- Kernel - mailweb.openeuler.org

[PATCH openEuler-1.0-LTS] net: qcom/emac: fix UAF in emac_remove
by Ze Zuo 11 Jun '24

11 Jun '24

From: Pavel Skripkin <paskripkin(a)gmail.com> stable inclusion from stable-v5.10.53 commit b560521eca03d0a2db6093a5a632cbdd0a0cf833 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9S29U CVE: CVE-2021-47311 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit ad297cd2db8953e2202970e9504cab247b6c7cb4 upstream. adpt is netdev private data and it cannot be used after free_netdev() call. Using adpt after free_netdev() can cause UAF bug. Fix it by moving free_netdev() at the end of the function. Fixes: 54e19bc74f33 ("net: qcom/emac: do not use devm on internal phy pdev") Signed-off-by: Pavel Skripkin <paskripkin(a)gmail.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Ze Zuo <zuoze1(a)huawei.com> --- drivers/net/ethernet/qualcomm/emac/emac.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index b10f2bcf8506..938602864c24 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -754,12 +754,13 @@ static int emac_remove(struct platform_device *pdev) put_device(&adpt->phydev->mdio.dev); mdiobus_unregister(adpt->mii_bus); - free_netdev(netdev); if (adpt->phy.digital) iounmap(adpt->phy.digital); iounmap(adpt->phy.base); + free_netdev(netdev); + return 0; } -- 2.25.1

2 1

[PATCH OLK-5.10] cvm_tsi: Fix security issue for Confidential cVM TSI
by Shengjie Li 11 Jun '24

11 Jun '24

virtcca inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IA45I1 -------------------------------- Fix security issue for Confidential cVM TSI: 1. Init TSI driver when config cvm_guest. 2. Modify the token structure to reduce the number of exposed variables. 3. Add a lock for obtaining the remote attestation report. Fixes: 31071f4b2a0b ("cvm_tsi: add cvm tsi interface") Signed-off-by: Shengjie Li <lishengjie12(a)huawei.com> --- arch/arm64/include/asm/cvm_smc.h | 22 +++---- arch/arm64/include/uapi/asm/cvm_tsi.h | 11 ++-- arch/arm64/kernel/cvm_tsi.c | 93 +++++++++++++-------------- 3 files changed, 63 insertions(+), 63 deletions(-) diff --git a/arch/arm64/include/asm/cvm_smc.h b/arch/arm64/include/asm/cvm_smc.h index c4d56333e3..91688bc169 100644 --- a/arch/arm64/include/asm/cvm_smc.h +++ b/arch/arm64/include/asm/cvm_smc.h @@ -124,30 +124,30 @@ static inline unsigned long tsi_measurement_read(struct cvm_measurement *cvm_mea return res.a0; } -static inline unsigned long tsi_attestation_token_init(struct cvm_attestation_cmd *attest_cmd) +static inline unsigned long tsi_attestation_token_init(unsigned char *challenge) { struct arm_smccc_res res; - unsigned char *challenge; + unsigned char *buf; - challenge = kmalloc(CHALLENGE_SIZE, GFP_KERNEL); - if (!challenge) + buf = kmalloc(CHALLENGE_SIZE, GFP_KERNEL); + if (!buf) return -ENOMEM; - memcpy(challenge, attest_cmd->challenge, CHALLENGE_SIZE); + memcpy(buf, challenge, CHALLENGE_SIZE); - arm_smccc_1_1_smc(SMC_TSI_ATTESTATION_TOKEN_INIT, virt_to_phys(challenge), &res); - kfree(challenge); + arm_smccc_1_1_smc(SMC_TSI_ATTESTATION_TOKEN_INIT, virt_to_phys(buf), &res); + kfree(buf); return res.a0; } -static inline unsigned long tsi_attestation_token_continue(struct cvm_attestation_cmd *attest_cmd) +static inline unsigned long tsi_attestation_token_continue(struct cvm_token_granule *token_granule) { struct arm_smccc_res res; - arm_smccc_1_1_smc(SMC_TSI_ATTESTATION_TOKEN_CONTINUE, virt_to_phys(attest_cmd->granule_ipa), - attest_cmd->offset, attest_cmd->size, &res); + arm_smccc_1_1_smc(SMC_TSI_ATTESTATION_TOKEN_CONTINUE, virt_to_phys(token_granule->ipa), + token_granule->offset, token_granule->size, &res); - attest_cmd->num_wr_bytes = res.a1; + token_granule->num_wr_bytes = res.a1; return res.a0; } diff --git a/arch/arm64/include/uapi/asm/cvm_tsi.h b/arch/arm64/include/uapi/asm/cvm_tsi.h index 43e17a0da0..1ed4386db2 100644 --- a/arch/arm64/include/uapi/asm/cvm_tsi.h +++ b/arch/arm64/include/uapi/asm/cvm_tsi.h @@ -55,10 +55,13 @@ struct cvm_measurement_extend { struct cvm_attestation_cmd { unsigned char challenge[CHALLENGE_SIZE]; /* input: challenge value */ - unsigned long token_size; /* return: challenge value */ - void *granule_head; - void *granule_ipa; /* IPA of the Granule to which the token will be written */ - unsigned long granule_count; + unsigned long token_size; /* return: token size */ +}; + +struct cvm_token_granule { + void *head; + void *ipa; /* IPA of the Granule to which the token will be written */ + unsigned long count; unsigned long offset; /* Offset within Granule to start of buffer in bytes */ unsigned long size; /* Size of buffer in bytes */ unsigned long num_wr_bytes; /* Number of bytes written to buffer */ diff --git a/arch/arm64/kernel/cvm_tsi.c b/arch/arm64/kernel/cvm_tsi.c index b48e5b17f4..a46f2b4724 100644 --- a/arch/arm64/kernel/cvm_tsi.c +++ b/arch/arm64/kernel/cvm_tsi.c @@ -4,6 +4,7 @@ #include <linux/slab.h> #include <linux/miscdevice.h> #include <linux/preempt.h> +#include <asm/cvm_guest.h> #include <asm/cvm_smc.h> #include <asm/cvm_tsi.h> @@ -16,20 +17,19 @@ struct attestation_token { static struct attestation_token token; +static DEFINE_SPINLOCK(token_lock); + static long tmm_tsi_ioctl(struct file *file, unsigned int cmd, unsigned long arg); -static int tmm_tsi_release(struct inode *inode, struct file *file); static ssize_t tmm_token_read(struct file *file, char __user *user_buffer, size_t size, loff_t *offset); static int tmm_get_tsi_version(struct cvm_tsi_version __user *arg); -static int tmm_get_attestation_token(struct cvm_attestation_cmd __user *arg, - struct attestation_token *attest_token); +static int tmm_get_attestation_token(struct cvm_attestation_cmd __user *arg); static int tmm_get_device_cert(struct cca_device_cert __user *arg); static const struct file_operations tmm_tsi_fops = { .owner = THIS_MODULE, .read = tmm_token_read, - .release = tmm_tsi_release, .unlocked_ioctl = tmm_tsi_ioctl }; @@ -44,11 +44,8 @@ static int __init tmm_tsi_init(void) unsigned long ver; int ret; - ver = tsi_get_version(); - if (ver == SMCCC_RET_NOT_SUPPORTED) { - pr_err("tmm_tsi: SMC return not supported!\n"); + if (!is_cvm_world()) return -EIO; - } ret = misc_register(&ioctl_dev); if (ret) { @@ -56,6 +53,11 @@ static int __init tmm_tsi_init(void) return ret; } + /* Allocate a large memory */ + token.buf = kzalloc(GRANULE_SIZE * MAX_TOKEN_GRANULE_PAGE, GFP_KERNEL); + if (!token.buf) + return -ENOMEM; + pr_warn("tmm_tsi: module loaded (version %lu.%lu).\n", TSI_ABI_VERSION_GET_MAJOR(ver), TSI_ABI_VERSION_GET_MINOR(ver)); @@ -65,8 +67,10 @@ static int __init tmm_tsi_init(void) static void __exit tmm_tsi_exit(void) { - if (token.buf != NULL) + if (token.buf != NULL) { + memset(token.buf, 0, GRANULE_SIZE * MAX_TOKEN_GRANULE_PAGE); kfree(token.buf); + } misc_deregister(&ioctl_dev); pr_warn("tmm_tsi: module unloaded.\n"); } @@ -80,7 +84,7 @@ static long tmm_tsi_ioctl(struct file *file, unsigned int cmd, unsigned long arg ret = tmm_get_tsi_version((struct cvm_tsi_version *)arg); break; case TMM_GET_ATTESTATION_TOKEN: - ret = tmm_get_attestation_token((struct cvm_attestation_cmd *)arg, &token); + ret = tmm_get_attestation_token((struct cvm_attestation_cmd *)arg); break; case TMM_GET_DEVICE_CERT: ret = tmm_get_device_cert((struct cca_device_cert *)arg); @@ -99,28 +103,25 @@ static ssize_t tmm_token_read(struct file *file, char __user *user_buffer, int ret; int to_copy; - if (*offset >= token.size) + spin_lock(&token_lock); + if (*offset >= token.size) { + spin_unlock(&token_lock); return 0; + } to_copy = min((int)size, (int)(token.size - *offset)); ret = copy_to_user(user_buffer, token.buf + *offset, to_copy); if (ret) { pr_err("tmm_tsi: copy token to user failed (%d)!\n", ret); + spin_unlock(&token_lock); return -1; } *offset += to_copy; + spin_unlock(&token_lock); return to_copy; } -static int tmm_tsi_release(struct inode *inode, struct file *file) -{ - if (token.buf != NULL) { - memset(token.buf, 0, GRANULE_SIZE * MAX_TOKEN_GRANULE_PAGE); - kfree(token.buf); - } - return 0; -} static int tmm_get_tsi_version(struct cvm_tsi_version __user *arg) { @@ -141,65 +142,61 @@ static int tmm_get_tsi_version(struct cvm_tsi_version __user *arg) return 0; } -static int tmm_get_attestation_token(struct cvm_attestation_cmd __user *arg, - struct attestation_token *attest_token) +static int tmm_get_attestation_token(struct cvm_attestation_cmd __user *arg) { unsigned long ret; - struct cvm_attestation_cmd cmd = {0}; + struct cvm_token_granule token_granule = {0}; + unsigned char challenge[CHALLENGE_SIZE]; - ret = copy_from_user(&(cmd.challenge), &(arg->challenge), sizeof(cmd.challenge)); + ret = copy_from_user(challenge, &(arg->challenge), CHALLENGE_SIZE); if (ret) { pr_err("tmm_tsi: copy data from user failed (%lu)!\n", ret); return -EFAULT; } - /* Allocate a large memory */ - attest_token->buf = kmalloc(GRANULE_SIZE * MAX_TOKEN_GRANULE_PAGE, GFP_KERNEL); - if (!attest_token->buf) - return -ENOMEM; - cmd.granule_head = attest_token->buf; - cmd.granule_ipa = cmd.granule_head; + spin_lock(&token_lock); + token_granule.head = token.buf; + token_granule.ipa = token_granule.head; - /* preempt_disable(); */ - - ret = tsi_attestation_token_init(&cmd); + ret = tsi_attestation_token_init(challenge); if (ret) { pr_err("tmm_tsi: tsi call tsi_attestation_token_init failed (%lu)!\n", ret); + spin_unlock(&token_lock); return -EIO; } do { /* Retrieve one Granule of data per loop iteration */ - cmd.granule_ipa = cmd.granule_head + - (unsigned long)(cmd.granule_count * GRANULE_SIZE); - cmd.offset = 0; + token_granule.ipa = token_granule.head + + (unsigned long)(token_granule.count * GRANULE_SIZE); + token_granule.offset = 0; do { /* Retrieve sub-Granule chunk of data per loop iteration */ - cmd.size = GRANULE_SIZE - cmd.offset; - ret = tsi_attestation_token_continue(&cmd); - cmd.offset += cmd.num_wr_bytes; - } while (ret == TSI_INCOMPLETE && cmd.offset < GRANULE_SIZE); + token_granule.size = GRANULE_SIZE - token_granule.offset; + ret = tsi_attestation_token_continue(&token_granule); + token_granule.offset += token_granule.num_wr_bytes; + } while (ret == TSI_INCOMPLETE && token_granule.offset < GRANULE_SIZE); - cmd.granule_count += 1; - if (cmd.granule_count >= MAX_TOKEN_GRANULE_PAGE && ret == TSI_INCOMPLETE) { + token_granule.count += 1; + if (token_granule.count >= MAX_TOKEN_GRANULE_PAGE && ret == TSI_INCOMPLETE) { pr_err("tmm_tsi: macro MAX_TOKEN_GRANULE_PAGE (%d) is too small!\n", MAX_TOKEN_GRANULE_PAGE); + spin_unlock(&token_lock); return -ENOMEM; } } while (ret == TSI_INCOMPLETE); - /* preempt_enable(); */ - /* Send to user space the total size of the token */ - cmd.granule_count = cmd.granule_count - 1; - cmd.token_size = (unsigned long)(GRANULE_SIZE * cmd.granule_count) + cmd.offset; - attest_token->size = cmd.token_size; + token_granule.count = token_granule.count - 1; + token.size = (unsigned long)(GRANULE_SIZE * token_granule.count) + token_granule.offset; - ret = copy_to_user(&(arg->token_size), &(cmd.token_size), sizeof(cmd.token_size)); + ret = copy_to_user(&(arg->token_size), &(token.size), sizeof(token.size)); if (ret) { pr_err("tmm_tsi: copy data to user failed (%lu)!\n", ret); + spin_unlock(&token_lock); return -EFAULT; } + spin_unlock(&token_lock); return 0; } @@ -211,7 +208,7 @@ static int tmm_get_device_cert(struct cca_device_cert __user *arg) unsigned long device_cert_size; device_cert_size = MAX_DEV_CERT_SIZE; - device_cert = kmalloc(device_cert_size, GFP_KERNEL); + device_cert = kzalloc(device_cert_size, GFP_KERNEL); if (!device_cert) return -ENOMEM; ret = tsi_get_device_cert(device_cert, &device_cert_size); -- 2.37.2.windows.2

2 1

[PATCH openEuler-22.03-LTS-SP1] tcp: defer shutdown(SEND_SHUTDOWN) for TCP_SYN_RECV sockets
by Zhengchao Shao 11 Jun '24

11 Jun '24

From: Eric Dumazet <edumazet(a)google.com> stable inclusion from stable-v5.10.217 commit 413c33b9f3bc36fdf719690a78824db9f88a9485 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9U4IQ CVE: CVE-2024-36905 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 94062790aedb505bdda209b10bea47b294d6394f ] TCP_SYN_RECV state is really special, it is only used by cross-syn connections, mostly used by fuzzers. In the following crash [1], syzbot managed to trigger a divide by zero in tcp_rcv_space_adjust() A socket makes the following state transitions, without ever calling tcp_init_transfer(), meaning tcp_init_buffer_space() is also not called. TCP_CLOSE connect() TCP_SYN_SENT TCP_SYN_RECV shutdown() -> tcp_shutdown(sk, SEND_SHUTDOWN) TCP_FIN_WAIT1 To fix this issue, change tcp_shutdown() to not perform a TCP_SYN_RECV -> TCP_FIN_WAIT1 transition, which makes no sense anyway. When tcp_rcv_state_process() later changes socket state from TCP_SYN_RECV to TCP_ESTABLISH, then look at sk->sk_shutdown to finally enter TCP_FIN_WAIT1 state, and send a FIN packet from a sane socket state. This means tcp_send_fin() can now be called from BH context, and must use GFP_ATOMIC allocations. [1] divide error: 0000 [#1] PREEMPT SMP KASAN NOPTI CPU: 1 PID: 5084 Comm: syz-executor358 Not tainted 6.9.0-rc6-syzkaller-00022-g98369dccd2f8 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/27/2024 RIP: 0010:tcp_rcv_space_adjust+0x2df/0x890 net/ipv4/tcp_input.c:767 Code: e3 04 4c 01 eb 48 8b 44 24 38 0f b6 04 10 84 c0 49 89 d5 0f 85 a5 03 00 00 41 8b 8e c8 09 00 00 89 e8 29 c8 48 0f af c3 31 d2 <48> f7 f1 48 8d 1c 43 49 8d 96 76 08 00 00 48 89 d0 48 c1 e8 03 48 RSP: 0018:ffffc900031ef3f0 EFLAGS: 00010246 RAX: 0c677a10441f8f42 RBX: 000000004fb95e7e RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: 0000000027d4b11f R08: ffffffff89e535a4 R09: 1ffffffff25e6ab7 R10: dffffc0000000000 R11: ffffffff8135e920 R12: ffff88802a9f8d30 R13: dffffc0000000000 R14: ffff88802a9f8d00 R15: 1ffff1100553f2da FS: 00005555775c0380(0000) GS:ffff8880b9500000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f1155bf2304 CR3: 000000002b9f2000 CR4: 0000000000350ef0 Call Trace: <TASK> tcp_recvmsg_locked+0x106d/0x25a0 net/ipv4/tcp.c:2513 tcp_recvmsg+0x25d/0x920 net/ipv4/tcp.c:2578 inet6_recvmsg+0x16a/0x730 net/ipv6/af_inet6.c:680 sock_recvmsg_nosec net/socket.c:1046 [inline] sock_recvmsg+0x109/0x280 net/socket.c:1068 ____sys_recvmsg+0x1db/0x470 net/socket.c:2803 ___sys_recvmsg net/socket.c:2845 [inline] do_recvmmsg+0x474/0xae0 net/socket.c:2939 __sys_recvmmsg net/socket.c:3018 [inline] __do_sys_recvmmsg net/socket.c:3041 [inline] __se_sys_recvmmsg net/socket.c:3034 [inline] __x64_sys_recvmmsg+0x199/0x250 net/socket.c:3034 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf5/0x240 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7faeb6363db9 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 c1 17 00 00 90 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 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffcc1997168 EFLAGS: 00000246 ORIG_RAX: 000000000000012b RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007faeb6363db9 RDX: 0000000000000001 RSI: 0000000020000bc0 RDI: 0000000000000005 RBP: 0000000000000000 R08: 0000000000000000 R09: 000000000000001c R10: 0000000000000122 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000001 R15: 0000000000000001 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot <syzkaller(a)googlegroups.com> Signed-off-by: Eric Dumazet <edumazet(a)google.com> Acked-by: Neal Cardwell <ncardwell(a)google.com> Link: https://lore.kernel.org/r/20240501125448.896529-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> --- net/ipv4/tcp.c | 4 ++-- net/ipv4/tcp_input.c | 2 ++ net/ipv4/tcp_output.c | 4 +++- 3 files changed, 7 insertions(+), 3 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 8eef91d14263..c8f65909a921 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2508,7 +2508,7 @@ void tcp_shutdown(struct sock *sk, int how) /* If we've already sent a FIN, or it's a closed state, skip this. */ if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_SYN_SENT | - TCPF_SYN_RECV | TCPF_CLOSE_WAIT)) { + TCPF_CLOSE_WAIT)) { /* Clear out any half completed packets. FIN if needed. */ if (tcp_close_state(sk)) tcp_send_fin(sk); @@ -2620,7 +2620,7 @@ void tcp_close(struct sock *sk, long timeout) * machine. State transitions: * * TCP_ESTABLISHED -> TCP_FIN_WAIT1 - * TCP_SYN_RECV -> TCP_FIN_WAIT1 (forget it, it's impossible) + * TCP_SYN_RECV -> TCP_FIN_WAIT1 (it is difficult) * TCP_CLOSE_WAIT -> TCP_LAST_ACK * * are legal only when FIN has been sent (i.e. in window), diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index f95a18b73677..9542f42b5d0c 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6514,6 +6514,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tcp_initialize_rcv_mss(sk); tcp_fast_path_on(tp); + if (sk->sk_shutdown & SEND_SHUTDOWN) + tcp_shutdown(sk, SEND_SHUTDOWN); break; case TCP_FIN_WAIT1: { diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 0996c71811d5..f32351a8f031 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3474,7 +3474,9 @@ void tcp_send_fin(struct sock *sk) return; } } else { - skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation); + skb = alloc_skb_fclone(MAX_TCP_HEADER, + sk_gfp_mask(sk, GFP_ATOMIC | + __GFP_NOWARN)); if (unlikely(!skb)) return; -- 2.34.1

2 1

[PATCH OLK-5.10] tcp: defer shutdown(SEND_SHUTDOWN) for TCP_SYN_RECV sockets
by Zhengchao Shao 11 Jun '24

11 Jun '24

From: Eric Dumazet <edumazet(a)google.com> stable inclusion from stable-v5.10.217 commit 413c33b9f3bc36fdf719690a78824db9f88a9485 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9U4IQ CVE: CVE-2024-36905 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 94062790aedb505bdda209b10bea47b294d6394f ] TCP_SYN_RECV state is really special, it is only used by cross-syn connections, mostly used by fuzzers. In the following crash [1], syzbot managed to trigger a divide by zero in tcp_rcv_space_adjust() A socket makes the following state transitions, without ever calling tcp_init_transfer(), meaning tcp_init_buffer_space() is also not called. TCP_CLOSE connect() TCP_SYN_SENT TCP_SYN_RECV shutdown() -> tcp_shutdown(sk, SEND_SHUTDOWN) TCP_FIN_WAIT1 To fix this issue, change tcp_shutdown() to not perform a TCP_SYN_RECV -> TCP_FIN_WAIT1 transition, which makes no sense anyway. When tcp_rcv_state_process() later changes socket state from TCP_SYN_RECV to TCP_ESTABLISH, then look at sk->sk_shutdown to finally enter TCP_FIN_WAIT1 state, and send a FIN packet from a sane socket state. This means tcp_send_fin() can now be called from BH context, and must use GFP_ATOMIC allocations. [1] divide error: 0000 [#1] PREEMPT SMP KASAN NOPTI CPU: 1 PID: 5084 Comm: syz-executor358 Not tainted 6.9.0-rc6-syzkaller-00022-g98369dccd2f8 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/27/2024 RIP: 0010:tcp_rcv_space_adjust+0x2df/0x890 net/ipv4/tcp_input.c:767 Code: e3 04 4c 01 eb 48 8b 44 24 38 0f b6 04 10 84 c0 49 89 d5 0f 85 a5 03 00 00 41 8b 8e c8 09 00 00 89 e8 29 c8 48 0f af c3 31 d2 <48> f7 f1 48 8d 1c 43 49 8d 96 76 08 00 00 48 89 d0 48 c1 e8 03 48 RSP: 0018:ffffc900031ef3f0 EFLAGS: 00010246 RAX: 0c677a10441f8f42 RBX: 000000004fb95e7e RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: 0000000027d4b11f R08: ffffffff89e535a4 R09: 1ffffffff25e6ab7 R10: dffffc0000000000 R11: ffffffff8135e920 R12: ffff88802a9f8d30 R13: dffffc0000000000 R14: ffff88802a9f8d00 R15: 1ffff1100553f2da FS: 00005555775c0380(0000) GS:ffff8880b9500000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f1155bf2304 CR3: 000000002b9f2000 CR4: 0000000000350ef0 Call Trace: <TASK> tcp_recvmsg_locked+0x106d/0x25a0 net/ipv4/tcp.c:2513 tcp_recvmsg+0x25d/0x920 net/ipv4/tcp.c:2578 inet6_recvmsg+0x16a/0x730 net/ipv6/af_inet6.c:680 sock_recvmsg_nosec net/socket.c:1046 [inline] sock_recvmsg+0x109/0x280 net/socket.c:1068 ____sys_recvmsg+0x1db/0x470 net/socket.c:2803 ___sys_recvmsg net/socket.c:2845 [inline] do_recvmmsg+0x474/0xae0 net/socket.c:2939 __sys_recvmmsg net/socket.c:3018 [inline] __do_sys_recvmmsg net/socket.c:3041 [inline] __se_sys_recvmmsg net/socket.c:3034 [inline] __x64_sys_recvmmsg+0x199/0x250 net/socket.c:3034 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf5/0x240 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7faeb6363db9 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 c1 17 00 00 90 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 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffcc1997168 EFLAGS: 00000246 ORIG_RAX: 000000000000012b RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007faeb6363db9 RDX: 0000000000000001 RSI: 0000000020000bc0 RDI: 0000000000000005 RBP: 0000000000000000 R08: 0000000000000000 R09: 000000000000001c R10: 0000000000000122 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000001 R15: 0000000000000001 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot <syzkaller(a)googlegroups.com> Signed-off-by: Eric Dumazet <edumazet(a)google.com> Acked-by: Neal Cardwell <ncardwell(a)google.com> Link: https://lore.kernel.org/r/20240501125448.896529-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> --- net/ipv4/tcp.c | 4 ++-- net/ipv4/tcp_input.c | 2 ++ net/ipv4/tcp_output.c | 4 +++- 3 files changed, 7 insertions(+), 3 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f1ab4fa04dce..758818ec3f8b 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2527,7 +2527,7 @@ void tcp_shutdown(struct sock *sk, int how) /* If we've already sent a FIN, or it's a closed state, skip this. */ if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_SYN_SENT | - TCPF_SYN_RECV | TCPF_CLOSE_WAIT)) { + TCPF_CLOSE_WAIT)) { /* Clear out any half completed packets. FIN if needed. */ if (tcp_close_state(sk)) tcp_send_fin(sk); @@ -2638,7 +2638,7 @@ void __tcp_close(struct sock *sk, long timeout) * machine. State transitions: * * TCP_ESTABLISHED -> TCP_FIN_WAIT1 - * TCP_SYN_RECV -> TCP_FIN_WAIT1 (forget it, it's impossible) + * TCP_SYN_RECV -> TCP_FIN_WAIT1 (it is difficult) * TCP_CLOSE_WAIT -> TCP_LAST_ACK * * are legal only when FIN has been sent (i.e. in window), diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2645dd64c382..0c783f8c0b36 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6541,6 +6541,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tcp_initialize_rcv_mss(sk); tcp_fast_path_on(tp); + if (sk->sk_shutdown & SEND_SHUTDOWN) + tcp_shutdown(sk, SEND_SHUTDOWN); break; case TCP_FIN_WAIT1: { diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 762f2009d61d..a1302d5cb98f 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3495,7 +3495,9 @@ void tcp_send_fin(struct sock *sk) return; } } else { - skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation); + skb = alloc_skb_fclone(MAX_TCP_HEADER, + sk_gfp_mask(sk, GFP_ATOMIC | + __GFP_NOWARN)); if (unlikely(!skb)) return; -- 2.34.1

2 1

[PATCH OLK-6.6] tcp: defer shutdown(SEND_SHUTDOWN) for TCP_SYN_RECV sockets
by Zhengchao Shao 11 Jun '24

11 Jun '24

From: Eric Dumazet <edumazet(a)google.com> stable inclusion from stable-v6.6.31 commit f47d0d32fa94e815fdd78b8b88684873e67939f4 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9U4IQ CVE: CVE-2024-36905 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 94062790aedb505bdda209b10bea47b294d6394f ] TCP_SYN_RECV state is really special, it is only used by cross-syn connections, mostly used by fuzzers. In the following crash [1], syzbot managed to trigger a divide by zero in tcp_rcv_space_adjust() A socket makes the following state transitions, without ever calling tcp_init_transfer(), meaning tcp_init_buffer_space() is also not called. TCP_CLOSE connect() TCP_SYN_SENT TCP_SYN_RECV shutdown() -> tcp_shutdown(sk, SEND_SHUTDOWN) TCP_FIN_WAIT1 To fix this issue, change tcp_shutdown() to not perform a TCP_SYN_RECV -> TCP_FIN_WAIT1 transition, which makes no sense anyway. When tcp_rcv_state_process() later changes socket state from TCP_SYN_RECV to TCP_ESTABLISH, then look at sk->sk_shutdown to finally enter TCP_FIN_WAIT1 state, and send a FIN packet from a sane socket state. This means tcp_send_fin() can now be called from BH context, and must use GFP_ATOMIC allocations. [1] divide error: 0000 [#1] PREEMPT SMP KASAN NOPTI CPU: 1 PID: 5084 Comm: syz-executor358 Not tainted 6.9.0-rc6-syzkaller-00022-g98369dccd2f8 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/27/2024 RIP: 0010:tcp_rcv_space_adjust+0x2df/0x890 net/ipv4/tcp_input.c:767 Code: e3 04 4c 01 eb 48 8b 44 24 38 0f b6 04 10 84 c0 49 89 d5 0f 85 a5 03 00 00 41 8b 8e c8 09 00 00 89 e8 29 c8 48 0f af c3 31 d2 <48> f7 f1 48 8d 1c 43 49 8d 96 76 08 00 00 48 89 d0 48 c1 e8 03 48 RSP: 0018:ffffc900031ef3f0 EFLAGS: 00010246 RAX: 0c677a10441f8f42 RBX: 000000004fb95e7e RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: 0000000027d4b11f R08: ffffffff89e535a4 R09: 1ffffffff25e6ab7 R10: dffffc0000000000 R11: ffffffff8135e920 R12: ffff88802a9f8d30 R13: dffffc0000000000 R14: ffff88802a9f8d00 R15: 1ffff1100553f2da FS: 00005555775c0380(0000) GS:ffff8880b9500000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f1155bf2304 CR3: 000000002b9f2000 CR4: 0000000000350ef0 Call Trace: <TASK> tcp_recvmsg_locked+0x106d/0x25a0 net/ipv4/tcp.c:2513 tcp_recvmsg+0x25d/0x920 net/ipv4/tcp.c:2578 inet6_recvmsg+0x16a/0x730 net/ipv6/af_inet6.c:680 sock_recvmsg_nosec net/socket.c:1046 [inline] sock_recvmsg+0x109/0x280 net/socket.c:1068 ____sys_recvmsg+0x1db/0x470 net/socket.c:2803 ___sys_recvmsg net/socket.c:2845 [inline] do_recvmmsg+0x474/0xae0 net/socket.c:2939 __sys_recvmmsg net/socket.c:3018 [inline] __do_sys_recvmmsg net/socket.c:3041 [inline] __se_sys_recvmmsg net/socket.c:3034 [inline] __x64_sys_recvmmsg+0x199/0x250 net/socket.c:3034 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf5/0x240 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7faeb6363db9 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 c1 17 00 00 90 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 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffcc1997168 EFLAGS: 00000246 ORIG_RAX: 000000000000012b RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007faeb6363db9 RDX: 0000000000000001 RSI: 0000000020000bc0 RDI: 0000000000000005 RBP: 0000000000000000 R08: 0000000000000000 R09: 000000000000001c R10: 0000000000000122 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000001 R15: 0000000000000001 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot <syzkaller(a)googlegroups.com> Signed-off-by: Eric Dumazet <edumazet(a)google.com> Acked-by: Neal Cardwell <ncardwell(a)google.com> Link: https://lore.kernel.org/r/20240501125448.896529-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> --- net/ipv4/tcp.c | 4 ++-- net/ipv4/tcp_input.c | 2 ++ net/ipv4/tcp_output.c | 4 +++- 3 files changed, 7 insertions(+), 3 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2ff83f2897ba..0f1380c3fcf4 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2714,7 +2714,7 @@ void tcp_shutdown(struct sock *sk, int how) /* If we've already sent a FIN, or it's a closed state, skip this. */ if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_SYN_SENT | - TCPF_SYN_RECV | TCPF_CLOSE_WAIT)) { + TCPF_CLOSE_WAIT)) { /* Clear out any half completed packets. FIN if needed. */ if (tcp_close_state(sk)) tcp_send_fin(sk); @@ -2823,7 +2823,7 @@ void __tcp_close(struct sock *sk, long timeout) * machine. State transitions: * * TCP_ESTABLISHED -> TCP_FIN_WAIT1 - * TCP_SYN_RECV -> TCP_FIN_WAIT1 (forget it, it's impossible) + * TCP_SYN_RECV -> TCP_FIN_WAIT1 (it is difficult) * TCP_CLOSE_WAIT -> TCP_LAST_ACK * * are legal only when FIN has been sent (i.e. in window), diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 7529412827de..259e48b57494 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6654,6 +6654,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tcp_initialize_rcv_mss(sk); tcp_fast_path_on(tp); + if (sk->sk_shutdown & SEND_SHUTDOWN) + tcp_shutdown(sk, SEND_SHUTDOWN); break; case TCP_FIN_WAIT1: { diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index f6950a42de20..cc18b8b70be0 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3585,7 +3585,9 @@ void tcp_send_fin(struct sock *sk) return; } } else { - skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation); + skb = alloc_skb_fclone(MAX_TCP_HEADER, + sk_gfp_mask(sk, GFP_ATOMIC | + __GFP_NOWARN)); if (unlikely(!skb)) return; -- 2.34.1

2 1

[PATCH openEuler-22.03-LTS-SP1] mmc: mmc_spi: fix error handling in mmc_spi_probe()
by Li Nan 11 Jun '24

11 Jun '24

From: Yang Yingliang <yangyingliang(a)huawei.com> stable inclusion from stable-v5.10.169 commit 0b3edcb24bd81b3b2e3dac89f4733bfd47d283be category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9R4N9 CVE: CVE-2023-52708 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… ---------------------------------------------------- commit cf4c9d2ac1e42c7d18b921bec39486896645b714 upstream. If mmc_add_host() fails, it doesn't need to call mmc_remove_host(), or it will cause null-ptr-deref, because of deleting a not added device in mmc_remove_host(). To fix this, goto label 'fail_glue_init', if mmc_add_host() fails, and change the label 'fail_add_host' to 'fail_gpiod_request'. Fixes: 15a0580ced08 ("mmc_spi host driver") Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Cc:stable@vger.kernel.org Link: https://lore.kernel.org/r/20230131013835.3564011-1-yangyingliang@huawei.com Signed-off-by: Ulf Hansson <ulf.hansson(a)linaro.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Li Nan <linan122(a)huawei.com> --- drivers/mmc/host/mmc_spi.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c index 02f4fd26e76a..1d814919eb6b 100644 --- a/drivers/mmc/host/mmc_spi.c +++ b/drivers/mmc/host/mmc_spi.c @@ -1450,7 +1450,7 @@ static int mmc_spi_probe(struct spi_device *spi) status = mmc_add_host(mmc); if (status != 0) - goto fail_add_host; + goto fail_glue_init; /* * Index 0 is card detect @@ -1458,7 +1458,7 @@ static int mmc_spi_probe(struct spi_device *spi) */ status = mmc_gpiod_request_cd(mmc, NULL, 0, false, 1000); if (status == -EPROBE_DEFER) - goto fail_add_host; + goto fail_gpiod_request; if (!status) { /* * The platform has a CD GPIO signal that may support @@ -1473,7 +1473,7 @@ static int mmc_spi_probe(struct spi_device *spi) /* Index 1 is write protect/read only */ status = mmc_gpiod_request_ro(mmc, NULL, 1, 0); if (status == -EPROBE_DEFER) - goto fail_add_host; + goto fail_gpiod_request; if (!status) has_ro = true; @@ -1487,7 +1487,7 @@ static int mmc_spi_probe(struct spi_device *spi) ? ", cd polling" : ""); return 0; -fail_add_host: +fail_gpiod_request: mmc_remove_host(mmc); fail_glue_init: mmc_spi_dma_free(host); -- 2.39.2

2 1

[PATCH OLK-5.10 0/2] Fix CVE-2024-36949
by Zheng Zucheng 11 Jun '24

11 Jun '24

Fix CVE-2024-36949 Mukul Joshi (1): drm/amdkfd: Rework kfd_locked handling Zhigang Luo (1): amd/amdkfd: sync all devices to wait all processes being evicted drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 7 ------- drivers/gpu/drm/amd/amdkfd/kfd_device.c | 23 ++++++++++++++--------- drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 2 ++ drivers/gpu/drm/amd/amdkfd/kfd_process.c | 8 +++++++- 4 files changed, 23 insertions(+), 17 deletions(-) -- 2.34.1

2 3

[PATCH openEuler-22.03-LTS-SP1] netfilter: nft_set_pipapo: do not free live element
by Wei Li 11 Jun '24

11 Jun '24

From: Florian Westphal <fw(a)strlen.de> mainline inclusion from mainline-v6.9-rc5 commit 3cfc9ec039af60dbd8965ae085b2c2ccdcfbe1cc category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9JFG2 CVE: CVE-2024-26924 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit?i… -------------------------------- Pablo reports a crash with large batches of elements with a back-to-back add/remove pattern. Quoting Pablo: add_elem("00000000") timeout 100 ms ... add_elem("0000000X") timeout 100 ms del_elem("0000000X") <---------------- delete one that was just added ... add_elem("00005000") timeout 100 ms 1) nft_pipapo_remove() removes element 0000000X Then, KASAN shows a splat. Looking at the remove function there is a chance that we will drop a rule that maps to a non-deactivated element. Removal happens in two steps, first we do a lookup for key k and return the to-be-removed element and mark it as inactive in the next generation. Then, in a second step, the element gets removed from the set/map. The _remove function does not work correctly if we have more than one element that share the same key. This can happen if we insert an element into a set when the set already holds an element with same key, but the element mapping to the existing key has timed out or is not active in the next generation. In such case its possible that removal will unmap the wrong element. If this happens, we will leak the non-deactivated element, it becomes unreachable. The element that got deactivated (and will be freed later) will remain reachable in the set data structure, this can result in a crash when such an element is retrieved during lookup (stale pointer). Add a check that the fully matching key does in fact map to the element that we have marked as inactive in the deactivation step. If not, we need to continue searching. Add a bug/warn trap at the end of the function as well, the remove function must not ever be called with an invisible/unreachable/non-existent element. v2: avoid uneeded temporary variable (Stefano) Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges") Reported-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Reviewed-by: Stefano Brivio <sbrivio(a)redhat.com> Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Conflicts: net/netfilter/nft_set_pipapo.c [lw: fix context conflict due to lack of commit f8bf7706151a ("netfilter: nf_tables: integrate pipapo into commit protocol")] Signed-off-by: Wei Li <liwei391(a)huawei.com> --- net/netfilter/nft_set_pipapo.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 9ca18f4c4eaf..ef6fb41fd31f 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1932,6 +1932,8 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, rules_fx = rules_f0; nft_pipapo_for_each_field(f, i, m) { + bool last = i == m->field_count - 1; + if (!pipapo_match_field(f, start, rules_fx, match_start, match_end)) break; @@ -1944,17 +1946,19 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, match_start += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); match_end += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); - } - if (i == m->field_count) { - priv->dirty = true; - pipapo_drop(m, rulemap); - pipapo_commit(set); - return; + if (last && f->mt[rulemap[i].to].e == e) { + priv->dirty = true; + pipapo_drop(m, rulemap); + pipapo_commit(set); + return; + } } first_rule += rules_f0; } + + WARN_ON_ONCE(1); /* elem_priv not found * } /** -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS-SP1 0/2] Fix CVE-2024-36949
by Zheng Zucheng 11 Jun '24

11 Jun '24

Fix CVE-2024-36949 Mukul Joshi (1): drm/amdkfd: Rework kfd_locked handling Zhigang Luo (1): amd/amdkfd: sync all devices to wait all processes being evicted drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 7 ------- drivers/gpu/drm/amd/amdkfd/kfd_device.c | 23 ++++++++++++++--------- drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 2 ++ drivers/gpu/drm/amd/amdkfd/kfd_process.c | 8 +++++++- 4 files changed, 23 insertions(+), 17 deletions(-) -- 2.34.1

2 3

[openEuler-22.03-LTS-SP1] powerpc/powernv: Add a null pointer check in opal_powercap_init()
by Zhang Zekun 11 Jun '24

11 Jun '24

From: Kunwu Chan <chentao(a)kylinos.cn> stable inclusion from stable-v5.10.209 commit a67a04ad05acb56640798625e73fa54d6d41cce1 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9Q9HG CVE: CVE-2023-52696 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit e123015c0ba859cf48aa7f89c5016cc6e98e018d ] kasprintf() returns a pointer to dynamically allocated memory which can be NULL upon failure. Fixes: b9ef7b4b867f ("powerpc: Convert to using %pOFn instead of device_node.name") Signed-off-by: Kunwu Chan <chentao(a)kylinos.cn> Signed-off-by: Michael Ellerman <mpe(a)ellerman.id.au> Link: https://msgid.link/20231126095739.1501990-1-chentao@kylinos.cn Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: sanglipeng1 <sanglipeng1(a)jd.com> Signed-off-by: Zhang Zekun <zhangzekun11(a)huawei.com> --- arch/powerpc/platforms/powernv/opal-powercap.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/powerpc/platforms/powernv/opal-powercap.c b/arch/powerpc/platforms/powernv/opal-powercap.c index c16d44f6f1d1..ce9ec3962cef 100644 --- a/arch/powerpc/platforms/powernv/opal-powercap.c +++ b/arch/powerpc/platforms/powernv/opal-powercap.c @@ -196,6 +196,12 @@ void __init opal_powercap_init(void) j = 0; pcaps[i].pg.name = kasprintf(GFP_KERNEL, "%pOFn", node); + if (!pcaps[i].pg.name) { + kfree(pcaps[i].pattrs); + kfree(pcaps[i].pg.attrs); + goto out_pcaps_pattrs; + } + if (has_min) { powercap_add_attr(min, "powercap-min", &pcaps[i].pattrs[j]); -- 2.17.1

1 0

[PATCH OLK-5.10] cvm: enhance security for cvm host feature
by Ju Fu 11 Jun '24

11 Jun '24

virtcca inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9TM0T -------------------------------- enhance security for cvm host feature Signed-off-by: Ju Fu <fuju1(a)huawei.com> --- arch/arm64/include/asm/kvm_emulate.h | 4 ++- arch/arm64/include/asm/kvm_tmi.h | 34 ++------------------ arch/arm64/include/asm/kvm_tmm.h | 2 +- arch/arm64/kvm/cvm.c | 48 ++++++++++++++++++++++++---- drivers/irqchip/irq-gic-v3-its.c | 2 +- 5 files changed, 49 insertions(+), 41 deletions(-) diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 540563623..1271df56c 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -571,7 +571,9 @@ static inline enum cvm_state kvm_cvm_state(struct kvm *kvm) { struct cvm *cvm = kvm->arch.cvm; - return cvm && READ_ONCE(cvm->state); + if (!cvm) + return 0; + return READ_ONCE(cvm->state); } #endif #endif /* __ARM64_KVM_EMULATE_H__ */ diff --git a/arch/arm64/include/asm/kvm_tmi.h b/arch/arm64/include/asm/kvm_tmi.h index 536594017..b89680f31 100644 --- a/arch/arm64/include/asm/kvm_tmi.h +++ b/arch/arm64/include/asm/kvm_tmi.h @@ -18,22 +18,6 @@ #define TMM_TTT_LEVEL_2 2 #define TMM_TTT_LEVEL_3 3 -#ifdef CONFIG_CVM_HOST_FVP_PLAT -#define CVM_MEM_BASE ULL(0x8800000000) /* choose FVP platform to run cVM */ -#define VQ_NUM 3 -#else -#define CVM_MEM_BASE ULL(0x800000000) /* choose qemu platform to run cVM */ -#define VQ_NUM 3 -#endif - -#define MEM_SEG_NUMS 2 - -/* define in QEMU hw/arm/virt.c */ -#define VIRT_PCIE_MMIO 0x10000000 /* 256MB */ -#define VIRT_PCIE_MMIO_SIZE 0x1000000 /* 16MB */ -#define VIRT_HIGH_PCIE_ECAM 0x8000000000 /* 512GB */ -#define VIRT_HIGH_PCIE_ECAM_SIZE 0x12000000 /* 288MB */ - /* TMI error codes. */ #define TMI_SUCCESS 0 #define TMI_ERROR_INPUT 1 @@ -214,6 +198,8 @@ struct tmi_tec_run { #define TMI_NO_MEASURE_CONTENT U(0) #define TMI_MEASURE_CONTENT U(1) +#define CVM_IPA_MAX_VAL (1UL << 48) + /* * SMC_TMM_INIT_COMPLETE is the only function in the TMI that originates from * the CVM world and is handled by the SPMD. The remaining functions are @@ -264,7 +250,7 @@ struct tmi_tec_run { #define TMI_ABI_VERSION_GET_MAJOR(_version) ((_version) >> 16) #define TMI_ABI_VERSION_GET_MINOR(_version) ((_version) & 0xFFFF) -#define TMI_ABI_VERSION_MAJOR U(0x0) +#define TMI_ABI_VERSION_MAJOR U(0x1) /* KVM_CAP_ARM_TMM on VM fd */ #define KVM_CAP_ARM_TMM_CONFIG_CVM_HOST 0 @@ -330,20 +316,6 @@ struct kvm_cap_arm_tmm_populate_region_args { __u32 reserved[3]; }; -enum tmi_tmm_mem_type { - TMM_MEM_TYPE_RD, - TMM_MEM_TYPE_TEC, - TMM_MEM_TYPE_TTT, - TMM_MEM_TYPE_CVM_PA, -}; - -enum tmi_tmm_map_size { - TMM_MEM_MAP_SIZE_4K, - TMM_MEM_MAP_SIZE_2M, - TMM_MEM_MAP_SIZE_1G, - TMM_MEM_MAP_SIZE_MAX, -}; - static inline bool tmm_is_addr_ttt_level_aligned(uint64_t addr, int level) { uint64_t mask = (1 << (12 + 9 * (3 - level))) - 1; diff --git a/arch/arm64/include/asm/kvm_tmm.h b/arch/arm64/include/asm/kvm_tmm.h index 88fa0873c..8cc7a35c9 100644 --- a/arch/arm64/include/asm/kvm_tmm.h +++ b/arch/arm64/include/asm/kvm_tmm.h @@ -8,7 +8,7 @@ #include <uapi/linux/kvm.h> enum cvm_state { - CVM_STATE_NONE, + CVM_STATE_NONE = 1, CVM_STATE_NEW, CVM_STATE_ACTIVE, CVM_STATE_DYING diff --git a/arch/arm64/kvm/cvm.c b/arch/arm64/kvm/cvm.c index 70521fec8..73b8daede 100644 --- a/arch/arm64/kvm/cvm.c +++ b/arch/arm64/kvm/cvm.c @@ -181,8 +181,9 @@ int kvm_arm_create_cvm(struct kvm *kvm) memcpy(cvm->params->rpv, &cvm->cvm_vmid, sizeof(cvm->cvm_vmid)); cvm->rd = tmi_cvm_create(__pa(cvm->params), numa_set); if (!cvm->rd) { - kvm_err("KVM creates cVM: %d\n", cvm->cvm_vmid); + kvm_err("KVM creates cVM failed: %d\n", cvm->cvm_vmid); ret = -ENOMEM; + goto out; } WRITE_ONCE(cvm->state, CVM_STATE_NEW); @@ -341,7 +342,7 @@ int kvm_cvm_populate_par_region(struct kvm *kvm, u64 numa_set, */ ipa = ALIGN_DOWN(ipa, map_size); - if (is_data_create_region(ipa_base, args)) { + if (is_data_create_region(ipa, args)) { pfn = gfn_to_pfn_memslot(memslot, gpa_to_gfn(ipa)); if (is_error_pfn(pfn)) { ret = -EFAULT; @@ -602,6 +603,7 @@ static int kvm_populate_ram_region(struct kvm *kvm, u64 map_size, static int kvm_populate_ipa_cvm_range(struct kvm *kvm, struct kvm_cap_arm_tmm_populate_region_args *args) { + struct cvm *cvm = (struct cvm *)kvm->arch.cvm; u64 l2_granule = cvm_granule_size(TMM_TTT_LEVEL_2); phys_addr_t ipa_base1, ipa_end2; @@ -612,7 +614,10 @@ static int kvm_populate_ipa_cvm_range(struct kvm *kvm, !IS_ALIGNED(args->populate_ipa_base2, PAGE_SIZE) || !IS_ALIGNED(args->populate_ipa_size2, PAGE_SIZE)) return -EINVAL; - if (args->populate_ipa_base2 < args->populate_ipa_base1 + args->populate_ipa_size1) + + if (args->populate_ipa_base1 < cvm->loader_start || + args->populate_ipa_base2 < args->populate_ipa_base1 + args->populate_ipa_size1 || + cvm->dtb_end < args->populate_ipa_base2 + args->populate_ipa_size2) return -EINVAL; if (args->flags & ~TMI_MEASURE_CONTENT) @@ -755,6 +760,26 @@ int kvm_init_tmm(void) return 0; } +static bool is_numa_ipa_range_valid(struct kvm_numa_info *numa_info) +{ + unsigned long i; + struct kvm_numa_node *numa_node, *prev_numa_node; + + prev_numa_node = NULL; + for (i = 0; i < numa_info->numa_cnt; i++) { + numa_node = &numa_info->numa_nodes[i]; + if (numa_node->ipa_start + numa_node->ipa_size < numa_node->ipa_start) + return false; + if (prev_numa_node && + numa_node->ipa_start < prev_numa_node->ipa_start + prev_numa_node->ipa_size) + return false; + prev_numa_node = numa_node; + } + if (numa_node->ipa_start + numa_node->ipa_size > CVM_IPA_MAX_VAL) + return false; + return true; +} + int kvm_load_user_data(struct kvm *kvm, unsigned long arg) { struct kvm_user_data user_data; @@ -766,26 +791,34 @@ int kvm_load_user_data(struct kvm *kvm, unsigned long arg) return -EFAULT; if (copy_from_user(&user_data, argp, sizeof(user_data))) - return -EFAULT; + return -EINVAL; numa_info = &user_data.numa_info; if (numa_info->numa_cnt > MAX_NUMA_NODE) - return -EFAULT; + return -EINVAL; if (numa_info->numa_cnt > 0) { unsigned long i, total_size = 0; struct kvm_numa_node *numa_node = &numa_info->numa_nodes[0]; unsigned long ipa_end = numa_node->ipa_start + numa_node->ipa_size; + if (!is_numa_ipa_range_valid(numa_info)) + return -EINVAL; if (user_data.loader_start < numa_node->ipa_start || user_data.dtb_end > ipa_end) - return -EFAULT; + return -EINVAL; for (i = 0; i < numa_info->numa_cnt; i++) total_size += numa_info->numa_nodes[i].ipa_size; if (total_size != user_data.ram_size) - return -EFAULT; + return -EINVAL; } + if (user_data.image_end <= user_data.loader_start || + user_data.initrd_start < user_data.image_end || + user_data.dtb_end < user_data.initrd_start || + user_data.ram_size < user_data.dtb_end - user_data.loader_start) + return -EINVAL; + cvm->loader_start = user_data.loader_start; cvm->image_end = user_data.image_end; cvm->initrd_start = user_data.initrd_start; @@ -871,6 +904,7 @@ int kvm_init_cvm_vm(struct kvm *kvm) return -ENOMEM; cvm->params = params; + WRITE_ONCE(cvm->state, CVM_STATE_NONE); return 0; } diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 2c2f23f35..153930d01 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -2905,7 +2905,7 @@ static void its_free_tables(struct its_node *its) for (i = 0; i < GITS_BASER_NR_REGS; i++) { if (its->tables[i].base) { #ifdef CONFIG_CVM_GUEST - if (!is_cvm_world()) + if (is_cvm_world()) its_free_shared_pages(its->tables[i].base, its->tables[i].order); else -- 2.25.1.windows.1

2 1

[PATCH openEuler-22.03-LTS-SP1 0/4] Fix CVE-2024-35915
by Zheng Zucheng 11 Jun '24

11 Jun '24

Fix CVE-2024-35915 Ryosuke Yasuoka (3): nfc: nci: Fix uninit-value in nci_dev_up and nci_ntf_packet nfc: nci: Fix uninit-value in nci_rx_work nfc: nci: Fix handling of zero-length payload packets in nci_rx_work() Tetsuo Handa (1): nfc: nci: Fix kcov check in nci_rx_work() net/nfc/nci/core.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) -- 2.34.1

2 5

[PATCH openEuler-22.03-LTS-SP1 0/4] Fix CVE-2024-35915
by Zheng Zucheng 11 Jun '24

11 Jun '24

Fix CVE-2024-35915 Ryosuke Yasuoka (3): nfc: nci: Fix uninit-value in nci_dev_up and nci_ntf_packet nfc: nci: Fix uninit-value in nci_rx_work nfc: nci: Fix handling of zero-length payload packets in nci_rx_work() Tetsuo Handa (1): nfc: nci: Fix kcov check in nci_rx_work() net/nfc/nci/core.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) -- 2.34.1

2 5

[PATCH openEuler-1.0-LTS 0/4] Fix CVE-2024-35915
by Zheng Zucheng 11 Jun '24

11 Jun '24

Fix CVE-2024-35915 Ryosuke Yasuoka (3): nfc: nci: Fix uninit-value in nci_dev_up and nci_ntf_packet nfc: nci: Fix uninit-value in nci_rx_work nfc: nci: Fix handling of zero-length payload packets in nci_rx_work() Tetsuo Handa (1): nfc: nci: Fix kcov check in nci_rx_work() net/nfc/nci/core.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) -- 2.34.1

2 5

[PATCH openEuler-1.0-LTS] nfp: Fix memory leak in nfp_cpp_area_cache_add()
by Li Huafei 11 Jun '24

11 Jun '24

From: Jianglei Nie <niejianglei2021(a)163.com> stable inclusion from stable-v4.19.221 commit eb51f639ef3fd5498b7def290ed8681b6aadd9a7 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9S258 CVE: CVE-2021-47516 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit c56c96303e9289cc34716b1179597b6f470833de upstream. In line 800 (#1), nfp_cpp_area_alloc() allocates and initializes a CPP area structure. But in line 807 (#2), when the cache is allocated failed, this CPP area structure is not freed, which will result in memory leak. We can fix it by freeing the CPP area when the cache is allocated failed (#2). 792 int nfp_cpp_area_cache_add(struct nfp_cpp *cpp, size_t size) 793 { 794 struct nfp_cpp_area_cache *cache; 795 struct nfp_cpp_area *area; 800 area = nfp_cpp_area_alloc(cpp, NFP_CPP_ID(7, NFP_CPP_ACTION_RW, 0), 801 0, size); // #1: allocates and initializes 802 if (!area) 803 return -ENOMEM; 805 cache = kzalloc(sizeof(*cache), GFP_KERNEL); 806 if (!cache) 807 return -ENOMEM; // #2: missing free 817 return 0; 818 } Fixes: 4cb584e0ee7d ("nfp: add CPP access core") Signed-off-by: Jianglei Nie <niejianglei2021(a)163.com> Acked-by: Simon Horman <simon.horman(a)corigine.com> Link: https://lore.kernel.org/r/20211209061511.122535-1-niejianglei2021@163.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Li Huafei <lihuafei1(a)huawei.com> --- drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c index 6f5d69293a252..f7b354e796cb6 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c @@ -803,8 +803,10 @@ int nfp_cpp_area_cache_add(struct nfp_cpp *cpp, size_t size) return -ENOMEM; cache = kzalloc(sizeof(*cache), GFP_KERNEL); - if (!cache) + if (!cache) { + nfp_cpp_area_free(area); return -ENOMEM; + } cache->id = 0; cache->addr = 0; -- 2.25.1

2 1

[PATCH openEuler-1.0-LTS] comedi: vmk80xx: fix bulk-buffer overflow
by Liu Shixin 11 Jun '24

11 Jun '24

From: Johan Hovold <johan(a)kernel.org> stable inclusion from stable-v4.19.217 commit 063f576c43d589a4c153554b681d32b3f8317c7b category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9RD4V CVE: CVE-2021-47474 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 78cdfd62bd54af615fba9e3ca1ba35de39d3871d upstream. The driver is using endpoint-sized buffers but must not assume that the tx and rx buffers are of equal size or a malicious device could overflow the slab-allocated receive buffer when doing bulk transfers. Fixes: 985cafccbf9b ("Staging: Comedi: vmk80xx: Add k8061 support") Cc: stable(a)vger.kernel.org # 2.6.31 Signed-off-by: Johan Hovold <johan(a)kernel.org> Reviewed-by: Ian Abbott <abbotti(a)mev.co.uk> Link: https://lore.kernel.org/r/20211025114532.4599-5-johan@kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Liu Shixin <liushixin2(a)huawei.com> --- drivers/staging/comedi/drivers/vmk80xx.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/drivers/staging/comedi/drivers/vmk80xx.c b/drivers/staging/comedi/drivers/vmk80xx.c index 2bbfaf54220e..ff52299c1fb0 100644 --- a/drivers/staging/comedi/drivers/vmk80xx.c +++ b/drivers/staging/comedi/drivers/vmk80xx.c @@ -159,22 +159,20 @@ static void vmk80xx_do_bulk_msg(struct comedi_device *dev) __u8 rx_addr; unsigned int tx_pipe; unsigned int rx_pipe; - size_t size; + size_t tx_size; + size_t rx_size; tx_addr = devpriv->ep_tx->bEndpointAddress; rx_addr = devpriv->ep_rx->bEndpointAddress; tx_pipe = usb_sndbulkpipe(usb, tx_addr); rx_pipe = usb_rcvbulkpipe(usb, rx_addr); - - /* - * The max packet size attributes of the K8061 - * input/output endpoints are identical - */ - size = usb_endpoint_maxp(devpriv->ep_tx); + tx_size = usb_endpoint_maxp(devpriv->ep_tx); + rx_size = usb_endpoint_maxp(devpriv->ep_rx); usb_bulk_msg(usb, tx_pipe, devpriv->usb_tx_buf, - size, NULL, devpriv->ep_tx->bInterval); - usb_bulk_msg(usb, rx_pipe, devpriv->usb_rx_buf, size, NULL, HZ * 10); + tx_size, NULL, devpriv->ep_tx->bInterval); + + usb_bulk_msg(usb, rx_pipe, devpriv->usb_rx_buf, rx_size, NULL, HZ * 10); } static int vmk80xx_read_packet(struct comedi_device *dev) -- 2.25.1

2 1

[PATCH OLK-6.6] drm/amd/display: Atom Integrated System Info v2_2 for DCN35
by Yi Yang 11 Jun '24

11 Jun '24

From: Gabe Teeger <gabe.teeger(a)amd.com> stable inclusion from stable-v6.6.31 commit 7e3030774431eb093165a31baff040d35446fb8b category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9TNHC CVE: CVE-2024-36897 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 9a35d205f466501dcfe5625ca313d944d0ac2d60 ] New request from KMD/VBIOS in order to support new UMA carveout model. This fixes a null dereference from accessing Ctx->dc_bios->integrated_info while it was NULL. DAL parses through the BIOS and extracts the necessary integrated_info but was missing a case for the new BIOS version 2.3. Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas(a)amd.com> Acked-by: Aurabindo Pillai <aurabindo.pillai(a)amd.com> Signed-off-by: Gabe Teeger <gabe.teeger(a)amd.com> Tested-by: Daniel Wheeler <daniel.wheeler(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yi Yang <yiyang13(a)huawei.com> --- drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c index 4c3c4c8de1cf..93720cf069d7 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c @@ -2961,6 +2961,7 @@ static enum bp_result construct_integrated_info( result = get_integrated_info_v2_1(bp, info); break; case 2: + case 3: result = get_integrated_info_v2_2(bp, info); break; default: -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS-SP1] iomap: Don't finish dio under irq when there exists pages
by Zhihao Cheng 11 Jun '24

11 Jun '24

hulk inclusion category: perf bugzilla: https://gitee.com/openeuler/kernel/issues/IA4DAW CVE: NA -------------------------------- Fixes: 6fac6d0e975afe1dec ("ext4: Optimize endio process for DIO overwrites") Signed-off-by: Zhihao Cheng <chengzhihao(a)huaweicloud.com> --- fs/iomap/direct-io.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 892a4f8109e5..f6b3311fcc3e 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -177,6 +177,11 @@ static void iomap_dio_bio_end_io(struct bio *bio) goto release_bio; } + if ((dio->flags & IOMAP_DIO_INLINE_COMP) && dio->size && + (dio->flags & IOMAP_DIO_WRITE) && + file_inode(iocb->ki_filp)->i_mapping->nrpages) + dio->flags &= ~IOMAP_DIO_INLINE_COMP; + /* * Flagged with IOMAP_DIO_INLINE_COMP, we can complete it inline */ -- 2.31.1

2 1

[PATCH openEuler-1.0-LTS] net: ti: fix UAF in tlan_remove_one
by Liu Shixin 11 Jun '24

11 Jun '24

From: Pavel Skripkin <paskripkin(a)gmail.com> stable inclusion from stable-v4.19.199 commit a0a817b2d308fac090a05cbbe80988e073ac5193 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9S1ZJ CVE: CVE-2021-47310 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 0336f8ffece62f882ab3012820965a786a983f70 upstream. priv is netdev private data and it cannot be used after free_netdev() call. Using priv after free_netdev() can cause UAF bug. Fix it by moving free_netdev() at the end of the function. Fixes: 1e0a8b13d355 ("tlan: cancel work at remove path") Signed-off-by: Pavel Skripkin <paskripkin(a)gmail.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Liu Shixin <liushixin2(a)huawei.com> --- drivers/net/ethernet/ti/tlan.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/ti/tlan.c b/drivers/net/ethernet/ti/tlan.c index 93d142867c2a..c6595b4ff55a 100644 --- a/drivers/net/ethernet/ti/tlan.c +++ b/drivers/net/ethernet/ti/tlan.c @@ -312,9 +312,8 @@ static void tlan_remove_one(struct pci_dev *pdev) pci_release_regions(pdev); #endif - free_netdev(dev); - cancel_work_sync(&priv->tlan_tqueue); + free_netdev(dev); } static void tlan_start(struct net_device *dev) -- 2.25.1

2 1

[PATCH OLK-5.10] iomap: Don't finish dio under irq when there exists pages
by Zhihao Cheng 11 Jun '24

11 Jun '24

hulk inclusion category: perf bugzilla: https://gitee.com/openeuler/kernel/issues/IA4DAW CVE: NA -------------------------------- Fixes: 48774b90b5677bdb4 ("ext4: Optimize endio process for DIO overwrites") Signed-off-by: Zhihao Cheng <chengzhihao(a)huaweicloud.com> --- fs/iomap/direct-io.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 892a4f8109e5..f6b3311fcc3e 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -177,6 +177,11 @@ static void iomap_dio_bio_end_io(struct bio *bio) goto release_bio; } + if ((dio->flags & IOMAP_DIO_INLINE_COMP) && dio->size && + (dio->flags & IOMAP_DIO_WRITE) && + file_inode(iocb->ki_filp)->i_mapping->nrpages) + dio->flags &= ~IOMAP_DIO_INLINE_COMP; + /* * Flagged with IOMAP_DIO_INLINE_COMP, we can complete it inline */ -- 2.31.1

2 1

[PATCH openEuler-22.03-LTS-SP1] powerpc/powernv: Add a null pointer check in opal_event_init()
by Guo Mengqi 11 Jun '24

11 Jun '24

From: Kunwu Chan <chentao(a)kylinos.cn> stable inclusion from stable-v5.10.209 commit e6ad05e3ae9c84c5a71d7bb2d44dc845ae7990cf category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9Q9IH Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 8649829a1dd25199bbf557b2621cedb4bf9b3050 ] kasprintf() returns a pointer to dynamically allocated memory which can be NULL upon failure. Fixes: 2717a33d6074 ("powerpc/opal-irqchip: Use interrupt names if present") Signed-off-by: Kunwu Chan <chentao(a)kylinos.cn> Signed-off-by: Michael Ellerman <mpe(a)ellerman.id.au> Link: https://msgid.link/20231127030755.1546750-1-chentao@kylinos.cn Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Wang Hai <wanghai38(a)huawei.com> --- arch/powerpc/platforms/powernv/opal-irqchip.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/powerpc/platforms/powernv/opal-irqchip.c b/arch/powerpc/platforms/powernv/opal-irqchip.c index c164419e254d..dcec0f760c8f 100644 --- a/arch/powerpc/platforms/powernv/opal-irqchip.c +++ b/arch/powerpc/platforms/powernv/opal-irqchip.c @@ -278,6 +278,8 @@ int __init opal_event_init(void) else name = kasprintf(GFP_KERNEL, "opal"); + if (!name) + continue; /* Install interrupt handler */ rc = request_irq(r->start, opal_interrupt, r->flags & IRQD_TRIGGER_MASK, name, NULL); -- 2.17.1

2 1

[PATCH openEuler-22.03-LTS-SP1] ACPI: video: check for error while searching for backlight device parent
by Yu Liao 11 Jun '24

11 Jun '24

From: Nikita Kiryushin <kiryushin(a)ancud.ru> stable inclusion from stable-v5.10.209 commit c4e1a0ef0b4782854c9b77a333ca912b392bed2f category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9Q9CJ CVE: CVE-2023-52693 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit ccd45faf4973746c4f30ea41eec864e5cf191099 ] If acpi_get_parent() called in acpi_video_dev_register_backlight() fails, for example, because acpi_ut_acquire_mutex() fails inside acpi_get_parent), this can lead to incorrect (uninitialized) acpi_parent handle being passed to acpi_get_pci_dev() for detecting the parent pci device. Check acpi_get_parent() result and set parent device only in case of success. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 9661e92c10a9 ("acpi: tie ACPI backlight devices to PCI devices if possible") Signed-off-by: Nikita Kiryushin <kiryushin(a)ancud.ru> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yu Liao <liaoyu15(a)huawei.com> --- drivers/acpi/acpi_video.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c index cf6c9ffe04a2..9d384656323a 100644 --- a/drivers/acpi/acpi_video.c +++ b/drivers/acpi/acpi_video.c @@ -1788,12 +1788,12 @@ static void acpi_video_dev_register_backlight(struct acpi_video_device *device) return; count++; - acpi_get_parent(device->dev->handle, &acpi_parent); - - pdev = acpi_get_pci_dev(acpi_parent); - if (pdev) { - parent = &pdev->dev; - pci_dev_put(pdev); + if (ACPI_SUCCESS(acpi_get_parent(device->dev->handle, &acpi_parent))) { + pdev = acpi_get_pci_dev(acpi_parent); + if (pdev) { + parent = &pdev->dev; + pci_dev_put(pdev); + } } memset(&props, 0, sizeof(struct backlight_properties)); -- 2.25.1

2 1

[PATCH OLK-5.10] netfilter: nft_set_pipapo: do not free live element
by Guo Mengqi 11 Jun '24

11 Jun '24

From: Florian Westphal <fw(a)strlen.de> mainline inclusion from mainline-v6.9-rc5 commit 3cfc9ec039af60dbd8965ae085b2c2ccdcfbe1cc category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9JFG2 CVE: CVE-2024-26924 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit?i… -------------------------------- Pablo reports a crash with large batches of elements with a back-to-back add/remove pattern. Quoting Pablo: add_elem("00000000") timeout 100 ms ... add_elem("0000000X") timeout 100 ms del_elem("0000000X") <---------------- delete one that was just added ... add_elem("00005000") timeout 100 ms 1) nft_pipapo_remove() removes element 0000000X Then, KASAN shows a splat. Looking at the remove function there is a chance that we will drop a rule that maps to a non-deactivated element. Removal happens in two steps, first we do a lookup for key k and return the to-be-removed element and mark it as inactive in the next generation. Then, in a second step, the element gets removed from the set/map. The _remove function does not work correctly if we have more than one element that share the same key. This can happen if we insert an element into a set when the set already holds an element with same key, but the element mapping to the existing key has timed out or is not active in the next generation. In such case its possible that removal will unmap the wrong element. If this happens, we will leak the non-deactivated element, it becomes unreachable. The element that got deactivated (and will be freed later) will remain reachable in the set data structure, this can result in a crash when such an element is retrieved during lookup (stale pointer). Add a check that the fully matching key does in fact map to the element that we have marked as inactive in the deactivation step. If not, we need to continue searching. Add a bug/warn trap at the end of the function as well, the remove function must not ever be called with an invisible/unreachable/non-existent element. v2: avoid uneeded temporary variable (Stefano) Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges") Reported-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Reviewed-by: Stefano Brivio <sbrivio(a)redhat.com> Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Wei Li <liwei391(a)huawei.com> --- net/netfilter/nft_set_pipapo.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 9c311b6f37af..8c43335d59f6 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1980,6 +1980,8 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, rules_fx = rules_f0; nft_pipapo_for_each_field(f, i, m) { + bool last = i == m->field_count - 1; + if (!pipapo_match_field(f, start, rules_fx, match_start, match_end)) break; @@ -1992,16 +1994,18 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, match_start += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); match_end += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); - } - if (i == m->field_count) { - priv->dirty = true; - pipapo_drop(m, rulemap); - return; + if (last && f->mt[rulemap[i].to].e == e) { + priv->dirty = true; + pipapo_drop(m, rulemap); + return; + } } first_rule += rules_f0; } + + WARN_ON_ONCE(1); /* elem_priv not found */ } /** -- 2.17.1

2 1

[PATCH openEuler-22.03-LTS-SP1] aio: fix mremap after fork null-deref
by Guo Mengqi 11 Jun '24

11 Jun '24

From: Seth Jenkins <sethjenkins(a)google.com> stable inclusion from stable-v5.10.169 commit c261f798f7baa8080cf0214081d43d5f86bb073f category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9K29F Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 81e9d6f8647650a7bead74c5f926e29970e834d1 upstream. Commit e4a0d3e720e7 ("aio: Make it possible to remap aio ring") introduced a null-deref if mremap is called on an old aio mapping after fork as mm->ioctx_table will be set to NULL. [jmoyer(a)redhat.com: fix 80 column issue] Link: https://lkml.kernel.org/r/x49sffq4nvg.fsf@segfault.boston.devel.redhat.com Fixes: e4a0d3e720e7 ("aio: Make it possible to remap aio ring") Signed-off-by: Seth Jenkins <sethjenkins(a)google.com> Signed-off-by: Jeff Moyer <jmoyer(a)redhat.com> Cc: Alexander Viro <viro(a)zeniv.linux.org.uk> Cc: Benjamin LaHaise <bcrl(a)kvack.org> Cc: Jann Horn <jannh(a)google.com> Cc: Pavel Emelyanov <xemul(a)parallels.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Wang Hai <wanghai38(a)huawei.com> --- fs/aio.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/aio.c b/fs/aio.c index 0063e4bc0aad..00641a1ad0b3 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -335,6 +335,9 @@ static int aio_ring_mremap(struct vm_area_struct *vma) spin_lock(&mm->ioctx_lock); rcu_read_lock(); table = rcu_dereference(mm->ioctx_table); + if (!table) + goto out_unlock; + for (i = 0; i < table->nr; i++) { struct kioctx *ctx; @@ -348,6 +351,7 @@ static int aio_ring_mremap(struct vm_area_struct *vma) } } +out_unlock: rcu_read_unlock(); spin_unlock(&mm->ioctx_lock); return res; -- 2.17.1

2 1

[PATCH OLK-5.10 0/2] CVE-2022-48652
by Guo Mengqi 11 Jun '24

11 Jun '24

CVE-2022-48652 Anatolii Gerasymenko (1): ice: ethtool: Prohibit improper channel config for DCB Ding Hui (1): ice: Fix crash by keep old cfg when update TCs more than queues drivers/net/ethernet/intel/ice/ice_ethtool.c | 10 ++++++ drivers/net/ethernet/intel/ice/ice_lib.c | 36 ++++++++++++++++---- 2 files changed, 40 insertions(+), 6 deletions(-) -- 2.17.1

2 3

[PATCH openEuler-22.03-LTS-SP1 0/2] CVE-2022-48652
by Guo Mengqi 11 Jun '24

11 Jun '24

CVE-2022-48652 Anatolii Gerasymenko (1): ice: ethtool: Prohibit improper channel config for DCB Ding Hui (1): ice: Fix crash by keep old cfg when update TCs more than queues drivers/net/ethernet/intel/ice/ice_ethtool.c | 10 ++++++ drivers/net/ethernet/intel/ice/ice_lib.c | 36 ++++++++++++++++---- 2 files changed, 40 insertions(+), 6 deletions(-) -- 2.17.1

2 3

[PATCH OLK-5.10] usb: typec: ucsi: Limit read size on v1.2
by Zheng Zucheng 11 Jun '24

11 Jun '24

From: Abhishek Pandit-Subedi <abhishekpandit(a)chromium.org> stable inclusion from stable-v6.6.27 commit 266f403ec47573046dee4bcebda82777ce702c40 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9QGLG CVE: CVE-2024-35924 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit b3db266fb031fba88c423d4bb8983a73a3db6527 ] Between UCSI 1.2 and UCSI 2.0, the size of the MESSAGE_IN region was increased from 16 to 256. In order to avoid overflowing reads for older systems, add a mechanism to use the read UCSI version to truncate read sizes on UCSI v1.2. Tested-by: Neil Armstrong <neil.armstrong(a)linaro.org> Reviewed-by: Prashant Malani <pmalani(a)chromium.org> Reviewed-by: Heikki Krogerus <heikki.krogerus(a)linux.intel.com> Signed-off-by: Abhishek Pandit-Subedi <abhishekpandit(a)chromium.org> Link: https://lore.kernel.org/r/20240209143723.v5.1.Iacf5570a66b82b73ef03daa6557e… Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: ZhangPeng <zhangpeng362(a)huawei.com> Conflicts: drivers/usb/typec/ucsi/ucsi.c [Some contexts around ucsi_register different. No functional impact.] Signed-off-by: Zheng Zucheng <zhengzucheng(a)huawei.com> --- drivers/usb/typec/ucsi/ucsi.c | 26 ++++++++++++++++++++++++-- drivers/usb/typec/ucsi/ucsi.h | 11 +++++++++++ 2 files changed, 35 insertions(+), 2 deletions(-) diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index 4cd5c291cdf3..be3104dd56a2 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -36,6 +36,19 @@ */ #define UCSI_SWAP_TIMEOUT_MS 5000 +static int ucsi_read_message_in(struct ucsi *ucsi, void *buf, + size_t buf_size) +{ + /* + * Below UCSI 2.0, MESSAGE_IN was limited to 16 bytes. Truncate the + * reads here. + */ + if (ucsi->version <= UCSI_VERSION_1_2) + buf_size = clamp(buf_size, (size_t)0, (size_t)16); + + return ucsi->ops->read(ucsi, UCSI_MESSAGE_IN, buf, buf_size); +} + static int ucsi_acknowledge_command(struct ucsi *ucsi) { u64 ctrl; @@ -72,7 +85,7 @@ static int ucsi_read_error(struct ucsi *ucsi) if (ret < 0) return ret; - ret = ucsi->ops->read(ucsi, UCSI_MESSAGE_IN, &error, sizeof(error)); + ret = ucsi_read_message_in(ucsi, &error, sizeof(error)); if (ret) return ret; @@ -165,7 +178,7 @@ int ucsi_send_command(struct ucsi *ucsi, u64 command, length = ret; if (data) { - ret = ucsi->ops->read(ucsi, UCSI_MESSAGE_IN, data, size); + ret = ucsi_read_message_in(ucsi, data, size); if (ret) goto out; } @@ -1303,6 +1316,15 @@ int ucsi_register(struct ucsi *ucsi) if (!ucsi->version) return -ENODEV; + /* + * Version format is JJ.M.N (JJ = Major version, M = Minor version, + * N = sub-minor version). + */ + dev_dbg(ucsi->dev, "Registered UCSI interface with version %x.%x.%x", + UCSI_BCD_GET_MAJOR(ucsi->version), + UCSI_BCD_GET_MINOR(ucsi->version), + UCSI_BCD_GET_SUBMINOR(ucsi->version)); + queue_work(system_long_wq, &ucsi->work); return 0; diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h index fce23ad16c6d..32f25dc88258 100644 --- a/drivers/usb/typec/ucsi/ucsi.h +++ b/drivers/usb/typec/ucsi/ucsi.h @@ -21,6 +21,17 @@ struct ucsi_altmode; #define UCSI_CONTROL 8 #define UCSI_MESSAGE_IN 16 #define UCSI_MESSAGE_OUT 32 +#define UCSIv2_MESSAGE_OUT 272 + +/* UCSI versions */ +#define UCSI_VERSION_1_2 0x0120 +#define UCSI_VERSION_2_0 0x0200 +#define UCSI_VERSION_2_1 0x0210 +#define UCSI_VERSION_3_0 0x0300 + +#define UCSI_BCD_GET_MAJOR(_v_) (((_v_) >> 8) & 0xFF) +#define UCSI_BCD_GET_MINOR(_v_) (((_v_) >> 4) & 0x0F) +#define UCSI_BCD_GET_SUBMINOR(_v_) ((_v_) & 0x0F) /* Command Status and Connector Change Indication (CCI) bits */ #define UCSI_CCI_CONNECTOR(_c_) (((_c_) & GENMASK(7, 1)) >> 1) -- 2.34.1

2 1

[PATCH openEuler-22.03-LTS-SP1] usb: typec: ucsi: Limit read size on v1.2
by Zheng Zucheng 11 Jun '24

11 Jun '24

From: Abhishek Pandit-Subedi <abhishekpandit(a)chromium.org> stable inclusion from stable-v6.6.27 commit 266f403ec47573046dee4bcebda82777ce702c40 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9QGLG CVE: CVE-2024-35924 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit b3db266fb031fba88c423d4bb8983a73a3db6527 ] Between UCSI 1.2 and UCSI 2.0, the size of the MESSAGE_IN region was increased from 16 to 256. In order to avoid overflowing reads for older systems, add a mechanism to use the read UCSI version to truncate read sizes on UCSI v1.2. Tested-by: Neil Armstrong <neil.armstrong(a)linaro.org> Reviewed-by: Prashant Malani <pmalani(a)chromium.org> Reviewed-by: Heikki Krogerus <heikki.krogerus(a)linux.intel.com> Signed-off-by: Abhishek Pandit-Subedi <abhishekpandit(a)chromium.org> Link: https://lore.kernel.org/r/20240209143723.v5.1.Iacf5570a66b82b73ef03daa6557e… Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: ZhangPeng <zhangpeng362(a)huawei.com> Conflicts: drivers/usb/typec/ucsi/ucsi.c [Some contexts around ucsi_register different. No functional impact.] Signed-off-by: Zheng Zucheng <zhengzucheng(a)huawei.com> --- drivers/usb/typec/ucsi/ucsi.c | 26 ++++++++++++++++++++++++-- drivers/usb/typec/ucsi/ucsi.h | 11 +++++++++++ 2 files changed, 35 insertions(+), 2 deletions(-) diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index 4cd5c291cdf3..be3104dd56a2 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -36,6 +36,19 @@ */ #define UCSI_SWAP_TIMEOUT_MS 5000 +static int ucsi_read_message_in(struct ucsi *ucsi, void *buf, + size_t buf_size) +{ + /* + * Below UCSI 2.0, MESSAGE_IN was limited to 16 bytes. Truncate the + * reads here. + */ + if (ucsi->version <= UCSI_VERSION_1_2) + buf_size = clamp(buf_size, (size_t)0, (size_t)16); + + return ucsi->ops->read(ucsi, UCSI_MESSAGE_IN, buf, buf_size); +} + static int ucsi_acknowledge_command(struct ucsi *ucsi) { u64 ctrl; @@ -72,7 +85,7 @@ static int ucsi_read_error(struct ucsi *ucsi) if (ret < 0) return ret; - ret = ucsi->ops->read(ucsi, UCSI_MESSAGE_IN, &error, sizeof(error)); + ret = ucsi_read_message_in(ucsi, &error, sizeof(error)); if (ret) return ret; @@ -165,7 +178,7 @@ int ucsi_send_command(struct ucsi *ucsi, u64 command, length = ret; if (data) { - ret = ucsi->ops->read(ucsi, UCSI_MESSAGE_IN, data, size); + ret = ucsi_read_message_in(ucsi, data, size); if (ret) goto out; } @@ -1303,6 +1316,15 @@ int ucsi_register(struct ucsi *ucsi) if (!ucsi->version) return -ENODEV; + /* + * Version format is JJ.M.N (JJ = Major version, M = Minor version, + * N = sub-minor version). + */ + dev_dbg(ucsi->dev, "Registered UCSI interface with version %x.%x.%x", + UCSI_BCD_GET_MAJOR(ucsi->version), + UCSI_BCD_GET_MINOR(ucsi->version), + UCSI_BCD_GET_SUBMINOR(ucsi->version)); + queue_work(system_long_wq, &ucsi->work); return 0; diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h index fce23ad16c6d..32f25dc88258 100644 --- a/drivers/usb/typec/ucsi/ucsi.h +++ b/drivers/usb/typec/ucsi/ucsi.h @@ -21,6 +21,17 @@ struct ucsi_altmode; #define UCSI_CONTROL 8 #define UCSI_MESSAGE_IN 16 #define UCSI_MESSAGE_OUT 32 +#define UCSIv2_MESSAGE_OUT 272 + +/* UCSI versions */ +#define UCSI_VERSION_1_2 0x0120 +#define UCSI_VERSION_2_0 0x0200 +#define UCSI_VERSION_2_1 0x0210 +#define UCSI_VERSION_3_0 0x0300 + +#define UCSI_BCD_GET_MAJOR(_v_) (((_v_) >> 8) & 0xFF) +#define UCSI_BCD_GET_MINOR(_v_) (((_v_) >> 4) & 0x0F) +#define UCSI_BCD_GET_SUBMINOR(_v_) ((_v_) & 0x0F) /* Command Status and Connector Change Indication (CCI) bits */ #define UCSI_CCI_CONNECTOR(_c_) (((_c_) & GENMASK(7, 1)) >> 1) -- 2.34.1

2 1

[PATCH OLK-5.10] iomap: Don't finish dio under irq when there exists pages
by Zhihao Cheng 11 Jun '24

11 Jun '24

From: Zhihao Cheng <chengzhihao1(a)huawei.com> hulk inclusion category: perf bugzilla: https://gitee.com/openeuler/kernel/issues/IA4DAW CVE: NA -------------------------------- Fixes: 48774b90b5677bdb4 ("ext4: Optimize endio process for DIO overwrites") Signed-off-by: Zhihao Cheng <chengzhihao1(a)huawei.com> Signed-off-by: Zhihao Cheng <chengzhihao(a)huaweicloud.com> --- fs/iomap/direct-io.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 892a4f8109e5..540f300c5685 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -180,7 +180,9 @@ static void iomap_dio_bio_end_io(struct bio *bio) /* * Flagged with IOMAP_DIO_INLINE_COMP, we can complete it inline */ - if (dio->flags & IOMAP_DIO_INLINE_COMP) { + if ((dio->flags & IOMAP_DIO_INLINE_COMP) && + !(dio->size && (dio->flags & IOMAP_DIO_WRITE) && + file_inode(iocb->ki_filp)->i_mapping->nrpages)) { iomap_dio_complete_work(&dio->aio.work); goto release_bio; } -- 2.31.1

2 1

[PATCH OLK-6.6] clk: sunxi-ng: h6: Reparent CPUX during PLL CPUX rate change
by Yu Liao 11 Jun '24

11 Jun '24

From: Jernej Skrabec <jernej.skrabec(a)gmail.com> stable inclusion from stable-v6.6.31 commit 0b82eb134d2942ecc669e2ab2be3f0a58d79428a category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9TOGH CVE: CVE-2023-52882 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 7e91ed763dc07437777bd012af7a2bd4493731ff ] While PLL CPUX clock rate change when CPU is running from it works in vast majority of cases, now and then it causes instability. This leads to system crashes and other undefined behaviour. After a lot of testing (30+ hours) while also doing a lot of frequency switches, we can't observe any instability issues anymore when doing reparenting to stable clock like 24 MHz oscillator. Fixes: 524353ea480b ("clk: sunxi-ng: add support for the Allwinner H6 CCU") Reported-by: Chad Wagner <wagnerch42(a)gmail.com> Link: https://forum.libreelec.tv/thread/27295-orange-pi-3-lts-freezes/ Tested-by: Chad Wagner <wagnerch42(a)gmail.com> Reviewed-by: Chen-Yu Tsai <wens(a)csie.org> Link: https://lore.kernel.org/r/20231013181712.2128037-1-jernej.skrabec@gmail.com Signed-off-by: Jernej Skrabec <jernej.skrabec(a)gmail.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/clk/sunxi-ng/ccu-sun50i-h6.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-h6.c b/drivers/clk/sunxi-ng/ccu-sun50i-h6.c index 42568c616181..892df807275c 100644 --- a/drivers/clk/sunxi-ng/ccu-sun50i-h6.c +++ b/drivers/clk/sunxi-ng/ccu-sun50i-h6.c @@ -1181,11 +1181,18 @@ static const u32 usb2_clk_regs[] = { SUN50I_H6_USB3_CLK_REG, }; +static struct ccu_mux_nb sun50i_h6_cpu_nb = { + .common = &cpux_clk.common, + .cm = &cpux_clk.mux, + .delay_us = 1, + .bypass_index = 0, /* index of 24 MHz oscillator */ +}; + static int sun50i_h6_ccu_probe(struct platform_device *pdev) { void __iomem *reg; + int i, ret; u32 val; - int i; reg = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(reg)) @@ -1252,7 +1259,15 @@ static int sun50i_h6_ccu_probe(struct platform_device *pdev) val |= BIT(24); writel(val, reg + SUN50I_H6_HDMI_CEC_CLK_REG); - return devm_sunxi_ccu_probe(&pdev->dev, reg, &sun50i_h6_ccu_desc); + ret = devm_sunxi_ccu_probe(&pdev->dev, reg, &sun50i_h6_ccu_desc); + if (ret) + return ret; + + /* Reparent CPU during PLL CPUX rate changes */ + ccu_mux_notifier_register(pll_cpux_clk.common.hw.clk, + &sun50i_h6_cpu_nb); + + return 0; } static const struct of_device_id sun50i_h6_ccu_ids[] = { -- 2.33.0

2 1

[PATCH OLK-5.10] firewire: ohci: mask bus reset interrupts between ISR and bottom half
by Ze Zuo 11 Jun '24

11 Jun '24

From: Adam Goldman <adamg(a)pobox.com> stable inclusion from stable-v5.10.217 commit fa273f312334246c909475c5868e6daab889cc8c category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9UOCQ CVE: CVE-2024-36950 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 752e3c53de0fa3b7d817a83050b6699b8e9c6ec9 ] In the FireWire OHCI interrupt handler, if a bus reset interrupt has occurred, mask bus reset interrupts until bus_reset_work has serviced and cleared the interrupt. Normally, we always leave bus reset interrupts masked. We infer the bus reset from the self-ID interrupt that happens shortly thereafter. A scenario where we unmask bus reset interrupts was introduced in 2008 in a007bb857e0b26f5d8b73c2ff90782d9c0972620: If OHCI_PARAM_DEBUG_BUSRESETS (8) is set in the debug parameter bitmask, we will unmask bus reset interrupts so we can log them. irq_handler logs the bus reset interrupt. However, we can't clear the bus reset event flag in irq_handler, because we won't service the event until later. irq_handler exits with the event flag still set. If the corresponding interrupt is still unmasked, the first bus reset will usually freeze the system due to irq_handler being called again each time it exits. This freeze can be reproduced by loading firewire_ohci with "modprobe firewire_ohci debug=-1" (to enable all debugging output). Apparently there are also some cases where bus_reset_work will get called soon enough to clear the event, and operation will continue normally. This freeze was first reported a few months after a007bb85 was committed, but until now it was never fixed. The debug level could safely be set to -1 through sysfs after the module was loaded, but this would be ineffectual in logging bus reset interrupts since they were only unmasked during initialization. irq_handler will now leave the event flag set but mask bus reset interrupts, so irq_handler won't be called again and there will be no freeze. If OHCI_PARAM_DEBUG_BUSRESETS is enabled, bus_reset_work will unmask the interrupt after servicing the event, so future interrupts will be caught as desired. As a side effect to this change, OHCI_PARAM_DEBUG_BUSRESETS can now be enabled through sysfs in addition to during initial module loading. However, when enabled through sysfs, logging of bus reset interrupts will be effective only starting with the second bus reset, after bus_reset_work has executed. Signed-off-by: Adam Goldman <adamg(a)pobox.com> Signed-off-by: Takashi Sakamoto <o-takashi(a)sakamocchi.jp> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Ze Zuo <zuoze1(a)huawei.com> --- drivers/firewire/ohci.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index 45d19cc0aeac..9b2471d12783 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -2049,6 +2049,8 @@ static void bus_reset_work(struct work_struct *work) ohci->generation = generation; reg_write(ohci, OHCI1394_IntEventClear, OHCI1394_busReset); + if (param_debug & OHCI_PARAM_DEBUG_BUSRESETS) + reg_write(ohci, OHCI1394_IntMaskSet, OHCI1394_busReset); if (ohci->quirks & QUIRK_RESET_PACKET) ohci->request_generation = generation; @@ -2115,12 +2117,14 @@ static irqreturn_t irq_handler(int irq, void *data) return IRQ_NONE; /* - * busReset and postedWriteErr must not be cleared yet + * busReset and postedWriteErr events must not be cleared yet * (OHCI 1.1 clauses 7.2.3.2 and 13.2.8.1) */ reg_write(ohci, OHCI1394_IntEventClear, event & ~(OHCI1394_busReset | OHCI1394_postedWriteErr)); log_irqs(ohci, event); + if (event & OHCI1394_busReset) + reg_write(ohci, OHCI1394_IntMaskClear, OHCI1394_busReset); if (event & OHCI1394_selfIDComplete) queue_work(selfid_workqueue, &ohci->bus_reset_work); -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS-SP1] clk: sunxi-ng: h6: Reparent CPUX during PLL CPUX rate change
by Yu Liao 11 Jun '24

11 Jun '24

From: Jernej Skrabec <jernej.skrabec(a)gmail.com> stable inclusion from stable-v5.10.217 commit bfc78b4628497eb6df09a6b5bba9dd31616ee175 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9TOGH CVE: CVE-2023-52882 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 7e91ed763dc07437777bd012af7a2bd4493731ff ] While PLL CPUX clock rate change when CPU is running from it works in vast majority of cases, now and then it causes instability. This leads to system crashes and other undefined behaviour. After a lot of testing (30+ hours) while also doing a lot of frequency switches, we can't observe any instability issues anymore when doing reparenting to stable clock like 24 MHz oscillator. Fixes: 524353ea480b ("clk: sunxi-ng: add support for the Allwinner H6 CCU") Reported-by: Chad Wagner <wagnerch42(a)gmail.com> Link: https://forum.libreelec.tv/thread/27295-orange-pi-3-lts-freezes/ Tested-by: Chad Wagner <wagnerch42(a)gmail.com> Reviewed-by: Chen-Yu Tsai <wens(a)csie.org> Link: https://lore.kernel.org/r/20231013181712.2128037-1-jernej.skrabec@gmail.com Signed-off-by: Jernej Skrabec <jernej.skrabec(a)gmail.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yu Liao <liaoyu15(a)huawei.com> --- drivers/clk/sunxi-ng/ccu-sun50i-h6.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-h6.c b/drivers/clk/sunxi-ng/ccu-sun50i-h6.c index bff446b78290..2d4fc55718eb 100644 --- a/drivers/clk/sunxi-ng/ccu-sun50i-h6.c +++ b/drivers/clk/sunxi-ng/ccu-sun50i-h6.c @@ -1181,12 +1181,19 @@ static const u32 usb2_clk_regs[] = { SUN50I_H6_USB3_CLK_REG, }; +static struct ccu_mux_nb sun50i_h6_cpu_nb = { + .common = &cpux_clk.common, + .cm = &cpux_clk.mux, + .delay_us = 1, + .bypass_index = 0, /* index of 24 MHz oscillator */ +}; + static int sun50i_h6_ccu_probe(struct platform_device *pdev) { struct resource *res; void __iomem *reg; + int i, ret; u32 val; - int i; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); reg = devm_ioremap_resource(&pdev->dev, res); @@ -1240,7 +1247,15 @@ static int sun50i_h6_ccu_probe(struct platform_device *pdev) val |= BIT(24); writel(val, reg + SUN50I_H6_HDMI_CEC_CLK_REG); - return sunxi_ccu_probe(pdev->dev.of_node, reg, &sun50i_h6_ccu_desc); + ret = sunxi_ccu_probe(pdev->dev.of_node, reg, &sun50i_h6_ccu_desc); + if (ret) + return ret; + + /* Reparent CPU during PLL CPUX rate changes */ + ccu_mux_notifier_register(pll_cpux_clk.common.hw.clk, + &sun50i_h6_cpu_nb); + + return 0; } static const struct of_device_id sun50i_h6_ccu_ids[] = { -- 2.33.0

2 1

[PATCH OLK-5.10] clk: sunxi-ng: h6: Reparent CPUX during PLL CPUX rate change
by Yu Liao 11 Jun '24

11 Jun '24

From: Jernej Skrabec <jernej.skrabec(a)gmail.com> stable inclusion from stable-v5.10.217 commit bfc78b4628497eb6df09a6b5bba9dd31616ee175 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9TOGH CVE: CVE-2023-52882 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 7e91ed763dc07437777bd012af7a2bd4493731ff ] While PLL CPUX clock rate change when CPU is running from it works in vast majority of cases, now and then it causes instability. This leads to system crashes and other undefined behaviour. After a lot of testing (30+ hours) while also doing a lot of frequency switches, we can't observe any instability issues anymore when doing reparenting to stable clock like 24 MHz oscillator. Fixes: 524353ea480b ("clk: sunxi-ng: add support for the Allwinner H6 CCU") Reported-by: Chad Wagner <wagnerch42(a)gmail.com> Link: https://forum.libreelec.tv/thread/27295-orange-pi-3-lts-freezes/ Tested-by: Chad Wagner <wagnerch42(a)gmail.com> Reviewed-by: Chen-Yu Tsai <wens(a)csie.org> Link: https://lore.kernel.org/r/20231013181712.2128037-1-jernej.skrabec@gmail.com Signed-off-by: Jernej Skrabec <jernej.skrabec(a)gmail.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yu Liao <liaoyu15(a)huawei.com> --- drivers/clk/sunxi-ng/ccu-sun50i-h6.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-h6.c b/drivers/clk/sunxi-ng/ccu-sun50i-h6.c index bff446b78290..2d4fc55718eb 100644 --- a/drivers/clk/sunxi-ng/ccu-sun50i-h6.c +++ b/drivers/clk/sunxi-ng/ccu-sun50i-h6.c @@ -1181,12 +1181,19 @@ static const u32 usb2_clk_regs[] = { SUN50I_H6_USB3_CLK_REG, }; +static struct ccu_mux_nb sun50i_h6_cpu_nb = { + .common = &cpux_clk.common, + .cm = &cpux_clk.mux, + .delay_us = 1, + .bypass_index = 0, /* index of 24 MHz oscillator */ +}; + static int sun50i_h6_ccu_probe(struct platform_device *pdev) { struct resource *res; void __iomem *reg; + int i, ret; u32 val; - int i; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); reg = devm_ioremap_resource(&pdev->dev, res); @@ -1240,7 +1247,15 @@ static int sun50i_h6_ccu_probe(struct platform_device *pdev) val |= BIT(24); writel(val, reg + SUN50I_H6_HDMI_CEC_CLK_REG); - return sunxi_ccu_probe(pdev->dev.of_node, reg, &sun50i_h6_ccu_desc); + ret = sunxi_ccu_probe(pdev->dev.of_node, reg, &sun50i_h6_ccu_desc); + if (ret) + return ret; + + /* Reparent CPU during PLL CPUX rate changes */ + ccu_mux_notifier_register(pll_cpux_clk.common.hw.clk, + &sun50i_h6_cpu_nb); + + return 0; } static const struct of_device_id sun50i_h6_ccu_ids[] = { -- 2.33.0

2 1

[PATCH openEuler-1.0-LTS] firewire: ohci: mask bus reset interrupts between ISR and bottom half
by Ze Zuo 11 Jun '24

11 Jun '24

From: Adam Goldman <adamg(a)pobox.com> stable inclusion from stable-v5.10.217 commit fa273f312334246c909475c5868e6daab889cc8c category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9UOCQ CVE: CVE-2024-36950 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 752e3c53de0fa3b7d817a83050b6699b8e9c6ec9 ] In the FireWire OHCI interrupt handler, if a bus reset interrupt has occurred, mask bus reset interrupts until bus_reset_work has serviced and cleared the interrupt. Normally, we always leave bus reset interrupts masked. We infer the bus reset from the self-ID interrupt that happens shortly thereafter. A scenario where we unmask bus reset interrupts was introduced in 2008 in a007bb857e0b26f5d8b73c2ff90782d9c0972620: If OHCI_PARAM_DEBUG_BUSRESETS (8) is set in the debug parameter bitmask, we will unmask bus reset interrupts so we can log them. irq_handler logs the bus reset interrupt. However, we can't clear the bus reset event flag in irq_handler, because we won't service the event until later. irq_handler exits with the event flag still set. If the corresponding interrupt is still unmasked, the first bus reset will usually freeze the system due to irq_handler being called again each time it exits. This freeze can be reproduced by loading firewire_ohci with "modprobe firewire_ohci debug=-1" (to enable all debugging output). Apparently there are also some cases where bus_reset_work will get called soon enough to clear the event, and operation will continue normally. This freeze was first reported a few months after a007bb85 was committed, but until now it was never fixed. The debug level could safely be set to -1 through sysfs after the module was loaded, but this would be ineffectual in logging bus reset interrupts since they were only unmasked during initialization. irq_handler will now leave the event flag set but mask bus reset interrupts, so irq_handler won't be called again and there will be no freeze. If OHCI_PARAM_DEBUG_BUSRESETS is enabled, bus_reset_work will unmask the interrupt after servicing the event, so future interrupts will be caught as desired. As a side effect to this change, OHCI_PARAM_DEBUG_BUSRESETS can now be enabled through sysfs in addition to during initial module loading. However, when enabled through sysfs, logging of bus reset interrupts will be effective only starting with the second bus reset, after bus_reset_work has executed. Signed-off-by: Adam Goldman <adamg(a)pobox.com> Signed-off-by: Takashi Sakamoto <o-takashi(a)sakamocchi.jp> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Ze Zuo <zuoze1(a)huawei.com> --- drivers/firewire/ohci.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index 45c048751f3b..11f53e5a4060 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -2018,6 +2018,8 @@ static void bus_reset_work(struct work_struct *work) ohci->generation = generation; reg_write(ohci, OHCI1394_IntEventClear, OHCI1394_busReset); + if (param_debug & OHCI_PARAM_DEBUG_BUSRESETS) + reg_write(ohci, OHCI1394_IntMaskSet, OHCI1394_busReset); if (ohci->quirks & QUIRK_RESET_PACKET) ohci->request_generation = generation; @@ -2084,12 +2086,14 @@ static irqreturn_t irq_handler(int irq, void *data) return IRQ_NONE; /* - * busReset and postedWriteErr must not be cleared yet + * busReset and postedWriteErr events must not be cleared yet * (OHCI 1.1 clauses 7.2.3.2 and 13.2.8.1) */ reg_write(ohci, OHCI1394_IntEventClear, event & ~(OHCI1394_busReset | OHCI1394_postedWriteErr)); log_irqs(ohci, event); + if (event & OHCI1394_busReset) + reg_write(ohci, OHCI1394_IntMaskClear, OHCI1394_busReset); if (event & OHCI1394_selfIDComplete) queue_work(selfid_workqueue, &ohci->bus_reset_work); -- 2.25.1

2 1

[PATCH OLK-5.10 0/2] Fix xfs fsmap errors.
by Zizhi Wo 11 Jun '24

11 Jun '24

Fix FS_IOC_GETFSMAP ioctl error in xfs. Darrick J. Wong (2): xfs: fix interval filtering in multi-step fsmap queries xfs: fix an agbno overflow in __xfs_getfsmap_datadev fs/xfs/xfs_fsmap.c | 80 ++++++++++++++++++++++++++++++++++------------ 1 file changed, 60 insertions(+), 20 deletions(-) -- 2.39.2

2 3

[PATCH openEuler-1.0-LTS] wifi: nl80211: don't free NULL coalescing rule
by Zhang Zekun 11 Jun '24

11 Jun '24

From: Johannes Berg <johannes.berg(a)intel.com> mainline inclusion from mainline-v6.9-rc6 commit 801ea33ae82d6a9d954074fbcf8ea9d18f1543a7 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9U96L CVE: CVE-2024-36941 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ---------------------------------------------------- If the parsing fails, we can dereference a NULL pointer here. Cc: stable(a)vger.kernel.org Fixes: be29b99a9b51 ("cfg80211/nl80211: Add packet coalesce support") Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit(a)intel.com> Link: https://msgid.link/20240418105220.b328f80406e7.Id75d961050deb05b3e4e354e024… Signed-off-by: Johannes Berg <johannes.berg(a)intel.com> Signed-off-by: Zhang Zekun <zhangzekun11(a)huawei.com> --- net/wireless/nl80211.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index de9580f13914..5acb25f6d5a8 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -11475,6 +11475,8 @@ static int nl80211_set_coalesce(struct sk_buff *skb, struct genl_info *info) error: for (i = 0; i < new_coalesce.n_rules; i++) { tmp_rule = &new_coalesce.rules[i]; + if (!tmp_rule) + continue; for (j = 0; j < tmp_rule->n_patterns; j++) kfree(tmp_rule->patterns[j].mask); kfree(tmp_rule->patterns); -- 2.17.1

2 1

[PATCH openEuler-22.03-LTS-SP1 0/5] Fix CVE-2023-52732
by Zizhi Wo 11 Jun '24

11 Jun '24

Fix CVE-2023-52732. Jeff Layton (4): ceph: drop private list from remove_session_caps_cb ceph: fix auth cap handling logic in remove_session_caps_cb ceph: refactor remove_session_caps_cb ceph: shut down access to inode when async create fails Xiubo Li (1): ceph: blocklist the kclient when receiving corrupted snap trace fs/ceph/addr.c | 30 ++++++-- fs/ceph/caps.c | 138 +++++++++++++++++++++++++++++++-- fs/ceph/export.c | 12 ++- fs/ceph/file.c | 13 +++- fs/ceph/inode.c | 33 +++++++- fs/ceph/locks.c | 7 ++ fs/ceph/mds_client.c | 144 ++++++++--------------------------- fs/ceph/snap.c | 36 ++++++++- fs/ceph/super.h | 12 +++ include/linux/ceph/libceph.h | 1 + 10 files changed, 296 insertions(+), 130 deletions(-) -- 2.39.2

2 6

[PATCH OLK-6.6] fs/9p: translate O_TRUNC into OTRUNC
by Ye Bin 11 Jun '24

11 Jun '24

From: Joakim Sindholt <opensource(a)zhasha.com> stable inclusion from stable-v6.6.31 commit dbf68fd7e392541d65a200906026f3a3353f84fe category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I9UNVB CVE: CVE-2024-36964 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 87de39e70503e04ddb58965520b15eb9efa7eef3 ] This one hits both 9P2000 and .u as it appears v9fs has never translated the O_TRUNC flag. Signed-off-by: Joakim Sindholt <opensource(a)zhasha.com> Signed-off-by: Eric Van Hensbergen <ericvh(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Ye Bin <yebin10(a)huawei.com> --- fs/9p/vfs_inode.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index ea695c4a7a3f..0e44c6765b51 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -178,6 +178,9 @@ int v9fs_uflags2omode(int uflags, int extended) break; } + if (uflags & O_TRUNC) + ret |= P9_OTRUNC; + if (extended) { if (uflags & O_EXCL) ret |= P9_OEXCL; -- 2.31.1

2 1

[PATCH openEuler-1.0-LTS v2] ext4: avoid deadlock in fs reclaim with page writeback
by Baokun Li 11 Jun '24

11 Jun '24

From: Jan Kara <jack(a)suse.cz> mainline inclusion from mainline-v6.4-rc2 commit 00d873c17e29cc32d90ca852b82685f1673acaa5 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I9SYGK CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Ext4 has a filesystem wide lock protecting ext4_writepages() calls to avoid races with switching of journalled data flag or inode format. This lock can however cause a deadlock like: CPU0 CPU1 ext4_writepages() percpu_down_read(sbi->s_writepages_rwsem); ext4_change_inode_journal_flag() percpu_down_write(sbi->s_writepages_rwsem); - blocks, all readers block from now on ext4_do_writepages() ext4_init_io_end() kmem_cache_zalloc(io_end_cachep, GFP_KERNEL) fs_reclaim frees dentry... dentry_unlink_inode() iput() - last ref => iput_final() - inode dirty => write_inode_now()... ext4_writepages() tries to acquire sbi->s_writepages_rwsem and blocks forever Make sure we cannot recurse into filesystem reclaim from writeback code to avoid the deadlock. Reported-by: syzbot+6898da502aef574c5f8a(a)syzkaller.appspotmail.com Link: https://lore.kernel.org/all/0000000000004c66b405fa108e27@google.com Fixes: c8585c6fcaf2 ("ext4: fix races between changing inode journal mode and ext4_writepages") CC: stable(a)vger.kernel.org Signed-off-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/20230504124723.20205-1-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Conflicts: fs/ext4/ext4.h fs/ext4/super.c fs/ext4/inode.c fs/ext4/migrate.c [Because we have merged in 41d10c74ff04 ("ext4: fix race between writepages and remount") and we don't have ext4_do_writepages() yet and i_mmap_sem hasn't switched to invalidate_lock yet.] Signed-off-by: Baokun Li <libaokun1(a)huawei.com> --- V1->V2: Correct fs/ext4/migrate.c fs/ext4/ext4.h | 25 +++++++++++++++++++++++++ fs/ext4/inode.c | 18 ++++++++++-------- fs/ext4/migrate.c | 11 ++++++----- fs/ext4/super.c | 11 ++++++----- 4 files changed, 47 insertions(+), 18 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 6df919b154b4..1794f5ce1b46 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -37,6 +37,7 @@ #include <crypto/hash.h> #include <linux/falloc.h> #include <linux/percpu-rwsem.h> +#include <linux/sched/mm.h> #ifdef __KERNEL__ #include <linux/compat.h> #endif @@ -1571,6 +1572,30 @@ static inline struct ext4_inode_info *EXT4_I(struct inode *inode) return container_of(inode, struct ext4_inode_info, vfs_inode); } +static inline int ext4_writepages_down_read(struct super_block *sb) +{ + percpu_down_read(&EXT4_SB(sb)->s_writepages_rwsem); + return memalloc_nofs_save(); +} + +static inline void ext4_writepages_up_read(struct super_block *sb, int ctx) +{ + memalloc_nofs_restore(ctx); + percpu_up_read(&EXT4_SB(sb)->s_writepages_rwsem); +} + +static inline int ext4_writepages_down_write(struct super_block *sb) +{ + percpu_down_write(&EXT4_SB(sb)->s_writepages_rwsem); + return memalloc_nofs_save(); +} + +static inline void ext4_writepages_up_write(struct super_block *sb, int ctx) +{ + memalloc_nofs_restore(ctx); + percpu_up_write(&EXT4_SB(sb)->s_writepages_rwsem); +} + static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) { return ino == EXT4_ROOT_INO || diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 35033bb43149..7110fda36c14 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2744,13 +2744,14 @@ static int ext4_writepages(struct address_space *mapping, struct blk_plug plug; bool give_up_on_write = false; unsigned long retry_warn_ddl = 0; + int alloc_ctx; #define RETRY_WARN_TIMEOUT (30 * HZ) if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; - percpu_down_read(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_read(inode->i_sb); trace_ext4_writepages(inode, wbc); /* @@ -2981,7 +2982,7 @@ static int ext4_writepages(struct address_space *mapping, out_writepages: trace_ext4_writepages_result(inode, wbc, ret, nr_to_write - wbc->nr_to_write); - percpu_up_read(&sbi->s_writepages_rwsem); + ext4_writepages_up_read(inode->i_sb, alloc_ctx); return ret; } @@ -2992,17 +2993,18 @@ static int ext4_dax_writepages(struct address_space *mapping, long nr_to_write = wbc->nr_to_write; struct inode *inode = mapping->host; struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb); + int alloc_ctx; if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; - percpu_down_read(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_read(inode->i_sb); trace_ext4_writepages(inode, wbc); ret = dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev, wbc); trace_ext4_writepages_result(inode, wbc, ret, nr_to_write - wbc->nr_to_write); - percpu_up_read(&sbi->s_writepages_rwsem); + ext4_writepages_up_read(inode->i_sb, alloc_ctx); return ret; } @@ -6245,7 +6247,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) journal_t *journal; handle_t *handle; int err; - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + int alloc_ctx; /* * We have to be very careful here: changing a data block's @@ -6285,7 +6287,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) } } - percpu_down_write(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_write(inode->i_sb); jbd2_journal_lock_updates(journal); /* @@ -6302,7 +6304,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) err = jbd2_journal_flush(journal); if (err < 0) { jbd2_journal_unlock_updates(journal); - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(inode->i_sb, alloc_ctx); ext4_inode_resume_unlocked_dio(inode); return err; } @@ -6311,7 +6313,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) ext4_set_aops(inode); jbd2_journal_unlock_updates(journal); - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(inode->i_sb, alloc_ctx); if (val) up_write(&EXT4_I(inode)->i_mmap_sem); diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index ed9e7816efbb..443a09087dac 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -407,7 +407,6 @@ static int free_ext_block(handle_t *handle, struct inode *inode) int ext4_ext_migrate(struct inode *inode) { - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); handle_t *handle; int retval = 0, i; __le32 *i_data; @@ -417,6 +416,7 @@ int ext4_ext_migrate(struct inode *inode) unsigned long max_entries; __u32 goal, tmp_csum_seed; uid_t owner[2]; + int alloc_ctx; /* * If the filesystem does not support extents, or the inode @@ -432,7 +432,7 @@ int ext4_ext_migrate(struct inode *inode) */ return retval; - percpu_down_write(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_write(inode->i_sb); /* * Worst case we can touch the allocation bitmaps and a block @@ -584,7 +584,7 @@ int ext4_ext_migrate(struct inode *inode) unlock_new_inode(tmp_inode); iput(tmp_inode); out_unlock: - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(inode->i_sb, alloc_ctx); return retval; } @@ -603,6 +603,7 @@ int ext4_ind_migrate(struct inode *inode) ext4_fsblk_t blk; handle_t *handle; int ret; + int alloc_ctx; if (!ext4_has_feature_extents(inode->i_sb) || (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) @@ -619,7 +620,7 @@ int ext4_ind_migrate(struct inode *inode) if (test_opt(inode->i_sb, DELALLOC)) ext4_alloc_da_blocks(inode); - percpu_down_write(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_write(inode->i_sb); handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1); if (IS_ERR(handle)) { @@ -661,6 +662,6 @@ int ext4_ind_migrate(struct inode *inode) ext4_journal_stop(handle); up_write(&EXT4_I(inode)->i_data_sem); out_unlock: - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(inode->i_sb, alloc_ctx); return ret; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 1cfec3ac7c9e..8761fe5037a6 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5559,6 +5559,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) ext4_group_t g; unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO; int err = 0; + int alloc_ctx; #ifdef CONFIG_QUOTA int i, j; char *to_free[EXT4_MAXQUOTAS]; @@ -5611,13 +5612,13 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) * s_writepages_rwsem to avoid race between writepages ops and * remount. */ - percpu_down_write(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_write(sb); if (!parse_options(data, sb, NULL, &journal_ioprio, 1)) { err = -EINVAL; - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(sb, alloc_ctx); goto restore_opts; } - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(sb, alloc_ctx); if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^ test_opt(sb, JOURNAL_CHECKSUM)) { @@ -5850,7 +5851,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) sb_any_quota_suspended(sb)) dquot_resume(sb, -1); - percpu_down_write(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_write(sb); sb->s_flags = old_sb_flags; sbi->s_mount_opt = old_opts.s_mount_opt; sbi->s_mount_opt2 = old_opts.s_mount_opt2; @@ -5859,7 +5860,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) sbi->s_commit_interval = old_opts.s_commit_interval; sbi->s_min_batch_time = old_opts.s_min_batch_time; sbi->s_max_batch_time = old_opts.s_max_batch_time; - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(sb, alloc_ctx); if (!test_opt(sb, BLOCK_VALIDITY) && sbi->system_blks) ext4_release_system_zone(sb); -- 2.31.1

2 1

[PATCH OLK-6.6] scsi: lpfc: Release hbalock before calling lpfc_worker_wake_up()
by Ye Bin 11 Jun '24

11 Jun '24

From: Justin Tee <justin.tee(a)broadcom.com> stable inclusion from stable-v6.6.31 commit e8bf2c05e8ad68e90f9d5889a9e4ef3f6fe00683 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I9U211 CVE: CVE-2024-36924 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit ded20192dff31c91cef2a04f7e20e60e9bb887d3 ] lpfc_worker_wake_up() calls the lpfc_work_done() routine, which takes the hbalock. Thus, lpfc_worker_wake_up() should not be called while holding the hbalock to avoid potential deadlock. Signed-off-by: Justin Tee <justin.tee(a)broadcom.com> Link: https://lore.kernel.org/r/20240305200503.57317-7-justintee8345@gmail.com Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Ye Bin <yebin10(a)huawei.com> --- drivers/scsi/lpfc/lpfc_els.c | 20 ++++++++++---------- drivers/scsi/lpfc/lpfc_hbadisc.c | 5 ++--- drivers/scsi/lpfc/lpfc_sli.c | 14 +++++++------- 3 files changed, 19 insertions(+), 20 deletions(-) diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index 18b8325fd419..44d3ada9fbbc 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -4432,23 +4432,23 @@ lpfc_els_retry_delay(struct timer_list *t) unsigned long flags; struct lpfc_work_evt *evtp = &ndlp->els_retry_evt; + /* Hold a node reference for outstanding queued work */ + if (!lpfc_nlp_get(ndlp)) + return; + spin_lock_irqsave(&phba->hbalock, flags); if (!list_empty(&evtp->evt_listp)) { spin_unlock_irqrestore(&phba->hbalock, flags); + lpfc_nlp_put(ndlp); return; } - /* We need to hold the node by incrementing the reference - * count until the queued work is done - */ - evtp->evt_arg1 = lpfc_nlp_get(ndlp); - if (evtp->evt_arg1) { - evtp->evt = LPFC_EVT_ELS_RETRY; - list_add_tail(&evtp->evt_listp, &phba->work_list); - lpfc_worker_wake_up(phba); - } + evtp->evt_arg1 = ndlp; + evtp->evt = LPFC_EVT_ELS_RETRY; + list_add_tail(&evtp->evt_listp, &phba->work_list); spin_unlock_irqrestore(&phba->hbalock, flags); - return; + + lpfc_worker_wake_up(phba); } /** diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index 5154eeaee0ec..93703ab6ce03 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -257,7 +257,9 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport) if (evtp->evt_arg1) { evtp->evt = LPFC_EVT_DEV_LOSS; list_add_tail(&evtp->evt_listp, &phba->work_list); + spin_unlock_irqrestore(&phba->hbalock, iflags); lpfc_worker_wake_up(phba); + return; } spin_unlock_irqrestore(&phba->hbalock, iflags); } else { @@ -275,10 +277,7 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport) lpfc_disc_state_machine(vport, ndlp, NULL, NLP_EVT_DEVICE_RM); } - } - - return; } /** diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 4dfadf254a72..9dab33686a93 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -1217,9 +1217,9 @@ lpfc_set_rrq_active(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp, empty = list_empty(&phba->active_rrq_list); list_add_tail(&rrq->list, &phba->active_rrq_list); phba->hba_flag |= HBA_RRQ_ACTIVE; + spin_unlock_irqrestore(&phba->hbalock, iflags); if (empty) lpfc_worker_wake_up(phba); - spin_unlock_irqrestore(&phba->hbalock, iflags); return 0; out: spin_unlock_irqrestore(&phba->hbalock, iflags); @@ -11369,18 +11369,18 @@ lpfc_sli_post_recovery_event(struct lpfc_hba *phba, unsigned long iflags; struct lpfc_work_evt *evtp = &ndlp->recovery_evt; + /* Hold a node reference for outstanding queued work */ + if (!lpfc_nlp_get(ndlp)) + return; + spin_lock_irqsave(&phba->hbalock, iflags); if (!list_empty(&evtp->evt_listp)) { spin_unlock_irqrestore(&phba->hbalock, iflags); + lpfc_nlp_put(ndlp); return; } - /* Incrementing the reference count until the queued work is done. */ - evtp->evt_arg1 = lpfc_nlp_get(ndlp); - if (!evtp->evt_arg1) { - spin_unlock_irqrestore(&phba->hbalock, iflags); - return; - } + evtp->evt_arg1 = ndlp; evtp->evt = LPFC_EVT_RECOVER_PORT; list_add_tail(&evtp->evt_listp, &phba->work_list); spin_unlock_irqrestore(&phba->hbalock, iflags); -- 2.31.1

2 1

[PATCH openEuler-1.0-LTS] ext4: avoid deadlock in fs reclaim with page writeback
by Baokun Li 11 Jun '24

11 Jun '24

From: Jan Kara <jack(a)suse.cz> mainline inclusion from mainline-v6.4-rc2 commit 00d873c17e29cc32d90ca852b82685f1673acaa5 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I9SYGK CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Ext4 has a filesystem wide lock protecting ext4_writepages() calls to avoid races with switching of journalled data flag or inode format. This lock can however cause a deadlock like: CPU0 CPU1 ext4_writepages() percpu_down_read(sbi->s_writepages_rwsem); ext4_change_inode_journal_flag() percpu_down_write(sbi->s_writepages_rwsem); - blocks, all readers block from now on ext4_do_writepages() ext4_init_io_end() kmem_cache_zalloc(io_end_cachep, GFP_KERNEL) fs_reclaim frees dentry... dentry_unlink_inode() iput() - last ref => iput_final() - inode dirty => write_inode_now()... ext4_writepages() tries to acquire sbi->s_writepages_rwsem and blocks forever Make sure we cannot recurse into filesystem reclaim from writeback code to avoid the deadlock. Reported-by: syzbot+6898da502aef574c5f8a(a)syzkaller.appspotmail.com Link: https://lore.kernel.org/all/0000000000004c66b405fa108e27@google.com Fixes: c8585c6fcaf2 ("ext4: fix races between changing inode journal mode and ext4_writepages") CC: stable(a)vger.kernel.org Signed-off-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/20230504124723.20205-1-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Conflicts: fs/ext4/ext4.h fs/ext4/super.c fs/ext4/inode.c fs/ext4/migrate.c [Because we have merged in 41d10c74ff04 ("ext4: fix race between writepages and remount") and we don't have ext4_do_writepages() yet and i_mmap_sem hasn't switched to invalidate_lock yet.] Signed-off-by: Baokun Li <libaokun1(a)huawei.com> --- fs/ext4/ext4.h | 25 +++++++++++++++++++++++++ fs/ext4/inode.c | 18 ++++++++++-------- fs/ext4/super.c | 11 ++++++----- 3 files changed, 41 insertions(+), 13 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 6df919b154b4..1794f5ce1b46 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -37,6 +37,7 @@ #include <crypto/hash.h> #include <linux/falloc.h> #include <linux/percpu-rwsem.h> +#include <linux/sched/mm.h> #ifdef __KERNEL__ #include <linux/compat.h> #endif @@ -1571,6 +1572,30 @@ static inline struct ext4_inode_info *EXT4_I(struct inode *inode) return container_of(inode, struct ext4_inode_info, vfs_inode); } +static inline int ext4_writepages_down_read(struct super_block *sb) +{ + percpu_down_read(&EXT4_SB(sb)->s_writepages_rwsem); + return memalloc_nofs_save(); +} + +static inline void ext4_writepages_up_read(struct super_block *sb, int ctx) +{ + memalloc_nofs_restore(ctx); + percpu_up_read(&EXT4_SB(sb)->s_writepages_rwsem); +} + +static inline int ext4_writepages_down_write(struct super_block *sb) +{ + percpu_down_write(&EXT4_SB(sb)->s_writepages_rwsem); + return memalloc_nofs_save(); +} + +static inline void ext4_writepages_up_write(struct super_block *sb, int ctx) +{ + memalloc_nofs_restore(ctx); + percpu_up_write(&EXT4_SB(sb)->s_writepages_rwsem); +} + static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) { return ino == EXT4_ROOT_INO || diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 35033bb43149..7110fda36c14 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2744,13 +2744,14 @@ static int ext4_writepages(struct address_space *mapping, struct blk_plug plug; bool give_up_on_write = false; unsigned long retry_warn_ddl = 0; + int alloc_ctx; #define RETRY_WARN_TIMEOUT (30 * HZ) if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; - percpu_down_read(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_read(inode->i_sb); trace_ext4_writepages(inode, wbc); /* @@ -2981,7 +2982,7 @@ static int ext4_writepages(struct address_space *mapping, out_writepages: trace_ext4_writepages_result(inode, wbc, ret, nr_to_write - wbc->nr_to_write); - percpu_up_read(&sbi->s_writepages_rwsem); + ext4_writepages_up_read(inode->i_sb, alloc_ctx); return ret; } @@ -2992,17 +2993,18 @@ static int ext4_dax_writepages(struct address_space *mapping, long nr_to_write = wbc->nr_to_write; struct inode *inode = mapping->host; struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb); + int alloc_ctx; if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; - percpu_down_read(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_read(inode->i_sb); trace_ext4_writepages(inode, wbc); ret = dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev, wbc); trace_ext4_writepages_result(inode, wbc, ret, nr_to_write - wbc->nr_to_write); - percpu_up_read(&sbi->s_writepages_rwsem); + ext4_writepages_up_read(inode->i_sb, alloc_ctx); return ret; } @@ -6245,7 +6247,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) journal_t *journal; handle_t *handle; int err; - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + int alloc_ctx; /* * We have to be very careful here: changing a data block's @@ -6285,7 +6287,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) } } - percpu_down_write(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_write(inode->i_sb); jbd2_journal_lock_updates(journal); /* @@ -6302,7 +6304,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) err = jbd2_journal_flush(journal); if (err < 0) { jbd2_journal_unlock_updates(journal); - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(inode->i_sb, alloc_ctx); ext4_inode_resume_unlocked_dio(inode); return err; } @@ -6311,7 +6313,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) ext4_set_aops(inode); jbd2_journal_unlock_updates(journal); - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(inode->i_sb, alloc_ctx); if (val) up_write(&EXT4_I(inode)->i_mmap_sem); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 1cfec3ac7c9e..8761fe5037a6 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5559,6 +5559,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) ext4_group_t g; unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO; int err = 0; + int alloc_ctx; #ifdef CONFIG_QUOTA int i, j; char *to_free[EXT4_MAXQUOTAS]; @@ -5611,13 +5612,13 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) * s_writepages_rwsem to avoid race between writepages ops and * remount. */ - percpu_down_write(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_write(sb); if (!parse_options(data, sb, NULL, &journal_ioprio, 1)) { err = -EINVAL; - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(sb, alloc_ctx); goto restore_opts; } - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(sb, alloc_ctx); if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^ test_opt(sb, JOURNAL_CHECKSUM)) { @@ -5850,7 +5851,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) sb_any_quota_suspended(sb)) dquot_resume(sb, -1); - percpu_down_write(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_write(sb); sb->s_flags = old_sb_flags; sbi->s_mount_opt = old_opts.s_mount_opt; sbi->s_mount_opt2 = old_opts.s_mount_opt2; @@ -5859,7 +5860,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) sbi->s_commit_interval = old_opts.s_commit_interval; sbi->s_min_batch_time = old_opts.s_min_batch_time; sbi->s_max_batch_time = old_opts.s_max_batch_time; - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(sb, alloc_ctx); if (!test_opt(sb, BLOCK_VALIDITY) && sbi->system_blks) ext4_release_system_zone(sb); -- 2.31.1

2 1

[PATCH OLK-6.6] kabi: reserve kabi for struct device
by Peng Zhang 11 Jun '24

11 Jun '24

From: ZhangPeng <zhangpeng362(a)huawei.com> hulk inclusion category: cleanup bugzilla: https://gitee.com/openeuler/kernel/issues/I8OWRC -------------------------------- Just testing if the kabi check is working. Please ignore this patch. Signed-off-by: ZhangPeng <zhangpeng362(a)huawei.com> --- include/linux/device.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/device.h b/include/linux/device.h index 17427fc8e035..0128883e652d 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -814,6 +814,7 @@ struct device { KABI_RESERVE(6) KABI_RESERVE(7) KABI_RESERVE(8) + KABI_RESERVE(9) }; /** -- 2.25.1

2 1

[PATCH] kabi: reserve kabi for struct device
by Peng Zhang 11 Jun '24

11 Jun '24

From: ZhangPeng <zhangpeng362(a)huawei.com> hulk inclusion category: cleanup bugzilla: https://gitee.com/openeuler/kernel/issues/I8OWRC -------------------------------- Just testing if the kabi check is working. Please ignore this patch. Signed-off-by: ZhangPeng <zhangpeng362(a)huawei.com> --- include/linux/device.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/device.h b/include/linux/device.h index 17427fc8e035..0128883e652d 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -814,6 +814,7 @@ struct device { KABI_RESERVE(6) KABI_RESERVE(7) KABI_RESERVE(8) + KABI_RESERVE(9) }; /** -- 2.25.1

1 0

[PATCH openEuler-22.03-LTS-SP1] ext4: avoid deadlock in fs reclaim with page writeback
by Baokun Li 11 Jun '24

11 Jun '24

From: Jan Kara <jack(a)suse.cz> mainline inclusion from mainline-v6.4-rc2 commit 00d873c17e29cc32d90ca852b82685f1673acaa5 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I9SYGK Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Ext4 has a filesystem wide lock protecting ext4_writepages() calls to avoid races with switching of journalled data flag or inode format. This lock can however cause a deadlock like: CPU0 CPU1 ext4_writepages() percpu_down_read(sbi->s_writepages_rwsem); ext4_change_inode_journal_flag() percpu_down_write(sbi->s_writepages_rwsem); - blocks, all readers block from now on ext4_do_writepages() ext4_init_io_end() kmem_cache_zalloc(io_end_cachep, GFP_KERNEL) fs_reclaim frees dentry... dentry_unlink_inode() iput() - last ref => iput_final() - inode dirty => write_inode_now()... ext4_writepages() tries to acquire sbi->s_writepages_rwsem and blocks forever Make sure we cannot recurse into filesystem reclaim from writeback code to avoid the deadlock. Reported-by: syzbot+6898da502aef574c5f8a(a)syzkaller.appspotmail.com Link: https://lore.kernel.org/all/0000000000004c66b405fa108e27@google.com Fixes: c8585c6fcaf2 ("ext4: fix races between changing inode journal mode and ext4_writepages") CC: stable(a)vger.kernel.org Signed-off-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/20230504124723.20205-1-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Conflicts: fs/ext4/ext4.h fs/ext4/super.c fs/ext4/inode.c [Because we have merged in 583b2fb551d0 ("ext4: fix race between writepages and remount") and we don't have ext4_do_writepages() yet and i_mmap_sem hasn't switched to invalidate_lock yet.] Signed-off-by: Baokun Li <libaokun1(a)huawei.com> --- fs/ext4/ext4.h | 25 +++++++++++++++++++++++++ fs/ext4/inode.c | 18 ++++++++++-------- fs/ext4/migrate.c | 11 ++++++----- fs/ext4/super.c | 11 ++++++----- 4 files changed, 47 insertions(+), 18 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 5d5ae6f44510..3cf1fe773f4f 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -37,6 +37,7 @@ #include <linux/falloc.h> #include <linux/percpu-rwsem.h> #include <linux/fiemap.h> +#include <linux/sched/mm.h> #ifdef __KERNEL__ #include <linux/compat.h> #endif @@ -1689,6 +1690,30 @@ static inline struct ext4_inode_info *EXT4_I(struct inode *inode) return container_of(inode, struct ext4_inode_info, vfs_inode); } +static inline int ext4_writepages_down_read(struct super_block *sb) +{ + percpu_down_read(&EXT4_SB(sb)->s_writepages_rwsem); + return memalloc_nofs_save(); +} + +static inline void ext4_writepages_up_read(struct super_block *sb, int ctx) +{ + memalloc_nofs_restore(ctx); + percpu_up_read(&EXT4_SB(sb)->s_writepages_rwsem); +} + +static inline int ext4_writepages_down_write(struct super_block *sb) +{ + percpu_down_write(&EXT4_SB(sb)->s_writepages_rwsem); + return memalloc_nofs_save(); +} + +static inline void ext4_writepages_up_write(struct super_block *sb, int ctx) +{ + memalloc_nofs_restore(ctx); + percpu_up_write(&EXT4_SB(sb)->s_writepages_rwsem); +} + static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) { return ino == EXT4_ROOT_INO || diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index f26d9b88d48d..9c438215cf56 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2705,13 +2705,14 @@ static int ext4_writepages(struct address_space *mapping, struct blk_plug plug; bool give_up_on_write = false; unsigned long retry_warn_ddl = 0; + int alloc_ctx; #define RETRY_WARN_TIMEOUT (30 * HZ) if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; - percpu_down_read(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_read(inode->i_sb); trace_ext4_writepages(inode, wbc); /* @@ -2932,7 +2933,7 @@ static int ext4_writepages(struct address_space *mapping, out_writepages: trace_ext4_writepages_result(inode, wbc, ret, nr_to_write - wbc->nr_to_write); - percpu_up_read(&sbi->s_writepages_rwsem); + ext4_writepages_up_read(inode->i_sb, alloc_ctx); return ret; } @@ -2943,17 +2944,18 @@ static int ext4_dax_writepages(struct address_space *mapping, long nr_to_write = wbc->nr_to_write; struct inode *inode = mapping->host; struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb); + int alloc_ctx; if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; - percpu_down_read(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_read(inode->i_sb); trace_ext4_writepages(inode, wbc); ret = dax_writeback_mapping_range(mapping, sbi->s_daxdev, wbc); trace_ext4_writepages_result(inode, wbc, ret, nr_to_write - wbc->nr_to_write); - percpu_up_read(&sbi->s_writepages_rwsem); + ext4_writepages_up_read(inode->i_sb, alloc_ctx); return ret; } @@ -6065,7 +6067,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) journal_t *journal; handle_t *handle; int err; - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + int alloc_ctx; /* * We have to be very careful here: changing a data block's @@ -6103,7 +6105,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) } } - percpu_down_write(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_write(inode->i_sb); jbd2_journal_lock_updates(journal); /* @@ -6120,7 +6122,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) err = jbd2_journal_flush(journal); if (err < 0) { jbd2_journal_unlock_updates(journal); - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(inode->i_sb, alloc_ctx); return err; } ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA); @@ -6128,7 +6130,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) ext4_set_aops(inode); jbd2_journal_unlock_updates(journal); - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(inode->i_sb, alloc_ctx); if (val) up_write(&EXT4_I(inode)->i_mmap_sem); diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index 04320715d61f..274f7ab37fff 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -409,7 +409,6 @@ static int free_ext_block(handle_t *handle, struct inode *inode) int ext4_ext_migrate(struct inode *inode) { - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); handle_t *handle; int retval = 0, i; __le32 *i_data; @@ -419,6 +418,7 @@ int ext4_ext_migrate(struct inode *inode) unsigned long max_entries; __u32 goal, tmp_csum_seed; uid_t owner[2]; + int alloc_ctx; /* * If the filesystem does not support extents, or the inode @@ -434,7 +434,7 @@ int ext4_ext_migrate(struct inode *inode) */ return retval; - percpu_down_write(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_write(inode->i_sb); /* * Worst case we can touch the allocation bitmaps and a block @@ -586,7 +586,7 @@ int ext4_ext_migrate(struct inode *inode) unlock_new_inode(tmp_inode); iput(tmp_inode); out_unlock: - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(inode->i_sb, alloc_ctx); return retval; } @@ -605,6 +605,7 @@ int ext4_ind_migrate(struct inode *inode) ext4_fsblk_t blk; handle_t *handle; int ret, ret2 = 0; + int alloc_ctx; if (!ext4_has_feature_extents(inode->i_sb) || (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) @@ -621,7 +622,7 @@ int ext4_ind_migrate(struct inode *inode) if (test_opt(inode->i_sb, DELALLOC)) ext4_alloc_da_blocks(inode); - percpu_down_write(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_write(inode->i_sb); handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1); if (IS_ERR(handle)) { @@ -665,6 +666,6 @@ int ext4_ind_migrate(struct inode *inode) ext4_journal_stop(handle); up_write(&EXT4_I(inode)->i_data_sem); out_unlock: - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(inode->i_sb, alloc_ctx); return ret; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ac032f517a60..2bdb16df5c23 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5939,6 +5939,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) ext4_group_t g; unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO; int err = 0; + int alloc_ctx; #ifdef CONFIG_QUOTA int i, j; char *to_free[EXT4_MAXQUOTAS]; @@ -5991,13 +5992,13 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) * here s_writepages_rwsem to avoid race between writepages ops and * remount. */ - percpu_down_write(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_write(sb); if (!parse_options(data, sb, NULL, &journal_ioprio, 1)) { err = -EINVAL; - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(sb, alloc_ctx); goto restore_opts; } - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(sb, alloc_ctx); if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^ test_opt(sb, JOURNAL_CHECKSUM)) { @@ -6215,7 +6216,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) return 0; restore_opts: - percpu_down_write(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_write(sb); sb->s_flags = old_sb_flags; sbi->s_mount_opt = old_opts.s_mount_opt; sbi->s_mount_opt2 = old_opts.s_mount_opt2; @@ -6224,7 +6225,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) sbi->s_commit_interval = old_opts.s_commit_interval; sbi->s_min_batch_time = old_opts.s_min_batch_time; sbi->s_max_batch_time = old_opts.s_max_batch_time; - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(sb, alloc_ctx); if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks) ext4_release_system_zone(sb); -- 2.31.1

2 1

[PATCH OLK-5.10] ext4: avoid deadlock in fs reclaim with page writeback
by Baokun Li 11 Jun '24

11 Jun '24

From: Jan Kara <jack(a)suse.cz> mainline inclusion from mainline-v6.4-rc2 commit 00d873c17e29cc32d90ca852b82685f1673acaa5 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I9SYGK Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Ext4 has a filesystem wide lock protecting ext4_writepages() calls to avoid races with switching of journalled data flag or inode format. This lock can however cause a deadlock like: CPU0 CPU1 ext4_writepages() percpu_down_read(sbi->s_writepages_rwsem); ext4_change_inode_journal_flag() percpu_down_write(sbi->s_writepages_rwsem); - blocks, all readers block from now on ext4_do_writepages() ext4_init_io_end() kmem_cache_zalloc(io_end_cachep, GFP_KERNEL) fs_reclaim frees dentry... dentry_unlink_inode() iput() - last ref => iput_final() - inode dirty => write_inode_now()... ext4_writepages() tries to acquire sbi->s_writepages_rwsem and blocks forever Make sure we cannot recurse into filesystem reclaim from writeback code to avoid the deadlock. Reported-by: syzbot+6898da502aef574c5f8a(a)syzkaller.appspotmail.com Link: https://lore.kernel.org/all/0000000000004c66b405fa108e27@google.com Fixes: c8585c6fcaf2 ("ext4: fix races between changing inode journal mode and ext4_writepages") CC: stable(a)vger.kernel.org Signed-off-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/20230504124723.20205-1-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Conflicts: fs/ext4/ext4.h fs/ext4/super.c fs/ext4/inode.c [Because we have merged in b66c23ec7fcf ("ext4: fix race between writepages and remount") and we don't have ext4_do_writepages() yet and i_mmap_sem hasn't switched to invalidate_lock yet.] Signed-off-by: Baokun Li <libaokun1(a)huawei.com> --- fs/ext4/ext4.h | 25 +++++++++++++++++++++++++ fs/ext4/inode.c | 18 ++++++++++-------- fs/ext4/migrate.c | 11 ++++++----- fs/ext4/super.c | 12 +++++++----- 4 files changed, 48 insertions(+), 18 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index b701f7ac7f66..a9530484147d 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -37,6 +37,7 @@ #include <linux/falloc.h> #include <linux/percpu-rwsem.h> #include <linux/fiemap.h> +#include <linux/sched/mm.h> #ifdef __KERNEL__ #include <linux/compat.h> #endif @@ -1701,6 +1702,30 @@ static inline struct ext4_inode_info *EXT4_I(struct inode *inode) return container_of(inode, struct ext4_inode_info, vfs_inode); } +static inline int ext4_writepages_down_read(struct super_block *sb) +{ + percpu_down_read(&EXT4_SB(sb)->s_writepages_rwsem); + return memalloc_nofs_save(); +} + +static inline void ext4_writepages_up_read(struct super_block *sb, int ctx) +{ + memalloc_nofs_restore(ctx); + percpu_up_read(&EXT4_SB(sb)->s_writepages_rwsem); +} + +static inline int ext4_writepages_down_write(struct super_block *sb) +{ + percpu_down_write(&EXT4_SB(sb)->s_writepages_rwsem); + return memalloc_nofs_save(); +} + +static inline void ext4_writepages_up_write(struct super_block *sb, int ctx) +{ + memalloc_nofs_restore(ctx); + percpu_up_write(&EXT4_SB(sb)->s_writepages_rwsem); +} + static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) { return ino == EXT4_ROOT_INO || diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 412af3c5fde4..0f8d23aa2838 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2709,13 +2709,14 @@ static int ext4_writepages(struct address_space *mapping, struct blk_plug plug; bool give_up_on_write = false; unsigned long retry_warn_ddl = 0; + int alloc_ctx; #define RETRY_WARN_TIMEOUT (30 * HZ) if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; - percpu_down_read(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_read(inode->i_sb); trace_ext4_writepages(inode, wbc); /* @@ -2936,7 +2937,7 @@ static int ext4_writepages(struct address_space *mapping, out_writepages: trace_ext4_writepages_result(inode, wbc, ret, nr_to_write - wbc->nr_to_write); - percpu_up_read(&sbi->s_writepages_rwsem); + ext4_writepages_up_read(inode->i_sb, alloc_ctx); return ret; } @@ -2947,17 +2948,18 @@ static int ext4_dax_writepages(struct address_space *mapping, long nr_to_write = wbc->nr_to_write; struct inode *inode = mapping->host; struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb); + int alloc_ctx; if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; - percpu_down_read(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_read(inode->i_sb); trace_ext4_writepages(inode, wbc); ret = dax_writeback_mapping_range(mapping, sbi->s_daxdev, wbc); trace_ext4_writepages_result(inode, wbc, ret, nr_to_write - wbc->nr_to_write); - percpu_up_read(&sbi->s_writepages_rwsem); + ext4_writepages_up_read(inode->i_sb, alloc_ctx); return ret; } @@ -6107,7 +6109,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) journal_t *journal; handle_t *handle; int err; - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + int alloc_ctx; /* * We have to be very careful here: changing a data block's @@ -6145,7 +6147,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) } } - percpu_down_write(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_write(inode->i_sb); jbd2_journal_lock_updates(journal); /* @@ -6162,7 +6164,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) err = jbd2_journal_flush(journal); if (err < 0) { jbd2_journal_unlock_updates(journal); - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(inode->i_sb, alloc_ctx); return err; } ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA); @@ -6170,7 +6172,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) ext4_set_aops(inode); jbd2_journal_unlock_updates(journal); - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(inode->i_sb, alloc_ctx); if (val) up_write(&EXT4_I(inode)->i_mmap_sem); diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index b0ea646454ac..50e449ec62bf 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -409,7 +409,6 @@ static int free_ext_block(handle_t *handle, struct inode *inode) int ext4_ext_migrate(struct inode *inode) { - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); handle_t *handle; int retval = 0, i; __le32 *i_data; @@ -419,6 +418,7 @@ int ext4_ext_migrate(struct inode *inode) unsigned long max_entries; __u32 goal, tmp_csum_seed; uid_t owner[2]; + int alloc_ctx; /* * If the filesystem does not support extents, or the inode @@ -435,7 +435,7 @@ int ext4_ext_migrate(struct inode *inode) */ return retval; - percpu_down_write(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_write(inode->i_sb); /* * Worst case we can touch the allocation bitmaps and a block @@ -587,7 +587,7 @@ int ext4_ext_migrate(struct inode *inode) unlock_new_inode(tmp_inode); iput(tmp_inode); out_unlock: - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(inode->i_sb, alloc_ctx); return retval; } @@ -606,6 +606,7 @@ int ext4_ind_migrate(struct inode *inode) ext4_fsblk_t blk; handle_t *handle; int ret, ret2 = 0; + int alloc_ctx; if (!ext4_has_feature_extents(inode->i_sb) || (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) @@ -622,7 +623,7 @@ int ext4_ind_migrate(struct inode *inode) if (test_opt(inode->i_sb, DELALLOC)) ext4_alloc_da_blocks(inode); - percpu_down_write(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_write(inode->i_sb); handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1); if (IS_ERR(handle)) { @@ -666,6 +667,6 @@ int ext4_ind_migrate(struct inode *inode) ext4_journal_stop(handle); up_write(&EXT4_I(inode)->i_data_sem); out_unlock: - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(inode->i_sb, alloc_ctx); return ret; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 90f886184fc6..bfa592bfd298 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5961,6 +5961,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) ext4_group_t g; unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO; int err = 0; + int alloc_ctx; #ifdef CONFIG_QUOTA int enable_quota = 0; int i, j; @@ -6014,13 +6015,13 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) * here s_writepages_rwsem to avoid race between writepages ops and * remount. */ - percpu_down_write(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_write(sb); if (!parse_options(data, sb, NULL, &journal_ioprio, 1)) { err = -EINVAL; - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(sb, alloc_ctx); goto restore_opts; } - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(sb, alloc_ctx); if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^ test_opt(sb, JOURNAL_CHECKSUM)) { @@ -6247,7 +6248,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if ((sb->s_flags & SB_RDONLY) && !(old_sb_flags & SB_RDONLY) && sb_any_quota_suspended(sb)) dquot_resume(sb, -1); - percpu_down_write(&sbi->s_writepages_rwsem); + + alloc_ctx = ext4_writepages_down_write(sb); sb->s_flags = old_sb_flags; sbi->s_mount_opt = old_opts.s_mount_opt; sbi->s_mount_opt2 = old_opts.s_mount_opt2; @@ -6256,7 +6258,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) sbi->s_commit_interval = old_opts.s_commit_interval; sbi->s_min_batch_time = old_opts.s_min_batch_time; sbi->s_max_batch_time = old_opts.s_max_batch_time; - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(sb, alloc_ctx); if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks) ext4_release_system_zone(sb); -- 2.31.1

2 1

[PATCH OLK-5.10] phonet: fix rtm_phonet_notify() skb allocation
by Wang Wensheng 11 Jun '24

11 Jun '24

From: Eric Dumazet <edumazet(a)google.com> mainline inclusion from mainline-v6.9 commit d8cac8568618dcb8a51af3db1103e8d4cc4aeea7 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9U4L2 CVE: CVE-2024-36946 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- fill_route() stores three components in the skb: - struct rtmsg - RTA_DST (u8) - RTA_OIF (u32) Therefore, rtm_phonet_notify() should use NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(1) + nla_total_size(4) Fixes: f062f41d0657 ("Phonet: routing table Netlink interface") Signed-off-by: Eric Dumazet <edumazet(a)google.com> Acked-by: Rémi Denis-Courmont <courmisch(a)gmail.com> Link: https://lore.kernel.org/r/20240502161700.1804476-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Wang Wensheng <wangwensheng4(a)huawei.com> --- net/phonet/pn_netlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c index 59aebe296890..dd4c7e9a634f 100644 --- a/net/phonet/pn_netlink.c +++ b/net/phonet/pn_netlink.c @@ -193,7 +193,7 @@ void rtm_phonet_notify(int event, struct net_device *dev, u8 dst) struct sk_buff *skb; int err = -ENOBUFS; - skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + + skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(1) + nla_total_size(4), GFP_KERNEL); if (skb == NULL) goto errout; -- 2.17.1

2 1

[PATCH openEuler-1.0-LTS] i40e: Fix NULL pointer dereference in i40e_dbg_dump_desc
by Li Huafei 11 Jun '24

11 Jun '24

From: Norbert Zulinski <norbertx.zulinski(a)intel.com> stable inclusion from stable-v5.10.85 commit e5b7fb2198abc50058f1a29c395b004f76ab1c83 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9S22G CVE: CVE-2021-47501 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 23ec111bf3549aae37140330c31a16abfc172421 upstream. When trying to dump VFs VSI RX/TX descriptors using debugfs there was a crash due to NULL pointer dereference in i40e_dbg_dump_desc. Added a check to i40e_dbg_dump_desc that checks if VSI type is correct for dumping RX/TX descriptors. Fixes: 02e9c290814c ("i40e: debugfs interface") Signed-off-by: Sylwester Dziedziuch <sylwesterx.dziedziuch(a)intel.com> Signed-off-by: Norbert Zulinski <norbertx.zulinski(a)intel.com> Signed-off-by: Mateusz Palczewski <mateusz.palczewski(a)intel.com> Tested-by: Gurucharan G <gurucharanx.g(a)intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen(a)intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: drivers/net/ethernet/intel/i40e/i40e_debugfs.c [ Conflicts caused by not merging 44ea803e2fa7 ("i40e: introduce new dump desc XDP command"). ] Signed-off-by: Li Huafei <lihuafei1(a)huawei.com> --- drivers/net/ethernet/intel/i40e/i40e_debugfs.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 56b911a5dd8be..3e6c6585012f9 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -506,6 +506,14 @@ static void i40e_dbg_dump_desc(int cnt, int vsi_seid, int ring_id, int desc_n, dev_info(&pf->pdev->dev, "vsi %d not found\n", vsi_seid); return; } + if (vsi->type != I40E_VSI_MAIN && + vsi->type != I40E_VSI_FDIR && + vsi->type != I40E_VSI_VMDQ2) { + dev_info(&pf->pdev->dev, + "vsi %d type %d descriptor rings not available\n", + vsi_seid, vsi->type); + return; + } if (ring_id >= vsi->num_queue_pairs || ring_id < 0) { dev_info(&pf->pdev->dev, "ring %d not found\n", ring_id); return; -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS-SP1] hugetlbfs: fix hugetlbfs_statfs() locking
by Yifan Qiao 11 Jun '24

11 Jun '24

From: Mina Almasry <almasrymina(a)google.com> mainline inclusion from mainline-v5.19-rc1 commit 4b25f030ae69ba710eff587cabb4c57cb7e7a8a1 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I9SY02 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ---------------------------------------------------------------------- After commit db71ef79b59b ("hugetlb: make free_huge_page irq safe"), the subpool lock should be locked with spin_lock_irq() and all call sites was modified as such, except for the ones in hugetlbfs_statfs(). Link: https://lkml.kernel.org/r/20220429202207.3045-1-almasrymina@google.com Fixes: db71ef79b59b ("hugetlb: make free_huge_page irq safe") Signed-off-by: Mina Almasry <almasrymina(a)google.com> Reviewed-by: Mike Kravetz <mike.kravetz(a)oracle.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Yifan Qiao <qiaoyifan4(a)huawei.com> --- fs/hugetlbfs/inode.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 8274f096e89f..73a008dfe322 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -1122,12 +1122,12 @@ static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf) if (sbinfo->spool) { long free_pages; - spin_lock(&sbinfo->spool->lock); + spin_lock_irq(&sbinfo->spool->lock); buf->f_blocks = sbinfo->spool->max_hpages; free_pages = sbinfo->spool->max_hpages - sbinfo->spool->used_hpages; buf->f_bavail = buf->f_bfree = free_pages; - spin_unlock(&sbinfo->spool->lock); + spin_unlock_irq(&sbinfo->spool->lock); buf->f_files = sbinfo->max_inodes; buf->f_ffree = sbinfo->free_inodes; } -- 2.39.2

2 1

[PATCH OLK-5.10] hugetlbfs: fix hugetlbfs_statfs() locking
by Yifan Qiao 11 Jun '24

11 Jun '24

From: Mina Almasry <almasrymina(a)google.com> mainline inclusion from mainline-v5.19-rc1 commit 4b25f030ae69ba710eff587cabb4c57cb7e7a8a1 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I9SY02 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ---------------------------------------------------------------------- After commit db71ef79b59b ("hugetlb: make free_huge_page irq safe"), the subpool lock should be locked with spin_lock_irq() and all call sites was modified as such, except for the ones in hugetlbfs_statfs(). Link: https://lkml.kernel.org/r/20220429202207.3045-1-almasrymina@google.com Fixes: db71ef79b59b ("hugetlb: make free_huge_page irq safe") Signed-off-by: Mina Almasry <almasrymina(a)google.com> Reviewed-by: Mike Kravetz <mike.kravetz(a)oracle.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Yifan Qiao <qiaoyifan4(a)huawei.com> --- fs/hugetlbfs/inode.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 508c20ef9061..1203178914cc 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -1133,12 +1133,12 @@ static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf) if (sbinfo->spool) { long free_pages; - spin_lock(&sbinfo->spool->lock); + spin_lock_irq(&sbinfo->spool->lock); buf->f_blocks = sbinfo->spool->max_hpages; free_pages = sbinfo->spool->max_hpages - sbinfo->spool->used_hpages; buf->f_bavail = buf->f_bfree = free_pages; - spin_unlock(&sbinfo->spool->lock); + spin_unlock_irq(&sbinfo->spool->lock); buf->f_files = sbinfo->max_inodes; buf->f_ffree = sbinfo->free_inodes; } -- 2.39.2

2 1

[PATCH OLK-6.6] gpiolib: cdev: fix uninitialised kfifo
by Luo Gengkun 11 Jun '24

11 Jun '24

From: Kent Gibson <warthog618(a)gmail.com> mainline inclusion from mainline-v6.9 commit ee0166b637a5e376118e9659e5b4148080f1d27e category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9U7YV CVE: CVE-2024-36898 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- If a line is requested with debounce, and that results in debouncing in software, and the line is subsequently reconfigured to enable edge detection then the allocation of the kfifo to contain edge events is overlooked. This results in events being written to and read from an uninitialised kfifo. Read events are returned to userspace. Initialise the kfifo in the case where the software debounce is already active. Fixes: 65cff7046406 ("gpiolib: cdev: support setting debounce") Signed-off-by: Kent Gibson <warthog618(a)gmail.com> Link: https://lore.kernel.org/r/20240510065342.36191-1-warthog618@gmail.com Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski(a)linaro.org> Conflicts: drivers/gpio/gpiolib-cdev.c [fix context conflict] Signed-off-by: Luo Gengkun <luogengkun2(a)huawei.com> --- drivers/gpio/gpiolib-cdev.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c index 84125e55de10..29b671c92621 100644 --- a/drivers/gpio/gpiolib-cdev.c +++ b/drivers/gpio/gpiolib-cdev.c @@ -1121,6 +1121,8 @@ static int edge_detector_update(struct line *line, struct gpio_v2_line_config *lc, unsigned int line_idx, u64 edflags) { + u64 eflags; + int ret; u64 active_edflags = READ_ONCE(line->edflags); unsigned int debounce_period_us = gpio_v2_line_config_debounce_period(lc, line_idx); @@ -1132,6 +1134,18 @@ static int edge_detector_update(struct line *line, /* sw debounced and still will be...*/ if (debounce_period_us && READ_ONCE(line->sw_debounced)) { WRITE_ONCE(line->desc->debounce_period_us, debounce_period_us); + /* + * ensure event fifo is initialised if edge detection + * is now enabled. + */ + eflags = edflags & GPIO_V2_LINE_EDGE_FLAGS; + if (eflags && !kfifo_initialized(&line->req->events)) { + ret = kfifo_alloc(&line->req->events, + line->req->event_buffer_size, + GFP_KERNEL); + if (ret) + return ret; + } return 0; } -- 2.34.1

2 1