one is dropped in favor of the existing one. In this case the cleanup path needs to drop the gc_entries counter. There is no memory leak, only a counter leak. Fixes: 58956317c8d ("neighbor: Improve garbage collection") Reported-by: Ian Kumlien Reported-by: Alan Maguire Signed-off-by: David Ahern Tested-by: Alan Maguire Signed-off-by: David S. Miller --- net/core/neighbour.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 30f6fd8f68e0..aff051e5521d 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -663,6 +663,8 @@ out: out_tbl_unlock: write_unlock_bh(&tbl->lock); out_neigh_release: + if (!exempt_from_gc) + atomic_dec(&tbl->gc_entries); neigh_release(n); goto out; } From 4b2a2bfeb3f056461a90bd621e8bd7d03fa47f60 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 1 May 2019 18:18:42 -0700 Subject: [PATCH 13/29] neighbor: Call __ipv4_neigh_lookup_noref in neigh_xmit Commit cd9ff4de0107 changed the key for IFF_POINTOPOINT devices to INADDR_ANY but neigh_xmit which is used for MPLS encapsulations was not updated to use the altered key. The result is that every packet Tx does a lookup on the gateway address which does not find an entry, a new one is created only to find the existing one in the table right before the insert since arp_constructor was updated to reset the primary key. This is seen in the allocs and destroys counters: ip -s -4 ntable show | head -10 | grep alloc which increase for each packet showing the unnecessary overhread. Fix by having neigh_xmit use __ipv4_neigh_lookup_noref for NEIGH_ARP_TABLE. Fixes: cd9ff4de0107 ("ipv4: Make neigh lookup keys for loopback/point-to-point devices be INADDR_ANY") Reported-by: Alan Maguire Signed-off-by: David Ahern Tested-by: Alan Maguire Signed-off-by: David S. Miller --- net/core/neighbour.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index aff051e5521d..9b9da5142613 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include #include @@ -2984,7 +2985,13 @@ int neigh_xmit(int index, struct net_device *dev, if (!tbl) goto out; rcu_read_lock_bh(); - neigh = __neigh_lookup_noref(tbl, addr, dev); + if (index == NEIGH_ARP_TABLE) { + u32 key = *((u32 *)addr); + + neigh = __ipv4_neigh_lookup_noref(dev, key); + } else { + neigh = __neigh_lookup_noref(tbl, addr, dev); + } if (!neigh) neigh = __neigh_create(tbl, addr, dev, false); err = PTR_ERR(neigh); From 25426043ec9e22b90c789407c28e40f32a9d1985 Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Thu, 2 May 2019 10:51:05 +0200 Subject: [PATCH 14/29] cls_matchall: avoid panic when receiving a packet before filter set When a matchall classifier is added, there is a small time interval in which tp->root is NULL. If we receive a packet in this small time slice a NULL pointer dereference will happen, leading to a kernel panic: # tc qdisc replace dev eth0 ingress # tc filter add dev eth0 parent ffff: matchall action gact drop Unable to handle kernel NULL pointer dereference at virtual address 0000000000000034 Mem abort info: ESR = 0x96000005 Exception class = DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 Data abort info: ISV = 0, ISS = 0x00000005 CM = 0, WnR = 0 user pgtable: 4k pages, 39-bit VAs, pgdp = 00000000a623d530 [0000000000000034] pgd=0000000000000000, pud=0000000000000000 Internal error: Oops: 96000005 [#1] SMP Modules linked in: cls_matchall sch_ingress nls_iso8859_1 nls_cp437 vfat fat m25p80 spi_nor mtd xhci_plat_hcd xhci_hcd phy_generic sfp mdio_i2c usbcore i2c_mv64xxx marvell10g mvpp2 usb_common spi_orion mvmdio i2c_core sbsa_gwdt phylink ip_tables x_tables autofs4 Process ksoftirqd/0 (pid: 9, stack limit = 0x0000000009de7d62) CPU: 0 PID: 9 Comm: ksoftirqd/0 Not tainted 5.1.0-rc6 #21 Hardware name: Marvell 8040 MACCHIATOBin Double-shot (DT) pstate: 40000005 (nZcv daif -PAN -UAO) pc : mall_classify+0x28/0x78 [cls_matchall] lr : tcf_classify+0x78/0x138 sp : ffffff80109db9d0 x29: ffffff80109db9d0 x28: ffffffc426058800 x27: 0000000000000000 x26: ffffffc425b0dd00 x25: 0000000020000000 x24: 0000000000000000 x23: ffffff80109dbac0 x22: 0000000000000001 x21: ffffffc428ab5100 x20: ffffffc425b0dd00 x19: ffffff80109dbac0 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000 x14: 0000000000000000 x13: ffffffbf108ad288 x12: dead000000000200 x11: 00000000f0000000 x10: 0000000000000001 x9 : ffffffbf1089a220 x8 : 0000000000000001 x7 : ffffffbebffaa950 x6 : 0000000000000000 x5 : 000000442d6ba000 x4 : 0000000000000000 x3 : ffffff8008735ad8 x2 : ffffff80109dbac0 x1 : ffffffc425b0dd00 x0 : ffffff8010592078 Call trace: mall_classify+0x28/0x78 [cls_matchall] tcf_classify+0x78/0x138 __netif_receive_skb_core+0x29c/0xa20 __netif_receive_skb_one_core+0x34/0x60 __netif_receive_skb+0x28/0x78 netif_receive_skb_internal+0x2c/0xc0 napi_gro_receive+0x1a0/0x1d8 mvpp2_poll+0x928/0xb18 [mvpp2] net_rx_action+0x108/0x378 __do_softirq+0x128/0x320 run_ksoftirqd+0x44/0x60 smpboot_thread_fn+0x168/0x1b0 kthread+0x12c/0x130 ret_from_fork+0x10/0x1c Code: aa0203f3 aa1e03e0 d503201f f9400684 (b9403480) ---[ end trace fc71e2ef7b8ab5a5 ]--- Kernel panic - not syncing: Fatal exception in interrupt SMP: stopping secondary CPUs Kernel Offset: disabled CPU features: 0x002,00002000 Memory Limit: none Rebooting in 1 seconds.. Fix this by adding a NULL check in mall_classify(). Fixes: ed76f5edccc9 ("net: sched: protect filter_chain list with filter_chain_lock mutex") Signed-off-by: Matteo Croce Acked-by: Cong Wang Signed-off-by: David S. Miller --- net/sched/cls_matchall.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index a13bc351a414..3d021f2aad1c 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -32,6 +32,9 @@ static int mall_classify(struct sk_buff *skb, const struct tcf_proto *tp, { struct cls_mall_head *head = rcu_dereference_bh(tp->root); + if (unlikely(!head)) + return -1; + if (tc_skip_sw(head->flags)) return -1; From 7fcd1e033dacedd520abebc943c960dcf5add3ae Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 2 May 2019 15:14:15 -0700 Subject: [PATCH 15/29] ipmr_base: Do not reset index in mr_table_dump e is the counter used to save the location of a dump when an skb is filled. Once the walk of the table is complete, mr_table_dump needs to return without resetting that index to 0. Dump of a specific table is looping because of the reset because there is no way to indicate the walk of the table is done. Move the reset to the caller so the dump of each table starts at 0, but the loop counter is maintained if a dump fills an skb. Fixes: e1cedae1ba6b0 ("ipmr: Refactor mr_rtm_dumproute") Signed-off-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/ipmr_base.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c index 3e614cc824f7..3a1af50bd0a5 100644 --- a/net/ipv4/ipmr_base.c +++ b/net/ipv4/ipmr_base.c @@ -335,8 +335,6 @@ next_entry2: } spin_unlock_bh(lock); err = 0; - e = 0; - out: cb->args[1] = e; return err; @@ -374,6 +372,7 @@ int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, err = mr_table_dump(mrt, skb, cb, fill, lock, filter); if (err < 0) break; + cb->args[1] = 0; next_table: t++; } From b4010af981ac8cdf1f7f58eb6b131c482e5dee02 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Wed, 1 May 2019 21:54:28 +0200 Subject: [PATCH 16/29] net: phy: fix phy_validate_pause We have valid scenarios where ETHTOOL_LINK_MODE_Pause_BIT doesn't need to be supported. Therefore extend the first check to check for rx_pause being set. See also phy_set_asym_pause: rx=0 and tx=1: advertise asym pause only rx=0 and tx=0: stop advertising both pause modes The fixed commit isn't wrong, it's just the one that introduced the linkmode bitmaps. Fixes: 3c1bcc8614db ("net: ethernet: Convert phydev advertize and supported from u32 to link mode") Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 77068c545de0..cd5966b0db57 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -2044,11 +2044,14 @@ bool phy_validate_pause(struct phy_device *phydev, struct ethtool_pauseparam *pp) { if (!linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, - phydev->supported) || - (!linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, - phydev->supported) && - pp->rx_pause != pp->tx_pause)) + phydev->supported) && pp->rx_pause) return false; + + if (!linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, + phydev->supported) && + pp->rx_pause != pp->tx_pause) + return false; + return true; } EXPORT_SYMBOL(phy_validate_pause); From 4014dfae3ccaaf3ec19c9ae0691a3f14e7132eae Mon Sep 17 00:00:00 2001 From: Paul Bolle Date: Wed, 1 May 2019 23:19:03 +0200 Subject: [PATCH 17/29] isdn: bas_gigaset: use usb_fill_int_urb() properly The switch to make bas_gigaset use usb_fill_int_urb() - instead of filling that urb "by hand" - missed the subtle ordering of the previous code. See, before the switch urb->dev was set to a member somewhere deep in a complicated structure and then supplied to usb_rcvisocpipe() and usb_sndisocpipe(). After that switch urb->dev wasn't set to anything specific before being supplied to those two macros. This triggers a nasty oops: BUG: unable to handle kernel NULL pointer dereference at 00000000 #PF error: [normal kernel read fault] *pde = 00000000 Oops: 0000 [#1] SMP CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.1.0-0.rc4.1.local0.fc28.i686 #1 Hardware name: IBM 2525FAG/2525FAG, BIOS 74ET64WW (2.09 ) 12/14/2006 EIP: gigaset_init_bchannel+0x89/0x320 [bas_gigaset] Code: 75 07 83 8b 84 00 00 00 40 8d 47 74 c7 07 01 00 00 00 89 45 f0 8b 44 b7 68 85 c0 0f 84 6a 02 00 00 8b 48 28 8b 93 88 00 00 00 <8b> 09 8d 54 12 03 c1 e2 0f c1 e1 08 09 ca 8b 8b 8c 00 00 00 80 ca EAX: f05ec200 EBX: ed404200 ECX: 00000000 EDX: 00000000 ESI: 00000000 EDI: f065a000 EBP: f30c9f40 ESP: f30c9f20 DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 EFLAGS: 00010086 CR0: 80050033 CR2: 00000000 CR3: 0ddc7000 CR4: 000006d0 Call Trace: ? gigaset_isdn_connD+0xf6/0x140 [gigaset] gigaset_handle_event+0x173e/0x1b90 [gigaset] tasklet_action_common.isra.16+0x4e/0xf0 tasklet_action+0x1e/0x20 __do_softirq+0xb2/0x293 ? __irqentry_text_end+0x3/0x3 call_on_stack+0x45/0x50 ? irq_exit+0xb5/0xc0 ? do_IRQ+0x78/0xd0 ? acpi_idle_enter_s2idle+0x50/0x50 ? common_interrupt+0xd4/0xdc ? acpi_idle_enter_s2idle+0x50/0x50 ? sched_cpu_activate+0x1b/0xf0 ? acpi_fan_resume.cold.7+0x9/0x18 ? cpuidle_enter_state+0x152/0x4c0 ? cpuidle_enter+0x14/0x20 ? call_cpuidle+0x21/0x40 ? do_idle+0x1c8/0x200 ? cpu_startup_entry+0x25/0x30 ? rest_init+0x88/0x8a ? arch_call_rest_init+0xd/0x19 ? start_kernel+0x42f/0x448 ? i386_start_kernel+0xac/0xb0 ? startup_32_smp+0x164/0x168 Modules linked in: ppp_generic slhc capi bas_gigaset gigaset kernelcapi nf_conntrack_netbios_ns nf_conntrack_broadcast xt_CT ip6t_rpfilter ip6t_REJECT nf_reject_ipv6 xt_conntrack ip_set nfnetlink ebtable_nat ebtable_broute bridge stp llc ip6table_nat ip6table_mangle ip6table_raw ip6table_security iptable_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 libcrc32c iptable_mangle iptable_raw iptable_security ebtable_filter ebtables ip6table_filter ip6_tables sunrpc ipw2200 iTCO_wdt gpio_ich snd_intel8x0 libipw iTCO_vendor_support snd_ac97_codec lib80211 ppdev ac97_bus snd_seq cfg80211 snd_seq_device pcspkr thinkpad_acpi lpc_ich snd_pcm i2c_i801 snd_timer ledtrig_audio snd soundcore rfkill parport_pc parport pcc_cpufreq acpi_cpufreq i915 i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sdhci_pci sysimgblt cqhci fb_sys_fops drm sdhci mmc_core tg3 ata_generic serio_raw yenta_socket pata_acpi video CR2: 0000000000000000 ---[ end trace 1fe07487b9200c73 ]--- EIP: gigaset_init_bchannel+0x89/0x320 [bas_gigaset] Code: 75 07 83 8b 84 00 00 00 40 8d 47 74 c7 07 01 00 00 00 89 45 f0 8b 44 b7 68 85 c0 0f 84 6a 02 00 00 8b 48 28 8b 93 88 00 00 00 <8b> 09 8d 54 12 03 c1 e2 0f c1 e1 08 09 ca 8b 8b 8c 00 00 00 80 ca EAX: f05ec200 EBX: ed404200 ECX: 00000000 EDX: 00000000 ESI: 00000000 EDI: f065a000 EBP: f30c9f40 ESP: cddcb3bc DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 EFLAGS: 00010086 CR0: 80050033 CR2: 00000000 CR3: 0ddc7000 CR4: 000006d0 Kernel panic - not syncing: Fatal exception in interrupt Kernel Offset: 0xcc00000 from 0xc0400000 (relocation range: 0xc0000000-0xf6ffdfff) ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]--- No-one noticed because this Oops is apparently only triggered by setting up an ISDN data connection on a live ISDN line on a gigaset base (ie, the PBX that the gigaset driver support). Very few people do that running present day kernels. Anyhow, a little code reorganization makes this problem go away, while avoiding the subtle ordering that was used in the past. So let's do that. Fixes: 78c696c19578 ("isdn: gigaset: use usb_fill_int_urb()") Signed-off-by: Paul Bolle Signed-off-by: David S. Miller --- drivers/isdn/gigaset/bas-gigaset.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/isdn/gigaset/bas-gigaset.c b/drivers/isdn/gigaset/bas-gigaset.c index ecdeb89645d0..149b1aca52a2 100644 --- a/drivers/isdn/gigaset/bas-gigaset.c +++ b/drivers/isdn/gigaset/bas-gigaset.c @@ -958,6 +958,7 @@ static void write_iso_callback(struct urb *urb) */ static int starturbs(struct bc_state *bcs) { + struct usb_device *udev = bcs->cs->hw.bas->udev; struct bas_bc_state *ubc = bcs->hw.bas; struct urb *urb; int j, k; @@ -975,8 +976,8 @@ static int starturbs(struct bc_state *bcs) rc = -EFAULT; goto error; } - usb_fill_int_urb(urb, bcs->cs->hw.bas->udev, - usb_rcvisocpipe(urb->dev, 3 + 2 * bcs->channel), + usb_fill_int_urb(urb, udev, + usb_rcvisocpipe(udev, 3 + 2 * bcs->channel), ubc->isoinbuf + k * BAS_INBUFSIZE, BAS_INBUFSIZE, read_iso_callback, bcs, BAS_FRAMETIME); @@ -1006,8 +1007,8 @@ static int starturbs(struct bc_state *bcs) rc = -EFAULT; goto error; } - usb_fill_int_urb(urb, bcs->cs->hw.bas->udev, - usb_sndisocpipe(urb->dev, 4 + 2 * bcs->channel), + usb_fill_int_urb(urb, udev, + usb_sndisocpipe(udev, 4 + 2 * bcs->channel), ubc->isooutbuf->data, sizeof(ubc->isooutbuf->data), write_iso_callback, &ubc->isoouturbs[k], From 594725db0ce11b2fd70f672d7540fa43c7f2f627 Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Thu, 2 May 2019 17:13:18 +0200 Subject: [PATCH 18/29] cls_cgroup: avoid panic when receiving a packet before filter set When a cgroup classifier is added, there is a small time interval in which tp->root is NULL. If we receive a packet in this small time slice a NULL pointer dereference will happen, leading to a kernel panic: # mkdir /sys/fs/cgroup/net_cls/0 # echo 0x100001 > /sys/fs/cgroup/net_cls/0/net_cls.classid # echo $$ >/sys/fs/cgroup/net_cls/0/tasks # ping -qfb 255.255.255.255 -I eth0 &>/dev/null & # tc qdisc add dev eth0 root handle 10: htb # while : ; do > tc filter add dev eth0 parent 10: protocol ip prio 10 handle 1: cgroup > tc filter delete dev eth0 > done Unable to handle kernel NULL pointer dereference at virtual address 0000000000000028 Mem abort info: ESR = 0x96000005 Exception class = DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 Data abort info: ISV = 0, ISS = 0x00000005 CM = 0, WnR = 0 user pgtable: 4k pages, 39-bit VAs, pgdp = 0000000098a7ff91 [0000000000000028] pgd=0000000000000000, pud=0000000000000000 Internal error: Oops: 96000005 [#1] SMP Modules linked in: sch_htb cls_cgroup algif_hash af_alg nls_iso8859_1 nls_cp437 vfat fat xhci_plat_hcd m25p80 spi_nor xhci_hcd mtd usbcore usb_common spi_orion sfp i2c_mv64xxx phy_generic mdio_i2c marvell10g i2c_core mvpp2 mvmdio phylink sbsa_gwdt ip_tables x_tables autofs4 Process ping (pid: 5421, stack limit = 0x00000000b20b1505) CPU: 3 PID: 5421 Comm: ping Not tainted 5.1.0-rc6 #31 Hardware name: Marvell 8040 MACCHIATOBin Double-shot (DT) pstate: 60000005 (nZCv daif -PAN -UAO) pc : cls_cgroup_classify+0x80/0xec [cls_cgroup] lr : cls_cgroup_classify+0x34/0xec [cls_cgroup] sp : ffffff8012e6b850 x29: ffffff8012e6b850 x28: ffffffc423dd3c00 x27: ffffff801093ebc0 x26: ffffffc425a85b00 x25: 0000000020000000 x24: 0000000000000000 x23: ffffff8012e6b910 x22: ffffffc428db4900 x21: ffffff8012e6b910 x20: 0000000000100001 x19: 0000000000000000 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000 x14: 0000000000000000 x13: 0000000000000000 x12: 000000000000001c x11: 0000000000000018 x10: ffffff8012e6b840 x9 : 0000000000003580 x8 : 000000000000009d x7 : 0000000000000002 x6 : ffffff8012e6b860 x5 : 000000007cd66ffe x4 : 000000009742a193 x3 : ffffff800865b4d8 x2 : ffffff8012e6b910 x1 : 0000000000000400 x0 : ffffffc42c38f300 Call trace: cls_cgroup_classify+0x80/0xec [cls_cgroup] tcf_classify+0x78/0x138 htb_enqueue+0x74/0x320 [sch_htb] __dev_queue_xmit+0x3e4/0x9d0 dev_queue_xmit+0x24/0x30 ip_finish_output2+0x2e4/0x4d0 ip_finish_output+0x1d8/0x270 ip_mc_output+0xa8/0x240 ip_local_out+0x58/0x68 ip_send_skb+0x2c/0x88 ip_push_pending_frames+0x44/0x50 raw_sendmsg+0x458/0x830 inet_sendmsg+0x54/0xe8 sock_sendmsg+0x34/0x50 __sys_sendto+0xd0/0x120 __arm64_sys_sendto+0x30/0x40 el0_svc_common.constprop.0+0x88/0xf8 el0_svc_handler+0x2c/0x38 el0_svc+0x8/0xc Code: 39496001 360002a1 b9425c14 34000274 (79405260) Fixes: ed76f5edccc9 ("net: sched: protect filter_chain list with filter_chain_lock mutex") Suggested-by: Cong Wang Signed-off-by: Matteo Croce Signed-off-by: David S. Miller --- net/sched/cls_cgroup.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index 4c1567854f95..706a160142ea 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -32,6 +32,8 @@ static int cls_cgroup_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct cls_cgroup_head *head = rcu_dereference_bh(tp->root); u32 classid = task_get_classid(skb); + if (unlikely(!head)) + return -1; if (!classid) return -1; if (!tcf_em_tree_match(skb, &head->ematches, NULL)) From d14a108d510ec66f6db15509b9d7d2f0b6208145 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 3 May 2019 13:10:17 +0100 Subject: [PATCH 19/29] net: rds: fix spelling mistake "syctl" -> "sysctl" There is a spelling mistake in a pr_warn warning. Fix it. Signed-off-by: Colin Ian King Acked-by: Santosh Shilimkar Signed-off-by: David S. Miller --- net/rds/tcp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/rds/tcp.c b/net/rds/tcp.c index faf726e00e27..66121bc6f34e 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -551,7 +551,7 @@ static __net_init int rds_tcp_init_net(struct net *net) tbl = kmemdup(rds_tcp_sysctl_table, sizeof(rds_tcp_sysctl_table), GFP_KERNEL); if (!tbl) { - pr_warn("could not set allocate syctl table\n"); + pr_warn("could not set allocate sysctl table\n"); return -ENOMEM; } rtn->ctl_table = tbl; From 17170e6570c082717c142733d9a638bcd20551f8 Mon Sep 17 00:00:00 2001 From: Laurentiu Tudor Date: Fri, 3 May 2019 16:03:11 +0300 Subject: [PATCH 20/29] dpaa_eth: fix SG frame cleanup Fix issue with the entry indexing in the sg frame cleanup code being off-by-1. This problem showed up when doing some basic iperf tests and manifested in traffic coming to a halt. Signed-off-by: Laurentiu Tudor Acked-by: Madalin Bucur Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index dfebc30c4841..d3f2408dc9e8 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -1648,7 +1648,7 @@ static struct sk_buff *dpaa_cleanup_tx_fd(const struct dpaa_priv *priv, qm_sg_entry_get_len(&sgt[0]), dma_dir); /* remaining pages were mapped with skb_frag_dma_map() */ - for (i = 1; i < nr_frags; i++) { + for (i = 1; i <= nr_frags; i++) { WARN_ON(qm_sg_entry_is_ext(&sgt[i])); dma_unmap_page(dev, qm_sg_addr(&sgt[i]), From ee0df19305d9fabd9479b785918966f6e25b733b Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 3 May 2019 13:33:23 +0000 Subject: [PATCH 21/29] net: ucc_geth - fix Oops when changing number of buffers in the ring When changing the number of buffers in the RX ring while the interface is running, the following Oops is encountered due to the new number of buffers being taken into account immediately while their allocation is done when opening the device only. [ 69.882706] Unable to handle kernel paging request for data at address 0xf0000100 [ 69.890172] Faulting instruction address: 0xc033e164 [ 69.895122] Oops: Kernel access of bad area, sig: 11 [#1] [ 69.900494] BE PREEMPT CMPCPRO [ 69.907120] CPU: 0 PID: 0 Comm: swapper Not tainted 4.14.115-00006-g179ade8ce3-dirty #269 [ 69.915956] task: c0684310 task.stack: c06da000 [ 69.920470] NIP: c033e164 LR: c02e44d0 CTR: c02e41fc [ 69.925504] REGS: dfff1e20 TRAP: 0300 Not tainted (4.14.115-00006-g179ade8ce3-dirty) [ 69.934161] MSR: 00009032 CR: 22004428 XER: 20000000 [ 69.940869] DAR: f0000100 DSISR: 20000000 [ 69.940869] GPR00: c0352d70 dfff1ed0 c0684310 f00000a4 00000040 dfff1f68 00000000 0000001f [ 69.940869] GPR08: df53f410 1cc00040 00000021 c0781640 42004424 100c82b6 f00000a4 df53f5b0 [ 69.940869] GPR16: df53f6c0 c05daf84 00000040 00000000 00000040 c0782be4 00000000 00000001 [ 69.940869] GPR24: 00000000 df53f400 000001b0 df53f410 df53f000 0000003f df708220 1cc00044 [ 69.978348] NIP [c033e164] skb_put+0x0/0x5c [ 69.982528] LR [c02e44d0] ucc_geth_poll+0x2d4/0x3f8 [ 69.987384] Call Trace: [ 69.989830] [dfff1ed0] [c02e4554] ucc_geth_poll+0x358/0x3f8 (unreliable) [ 69.996522] [dfff1f20] [c0352d70] net_rx_action+0x248/0x30c [ 70.002099] [dfff1f80] [c04e93e4] __do_softirq+0xfc/0x310 [ 70.007492] [dfff1fe0] [c0021124] irq_exit+0xd0/0xd4 [ 70.012458] [dfff1ff0] [c000e7e0] call_do_irq+0x24/0x3c [ 70.017683] [c06dbe80] [c0006bac] do_IRQ+0x64/0xc4 [ 70.022474] [c06dbea0] [c001097c] ret_from_except+0x0/0x14 [ 70.027964] --- interrupt: 501 at rcu_idle_exit+0x84/0x90 [ 70.027964] LR = rcu_idle_exit+0x74/0x90 [ 70.037585] [c06dbf60] [20000000] 0x20000000 (unreliable) [ 70.042984] [c06dbf80] [c004bb0c] do_idle+0xb4/0x11c [ 70.047945] [c06dbfa0] [c004bd14] cpu_startup_entry+0x18/0x1c [ 70.053682] [c06dbfb0] [c05fb034] start_kernel+0x370/0x384 [ 70.059153] [c06dbff0] [00003438] 0x3438 [ 70.063062] Instruction dump: [ 70.066023] 38a00000 38800000 90010014 4bfff015 80010014 7c0803a6 3123ffff 7c691910 [ 70.073767] 38210010 4e800020 38600000 4e800020 <80e3005c> 80c30098 3107ffff 7d083910 [ 70.081690] ---[ end trace be7ccd9c1e1a9f12 ]--- This patch forbids the modification of the number of buffers in the ring while the interface is running. Fixes: ac421852b3a0 ("ucc_geth: add ethtool support") Signed-off-by: Christophe Leroy Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/ucc_geth_ethtool.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/freescale/ucc_geth_ethtool.c b/drivers/net/ethernet/freescale/ucc_geth_ethtool.c index 0beee2cc2ddd..722b6de24816 100644 --- a/drivers/net/ethernet/freescale/ucc_geth_ethtool.c +++ b/drivers/net/ethernet/freescale/ucc_geth_ethtool.c @@ -252,14 +252,12 @@ uec_set_ringparam(struct net_device *netdev, return -EINVAL; } + if (netif_running(netdev)) + return -EBUSY; + ug_info->bdRingLenRx[queue] = ring->rx_pending; ug_info->bdRingLenTx[queue] = ring->tx_pending; - if (netif_running(netdev)) { - /* FIXME: restart automatically */ - netdev_info(netdev, "Please re-open the interface\n"); - } - return ret; } From 47d3d7fdb10a21c223036b58bd70ffdc24a472c4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 3 May 2019 08:24:44 -0700 Subject: [PATCH 22/29] ip6: fix skb leak in ip6frag_expire_frag_queue() Since ip6frag_expire_frag_queue() now pulls the head skb from frag queue, we should no longer use skb_get(), since this leads to an skb leak. Stefan Bader initially reported a problem in 4.4.stable [1] caused by the skb_get(), so this patch should also fix this issue. 296583.091021] kernel BUG at /build/linux-6VmqmP/linux-4.4.0/net/core/skbuff.c:1207! [296583.091734] Call Trace: [296583.091749] [] __pskb_pull_tail+0x50/0x350 [296583.091764] [] _decode_session6+0x26a/0x400 [296583.091779] [] __xfrm_decode_session+0x39/0x50 [296583.091795] [] icmpv6_route_lookup+0xf0/0x1c0 [296583.091809] [] icmp6_send+0x5e1/0x940 [296583.091823] [] ? __netif_receive_skb+0x18/0x60 [296583.091838] [] ? netif_receive_skb_internal+0x32/0xa0 [296583.091858] [] ? ixgbe_clean_rx_irq+0x594/0xac0 [ixgbe] [296583.091876] [] ? nf_ct_net_exit+0x50/0x50 [nf_defrag_ipv6] [296583.091893] [] icmpv6_send+0x21/0x30 [296583.091906] [] ip6_expire_frag_queue+0xe0/0x120 [296583.091921] [] nf_ct_frag6_expire+0x1f/0x30 [nf_defrag_ipv6] [296583.091938] [] call_timer_fn+0x37/0x140 [296583.091951] [] ? nf_ct_net_exit+0x50/0x50 [nf_defrag_ipv6] [296583.091968] [] run_timer_softirq+0x234/0x330 [296583.091982] [] __do_softirq+0x109/0x2b0 Fixes: d4289fcc9b16 ("net: IP6 defrag: use rbtrees for IPv6 defrag") Signed-off-by: Eric Dumazet Reported-by: Stefan Bader Cc: Peter Oskolkov Cc: Florian Westphal Signed-off-by: David S. Miller --- include/net/ipv6_frag.h | 1 - 1 file changed, 1 deletion(-) diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h index 28aa9b30aece..1f77fb4dc79d 100644 --- a/include/net/ipv6_frag.h +++ b/include/net/ipv6_frag.h @@ -94,7 +94,6 @@ ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq) goto out; head->dev = dev; - skb_get(head); spin_unlock(&fq->q.lock); icmpv6_send(head, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0); From 9b3040a6aafd7898ece7fc7efcbca71e42aa8069 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sun, 5 May 2019 11:16:20 -0700 Subject: [PATCH 23/29] ipv4: Define __ipv4_neigh_lookup_noref when CONFIG_INET is disabled Define __ipv4_neigh_lookup_noref to return NULL when CONFIG_INET is disabled. Fixes: 4b2a2bfeb3f0 ("neighbor: Call __ipv4_neigh_lookup_noref in neigh_xmit") Reported-by: kbuild test robot Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/arp.h | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/include/net/arp.h b/include/net/arp.h index 977aabfcdc03..c8f580a0e6b1 100644 --- a/include/net/arp.h +++ b/include/net/arp.h @@ -18,6 +18,7 @@ static inline u32 arp_hashfn(const void *pkey, const struct net_device *dev, u32 return val * hash_rnd[0]; } +#ifdef CONFIG_INET static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key) { if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) @@ -25,6 +26,13 @@ static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev return ___neigh_lookup_noref(&arp_tbl, neigh_key_eq32, arp_hashfn, &key, dev); } +#else +static inline +struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key) +{ + return NULL; +} +#endif static inline struct neighbour *__ipv4_neigh_lookup(struct net_device *dev, u32 key) { From 638a3a1e349ddf5b82f222ff5cb3b4f266e7c278 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Mon, 6 May 2019 22:44:04 +0800 Subject: [PATCH 24/29] l2tp: Fix possible NULL pointer dereference BUG: unable to handle kernel NULL pointer dereference at 0000000000000128 PGD 0 P4D 0 Oops: 0000 [#1 CPU: 0 PID: 5697 Comm: modprobe Tainted: G W 5.1.0-rc7+ #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014 RIP: 0010:__lock_acquire+0x53/0x10b0 Code: 8b 1c 25 40 5e 01 00 4c 8b 6d 10 45 85 e4 0f 84 bd 06 00 00 44 8b 1d 7c d2 09 02 49 89 fe 41 89 d2 45 85 db 0f 84 47 02 00 00 <48> 81 3f a0 05 70 83 b8 00 00 00 00 44 0f 44 c0 83 fe 01 0f 86 3a RSP: 0018:ffffc90001c07a28 EFLAGS: 00010002 RAX: 0000000000000000 RBX: ffff88822f038440 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000128 RBP: ffffc90001c07a88 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000001 R12: 0000000000000001 R13: 0000000000000000 R14: 0000000000000128 R15: 0000000000000000 FS: 00007fead0811540(0000) GS:ffff888237a00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000128 CR3: 00000002310da000 CR4: 00000000000006f0 Call Trace: ? __lock_acquire+0x24e/0x10b0 lock_acquire+0xdf/0x230 ? flush_workqueue+0x71/0x530 flush_workqueue+0x97/0x530 ? flush_workqueue+0x71/0x530 l2tp_exit_net+0x170/0x2b0 [l2tp_core ? l2tp_exit_net+0x93/0x2b0 [l2tp_core ops_exit_list.isra.6+0x36/0x60 unregister_pernet_operations+0xb8/0x110 unregister_pernet_device+0x25/0x40 l2tp_init+0x55/0x1000 [l2tp_core ? 0xffffffffa018d000 do_one_initcall+0x6c/0x3cc ? do_init_module+0x22/0x1f1 ? rcu_read_lock_sched_held+0x97/0xb0 ? kmem_cache_alloc_trace+0x325/0x3b0 do_init_module+0x5b/0x1f1 load_module+0x1db1/0x2690 ? m_show+0x1d0/0x1d0 __do_sys_finit_module+0xc5/0xd0 __x64_sys_finit_module+0x15/0x20 do_syscall_64+0x6b/0x1d0 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7fead031a839 Code: 00 f3 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 1f f6 2c 00 f7 d8 64 89 01 48 RSP: 002b:00007ffe8d9acca8 EFLAGS: 00000246 ORIG_RAX: 0000000000000139 RAX: ffffffffffffffda RBX: 0000560078398b80 RCX: 00007fead031a839 RDX: 0000000000000000 RSI: 000056007659dc2e RDI: 0000000000000003 RBP: 000056007659dc2e R08: 0000000000000000 R09: 0000560078398b80 R10: 0000000000000003 R11: 0000000000000246 R12: 0000000000000000 R13: 00005600783a04a0 R14: 0000000000040000 R15: 0000560078398b80 Modules linked in: l2tp_core(+) e1000 ip_tables ipv6 [last unloaded: l2tp_core CR2: 0000000000000128 ---[ end trace 8322b2b8bf83f8e1 If alloc_workqueue fails in l2tp_init, l2tp_net_ops is unregistered on failure path. Then l2tp_exit_net is called which will flush NULL workqueue, this patch add a NULL check to fix it. Fixes: 67e04c29ec0d ("l2tp: unregister l2tp_net_ops on failure path") Signed-off-by: YueHaibing Acked-by: Guillaume Nault Signed-off-by: David S. Miller --- net/l2tp/l2tp_core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 52b5a2797c0c..e4dec03a19fe 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1735,7 +1735,8 @@ static __net_exit void l2tp_exit_net(struct net *net) } rcu_read_unlock_bh(); - flush_workqueue(l2tp_wq); + if (l2tp_wq) + flush_workqueue(l2tp_wq); rcu_barrier(); for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) From 68be930249d051fd54d3d99156b3dcadcb2a1f9b Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Mon, 6 May 2019 23:25:29 +0800 Subject: [PATCH 25/29] net: dsa: Fix error cleanup path in dsa_init_module BUG: unable to handle kernel paging request at ffffffffa01c5430 PGD 3270067 P4D 3270067 PUD 3271063 PMD 230bc5067 PTE 0 Oops: 0000 [#1 CPU: 0 PID: 6159 Comm: modprobe Not tainted 5.1.0+ #33 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014 RIP: 0010:raw_notifier_chain_register+0x16/0x40 Code: 63 f8 66 90 e9 5d ff ff ff 90 90 90 90 90 90 90 90 90 90 90 55 48 8b 07 48 89 e5 48 85 c0 74 1c 8b 56 10 3b 50 10 7e 07 eb 12 <39> 50 10 7c 0d 48 8d 78 08 48 8b 40 08 48 85 c0 75 ee 48 89 46 08 RSP: 0018:ffffc90001c33c08 EFLAGS: 00010282 RAX: ffffffffa01c5420 RBX: ffffffffa01db420 RCX: 4fcef45928070a8b RDX: 0000000000000000 RSI: ffffffffa01db420 RDI: ffffffffa01b0068 RBP: ffffc90001c33c08 R08: 000000003e0a33d0 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000094443661 R12: ffff88822c320700 R13: ffff88823109be80 R14: 0000000000000000 R15: ffffc90001c33e78 FS: 00007fab8bd08540(0000) GS:ffff888237a00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffffa01c5430 CR3: 00000002297ea000 CR4: 00000000000006f0 Call Trace: register_netdevice_notifier+0x43/0x250 ? 0xffffffffa01e0000 dsa_slave_register_notifier+0x13/0x70 [dsa_core ? 0xffffffffa01e0000 dsa_init_module+0x2e/0x1000 [dsa_core do_one_initcall+0x6c/0x3cc ? do_init_module+0x22/0x1f1 ? rcu_read_lock_sched_held+0x97/0xb0 ? kmem_cache_alloc_trace+0x325/0x3b0 do_init_module+0x5b/0x1f1 load_module+0x1db1/0x2690 ? m_show+0x1d0/0x1d0 __do_sys_finit_module+0xc5/0xd0 __x64_sys_finit_module+0x15/0x20 do_syscall_64+0x6b/0x1d0 entry_SYSCALL_64_after_hwframe+0x49/0xbe Cleanup allocated resourses if there are errors, otherwise it will trgger memleak. Fixes: c9eb3e0f8701 ("net: dsa: Add support for learning FDB through notification") Signed-off-by: YueHaibing Reviewed-by: Vivien Didelot Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- net/dsa/dsa.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 36de4f2a3366..cb080efdc7b3 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -344,15 +344,22 @@ static int __init dsa_init_module(void) rc = dsa_slave_register_notifier(); if (rc) - return rc; + goto register_notifier_fail; rc = dsa_legacy_register(); if (rc) - return rc; + goto legacy_register_fail; dev_add_pack(&dsa_pack_type); return 0; + +legacy_register_fail: + dsa_slave_unregister_notifier(); +register_notifier_fail: + destroy_workqueue(dsa_owq); + + return rc; } module_init(dsa_init_module); From ff6ab32bd4e073976e4d8797b4d514a172cfe6cb Mon Sep 17 00:00:00 2001 From: Stephen Suryaputra Date: Mon, 6 May 2019 15:00:01 -0400 Subject: [PATCH 26/29] vrf: sit mtu should not be updated when vrf netdev is the link VRF netdev mtu isn't typically set and have an mtu of 65536. When the link of a tunnel is set, the tunnel mtu is changed from 1480 to the link mtu minus tunnel header. In the case of VRF netdev is the link, then the tunnel mtu becomes 65516. So, fix it by not setting the tunnel mtu in this case. Signed-off-by: Stephen Suryaputra Reviewed-by: David Ahern Signed-off-by: David S. Miller --- net/ipv6/sit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index b2109b74857d..971d60bf9640 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1084,7 +1084,7 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev) if (!tdev && tunnel->parms.link) tdev = __dev_get_by_index(tunnel->net, tunnel->parms.link); - if (tdev) { + if (tdev && !netif_is_l3_master(tdev)) { int t_hlen = tunnel->hlen + sizeof(struct iphdr); dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr); From 0504453139ef5a593c9587e1e851febee859c7d8 Mon Sep 17 00:00:00 2001 From: Harini Katakam Date: Tue, 7 May 2019 19:59:10 +0530 Subject: [PATCH 27/29] net: macb: Change interrupt and napi enable order in open Current order in open: -> Enable interrupts (macb_init_hw) -> Enable NAPI -> Start PHY Sequence of RX handling: -> RX interrupt occurs -> Interrupt is cleared and interrupt bits disabled in handler -> NAPI is scheduled -> In NAPI, RX budget is processed and RX interrupts are re-enabled With the above, on QEMU or fixed link setups (where PHY state doesn't matter), there's a chance macb RX interrupt occurs before NAPI is enabled. This will result in NAPI being scheduled before it is enabled. Fix this macb open by changing the order. Fixes: ae1f2a56d273 ("net: macb: Added support for many RX queues") Signed-off-by: Harini Katakam Acked-by: Nicolas Ferre Signed-off-by: David S. Miller --- drivers/net/ethernet/cadence/macb_main.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 3da2795e2486..a6535e226d84 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -2461,12 +2461,12 @@ static int macb_open(struct net_device *dev) goto pm_exit; } - bp->macbgem_ops.mog_init_rings(bp); - macb_init_hw(bp); - for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) napi_enable(&queue->napi); + bp->macbgem_ops.mog_init_rings(bp); + macb_init_hw(bp); + /* schedule a link state check */ phy_start(dev->phydev); From 822dd046d7e22a8d01728200a003da230e4c6f7f Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Tue, 7 May 2019 17:35:55 +0200 Subject: [PATCH 28/29] dt-bindings: net: Fix a typo in the phy-mode list for ethernet bindings The phy_mode "2000base-x" is actually supposed to be "1000base-x", even though the commit title of the original patch says otherwise. Fixes: 55601a880690 ("net: phy: Add 2000base-x, 2500base-x and rxaui modes") Signed-off-by: Maxime Chevallier Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- Documentation/devicetree/bindings/net/ethernet.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/net/ethernet.txt b/Documentation/devicetree/bindings/net/ethernet.txt index a68621580584..d45b5b56fa39 100644 --- a/Documentation/devicetree/bindings/net/ethernet.txt +++ b/Documentation/devicetree/bindings/net/ethernet.txt @@ -36,7 +36,7 @@ Documentation/devicetree/bindings/phy/phy-bindings.txt. * "smii" * "xgmii" * "trgmii" - * "2000base-x", + * "1000base-x", * "2500base-x", * "rxaui" * "xaui" From a3147770bea76c8dbad73eca3a24c2118da5e719 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Mon, 6 May 2019 23:57:54 +0800 Subject: [PATCH 29/29] cxgb4: Fix error path in cxgb4_init_module BUG: unable to handle kernel paging request at ffffffffa016a270 PGD 3270067 P4D 3270067 PUD 3271063 PMD 230bbd067 PTE 0 Oops: 0000 [#1 CPU: 0 PID: 6134 Comm: modprobe Not tainted 5.1.0+ #33 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014 RIP: 0010:atomic_notifier_chain_register+0x24/0x60 Code: 1f 80 00 00 00 00 55 48 89 e5 41 54 49 89 f4 53 48 89 fb e8 ae b4 38 01 48 8b 53 38 48 8d 4b 38 48 85 d2 74 20 45 8b 44 24 10 <44> 3b 42 10 7e 08 eb 13 44 39 42 10 7c 0d 48 8d 4a 08 48 8b 52 08 RSP: 0018:ffffc90000e2bc60 EFLAGS: 00010086 RAX: 0000000000000292 RBX: ffffffff83467240 RCX: ffffffff83467278 RDX: ffffffffa016a260 RSI: ffffffff83752140 RDI: ffffffff83467240 RBP: ffffc90000e2bc70 R08: 0000000000000000 R09: 0000000000000001 R10: 0000000000000000 R11: 00000000014fa61f R12: ffffffffa01c8260 R13: ffff888231091e00 R14: 0000000000000000 R15: ffffc90000e2be78 FS: 00007fbd8d7cd540(0000) GS:ffff888237a00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffffa016a270 CR3: 000000022c7e3000 CR4: 00000000000006f0 Call Trace: register_inet6addr_notifier+0x13/0x20 cxgb4_init_module+0x6c/0x1000 [cxgb4 ? 0xffffffffa01d7000 do_one_initcall+0x6c/0x3cc ? do_init_module+0x22/0x1f1 ? rcu_read_lock_sched_held+0x97/0xb0 ? kmem_cache_alloc_trace+0x325/0x3b0 do_init_module+0x5b/0x1f1 load_module+0x1db1/0x2690 ? m_show+0x1d0/0x1d0 __do_sys_finit_module+0xc5/0xd0 __x64_sys_finit_module+0x15/0x20 do_syscall_64+0x6b/0x1d0 entry_SYSCALL_64_after_hwframe+0x49/0xbe If pci_register_driver fails, register inet6addr_notifier is pointless. This patch fix the error path in cxgb4_init_module. Fixes: b5a02f503caa ("cxgb4 : Update ipv6 address handling api") Signed-off-by: YueHaibing Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 89179e316687..4bc0c357cb8e 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -6161,15 +6161,24 @@ static int __init cxgb4_init_module(void) ret = pci_register_driver(&cxgb4_driver); if (ret < 0) - debugfs_remove(cxgb4_debugfs_root); + goto err_pci; #if IS_ENABLED(CONFIG_IPV6) if (!inet6addr_registered) { - register_inet6addr_notifier(&cxgb4_inet6addr_notifier); - inet6addr_registered = true; + ret = register_inet6addr_notifier(&cxgb4_inet6addr_notifier); + if (ret) + pci_unregister_driver(&cxgb4_driver); + else + inet6addr_registered = true; } #endif + if (ret == 0) + return ret; + +err_pci: + debugfs_remove(cxgb4_debugfs_root); + return ret; }