From: Sasha Levin Date: Sun, 17 Jul 2022 14:52:40 +0000 (-0400) Subject: Fixes for 4.9 X-Git-Tag: v4.9.324~36 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=d57759d86814dcef696e5d29931f33cf57d8b146;p=thirdparty%2Fkernel%2Fstable-queue.git Fixes for 4.9 Signed-off-by: Sasha Levin --- diff --git a/queue-4.9/arm-9209-1-spectre-bhb-avoid-pr_info-every-time-a-cp.patch b/queue-4.9/arm-9209-1-spectre-bhb-avoid-pr_info-every-time-a-cp.patch new file mode 100644 index 00000000000..2d6e026227f --- /dev/null +++ b/queue-4.9/arm-9209-1-spectre-bhb-avoid-pr_info-every-time-a-cp.patch @@ -0,0 +1,58 @@ +From df9d39ca5ed73e4e5e2d7bd2bd2ce51d7ad1f136 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 31 May 2022 09:53:42 +0100 +Subject: ARM: 9209/1: Spectre-BHB: avoid pr_info() every time a CPU comes out + of idle + +From: Ard Biesheuvel + +[ Upstream commit 0609e200246bfd3b7516091c491bec4308349055 ] + +Jon reports that the Spectre-BHB init code is filling up the kernel log +with spurious notifications about which mitigation has been enabled, +every time any CPU comes out of a low power state. + +Given that Spectre-BHB mitigations are system wide, only a single +mitigation can be enabled, and we already print an error if two types of +CPUs coexist in a single system that require different Spectre-BHB +mitigations. + +This means that the pr_info() that describes the selected mitigation +does not need to be emitted for each CPU anyway, and so we can simply +emit it only once. + +In order to clarify the above in the log message, update it to describe +that the selected mitigation will be enabled on all CPUs, including ones +that are unaffected. If another CPU comes up later that is affected and +requires a different mitigation, we report an error as before. + +Fixes: b9baf5c8c5c3 ("ARM: Spectre-BHB workaround") +Tested-by: Jon Hunter +Signed-off-by: Ard Biesheuvel +Signed-off-by: Russell King (Oracle) +Signed-off-by: Sasha Levin +--- + arch/arm/mm/proc-v7-bugs.c | 6 +++--- + 1 file changed, 3 insertions(+), 3 deletions(-) + +diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c +index 35c4660e638a..4af4195eed76 100644 +--- a/arch/arm/mm/proc-v7-bugs.c ++++ b/arch/arm/mm/proc-v7-bugs.c +@@ -217,10 +217,10 @@ static int spectre_bhb_install_workaround(int method) + return SPECTRE_VULNERABLE; + + spectre_bhb_method = method; +- } + +- pr_info("CPU%u: Spectre BHB: using %s workaround\n", +- smp_processor_id(), spectre_bhb_method_name(method)); ++ pr_info("CPU%u: Spectre BHB: enabling %s workaround for all CPUs\n", ++ smp_processor_id(), spectre_bhb_method_name(method)); ++ } + + return SPECTRE_MITIGATED; + } +-- +2.35.1 + diff --git a/queue-4.9/cipso-fix-data-races-around-sysctl.patch b/queue-4.9/cipso-fix-data-races-around-sysctl.patch new file mode 100644 index 00000000000..bcbc69e9a91 --- /dev/null +++ b/queue-4.9/cipso-fix-data-races-around-sysctl.patch @@ -0,0 +1,95 @@ +From 5ac71d421f9f347ac2dec3449dd6852b3d521d81 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 6 Jul 2022 16:40:01 -0700 +Subject: cipso: Fix data-races around sysctl. + +From: Kuniyuki Iwashima + +[ Upstream commit dd44f04b9214adb68ef5684ae87a81ba03632250 ] + +While reading cipso sysctl variables, they can be changed concurrently. +So, we need to add READ_ONCE() to avoid data-races. + +Fixes: 446fda4f2682 ("[NetLabel]: CIPSOv4 engine") +Signed-off-by: Kuniyuki Iwashima +Acked-by: Paul Moore +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + Documentation/networking/ip-sysctl.txt | 2 +- + net/ipv4/cipso_ipv4.c | 12 +++++++----- + 2 files changed, 8 insertions(+), 6 deletions(-) + +diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt +index a374412610ba..67dfda40b8e6 100644 +--- a/Documentation/networking/ip-sysctl.txt ++++ b/Documentation/networking/ip-sysctl.txt +@@ -781,7 +781,7 @@ cipso_cache_enable - BOOLEAN + cipso_cache_bucket_size - INTEGER + The CIPSO label cache consists of a fixed size hash table with each + hash bucket containing a number of cache entries. This variable limits +- the number of entries in each hash bucket; the larger the value the ++ the number of entries in each hash bucket; the larger the value is, the + more CIPSO label mappings that can be cached. When the number of + entries in a given hash bucket reaches this limit adding new entries + causes the oldest entry in the bucket to be removed to make room. +diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c +index b7dc20a65b64..0bf7196d5d40 100644 +--- a/net/ipv4/cipso_ipv4.c ++++ b/net/ipv4/cipso_ipv4.c +@@ -254,7 +254,7 @@ static int cipso_v4_cache_check(const unsigned char *key, + struct cipso_v4_map_cache_entry *prev_entry = NULL; + u32 hash; + +- if (!cipso_v4_cache_enabled) ++ if (!READ_ONCE(cipso_v4_cache_enabled)) + return -ENOENT; + + hash = cipso_v4_map_cache_hash(key, key_len); +@@ -311,13 +311,14 @@ static int cipso_v4_cache_check(const unsigned char *key, + int cipso_v4_cache_add(const unsigned char *cipso_ptr, + const struct netlbl_lsm_secattr *secattr) + { ++ int bkt_size = READ_ONCE(cipso_v4_cache_bucketsize); + int ret_val = -EPERM; + u32 bkt; + struct cipso_v4_map_cache_entry *entry = NULL; + struct cipso_v4_map_cache_entry *old_entry = NULL; + u32 cipso_ptr_len; + +- if (!cipso_v4_cache_enabled || cipso_v4_cache_bucketsize <= 0) ++ if (!READ_ONCE(cipso_v4_cache_enabled) || bkt_size <= 0) + return 0; + + cipso_ptr_len = cipso_ptr[1]; +@@ -337,7 +338,7 @@ int cipso_v4_cache_add(const unsigned char *cipso_ptr, + + bkt = entry->hash & (CIPSO_V4_CACHE_BUCKETS - 1); + spin_lock_bh(&cipso_v4_cache[bkt].lock); +- if (cipso_v4_cache[bkt].size < cipso_v4_cache_bucketsize) { ++ if (cipso_v4_cache[bkt].size < bkt_size) { + list_add(&entry->list, &cipso_v4_cache[bkt].list); + cipso_v4_cache[bkt].size += 1; + } else { +@@ -1214,7 +1215,8 @@ static int cipso_v4_gentag_rbm(const struct cipso_v4_doi *doi_def, + /* This will send packets using the "optimized" format when + * possible as specified in section 3.4.2.6 of the + * CIPSO draft. */ +- if (cipso_v4_rbm_optfmt && ret_val > 0 && ret_val <= 10) ++ if (READ_ONCE(cipso_v4_rbm_optfmt) && ret_val > 0 && ++ ret_val <= 10) + tag_len = 14; + else + tag_len = 4 + ret_val; +@@ -1617,7 +1619,7 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option) + * all the CIPSO validations here but it doesn't + * really specify _exactly_ what we need to validate + * ... so, just make it a sysctl tunable. */ +- if (cipso_v4_rbm_strictvalid) { ++ if (READ_ONCE(cipso_v4_rbm_strictvalid)) { + if (cipso_v4_map_lvl_valid(doi_def, + tag[3]) < 0) { + err_offset = opt_iter + 3; +-- +2.35.1 + diff --git a/queue-4.9/icmp-fix-data-races-around-sysctl.patch b/queue-4.9/icmp-fix-data-races-around-sysctl.patch new file mode 100644 index 00000000000..ca5697a5cde --- /dev/null +++ b/queue-4.9/icmp-fix-data-races-around-sysctl.patch @@ -0,0 +1,42 @@ +From 8e4dd72311858199ba8afbc4b4bf10393203256a Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 6 Jul 2022 16:40:02 -0700 +Subject: icmp: Fix data-races around sysctl. + +From: Kuniyuki Iwashima + +[ Upstream commit 48d7ee321ea5182c6a70782aa186422a70e67e22 ] + +While reading icmp sysctl variables, they can be changed concurrently. +So, we need to add READ_ONCE() to avoid data-races. + +Fixes: 4cdf507d5452 ("icmp: add a global rate limitation") +Signed-off-by: Kuniyuki Iwashima +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + net/ipv4/icmp.c | 5 +++-- + 1 file changed, 3 insertions(+), 2 deletions(-) + +diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c +index e27ebd00bff2..ada92153b0db 100644 +--- a/net/ipv4/icmp.c ++++ b/net/ipv4/icmp.c +@@ -268,11 +268,12 @@ bool icmp_global_allow(void) + spin_lock(&icmp_global.lock); + delta = min_t(u32, now - icmp_global.stamp, HZ); + if (delta >= HZ / 50) { +- incr = sysctl_icmp_msgs_per_sec * delta / HZ ; ++ incr = READ_ONCE(sysctl_icmp_msgs_per_sec) * delta / HZ; + if (incr) + WRITE_ONCE(icmp_global.stamp, now); + } +- credit = min_t(u32, icmp_global.credit + incr, sysctl_icmp_msgs_burst); ++ credit = min_t(u32, icmp_global.credit + incr, ++ READ_ONCE(sysctl_icmp_msgs_burst)); + if (credit) { + /* We want to use a credit of one in average, but need to randomize + * it for security reasons. +-- +2.35.1 + diff --git a/queue-4.9/ipv4-fix-data-races-around-sysctl_ip_dynaddr.patch b/queue-4.9/ipv4-fix-data-races-around-sysctl_ip_dynaddr.patch new file mode 100644 index 00000000000..fb8246e6a32 --- /dev/null +++ b/queue-4.9/ipv4-fix-data-races-around-sysctl_ip_dynaddr.patch @@ -0,0 +1,59 @@ +From 72111a0ccad0ed9cb061ba7131378ffc554289cc Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 11 Jul 2022 17:15:32 -0700 +Subject: ipv4: Fix data-races around sysctl_ip_dynaddr. + +From: Kuniyuki Iwashima + +[ Upstream commit e49e4aff7ec19b2d0d0957ee30e93dade57dab9e ] + +While reading sysctl_ip_dynaddr, it can be changed concurrently. +Thus, we need to add READ_ONCE() to its readers. + +Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") +Signed-off-by: Kuniyuki Iwashima +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + Documentation/networking/ip-sysctl.txt | 2 +- + net/ipv4/af_inet.c | 4 ++-- + 2 files changed, 3 insertions(+), 3 deletions(-) + +diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt +index 67dfda40b8e6..dfac66c71cb5 100644 +--- a/Documentation/networking/ip-sysctl.txt ++++ b/Documentation/networking/ip-sysctl.txt +@@ -849,7 +849,7 @@ ip_nonlocal_bind - BOOLEAN + which can be quite useful - but may break some applications. + Default: 0 + +-ip_dynaddr - BOOLEAN ++ip_dynaddr - INTEGER + If set non-zero, enables support for dynamic addresses. + If set to a non-zero value larger than 1, a kernel log + message will be printed when dynamic address rewriting +diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c +index 8f2fb14fd4f7..970a498c1166 100644 +--- a/net/ipv4/af_inet.c ++++ b/net/ipv4/af_inet.c +@@ -1122,7 +1122,7 @@ static int inet_sk_reselect_saddr(struct sock *sk) + if (new_saddr == old_saddr) + return 0; + +- if (sock_net(sk)->ipv4.sysctl_ip_dynaddr > 1) { ++ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_dynaddr) > 1) { + pr_info("%s(): shifting inet->saddr from %pI4 to %pI4\n", + __func__, &old_saddr, &new_saddr); + } +@@ -1177,7 +1177,7 @@ int inet_sk_rebuild_header(struct sock *sk) + * Other protocols have to map its equivalent state to TCP_SYN_SENT. + * DCCP maps its DCCP_REQUESTING state to TCP_SYN_SENT. -acme + */ +- if (!sock_net(sk)->ipv4.sysctl_ip_dynaddr || ++ if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_dynaddr) || + sk->sk_state != TCP_SYN_SENT || + (sk->sk_userlocks & SOCK_BINDADDR_LOCK) || + (err = inet_sk_reselect_saddr(sk)) != 0) +-- +2.35.1 + diff --git a/queue-4.9/series b/queue-4.9/series index 46dcd76a941..4c2d4078311 100644 --- a/queue-4.9/series +++ b/queue-4.9/series @@ -5,3 +5,9 @@ net-sock-tracing-fix-sock_exceed_buf_limit-not-to-dereference-stale-pointer.patc arm-9213-1-print-message-about-disabled-spectre-workarounds-only-once.patch nilfs2-fix-incorrect-masking-of-permission-flags-for-symlinks.patch net-dsa-bcm_sf2-force-pause-link-settings.patch +arm-9209-1-spectre-bhb-avoid-pr_info-every-time-a-cp.patch +cipso-fix-data-races-around-sysctl.patch +icmp-fix-data-races-around-sysctl.patch +ipv4-fix-data-races-around-sysctl_ip_dynaddr.patch +sfc-fix-use-after-free-when-disabling-sriov.patch +sfc-fix-kernel-panic-when-creating-vf.patch diff --git a/queue-4.9/sfc-fix-kernel-panic-when-creating-vf.patch b/queue-4.9/sfc-fix-kernel-panic-when-creating-vf.patch new file mode 100644 index 00000000000..78b23996504 --- /dev/null +++ b/queue-4.9/sfc-fix-kernel-panic-when-creating-vf.patch @@ -0,0 +1,71 @@ +From 8cedab0aae867571bd2287ea5f36c9550ad992bc Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 13 Jul 2022 11:21:16 +0200 +Subject: sfc: fix kernel panic when creating VF +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +From: Íñigo Huguet + +[ Upstream commit ada74c5539eba06cf8b47d068f92e0b3963a9a6e ] + +When creating VFs a kernel panic can happen when calling to +efx_ef10_try_update_nic_stats_vf. + +When releasing a DMA coherent buffer, sometimes, I don't know in what +specific circumstances, it has to unmap memory with vunmap. It is +disallowed to do that in IRQ context or with BH disabled. Otherwise, we +hit this line in vunmap, causing the crash: + BUG_ON(in_interrupt()); + +This patch reenables BH to release the buffer. + +Log messages when the bug is hit: + kernel BUG at mm/vmalloc.c:2727! + invalid opcode: 0000 [#1] PREEMPT SMP NOPTI + CPU: 6 PID: 1462 Comm: NetworkManager Kdump: loaded Tainted: G I --------- --- 5.14.0-119.el9.x86_64 #1 + Hardware name: Dell Inc. PowerEdge R740/06WXJT, BIOS 2.8.2 08/27/2020 + RIP: 0010:vunmap+0x2e/0x30 + ...skip... + Call Trace: + __iommu_dma_free+0x96/0x100 + efx_nic_free_buffer+0x2b/0x40 [sfc] + efx_ef10_try_update_nic_stats_vf+0x14a/0x1c0 [sfc] + efx_ef10_update_stats_vf+0x18/0x40 [sfc] + efx_start_all+0x15e/0x1d0 [sfc] + efx_net_open+0x5a/0xe0 [sfc] + __dev_open+0xe7/0x1a0 + __dev_change_flags+0x1d7/0x240 + dev_change_flags+0x21/0x60 + ...skip... + +Fixes: d778819609a2 ("sfc: DMA the VF stats only when requested") +Reported-by: Ma Yuying +Signed-off-by: Íñigo Huguet +Acked-by: Edward Cree +Link: https://lore.kernel.org/r/20220713092116.21238-1-ihuguet@redhat.com +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/sfc/ef10.c | 3 +++ + 1 file changed, 3 insertions(+) + +diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c +index aa2cef8675f4..7b8e0f624c98 100644 +--- a/drivers/net/ethernet/sfc/ef10.c ++++ b/drivers/net/ethernet/sfc/ef10.c +@@ -1830,7 +1830,10 @@ static int efx_ef10_try_update_nic_stats_vf(struct efx_nic *efx) + + efx_update_sw_stats(efx, stats); + out: ++ /* releasing a DMA coherent buffer with BH disabled can panic */ ++ spin_unlock_bh(&efx->stats_lock); + efx_nic_free_buffer(efx, &stats_buf); ++ spin_lock_bh(&efx->stats_lock); + return rc; + } + +-- +2.35.1 + diff --git a/queue-4.9/sfc-fix-use-after-free-when-disabling-sriov.patch b/queue-4.9/sfc-fix-use-after-free-when-disabling-sriov.patch new file mode 100644 index 00000000000..56aa87f8d66 --- /dev/null +++ b/queue-4.9/sfc-fix-use-after-free-when-disabling-sriov.patch @@ -0,0 +1,113 @@ +From aa335e346780baf8806a61580c441998c1a86974 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 12 Jul 2022 08:26:42 +0200 +Subject: sfc: fix use after free when disabling sriov +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +From: Íñigo Huguet + +[ Upstream commit ebe41da5d47ac0fff877e57bd14c54dccf168827 ] + +Use after free is detected by kfence when disabling sriov. What was read +after being freed was vf->pci_dev: it was freed from pci_disable_sriov +and later read in efx_ef10_sriov_free_vf_vports, called from +efx_ef10_sriov_free_vf_vswitching. + +Set the pointer to NULL at release time to not trying to read it later. + +Reproducer and dmesg log (note that kfence doesn't detect it every time): +$ echo 1 > /sys/class/net/enp65s0f0np0/device/sriov_numvfs +$ echo 0 > /sys/class/net/enp65s0f0np0/device/sriov_numvfs + + BUG: KFENCE: use-after-free read in efx_ef10_sriov_free_vf_vswitching+0x82/0x170 [sfc] + + Use-after-free read at 0x00000000ff3c1ba5 (in kfence-#224): + efx_ef10_sriov_free_vf_vswitching+0x82/0x170 [sfc] + efx_ef10_pci_sriov_disable+0x38/0x70 [sfc] + efx_pci_sriov_configure+0x24/0x40 [sfc] + sriov_numvfs_store+0xfe/0x140 + kernfs_fop_write_iter+0x11c/0x1b0 + new_sync_write+0x11f/0x1b0 + vfs_write+0x1eb/0x280 + ksys_write+0x5f/0xe0 + do_syscall_64+0x5c/0x80 + entry_SYSCALL_64_after_hwframe+0x44/0xae + + kfence-#224: 0x00000000edb8ef95-0x00000000671f5ce1, size=2792, cache=kmalloc-4k + + allocated by task 6771 on cpu 10 at 3137.860196s: + pci_alloc_dev+0x21/0x60 + pci_iov_add_virtfn+0x2a2/0x320 + sriov_enable+0x212/0x3e0 + efx_ef10_sriov_configure+0x67/0x80 [sfc] + efx_pci_sriov_configure+0x24/0x40 [sfc] + sriov_numvfs_store+0xba/0x140 + kernfs_fop_write_iter+0x11c/0x1b0 + new_sync_write+0x11f/0x1b0 + vfs_write+0x1eb/0x280 + ksys_write+0x5f/0xe0 + do_syscall_64+0x5c/0x80 + entry_SYSCALL_64_after_hwframe+0x44/0xae + + freed by task 6771 on cpu 12 at 3170.991309s: + device_release+0x34/0x90 + kobject_cleanup+0x3a/0x130 + pci_iov_remove_virtfn+0xd9/0x120 + sriov_disable+0x30/0xe0 + efx_ef10_pci_sriov_disable+0x57/0x70 [sfc] + efx_pci_sriov_configure+0x24/0x40 [sfc] + sriov_numvfs_store+0xfe/0x140 + kernfs_fop_write_iter+0x11c/0x1b0 + new_sync_write+0x11f/0x1b0 + vfs_write+0x1eb/0x280 + ksys_write+0x5f/0xe0 + do_syscall_64+0x5c/0x80 + entry_SYSCALL_64_after_hwframe+0x44/0xae + +Fixes: 3c5eb87605e85 ("sfc: create vports for VFs and assign random MAC addresses") +Reported-by: Yanghang Liu +Signed-off-by: Íñigo Huguet +Acked-by: Martin Habets +Link: https://lore.kernel.org/r/20220712062642.6915-1-ihuguet@redhat.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/sfc/ef10_sriov.c | 10 +++++++--- + 1 file changed, 7 insertions(+), 3 deletions(-) + +diff --git a/drivers/net/ethernet/sfc/ef10_sriov.c b/drivers/net/ethernet/sfc/ef10_sriov.c +index bef23e19cbbd..41a60f66646d 100644 +--- a/drivers/net/ethernet/sfc/ef10_sriov.c ++++ b/drivers/net/ethernet/sfc/ef10_sriov.c +@@ -414,8 +414,9 @@ static int efx_ef10_pci_sriov_enable(struct efx_nic *efx, int num_vfs) + static int efx_ef10_pci_sriov_disable(struct efx_nic *efx, bool force) + { + struct pci_dev *dev = efx->pci_dev; ++ struct efx_ef10_nic_data *nic_data = efx->nic_data; + unsigned int vfs_assigned = pci_vfs_assigned(dev); +- int rc = 0; ++ int i, rc = 0; + + if (vfs_assigned && !force) { + netif_info(efx, drv, efx->net_dev, "VFs are assigned to guests; " +@@ -423,10 +424,13 @@ static int efx_ef10_pci_sriov_disable(struct efx_nic *efx, bool force) + return -EBUSY; + } + +- if (!vfs_assigned) ++ if (!vfs_assigned) { ++ for (i = 0; i < efx->vf_count; i++) ++ nic_data->vf[i].pci_dev = NULL; + pci_disable_sriov(dev); +- else ++ } else { + rc = -EBUSY; ++ } + + efx_ef10_sriov_free_vf_vswitching(efx); + efx->vf_count = 0; +-- +2.35.1 +