- Kernel - mailweb.openeuler.org

[openeuler:openEuler-1.0-LTS] BUILD SUCCESS WITH WARNING c6c0f64fb7e3a44c5ddebc0bf9dfbb71901a28e3
by kernel test robot 15 May '24

15 May '24

tree/branch: https://gitee.com/openeuler/kernel.git openEuler-1.0-LTS branch HEAD: c6c0f64fb7e3a44c5ddebc0bf9dfbb71901a28e3 !7193 CVE-2024-26921 Warning: (recently discovered and may have been fixed) drivers/spi/spi-phytium-plat.c:186:34: warning: unused variable 'phytium_spi_of_match' [-Wunused-const-variable] mm/debug.c:143:21: warning: more '%' conversions than data arguments [-Wformat-insufficient-args] mm/debug.c:174:3: warning: format specifies type 'void *' but the argument has type 'int' [-Wformat] mm/debug.c:175:18: warning: format specifies type 'unsigned long' but the argument has type 'const unsigned long *' [-Wformat] mm/debug.c:175:3: warning: format specifies type 'int' but the argument has type 'unsigned long' [-Wformat] Unverified Warning (likely false positive, please contact us if interested): drivers/block/loop.c:1338 loop_set_status() warn: inconsistent returns '&loop_ctl_mutex'. Warning ids grouped by kconfigs: gcc_recent_errors |-- arm64-allmodconfig | `-- drivers-gpu-drm-nouveau-nvkm-core-object.c:warning:ISO-C90-forbids-mixed-declarations-and-code |-- arm64-defconfig | `-- drivers-gpu-drm-nouveau-nvkm-core-object.c:warning:ISO-C90-forbids-mixed-declarations-and-code |-- x86_64-buildonly-randconfig-006-20240515 | |-- fs-proc-array.c:warning:gtime-may-be-used-uninitialized-in-this-function | |-- fs-proc-array.c:warning:maj_flt-may-be-used-uninitialized-in-this-function | `-- fs-proc-array.c:warning:min_flt-may-be-used-uninitialized-in-this-function |-- x86_64-randconfig-013-20240515 | `-- drivers-gpu-drm-nouveau-nvkm-core-object.c:warning:ISO-C90-forbids-mixed-declarations-and-code `-- x86_64-randconfig-014-20240515 `-- drivers-gpu-drm-nouveau-nvkm-core-object.c:warning:ISO-C90-forbids-mixed-declarations-and-code clang_recent_errors |-- x86_64-allyesconfig | |-- drivers-gpu-drm-nouveau-nvkm-core-object.c:warning:mixing-declarations-and-code-is-a-C99-extension | `-- net-ipv4-arp.c:warning:comparison-of-distinct-pointer-types-(-typeof-(dev-addr_len)-(aka-unsigned-char-)-and-typeof-(sizeof-(r-arp_ha.sa_data))-(aka-unsigned-long-)) |-- x86_64-randconfig-002-20240515 | `-- net-ipv4-arp.c:warning:comparison-of-distinct-pointer-types-(-typeof-(dev-addr_len)-(aka-unsigned-char-)-and-typeof-(sizeof-(r-arp_ha.sa_data))-(aka-unsigned-long-)) |-- x86_64-randconfig-003-20240515 | `-- net-ipv4-arp.c:warning:comparison-of-distinct-pointer-types-(-typeof-(dev-addr_len)-(aka-unsigned-char-)-and-typeof-(sizeof-(r-arp_ha.sa_data))-(aka-unsigned-long-)) |-- x86_64-randconfig-004-20240515 | `-- net-ipv4-arp.c:warning:comparison-of-distinct-pointer-types-(-typeof-(dev-addr_len)-(aka-unsigned-char-)-and-typeof-(sizeof-(r-arp_ha.sa_data))-(aka-unsigned-long-)) |-- x86_64-randconfig-005-20240420 | |-- drivers-spi-spi-phytium-plat.c:warning:unused-variable-phytium_spi_of_match | |-- mm-debug.c:warning:format-specifies-type-int-but-the-argument-has-type-unsigned-long | |-- mm-debug.c:warning:format-specifies-type-unsigned-long-but-the-argument-has-type-const-unsigned-long | |-- mm-debug.c:warning:format-specifies-type-void-but-the-argument-has-type-int | `-- mm-debug.c:warning:more-conversions-than-data-arguments |-- x86_64-randconfig-005-20240515 | |-- drivers-gpu-drm-nouveau-nvkm-core-object.c:warning:mixing-declarations-and-code-is-a-C99-extension | `-- net-ipv4-arp.c:warning:comparison-of-distinct-pointer-types-(-typeof-(dev-addr_len)-(aka-unsigned-char-)-and-typeof-(sizeof-(r-arp_ha.sa_data))-(aka-unsigned-long-)) |-- x86_64-randconfig-006-20240515 | `-- net-ipv4-arp.c:warning:comparison-of-distinct-pointer-types-(-typeof-(dev-addr_len)-(aka-unsigned-char-)-and-typeof-(sizeof-(r-arp_ha.sa_data))-(aka-unsigned-long-)) |-- x86_64-randconfig-011-20240515 | `-- net-ipv4-arp.c:warning:comparison-of-distinct-pointer-types-(-typeof-(dev-addr_len)-(aka-unsigned-char-)-and-typeof-(sizeof-(r-arp_ha.sa_data))-(aka-unsigned-long-)) |-- x86_64-randconfig-012-20240515 | |-- drivers-gpu-drm-nouveau-nvkm-core-object.c:warning:mixing-declarations-and-code-is-a-C99-extension | `-- net-ipv4-arp.c:warning:comparison-of-distinct-pointer-types-(-typeof-(dev-addr_len)-(aka-unsigned-char-)-and-typeof-(sizeof-(r-arp_ha.sa_data))-(aka-unsigned-long-)) |-- x86_64-randconfig-015-20240515 | `-- net-ipv4-arp.c:warning:comparison-of-distinct-pointer-types-(-typeof-(dev-addr_len)-(aka-unsigned-char-)-and-typeof-(sizeof-(r-arp_ha.sa_data))-(aka-unsigned-long-)) |-- x86_64-randconfig-016-20240515 | `-- net-ipv4-arp.c:warning:comparison-of-distinct-pointer-types-(-typeof-(dev-addr_len)-(aka-unsigned-char-)-and-typeof-(sizeof-(r-arp_ha.sa_data))-(aka-unsigned-long-)) |-- x86_64-randconfig-161-20240430 | `-- drivers-block-loop.c-loop_set_status()-warn:inconsistent-returns-loop_ctl_mutex-. |-- x86_64-randconfig-161-20240515 | `-- net-ipv4-arp.c:warning:comparison-of-distinct-pointer-types-(-typeof-(dev-addr_len)-(aka-unsigned-char-)-and-typeof-(sizeof-(r-arp_ha.sa_data))-(aka-unsigned-long-)) `-- x86_64-rhel-8.3-rust `-- net-ipv4-arp.c:warning:comparison-of-distinct-pointer-types-(-typeof-(dev-addr_len)-(aka-unsigned-char-)-and-typeof-(sizeof-(r-arp_ha.sa_data))-(aka-unsigned-long-)) elapsed time: 735m configs tested: 30 configs skipped: 148 tested configs: arm64 allmodconfig gcc arm64 allnoconfig gcc arm64 defconfig gcc arm64 randconfig-001-20240515 gcc arm64 randconfig-002-20240515 gcc arm64 randconfig-003-20240515 gcc arm64 randconfig-004-20240515 gcc x86_64 allnoconfig clang x86_64 allyesconfig clang x86_64 buildonly-randconfig-001-20240515 gcc x86_64 buildonly-randconfig-002-20240515 gcc x86_64 buildonly-randconfig-003-20240515 clang x86_64 buildonly-randconfig-004-20240515 clang x86_64 buildonly-randconfig-005-20240515 clang x86_64 buildonly-randconfig-006-20240515 gcc x86_64 defconfig gcc x86_64 randconfig-001-20240515 gcc x86_64 randconfig-002-20240515 clang x86_64 randconfig-003-20240515 clang x86_64 randconfig-004-20240515 clang x86_64 randconfig-005-20240515 clang x86_64 randconfig-006-20240515 clang x86_64 randconfig-011-20240515 clang x86_64 randconfig-012-20240515 clang x86_64 randconfig-013-20240515 gcc x86_64 randconfig-014-20240515 gcc x86_64 randconfig-015-20240515 clang x86_64 randconfig-016-20240515 clang x86_64 randconfig-071-20240515 gcc x86_64 rhel-8.3-rust clang -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[PATCH OLK-6.6 0/2] Avoiding false sharing in field access of tk_core
by Zheng Zengkai 15 May '24

15 May '24

Backport patch from OLK-5.10 to stabilize the performance of unixbench context1. Wang ShaoBo (1): timekeeping: Avoiding false sharing in field access of tk_core Zheng Zengkai (1): openeuler_defconfig: Enable CONFIG_ARCH_LLC_128_LINE_SIZE for Hisilicon platforms arch/arm64/Kconfig | 9 +++++++++ arch/arm64/configs/openeuler_defconfig | 1 + arch/arm64/include/asm/cache.h | 6 ++++++ kernel/time/timekeeping.c | 7 +++++++ 4 files changed, 23 insertions(+) -- 2.20.1

2 3

[PATCH openEuler-22.03-LTS-SP2] net: bnxt: fix a potential use-after-free in bnxt_init_tc
by Baogen Shang 15 May '24

15 May '24

From: Dinghao Liu <dinghao.liu(a)zju.edu.cn> stable inclusion from stable-v5.10.204 commit 49809af89c07c51eecba64abb013c78ff6812156 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I9J6AL CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=… ------------------------- [ Upstream commit d007caaaf052f82ca2340d4c7b32d04a3f5dbf3f ] When flow_indr_dev_register() fails, bnxt_init_tc will free bp->tc_info through kfree(). However, the caller function bnxt_init_one() will ignore this failure and call bnxt_shutdown_tc() on failure of bnxt_dl_register(), where a use-after-free happens. Fix this issue by setting bp->tc_info to NULL after kfree(). Fixes: 627c89d00fb9 ("bnxt_en: flow_offload: offload tunnel decap rules via indirect callbacks") Signed-off-by: Dinghao Liu <dinghao.liu(a)zju.edu.cn> Reviewed-by: Pavan Chebbi <pavan.chebbi(a)broadcom.com> Reviewed-by: Michael Chan <michael.chan(a)broadcom.com> Reviewed-by: Somnath Kotur <somnath.kotur(a)broadcom.com> Link: https://lore.kernel.org/r/20231204024004.8245-1-dinghao.liu@zju.edu.cn Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Baogen Shang <baogen.shang(a)windriver.com> --- drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index 3e9b1f59e381..775d0b7521ca 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -2061,6 +2061,7 @@ int bnxt_init_tc(struct bnxt *bp) rhashtable_destroy(&tc_info->flow_table); free_tc_info: kfree(tc_info); + bp->tc_info = NULL; return rc; } -- 2.33.0

1 0

[PATCH openEuler-22.03-LTS-SP2] net/bnx2x: Prevent access to a freed page in page_pool
by Baogen Shang 15 May '24

15 May '24

From: Thinh Tran <thinhtr(a)linux.ibm.com> stable inclusion from stable-v5.10.214 commit 8eebff95ce9558be66a36aa7cfb43223f3ab4699 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I9J6AL CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=… ------------------------- [ Upstream commit d27e2da94a42655861ca4baea30c8cd65546f25d ] Fix race condition leading to system crash during EEH error handling During EEH error recovery, the bnx2x driver's transmit timeout logic could cause a race condition when handling reset tasks. The bnx2x_tx_timeout() schedules reset tasks via bnx2x_sp_rtnl_task(), which ultimately leads to bnx2x_nic_unload(). In bnx2x_nic_unload() SGEs are freed using bnx2x_free_rx_sge_range(). However, this could overlap with the EEH driver's attempt to reset the device using bnx2x_io_slot_reset(), which also tries to free SGEs. This race condition can result in system crashes due to accessing freed memory locations in bnx2x_free_rx_sge() 799 static inline void bnx2x_free_rx_sge(struct bnx2x *bp, 800 struct bnx2x_fastpath *fp, u16 index) 801 { 802 struct sw_rx_page *sw_buf = &fp->rx_page_ring[index]; 803 struct page *page = sw_buf->page; .... where sw_buf was set to NULL after the call to dma_unmap_page() by the preceding thread. EEH: Beginning: 'slot_reset' PCI 0011:01:00.0#10000: EEH: Invoking bnx2x->slot_reset() bnx2x: [bnx2x_io_slot_reset:14228(eth1)]IO slot reset initializing... bnx2x 0011:01:00.0: enabling device (0140 -> 0142) bnx2x: [bnx2x_io_slot_reset:14244(eth1)]IO slot reset --> driver unload Kernel attempted to read user page (0) - exploit attempt? (uid: 0) BUG: Kernel NULL pointer dereference on read at 0x00000000 Faulting instruction address: 0xc0080000025065fc Oops: Kernel access of bad area, sig: 11 [#1] ..... Call Trace: [c000000003c67a20] [c00800000250658c] bnx2x_io_slot_reset+0x204/0x610 [bnx2x] (unreliable) [c000000003c67af0] [c0000000000518a8] eeh_report_reset+0xb8/0xf0 [c000000003c67b60] [c000000000052130] eeh_pe_report+0x180/0x550 [c000000003c67c70] [c00000000005318c] eeh_handle_normal_event+0x84c/0xa60 [c000000003c67d50] [c000000000053a84] eeh_event_handler+0xf4/0x170 [c000000003c67da0] [c000000000194c58] kthread+0x1c8/0x1d0 [c000000003c67e10] [c00000000000cf64] ret_from_kernel_thread+0x5c/0x64 To solve this issue, we need to verify page pool allocations before freeing. Fixes: 4cace675d687 ("bnx2x: Alloc 4k fragment for each rx ring buffer element") Signed-off-by: Thinh Tran <thinhtr(a)linux.ibm.com> Reviewed-by: Jiri Pirko <jiri(a)nvidia.com> Link: https://lore.kernel.org/r/20240315205535.1321-1-thinhtr@linux.ibm.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Baogen Shang <baogen.shang(a)windriver.com> --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index d8b1824c334d..0bc1367fd649 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -1002,9 +1002,6 @@ static inline void bnx2x_set_fw_mac_addr(__le16 *fw_hi, __le16 *fw_mid, static inline void bnx2x_free_rx_mem_pool(struct bnx2x *bp, struct bnx2x_alloc_pool *pool) { - if (!pool->page) - return; - put_page(pool->page); pool->page = NULL; @@ -1015,6 +1012,9 @@ static inline void bnx2x_free_rx_sge_range(struct bnx2x *bp, { int i; + if (!fp->page_pool.page) + return; + if (fp->mode == TPA_MODE_DISABLED) return; -- 2.33.0

1 0

[PATCH openEuler-22.03-LTS 4/4] net/tg3: fix race condition in tg3_reset_task()
by Baogen Shang 15 May '24

15 May '24

From: Thinh Tran <thinhtr(a)linux.vnet.ibm.com> stable inclusion from stable-v5.10.209 commit 1059aa41c5a84abfab4cc7371d6b5ff2b30b6c2d category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I9J6AL CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=… ------------------------- [ Upstream commit 16b55b1f2269962fb6b5154b8bf43f37c9a96637 ] When an EEH error is encountered by a PCI adapter, the EEH driver modifies the PCI channel's state as shown below: enum { /* I/O channel is in normal state */ pci_channel_io_normal = (__force pci_channel_state_t) 1, /* I/O to channel is blocked */ pci_channel_io_frozen = (__force pci_channel_state_t) 2, /* PCI card is dead */ pci_channel_io_perm_failure = (__force pci_channel_state_t) 3, }; If the same EEH error then causes the tg3 driver's transmit timeout logic to execute, the tg3_tx_timeout() function schedules a reset task via tg3_reset_task_schedule(), which may cause a race condition between the tg3 and EEH driver as both attempt to recover the HW via a reset action. EEH driver gets error event --> eeh_set_channel_state() and set device to one of error state above scheduler: tg3_reset_task() get returned error from tg3_init_hw() --> dev_close() shuts down the interface tg3_io_slot_reset() and tg3_io_resume() fail to reset/resume the device To resolve this issue, we avoid the race condition by checking the PCI channel state in the tg3_reset_task() function and skip the tg3 driver initiated reset when the PCI channel is not in the normal state. (The driver has no access to tg3 device registers at this point and cannot even complete the reset task successfully without external assistance.) We'll leave the reset procedure to be managed by the EEH driver which calls the tg3_io_error_detected(), tg3_io_slot_reset() and tg3_io_resume() functions as appropriate. Adding the same checking in tg3_dump_state() to avoid dumping all device registers when the PCI channel is not in the normal state. Signed-off-by: Thinh Tran <thinhtr(a)linux.vnet.ibm.com> Tested-by: Venkata Sai Duggi <venkata.sai.duggi(a)ibm.com> Reviewed-by: David Christensen <drc(a)linux.vnet.ibm.com> Reviewed-by: Michael Chan <michael.chan(a)broadcom.com> Link: https://lore.kernel.org/r/20231201001911.656-1-thinhtr@linux.vnet.ibm.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Baogen Shang <baogen.shang(a)windriver.com> --- drivers/net/ethernet/broadcom/tg3.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 07abbc18728b..67de7b1deab1 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -6454,6 +6454,14 @@ static void tg3_dump_state(struct tg3 *tp) int i; u32 *regs; + /* If it is a PCI error, all registers will be 0xffff, + * we don't dump them out, just report the error and return + */ + if (tp->pdev->error_state != pci_channel_io_normal) { + netdev_err(tp->dev, "PCI channel ERROR!\n"); + return; + } + regs = kzalloc(TG3_REG_BLK_SIZE, GFP_ATOMIC); if (!regs) return; @@ -11186,7 +11194,8 @@ static void tg3_reset_task(struct work_struct *work) rtnl_lock(); tg3_full_lock(tp, 0); - if (tp->pcierr_recovery || !netif_running(tp->dev)) { + if (tp->pcierr_recovery || !netif_running(tp->dev) || + tp->pdev->error_state != pci_channel_io_normal) { tg3_flag_clear(tp, RESET_TASK_PENDING); tg3_full_unlock(tp); rtnl_unlock(); -- 2.33.0

1 0

[PATCH openEuler-22.03-LTS 3/4] net/tg3: resolve deadlock in tg3_reset_task() during EEH
by Baogen Shang 15 May '24

15 May '24

From: David Christensen <drc(a)linux.vnet.ibm.com> stable inclusion from stable-v5.10.166 commit 62a0806eb4d2318874563f79c8fdd6bfe34ceddd category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I9J6AL CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=… ------------------------- [ Upstream commit 6c4ca03bd890566d873e3593b32d034bf2f5a087 ] During EEH error injection testing, a deadlock was encountered in the tg3 driver when tg3_io_error_detected() was attempting to cancel outstanding reset tasks: crash> foreach UN bt ... PID: 159 TASK: c0000000067c6000 CPU: 8 COMMAND: "eehd" ... #5 [c00000000681f990] __cancel_work_timer at c00000000019fd18 #6 [c00000000681fa30] tg3_io_error_detected at c00800000295f098 [tg3] #7 [c00000000681faf0] eeh_report_error at c00000000004e25c ... PID: 290 TASK: c000000036e5f800 CPU: 6 COMMAND: "kworker/6:1" ... #4 [c00000003721fbc0] rtnl_lock at c000000000c940d8 #5 [c00000003721fbe0] tg3_reset_task at c008000002969358 [tg3] #6 [c00000003721fc60] process_one_work at c00000000019e5c4 ... PID: 296 TASK: c000000037a65800 CPU: 21 COMMAND: "kworker/21:1" ... #4 [c000000037247bc0] rtnl_lock at c000000000c940d8 #5 [c000000037247be0] tg3_reset_task at c008000002969358 [tg3] #6 [c000000037247c60] process_one_work at c00000000019e5c4 ... PID: 655 TASK: c000000036f49000 CPU: 16 COMMAND: "kworker/16:2" ...:1 #4 [c0000000373ebbc0] rtnl_lock at c000000000c940d8 #5 [c0000000373ebbe0] tg3_reset_task at c008000002969358 [tg3] #6 [c0000000373ebc60] process_one_work at c00000000019e5c4 ... Code inspection shows that both tg3_io_error_detected() and tg3_reset_task() attempt to acquire the RTNL lock at the beginning of their code blocks. If tg3_reset_task() should happen to execute between the times when tg3_io_error_deteced() acquires the RTNL lock and tg3_reset_task_cancel() is called, a deadlock will occur. Moving tg3_reset_task_cancel() call earlier within the code block, prior to acquiring RTNL, prevents this from happening, but also exposes another deadlock issue where tg3_reset_task() may execute AFTER tg3_io_error_detected() has executed: crash> foreach UN bt PID: 159 TASK: c0000000067d2000 CPU: 9 COMMAND: "eehd" ... #4 [c000000006867a60] rtnl_lock at c000000000c940d8 #5 [c000000006867a80] tg3_io_slot_reset at c0080000026c2ea8 [tg3] #6 [c000000006867b00] eeh_report_reset at c00000000004de88 ... PID: 363 TASK: c000000037564000 CPU: 6 COMMAND: "kworker/6:1" ... #3 [c000000036c1bb70] msleep at c000000000259e6c #4 [c000000036c1bba0] napi_disable at c000000000c6b848 #5 [c000000036c1bbe0] tg3_reset_task at c0080000026d942c [tg3] #6 [c000000036c1bc60] process_one_work at c00000000019e5c4 ... This issue can be avoided by aborting tg3_reset_task() if EEH error recovery is already in progress. Fixes: db84bf43ef23 ("tg3: tg3_reset_task() needs to use rtnl_lock to synchronize") Signed-off-by: David Christensen <drc(a)linux.vnet.ibm.com> Reviewed-by: Pavan Chebbi <pavan.chebbi(a)broadcom.com> Link: https://lore.kernel.org/r/20230124185339.225806-1-drc@linux.vnet.ibm.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Baogen Shang <baogen.shang(a)windriver.com> --- drivers/net/ethernet/broadcom/tg3.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 215a02ca4688..07abbc18728b 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -11186,7 +11186,7 @@ static void tg3_reset_task(struct work_struct *work) rtnl_lock(); tg3_full_lock(tp, 0); - if (!netif_running(tp->dev)) { + if (tp->pcierr_recovery || !netif_running(tp->dev)) { tg3_flag_clear(tp, RESET_TASK_PENDING); tg3_full_unlock(tp); rtnl_unlock(); @@ -18188,6 +18188,9 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev, netdev_info(netdev, "PCI I/O error detected\n"); + /* Want to make sure that the reset task doesn't run */ + tg3_reset_task_cancel(tp); + rtnl_lock(); /* Could be second call or maybe we don't have netdev yet */ @@ -18204,9 +18207,6 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev, tg3_timer_stop(tp); - /* Want to make sure that the reset task doesn't run */ - tg3_reset_task_cancel(tp); - netif_device_detach(netdev); /* Clean up software state, even if MMIO is blocked */ -- 2.33.0

1 0

[PATCH openEuler-22.03-LTS 2/4] net: bnxt: fix a potential use-after-free in bnxt_init_tc
by Baogen Shang 15 May '24

15 May '24

From: Dinghao Liu <dinghao.liu(a)zju.edu.cn> stable inclusion from stable-v5.10.204 commit 49809af89c07c51eecba64abb013c78ff6812156 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I9J6AL CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=… ------------------------- [ Upstream commit d007caaaf052f82ca2340d4c7b32d04a3f5dbf3f ] When flow_indr_dev_register() fails, bnxt_init_tc will free bp->tc_info through kfree(). However, the caller function bnxt_init_one() will ignore this failure and call bnxt_shutdown_tc() on failure of bnxt_dl_register(), where a use-after-free happens. Fix this issue by setting bp->tc_info to NULL after kfree(). Fixes: 627c89d00fb9 ("bnxt_en: flow_offload: offload tunnel decap rules via indirect callbacks") Signed-off-by: Dinghao Liu <dinghao.liu(a)zju.edu.cn> Reviewed-by: Pavan Chebbi <pavan.chebbi(a)broadcom.com> Reviewed-by: Michael Chan <michael.chan(a)broadcom.com> Reviewed-by: Somnath Kotur <somnath.kotur(a)broadcom.com> Link: https://lore.kernel.org/r/20231204024004.8245-1-dinghao.liu@zju.edu.cn Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Baogen Shang <baogen.shang(a)windriver.com> --- drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index 3e9b1f59e381..775d0b7521ca 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -2061,6 +2061,7 @@ int bnxt_init_tc(struct bnxt *bp) rhashtable_destroy(&tc_info->flow_table); free_tc_info: kfree(tc_info); + bp->tc_info = NULL; return rc; } -- 2.33.0

1 0

[PATCH openEuler-22.03-LTS 1/4] net/bnx2x: Prevent access to a freed page in page_pool
by Baogen Shang 15 May '24

15 May '24

From: Thinh Tran <thinhtr(a)linux.ibm.com> stable inclusion from stable-v5.10.214 commit 8eebff95ce9558be66a36aa7cfb43223f3ab4699 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I9J6AL CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=… ------------------------- [ Upstream commit d27e2da94a42655861ca4baea30c8cd65546f25d ] Fix race condition leading to system crash during EEH error handling During EEH error recovery, the bnx2x driver's transmit timeout logic could cause a race condition when handling reset tasks. The bnx2x_tx_timeout() schedules reset tasks via bnx2x_sp_rtnl_task(), which ultimately leads to bnx2x_nic_unload(). In bnx2x_nic_unload() SGEs are freed using bnx2x_free_rx_sge_range(). However, this could overlap with the EEH driver's attempt to reset the device using bnx2x_io_slot_reset(), which also tries to free SGEs. This race condition can result in system crashes due to accessing freed memory locations in bnx2x_free_rx_sge() 799 static inline void bnx2x_free_rx_sge(struct bnx2x *bp, 800 struct bnx2x_fastpath *fp, u16 index) 801 { 802 struct sw_rx_page *sw_buf = &fp->rx_page_ring[index]; 803 struct page *page = sw_buf->page; .... where sw_buf was set to NULL after the call to dma_unmap_page() by the preceding thread. EEH: Beginning: 'slot_reset' PCI 0011:01:00.0#10000: EEH: Invoking bnx2x->slot_reset() bnx2x: [bnx2x_io_slot_reset:14228(eth1)]IO slot reset initializing... bnx2x 0011:01:00.0: enabling device (0140 -> 0142) bnx2x: [bnx2x_io_slot_reset:14244(eth1)]IO slot reset --> driver unload Kernel attempted to read user page (0) - exploit attempt? (uid: 0) BUG: Kernel NULL pointer dereference on read at 0x00000000 Faulting instruction address: 0xc0080000025065fc Oops: Kernel access of bad area, sig: 11 [#1] ..... Call Trace: [c000000003c67a20] [c00800000250658c] bnx2x_io_slot_reset+0x204/0x610 [bnx2x] (unreliable) [c000000003c67af0] [c0000000000518a8] eeh_report_reset+0xb8/0xf0 [c000000003c67b60] [c000000000052130] eeh_pe_report+0x180/0x550 [c000000003c67c70] [c00000000005318c] eeh_handle_normal_event+0x84c/0xa60 [c000000003c67d50] [c000000000053a84] eeh_event_handler+0xf4/0x170 [c000000003c67da0] [c000000000194c58] kthread+0x1c8/0x1d0 [c000000003c67e10] [c00000000000cf64] ret_from_kernel_thread+0x5c/0x64 To solve this issue, we need to verify page pool allocations before freeing. Fixes: 4cace675d687 ("bnx2x: Alloc 4k fragment for each rx ring buffer element") Signed-off-by: Thinh Tran <thinhtr(a)linux.ibm.com> Reviewed-by: Jiri Pirko <jiri(a)nvidia.com> Link: https://lore.kernel.org/r/20240315205535.1321-1-thinhtr@linux.ibm.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Baogen Shang <baogen.shang(a)windriver.com> --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index d8b1824c334d..0bc1367fd649 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -1002,9 +1002,6 @@ static inline void bnx2x_set_fw_mac_addr(__le16 *fw_hi, __le16 *fw_mid, static inline void bnx2x_free_rx_mem_pool(struct bnx2x *bp, struct bnx2x_alloc_pool *pool) { - if (!pool->page) - return; - put_page(pool->page); pool->page = NULL; @@ -1015,6 +1012,9 @@ static inline void bnx2x_free_rx_sge_range(struct bnx2x *bp, { int i; + if (!fp->page_pool.page) + return; + if (fp->mode == TPA_MODE_DISABLED) return; -- 2.33.0

1 0

[PATCH openEuler-22.03-LTS 0/4] backport important fix for broadcom net card
by Baogen Shang 15 May '24

15 May '24

From: Baogen Shang <baogen.shang(a)windriver.com> David Christensen (1): net/tg3: resolve deadlock in tg3_reset_task() during EEH Dinghao Liu (1): net: bnxt: fix a potential use-after-free in bnxt_init_tc Thinh Tran (2): net/bnx2x: Prevent access to a freed page in page_pool net/tg3: fix race condition in tg3_reset_task() drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h | 6 +++--- drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c | 1 + drivers/net/ethernet/broadcom/tg3.c | 17 +++++++++++++---- 3 files changed, 17 insertions(+), 7 deletions(-) -- 2.33.0

1 0

[PATCH openEuler-22.03-LTS] nvme-fc: do not wait in vain when unloading module
by Baogen Shang 15 May '24

15 May '24

From: Daniel Wagner <dwagner(a)suse.de> stable inclusion from stable-v5.10.211 commit 4f2c95015ec2a1899161be6c0bdaecedd5a7bfb2 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I9J6AL CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=… ------------------------- [ Upstream commit 70fbfc47a392b98e5f8dba70c6efc6839205c982 ] The module exit path has race between deleting all controllers and freeing 'left over IDs'. To prevent double free a synchronization between nvme_delete_ctrl and ida_destroy has been added by the initial commit. There is some logic around trying to prevent from hanging forever in wait_for_completion, though it does not handling all cases. E.g. blktests is able to reproduce the situation where the module unload hangs forever. If we completely rely on the cleanup code executed from the nvme_delete_ctrl path, all IDs will be freed eventually. This makes calling ida_destroy unnecessary. We only have to ensure that all nvme_delete_ctrl code has been executed before we leave nvme_fc_exit_module. This is done by flushing the nvme_delete_wq workqueue. While at it, remove the unused nvme_fc_wq workqueue too. Reviewed-by: Christoph Hellwig <hch(a)lst.de> Reviewed-by: Hannes Reinecke <hare(a)suse.de> Signed-off-by: Daniel Wagner <dwagner(a)suse.de> Signed-off-by: Keith Busch <kbusch(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Baogen Shang <baogen.shang(a)windriver.com> --- drivers/nvme/host/fc.c | 47 ++++++------------------------------------ 1 file changed, 6 insertions(+), 41 deletions(-) diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index b534a85e2bf1..92db88ceb96f 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -220,11 +220,6 @@ static LIST_HEAD(nvme_fc_lport_list); static DEFINE_IDA(nvme_fc_local_port_cnt); static DEFINE_IDA(nvme_fc_ctrl_cnt); -static struct workqueue_struct *nvme_fc_wq; - -static bool nvme_fc_waiting_to_unload; -static DECLARE_COMPLETION(nvme_fc_unload_proceed); - /* * These items are short-term. They will eventually be moved into * a generic FC class. See comments in module init. @@ -254,8 +249,6 @@ nvme_fc_free_lport(struct kref *ref) /* remove from transport list */ spin_lock_irqsave(&nvme_fc_lock, flags); list_del(&lport->port_list); - if (nvme_fc_waiting_to_unload && list_empty(&nvme_fc_lport_list)) - complete(&nvme_fc_unload_proceed); spin_unlock_irqrestore(&nvme_fc_lock, flags); ida_simple_remove(&nvme_fc_local_port_cnt, lport->localport.port_num); @@ -3823,10 +3816,6 @@ static int __init nvme_fc_init_module(void) { int ret; - nvme_fc_wq = alloc_workqueue("nvme_fc_wq", WQ_MEM_RECLAIM, 0); - if (!nvme_fc_wq) - return -ENOMEM; - /* * NOTE: * It is expected that in the future the kernel will combine @@ -3844,7 +3833,7 @@ static int __init nvme_fc_init_module(void) ret = class_register(&fc_class); if (ret) { pr_err("couldn't register class fc\n"); - goto out_destroy_wq; + return ret; } /* @@ -3868,8 +3857,6 @@ static int __init nvme_fc_init_module(void) device_destroy(&fc_class, MKDEV(0, 0)); out_destroy_class: class_unregister(&fc_class); -out_destroy_wq: - destroy_workqueue(nvme_fc_wq); return ret; } @@ -3889,45 +3876,23 @@ nvme_fc_delete_controllers(struct nvme_fc_rport *rport) spin_unlock(&rport->lock); } -static void -nvme_fc_cleanup_for_unload(void) +static void __exit nvme_fc_exit_module(void) { struct nvme_fc_lport *lport; struct nvme_fc_rport *rport; - - list_for_each_entry(lport, &nvme_fc_lport_list, port_list) { - list_for_each_entry(rport, &lport->endp_list, endp_list) { - nvme_fc_delete_controllers(rport); - } - } -} - -static void __exit nvme_fc_exit_module(void) -{ unsigned long flags; - bool need_cleanup = false; spin_lock_irqsave(&nvme_fc_lock, flags); - nvme_fc_waiting_to_unload = true; - if (!list_empty(&nvme_fc_lport_list)) { - need_cleanup = true; - nvme_fc_cleanup_for_unload(); - } + list_for_each_entry(lport, &nvme_fc_lport_list, port_list) + list_for_each_entry(rport, &lport->endp_list, endp_list) + nvme_fc_delete_controllers(rport); spin_unlock_irqrestore(&nvme_fc_lock, flags); - if (need_cleanup) { - pr_info("%s: waiting for ctlr deletes\n", __func__); - wait_for_completion(&nvme_fc_unload_proceed); - pr_info("%s: ctrl deletes complete\n", __func__); - } + flush_workqueue(nvme_delete_wq); nvmf_unregister_transport(&nvme_fc_transport); - ida_destroy(&nvme_fc_local_port_cnt); - ida_destroy(&nvme_fc_ctrl_cnt); - device_destroy(&fc_class, MKDEV(0, 0)); class_unregister(&fc_class); - destroy_workqueue(nvme_fc_wq); } module_init(nvme_fc_init_module); -- 2.33.0

1 0