From: Martin KaFai Lau martin.lau@kernel.org

[ Upstream commit ee9fd0ac3017c4313be91a220a9ac4c99dde7ad4 ]

KCSAN reported a data-race when accessing node->ref. Although node->ref does not have to be accurate, take this chance to use a more common READ_ONCE() and WRITE_ONCE() pattern instead of data_race().

There is an existing bpf_lru_node_is_ref() and bpf_lru_node_set_ref(). This patch also adds bpf_lru_node_clear_ref() to do the WRITE_ONCE(node->ref, 0) also.

================================================================== BUG: KCSAN: data-race in __bpf_lru_list_rotate / __htab_lru_percpu_map_update_elem

write to 0xffff888137038deb of 1 bytes by task 11240 on cpu 1: __bpf_lru_node_move kernel/bpf/bpf_lru_list.c:113 [inline] __bpf_lru_list_rotate_active kernel/bpf/bpf_lru_list.c:149 [inline] __bpf_lru_list_rotate+0x1bf/0x750 kernel/bpf/bpf_lru_list.c:240 bpf_lru_list_pop_free_to_local kernel/bpf/bpf_lru_list.c:329 [inline] bpf_common_lru_pop_free kernel/bpf/bpf_lru_list.c:447 [inline] bpf_lru_pop_free+0x638/0xe20 kernel/bpf/bpf_lru_list.c:499 prealloc_lru_pop kernel/bpf/hashtab.c:290 [inline] __htab_lru_percpu_map_update_elem+0xe7/0x820 kernel/bpf/hashtab.c:1316 bpf_percpu_hash_update+0x5e/0x90 kernel/bpf/hashtab.c:2313 bpf_map_update_value+0x2a9/0x370 kernel/bpf/syscall.c:200 generic_map_update_batch+0x3ae/0x4f0 kernel/bpf/syscall.c:1687 bpf_map_do_batch+0x2d9/0x3d0 kernel/bpf/syscall.c:4534 __sys_bpf+0x338/0x810 __do_sys_bpf kernel/bpf/syscall.c:5096 [inline] __se_sys_bpf kernel/bpf/syscall.c:5094 [inline] __x64_sys_bpf+0x43/0x50 kernel/bpf/syscall.c:5094 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd

read to 0xffff888137038deb of 1 bytes by task 11241 on cpu 0: bpf_lru_node_set_ref kernel/bpf/bpf_lru_list.h:70 [inline] __htab_lru_percpu_map_update_elem+0x2f1/0x820 kernel/bpf/hashtab.c:1332 bpf_percpu_hash_update+0x5e/0x90 kernel/bpf/hashtab.c:2313 bpf_map_update_value+0x2a9/0x370 kernel/bpf/syscall.c:200 generic_map_update_batch+0x3ae/0x4f0 kernel/bpf/syscall.c:1687 bpf_map_do_batch+0x2d9/0x3d0 kernel/bpf/syscall.c:4534 __sys_bpf+0x338/0x810 __do_sys_bpf kernel/bpf/syscall.c:5096 [inline] __se_sys_bpf kernel/bpf/syscall.c:5094 [inline] __x64_sys_bpf+0x43/0x50 kernel/bpf/syscall.c:5094 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd

value changed: 0x01 -> 0x00

Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 11241 Comm: syz-executor.3 Not tainted 6.3.0-rc7-syzkaller-00136-g6a66fdd29ea1 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/30/2023 ==================================================================

Reported-by: syzbot+ebe648a84e8784763f82@syzkaller.appspotmail.com Signed-off-by: Martin KaFai Lau martin.lau@kernel.org Acked-by: Yonghong Song yhs@fb.com Link: https://lore.kernel.org/r/20230511043748.1384166-1-martin.lau@linux.dev Signed-off-by: Alexei Starovoitov ast@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/bpf/bpf_lru_list.c | 21 +++++++++++++-------- kernel/bpf/bpf_lru_list.h | 7 ++----- 2 files changed, 15 insertions(+), 13 deletions(-)

diff --git a/kernel/bpf/bpf_lru_list.c b/kernel/bpf/bpf_lru_list.c index d99e89f113c43..3dabdd137d102 100644 --- a/kernel/bpf/bpf_lru_list.c +++ b/kernel/bpf/bpf_lru_list.c @@ -41,7 +41,12 @@ static struct list_head *local_pending_list(struct bpf_lru_locallist *loc_l) /* bpf_lru_node helpers */ static bool bpf_lru_node_is_ref(const struct bpf_lru_node *node) { - return node->ref; + return READ_ONCE(node->ref); +} + +static void bpf_lru_node_clear_ref(struct bpf_lru_node *node) +{ + WRITE_ONCE(node->ref, 0); }

static void bpf_lru_list_count_inc(struct bpf_lru_list *l, @@ -89,7 +94,7 @@ static void __bpf_lru_node_move_in(struct bpf_lru_list *l,

bpf_lru_list_count_inc(l, tgt_type); node->type = tgt_type; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_move(&node->list, &l->lists[tgt_type]); }

@@ -110,7 +115,7 @@ static void __bpf_lru_node_move(struct bpf_lru_list *l, bpf_lru_list_count_inc(l, tgt_type); node->type = tgt_type; } - node->ref = 0; + bpf_lru_node_clear_ref(node);

/* If the moving node is the next_inactive_rotation candidate, * move the next_inactive_rotation pointer also. @@ -353,7 +358,7 @@ static void __local_list_add_pending(struct bpf_lru *lru, *(u32 *)((void *)node + lru->hash_offset) = hash; node->cpu = cpu; node->type = BPF_LRU_LOCAL_LIST_T_PENDING; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_add(&node->list, local_pending_list(loc_l)); }

@@ -419,7 +424,7 @@ static struct bpf_lru_node *bpf_percpu_lru_pop_free(struct bpf_lru *lru, if (!list_empty(free_list)) { node = list_first_entry(free_list, struct bpf_lru_node, list); *(u32 *)((void *)node + lru->hash_offset) = hash; - node->ref = 0; + bpf_lru_node_clear_ref(node); __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_INACTIVE); }

@@ -522,7 +527,7 @@ static void bpf_common_lru_push_free(struct bpf_lru *lru, }

node->type = BPF_LRU_LOCAL_LIST_T_FREE; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_move(&node->list, local_free_list(loc_l));

raw_spin_unlock_irqrestore(&loc_l->lock, flags); @@ -568,7 +573,7 @@ static void bpf_common_lru_populate(struct bpf_lru *lru, void *buf,

node = (struct bpf_lru_node *)(buf + node_offset); node->type = BPF_LRU_LIST_T_FREE; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_add(&node->list, &l->lists[BPF_LRU_LIST_T_FREE]); buf += elem_size; } @@ -594,7 +599,7 @@ static void bpf_percpu_lru_populate(struct bpf_lru *lru, void *buf, node = (struct bpf_lru_node *)(buf + node_offset); node->cpu = cpu; node->type = BPF_LRU_LIST_T_FREE; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_add(&node->list, &l->lists[BPF_LRU_LIST_T_FREE]); i++; buf += elem_size; diff --git a/kernel/bpf/bpf_lru_list.h b/kernel/bpf/bpf_lru_list.h index 6b12f06ee18c3..9c12ee453c616 100644 --- a/kernel/bpf/bpf_lru_list.h +++ b/kernel/bpf/bpf_lru_list.h @@ -63,11 +63,8 @@ struct bpf_lru {

static inline void bpf_lru_node_set_ref(struct bpf_lru_node *node) { - /* ref is an approximation on access frequency. It does not - * have to be very accurate. Hence, no protection is used. - */ - if (!node->ref) - node->ref = 1; + if (!READ_ONCE(node->ref)) + WRITE_ONCE(node->ref, 1); }

int bpf_lru_init(struct bpf_lru *lru, bool percpu, u32 hash_offset,

From: "Gustavo A. R. Silva" gustavoars@kernel.org

[ Upstream commit 71e7552c90db2a2767f5c17c7ec72296b0d92061 ]

-Wstringop-overflow is legitimately warning us about extra_size pontentially being zero at some point, hence potenially ending up _allocating_ zero bytes of memory for extra pointer and then trying to access such object in a call to copy_from_user().

Fix this by adding a sanity check to ensure we never end up trying to allocate zero bytes of data for extra pointer, before continue executing the rest of the code in the function.

Address the following -Wstringop-overflow warning seen when built m68k architecture with allyesconfig configuration: from net/wireless/wext-core.c:11: In function '_copy_from_user', inlined from 'copy_from_user' at include/linux/uaccess.h:183:7, inlined from 'ioctl_standard_iw_point' at net/wireless/wext-core.c:825:7: arch/m68k/include/asm/string.h:48:25: warning: '__builtin_memset' writing 1 or more bytes into a region of size 0 overflows the destination [-Wstringop-overflow=] 48 | #define memset(d, c, n) __builtin_memset(d, c, n) | ^~~~~~~~~~~~~~~~~~~~~~~~~ include/linux/uaccess.h:153:17: note: in expansion of macro 'memset' 153 | memset(to + (n - res), 0, res); | ^~~~~~ In function 'kmalloc', inlined from 'kzalloc' at include/linux/slab.h:694:9, inlined from 'ioctl_standard_iw_point' at net/wireless/wext-core.c:819:10: include/linux/slab.h:577:16: note: at offset 1 into destination object of size 0 allocated by '__kmalloc' 577 | return __kmalloc(size, flags); | ^~~~~~~~~~~~~~~~~~~~~~

This help with the ongoing efforts to globally enable -Wstringop-overflow.

Link: https://github.com/KSPP/linux/issues/315 Signed-off-by: Gustavo A. R. Silva gustavoars@kernel.org Reviewed-by: Simon Horman simon.horman@corigine.com Link: https://lore.kernel.org/r/ZItSlzvIpjdjNfd8@work Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/wireless/wext-core.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index 76a80a41615be..a57f54bc0e1a7 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -796,6 +796,12 @@ static int ioctl_standard_iw_point(struct iw_point *iwp, unsigned int cmd, } }

+ /* Sanity-check to ensure we never end up _allocating_ zero + * bytes of data for extra. + */ + if (extra_size <= 0) + return -EFAULT; + /* kzalloc() ensures NULL-termination for essid_compat. */ extra = kzalloc(extra_size, GFP_KERNEL); if (!extra)

From: Ying Hsu yinghsu@chromium.org

[ Upstream commit 004d25060c78fc31f66da0fa439c544dda1ac9d5 ]

In a setup where a Thunderbolt hub connects to Ethernet and a display through USB Type-C, users may experience a hung task timeout when they remove the cable between the PC and the Thunderbolt hub. This is because the igb_down function is called multiple times when the Thunderbolt hub is unplugged. For example, the igb_io_error_detected triggers the first call, and the igb_remove triggers the second call. The second call to igb_down will block at napi_synchronize. Here's the call trace: __schedule+0x3b0/0xddb ? __mod_timer+0x164/0x5d3 schedule+0x44/0xa8 schedule_timeout+0xb2/0x2a4 ? run_local_timers+0x4e/0x4e msleep+0x31/0x38 igb_down+0x12c/0x22a [igb 6615058754948bfde0bf01429257eb59f13030d4] __igb_close+0x6f/0x9c [igb 6615058754948bfde0bf01429257eb59f13030d4] igb_close+0x23/0x2b [igb 6615058754948bfde0bf01429257eb59f13030d4] __dev_close_many+0x95/0xec dev_close_many+0x6e/0x103 unregister_netdevice_many+0x105/0x5b1 unregister_netdevice_queue+0xc2/0x10d unregister_netdev+0x1c/0x23 igb_remove+0xa7/0x11c [igb 6615058754948bfde0bf01429257eb59f13030d4] pci_device_remove+0x3f/0x9c device_release_driver_internal+0xfe/0x1b4 pci_stop_bus_device+0x5b/0x7f pci_stop_bus_device+0x30/0x7f pci_stop_bus_device+0x30/0x7f pci_stop_and_remove_bus_device+0x12/0x19 pciehp_unconfigure_device+0x76/0xe9 pciehp_disable_slot+0x6e/0x131 pciehp_handle_presence_or_link_change+0x7a/0x3f7 pciehp_ist+0xbe/0x194 irq_thread_fn+0x22/0x4d ? irq_thread+0x1fd/0x1fd irq_thread+0x17b/0x1fd ? irq_forced_thread_fn+0x5f/0x5f kthread+0x142/0x153 ? __irq_get_irqchip_state+0x46/0x46 ? kthread_associate_blkcg+0x71/0x71 ret_from_fork+0x1f/0x30

In this case, igb_io_error_detected detaches the network interface and requests a PCIE slot reset, however, the PCIE reset callback is not being invoked and thus the Ethernet connection breaks down. As the PCIE error in this case is a non-fatal one, requesting a slot reset can be avoided. This patch fixes the task hung issue and preserves Ethernet connection by ignoring non-fatal PCIE errors.

Signed-off-by: Ying Hsu yinghsu@chromium.org Tested-by: Pucha Himasekhar Reddy himasekharx.reddy.pucha@intel.com (A Contingent worker at Intel) Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Reviewed-by: Simon Horman simon.horman@corigine.com Link: https://lore.kernel.org/r/20230620174732.4145155-1-anthony.l.nguyen@intel.co... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/igb/igb_main.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index c5f465814dec3..4465982100127 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -9453,6 +9453,11 @@ static pci_ers_result_t igb_io_error_detected(struct pci_dev *pdev, struct net_device *netdev = pci_get_drvdata(pdev); struct igb_adapter *adapter = netdev_priv(netdev);

+ if (state == pci_channel_io_normal) { + dev_warn(&pdev->dev, "Non-correctable non-fatal error reported.\n"); + return PCI_ERS_RESULT_CAN_RECOVER; + } + netif_device_detach(netdev);

if (state == pci_channel_io_perm_failure)