From: Dave Jiang dave.jiang@intel.com

[ Upstream commit 077cdb355b3d8ee0f258856962e6dac06e744401 ]

The idxd_unregister_driver() has never been called for the idxd driver upon removal. Add fix to call unregister driver on module removal.

Fixes: c52ca478233c ("dmaengine: idxd: add configuration component of driver") Signed-off-by: Dave Jiang dave.jiang@intel.com Link: https://lore.kernel.org/r/161947994449.1053102.13189942817915448216.stgit@dj... Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/dma/idxd/init.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index f73677490b6c..eb41bb9df0fd 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -719,6 +719,7 @@ module_init(idxd_init_module);

static void __exit idxd_exit_module(void) { + idxd_unregister_driver(); pci_unregister_driver(&idxd_pci_driver); idxd_cdev_remove(); idxd_unregister_bus_type();

From: Quanyang Wang quanyang.wang@windriver.com

[ Upstream commit 538ea65a9fd1194352a41313bff876b74b5d90c5 ]

In some scenarios (kdump), dpdma hardware irqs has been enabled when calling request_irq in probe function, and then the dpdma irq handler xilinx_dpdma_irq_handler is invoked to access xdev->chan[i]. But at this moment xdev->chan[i] hasn't been initialized.

We should ensure the dpdma controller to be in a consistent and clean state before further initialization. So add dpdma_hw_init() to do this.

Furthermore, in xilinx_dpdma_disable_irq, disable all interrupts instead of error interrupts.

This patch is to fix the kdump kernel crash as below:

[ 3.696128] Unable to handle kernel NULL pointer dereference at virtual address 000000000000012c [ 3.696710] xilinx-zynqmp-dpdma fd4c0000.dma-controller: Xilinx DPDMA engine is probed [ 3.704900] Mem abort info: [ 3.704902] ESR = 0x96000005 [ 3.704905] EC = 0x25: DABT (current EL), IL = 32 bits [ 3.704907] SET = 0, FnV = 0 [ 3.704912] EA = 0, S1PTW = 0 [ 3.713800] ahci-ceva fd0c0000.ahci: supply ahci not found, using dummy regulator [ 3.715585] Data abort info: [ 3.715587] ISV = 0, ISS = 0x00000005 [ 3.715589] CM = 0, WnR = 0 [ 3.715592] [000000000000012c] user address but active_mm is swapper [ 3.715596] Internal error: Oops: 96000005 [#1] SMP [ 3.715599] Modules linked in: [ 3.715608] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.10.0-12170-g60894882155f-dirty #77 [ 3.723937] Hardware name: ZynqMP ZCU102 Rev1.0 (DT) [ 3.723942] pstate: 80000085 (Nzcv daIf -PAN -UAO -TCO BTYPE=--) [ 3.723956] pc : xilinx_dpdma_irq_handler+0x418/0x560 [ 3.793049] lr : xilinx_dpdma_irq_handler+0x3d8/0x560 [ 3.798089] sp : ffffffc01186bdf0 [ 3.801388] x29: ffffffc01186bdf0 x28: ffffffc011836f28 [ 3.806692] x27: ffffff8023e0ac80 x26: 0000000000000080 [ 3.811996] x25: 0000000008000408 x24: 0000000000000003 [ 3.817300] x23: ffffffc01186be70 x22: ffffffc011291740 [ 3.822604] x21: 0000000000000000 x20: 0000000008000408 [ 3.827908] x19: 0000000000000000 x18: 0000000000000010 [ 3.833212] x17: 0000000000000000 x16: 0000000000000000 [ 3.838516] x15: 0000000000000000 x14: ffffffc011291740 [ 3.843820] x13: ffffffc02eb4d000 x12: 0000000034d4d91d [ 3.849124] x11: 0000000000000040 x10: ffffffc0112d2d48 [ 3.854428] x9 : ffffffc0112d2d40 x8 : ffffff8021c00268 [ 3.859732] x7 : 0000000000000000 x6 : ffffffc011836000 [ 3.865036] x5 : 0000000000000003 x4 : 0000000000000000 [ 3.870340] x3 : 0000000000000001 x2 : 0000000000000000 [ 3.875644] x1 : 0000000000000000 x0 : 000000000000012c [ 3.880948] Call trace: [ 3.883382] xilinx_dpdma_irq_handler+0x418/0x560 [ 3.888079] __handle_irq_event_percpu+0x5c/0x178 [ 3.892774] handle_irq_event_percpu+0x34/0x98 [ 3.897210] handle_irq_event+0x44/0xb8 [ 3.901030] handle_fasteoi_irq+0xd0/0x190 [ 3.905117] generic_handle_irq+0x30/0x48 [ 3.909111] __handle_domain_irq+0x64/0xc0 [ 3.913192] gic_handle_irq+0x78/0xa0 [ 3.916846] el1_irq+0xc4/0x180 [ 3.919982] cpuidle_enter_state+0x134/0x2f8 [ 3.924243] cpuidle_enter+0x38/0x50 [ 3.927810] call_cpuidle+0x1c/0x40 [ 3.931290] do_idle+0x20c/0x270 [ 3.934502] cpu_startup_entry+0x28/0x58 [ 3.938410] rest_init+0xbc/0xcc [ 3.941631] arch_call_rest_init+0x10/0x1c [ 3.945718] start_kernel+0x51c/0x558

Fixes: 7cbb0c63de3f ("dmaengine: xilinx: dpdma: Add the Xilinx DisplayPort DMA engine driver") Signed-off-by: Quanyang Wang quanyang.wang@windriver.com Link: https://lore.kernel.org/r/20210430064041.4058180-1-quanyang.wang@windriver.c... Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/dma/xilinx/xilinx_dpdma.c | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-)

diff --git a/drivers/dma/xilinx/xilinx_dpdma.c b/drivers/dma/xilinx/xilinx_dpdma.c index 70b29bd079c9..ff7dfb3fdeb4 100644 --- a/drivers/dma/xilinx/xilinx_dpdma.c +++ b/drivers/dma/xilinx/xilinx_dpdma.c @@ -1459,7 +1459,7 @@ static void xilinx_dpdma_enable_irq(struct xilinx_dpdma_device *xdev) */ static void xilinx_dpdma_disable_irq(struct xilinx_dpdma_device *xdev) { - dpdma_write(xdev->reg, XILINX_DPDMA_IDS, XILINX_DPDMA_INTR_ERR_ALL); + dpdma_write(xdev->reg, XILINX_DPDMA_IDS, XILINX_DPDMA_INTR_ALL); dpdma_write(xdev->reg, XILINX_DPDMA_EIDS, XILINX_DPDMA_EINTR_ALL); }

@@ -1596,6 +1596,26 @@ static struct dma_chan *of_dma_xilinx_xlate(struct of_phandle_args *dma_spec, return dma_get_slave_channel(&xdev->chan[chan_id]->vchan.chan); }

+static void dpdma_hw_init(struct xilinx_dpdma_device *xdev) +{ + unsigned int i; + void __iomem *reg; + + /* Disable all interrupts */ + xilinx_dpdma_disable_irq(xdev); + + /* Stop all channels */ + for (i = 0; i < ARRAY_SIZE(xdev->chan); i++) { + reg = xdev->reg + XILINX_DPDMA_CH_BASE + + XILINX_DPDMA_CH_OFFSET * i; + dpdma_clr(reg, XILINX_DPDMA_CH_CNTL, XILINX_DPDMA_CH_CNTL_ENABLE); + } + + /* Clear the interrupt status registers */ + dpdma_write(xdev->reg, XILINX_DPDMA_ISR, XILINX_DPDMA_INTR_ALL); + dpdma_write(xdev->reg, XILINX_DPDMA_EISR, XILINX_DPDMA_EINTR_ALL); +} + static int xilinx_dpdma_probe(struct platform_device *pdev) { struct xilinx_dpdma_device *xdev; @@ -1622,6 +1642,8 @@ static int xilinx_dpdma_probe(struct platform_device *pdev) if (IS_ERR(xdev->reg)) return PTR_ERR(xdev->reg);

+ dpdma_hw_init(xdev); + xdev->irq = platform_get_irq(pdev, 0); if (xdev->irq < 0) { dev_err(xdev->dev, "failed to get platform irq\n");

From: Randy Dunlap rdunlap@infradead.org

[ Upstream commit 0cfbb589d67f16fa55b26ae02b69c31b52e344b1 ]

When CONFIG_HAS_IOMEM is not set/enabled, certain iomap() family functions [including ioremap(), devm_ioremap(), etc.] are not available. Drivers that use these functions should depend on HAS_IOMEM so that they do not cause build errors.

Rectifies these build errors: s390-linux-ld: drivers/dma/qcom/hidma_mgmt.o: in function `hidma_mgmt_probe': hidma_mgmt.c:(.text+0x780): undefined reference to `devm_ioremap_resource' s390-linux-ld: drivers/dma/qcom/hidma_mgmt.o: in function `hidma_mgmt_init': hidma_mgmt.c:(.init.text+0x126): undefined reference to `of_address_to_resource' s390-linux-ld: hidma_mgmt.c:(.init.text+0x16e): undefined reference to `of_address_to_resource'

Fixes: 67a2003e0607 ("dmaengine: add Qualcomm Technologies HIDMA channel driver") Signed-off-by: Randy Dunlap rdunlap@infradead.org Reported-by: kernel test robot lkp@intel.com Cc: Sinan Kaya okaya@codeaurora.org Cc: Vinod Koul vkoul@kernel.org Cc: dmaengine@vger.kernel.org Link: https://lore.kernel.org/r/20210522021313.16405-3-rdunlap@infradead.org Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/dma/qcom/Kconfig | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/dma/qcom/Kconfig b/drivers/dma/qcom/Kconfig index 365f94eb3b08..3f926a653bd8 100644 --- a/drivers/dma/qcom/Kconfig +++ b/drivers/dma/qcom/Kconfig @@ -33,6 +33,7 @@ config QCOM_GPI_DMA

config QCOM_HIDMA_MGMT tristate "Qualcomm Technologies HIDMA Management support" + depends on HAS_IOMEM select DMA_ENGINE help Enable support for the Qualcomm Technologies HIDMA Management.

From: Yang Yingliang yangyingliang@huawei.com

[ Upstream commit fffdaba402cea79b8d219355487d342ec23f91c6 ]

Add the missing iounmap() before return from d40_probe() in the error handling case.

Fixes: 8d318a50b3d7 ("DMAENGINE: Support for ST-Ericssons DMA40 block v3") Reported-by: Hulk Robot hulkci@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com Reviewed-by: Linus Walleij linus.walleij@linaro.org Link: https://lore.kernel.org/r/20210518141108.1324127-1-yangyingliang@huawei.com Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/dma/ste_dma40.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c index 265d7c07b348..e1827393143f 100644 --- a/drivers/dma/ste_dma40.c +++ b/drivers/dma/ste_dma40.c @@ -3675,6 +3675,9 @@ static int __init d40_probe(struct platform_device *pdev)

kfree(base->lcla_pool.base_unaligned);

+ if (base->lcpa_base) + iounmap(base->lcpa_base); + if (base->phy_lcpa) release_mem_region(base->phy_lcpa, base->lcpa_size);

From: yangerkun yangerkun@huawei.com

[ Upstream commit e8675d291ac007e1c636870db880f837a9ea112a ]

Our syzkaller trigger the "BUG_ON(!list_empty(&inode->i_wb_list))" in clear_inode:

kernel BUG at fs/inode.c:519! Internal error: Oops - BUG: 0 [#1] SMP Modules linked in: Process syz-executor.0 (pid: 249, stack limit = 0x00000000a12409d7) CPU: 1 PID: 249 Comm: syz-executor.0 Not tainted 4.19.95 Hardware name: linux,dummy-virt (DT) pstate: 80000005 (Nzcv daif -PAN -UAO) pc : clear_inode+0x280/0x2a8 lr : clear_inode+0x280/0x2a8 Call trace: clear_inode+0x280/0x2a8 ext4_clear_inode+0x38/0xe8 ext4_free_inode+0x130/0xc68 ext4_evict_inode+0xb20/0xcb8 evict+0x1a8/0x3c0 iput+0x344/0x460 do_unlinkat+0x260/0x410 __arm64_sys_unlinkat+0x6c/0xc0 el0_svc_common+0xdc/0x3b0 el0_svc_handler+0xf8/0x160 el0_svc+0x10/0x218 Kernel panic - not syncing: Fatal exception

A crash dump of this problem show that someone called __munlock_pagevec to clear page LRU without lock_page: do_mmap -> mmap_region -> do_munmap -> munlock_vma_pages_range -> __munlock_pagevec.

As a result memory_failure will call identify_page_state without wait_on_page_writeback. And after truncate_error_page clear the mapping of this page. end_page_writeback won't call sb_clear_inode_writeback to clear inode->i_wb_list. That will trigger BUG_ON in clear_inode!

Fix it by checking PageWriteback too to help determine should we skip wait_on_page_writeback.

Link: https://lkml.kernel.org/r/20210604084705.3729204-1-yangerkun@huawei.com Fixes: 0bc1f8b0682c ("hwpoison: fix the handling path of the victimized page frame that belong to non-LRU") Signed-off-by: yangerkun yangerkun@huawei.com Acked-by: Naoya Horiguchi naoya.horiguchi@nec.com Cc: Jan Kara jack@suse.cz Cc: Theodore Ts'o tytso@mit.edu Cc: Oscar Salvador osalvador@suse.de Cc: Yu Kuai yukuai3@huawei.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- mm/memory-failure.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/mm/memory-failure.c b/mm/memory-failure.c index bd3945446d47..fd2c0271502a 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1527,7 +1527,12 @@ try_again: return 0; }

- if (!PageTransTail(p) && !PageLRU(p)) + /* + * __munlock_pagevec may clear a writeback page's LRU flag without + * page_lock. We need wait writeback completion for this page or it + * may trigger vfs BUG while evict inode. + */ + if (!PageTransTail(p) && !PageLRU(p) && !PageWriteback(p)) goto identify_page_state;

/*

From: Matthew Bobrowski repnop@google.com

[ Upstream commit f644bc449b37cc32d3ce7b36a88073873aa21bd5 ]

Ensure that clean up is performed on the allocated file descriptor and struct file object in the event that an error is encountered while copying fid info objects. Currently, we return directly to the caller when an error is experienced in the fid info copying helper, which isn't ideal given that the listener process could be left with a dangling file descriptor in their fdtable.

Fixes: 5e469c830fdb ("fanotify: copy event fid info to user") Fixes: 44d705b0370b ("fanotify: report name info for FAN_DIR_MODIFY event") Link: https://lore.kernel.org/linux-fsdevel/YMKv1U7tNPK955ho@google.com/T/#m15361c... Link: https://lore.kernel.org/r/1ef8ae9100101eb1a91763c516c2e9a3a3b112bd.162337634... Signed-off-by: Matthew Bobrowski repnop@google.com Signed-off-by: Jan Kara jack@suse.cz Signed-off-by: Sasha Levin sashal@kernel.org --- fs/notify/fanotify/fanotify_user.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 9e0c1afac8bd..c175523b0a2c 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -378,7 +378,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, info_type, fanotify_info_name(info), info->name_len, buf, count); if (ret < 0) - return ret; + goto out_close_fd;

buf += ret; count -= ret; @@ -426,7 +426,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, fanotify_event_object_fh(event), info_type, dot, dot_len, buf, count); if (ret < 0) - return ret; + goto out_close_fd;

buf += ret; count -= ret;

From: Johannes Berg johannes.berg@intel.com

[ Upstream commit b90f51e8e1f5014c01c82a7bf4c611643d0a8bcb ]

Due to the locking changes and callbacks happening inside cfg80211, we need to use cfg80211 versions of the register and unregister functions if called within cfg80211 methods, otherwise deadlocks occur.

Fixes: a05829a7222e ("cfg80211: avoid holding the RTNL when calling the driver") Acked-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Link: https://lore.kernel.org/r/20210426212801.3d902cc9e6f4.Ie0b1e0c545920c61400a4... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c index cbec65e5a464..62ea47f9fee5 100644 --- a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c +++ b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c @@ -2579,7 +2579,7 @@ static int rtw_cfg80211_add_monitor_if(struct adapter *padapter, char *name, str mon_wdev->iftype = NL80211_IFTYPE_MONITOR; mon_ndev->ieee80211_ptr = mon_wdev;

- ret = register_netdevice(mon_ndev); + ret = cfg80211_register_netdevice(mon_ndev); if (ret) { goto out; } @@ -2661,7 +2661,7 @@ static int cfg80211_rtw_del_virtual_intf(struct wiphy *wiphy, adapter = rtw_netdev_priv(ndev); pwdev_priv = adapter_wdev_data(adapter);

- unregister_netdevice(ndev); + cfg80211_unregister_netdevice(ndev);

if (ndev == pwdev_priv->pmon_ndev) { pwdev_priv->pmon_ndev = NULL;

From: Petr Machata petrm@nvidia.com

[ Upstream commit 306b9228c097b4101c150ccd262372ded8348644 ]

A max-shaper is the HW component responsible for delaying egress traffic above a configured transmission rate. Burst size is the amount of traffic that is allowed to pass without accounting. The burst size value needs to be such that it can be expressed as 2^BS * 512 bits, where BS lies in a certain ASIC-dependent range. mlxsw enforces that this holds before attempting to configure the shaper.

The assumption for Spectrum-3 was that the lower limit of BS would be 5, like for Spectrum-1. But as of now, the limit is still 11. Therefore fix the driver accordingly, so that incorrect values are rejected early with a proper message.

Fixes: 23effa2479ba ("mlxsw: reg: Add max_shaper_bs to QoS ETS Element Configuration") Reported-by: Maksym Yaremchuk maksymy@nvidia.com Signed-off-by: Petr Machata petrm@nvidia.com Signed-off-by: Ido Schimmel idosch@nvidia.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlxsw/reg.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index c4adc7f740d3..769386971ac3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -3863,7 +3863,7 @@ MLXSW_ITEM32(reg, qeec, max_shaper_bs, 0x1C, 0, 6); #define MLXSW_REG_QEEC_HIGHEST_SHAPER_BS 25 #define MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP1 5 #define MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP2 11 -#define MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP3 5 +#define MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP3 11

static inline void mlxsw_reg_qeec_pack(char *payload, u8 local_port, enum mlxsw_reg_qeec_hr hr, u8 index,

From: Kev Jackson foamdino@gmail.com

[ Upstream commit 11fc79fc9f2e395aa39fa5baccae62767c5d8280 ]

When calling xsk_socket__create_shared(), the logic at line 1097 marks a boolean flag true within the xsk_umem structure to track setup progress in order to support multiple calls to the function. However, instead of marking umem->tx_ring_setup_done, the code incorrectly sets umem->rx_ring_setup_done. This leads to improper behaviour when creating and destroying xsk and umem structures.

Multiple calls to this function is documented as supported.

Fixes: ca7a83e2487a ("libbpf: Only create rx and tx XDP rings when necessary") Signed-off-by: Kev Jackson foamdino@gmail.com Signed-off-by: Andrii Nakryiko andrii@kernel.org Acked-by: Yonghong Song yhs@fb.com Link: https://lore.kernel.org/bpf/YL4aU4f3Aaik7CN0@linux-dev Signed-off-by: Sasha Levin sashal@kernel.org --- tools/lib/bpf/xsk.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index 007fe5d59438..fe2bec500bf6 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -928,7 +928,7 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr, goto out_put_ctx; } if (xsk->fd == umem->fd) - umem->rx_ring_setup_done = true; + umem->tx_ring_setup_done = true; }

err = xsk_get_mmap_offsets(xsk->fd, &off);

From: Nicolas Dichtel nicolas.dichtel@6wind.com

[ Upstream commit 9bb392f62447d73cc7dd7562413a2cd9104c82f8 ]

My initial goal was to fix the default MTU, which is set to 65536, ie above the maximum defined in the driver: 65535 (ETH_MAX_MTU).

In fact, it's seems more consistent, wrt min_mtu, to set the max_mtu to IP6_MAX_MTU (65535 + sizeof(struct ipv6hdr)) and use it by default.

Let's also, for consistency, set the mtu in vrf_setup(). This function calls ether_setup(), which set the mtu to 1500. Thus, the whole mtu config is done in the same function.

Before the patch: $ ip link add blue type vrf table 1234 $ ip link list blue 9: blue: <NOARP,MASTER> mtu 65536 qdisc noop state DOWN mode DEFAULT group default qlen 1000 link/ether fa:f5:27:70:24:2a brd ff:ff:ff:ff:ff:ff $ ip link set dev blue mtu 65535 $ ip link set dev blue mtu 65536 Error: mtu greater than device maximum.

Fixes: 5055376a3b44 ("net: vrf: Fix ping failed when vrf mtu is set to 0") CC: Miaohe Lin linmiaohe@huawei.com Signed-off-by: Nicolas Dichtel nicolas.dichtel@6wind.com Reviewed-by: David Ahern dsahern@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/vrf.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 503e2fd7ce51..28a6c4cfe9b8 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -1183,9 +1183,6 @@ static int vrf_dev_init(struct net_device *dev)

dev->flags = IFF_MASTER | IFF_NOARP;

- /* MTU is irrelevant for VRF device; set to 64k similar to lo */ - dev->mtu = 64 * 1024; - /* similarly, oper state is irrelevant; set to up to avoid confusion */ dev->operstate = IF_OPER_UP; netdev_lockdep_set_classes(dev); @@ -1685,7 +1682,8 @@ static void vrf_setup(struct net_device *dev) * which breaks networking. */ dev->min_mtu = IPV6_MIN_MTU; - dev->max_mtu = ETH_MAX_MTU; + dev->max_mtu = IP6_MAX_MTU; + dev->mtu = dev->max_mtu; }

static int vrf_validate(struct nlattr *tb[], struct nlattr *data[],

From: Vladimir Oltean vladimir.oltean@nxp.com

[ Upstream commit 1650bdb1c516c248fb06f6d076559ff6437a5853 ]

Because flow control is set up statically in ocelot_init_port(), and not in phylink_mac_link_up(), what happens is that after the blamed commit, the flow control remains disabled after the port flushing procedure.

Fixes: eb4733d7cffc ("net: dsa: felix: implement port flushing on .phylink_mac_link_down") Signed-off-by: Vladimir Oltean vladimir.oltean@nxp.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mscc/ocelot.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 46e5c9136bac..0c4c976548c8 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -378,6 +378,7 @@ static u32 ocelot_read_eq_avail(struct ocelot *ocelot, int port)

int ocelot_port_flush(struct ocelot *ocelot, int port) { + unsigned int pause_ena; int err, val;

/* Disable dequeuing from the egress queues */ @@ -386,6 +387,7 @@ int ocelot_port_flush(struct ocelot *ocelot, int port) QSYS_PORT_MODE, port);

/* Disable flow control */ + ocelot_fields_read(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, &pause_ena); ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, 0);

/* Disable priority flow control */ @@ -421,6 +423,9 @@ int ocelot_port_flush(struct ocelot *ocelot, int port) /* Clear flushing again. */ ocelot_rmw_gix(ocelot, 0, REW_PORT_CFG_FLUSH_ENA, REW_PORT_CFG, port);

+ /* Re-enable flow control */ + ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, pause_ena); + return err; } EXPORT_SYMBOL(ocelot_port_flush);

From: Aleksander Jan Bajkowski olek2@wp.pl

[ Upstream commit f2386cf7c5f4ff5d7b584f5d92014edd7df6c676 ]

This patch fixes TX hangs with threaded NAPI enabled. The scheduled NAPI seems to be executed in parallel with the interrupt on second thread. Sometimes it happens that ltq_dma_disable_irq() is executed after xrx200_tx_housekeeping(). The symptom is that TX interrupts are disabled in the DMA controller. As a result, the TX hangs after a few seconds of the iperf test. Scheduling NAPI after disabling interrupts fixes this issue.

Tested on Lantiq xRX200 (BT Home Hub 5A).

Fixes: 9423361da523 ("net: lantiq: Disable IRQs only if NAPI gets scheduled ") Signed-off-by: Aleksander Jan Bajkowski olek2@wp.pl Acked-by: Hauke Mehrtens hauke@hauke-m.de Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/lantiq_xrx200.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c index 135ba5b6ae98..3da494df72f3 100644 --- a/drivers/net/ethernet/lantiq_xrx200.c +++ b/drivers/net/ethernet/lantiq_xrx200.c @@ -352,8 +352,8 @@ static irqreturn_t xrx200_dma_irq(int irq, void *ptr) struct xrx200_chan *ch = ptr;

if (napi_schedule_prep(&ch->napi)) { - __napi_schedule(&ch->napi); ltq_dma_disable_irq(&ch->dma); + __napi_schedule(&ch->napi); }

ltq_dma_ack_irq(&ch->dma);

From: Florian Westphal fw@strlen.de

[ Upstream commit 12f36e9bf678a81d030ca1b693dcda62b55af7c5 ]

The ip6tables rpfilter match has an extra check to skip packets with "::" source address.

Extend this to ipv6 fib expression. Else ipv6 duplicate address detection packets will fail rpf route check -- lookup returns -ENETUNREACH.

While at it, extend the prerouting check to also cover the ingress hook.

Closes: https://bugzilla.netfilter.org/show_bug.cgi?id=1543 Fixes: f6d0cbcf09c5 ("netfilter: nf_tables: add fib expression") Signed-off-by: Florian Westphal fw@strlen.de Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv6/netfilter/nft_fib_ipv6.c | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c index e204163c7036..92f3235fa287 100644 --- a/net/ipv6/netfilter/nft_fib_ipv6.c +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -135,6 +135,17 @@ void nft_fib6_eval_type(const struct nft_expr *expr, struct nft_regs *regs, } EXPORT_SYMBOL_GPL(nft_fib6_eval_type);

+static bool nft_fib_v6_skip_icmpv6(const struct sk_buff *skb, u8 next, const struct ipv6hdr *iph) +{ + if (likely(next != IPPROTO_ICMPV6)) + return false; + + if (ipv6_addr_type(&iph->saddr) != IPV6_ADDR_ANY) + return false; + + return ipv6_addr_type(&iph->daddr) & IPV6_ADDR_LINKLOCAL; +} + void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { @@ -163,10 +174,13 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,

lookup_flags = nft_fib6_flowi_init(&fl6, priv, pkt, oif, iph);

- if (nft_hook(pkt) == NF_INET_PRE_ROUTING && - nft_fib_is_loopback(pkt->skb, nft_in(pkt))) { - nft_fib_store_result(dest, priv, nft_in(pkt)); - return; + if (nft_hook(pkt) == NF_INET_PRE_ROUTING || + nft_hook(pkt) == NF_INET_INGRESS) { + if (nft_fib_is_loopback(pkt->skb, nft_in(pkt)) || + nft_fib_v6_skip_icmpv6(pkt->skb, pkt->tprot, iph)) { + nft_fib_store_result(dest, priv, nft_in(pkt)); + return; + } }

*dest = 0;

From: Maciej Fijalkowski maciej.fijalkowski@intel.com

[ Upstream commit 2e84f6b3773f43263124c76499c0c4ec3f40aa9b ]

Commit ae15e0ba1b33 ("ice: Change number of XDP Tx queues to match number of Rx queues") tried to address the incorrect setting of XDP queue count that was based on the Tx queue count, whereas in theory we should provide the XDP queue per Rx queue. However, the routines that setup and destroy the set of Tx resources are still based on the vsi->num_txq.

Ice supports the asynchronous Tx/Rx queue count, so for a setup where vsi->num_txq > vsi->num_rxq, ice_vsi_stop_tx_rings and ice_vsi_cfg_txqs will be accessing the vsi->xdp_rings out of the bounds.

Parameterize two mentioned functions so they get the size of Tx resources array as the input.

Fixes: ae15e0ba1b33 ("ice: Change number of XDP Tx queues to match number of Rx queues") Signed-off-by: Maciej Fijalkowski maciej.fijalkowski@intel.com Tested-by: Kiran Bhandare kiranx.bhandare@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/ice/ice_lib.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 27e439853c3b..55432ea360ad 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -1715,12 +1715,13 @@ setup_rings: * ice_vsi_cfg_txqs - Configure the VSI for Tx * @vsi: the VSI being configured * @rings: Tx ring array to be configured + * @count: number of Tx ring array elements * * Return 0 on success and a negative value on error * Configure the Tx VSI for operation. */ static int -ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_ring **rings) +ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_ring **rings, u16 count) { struct ice_aqc_add_tx_qgrp *qg_buf; u16 q_idx = 0; @@ -1732,7 +1733,7 @@ ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_ring **rings)

qg_buf->num_txqs = 1;

- for (q_idx = 0; q_idx < vsi->num_txq; q_idx++) { + for (q_idx = 0; q_idx < count; q_idx++) { err = ice_vsi_cfg_txq(vsi, rings[q_idx], qg_buf); if (err) goto err_cfg_txqs; @@ -1752,7 +1753,7 @@ err_cfg_txqs: */ int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi) { - return ice_vsi_cfg_txqs(vsi, vsi->tx_rings); + return ice_vsi_cfg_txqs(vsi, vsi->tx_rings, vsi->num_txq); }

/** @@ -1767,7 +1768,7 @@ int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi) int ret; int i;

- ret = ice_vsi_cfg_txqs(vsi, vsi->xdp_rings); + ret = ice_vsi_cfg_txqs(vsi, vsi->xdp_rings, vsi->num_xdp_txq); if (ret) return ret;

@@ -1965,17 +1966,18 @@ int ice_vsi_stop_all_rx_rings(struct ice_vsi *vsi) * @rst_src: reset source * @rel_vmvf_num: Relative ID of VF/VM * @rings: Tx ring array to be stopped + * @count: number of Tx ring array elements */ static int ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, - u16 rel_vmvf_num, struct ice_ring **rings) + u16 rel_vmvf_num, struct ice_ring **rings, u16 count) { u16 q_idx;

if (vsi->num_txq > ICE_LAN_TXQ_MAX_QDIS) return -EINVAL;

- for (q_idx = 0; q_idx < vsi->num_txq; q_idx++) { + for (q_idx = 0; q_idx < count; q_idx++) { struct ice_txq_meta txq_meta = { }; int status;

@@ -2003,7 +2005,7 @@ int ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, u16 rel_vmvf_num) { - return ice_vsi_stop_tx_rings(vsi, rst_src, rel_vmvf_num, vsi->tx_rings); + return ice_vsi_stop_tx_rings(vsi, rst_src, rel_vmvf_num, vsi->tx_rings, vsi->num_txq); }

/** @@ -2012,7 +2014,7 @@ ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, */ int ice_vsi_stop_xdp_tx_rings(struct ice_vsi *vsi) { - return ice_vsi_stop_tx_rings(vsi, ICE_NO_RESET, 0, vsi->xdp_rings); + return ice_vsi_stop_tx_rings(vsi, ICE_NO_RESET, 0, vsi->xdp_rings, vsi->num_xdp_txq); }

/**

From: Ido Schimmel idosch@nvidia.com

[ Upstream commit d2e381c4963663bca6f30c3b996fa4dbafe8fcb5 ]

Cited commit started returning errors when notification info is not filled by the bridge driver, resulting in the following regression:

# ip link add name br1 type bridge vlan_filtering 1 # bridge vlan add dev br1 vid 555 self pvid untagged RTNETLINK answers: Invalid argument

As long as the bridge driver does not fill notification info for the bridge device itself, an empty notification should not be considered as an error. This is explained in commit 59ccaaaa49b5 ("bridge: dont send notification when skb->len == 0 in rtnl_bridge_notify").

Fix by removing the error and add a comment to avoid future bugs.

Fixes: a8db57c1d285 ("rtnetlink: Fix missing error code in rtnl_bridge_notify()") Signed-off-by: Ido Schimmel idosch@nvidia.com Reviewed-by: Nikolay Aleksandrov nikolay@nvidia.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/core/rtnetlink.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 9ad046917b34..2123427883ba 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -4833,10 +4833,12 @@ static int rtnl_bridge_notify(struct net_device *dev) if (err < 0) goto errout;

- if (!skb->len) { - err = -EINVAL; + /* Notification info is only filled for bridge ports, not the bridge + * device itself. Therefore, a zero notification length is valid and + * should not result in an error. + */ + if (!skb->len) goto errout; - }

rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); return 0;

From: Vlad Buslov vladbu@nvidia.com

[ Upstream commit fb1a3132ee1ac968316e45d21a48703a6db0b6c3 ]

Function mlx5e_rep_neigh_update() wasn't updated to accommodate rtnl lock removal from TC filter update path and properly handle concurrent encap entry insertion/deletion which can lead to following use-after-free:

[23827.464923] ================================================================== [23827.469446] BUG: KASAN: use-after-free in mlx5e_encap_take+0x72/0x140 [mlx5_core] [23827.470971] Read of size 4 at addr ffff8881d132228c by task kworker/u20:6/21635 [23827.472251] [23827.472615] CPU: 9 PID: 21635 Comm: kworker/u20:6 Not tainted 5.13.0-rc3+ #5 [23827.473788] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 [23827.475639] Workqueue: mlx5e mlx5e_rep_neigh_update [mlx5_core] [23827.476731] Call Trace: [23827.477260] dump_stack+0xbb/0x107 [23827.477906] print_address_description.constprop.0+0x18/0x140 [23827.478896] ? mlx5e_encap_take+0x72/0x140 [mlx5_core] [23827.479879] ? mlx5e_encap_take+0x72/0x140 [mlx5_core] [23827.480905] kasan_report.cold+0x7c/0xd8 [23827.481701] ? mlx5e_encap_take+0x72/0x140 [mlx5_core] [23827.482744] kasan_check_range+0x145/0x1a0 [23827.493112] mlx5e_encap_take+0x72/0x140 [mlx5_core] [23827.494054] ? mlx5e_tc_tun_encap_info_equal_generic+0x140/0x140 [mlx5_core] [23827.495296] mlx5e_rep_neigh_update+0x41e/0x5e0 [mlx5_core] [23827.496338] ? mlx5e_rep_neigh_entry_release+0xb80/0xb80 [mlx5_core] [23827.497486] ? read_word_at_a_time+0xe/0x20 [23827.498250] ? strscpy+0xa0/0x2a0 [23827.498889] process_one_work+0x8ac/0x14e0 [23827.499638] ? lockdep_hardirqs_on_prepare+0x400/0x400 [23827.500537] ? pwq_dec_nr_in_flight+0x2c0/0x2c0 [23827.501359] ? rwlock_bug.part.0+0x90/0x90 [23827.502116] worker_thread+0x53b/0x1220 [23827.502831] ? process_one_work+0x14e0/0x14e0 [23827.503627] kthread+0x328/0x3f0 [23827.504254] ? _raw_spin_unlock_irq+0x24/0x40 [23827.505065] ? __kthread_bind_mask+0x90/0x90 [23827.505912] ret_from_fork+0x1f/0x30 [23827.506621] [23827.506987] Allocated by task 28248: [23827.507694] kasan_save_stack+0x1b/0x40 [23827.508476] __kasan_kmalloc+0x7c/0x90 [23827.509197] mlx5e_attach_encap+0xde1/0x1d40 [mlx5_core] [23827.510194] mlx5e_tc_add_fdb_flow+0x397/0xc40 [mlx5_core] [23827.511218] __mlx5e_add_fdb_flow+0x519/0xb30 [mlx5_core] [23827.512234] mlx5e_configure_flower+0x191c/0x4870 [mlx5_core] [23827.513298] tc_setup_cb_add+0x1d5/0x420 [23827.514023] fl_hw_replace_filter+0x382/0x6a0 [cls_flower] [23827.514975] fl_change+0x2ceb/0x4a51 [cls_flower] [23827.515821] tc_new_tfilter+0x89a/0x2070 [23827.516548] rtnetlink_rcv_msg+0x644/0x8c0 [23827.517300] netlink_rcv_skb+0x11d/0x340 [23827.518021] netlink_unicast+0x42b/0x700 [23827.518742] netlink_sendmsg+0x743/0xc20 [23827.519467] sock_sendmsg+0xb2/0xe0 [23827.520131] ____sys_sendmsg+0x590/0x770 [23827.520851] ___sys_sendmsg+0xd8/0x160 [23827.521552] __sys_sendmsg+0xb7/0x140 [23827.522238] do_syscall_64+0x3a/0x70 [23827.522907] entry_SYSCALL_64_after_hwframe+0x44/0xae [23827.523797] [23827.524163] Freed by task 25948: [23827.524780] kasan_save_stack+0x1b/0x40 [23827.525488] kasan_set_track+0x1c/0x30 [23827.526187] kasan_set_free_info+0x20/0x30 [23827.526968] __kasan_slab_free+0xed/0x130 [23827.527709] slab_free_freelist_hook+0xcf/0x1d0 [23827.528528] kmem_cache_free_bulk+0x33a/0x6e0 [23827.529317] kfree_rcu_work+0x55f/0xb70 [23827.530024] process_one_work+0x8ac/0x14e0 [23827.530770] worker_thread+0x53b/0x1220 [23827.531480] kthread+0x328/0x3f0 [23827.532114] ret_from_fork+0x1f/0x30 [23827.532785] [23827.533147] Last potentially related work creation: [23827.534007] kasan_save_stack+0x1b/0x40 [23827.534710] kasan_record_aux_stack+0xab/0xc0 [23827.535492] kvfree_call_rcu+0x31/0x7b0 [23827.536206] mlx5e_tc_del_fdb_flow+0x577/0xef0 [mlx5_core] [23827.537305] mlx5e_flow_put+0x49/0x80 [mlx5_core] [23827.538290] mlx5e_delete_flower+0x6d1/0xe60 [mlx5_core] [23827.539300] tc_setup_cb_destroy+0x18e/0x2f0 [23827.540144] fl_hw_destroy_filter+0x1d2/0x310 [cls_flower] [23827.541148] __fl_delete+0x4dc/0x660 [cls_flower] [23827.541985] fl_delete+0x97/0x160 [cls_flower] [23827.542782] tc_del_tfilter+0x7ab/0x13d0 [23827.543503] rtnetlink_rcv_msg+0x644/0x8c0 [23827.544257] netlink_rcv_skb+0x11d/0x340 [23827.544981] netlink_unicast+0x42b/0x700 [23827.545700] netlink_sendmsg+0x743/0xc20 [23827.546424] sock_sendmsg+0xb2/0xe0 [23827.547084] ____sys_sendmsg+0x590/0x770 [23827.547850] ___sys_sendmsg+0xd8/0x160 [23827.548606] __sys_sendmsg+0xb7/0x140 [23827.549303] do_syscall_64+0x3a/0x70 [23827.549969] entry_SYSCALL_64_after_hwframe+0x44/0xae [23827.550853] [23827.551217] The buggy address belongs to the object at ffff8881d1322200 [23827.551217] which belongs to the cache kmalloc-256 of size 256 [23827.553341] The buggy address is located 140 bytes inside of [23827.553341] 256-byte region [ffff8881d1322200, ffff8881d1322300) [23827.555747] The buggy address belongs to the page: [23827.556847] page:00000000898762aa refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x1d1320 [23827.558651] head:00000000898762aa order:2 compound_mapcount:0 compound_pincount:0 [23827.559961] flags: 0x2ffff800010200(slab|head|node=0|zone=2|lastcpupid=0x1ffff) [23827.561243] raw: 002ffff800010200 dead000000000100 dead000000000122 ffff888100042b40 [23827.562653] raw: 0000000000000000 0000000000200020 00000001ffffffff 0000000000000000 [23827.564112] page dumped because: kasan: bad access detected [23827.565439] [23827.565932] Memory state around the buggy address: [23827.566917] ffff8881d1322180: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [23827.568485] ffff8881d1322200: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [23827.569818] >ffff8881d1322280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [23827.571143] ^ [23827.571879] ffff8881d1322300: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [23827.573283] ffff8881d1322380: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [23827.574654] ==================================================================

Most of the necessary logic is already correctly implemented by mlx5e_get_next_valid_encap() helper that is used in neigh stats update handler. Make the handler generic by renaming it to mlx5e_get_next_matching_encap() and use callback to test whether flow is matching instead of hardcoded check for 'valid' flag value. Implement mlx5e_get_next_valid_encap() by calling mlx5e_get_next_matching_encap() with callback that tests encap MLX5_ENCAP_ENTRY_VALID flag. Implement new mlx5e_get_next_init_encap() helper by calling mlx5e_get_next_matching_encap() with callback that tests encap completion result to be non-error and use it in mlx5e_rep_neigh_update() to safely iterate over nhe->encap_list.

Remove encap completion logic from mlx5e_rep_update_flows() since the encap entries passed to this function are already guaranteed to be properly initialized by similar code in mlx5e_get_next_init_encap().

Fixes: 2a1f1768fa17 ("net/mlx5e: Refactor neigh update for concurrent execution") Signed-off-by: Vlad Buslov vladbu@nvidia.com Reviewed-by: Roi Dayan roid@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../mellanox/mlx5/core/en/rep/neigh.c | 15 ++++----- .../ethernet/mellanox/mlx5/core/en/rep/tc.c | 6 +--- .../mellanox/mlx5/core/en/tc_tun_encap.c | 33 +++++++++++++++++-- .../net/ethernet/mellanox/mlx5/core/en_tc.h | 3 ++ 4 files changed, 40 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c index be0ee03de721..2e9bee4e5209 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c @@ -129,10 +129,9 @@ static void mlx5e_rep_neigh_update(struct work_struct *work) work); struct mlx5e_neigh_hash_entry *nhe = update_work->nhe; struct neighbour *n = update_work->n; + struct mlx5e_encap_entry *e = NULL; bool neigh_connected, same_dev; - struct mlx5e_encap_entry *e; unsigned char ha[ETH_ALEN]; - struct mlx5e_priv *priv; u8 nud_state, dead;

rtnl_lock(); @@ -156,14 +155,12 @@ static void mlx5e_rep_neigh_update(struct work_struct *work) if (!same_dev) goto out;

- list_for_each_entry(e, &nhe->encap_list, encap_list) { - if (!mlx5e_encap_take(e)) - continue; + /* mlx5e_get_next_init_encap() releases previous encap before returning + * the next one. + */ + while ((e = mlx5e_get_next_init_encap(nhe, e)) != NULL) + mlx5e_rep_update_flows(netdev_priv(e->out_dev), e, neigh_connected, ha);

- priv = netdev_priv(e->out_dev); - mlx5e_rep_update_flows(priv, e, neigh_connected, ha); - mlx5e_encap_put(priv, e); - } out: rtnl_unlock(); mlx5e_release_neigh_update_work(update_work); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c index 96ba027dbef3..9992f94f794b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c @@ -93,13 +93,9 @@ void mlx5e_rep_update_flows(struct mlx5e_priv *priv,

ASSERT_RTNL();

- /* wait for encap to be fully initialized */ - wait_for_completion(&e->res_ready); - mutex_lock(&esw->offloads.encap_tbl_lock); encap_connected = !!(e->flags & MLX5_ENCAP_ENTRY_VALID); - if (e->compl_result < 0 || (encap_connected == neigh_connected && - ether_addr_equal(e->h_dest, ha))) + if (encap_connected == neigh_connected && ether_addr_equal(e->h_dest, ha)) goto unlock;

mlx5e_take_all_encap_flows(e, &flow_list); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index 1560fcbf4ac7..a17d79effa27 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -250,9 +250,12 @@ static void mlx5e_take_all_route_decap_flows(struct mlx5e_route_entry *r, mlx5e_take_tmp_flow(flow, flow_list, 0); }

+typedef bool (match_cb)(struct mlx5e_encap_entry *); + static struct mlx5e_encap_entry * -mlx5e_get_next_valid_encap(struct mlx5e_neigh_hash_entry *nhe, - struct mlx5e_encap_entry *e) +mlx5e_get_next_matching_encap(struct mlx5e_neigh_hash_entry *nhe, + struct mlx5e_encap_entry *e, + match_cb match) { struct mlx5e_encap_entry *next = NULL;

@@ -287,7 +290,7 @@ retry: /* wait for encap to be fully initialized */ wait_for_completion(&next->res_ready); /* continue searching if encap entry is not in valid state after completion */ - if (!(next->flags & MLX5_ENCAP_ENTRY_VALID)) { + if (!match(next)) { e = next; goto retry; } @@ -295,6 +298,30 @@ retry: return next; }

+static bool mlx5e_encap_valid(struct mlx5e_encap_entry *e) +{ + return e->flags & MLX5_ENCAP_ENTRY_VALID; +} + +static struct mlx5e_encap_entry * +mlx5e_get_next_valid_encap(struct mlx5e_neigh_hash_entry *nhe, + struct mlx5e_encap_entry *e) +{ + return mlx5e_get_next_matching_encap(nhe, e, mlx5e_encap_valid); +} + +static bool mlx5e_encap_initialized(struct mlx5e_encap_entry *e) +{ + return e->compl_result >= 0; +} + +struct mlx5e_encap_entry * +mlx5e_get_next_init_encap(struct mlx5e_neigh_hash_entry *nhe, + struct mlx5e_encap_entry *e) +{ + return mlx5e_get_next_matching_encap(nhe, e, mlx5e_encap_initialized); +} + void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe) { struct mlx5e_neigh *m_neigh = &nhe->m_neigh; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index 25c091795bcd..17027536efba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -178,6 +178,9 @@ void mlx5e_take_all_encap_flows(struct mlx5e_encap_entry *e, struct list_head *f void mlx5e_put_flow_list(struct mlx5e_priv *priv, struct list_head *flow_list);

struct mlx5e_neigh_hash_entry; +struct mlx5e_encap_entry * +mlx5e_get_next_init_encap(struct mlx5e_neigh_hash_entry *nhe, + struct mlx5e_encap_entry *e); void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe);

void mlx5e_tc_reoffload_flows_work(struct work_struct *work);

From: Dima Chumak dchumak@nvidia.com

[ Upstream commit a3e5fd9314dfc4314a9567cde96e1aef83a7458a ]

When adding a hairpin flow, a firmware-side send queue is created for the peer net device, which claims some host memory pages for its internal ring buffer. If the peer net device is removed/unbound before the hairpin flow is deleted, then the send queue is not destroyed which leads to a stack trace on pci device remove:

[ 748.005230] mlx5_core 0000:08:00.2: wait_func:1094:(pid 12985): MANAGE_PAGES(0x108) timeout. Will cause a leak of a command resource [ 748.005231] mlx5_core 0000:08:00.2: reclaim_pages:514:(pid 12985): failed reclaiming pages: err -110 [ 748.001835] mlx5_core 0000:08:00.2: mlx5_reclaim_root_pages:653:(pid 12985): failed reclaiming pages (-110) for func id 0x0 [ 748.002171] ------------[ cut here ]------------ [ 748.001177] FW pages counter is 4 after reclaiming all pages [ 748.001186] WARNING: CPU: 1 PID: 12985 at drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c:685 mlx5_reclaim_startup_pages+0x34b/0x460 [mlx5_core] [ +0.002771] Modules linked in: cls_flower mlx5_ib mlx5_core ptp pps_core act_mirred sch_ingress openvswitch nsh xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink xt_addrtype iptable_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 br_netfilter rpcrdma rdma_ucm ib_iser libiscsi scsi_transport_iscsi rdma_cm ib_umad ib_ipoib iw_cm ib_cm ib_uverbs ib_core overlay fuse [last unloaded: pps_core] [ 748.007225] CPU: 1 PID: 12985 Comm: tee Not tainted 5.12.0+ #1 [ 748.001376] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 [ 748.002315] RIP: 0010:mlx5_reclaim_startup_pages+0x34b/0x460 [mlx5_core] [ 748.001679] Code: 28 00 00 00 0f 85 22 01 00 00 48 81 c4 b0 00 00 00 31 c0 5b 5d 41 5c 41 5d 41 5e 41 5f c3 48 c7 c7 40 cc 19 a1 e8 9f 71 0e e2 <0f> 0b e9 30 ff ff ff 48 c7 c7 a0 cc 19 a1 e8 8c 71 0e e2 0f 0b e9 [ 748.003781] RSP: 0018:ffff88815220faf8 EFLAGS: 00010286 [ 748.001149] RAX: 0000000000000000 RBX: ffff8881b4900280 RCX: 0000000000000000 [ 748.001445] RDX: 0000000000000027 RSI: 0000000000000004 RDI: ffffed102a441f51 [ 748.001614] RBP: 00000000000032b9 R08: 0000000000000001 R09: ffffed1054a15ee8 [ 748.001446] R10: ffff8882a50af73b R11: ffffed1054a15ee7 R12: fffffbfff07c1e30 [ 748.001447] R13: dffffc0000000000 R14: ffff8881b492cba8 R15: 0000000000000000 [ 748.001429] FS: 00007f58bd08b580(0000) GS:ffff8882a5080000(0000) knlGS:0000000000000000 [ 748.001695] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 748.001309] CR2: 000055a026351740 CR3: 00000001d3b48006 CR4: 0000000000370ea0 [ 748.001506] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 748.001483] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 748.001654] Call Trace: [ 748.000576] ? mlx5_satisfy_startup_pages+0x290/0x290 [mlx5_core] [ 748.001416] ? mlx5_cmd_teardown_hca+0xa2/0xd0 [mlx5_core] [ 748.001354] ? mlx5_cmd_init_hca+0x280/0x280 [mlx5_core] [ 748.001203] mlx5_function_teardown+0x30/0x60 [mlx5_core] [ 748.001275] mlx5_uninit_one+0xa7/0xc0 [mlx5_core] [ 748.001200] remove_one+0x5f/0xc0 [mlx5_core] [ 748.001075] pci_device_remove+0x9f/0x1d0 [ 748.000833] device_release_driver_internal+0x1e0/0x490 [ 748.001207] unbind_store+0x19f/0x200 [ 748.000942] ? sysfs_file_ops+0x170/0x170 [ 748.001000] kernfs_fop_write_iter+0x2bc/0x450 [ 748.000970] new_sync_write+0x373/0x610 [ 748.001124] ? new_sync_read+0x600/0x600 [ 748.001057] ? lock_acquire+0x4d6/0x700 [ 748.000908] ? lockdep_hardirqs_on_prepare+0x400/0x400 [ 748.001126] ? fd_install+0x1c9/0x4d0 [ 748.000951] vfs_write+0x4d0/0x800 [ 748.000804] ksys_write+0xf9/0x1d0 [ 748.000868] ? __x64_sys_read+0xb0/0xb0 [ 748.000811] ? filp_open+0x50/0x50 [ 748.000919] ? syscall_enter_from_user_mode+0x1d/0x50 [ 748.001223] do_syscall_64+0x3f/0x80 [ 748.000892] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 748.001026] RIP: 0033:0x7f58bcfb22f7 [ 748.000944] Code: 0d 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 48 89 54 24 18 48 89 74 24 [ 748.003925] RSP: 002b:00007fffd7f2aaa8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 748.001732] RAX: ffffffffffffffda RBX: 000000000000000d RCX: 00007f58bcfb22f7 [ 748.001426] RDX: 000000000000000d RSI: 00007fffd7f2abc0 RDI: 0000000000000003 [ 748.001746] RBP: 00007fffd7f2abc0 R08: 0000000000000000 R09: 0000000000000001 [ 748.001631] R10: 00000000000001b6 R11: 0000000000000246 R12: 000000000000000d [ 748.001537] R13: 00005597ac2c24a0 R14: 000000000000000d R15: 00007f58bd084700 [ 748.001564] irq event stamp: 0 [ 748.000787] hardirqs last enabled at (0): [<0000000000000000>] 0x0 [ 748.001399] hardirqs last disabled at (0): [<ffffffff813132cf>] copy_process+0x146f/0x5eb0 [ 748.001854] softirqs last enabled at (0): [<ffffffff8131330e>] copy_process+0x14ae/0x5eb0 [ 748.013431] softirqs last disabled at (0): [<0000000000000000>] 0x0 [ 748.001492] ---[ end trace a6fabd773d1c51ae ]---

Fix by destroying the send queue of a hairpin peer net device that is being removed/unbound, which returns the allocated ring buffer pages to the host.

Fixes: 4d8fcf216c90 ("net/mlx5e: Avoid unbounded peer devices when unpairing TC hairpin rules") Signed-off-by: Dima Chumak dchumak@nvidia.com Reviewed-by: Roi Dayan roid@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../net/ethernet/mellanox/mlx5/core/en_tc.c | 2 +- .../ethernet/mellanox/mlx5/core/transobj.c | 30 +++++++++++++++---- include/linux/mlx5/transobj.h | 1 + 3 files changed, 26 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index b633f669ea57..b3b8e44540a5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -4622,7 +4622,7 @@ static void mlx5e_tc_hairpin_update_dead_peer(struct mlx5e_priv *priv, list_for_each_entry_safe(hpe, tmp, &init_wait_list, dead_peer_wait_list) { wait_for_completion(&hpe->res_ready); if (!IS_ERR_OR_NULL(hpe->hp) && hpe->peer_vhca_id == peer_vhca_id) - hpe->hp->pair->peer_gone = true; + mlx5_core_hairpin_clear_dead_peer(hpe->hp->pair);

mlx5e_hairpin_put(priv, hpe); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c index 01cc00ad8acf..b6931bbe52d2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c @@ -424,6 +424,15 @@ err_modify_sq: return err; }

+static void mlx5_hairpin_unpair_peer_sq(struct mlx5_hairpin *hp) +{ + int i; + + for (i = 0; i < hp->num_channels; i++) + mlx5_hairpin_modify_sq(hp->peer_mdev, hp->sqn[i], MLX5_SQC_STATE_RDY, + MLX5_SQC_STATE_RST, 0, 0); +} + static void mlx5_hairpin_unpair_queues(struct mlx5_hairpin *hp) { int i; @@ -432,13 +441,9 @@ static void mlx5_hairpin_unpair_queues(struct mlx5_hairpin *hp) for (i = 0; i < hp->num_channels; i++) mlx5_hairpin_modify_rq(hp->func_mdev, hp->rqn[i], MLX5_RQC_STATE_RDY, MLX5_RQC_STATE_RST, 0, 0); - /* unset peer SQs */ - if (hp->peer_gone) - return; - for (i = 0; i < hp->num_channels; i++) - mlx5_hairpin_modify_sq(hp->peer_mdev, hp->sqn[i], MLX5_SQC_STATE_RDY, - MLX5_SQC_STATE_RST, 0, 0); + if (!hp->peer_gone) + mlx5_hairpin_unpair_peer_sq(hp); }

struct mlx5_hairpin * @@ -485,3 +490,16 @@ void mlx5_core_hairpin_destroy(struct mlx5_hairpin *hp) mlx5_hairpin_destroy_queues(hp); kfree(hp); } + +void mlx5_core_hairpin_clear_dead_peer(struct mlx5_hairpin *hp) +{ + int i; + + mlx5_hairpin_unpair_peer_sq(hp); + + /* destroy peer SQ */ + for (i = 0; i < hp->num_channels; i++) + mlx5_core_destroy_sq(hp->peer_mdev, hp->sqn[i]); + + hp->peer_gone = true; +} diff --git a/include/linux/mlx5/transobj.h b/include/linux/mlx5/transobj.h index 028f442530cf..60ffeb6b67ae 100644 --- a/include/linux/mlx5/transobj.h +++ b/include/linux/mlx5/transobj.h @@ -85,4 +85,5 @@ mlx5_core_hairpin_create(struct mlx5_core_dev *func_mdev, struct mlx5_hairpin_params *params);

void mlx5_core_hairpin_destroy(struct mlx5_hairpin *pair); +void mlx5_core_hairpin_clear_dead_peer(struct mlx5_hairpin *hp); #endif /* __TRANSOBJ_H__ */

From: Maor Gottlieb maorg@nvidia.com

[ Upstream commit 4aaf96ac8b45d8e2e019b6b53cce65a73c4ace2c ]

SW steering uses RC QP to write/read to/from ICM, hence it's not supported when RoCE is not supported as well.

Fixes: 70605ea545e8 ("net/mlx5: DR, Expose APIs for direct rule managing") Signed-off-by: Maor Gottlieb maorg@nvidia.com Reviewed-by: Alex Vesker valex@nvidia.com Reviewed-by: Yevgeny Kliteynik kliteyn@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h index 612b0ac31db2..9737565cd8d4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h @@ -124,10 +124,11 @@ int mlx5dr_action_destroy(struct mlx5dr_action *action); static inline bool mlx5dr_is_supported(struct mlx5_core_dev *dev) { - return MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner) || - (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner_v2) && - (MLX5_CAP_GEN(dev, steering_format_version) <= - MLX5_STEERING_FORMAT_CONNECTX_6DX)); + return MLX5_CAP_GEN(dev, roce) && + (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner) || + (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner_v2) && + (MLX5_CAP_GEN(dev, steering_format_version) <= + MLX5_STEERING_FORMAT_CONNECTX_6DX))); }

/* buddy functions & structure */

From: Aya Levin ayal@nvidia.com

[ Upstream commit 6d6727dddc7f93fcc155cb8d0c49c29ae0e71122 ]

The device is able to offload either the outer header csum or inner header csum. The driver utilizes the inner csum offload. Hence, block setting of tx-udp_tnl-csum-segmentation and set it to off[fixed].

Fixes: b49663c8fb49 ("net/mlx5e: Add support for UDP tunnel segmentation with outer checksum offload") Signed-off-by: Aya Levin ayal@nvidia.com Reviewed-by: Tariq Toukan tariqt@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 99dc9f2beed5..2a3da167f248 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -5168,13 +5168,9 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) }

if (mlx5_vxlan_allowed(mdev->vxlan) || mlx5_geneve_tx_allowed(mdev)) { - netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM; - netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM; - netdev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM; - netdev->vlan_features |= NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM; + netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL; + netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL; + netdev->vlan_features |= NETIF_F_GSO_UDP_TUNNEL; }

if (mlx5e_tunnel_proto_supported_tx(mdev, IPPROTO_GRE)) {

From: Willem de Bruijn willemb@google.com

[ Upstream commit 3bdd5ee0ec8c14131d560da492e6df452c6fdd75 ]

msg_zerocopy signals if a send operation required copying with a flag in serr->ee.ee_code.

This field can be incorrect as of the below commit, as a result of both structs uarg and serr pointing into the same skb->cb[].

uarg->zerocopy must be read before skb->cb[] is reinitialized to hold serr. Similar to other fields len, hi and lo, use a local variable to temporarily hold the value.

This was not a problem before, when the value was passed as a function argument.

Fixes: 75518851a2a0 ("skbuff: Push status and refcounts into sock_zerocopy_callback") Reported-by: Talal Ahmad talalahmad@google.com Signed-off-by: Willem de Bruijn willemb@google.com Acked-by: Soheil Hassas Yeganeh soheil@google.com Reviewed-by: Eric Dumazet edumazet@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/core/skbuff.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c index c421c8f80925..7997d99afbd8 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1252,6 +1252,7 @@ static void __msg_zerocopy_callback(struct ubuf_info *uarg) struct sock *sk = skb->sk; struct sk_buff_head *q; unsigned long flags; + bool is_zerocopy; u32 lo, hi; u16 len;

@@ -1266,6 +1267,7 @@ static void __msg_zerocopy_callback(struct ubuf_info *uarg) len = uarg->len; lo = uarg->id; hi = uarg->id + len - 1; + is_zerocopy = uarg->zerocopy;

serr = SKB_EXT_ERR(skb); memset(serr, 0, sizeof(*serr)); @@ -1273,7 +1275,7 @@ static void __msg_zerocopy_callback(struct ubuf_info *uarg) serr->ee.ee_origin = SO_EE_ORIGIN_ZEROCOPY; serr->ee.ee_data = hi; serr->ee.ee_info = lo; - if (!uarg->zerocopy) + if (!is_zerocopy) serr->ee.ee_code |= SO_EE_CODE_ZEROCOPY_COPIED;

q = &sk->sk_error_queue;

From: Maxim Mikityanskiy maximmi@nvidia.com

[ Upstream commit 07718be265680dcf496347d475ce1a5442f55ad7 ]

The TCP option parser in mptcp (mptcp_get_options) could read one byte out of bounds. When the length is 1, the execution flow gets into the loop, reads one byte of the opcode, and if the opcode is neither TCPOPT_EOL nor TCPOPT_NOP, it reads one more byte, which exceeds the length of 1.

This fix is inspired by commit 9609dad263f8 ("ipv4: tcp_input: fix stack out of bounds when parsing TCP options.").

Cc: Young Xiao 92siuyang@gmail.com Fixes: cec37a6e41aa ("mptcp: Handle MP_CAPABLE options for outgoing connections") Signed-off-by: Maxim Mikityanskiy maximmi@nvidia.com Reviewed-by: Mat Martineau mathew.j.martineau@linux.intel.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/mptcp/options.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 8848a9e2a95b..47d90cf31f12 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -337,6 +337,8 @@ void mptcp_get_options(const struct sk_buff *skb, length--; continue; default: + if (length < 2) + return; opsize = *ptr++; if (opsize < 2) /* "silly options" */ return;

From: Paolo Abeni pabeni@redhat.com

[ Upstream commit 72f961320d5d15bfcb26dbe3edaa3f7d25fd2c8a ]

If the host is under sever memory pressure, and RX forward memory allocation for the msk fails, we try to borrow the required memory from the ingress subflow.

The current attempt is a bit flaky: if skb->truesize is less than SK_MEM_QUANTUM, the ssk will not release any memory, and the next schedule will fail again.

Instead, directly move the required amount of pages from the ssk to the msk, if available

Fixes: 9c3f94e1681b ("mptcp: add missing memory scheduling in the rx path") Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Mat Martineau mathew.j.martineau@linux.intel.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/mptcp/protocol.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 225b98821517..1d981babbcfe 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -287,11 +287,13 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,

/* try to fetch required memory from subflow */ if (!sk_rmem_schedule(sk, skb, skb->truesize)) { - if (ssk->sk_forward_alloc < skb->truesize) - goto drop; - __sk_mem_reclaim(ssk, skb->truesize); - if (!sk_rmem_schedule(sk, skb, skb->truesize)) + int amount = sk_mem_pages(skb->truesize) << SK_MEM_QUANTUM_SHIFT; + + if (ssk->sk_forward_alloc < amount) goto drop; + + ssk->sk_forward_alloc -= amount; + sk->sk_forward_alloc += amount; }

/* the skb map_seq accounts for the skb offset:

From: Paolo Abeni pabeni@redhat.com

[ Upstream commit 61e710227e97172355d5f150d5c78c64175d9fb2 ]

warn_bad_map() produces a kernel WARN on bad input coming from the network. Use pr_debug() to avoid spamming the system log.

Additionally, when the right bound check fails, warn_bad_map() reports the wrong ssn value, let's fix it.

Fixes: 648ef4b88673 ("mptcp: Implement MPTCP receive path") Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/107 Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Mat Martineau mathew.j.martineau@linux.intel.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/mptcp/subflow.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 1ee4d106ce1c..98a5a68ec15d 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -754,10 +754,10 @@ static u64 expand_seq(u64 old_seq, u16 old_data_len, u64 seq) return seq | ((old_seq + old_data_len + 1) & GENMASK_ULL(63, 32)); }

-static void warn_bad_map(struct mptcp_subflow_context *subflow, u32 ssn) +static void dbg_bad_map(struct mptcp_subflow_context *subflow, u32 ssn) { - WARN_ONCE(1, "Bad mapping: ssn=%d map_seq=%d map_data_len=%d", - ssn, subflow->map_subflow_seq, subflow->map_data_len); + pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d", + ssn, subflow->map_subflow_seq, subflow->map_data_len); }

static bool skb_is_fully_mapped(struct sock *ssk, struct sk_buff *skb) @@ -782,13 +782,13 @@ static bool validate_mapping(struct sock *ssk, struct sk_buff *skb) /* Mapping covers data later in the subflow stream, * currently unsupported. */ - warn_bad_map(subflow, ssn); + dbg_bad_map(subflow, ssn); return false; } if (unlikely(!before(ssn, subflow->map_subflow_seq + subflow->map_data_len))) { /* Mapping does covers past subflow data, invalid */ - warn_bad_map(subflow, ssn + skb->len); + dbg_bad_map(subflow, ssn); return false; } return true;

From: Paolo Abeni pabeni@redhat.com

[ Upstream commit 499ada5073361c631f2a3c4a8aed44d53b6f82ec ]

Maxim reported a soft lookup in subflow_error_report():

watchdog: BUG: soft lockup - CPU#0 stuck for 22s! [swapper/0:0] RIP: 0010:native_queued_spin_lock_slowpath RSP: 0018:ffffa859c0003bc0 EFLAGS: 00000202 RAX: 0000000000000101 RBX: 0000000000000001 RCX: 0000000000000000 RDX: ffff9195c2772d88 RSI: 0000000000000000 RDI: ffff9195c2772d88 RBP: ffff9195c2772d00 R08: 00000000000067b0 R09: c6e31da9eb1e44f4 R10: ffff9195ef379700 R11: ffff9195edb50710 R12: ffff9195c2772d88 R13: ffff9195f500e3d0 R14: ffff9195ef379700 R15: ffff9195ef379700 FS: 0000000000000000(0000) GS:ffff91961f400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000c000407000 CR3: 0000000002988000 CR4: 00000000000006f0 Call Trace: <IRQ> _raw_spin_lock_bh subflow_error_report mptcp_subflow_data_available __mptcp_move_skbs_from_subflow mptcp_data_ready tcp_data_queue tcp_rcv_established tcp_v4_do_rcv tcp_v4_rcv ip_protocol_deliver_rcu ip_local_deliver_finish __netif_receive_skb_one_core netif_receive_skb rtl8139_poll 8139too __napi_poll net_rx_action __do_softirq __irq_exit_rcu common_interrupt </IRQ>

The calling function - mptcp_subflow_data_available() - can be invoked from different contexts: - plain ssk socket lock - ssk socket lock + mptcp_data_lock - ssk socket lock + mptcp_data_lock + msk socket lock.

Since subflow_error_report() tries to acquire the mptcp_data_lock, the latter two call chains will cause soft lookup.

This change addresses the issue moving the error reporting call to outer functions, where the held locks list is known and the we can acquire only the needed one.

Reported-by: Maxim Galaganov max@internet.ru Fixes: 15cc10453398 ("mptcp: deliver ssk errors to msk") Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/199 Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Mat Martineau mathew.j.martineau@linux.intel.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/mptcp/protocol.c | 9 ++++++ net/mptcp/subflow.c | 75 +++++++++++++++++++++++--------------------- 2 files changed, 48 insertions(+), 36 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 78152b0820ce..d8187ac06539 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -699,6 +699,12 @@ static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk)

__mptcp_move_skbs_from_subflow(msk, ssk, &moved); __mptcp_ofo_queue(msk); + if (unlikely(ssk->sk_err)) { + if (!sock_owned_by_user(sk)) + __mptcp_error_report(sk); + else + set_bit(MPTCP_ERROR_REPORT, &msk->flags); + }

/* If the moves have caught up with the DATA_FIN sequence number * it's time to ack the DATA_FIN and change socket state, but @@ -1932,6 +1938,9 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk) done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved); mptcp_data_unlock(sk); tcp_cleanup_rbuf(ssk, moved); + + if (unlikely(ssk->sk_err)) + __mptcp_error_report(sk); unlock_sock_fast(ssk, slowpath); } while (!done);

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 98a5a68ec15d..d6d8ad4f918e 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1033,7 +1033,6 @@ fallback: * subflow_error_report() will introduce the appropriate barriers */ ssk->sk_err = EBADMSG; - ssk->sk_error_report(ssk); tcp_set_state(ssk, TCP_CLOSE); tcp_send_active_reset(ssk, GFP_ATOMIC); WRITE_ONCE(subflow->data_avail, 0); @@ -1086,41 +1085,6 @@ void mptcp_space(const struct sock *ssk, int *space, int *full_space) *full_space = tcp_full_space(sk); }

-static void subflow_data_ready(struct sock *sk) -{ - struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - u16 state = 1 << inet_sk_state_load(sk); - struct sock *parent = subflow->conn; - struct mptcp_sock *msk; - - msk = mptcp_sk(parent); - if (state & TCPF_LISTEN) { - /* MPJ subflow are removed from accept queue before reaching here, - * avoid stray wakeups - */ - if (reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue)) - return; - - set_bit(MPTCP_DATA_READY, &msk->flags); - parent->sk_data_ready(parent); - return; - } - - WARN_ON_ONCE(!__mptcp_check_fallback(msk) && !subflow->mp_capable && - !subflow->mp_join && !(state & TCPF_CLOSE)); - - if (mptcp_subflow_data_available(sk)) - mptcp_data_ready(parent, sk); -} - -static void subflow_write_space(struct sock *ssk) -{ - struct sock *sk = mptcp_subflow_ctx(ssk)->conn; - - mptcp_propagate_sndbuf(sk, ssk); - mptcp_write_space(sk); -} - void __mptcp_error_report(struct sock *sk) { struct mptcp_subflow_context *subflow; @@ -1161,6 +1125,43 @@ static void subflow_error_report(struct sock *ssk) mptcp_data_unlock(sk); }

+static void subflow_data_ready(struct sock *sk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + u16 state = 1 << inet_sk_state_load(sk); + struct sock *parent = subflow->conn; + struct mptcp_sock *msk; + + msk = mptcp_sk(parent); + if (state & TCPF_LISTEN) { + /* MPJ subflow are removed from accept queue before reaching here, + * avoid stray wakeups + */ + if (reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue)) + return; + + set_bit(MPTCP_DATA_READY, &msk->flags); + parent->sk_data_ready(parent); + return; + } + + WARN_ON_ONCE(!__mptcp_check_fallback(msk) && !subflow->mp_capable && + !subflow->mp_join && !(state & TCPF_CLOSE)); + + if (mptcp_subflow_data_available(sk)) + mptcp_data_ready(parent, sk); + else if (unlikely(sk->sk_err)) + subflow_error_report(sk); +} + +static void subflow_write_space(struct sock *ssk) +{ + struct sock *sk = mptcp_subflow_ctx(ssk)->conn; + + mptcp_propagate_sndbuf(sk, ssk); + mptcp_write_space(sk); +} + static struct inet_connection_sock_af_ops * subflow_default_af_ops(struct sock *sk) { @@ -1469,6 +1470,8 @@ static void subflow_state_change(struct sock *sk) */ if (mptcp_subflow_data_available(sk)) mptcp_data_ready(parent, sk); + else if (unlikely(sk->sk_err)) + subflow_error_report(sk);

subflow_sched_work_if_closed(mptcp_sk(parent), sk);

From: Rahul Lakkireddy rahul.lakkireddy@chelsio.com

[ Upstream commit 42a2039753a7f758ba5c85cb199fcf10dc2111eb ]

Boot images are copied to memory and updated with current underlying device ID before flashing them to adapter. Ensure the updated images are always flashed in Big Endian to allow the firmware to read the new images during boot properly.

Fixes: 550883558f17 ("cxgb4: add support to flash boot image") Signed-off-by: Rahul Lakkireddy rahul.lakkireddy@chelsio.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 44 +++++++++++++--------- 1 file changed, 27 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 80882cfc370f..029f0c83d785 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -3060,16 +3060,19 @@ int t4_read_flash(struct adapter *adapter, unsigned int addr, * @addr: the start address to write * @n: length of data to write in bytes * @data: the data to write + * @byte_oriented: whether to store data as bytes or as words * * Writes up to a page of data (256 bytes) to the serial flash starting * at the given address. All the data must be written to the same page. + * If @byte_oriented is set the write data is stored as byte stream + * (i.e. matches what on disk), otherwise in big-endian. */ static int t4_write_flash(struct adapter *adapter, unsigned int addr, - unsigned int n, const u8 *data) + unsigned int n, const u8 *data, bool byte_oriented) { - int ret; - u32 buf[64]; unsigned int i, c, left, val, offset = addr & 0xff; + u32 buf[64]; + int ret;

if (addr >= adapter->params.sf_size || offset + n > SF_PAGE_SIZE) return -EINVAL; @@ -3080,10 +3083,14 @@ static int t4_write_flash(struct adapter *adapter, unsigned int addr, (ret = sf1_write(adapter, 4, 1, 1, val)) != 0) goto unlock;

- for (left = n; left; left -= c) { + for (left = n; left; left -= c, data += c) { c = min(left, 4U); - for (val = 0, i = 0; i < c; ++i) - val = (val << 8) + *data++; + for (val = 0, i = 0; i < c; ++i) { + if (byte_oriented) + val = (val << 8) + data[i]; + else + val = (val << 8) + data[c - i - 1]; + }

ret = sf1_write(adapter, c, c != left, 1, val); if (ret) @@ -3096,7 +3103,8 @@ static int t4_write_flash(struct adapter *adapter, unsigned int addr, t4_write_reg(adapter, SF_OP_A, 0); /* unlock SF */

/* Read the page to verify the write succeeded */ - ret = t4_read_flash(adapter, addr & ~0xff, ARRAY_SIZE(buf), buf, 1); + ret = t4_read_flash(adapter, addr & ~0xff, ARRAY_SIZE(buf), buf, + byte_oriented); if (ret) return ret;

@@ -3692,7 +3700,7 @@ int t4_load_fw(struct adapter *adap, const u8 *fw_data, unsigned int size) */ memcpy(first_page, fw_data, SF_PAGE_SIZE); ((struct fw_hdr *)first_page)->fw_ver = cpu_to_be32(0xffffffff); - ret = t4_write_flash(adap, fw_start, SF_PAGE_SIZE, first_page); + ret = t4_write_flash(adap, fw_start, SF_PAGE_SIZE, first_page, true); if (ret) goto out;

@@ -3700,14 +3708,14 @@ int t4_load_fw(struct adapter *adap, const u8 *fw_data, unsigned int size) for (size -= SF_PAGE_SIZE; size; size -= SF_PAGE_SIZE) { addr += SF_PAGE_SIZE; fw_data += SF_PAGE_SIZE; - ret = t4_write_flash(adap, addr, SF_PAGE_SIZE, fw_data); + ret = t4_write_flash(adap, addr, SF_PAGE_SIZE, fw_data, true); if (ret) goto out; }

- ret = t4_write_flash(adap, - fw_start + offsetof(struct fw_hdr, fw_ver), - sizeof(hdr->fw_ver), (const u8 *)&hdr->fw_ver); + ret = t4_write_flash(adap, fw_start + offsetof(struct fw_hdr, fw_ver), + sizeof(hdr->fw_ver), (const u8 *)&hdr->fw_ver, + true); out: if (ret) dev_err(adap->pdev_dev, "firmware download failed, error %d\n", @@ -10208,7 +10216,7 @@ int t4_load_cfg(struct adapter *adap, const u8 *cfg_data, unsigned int size) n = size - i; else n = SF_PAGE_SIZE; - ret = t4_write_flash(adap, addr, n, cfg_data); + ret = t4_write_flash(adap, addr, n, cfg_data, true); if (ret) goto out;

@@ -10677,13 +10685,14 @@ int t4_load_boot(struct adapter *adap, u8 *boot_data, for (size -= SF_PAGE_SIZE; size; size -= SF_PAGE_SIZE) { addr += SF_PAGE_SIZE; boot_data += SF_PAGE_SIZE; - ret = t4_write_flash(adap, addr, SF_PAGE_SIZE, boot_data); + ret = t4_write_flash(adap, addr, SF_PAGE_SIZE, boot_data, + false); if (ret) goto out; }

ret = t4_write_flash(adap, boot_sector, SF_PAGE_SIZE, - (const u8 *)header); + (const u8 *)header, false);

out: if (ret) @@ -10758,7 +10767,7 @@ int t4_load_bootcfg(struct adapter *adap, const u8 *cfg_data, unsigned int size) for (i = 0; i < size; i += SF_PAGE_SIZE) { n = min_t(u32, size - i, SF_PAGE_SIZE);

- ret = t4_write_flash(adap, addr, n, cfg_data); + ret = t4_write_flash(adap, addr, n, cfg_data, false); if (ret) goto out;

@@ -10770,7 +10779,8 @@ int t4_load_bootcfg(struct adapter *adap, const u8 *cfg_data, unsigned int size) for (i = 0; i < npad; i++) { u8 data = 0;

- ret = t4_write_flash(adap, cfg_addr + size + i, 1, &data); + ret = t4_write_flash(adap, cfg_addr + size + i, 1, &data, + false); if (ret) goto out; }

From: Rahul Lakkireddy rahul.lakkireddy@chelsio.com

[ Upstream commit 6d297540f75d759489054e8b07932208fc4db2cb ]

When using firmware-assisted PHY firmware image write to flash, halt the chip before beginning the flash write operation to allow the running firmware to store the image persistently. Otherwise, the running firmware will only store the PHY image in local on-chip RAM, which will be lost after next reset.

Fixes: 4ee339e1e92a ("cxgb4: add support to flash PHY image") Signed-off-by: Rahul Lakkireddy rahul.lakkireddy@chelsio.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- .../ethernet/chelsio/cxgb4/cxgb4_ethtool.c | 22 ++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index bc2de01d0539..df20485b5744 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -1337,11 +1337,27 @@ static int cxgb4_ethtool_flash_phy(struct net_device *netdev, return ret; }

+ /* We have to RESET the chip/firmware because we need the + * chip in uninitialized state for loading new PHY image. + * Otherwise, the running firmware will only store the PHY + * image in local RAM which will be lost after next reset. + */ + ret = t4_fw_reset(adap, adap->mbox, PIORSTMODE_F | PIORST_F); + if (ret < 0) { + dev_err(adap->pdev_dev, + "Set FW to RESET for flashing PHY FW failed. ret: %d\n", + ret); + return ret; + } + ret = t4_load_phy_fw(adap, MEMWIN_NIC, NULL, data, size); - if (ret) - dev_err(adap->pdev_dev, "Failed to load PHY FW\n"); + if (ret < 0) { + dev_err(adap->pdev_dev, "Failed to load PHY FW. ret: %d\n", + ret); + return ret; + }

- return ret; + return 0; }

static int cxgb4_ethtool_flash_fw(struct net_device *netdev,

From: Changbin Du changbin.du@gmail.com

[ Upstream commit ea6932d70e223e02fea3ae20a4feff05d7c1ea9a ]

There is a panic in socket ioctl cmd SIOCGSKNS when NET_NS is not enabled. The reason is that nsfs tries to access ns->ops but the proc_ns_operations is not implemented in this case.

[7.670023] Unable to handle kernel NULL pointer dereference at virtual address 00000010 [7.670268] pgd = 32b54000 [7.670544] [00000010] *pgd=00000000 [7.671861] Internal error: Oops: 5 [#1] SMP ARM [7.672315] Modules linked in: [7.672918] CPU: 0 PID: 1 Comm: systemd Not tainted 5.13.0-rc3-00375-g6799d4f2da49 #16 [7.673309] Hardware name: Generic DT based system [7.673642] PC is at nsfs_evict+0x24/0x30 [7.674486] LR is at clear_inode+0x20/0x9c

The same to tun SIOCGSKNS command.

To fix this problem, we make get_net_ns() return -EINVAL when NET_NS is disabled. Meanwhile move it to right place net/core/net_namespace.c.

Signed-off-by: Changbin Du changbin.du@gmail.com Fixes: c62cce2caee5 ("net: add an ioctl to get a socket network namespace") Cc: Cong Wang xiyou.wangcong@gmail.com Cc: Jakub Kicinski kuba@kernel.org Cc: David Laight David.Laight@ACULAB.COM Cc: Christian Brauner christian.brauner@ubuntu.com Suggested-by: Jakub Kicinski kuba@kernel.org Acked-by: Christian Brauner christian.brauner@ubuntu.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/socket.h | 2 -- include/net/net_namespace.h | 7 +++++++ net/core/net_namespace.c | 12 ++++++++++++ net/socket.c | 13 ------------- 4 files changed, 19 insertions(+), 15 deletions(-)

diff --git a/include/linux/socket.h b/include/linux/socket.h index 385894b4a8bb..42222a84167f 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -438,6 +438,4 @@ extern int __sys_socketpair(int family, int type, int protocol, int __user *usockvec); extern int __sys_shutdown_sock(struct socket *sock, int how); extern int __sys_shutdown(int fd, int how); - -extern struct ns_common *get_net_ns(struct ns_common *ns); #endif /* _LINUX_SOCKET_H */ diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index dcaee24a4d87..14b6f7f44532 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -197,6 +197,8 @@ struct net *copy_net_ns(unsigned long flags, struct user_namespace *user_ns, void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid);

void net_ns_barrier(void); + +struct ns_common *get_net_ns(struct ns_common *ns); #else /* CONFIG_NET_NS */ #include <linux/sched.h> #include <linux/nsproxy.h> @@ -216,6 +218,11 @@ static inline void net_ns_get_ownership(const struct net *net, }

static inline void net_ns_barrier(void) {} + +static inline struct ns_common *get_net_ns(struct ns_common *ns) +{ + return ERR_PTR(-EINVAL); +} #endif /* CONFIG_NET_NS */

diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 43b6ac4c4439..cc8dafb25d61 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -641,6 +641,18 @@ void __put_net(struct net *net) } EXPORT_SYMBOL_GPL(__put_net);

+/** + * get_net_ns - increment the refcount of the network namespace + * @ns: common namespace (net) + * + * Returns the net's common namespace. + */ +struct ns_common *get_net_ns(struct ns_common *ns) +{ + return &get_net(container_of(ns, struct net, ns))->ns; +} +EXPORT_SYMBOL_GPL(get_net_ns); + struct net *get_net_ns_by_fd(int fd) { struct file *file; diff --git a/net/socket.c b/net/socket.c index 84a8049c2b09..03259cb919f7 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1072,19 +1072,6 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, * what to do with it - that's up to the protocol still. */

-/** - * get_net_ns - increment the refcount of the network namespace - * @ns: common namespace (net) - * - * Returns the net's common namespace. - */ - -struct ns_common *get_net_ns(struct ns_common *ns) -{ - return &get_net(container_of(ns, struct net, ns))->ns; -} -EXPORT_SYMBOL_GPL(get_net_ns); - static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) { struct socket *sock;

From: Jakub Kicinski kuba@kernel.org

[ Upstream commit e175aef902697826d344ce3a12189329848fe898 ]

Outer nest for ETHTOOL_A_STRSET_STRINGSETS is not accounted for. This may result in ETHTOOL_MSG_STRSET_GET producing a warning like:

calculated message payload length (684) not sufficient WARNING: CPU: 0 PID: 30967 at net/ethtool/netlink.c:369 ethnl_default_doit+0x87a/0xa20

and a splat.

As usually with such warnings three conditions must be met for the warning to trigger: - there must be no skb size rounding up (e.g. reply_size of 684); - string set must be per-device (so that the header gets populated); - the device name must be at least 12 characters long.

all in all with current user space it looks like reading priv flags is the only place this could potentially happen. Or with syzbot :)

Reported-by: syzbot+59aa77b92d06cd5a54f2@syzkaller.appspotmail.com Fixes: 71921690f974 ("ethtool: provide string sets with STRSET_GET request") Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ethtool/strset.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c index c3a5489964cd..9908b922cce8 100644 --- a/net/ethtool/strset.c +++ b/net/ethtool/strset.c @@ -328,6 +328,8 @@ static int strset_reply_size(const struct ethnl_req_info *req_base, int len = 0; int ret;

+ len += nla_total_size(0); /* ETHTOOL_A_STRSET_STRINGSETS */ + for (i = 0; i < ETH_SS_COUNT; i++) { const struct strset_info *set_info = &data->sets[i];

From: Christophe JAILLET christophe.jaillet@wanadoo.fr

[ Upstream commit 49a10c7b176295f8fafb338911cf028e97f65f4d ]

If an error occurs after a 'pci_enable_pcie_error_reporting()' call, it must be undone by a corresponding 'pci_disable_pcie_error_reporting()' call, as already done in the remove function.

Fixes: e87ad5539343 ("netxen: support pci error handlers") Signed-off-by: Christophe JAILLET christophe.jaillet@wanadoo.fr Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index 7e6bac85495d..344ea1143454 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@ -1602,6 +1602,8 @@ err_out_free_netdev: free_netdev(netdev);

err_out_free_res: + if (NX_IS_REVISION_P3(pdev->revision)) + pci_disable_pcie_error_reporting(pdev); pci_release_regions(pdev);

err_out_disable_pdev:

From: David Ahern dsahern@kernel.org

[ Upstream commit b87b04f5019e821c8c6c7761f258402e43500a1f ]

Oliver reported a use case where deleting a VRF device can hang waiting for the refcnt to drop to 0. The root cause is that the dst is allocated against the VRF device but cached on the loopback device.

The use case (added to the selftests) has an implicit VRF crossing due to the ordering of the FIB rules (lookup local is before the l3mdev rule, but the problem occurs even if the FIB rules are re-ordered with local after l3mdev because the VRF table does not have a default route to terminate the lookup). The end result is is that the FIB lookup returns the loopback device as the nexthop, but the ingress device is in a VRF. The mismatch causes the dst alloc against the VRF device but then cached on the loopback.

The fix is to bring the trick used for IPv6 (see ip6_rt_get_dev_rcu): pick the dst alloc device based the fib lookup result but with checks that the result has a nexthop device (e.g., not an unreachable or prohibit entry).

Fixes: f5a0aab84b74 ("net: ipv4: dst for local input routes should use l3mdev if relevant") Reported-by: Oliver Herms oliver.peter.herms@gmail.com Signed-off-by: David Ahern dsahern@kernel.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/route.c | 15 +++++++++++++- tools/testing/selftests/net/fib_tests.sh | 25 ++++++++++++++++++++++++ 2 files changed, 39 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c index d635b4f32d34..09506203156d 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2081,6 +2081,19 @@ martian_source: return err; }

+/* get device for dst_alloc with local routes */ +static struct net_device *ip_rt_get_dev(struct net *net, + const struct fib_result *res) +{ + struct fib_nh_common *nhc = res->fi ? res->nhc : NULL; + struct net_device *dev = NULL; + + if (nhc) + dev = l3mdev_master_dev_rcu(nhc->nhc_dev); + + return dev ? : net->loopback_dev; +} + /* * NOTE. We drop all the packets that has local source * addresses, because every properly looped back packet @@ -2237,7 +2250,7 @@ local_input: } }

- rth = rt_dst_alloc(l3mdev_master_dev_rcu(dev) ? : net->loopback_dev, + rth = rt_dst_alloc(ip_rt_get_dev(net, res), flags | RTCF_LOCAL, res->type, IN_DEV_ORCONF(in_dev, NOPOLICY), false); if (!rth) diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 2b5707738609..6fad54c7ecb4 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -1384,12 +1384,37 @@ ipv4_rt_replace() ipv4_rt_replace_mpath }

+# checks that cached input route on VRF port is deleted +# when VRF is deleted +ipv4_local_rt_cache() +{ + run_cmd "ip addr add 10.0.0.1/32 dev lo" + run_cmd "ip netns add test-ns" + run_cmd "ip link add veth-outside type veth peer name veth-inside" + run_cmd "ip link add vrf-100 type vrf table 1100" + run_cmd "ip link set veth-outside master vrf-100" + run_cmd "ip link set veth-inside netns test-ns" + run_cmd "ip link set veth-outside up" + run_cmd "ip link set vrf-100 up" + run_cmd "ip route add 10.1.1.1/32 dev veth-outside table 1100" + run_cmd "ip netns exec test-ns ip link set veth-inside up" + run_cmd "ip netns exec test-ns ip addr add 10.1.1.1/32 dev veth-inside" + run_cmd "ip netns exec test-ns ip route add 10.0.0.1/32 dev veth-inside" + run_cmd "ip netns exec test-ns ip route add default via 10.0.0.1" + run_cmd "ip netns exec test-ns ping 10.0.0.1 -c 1 -i 1" + run_cmd "ip link delete vrf-100" + + # if we do not hang test is a success + log_test $? 0 "Cached route removed from VRF port device" +} + ipv4_route_test() { route_setup

ipv4_rt_add ipv4_rt_replace + ipv4_local_rt_cache

route_cleanup }

From: Daniel Borkmann daniel@iogearbox.net

[ Upstream commit 9183671af6dbf60a1219371d4ed73e23f43b49db ]

The verifier only enumerates valid control-flow paths and skips paths that are unreachable in the non-speculative domain. And so it can miss issues under speculative execution on mispredicted branches.

For example, a type confusion has been demonstrated with the following crafted program:

// r0 = pointer to a map array entry // r6 = pointer to readable stack slot // r9 = scalar controlled by attacker 1: r0 = *(u64 *)(r0) // cache miss 2: if r0 != 0x0 goto line 4 3: r6 = r9 4: if r0 != 0x1 goto line 6 5: r9 = *(u8 *)(r6) 6: // leak r9

Since line 3 runs iff r0 == 0 and line 5 runs iff r0 == 1, the verifier concludes that the pointer dereference on line 5 is safe. But: if the attacker trains both the branches to fall-through, such that the following is speculatively executed ...

r6 = r9 r9 = *(u8 *)(r6) // leak r9

... then the program will dereference an attacker-controlled value and could leak its content under speculative execution via side-channel. This requires to mistrain the branch predictor, which can be rather tricky, because the branches are mutually exclusive. However such training can be done at congruent addresses in user space using different branches that are not mutually exclusive. That is, by training branches in user space ...

A: if r0 != 0x0 goto line C B: ... C: if r0 != 0x0 goto line D D: ...

... such that addresses A and C collide to the same CPU branch prediction entries in the PHT (pattern history table) as those of the BPF program's lines 2 and 4, respectively. A non-privileged attacker could simply brute force such collisions in the PHT until observing the attack succeeding.

Alternative methods to mistrain the branch predictor are also possible that avoid brute forcing the collisions in the PHT. A reliable attack has been demonstrated, for example, using the following crafted program:

// r0 = pointer to a [control] map array entry // r7 = *(u64 *)(r0 + 0), training/attack phase // r8 = *(u64 *)(r0 + 8), oob address // [...] // r0 = pointer to a [data] map array entry 1: if r7 == 0x3 goto line 3 2: r8 = r0 // crafted sequence of conditional jumps to separate the conditional // branch in line 193 from the current execution flow 3: if r0 != 0x0 goto line 5 4: if r0 == 0x0 goto exit 5: if r0 != 0x0 goto line 7 6: if r0 == 0x0 goto exit [...] 187: if r0 != 0x0 goto line 189 188: if r0 == 0x0 goto exit // load any slowly-loaded value (due to cache miss in phase 3) ... 189: r3 = *(u64 *)(r0 + 0x1200) // ... and turn it into known zero for verifier, while preserving slowly- // loaded dependency when executing: 190: r3 &= 1 191: r3 &= 2 // speculatively bypassed phase dependency 192: r7 += r3 193: if r7 == 0x3 goto exit 194: r4 = *(u8 *)(r8 + 0) // leak r4

As can be seen, in training phase (phase != 0x3), the condition in line 1 turns into false and therefore r8 with the oob address is overridden with the valid map value address, which in line 194 we can read out without issues. However, in attack phase, line 2 is skipped, and due to the cache miss in line 189 where the map value is (zeroed and later) added to the phase register, the condition in line 193 takes the fall-through path due to prior branch predictor training, where under speculation, it'll load the byte at oob address r8 (unknown scalar type at that point) which could then be leaked via side-channel.

One way to mitigate these is to 'branch off' an unreachable path, meaning, the current verification path keeps following the is_branch_taken() path and we push the other branch to the verification stack. Given this is unreachable from the non-speculative domain, this branch's vstate is explicitly marked as speculative. This is needed for two reasons: i) if this path is solely seen from speculative execution, then we later on still want the dead code elimination to kick in in order to sanitize these instructions with jmp-1s, and ii) to ensure that paths walked in the non-speculative domain are not pruned from earlier walks of paths walked in the speculative domain. Additionally, for robustness, we mark the registers which have been part of the conditional as unknown in the speculative path given there should be no assumptions made on their content.

The fix in here mitigates type confusion attacks described earlier due to i) all code paths in the BPF program being explored and ii) existing verifier logic already ensuring that given memory access instruction references one specific data structure.

An alternative to this fix that has also been looked at in this scope was to mark aux->alu_state at the jump instruction with a BPF_JMP_TAKEN state as well as direction encoding (always-goto, always-fallthrough, unknown), such that mixing of different always-* directions themselves as well as mixing of always-* with unknown directions would cause a program rejection by the verifier, e.g. programs with constructs like 'if ([...]) { x = 0; } else { x = 1; }' with subsequent 'if (x == 1) { [...] }'. For unprivileged, this would result in only single direction always-* taken paths, and unknown taken paths being allowed, such that the former could be patched from a conditional jump to an unconditional jump (ja). Compared to this approach here, it would have two downsides: i) valid programs that otherwise are not performing any pointer arithmetic, etc, would potentially be rejected/broken, and ii) we are required to turn off path pruning for unprivileged, where both can be avoided in this work through pushing the invalid branch to the verification stack.

The issue was originally discovered by Adam and Ofek, and later independently discovered and reported as a result of Benedict and Piotr's research work.

Fixes: b2157399cc98 ("bpf: prevent out-of-bounds speculation") Reported-by: Adam Morrison mad@cs.tau.ac.il Reported-by: Ofek Kirzner ofekkir@gmail.com Reported-by: Benedict Schlueter benedict.schlueter@rub.de Reported-by: Piotr Krysiuk piotras@gmail.com Signed-off-by: Daniel Borkmann daniel@iogearbox.net Reviewed-by: John Fastabend john.fastabend@gmail.com Reviewed-by: Benedict Schlueter benedict.schlueter@rub.de Reviewed-by: Piotr Krysiuk piotras@gmail.com Acked-by: Alexei Starovoitov ast@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/bpf/verifier.c | 44 +++++++++++++++++++++++++++++++++++++++---- 1 file changed, 40 insertions(+), 4 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 9e600767803b..bdf4be10c8cc 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5937,6 +5937,27 @@ struct bpf_sanitize_info { bool mask_to_left; };

+static struct bpf_verifier_state * +sanitize_speculative_path(struct bpf_verifier_env *env, + const struct bpf_insn *insn, + u32 next_idx, u32 curr_idx) +{ + struct bpf_verifier_state *branch; + struct bpf_reg_state *regs; + + branch = push_stack(env, next_idx, curr_idx, true); + if (branch && insn) { + regs = branch->frame[branch->curframe]->regs; + if (BPF_SRC(insn->code) == BPF_K) { + mark_reg_unknown(env, regs, insn->dst_reg); + } else if (BPF_SRC(insn->code) == BPF_X) { + mark_reg_unknown(env, regs, insn->dst_reg); + mark_reg_unknown(env, regs, insn->src_reg); + } + } + return branch; +} + static int sanitize_ptr_alu(struct bpf_verifier_env *env, struct bpf_insn *insn, const struct bpf_reg_state *ptr_reg, @@ -6020,7 +6041,8 @@ do_sim: tmp = *dst_reg; *dst_reg = *ptr_reg; } - ret = push_stack(env, env->insn_idx + 1, env->insn_idx, true); + ret = sanitize_speculative_path(env, NULL, env->insn_idx + 1, + env->insn_idx); if (!ptr_is_dst_reg && ret) *dst_reg = tmp; return !ret ? REASON_STACK : 0; @@ -8204,14 +8226,28 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, if (err) return err; } + if (pred == 1) { - /* only follow the goto, ignore fall-through */ + /* Only follow the goto, ignore fall-through. If needed, push + * the fall-through branch for simulation under speculative + * execution. + */ + if (!env->bypass_spec_v1 && + !sanitize_speculative_path(env, insn, *insn_idx + 1, + *insn_idx)) + return -EFAULT; *insn_idx += insn->off; return 0; } else if (pred == 0) { - /* only follow fall-through branch, since - * that's where the program will go + /* Only follow the fall-through branch, since that's where the + * program will go. If needed, push the goto branch for + * simulation under speculative execution. */ + if (!env->bypass_spec_v1 && + !sanitize_speculative_path(env, insn, + *insn_idx + insn->off + 1, + *insn_idx)) + return -EFAULT; return 0; }

From: Jakub Kicinski kuba@kernel.org

[ Upstream commit 475b92f932168a78da8109acd10bfb7578b8f2bb ]

Scaled PPM conversion to PPB may (on 64bit systems) result in a value larger than s32 can hold (freq/scaled_ppm is a long). This means the kernel will not correctly reject unreasonably high ->freq values (e.g. > 4294967295ppb, 281474976645 scaled PPM).

The conversion is equivalent to a division by ~66 (65.536), so the value of ppb is always smaller than ppm, but not small enough to assume narrowing the type from long -> s32 is okay.

Note that reasonable user space (e.g. ptp4l) will not use such high values, anyway, 4289046510ppb ~= 4.3x, so the fix is somewhat pedantic.

Fixes: d39a743511cd ("ptp: validate the requested frequency adjustment.") Fixes: d94ba80ebbea ("ptp: Added a brand new class driver for ptp clocks.") Signed-off-by: Jakub Kicinski kuba@kernel.org Acked-by: Richard Cochran richardcochran@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/ptp/ptp_clock.c | 6 +++--- include/linux/ptp_clock_kernel.h | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 03a246e60fd9..21c4c34c52d8 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -63,7 +63,7 @@ static void enqueue_external_timestamp(struct timestamp_event_queue *queue, spin_unlock_irqrestore(&queue->lock, flags); }

-s32 scaled_ppm_to_ppb(long ppm) +long scaled_ppm_to_ppb(long ppm) { /* * The 'freq' field in the 'struct timex' is in parts per @@ -80,7 +80,7 @@ s32 scaled_ppm_to_ppb(long ppm) s64 ppb = 1 + ppm; ppb *= 125; ppb >>= 13; - return (s32) ppb; + return (long) ppb; } EXPORT_SYMBOL(scaled_ppm_to_ppb);

@@ -138,7 +138,7 @@ static int ptp_clock_adjtime(struct posix_clock *pc, struct __kernel_timex *tx) delta = ktime_to_ns(kt); err = ops->adjtime(ops, delta); } else if (tx->modes & ADJ_FREQUENCY) { - s32 ppb = scaled_ppm_to_ppb(tx->freq); + long ppb = scaled_ppm_to_ppb(tx->freq); if (ppb > ops->max_adj || ppb < -ops->max_adj) return -ERANGE; if (ops->adjfine) diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 0d47fd33b228..51d7f1b8b32a 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -235,7 +235,7 @@ extern int ptp_clock_index(struct ptp_clock *ptp); * @ppm: Parts per million, but with a 16 bit binary fractional field */

-extern s32 scaled_ppm_to_ppb(long ppm); +extern long scaled_ppm_to_ppb(long ppm);

/** * ptp_find_pin() - obtain the pin index of a given auxiliary function

From: Aleksander Jan Bajkowski olek2@wp.pl

[ Upstream commit 7ea6cd16f1599c1eac6018751eadbc5fc736b99a ]

The previous commit didn't fix the bug properly. By mistake, it replaces the pointer of the next skb in the descriptor ring instead of the current one. As a result, the two descriptors are assigned the same SKB. The error is seen during the iperf test when skb_put tries to insert a second packet and exceeds the available buffer.

Fixes: c7718ee96dbc ("net: lantiq: fix memory corruption in RX ring ") Signed-off-by: Aleksander Jan Bajkowski olek2@wp.pl Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/lantiq_xrx200.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c index 3da494df72f3..072075bc60ee 100644 --- a/drivers/net/ethernet/lantiq_xrx200.c +++ b/drivers/net/ethernet/lantiq_xrx200.c @@ -154,6 +154,7 @@ static int xrx200_close(struct net_device *net_dev)

static int xrx200_alloc_skb(struct xrx200_chan *ch) { + struct sk_buff *skb = ch->skb[ch->dma.desc]; dma_addr_t mapping; int ret = 0;

@@ -168,6 +169,7 @@ static int xrx200_alloc_skb(struct xrx200_chan *ch) XRX200_DMA_DATA_LEN, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(ch->priv->dev, mapping))) { dev_kfree_skb_any(ch->skb[ch->dma.desc]); + ch->skb[ch->dma.desc] = skb; ret = -ENOMEM; goto skip; } @@ -198,7 +200,6 @@ static int xrx200_hw_receive(struct xrx200_chan *ch) ch->dma.desc %= LTQ_DESC_NUM;

if (ret) { - ch->skb[ch->dma.desc] = skb; net_dev->stats.rx_dropped++; netdev_err(net_dev, "failed to allocate new rx buffer\n"); return ret;

From: Joakim Zhang qiangqing.zhang@nxp.com

[ Upstream commit d23765646e71b43ed2b809930411ba5c0aadee7b ]

Commit da722186f654 ("net: fec: set GPR bit on suspend by DT configuration.") refactor the fec_devtype, need adjust ptp driver accordingly.

Fixes: da722186f654 ("net: fec: set GPR bit on suspend by DT configuration.") Signed-off-by: Joakim Zhang qiangqing.zhang@nxp.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/freescale/fec_ptp.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index 1753807cbf97..ce8e5555f3e0 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -215,15 +215,13 @@ static u64 fec_ptp_read(const struct cyclecounter *cc) { struct fec_enet_private *fep = container_of(cc, struct fec_enet_private, cc); - const struct platform_device_id *id_entry = - platform_get_device_id(fep->pdev); u32 tempval;

tempval = readl(fep->hwp + FEC_ATIME_CTRL); tempval |= FEC_T_CTRL_CAPTURE; writel(tempval, fep->hwp + FEC_ATIME_CTRL);

- if (id_entry->driver_data & FEC_QUIRK_BUG_CAPTURE) + if (fep->quirks & FEC_QUIRK_BUG_CAPTURE) udelay(1);

return readl(fep->hwp + FEC_ATIME);

From: Eric Dumazet edumazet@google.com

[ Upstream commit a494bd642d9120648b06bb7d28ce6d05f55a7819 ]

While unix_may_send(sk, osk) is called while osk is locked, it appears unix_release_sock() can overwrite unix_peer() after this lock has been released, making KCSAN unhappy.

Changing unix_release_sock() to access/change unix_peer() before lock is released should fix this issue.

BUG: KCSAN: data-race in unix_dgram_sendmsg / unix_release_sock

write to 0xffff88810465a338 of 8 bytes by task 20852 on cpu 1: unix_release_sock+0x4ed/0x6e0 net/unix/af_unix.c:558 unix_release+0x2f/0x50 net/unix/af_unix.c:859 __sock_release net/socket.c:599 [inline] sock_close+0x6c/0x150 net/socket.c:1258 __fput+0x25b/0x4e0 fs/file_table.c:280 ____fput+0x11/0x20 fs/file_table.c:313 task_work_run+0xae/0x130 kernel/task_work.c:164 tracehook_notify_resume include/linux/tracehook.h:189 [inline] exit_to_user_mode_loop kernel/entry/common.c:175 [inline] exit_to_user_mode_prepare+0x156/0x190 kernel/entry/common.c:209 __syscall_exit_to_user_mode_work kernel/entry/common.c:291 [inline] syscall_exit_to_user_mode+0x20/0x40 kernel/entry/common.c:302 do_syscall_64+0x56/0x90 arch/x86/entry/common.c:57 entry_SYSCALL_64_after_hwframe+0x44/0xae

read to 0xffff88810465a338 of 8 bytes by task 20888 on cpu 0: unix_may_send net/unix/af_unix.c:189 [inline] unix_dgram_sendmsg+0x923/0x1610 net/unix/af_unix.c:1712 sock_sendmsg_nosec net/socket.c:654 [inline] sock_sendmsg net/socket.c:674 [inline] ____sys_sendmsg+0x360/0x4d0 net/socket.c:2350 ___sys_sendmsg net/socket.c:2404 [inline] __sys_sendmmsg+0x315/0x4b0 net/socket.c:2490 __do_sys_sendmmsg net/socket.c:2519 [inline] __se_sys_sendmmsg net/socket.c:2516 [inline] __x64_sys_sendmmsg+0x53/0x60 net/socket.c:2516 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae

value changed: 0xffff888167905400 -> 0x0000000000000000

Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 20888 Comm: syz-executor.0 Not tainted 5.13.0-rc5-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/unix/af_unix.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 5a31307ceb76..5d1192ceb139 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -535,12 +535,14 @@ static void unix_release_sock(struct sock *sk, int embrion) u->path.mnt = NULL; state = sk->sk_state; sk->sk_state = TCP_CLOSE; + + skpair = unix_peer(sk); + unix_peer(sk) = NULL; + unix_state_unlock(sk);

wake_up_interruptible_all(&u->peer_wait);

- skpair = unix_peer(sk); - if (skpair != NULL) { if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) { unix_state_lock(skpair); @@ -555,7 +557,6 @@ static void unix_release_sock(struct sock *sk, int embrion)

unix_dgram_peer_wake_disconnect(sk, skpair); sock_put(skpair); /* It may now die */ - unix_peer(sk) = NULL; }

/* Try to flush out this socket. Throw out buffers at least */

From: Leon Romanovsky leonro@nvidia.com

[ Upstream commit 2058cc9c8041fde9c0bdd8e868c72b137cff8563 ]

The device can be requested to be attached despite being not probed. This situation is possible if devlink reload races with module removal, and the following kernel panic is an outcome of such race.

mlx5_core 0000:00:09.0: firmware version: 4.7.9999 mlx5_core 0000:00:09.0: 0.000 Gb/s available PCIe bandwidth (8.0 GT/s PCIe x255 link) BUG: unable to handle page fault for address: fffffffffffffff0 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 3218067 P4D 3218067 PUD 321a067 PMD 0 Oops: 0000 [#1] SMP KASAN NOPTI CPU: 7 PID: 250 Comm: devlink Not tainted 5.12.0-rc2+ #2836 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:mlx5_attach_device+0x80/0x280 [mlx5_core] Code: f8 48 c1 e8 03 42 80 3c 38 00 0f 85 80 01 00 00 48 8b 45 68 48 8d 78 f0 48 89 fe 48 c1 ee 03 42 80 3c 3e 00 0f 85 70 01 00 00 <48> 8b 40 f0 48 85 c0 74 0d 48 89 ef ff d0 85 c0 0f 85 84 05 0e 00 RSP: 0018:ffff8880129675f0 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000001 RCX: ffffffff827407f1 RDX: 1ffff110011336cf RSI: 1ffffffffffffffe RDI: fffffffffffffff0 RBP: ffff888008e0c000 R08: 0000000000000008 R09: ffffffffa0662ee7 R10: fffffbfff40cc5dc R11: 0000000000000000 R12: ffff88800ea002e0 R13: ffffed1001d459f7 R14: ffffffffa05ef4f8 R15: dffffc0000000000 FS: 00007f51dfeaf740(0000) GS:ffff88806d5c0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: fffffffffffffff0 CR3: 000000000bc82006 CR4: 0000000000370ea0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: mlx5_load_one+0x117/0x1d0 [mlx5_core] devlink_reload+0x2d5/0x520 ? devlink_remote_reload_actions_performed+0x30/0x30 ? mutex_trylock+0x24b/0x2d0 ? devlink_nl_cmd_reload+0x62b/0x1070 devlink_nl_cmd_reload+0x66d/0x1070 ? devlink_reload+0x520/0x520 ? devlink_nl_pre_doit+0x64/0x4d0 genl_family_rcv_msg_doit+0x1e9/0x2f0 ? mutex_lock_io_nested+0x1130/0x1130 ? genl_family_rcv_msg_attrs_parse.constprop.0+0x240/0x240 ? security_capable+0x51/0x90 genl_rcv_msg+0x27f/0x4a0 ? genl_get_cmd+0x3c0/0x3c0 ? lock_acquire+0x1a9/0x6d0 ? devlink_reload+0x520/0x520 ? lock_release+0x6c0/0x6c0 netlink_rcv_skb+0x11d/0x340 ? genl_get_cmd+0x3c0/0x3c0 ? netlink_ack+0x9f0/0x9f0 ? lock_release+0x1f9/0x6c0 genl_rcv+0x24/0x40 netlink_unicast+0x433/0x700 ? netlink_attachskb+0x730/0x730 ? _copy_from_iter_full+0x178/0x650 ? __alloc_skb+0x113/0x2b0 netlink_sendmsg+0x6f1/0xbd0 ? netlink_unicast+0x700/0x700 ? netlink_unicast+0x700/0x700 sock_sendmsg+0xb0/0xe0 __sys_sendto+0x193/0x240 ? __x64_sys_getpeername+0xb0/0xb0 ? copy_page_range+0x2300/0x2300 ? __up_read+0x1a1/0x7b0 ? do_user_addr_fault+0x219/0xdc0 __x64_sys_sendto+0xdd/0x1b0 ? syscall_enter_from_user_mode+0x1d/0x50 do_syscall_64+0x2d/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f51dffb514a Code: d8 64 89 02 48 c7 c0 ff ff ff ff eb b8 0f 1f 00 f3 0f 1e fa 41 89 ca 64 8b 04 25 18 00 00 00 85 c0 75 15 b8 2c 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 76 c3 0f 1f 44 00 00 55 48 83 ec 30 44 89 4c RSP: 002b:00007ffcaef22e78 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f51dffb514a RDX: 0000000000000030 RSI: 000055750daf2440 RDI: 0000000000000003 RBP: 000055750daf2410 R08: 00007f51e0081200 R09: 000000000000000c R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 Modules linked in: mlx5_core(-) ptp pps_core ib_ipoib rdma_ucm rdma_cm iw_cm ib_cm ib_umad ib_uverbs ib_core [last unloaded: mlx5_ib] CR2: fffffffffffffff0 ---[ end trace 7789831bfe74fa42 ]---

Fixes: a925b5e309c9 ("net/mlx5: Register mlx5 devices to auxiliary virtual bus") Signed-off-by: Leon Romanovsky leonro@nvidia.com Reviewed-by: Parav Pandit parav@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/dev.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index 9153c9bda96f..f0623e94716b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -323,6 +323,16 @@ int mlx5_attach_device(struct mlx5_core_dev *dev) } } else { adev = &priv->adev[i]->adev; + + /* Pay attention that this is not PCI driver that + * mlx5_core_dev is connected, but auxiliary driver. + * + * Here we can race of module unload with devlink + * reload, but we don't need to take extra lock because + * we are holding global mlx5_intf_mutex. + */ + if (!adev->dev.driver) + continue; adrv = to_auxiliary_drv(adev->dev.driver);

if (adrv->resume) @@ -353,6 +363,10 @@ void mlx5_detach_device(struct mlx5_core_dev *dev) continue;

adev = &priv->adev[i]->adev; + /* Auxiliary driver was unbind manually through sysfs */ + if (!adev->dev.driver) + goto skip_suspend; + adrv = to_auxiliary_drv(adev->dev.driver);

if (adrv->suspend) { @@ -360,6 +374,7 @@ void mlx5_detach_device(struct mlx5_core_dev *dev) continue; }

+skip_suspend: del_adev(&priv->adev[i]->adev); priv->adev[i] = NULL; }

From: Parav Pandit parav@nvidia.com

[ Upstream commit ca36fc4d77b35b8d142cf1ed0eae5ec2e071dc3c ]

E-switch should be able to set the GUID of host PF vport. Currently it returns an error. This results in below error when user attempts to configure MAC address of the PF of an external controller.

$ devlink port function set pci/0000:03:00.0/196608 \ hw_addr 00:00:00:11:22:33

mlx5_core 0000:03:00.0: mlx5_esw_set_vport_mac_locked:1876:(pid 6715):\ "Failed to set vport 0 node guid, err = -22. RDMA_CM will not function properly for this VF."

Check for zero vport is no longer needed.

Fixes: 330077d14de1 ("net/mlx5: E-switch, Supporting setting devlink port function mac address") Signed-off-by: Yuval Avnery yuvalav@nvidia.com Signed-off-by: Parav Pandit parav@nvidia.com Reviewed-by: Bodong Wang bodong@nvidia.com Reviewed-by: Alaa Hleihel alaa@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/vport.c | 2 -- 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index e05c5c0f3ae1..7d21fbb9192f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -465,8 +465,6 @@ int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev, void *in; int err;

- if (!vport) - return -EINVAL; if (!MLX5_CAP_GEN(mdev, vport_group_manager)) return -EACCES;

From: Alex Vesker valex@nvidia.com

[ Upstream commit 65fb7d109abe3a1a9f1c2d3ba7e1249bc978d5f0 ]

Decapsulation L3 on small inner packets which are less than 64 Bytes was done incorrectly. In small packets there is an extra padding added in L2 which should not be included in L3 length. The issue was that after decapL3 the extra L2 padding caused an update on the L3 length.

To avoid this issue the new header is pushed to the beginning of the packet (offset 0) which should not cause a HW reparse and update the L3 length.

Fixes: c349b4137cfd ("net/mlx5: DR, Add STEv1 modify header logic") Reviewed-by: Erez Shitrit erezsh@nvidia.com Reviewed-by: Yevgeny Kliteynik kliteyn@nvidia.com Signed-off-by: Alex Vesker valex@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../mellanox/mlx5/core/steering/dr_ste_v1.c | 26 ++++++++++++------- 1 file changed, 16 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c index f146c618a78e..46ef45fa9167 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c @@ -712,7 +712,11 @@ static int dr_ste_v1_set_action_decap_l3_list(void *data, if (hw_action_sz / DR_STE_ACTION_DOUBLE_SZ < DR_STE_DECAP_L3_ACTION_NUM) return -EINVAL;

- memcpy(padded_data, data, data_sz); + inline_data_sz = + MLX5_FLD_SZ_BYTES(ste_double_action_insert_with_inline_v1, inline_data); + + /* Add an alignment padding */ + memcpy(padded_data + data_sz % inline_data_sz, data, data_sz);

/* Remove L2L3 outer headers */ MLX5_SET(ste_single_action_remove_header_v1, hw_action, action_id, @@ -724,32 +728,34 @@ static int dr_ste_v1_set_action_decap_l3_list(void *data, hw_action += DR_STE_ACTION_DOUBLE_SZ; used_actions++; /* Remove and NOP are a single double action */

- inline_data_sz = - MLX5_FLD_SZ_BYTES(ste_double_action_insert_with_inline_v1, inline_data); + /* Point to the last dword of the header */ + data_ptr += (data_sz / inline_data_sz) * inline_data_sz;

- /* Add the new header inline + 2 extra bytes */ + /* Add the new header using inline action 4Byte at a time, the header + * is added in reversed order to the beginning of the packet to avoid + * incorrect parsing by the HW. Since header is 14B or 18B an extra + * two bytes are padded and later removed. + */ for (i = 0; i < data_sz / inline_data_sz + 1; i++) { void *addr_inline;

MLX5_SET(ste_double_action_insert_with_inline_v1, hw_action, action_id, DR_STE_V1_ACTION_ID_INSERT_INLINE); /* The hardware expects here offset to words (2 bytes) */ - MLX5_SET(ste_double_action_insert_with_inline_v1, hw_action, start_offset, - i * 2); + MLX5_SET(ste_double_action_insert_with_inline_v1, hw_action, start_offset, 0);

/* Copy bytes one by one to avoid endianness problem */ addr_inline = MLX5_ADDR_OF(ste_double_action_insert_with_inline_v1, hw_action, inline_data); - memcpy(addr_inline, data_ptr, inline_data_sz); + memcpy(addr_inline, data_ptr - i * inline_data_sz, inline_data_sz); hw_action += DR_STE_ACTION_DOUBLE_SZ; - data_ptr += inline_data_sz; used_actions++; }

- /* Remove 2 extra bytes */ + /* Remove first 2 extra bytes */ MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, action_id, DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE); - MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, start_offset, data_sz / 2); + MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, start_offset, 0); /* The hardware expects here size in words (2 bytes) */ MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, remove_size, 1); used_actions++;

From: Aya Levin ayal@nvidia.com

[ Upstream commit 0232fc2ddcf4ffe01069fd1aa07922652120f44a ]

Reset only the index part of the mkey and keep the variant part. On devlink reload, driver recreates mkeys, so the mkey index may change. Trying to preserve the variant part of the mkey, driver mistakenly merged the mkey index with current value. In case of a devlink reload, current value of index part is dirty, so the index may be corrupted.

Fixes: 54c62e13ad76 ("{IB,net}/mlx5: Setup mkey variant before mr create command invocation") Signed-off-by: Aya Levin ayal@nvidia.com Signed-off-by: Amir Tzin amirtz@nvidia.com Reviewed-by: Tariq Toukan tariqt@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/mr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c index 50af84e76fb6..174f71ed5280 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c @@ -54,7 +54,7 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev, mkey_index = MLX5_GET(create_mkey_out, lout, mkey_index); mkey->iova = MLX5_GET64(mkc, mkc, start_addr); mkey->size = MLX5_GET64(mkc, mkc, len); - mkey->key |= mlx5_idx_to_mkey(mkey_index); + mkey->key = (u32)mlx5_mkey_variant(mkey->key) | mlx5_idx_to_mkey(mkey_index); mkey->pd = MLX5_GET(mkc, mkc, pd); init_waitqueue_head(&mkey->wait);

From: Pavel Skripkin paskripkin@gmail.com

[ Upstream commit 7edcc682301492380fbdd604b4516af5ae667a13 ]

My local syzbot instance hit memory leak in mkiss_open()[1]. The problem was in missing free_netdev() in mkiss_close().

In mkiss_open() netdevice is allocated and then registered, but in mkiss_close() netdevice was only unregistered, but not freed.

Fail log:

BUG: memory leak unreferenced object 0xffff8880281ba000 (size 4096): comm "syz-executor.1", pid 11443, jiffies 4295046091 (age 17.660s) hex dump (first 32 bytes): 61 78 30 00 00 00 00 00 00 00 00 00 00 00 00 00 ax0............. 00 27 fa 2a 80 88 ff ff 00 00 00 00 00 00 00 00 .'.*............ backtrace: [<ffffffff81a27201>] kvmalloc_node+0x61/0xf0 [<ffffffff8706e7e8>] alloc_netdev_mqs+0x98/0xe80 [<ffffffff84e64192>] mkiss_open+0xb2/0x6f0 [1] [<ffffffff842355db>] tty_ldisc_open+0x9b/0x110 [<ffffffff84236488>] tty_set_ldisc+0x2e8/0x670 [<ffffffff8421f7f3>] tty_ioctl+0xda3/0x1440 [<ffffffff81c9f273>] __x64_sys_ioctl+0x193/0x200 [<ffffffff8911263a>] do_syscall_64+0x3a/0xb0 [<ffffffff89200068>] entry_SYSCALL_64_after_hwframe+0x44/0xae

BUG: memory leak unreferenced object 0xffff8880141a9a00 (size 96): comm "syz-executor.1", pid 11443, jiffies 4295046091 (age 17.660s) hex dump (first 32 bytes): e8 a2 1b 28 80 88 ff ff e8 a2 1b 28 80 88 ff ff ...(.......(.... 98 92 9c aa b0 40 02 00 00 00 00 00 00 00 00 00 .....@.......... backtrace: [<ffffffff8709f68b>] __hw_addr_create_ex+0x5b/0x310 [<ffffffff8709fb38>] __hw_addr_add_ex+0x1f8/0x2b0 [<ffffffff870a0c7b>] dev_addr_init+0x10b/0x1f0 [<ffffffff8706e88b>] alloc_netdev_mqs+0x13b/0xe80 [<ffffffff84e64192>] mkiss_open+0xb2/0x6f0 [1] [<ffffffff842355db>] tty_ldisc_open+0x9b/0x110 [<ffffffff84236488>] tty_set_ldisc+0x2e8/0x670 [<ffffffff8421f7f3>] tty_ioctl+0xda3/0x1440 [<ffffffff81c9f273>] __x64_sys_ioctl+0x193/0x200 [<ffffffff8911263a>] do_syscall_64+0x3a/0xb0 [<ffffffff89200068>] entry_SYSCALL_64_after_hwframe+0x44/0xae

BUG: memory leak unreferenced object 0xffff8880219bfc00 (size 512): comm "syz-executor.1", pid 11443, jiffies 4295046091 (age 17.660s) hex dump (first 32 bytes): 00 a0 1b 28 80 88 ff ff 80 8f b1 8d ff ff ff ff ...(............ 80 8f b1 8d ff ff ff ff 00 00 00 00 00 00 00 00 ................ backtrace: [<ffffffff81a27201>] kvmalloc_node+0x61/0xf0 [<ffffffff8706eec7>] alloc_netdev_mqs+0x777/0xe80 [<ffffffff84e64192>] mkiss_open+0xb2/0x6f0 [1] [<ffffffff842355db>] tty_ldisc_open+0x9b/0x110 [<ffffffff84236488>] tty_set_ldisc+0x2e8/0x670 [<ffffffff8421f7f3>] tty_ioctl+0xda3/0x1440 [<ffffffff81c9f273>] __x64_sys_ioctl+0x193/0x200 [<ffffffff8911263a>] do_syscall_64+0x3a/0xb0 [<ffffffff89200068>] entry_SYSCALL_64_after_hwframe+0x44/0xae

BUG: memory leak unreferenced object 0xffff888029b2b200 (size 256): comm "syz-executor.1", pid 11443, jiffies 4295046091 (age 17.660s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<ffffffff81a27201>] kvmalloc_node+0x61/0xf0 [<ffffffff8706f062>] alloc_netdev_mqs+0x912/0xe80 [<ffffffff84e64192>] mkiss_open+0xb2/0x6f0 [1] [<ffffffff842355db>] tty_ldisc_open+0x9b/0x110 [<ffffffff84236488>] tty_set_ldisc+0x2e8/0x670 [<ffffffff8421f7f3>] tty_ioctl+0xda3/0x1440 [<ffffffff81c9f273>] __x64_sys_ioctl+0x193/0x200 [<ffffffff8911263a>] do_syscall_64+0x3a/0xb0 [<ffffffff89200068>] entry_SYSCALL_64_after_hwframe+0x44/0xae

Fixes: 815f62bf7427 ("[PATCH] SMP rewrite of mkiss") Signed-off-by: Pavel Skripkin paskripkin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/hamradio/mkiss.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index 17be2bb2985c..920e9f888cc3 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -799,6 +799,7 @@ static void mkiss_close(struct tty_struct *tty) ax->tty = NULL;

unregister_netdev(ax->dev); + free_netdev(ax->dev); }

/* Perform I/O control on an active ax25 channel. */

From: Pavel Machek pavel@denx.de

[ Upstream commit 39eb028183bc7378bb6187067e20bf6d8c836407 ]

While fixing coverity warning, commit dd2c79677375 introduced typo in shift value. Fix that.

Signed-off-by: Pavel Machek (CIP) pavel@denx.de Fixes: dd2c79677375 ("cxgb4: Fix unintentional sign extension issues") Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c index e664e05b9f02..5fbc087268db 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c @@ -198,7 +198,7 @@ static void set_nat_params(struct adapter *adap, struct filter_entry *f, WORD_MASK, f->fs.nat_lip[3] | f->fs.nat_lip[2] << 8 | f->fs.nat_lip[1] << 16 | - (u64)f->fs.nat_lip[0] << 25, 1); + (u64)f->fs.nat_lip[0] << 24, 1); } }

From: Rukhsana Ansari rukhsana.ansari@broadcom.com

[ Upstream commit c12e1643d2738bcd4e26252ce531878841dd3f38 ]

TQM fastpath ring needs to be sized to store both the requester and responder side of RoCE QPs in TQM for supporting bi-directional tests. Fix bnxt_alloc_ctx_mem() to multiply the RoCE QPs by a factor of 2 when computing the number of entries for TQM fastpath ring. This fixes an RX pipeline stall issue when running bi-directional max RoCE QP tests.

Fixes: c7dd7ab4b204 ("bnxt_en: Improve TQM ring context memory sizing formulas.") Signed-off-by: Rukhsana Ansari rukhsana.ansari@broadcom.com Signed-off-by: Michael Chan michael.chan@broadcom.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index e9ac20c1c389..48c19602a0f3 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -7295,7 +7295,7 @@ skip_rdma: entries_sp = ctx->vnic_max_vnic_entries + ctx->qp_max_l2_entries + 2 * (extra_qps + ctx->qp_min_qp1_entries) + min; entries_sp = roundup(entries_sp, ctx->tqm_entries_multiple); - entries = ctx->qp_max_l2_entries + extra_qps + ctx->qp_min_qp1_entries; + entries = ctx->qp_max_l2_entries + 2 * (extra_qps + ctx->qp_min_qp1_entries); entries = roundup(entries, ctx->tqm_entries_multiple); entries = clamp_t(u32, entries, min, ctx->tqm_max_entries_per_ring); for (i = 0; i < ctx->tqm_fp_rings_count + 1; i++) {

From: Toke Høiland-Jørgensen toke@redhat.com

[ Upstream commit 321827477360934dc040e9d3c626bf1de6c3ab3c ]

When constructing ICMP response messages, the kernel will try to pick a suitable source address for the outgoing packet. However, if no IPv4 addresses are configured on the system at all, this will fail and we end up producing an ICMP message with a source address of 0.0.0.0. This can happen on a box routing IPv4 traffic via v6 nexthops, for instance.

Since 0.0.0.0 is not generally routable on the internet, there's a good chance that such ICMP messages will never make it back to the sender of the original packet that the ICMP message was sent in response to. This, in turn, can create connectivity and PMTUd problems for senders. Fortunately, RFC7600 reserves a dummy address to be used as a source for ICMP messages (192.0.0.8/32), so let's teach the kernel to substitute that address as a last resort if the regular source address selection procedure fails.

Below is a quick example reproducing this issue with network namespaces:

ip netns add ns0 ip l add type veth peer netns ns0 ip l set dev veth0 up ip a add 10.0.0.1/24 dev veth0 ip a add fc00:dead:cafe:42::1/64 dev veth0 ip r add 10.1.0.0/24 via inet6 fc00:dead:cafe:42::2 ip -n ns0 l set dev veth0 up ip -n ns0 a add fc00:dead:cafe:42::2/64 dev veth0 ip -n ns0 r add 10.0.0.0/24 via inet6 fc00:dead:cafe:42::1 ip netns exec ns0 sysctl -w net.ipv4.icmp_ratelimit=0 ip netns exec ns0 sysctl -w net.ipv4.ip_forward=1 tcpdump -tpni veth0 -c 2 icmp & ping -w 1 10.1.0.1 > /dev/null tcpdump: verbose output suppressed, use -v[v]... for full protocol decode listening on veth0, link-type EN10MB (Ethernet), snapshot length 262144 bytes IP 10.0.0.1 > 10.1.0.1: ICMP echo request, id 29, seq 1, length 64 IP 0.0.0.0 > 10.0.0.1: ICMP net 10.1.0.1 unreachable, length 92 2 packets captured 2 packets received by filter 0 packets dropped by kernel

With this patch the above capture changes to: IP 10.0.0.1 > 10.1.0.1: ICMP echo request, id 31127, seq 1, length 64 IP 192.0.0.8 > 10.0.0.1: ICMP net 10.1.0.1 unreachable, length 92

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Juliusz Chroboczek jch@irif.fr Reviewed-by: David Ahern dsahern@kernel.org Signed-off-by: Toke Høiland-Jørgensen toke@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- include/uapi/linux/in.h | 3 +++ net/ipv4/icmp.c | 7 +++++++ 2 files changed, 10 insertions(+)

diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index 7d6687618d80..d1b327036ae4 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -289,6 +289,9 @@ struct sockaddr_in { /* Address indicating an error return. */ #define INADDR_NONE ((unsigned long int) 0xffffffff)

+/* Dummy address for src of ICMP replies if no real address is set (RFC7600). */ +#define INADDR_DUMMY ((unsigned long int) 0xc0000008) + /* Network number for local host loopback. */ #define IN_LOOPBACKNET 127

diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 616e2dc1c8fa..cd65d3146c30 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -759,6 +759,13 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, icmp_param.data_len = room; icmp_param.head_len = sizeof(struct icmphdr);

+ /* if we don't have a source address at this point, fall back to the + * dummy address instead of sending out a packet with a source address + * of 0.0.0.0 + */ + if (!fl4.saddr) + fl4.saddr = htonl(INADDR_DUMMY); + icmp_push_reply(&icmp_param, &fl4, &ipc, &rt); ende: ip_rt_put(rt);

From: Axel Lin axel.lin@ingics.com

[ Upstream commit 3d681804efcb6e5d8089a433402e19179347d7ae ]

Show proper error code instead of 0.

Signed-off-by: Axel Lin axel.lin@ingics.com Link: https://lore.kernel.org/r/20210512075824.620580-1-axel.lin@ingics.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/regulator/cros-ec-regulator.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/regulator/cros-ec-regulator.c b/drivers/regulator/cros-ec-regulator.c index eb3fc1db4edc..c4754f3cf233 100644 --- a/drivers/regulator/cros-ec-regulator.c +++ b/drivers/regulator/cros-ec-regulator.c @@ -225,8 +225,9 @@ static int cros_ec_regulator_probe(struct platform_device *pdev)

drvdata->dev = devm_regulator_register(dev, &drvdata->desc, &cfg); if (IS_ERR(drvdata->dev)) { + ret = PTR_ERR(drvdata->dev); dev_err(&pdev->dev, "Failed to register regulator: %d\n", ret); - return PTR_ERR(drvdata->dev); + return ret; }

platform_set_drvdata(pdev, drvdata);

From: Axel Lin axel.lin@ingics.com

[ Upstream commit 0514582a1a5b4ac1a3fd64792826d392d7ae9ddc ]

The valid selectors for bd70528 bucks are 0 ~ 0xf, so the .n_voltages should be 16 (0x10). Use 0x10 to make it consistent with BD70528_LDO_VOLTS. Also remove redundant defines for BD70528_BUCK_VOLTS.

Signed-off-by: Axel Lin axel.lin@ingics.com Acked-by: Matti Vaittinen matti.vaittinen@fi.rohmeurope.com Link: https://lore.kernel.org/r/20210523071045.2168904-1-axel.lin@ingics.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/mfd/rohm-bd70528.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/include/linux/mfd/rohm-bd70528.h b/include/linux/mfd/rohm-bd70528.h index a57af878fd0c..4a5966475a35 100644 --- a/include/linux/mfd/rohm-bd70528.h +++ b/include/linux/mfd/rohm-bd70528.h @@ -26,9 +26,7 @@ struct bd70528_data { struct mutex rtc_timer_lock; };

-#define BD70528_BUCK_VOLTS 17 -#define BD70528_BUCK_VOLTS 17 -#define BD70528_BUCK_VOLTS 17 +#define BD70528_BUCK_VOLTS 0x10 #define BD70528_LDO_VOLTS 0x20

#define BD70528_REG_BUCK1_EN 0x0F

From: Jack Yu jack.yu@realtek.com

[ Upstream commit 6308c44ed6eeadf65c0a7ba68d609773ed860fbb ]

The power of "LDO2", "MICBIAS1" and "Mic Det Power" were powered off after the DAPM widgets were added, and these powers were set by the JD settings "RT5659_JD_HDA_HEADER" in the probe function. In the codec probe function, these powers were ignored to prevent them controlled by DAPM.

Signed-off-by: Oder Chiou oder_chiou@realtek.com Signed-off-by: Jack Yu jack.yu@realtek.com Message-Id: 15fced51977b458798ca4eebf03dafb9@realtek.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/codecs/rt5659.c | 26 +++++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-)

diff --git a/sound/soc/codecs/rt5659.c b/sound/soc/codecs/rt5659.c index 91a4ef7f620c..a9b079d56fd6 100644 --- a/sound/soc/codecs/rt5659.c +++ b/sound/soc/codecs/rt5659.c @@ -2433,13 +2433,18 @@ static int set_dmic_power(struct snd_soc_dapm_widget *w, return 0; }

-static const struct snd_soc_dapm_widget rt5659_dapm_widgets[] = { +static const struct snd_soc_dapm_widget rt5659_particular_dapm_widgets[] = { SND_SOC_DAPM_SUPPLY("LDO2", RT5659_PWR_ANLG_3, RT5659_PWR_LDO2_BIT, 0, NULL, 0), - SND_SOC_DAPM_SUPPLY("PLL", RT5659_PWR_ANLG_3, RT5659_PWR_PLL_BIT, 0, - NULL, 0), + SND_SOC_DAPM_SUPPLY("MICBIAS1", RT5659_PWR_ANLG_2, RT5659_PWR_MB1_BIT, + 0, NULL, 0), SND_SOC_DAPM_SUPPLY("Mic Det Power", RT5659_PWR_VOL, RT5659_PWR_MIC_DET_BIT, 0, NULL, 0), +}; + +static const struct snd_soc_dapm_widget rt5659_dapm_widgets[] = { + SND_SOC_DAPM_SUPPLY("PLL", RT5659_PWR_ANLG_3, RT5659_PWR_PLL_BIT, 0, + NULL, 0), SND_SOC_DAPM_SUPPLY("Mono Vref", RT5659_PWR_ANLG_1, RT5659_PWR_VREF3_BIT, 0, NULL, 0),

@@ -2464,8 +2469,6 @@ static const struct snd_soc_dapm_widget rt5659_dapm_widgets[] = { RT5659_ADC_MONO_R_ASRC_SFT, 0, NULL, 0),

/* Input Side */ - SND_SOC_DAPM_SUPPLY("MICBIAS1", RT5659_PWR_ANLG_2, RT5659_PWR_MB1_BIT, - 0, NULL, 0), SND_SOC_DAPM_SUPPLY("MICBIAS2", RT5659_PWR_ANLG_2, RT5659_PWR_MB2_BIT, 0, NULL, 0), SND_SOC_DAPM_SUPPLY("MICBIAS3", RT5659_PWR_ANLG_2, RT5659_PWR_MB3_BIT, @@ -3660,10 +3663,23 @@ static int rt5659_set_bias_level(struct snd_soc_component *component,

static int rt5659_probe(struct snd_soc_component *component) { + struct snd_soc_dapm_context *dapm = + snd_soc_component_get_dapm(component); struct rt5659_priv *rt5659 = snd_soc_component_get_drvdata(component);

rt5659->component = component;

+ switch (rt5659->pdata.jd_src) { + case RT5659_JD_HDA_HEADER: + break; + + default: + snd_soc_dapm_new_controls(dapm, + rt5659_particular_dapm_widgets, + ARRAY_SIZE(rt5659_particular_dapm_widgets)); + break; + } + return 0; }

From: Nicolas Cavallari nicolas.cavallari@green-communications.fr

[ Upstream commit a8437f05384cb472518ec21bf4fffbe8f0a47378 ]

Otherwise, when compiled as module, a WARN_ON is triggered:

WARNING: CPU: 0 PID: 5 at sound/core/init.c:208 snd_card_new+0x310/0x39c [snd] [...] CPU: 0 PID: 5 Comm: kworker/0:0 Not tainted 5.10.39 #1 Hardware name: Freescale i.MX6 Quad/DualLite (Device Tree) Workqueue: events deferred_probe_work_func [<c0111988>] (unwind_backtrace) from [<c010c8ac>] (show_stack+0x10/0x14) [<c010c8ac>] (show_stack) from [<c092784c>] (dump_stack+0xdc/0x104) [<c092784c>] (dump_stack) from [<c0129710>] (__warn+0xd8/0x114) [<c0129710>] (__warn) from [<c0922a48>] (warn_slowpath_fmt+0x5c/0xc4) [<c0922a48>] (warn_slowpath_fmt) from [<bf0496f8>] (snd_card_new+0x310/0x39c [snd]) [<bf0496f8>] (snd_card_new [snd]) from [<bf1d7df8>] (snd_soc_bind_card+0x334/0x9c4 [snd_soc_core]) [<bf1d7df8>] (snd_soc_bind_card [snd_soc_core]) from [<bf1e9cd8>] (devm_snd_soc_register_card+0x30/0x6c [snd_soc_core]) [<bf1e9cd8>] (devm_snd_soc_register_card [snd_soc_core]) from [<bf22d964>] (fsl_asoc_card_probe+0x550/0xcc8 [snd_soc_fsl_asoc_card]) [<bf22d964>] (fsl_asoc_card_probe [snd_soc_fsl_asoc_card]) from [<c060c930>] (platform_drv_probe+0x48/0x98) [...]

Signed-off-by: Nicolas Cavallari nicolas.cavallari@green-communications.fr Acked-by: Shengjiu Wang shengjiu.wang@gmail.com Link: https://lore.kernel.org/r/20210527163409.22049-1-nicolas.cavallari@green-com... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/fsl/fsl-asoc-card.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/sound/soc/fsl/fsl-asoc-card.c b/sound/soc/fsl/fsl-asoc-card.c index f62f81ceab0d..9dcbe5d5a428 100644 --- a/sound/soc/fsl/fsl-asoc-card.c +++ b/sound/soc/fsl/fsl-asoc-card.c @@ -732,6 +732,7 @@ static int fsl_asoc_card_probe(struct platform_device *pdev) /* Initialize sound card */ priv->pdev = pdev; priv->card.dev = &pdev->dev; + priv->card.owner = THIS_MODULE; ret = snd_soc_of_parse_card_name(&priv->card, "model"); if (ret) { snprintf(priv->name, sizeof(priv->name), "%s-audio",

From: ChiYuan Huang cy_huang@richtek.com

[ Upstream commit 46639a5e684edd0b80ae9dff220f193feb356277 ]

- Fix to make regcache value first reading back from HW.

Signed-off-by: ChiYuan Huang cy_huang@richtek.com Link: https://lore.kernel.org/r/1622542155-6373-1-git-send-email-u0084500@gmail.co... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/regulator/rtmv20-regulator.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/regulator/rtmv20-regulator.c b/drivers/regulator/rtmv20-regulator.c index 5adc552dffd5..4bca64de0f67 100644 --- a/drivers/regulator/rtmv20-regulator.c +++ b/drivers/regulator/rtmv20-regulator.c @@ -27,6 +27,7 @@ #define RTMV20_REG_LDIRQ 0x30 #define RTMV20_REG_LDSTAT 0x40 #define RTMV20_REG_LDMASK 0x50 +#define RTMV20_MAX_REGS (RTMV20_REG_LDMASK + 1)

#define RTMV20_VID_MASK GENMASK(7, 4) #define RICHTEK_VID 0x80 @@ -313,6 +314,7 @@ static const struct regmap_config rtmv20_regmap_config = { .val_bits = 8, .cache_type = REGCACHE_RBTREE, .max_register = RTMV20_REG_LDMASK, + .num_reg_defaults_raw = RTMV20_MAX_REGS,

.writeable_reg = rtmv20_is_accessible_reg, .readable_reg = rtmv20_is_accessible_reg,

From: Vincent Guittot vincent.guittot@linaro.org

[ Upstream commit fcf6631f3736985ec89bdd76392d3c7bfb60119f ]

Rounding in PELT calculation happening when entities are attached/detached of a cfs_rq can result into situations where util/runnable_avg is not null but util/runnable_sum is. This is normally not possible so we need to ensure that util/runnable_sum stays synced with util/runnable_avg.

detach_entity_load_avg() is the last place where we don't sync util/runnable_sum with util/runnbale_avg when moving some sched_entities

Signed-off-by: Vincent Guittot vincent.guittot@linaro.org Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/20210601085832.12626-1-vincent.guittot@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/sched/fair.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 487312a5ceab..47fcc3fe9dc5 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3760,11 +3760,17 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s */ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { + /* + * cfs_rq->avg.period_contrib can be used for both cfs_rq and se. + * See ___update_load_avg() for details. + */ + u32 divider = get_pelt_divider(&cfs_rq->avg); + dequeue_load_avg(cfs_rq, se); sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg); - sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum); + cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * divider; sub_positive(&cfs_rq->avg.runnable_avg, se->avg.runnable_avg); - sub_positive(&cfs_rq->avg.runnable_sum, se->avg.runnable_sum); + cfs_rq->avg.runnable_sum = cfs_rq->avg.runnable_avg * divider;

add_tg_cfs_propagate(cfs_rq, -se->avg.load_sum);

From: Axel Lin axel.lin@ingics.com

[ Upstream commit 50bec7fb4cb1bcf9d387046b6dec7186590791ec ]

Take ldo3_voltages as example, the ARRAY_SIZE(ldo3_voltages) is 16. i.e. the valid selector is 0 ~ 0xF. But in current code the vsel_mask is "(1 << 15) - 1", i.e. 0x7FFF. Fix it.

Signed-off-by: Axel Lin axel.lin@ingics.com Link: https://lore.kernel.org/r/20210529013236.373847-1-axel.lin@ingics.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/staging/hikey9xx/hi6421v600-regulator.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/hikey9xx/hi6421v600-regulator.c b/drivers/staging/hikey9xx/hi6421v600-regulator.c index f6a14e9c3cbf..e10fe3058176 100644 --- a/drivers/staging/hikey9xx/hi6421v600-regulator.c +++ b/drivers/staging/hikey9xx/hi6421v600-regulator.c @@ -83,7 +83,7 @@ static const unsigned int ldo34_voltages[] = { .owner = THIS_MODULE, \ .volt_table = vtable, \ .n_voltages = ARRAY_SIZE(vtable), \ - .vsel_mask = (1 << (ARRAY_SIZE(vtable) - 1)) - 1, \ + .vsel_mask = ARRAY_SIZE(vtable) - 1, \ .vsel_reg = vreg, \ .enable_reg = ereg, \ .enable_mask = emask, \

From: Axel Lin axel.lin@ingics.com

[ Upstream commit cb2381cbecb81a8893b2d1e1af29bc2e5531df27 ]

devm_gpiod_get_array_optional may return NULL if no GPIO was assigned.

Signed-off-by: Axel Lin axel.lin@ingics.com Link: https://lore.kernel.org/r/20210603094944.1114156-1-axel.lin@ingics.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/regulator/rt4801-regulator.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/regulator/rt4801-regulator.c b/drivers/regulator/rt4801-regulator.c index 2055a9cb13ba..7a87788d3f09 100644 --- a/drivers/regulator/rt4801-regulator.c +++ b/drivers/regulator/rt4801-regulator.c @@ -66,7 +66,7 @@ static int rt4801_enable(struct regulator_dev *rdev) struct gpio_descs *gpios = priv->enable_gpios; int id = rdev_get_id(rdev), ret;

- if (gpios->ndescs <= id) { + if (!gpios || gpios->ndescs <= id) { dev_warn(&rdev->dev, "no dedicated gpio can control\n"); goto bypass_gpio; } @@ -88,7 +88,7 @@ static int rt4801_disable(struct regulator_dev *rdev) struct gpio_descs *gpios = priv->enable_gpios; int id = rdev_get_id(rdev);

- if (gpios->ndescs <= id) { + if (!gpios || gpios->ndescs <= id) { dev_warn(&rdev->dev, "no dedicated gpio can control\n"); goto bypass_gpio; }

From: Sergio Paracuellos sergio.paracuellos@gmail.com

[ Upstream commit eb367d875f94a228c17c8538e3f2efcf2eb07ead ]

In 'rt2880_pmx_group_enable' driver is printing an error and returning -EBUSY if a pin has been already enabled. This begets anoying messages in the caller when this happens like the following:

rt2880-pinmux pinctrl: pcie is already enabled mt7621-pci 1e140000.pcie: Error applying setting, reverse things back

To avoid this just print the already enabled message in the pinctrl driver and return 0 instead to not confuse the user with a real bad problem.

Signed-off-by: Sergio Paracuellos sergio.paracuellos@gmail.com Link: https://lore.kernel.org/r/20210604055337.20407-1-sergio.paracuellos@gmail.co... Signed-off-by: Linus Walleij linus.walleij@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/pinctrl/ralink/pinctrl-rt2880.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/ralink/pinctrl-rt2880.c b/drivers/pinctrl/ralink/pinctrl-rt2880.c index 1f4bca854add..a9b511c7e850 100644 --- a/drivers/pinctrl/ralink/pinctrl-rt2880.c +++ b/drivers/pinctrl/ralink/pinctrl-rt2880.c @@ -127,7 +127,7 @@ static int rt2880_pmx_group_enable(struct pinctrl_dev *pctrldev, if (p->groups[group].enabled) { dev_err(p->dev, "%s is already enabled\n", p->groups[group].name); - return -EBUSY; + return 0; }

p->groups[group].enabled = 1;

From: Srinivasa Rao Mandadapu srivasam@codeaurora.org

[ Upstream commit c8a4556d98510ca05bad8d02265a4918b03a8c0b ]

This patch fixes PoP noise of around 15ms observed during audio capture begin. Enables BCLK and LRCLK in snd_soc_dai_ops prepare call for introducing some delay before capture start.

(am from https://patchwork.kernel.org/patch/12276369/) (also found at https://lore.kernel.org/r/20210524142114.18676-1-srivasam@codeaurora.org)

Co-developed-by: Judy Hsiao judyhsiao@chromium.org Signed-off-by: Judy Hsiao judyhsiao@chromium.org Signed-off-by: Srinivasa Rao Mandadapu srivasam@codeaurora.org Reviewed-by: Srinivas Kandagatla srinivas.kandagatla@linaro.org Link: https://lore.kernel.org/r/20210604154545.1198337-1-judyhsiao@chromium.org Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/qcom/lpass-cpu.c | 79 ++++++++++++++++++++++++++++++++++++++ sound/soc/qcom/lpass.h | 4 ++ 2 files changed, 83 insertions(+)

diff --git a/sound/soc/qcom/lpass-cpu.c b/sound/soc/qcom/lpass-cpu.c index 936384a94f25..74d3d8c58608 100644 --- a/sound/soc/qcom/lpass-cpu.c +++ b/sound/soc/qcom/lpass-cpu.c @@ -93,8 +93,30 @@ static void lpass_cpu_daiops_shutdown(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { struct lpass_data *drvdata = snd_soc_dai_get_drvdata(dai); + struct lpaif_i2sctl *i2sctl = drvdata->i2sctl; + unsigned int id = dai->driver->id;

clk_disable_unprepare(drvdata->mi2s_osr_clk[dai->driver->id]); + /* + * Ensure LRCLK is disabled even in device node validation. + * Will not impact if disabled in lpass_cpu_daiops_trigger() + * suspend. + */ + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) + regmap_fields_write(i2sctl->spken, id, LPAIF_I2SCTL_SPKEN_DISABLE); + else + regmap_fields_write(i2sctl->micen, id, LPAIF_I2SCTL_MICEN_DISABLE); + + /* + * BCLK may not be enabled if lpass_cpu_daiops_prepare is called before + * lpass_cpu_daiops_shutdown. It's paired with the clk_enable in + * lpass_cpu_daiops_prepare. + */ + if (drvdata->mi2s_was_prepared[dai->driver->id]) { + drvdata->mi2s_was_prepared[dai->driver->id] = false; + clk_disable(drvdata->mi2s_bit_clk[dai->driver->id]); + } + clk_unprepare(drvdata->mi2s_bit_clk[dai->driver->id]); }

@@ -275,6 +297,18 @@ static int lpass_cpu_daiops_trigger(struct snd_pcm_substream *substream, case SNDRV_PCM_TRIGGER_START: case SNDRV_PCM_TRIGGER_RESUME: case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: + /* + * Ensure lpass BCLK/LRCLK is enabled during + * device resume as lpass_cpu_daiops_prepare() is not called + * after the device resumes. We don't check mi2s_was_prepared before + * enable/disable BCLK in trigger events because: + * 1. These trigger events are paired, so the BCLK + * enable_count is balanced. + * 2. the BCLK can be shared (ex: headset and headset mic), + * we need to increase the enable_count so that we don't + * turn off the shared BCLK while other devices are using + * it. + */ if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { ret = regmap_fields_write(i2sctl->spken, id, LPAIF_I2SCTL_SPKEN_ENABLE); @@ -296,6 +330,10 @@ static int lpass_cpu_daiops_trigger(struct snd_pcm_substream *substream, case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_SUSPEND: case SNDRV_PCM_TRIGGER_PAUSE_PUSH: + /* + * To ensure lpass BCLK/LRCLK is disabled during + * device suspend. + */ if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { ret = regmap_fields_write(i2sctl->spken, id, LPAIF_I2SCTL_SPKEN_DISABLE); @@ -315,12 +353,53 @@ static int lpass_cpu_daiops_trigger(struct snd_pcm_substream *substream, return ret; }

+static int lpass_cpu_daiops_prepare(struct snd_pcm_substream *substream, + struct snd_soc_dai *dai) +{ + struct lpass_data *drvdata = snd_soc_dai_get_drvdata(dai); + struct lpaif_i2sctl *i2sctl = drvdata->i2sctl; + unsigned int id = dai->driver->id; + int ret; + + /* + * Ensure lpass BCLK/LRCLK is enabled bit before playback/capture + * data flow starts. This allows other codec to have some delay before + * the data flow. + * (ex: to drop start up pop noise before capture starts). + */ + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) + ret = regmap_fields_write(i2sctl->spken, id, LPAIF_I2SCTL_SPKEN_ENABLE); + else + ret = regmap_fields_write(i2sctl->micen, id, LPAIF_I2SCTL_MICEN_ENABLE); + + if (ret) { + dev_err(dai->dev, "error writing to i2sctl reg: %d\n", ret); + return ret; + } + + /* + * Check mi2s_was_prepared before enabling BCLK as lpass_cpu_daiops_prepare can + * be called multiple times. It's paired with the clk_disable in + * lpass_cpu_daiops_shutdown. + */ + if (!drvdata->mi2s_was_prepared[dai->driver->id]) { + ret = clk_enable(drvdata->mi2s_bit_clk[id]); + if (ret) { + dev_err(dai->dev, "error in enabling mi2s bit clk: %d\n", ret); + return ret; + } + drvdata->mi2s_was_prepared[dai->driver->id] = true; + } + return 0; +} + const struct snd_soc_dai_ops asoc_qcom_lpass_cpu_dai_ops = { .set_sysclk = lpass_cpu_daiops_set_sysclk, .startup = lpass_cpu_daiops_startup, .shutdown = lpass_cpu_daiops_shutdown, .hw_params = lpass_cpu_daiops_hw_params, .trigger = lpass_cpu_daiops_trigger, + .prepare = lpass_cpu_daiops_prepare, }; EXPORT_SYMBOL_GPL(asoc_qcom_lpass_cpu_dai_ops);

diff --git a/sound/soc/qcom/lpass.h b/sound/soc/qcom/lpass.h index 83b2e08ade06..7f72214404ba 100644 --- a/sound/soc/qcom/lpass.h +++ b/sound/soc/qcom/lpass.h @@ -67,6 +67,10 @@ struct lpass_data { /* MI2S SD lines to use for playback/capture */ unsigned int mi2s_playback_sd_mode[LPASS_MAX_MI2S_PORTS]; unsigned int mi2s_capture_sd_mode[LPASS_MAX_MI2S_PORTS]; + + /* The state of MI2S prepare dai_ops was called */ + bool mi2s_was_prepared[LPASS_MAX_MI2S_PORTS]; + int hdmi_port_enable;

/* low-power audio interface (LPAIF) registers */

From: Riwen Lu luriwen@kylinos.cn

[ Upstream commit 78d13552346289bad4a9bf8eabb5eec5e5a321a5 ]

The scpi hwmon shows the sub-zero temperature in an unsigned integer, which would confuse the users when the machine works in low temperature environment. This shows the sub-zero temperature in an signed value and users can get it properly from sensors.

Signed-off-by: Riwen Lu luriwen@kylinos.cn Tested-by: Xin Chen chenxin@kylinos.cn Link: https://lore.kernel.org/r/20210604030959.736379-1-luriwen@kylinos.cn Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hwmon/scpi-hwmon.c | 9 +++++++++ 1 file changed, 9 insertions(+)

diff --git a/drivers/hwmon/scpi-hwmon.c b/drivers/hwmon/scpi-hwmon.c index 25aac40f2764..919877970ae3 100644 --- a/drivers/hwmon/scpi-hwmon.c +++ b/drivers/hwmon/scpi-hwmon.c @@ -99,6 +99,15 @@ scpi_show_sensor(struct device *dev, struct device_attribute *attr, char *buf)

scpi_scale_reading(&value, sensor);

+ /* + * Temperature sensor values are treated as signed values based on + * observation even though that is not explicitly specified, and + * because an unsigned u64 temperature does not really make practical + * sense especially when the temperature is below zero degrees Celsius. + */ + if (sensor->info.class == TEMPERATURE) + return sprintf(buf, "%lld\n", (s64)value); + return sprintf(buf, "%llu\n", value); }

From: Feng Tang feng.tang@intel.com

[ Upstream commit 2e3025434a6ba090c85871a1d4080ff784109e1f ]

0day robot reported a 9.2% regression for will-it-scale mmap1 test case[1], caused by commit 57efa1fe5957 ("mm/gup: prevent gup_fast from racing with COW during fork").

Further debug shows the regression is due to that commit changes the offset of hot fields 'mmap_lock' inside structure 'mm_struct', thus some cache alignment changes.

From the perf data, the contention for 'mmap_lock' is very severe and

takes around 95% cpu cycles, and it is a rw_semaphore

struct rw_semaphore { atomic_long_t count; /* 8 bytes */ atomic_long_t owner; /* 8 bytes */ struct optimistic_spin_queue osq; /* spinner MCS lock */ ...

Before commit 57efa1fe5957 adds the 'write_protect_seq', it happens to have a very optimal cache alignment layout, as Linus explained:

"and before the addition of the 'write_protect_seq' field, the mmap_sem was at offset 120 in 'struct mm_struct'.

Which meant that count and owner were in two different cachelines, and then when you have contention and spend time in rwsem_down_write_slowpath(), this is probably *exactly* the kind of layout you want.

Because first the rwsem_write_trylock() will do a cmpxchg on the first cacheline (for the optimistic fast-path), and then in the case of contention, rwsem_down_write_slowpath() will just access the second cacheline.

Which is probably just optimal for a load that spends a lot of time contended - new waiters touch that first cacheline, and then they queue themselves up on the second cacheline."

After the commit, the rw_semaphore is at offset 128, which means the 'count' and 'owner' fields are now in the same cacheline, and causes more cache bouncing.

Currently there are 3 "#ifdef CONFIG_XXX" before 'mmap_lock' which will affect its offset:

CONFIG_MMU CONFIG_MEMBARRIER CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES

The layout above is on 64 bits system with 0day's default kernel config (similar to RHEL-8.3's config), in which all these 3 options are 'y'. And the layout can vary with different kernel configs.

Relayouting a structure is usually a double-edged sword, as sometimes it can helps one case, but hurt other cases. For this case, one solution is, as the newly added 'write_protect_seq' is a 4 bytes long seqcount_t (when CONFIG_DEBUG_LOCK_ALLOC=n), placing it into an existing 4 bytes hole in 'mm_struct' will not change other fields' alignment, while restoring the regression.

Link: https://lore.kernel.org/lkml/20210525031636.GB7744@xsang-OptiPlex-9020/ [1] Reported-by: kernel test robot oliver.sang@intel.com Signed-off-by: Feng Tang feng.tang@intel.com Reviewed-by: John Hubbard jhubbard@nvidia.com Reviewed-by: Jason Gunthorpe jgg@nvidia.com Cc: Peter Xu peterx@redhat.com Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/mm_types.h | 27 ++++++++++++++++++++------- 1 file changed, 20 insertions(+), 7 deletions(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 5aacc1c10a45..8f0fb62e8975 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -445,13 +445,6 @@ struct mm_struct { */ atomic_t has_pinned;

- /** - * @write_protect_seq: Locked when any thread is write - * protecting pages mapped by this mm to enforce a later COW, - * for instance during page table copying for fork(). - */ - seqcount_t write_protect_seq; - #ifdef CONFIG_MMU atomic_long_t pgtables_bytes; /* PTE page table pages */ #endif @@ -460,6 +453,18 @@ struct mm_struct { spinlock_t page_table_lock; /* Protects page tables and some * counters */ + /* + * With some kernel config, the current mmap_lock's offset + * inside 'mm_struct' is at 0x120, which is very optimal, as + * its two hot fields 'count' and 'owner' sit in 2 different + * cachelines, and when mmap_lock is highly contended, both + * of the 2 fields will be accessed frequently, current layout + * will help to reduce cache bouncing. + * + * So please be careful with adding new fields before + * mmap_lock, which can easily push the 2 fields into one + * cacheline. + */ struct rw_semaphore mmap_lock;

struct list_head mmlist; /* List of maybe swapped mm's. These @@ -480,7 +485,15 @@ struct mm_struct { unsigned long stack_vm; /* VM_STACK */ unsigned long def_flags;

+ /** + * @write_protect_seq: Locked when any thread is write + * protecting pages mapped by this mm to enforce a later COW, + * for instance during page table copying for fork(). + */ + seqcount_t write_protect_seq; + spinlock_t arg_lock; /* protect the below fields */ + unsigned long start_code, end_code, start_data, end_data; unsigned long start_brk, brk, start_stack; unsigned long arg_start, arg_end, env_start, env_end;

From: Odin Ugedal odin@uged.al

[ Upstream commit a7b359fc6a37faaf472125867c8dc5a068c90982 ]

Fix an issue where fairness is decreased since cfs_rq's can end up not being decayed properly. For two sibling control groups with the same priority, this can often lead to a load ratio of 99/1 (!!).

This happens because when a cfs_rq is throttled, all the descendant cfs_rq's will be removed from the leaf list. When they initial cfs_rq is unthrottled, it will currently only re add descendant cfs_rq's if they have one or more entities enqueued. This is not a perfect heuristic.

Instead, we insert all cfs_rq's that contain one or more enqueued entities, or it its load is not completely decayed.

Can often lead to situations like this for equally weighted control groups:

$ ps u -C stress USER PID %CPU %MEM VSZ RSS TTY STAT START TIME COMMAND root 10009 88.8 0.0 3676 100 pts/1 R+ 11:04 0:13 stress --cpu 1 root 10023 3.0 0.0 3676 104 pts/1 R+ 11:04 0:00 stress --cpu 1

Fixes: 31bc6aeaab1d ("sched/fair: Optimize update_blocked_averages()") [vingo: !SMP build fix] Signed-off-by: Odin Ugedal odin@uged.al Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Reviewed-by: Vincent Guittot vincent.guittot@linaro.org Link: https://lore.kernel.org/r/20210612112815.61678-1-odin@uged.al Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/sched/fair.c | 44 +++++++++++++++++++++++++------------------- 1 file changed, 25 insertions(+), 19 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 47fcc3fe9dc5..56e2334fe66b 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3293,6 +3293,24 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags)

#ifdef CONFIG_SMP #ifdef CONFIG_FAIR_GROUP_SCHED + +static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq) +{ + if (cfs_rq->load.weight) + return false; + + if (cfs_rq->avg.load_sum) + return false; + + if (cfs_rq->avg.util_sum) + return false; + + if (cfs_rq->avg.runnable_sum) + return false; + + return true; +} + /** * update_tg_load_avg - update the tg's load avg * @cfs_rq: the cfs_rq whose avg changed @@ -4086,6 +4104,11 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq)

#else /* CONFIG_SMP */

+static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq) +{ + return true; +} + #define UPDATE_TG 0x0 #define SKIP_AGE_LOAD 0x0 #define DO_ATTACH 0x0 @@ -4744,8 +4767,8 @@ static int tg_unthrottle_up(struct task_group *tg, void *data) cfs_rq->throttled_clock_task_time += rq_clock_task(rq) - cfs_rq->throttled_clock_task;

- /* Add cfs_rq with already running entity in the list */ - if (cfs_rq->nr_running >= 1) + /* Add cfs_rq with load or one or more already running entities to the list */ + if (!cfs_rq_is_decayed(cfs_rq) || cfs_rq->nr_running) list_add_leaf_cfs_rq(cfs_rq); }

@@ -7972,23 +7995,6 @@ static bool __update_blocked_others(struct rq *rq, bool *done)

#ifdef CONFIG_FAIR_GROUP_SCHED

-static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq) -{ - if (cfs_rq->load.weight) - return false; - - if (cfs_rq->avg.load_sum) - return false; - - if (cfs_rq->avg.util_sum) - return false; - - if (cfs_rq->avg.runnable_sum) - return false; - - return true; -} - static bool __update_blocked_fair(struct rq *rq, bool *done) { struct cfs_rq *cfs_rq, *pos;

From: John Garry john.garry@huawei.com

[ Upstream commit fe7a98b9d9b36e5c8a22d76b67d29721f153f66e ]

The error code is not set at all in the sys event iter function.

This may lead to an uninitialized value of "ret" in metricgroup__add_metric() when no CPU metric is added.

Fix by properly setting the error code.

It is not necessary to init "ret" to 0 in metricgroup__add_metric(), as if we have no CPU or sys event metric matching, then "has_match" should be 0 and "ret" is set to -EINVAL.

However gcc cannot detect that it may not have been set after the map_for_each_metric() loop for CPU metrics, which is strange.

Fixes: be335ec28efa8 ("perf metricgroup: Support adding metrics for system PMUs") Signed-off-by: John Garry john.garry@huawei.com Acked-by: Ian Rogers irogers@google.com Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Jiri Olsa jolsa@redhat.com Cc: Kajol Jain kjain@linux.ibm.com Cc: Mark Rutland mark.rutland@arm.com Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Link: http://lore.kernel.org/lkml/1623335580-187317-3-git-send-email-john.garry@hu... Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/util/metricgroup.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 1af71ac1cc68..939aed36e0c2 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -1072,16 +1072,18 @@ static int metricgroup__add_metric_sys_event_iter(struct pmu_event *pe,

ret = add_metric(d->metric_list, pe, d->metric_no_group, &m, NULL, d->ids); if (ret) - return ret; + goto out;

ret = resolve_metric(d->metric_no_group, d->metric_list, NULL, d->ids); if (ret) - return ret; + goto out;

*(d->has_match) = true;

- return *d->ret; +out: + *(d->ret) = ret; + return ret; }

static int metricgroup__add_metric(const char *metric, bool metric_no_group,

From: Daniel Borkmann daniel@iogearbox.net

[ Upstream commit fe9a5ca7e370e613a9a75a13008a3845ea759d6e ]

... in such circumstances, we do not want to mark the instruction as seen given the goal is still to jmp-1 rewrite/sanitize dead code, if it is not reachable from the non-speculative path verification. We do however want to verify it for safety regardless.

With the patch as-is all the insns that have been marked as seen before the patch will also be marked as seen after the patch (just with a potentially different non-zero count). An upcoming patch will also verify paths that are unreachable in the non-speculative domain, hence this extension is needed.

Signed-off-by: Daniel Borkmann daniel@iogearbox.net Reviewed-by: John Fastabend john.fastabend@gmail.com Reviewed-by: Benedict Schlueter benedict.schlueter@rub.de Reviewed-by: Piotr Krysiuk piotras@gmail.com Acked-by: Alexei Starovoitov ast@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/bpf/verifier.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 0ffe85f22887..2423b4e918b9 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6048,6 +6048,19 @@ do_sim: return !ret ? REASON_STACK : 0; }

+static void sanitize_mark_insn_seen(struct bpf_verifier_env *env) +{ + struct bpf_verifier_state *vstate = env->cur_state; + + /* If we simulate paths under speculation, we don't update the + * insn as 'seen' such that when we verify unreachable paths in + * the non-speculative domain, sanitize_dead_code() can still + * rewrite/sanitize them. + */ + if (!vstate->speculative) + env->insn_aux_data[env->insn_idx].seen = env->pass_cnt; +} + static int sanitize_err(struct bpf_verifier_env *env, const struct bpf_insn *insn, int reason, const struct bpf_reg_state *off_reg, @@ -10096,7 +10109,7 @@ static int do_check(struct bpf_verifier_env *env) }

regs = cur_regs(env); - env->insn_aux_data[env->insn_idx].seen = env->pass_cnt; + sanitize_mark_insn_seen(env); prev_insn_idx = env->insn_idx;

if (class == BPF_ALU || class == BPF_ALU64) { @@ -10321,7 +10334,7 @@ process_bpf_exit: return err;

env->insn_idx++; - env->insn_aux_data[env->insn_idx].seen = env->pass_cnt; + sanitize_mark_insn_seen(env); } else { verbose(env, "invalid BPF_LD mode\n"); return -EINVAL; @@ -12098,6 +12111,9 @@ static void free_states(struct bpf_verifier_env *env) * insn_aux_data was touched. These variables are compared to clear temporary * data from failed pass. For testing and experiments do_check_common() can be * run multiple times even when prior attempt to verify is unsuccessful. + * + * Note that special handling is needed on !env->bypass_spec_v1 if this is + * ever called outside of error path with subsequent program rejection. */ static void sanitize_insn_aux_data(struct bpf_verifier_env *env) {

From: Tetsuo Handa penguin-kernel@i-love.sakura.ne.jp

commit 8d0caedb759683041d9db82069937525999ada53 upstream.

syzbot is reporting hung task at register_netdevice_notifier() [1] and unregister_netdevice_notifier() [2], for cleanup_net() might perform time consuming operations while CAN driver's raw/bcm/isotp modules are calling {register,unregister}_netdevice_notifier() on each socket.

Change raw/bcm/isotp modules to call register_netdevice_notifier() from module's __init function and call unregister_netdevice_notifier() from module's __exit function, as with gw/j1939 modules are doing.

Link: https://syzkaller.appspot.com/bug?id=391b9498827788b3cc6830226d4ff5be87107c3... [1] Link: https://syzkaller.appspot.com/bug?id=1724d278c83ca6e6df100a2e320c10d991cf2bc... [2] Link: https://lore.kernel.org/r/54a5f451-05ed-f977-8534-79e7aa2bcc8f@i-love.sakura... Cc: linux-stable stable@vger.kernel.org Reported-by: syzbot syzbot+355f8edb2ff45d5f95fa@syzkaller.appspotmail.com Reported-by: syzbot syzbot+0f1827363a305f74996f@syzkaller.appspotmail.com Reviewed-by: Kirill Tkhai ktkhai@virtuozzo.com Tested-by: syzbot syzbot+355f8edb2ff45d5f95fa@syzkaller.appspotmail.com Tested-by: Oliver Hartkopp socketcan@hartkopp.net Signed-off-by: Tetsuo Handa penguin-kernel@I-love.SAKURA.ne.jp Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/can/bcm.c | 59 +++++++++++++++++++++++++++++++++++++++++------------ net/can/isotp.c | 61 +++++++++++++++++++++++++++++++++++++++++++------------ net/can/raw.c | 62 +++++++++++++++++++++++++++++++++++++++++++------------- 3 files changed, 142 insertions(+), 40 deletions(-)

--- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -125,7 +125,7 @@ struct bcm_sock { struct sock sk; int bound; int ifindex; - struct notifier_block notifier; + struct list_head notifier; struct list_head rx_ops; struct list_head tx_ops; unsigned long dropped_usr_msgs; @@ -133,6 +133,10 @@ struct bcm_sock { char procname [32]; /* inode number in decimal with \0 */ };

+static LIST_HEAD(bcm_notifier_list); +static DEFINE_SPINLOCK(bcm_notifier_lock); +static struct bcm_sock *bcm_busy_notifier; + static inline struct bcm_sock *bcm_sk(const struct sock *sk) { return (struct bcm_sock *)sk; @@ -1381,20 +1385,15 @@ static int bcm_sendmsg(struct socket *so /* * notification handler for netdevice status changes */ -static int bcm_notifier(struct notifier_block *nb, unsigned long msg, - void *ptr) +static void bcm_notify(struct bcm_sock *bo, unsigned long msg, + struct net_device *dev) { - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct bcm_sock *bo = container_of(nb, struct bcm_sock, notifier); struct sock *sk = &bo->sk; struct bcm_op *op; int notify_enodev = 0;

if (!net_eq(dev_net(dev), sock_net(sk))) - return NOTIFY_DONE; - - if (dev->type != ARPHRD_CAN) - return NOTIFY_DONE; + return;

switch (msg) {

@@ -1429,7 +1428,28 @@ static int bcm_notifier(struct notifier_ sk->sk_error_report(sk); } } +}

+static int bcm_notifier(struct notifier_block *nb, unsigned long msg, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + + if (dev->type != ARPHRD_CAN) + return NOTIFY_DONE; + if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN) + return NOTIFY_DONE; + if (unlikely(bcm_busy_notifier)) /* Check for reentrant bug. */ + return NOTIFY_DONE; + + spin_lock(&bcm_notifier_lock); + list_for_each_entry(bcm_busy_notifier, &bcm_notifier_list, notifier) { + spin_unlock(&bcm_notifier_lock); + bcm_notify(bcm_busy_notifier, msg, dev); + spin_lock(&bcm_notifier_lock); + } + bcm_busy_notifier = NULL; + spin_unlock(&bcm_notifier_lock); return NOTIFY_DONE; }

@@ -1449,9 +1469,9 @@ static int bcm_init(struct sock *sk) INIT_LIST_HEAD(&bo->rx_ops);

/* set notifier */ - bo->notifier.notifier_call = bcm_notifier; - - register_netdevice_notifier(&bo->notifier); + spin_lock(&bcm_notifier_lock); + list_add_tail(&bo->notifier, &bcm_notifier_list); + spin_unlock(&bcm_notifier_lock);

return 0; } @@ -1474,7 +1494,14 @@ static int bcm_release(struct socket *so

/* remove bcm_ops, timer, rx_unregister(), etc. */

- unregister_netdevice_notifier(&bo->notifier); + spin_lock(&bcm_notifier_lock); + while (bcm_busy_notifier == bo) { + spin_unlock(&bcm_notifier_lock); + schedule_timeout_uninterruptible(1); + spin_lock(&bcm_notifier_lock); + } + list_del(&bo->notifier); + spin_unlock(&bcm_notifier_lock);

lock_sock(sk);

@@ -1695,6 +1722,10 @@ static struct pernet_operations canbcm_p .exit = canbcm_pernet_exit, };

+static struct notifier_block canbcm_notifier = { + .notifier_call = bcm_notifier +}; + static int __init bcm_module_init(void) { int err; @@ -1708,12 +1739,14 @@ static int __init bcm_module_init(void) }

register_pernet_subsys(&canbcm_pernet_ops); + register_netdevice_notifier(&canbcm_notifier); return 0; }

static void __exit bcm_module_exit(void) { can_proto_unregister(&bcm_can_proto); + unregister_netdevice_notifier(&canbcm_notifier); unregister_pernet_subsys(&canbcm_pernet_ops); }

--- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -143,10 +143,14 @@ struct isotp_sock { u32 force_tx_stmin; u32 force_rx_stmin; struct tpcon rx, tx; - struct notifier_block notifier; + struct list_head notifier; wait_queue_head_t wait; };

+static LIST_HEAD(isotp_notifier_list); +static DEFINE_SPINLOCK(isotp_notifier_lock); +static struct isotp_sock *isotp_busy_notifier; + static inline struct isotp_sock *isotp_sk(const struct sock *sk) { return (struct isotp_sock *)sk; @@ -1013,7 +1017,14 @@ static int isotp_release(struct socket * /* wait for complete transmission of current pdu */ wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE);

- unregister_netdevice_notifier(&so->notifier); + spin_lock(&isotp_notifier_lock); + while (isotp_busy_notifier == so) { + spin_unlock(&isotp_notifier_lock); + schedule_timeout_uninterruptible(1); + spin_lock(&isotp_notifier_lock); + } + list_del(&so->notifier); + spin_unlock(&isotp_notifier_lock);

lock_sock(sk);

@@ -1317,21 +1328,16 @@ static int isotp_getsockopt(struct socke return 0; }

-static int isotp_notifier(struct notifier_block *nb, unsigned long msg, - void *ptr) +static void isotp_notify(struct isotp_sock *so, unsigned long msg, + struct net_device *dev) { - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct isotp_sock *so = container_of(nb, struct isotp_sock, notifier); struct sock *sk = &so->sk;

if (!net_eq(dev_net(dev), sock_net(sk))) - return NOTIFY_DONE; - - if (dev->type != ARPHRD_CAN) - return NOTIFY_DONE; + return;

if (so->ifindex != dev->ifindex) - return NOTIFY_DONE; + return;

switch (msg) { case NETDEV_UNREGISTER: @@ -1357,7 +1363,28 @@ static int isotp_notifier(struct notifie sk->sk_error_report(sk); break; } +}

+static int isotp_notifier(struct notifier_block *nb, unsigned long msg, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + + if (dev->type != ARPHRD_CAN) + return NOTIFY_DONE; + if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN) + return NOTIFY_DONE; + if (unlikely(isotp_busy_notifier)) /* Check for reentrant bug. */ + return NOTIFY_DONE; + + spin_lock(&isotp_notifier_lock); + list_for_each_entry(isotp_busy_notifier, &isotp_notifier_list, notifier) { + spin_unlock(&isotp_notifier_lock); + isotp_notify(isotp_busy_notifier, msg, dev); + spin_lock(&isotp_notifier_lock); + } + isotp_busy_notifier = NULL; + spin_unlock(&isotp_notifier_lock); return NOTIFY_DONE; }

@@ -1394,8 +1421,9 @@ static int isotp_init(struct sock *sk)

init_waitqueue_head(&so->wait);

- so->notifier.notifier_call = isotp_notifier; - register_netdevice_notifier(&so->notifier); + spin_lock(&isotp_notifier_lock); + list_add_tail(&so->notifier, &isotp_notifier_list); + spin_unlock(&isotp_notifier_lock);

return 0; } @@ -1442,6 +1470,10 @@ static const struct can_proto isotp_can_ .prot = &isotp_proto, };

+static struct notifier_block canisotp_notifier = { + .notifier_call = isotp_notifier +}; + static __init int isotp_module_init(void) { int err; @@ -1451,6 +1483,8 @@ static __init int isotp_module_init(void err = can_proto_register(&isotp_can_proto); if (err < 0) pr_err("can: registration of isotp protocol failed\n"); + else + register_netdevice_notifier(&canisotp_notifier);

return err; } @@ -1458,6 +1492,7 @@ static __init int isotp_module_init(void static __exit void isotp_module_exit(void) { can_proto_unregister(&isotp_can_proto); + unregister_netdevice_notifier(&canisotp_notifier); }

module_init(isotp_module_init); --- a/net/can/raw.c +++ b/net/can/raw.c @@ -83,7 +83,7 @@ struct raw_sock { struct sock sk; int bound; int ifindex; - struct notifier_block notifier; + struct list_head notifier; int loopback; int recv_own_msgs; int fd_frames; @@ -95,6 +95,10 @@ struct raw_sock { struct uniqframe __percpu *uniq; };

+static LIST_HEAD(raw_notifier_list); +static DEFINE_SPINLOCK(raw_notifier_lock); +static struct raw_sock *raw_busy_notifier; + /* Return pointer to store the extra msg flags for raw_recvmsg(). * We use the space of one unsigned int beyond the 'struct sockaddr_can' * in skb->cb. @@ -263,21 +267,16 @@ static int raw_enable_allfilters(struct return err; }

-static int raw_notifier(struct notifier_block *nb, - unsigned long msg, void *ptr) +static void raw_notify(struct raw_sock *ro, unsigned long msg, + struct net_device *dev) { - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct raw_sock *ro = container_of(nb, struct raw_sock, notifier); struct sock *sk = &ro->sk;

if (!net_eq(dev_net(dev), sock_net(sk))) - return NOTIFY_DONE; - - if (dev->type != ARPHRD_CAN) - return NOTIFY_DONE; + return;

if (ro->ifindex != dev->ifindex) - return NOTIFY_DONE; + return;

switch (msg) { case NETDEV_UNREGISTER: @@ -305,7 +304,28 @@ static int raw_notifier(struct notifier_ sk->sk_error_report(sk); break; } +} + +static int raw_notifier(struct notifier_block *nb, unsigned long msg, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + + if (dev->type != ARPHRD_CAN) + return NOTIFY_DONE; + if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN) + return NOTIFY_DONE; + if (unlikely(raw_busy_notifier)) /* Check for reentrant bug. */ + return NOTIFY_DONE;

+ spin_lock(&raw_notifier_lock); + list_for_each_entry(raw_busy_notifier, &raw_notifier_list, notifier) { + spin_unlock(&raw_notifier_lock); + raw_notify(raw_busy_notifier, msg, dev); + spin_lock(&raw_notifier_lock); + } + raw_busy_notifier = NULL; + spin_unlock(&raw_notifier_lock); return NOTIFY_DONE; }

@@ -334,9 +354,9 @@ static int raw_init(struct sock *sk) return -ENOMEM;

/* set notifier */ - ro->notifier.notifier_call = raw_notifier; - - register_netdevice_notifier(&ro->notifier); + spin_lock(&raw_notifier_lock); + list_add_tail(&ro->notifier, &raw_notifier_list); + spin_unlock(&raw_notifier_lock);

return 0; } @@ -351,7 +371,14 @@ static int raw_release(struct socket *so

ro = raw_sk(sk);

- unregister_netdevice_notifier(&ro->notifier); + spin_lock(&raw_notifier_lock); + while (raw_busy_notifier == ro) { + spin_unlock(&raw_notifier_lock); + schedule_timeout_uninterruptible(1); + spin_lock(&raw_notifier_lock); + } + list_del(&ro->notifier); + spin_unlock(&raw_notifier_lock);

lock_sock(sk);

@@ -889,6 +916,10 @@ static const struct can_proto raw_can_pr .prot = &raw_proto, };

+static struct notifier_block canraw_notifier = { + .notifier_call = raw_notifier +}; + static __init int raw_module_init(void) { int err; @@ -898,6 +929,8 @@ static __init int raw_module_init(void) err = can_proto_register(&raw_can_proto); if (err < 0) pr_err("can: registration of raw protocol failed\n"); + else + register_netdevice_notifier(&canraw_notifier);

return err; } @@ -905,6 +938,7 @@ static __init int raw_module_init(void) static __exit void raw_module_exit(void) { can_proto_unregister(&raw_can_proto); + unregister_netdevice_notifier(&canraw_notifier); }

module_init(raw_module_init);

From: Pavel Skripkin paskripkin@gmail.com

commit 91c02557174be7f72e46ed7311e3bea1939840b0 upstream.

Syzbot reported memory leak in SocketCAN driver for Microchip CAN BUS Analyzer Tool. The problem was in unfreed usb_coherent.

In mcba_usb_start() 20 coherent buffers are allocated and there is nothing, that frees them:

1) In callback function the urb is resubmitted and that's all 2) In disconnect function urbs are simply killed, but URB_FREE_BUFFER is not set (see mcba_usb_start) and this flag cannot be used with coherent buffers.

Fail log: | [ 1354.053291][ T8413] mcba_usb 1-1:0.0 can0: device disconnected | [ 1367.059384][ T8420] kmemleak: 20 new suspected memory leaks (see /sys/kernel/debug/kmem)

So, all allocated buffers should be freed with usb_free_coherent() explicitly

NOTE: The same pattern for allocating and freeing coherent buffers is used in drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c

Fixes: 51f3baad7de9 ("can: mcba_usb: Add support for Microchip CAN BUS Analyzer") Link: https://lore.kernel.org/r/20210609215833.30393-1-paskripkin@gmail.com Cc: linux-stable stable@vger.kernel.org Reported-and-tested-by: syzbot+57281c762a3922e14dfe@syzkaller.appspotmail.com Signed-off-by: Pavel Skripkin paskripkin@gmail.com Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/can/usb/mcba_usb.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-)

--- a/drivers/net/can/usb/mcba_usb.c +++ b/drivers/net/can/usb/mcba_usb.c @@ -82,6 +82,8 @@ struct mcba_priv { bool can_ka_first_pass; bool can_speed_check; atomic_t free_ctx_cnt; + void *rxbuf[MCBA_MAX_RX_URBS]; + dma_addr_t rxbuf_dma[MCBA_MAX_RX_URBS]; };

/* CAN frame */ @@ -633,6 +635,7 @@ static int mcba_usb_start(struct mcba_pr for (i = 0; i < MCBA_MAX_RX_URBS; i++) { struct urb *urb = NULL; u8 *buf; + dma_addr_t buf_dma;

/* create a URB, and a buffer for it */ urb = usb_alloc_urb(0, GFP_KERNEL); @@ -642,7 +645,7 @@ static int mcba_usb_start(struct mcba_pr }

buf = usb_alloc_coherent(priv->udev, MCBA_USB_RX_BUFF_SIZE, - GFP_KERNEL, &urb->transfer_dma); + GFP_KERNEL, &buf_dma); if (!buf) { netdev_err(netdev, "No memory left for USB buffer\n"); usb_free_urb(urb); @@ -661,11 +664,14 @@ static int mcba_usb_start(struct mcba_pr if (err) { usb_unanchor_urb(urb); usb_free_coherent(priv->udev, MCBA_USB_RX_BUFF_SIZE, - buf, urb->transfer_dma); + buf, buf_dma); usb_free_urb(urb); break; }

+ priv->rxbuf[i] = buf; + priv->rxbuf_dma[i] = buf_dma; + /* Drop reference, USB core will take care of freeing it */ usb_free_urb(urb); } @@ -708,7 +714,14 @@ static int mcba_usb_open(struct net_devi

static void mcba_urb_unlink(struct mcba_priv *priv) { + int i; + usb_kill_anchored_urbs(&priv->rx_submitted); + + for (i = 0; i < MCBA_MAX_RX_URBS; ++i) + usb_free_coherent(priv->udev, MCBA_USB_RX_BUFF_SIZE, + priv->rxbuf[i], priv->rxbuf_dma[i]); + usb_kill_anchored_urbs(&priv->tx_submitted); }

From: Breno Lima breno.lima@nxp.com

commit c6d580d96f140596d69220f60ce0cfbea4ee5c0f upstream.

i.MX8MM cannot detect certain CDP USB HUBs. usbmisc_imx.c driver is not following CDP timing requirements defined by USB BC 1.2 specification and section 3.2.4 Detection Timing CDP.

During Primary Detection the i.MX device should turn on VDP_SRC and IDM_SINK for a minimum of 40ms (TVDPSRC_ON). After a time of TVDPSRC_ON, the i.MX is allowed to check the status of the D- line. Current implementation is waiting between 1ms and 2ms, and certain BC 1.2 complaint USB HUBs cannot be detected. Increase delay to 40ms allowing enough time for primary detection.

During secondary detection the i.MX is required to disable VDP_SRC and IDM_SNK, and enable VDM_SRC and IDP_SINK for at least 40ms (TVDMSRC_ON).

Current implementation is not disabling VDP_SRC and IDM_SNK, introduce disable sequence in imx7d_charger_secondary_detection() function.

VDM_SRC and IDP_SINK should be enabled for at least 40ms (TVDMSRC_ON). Increase delay allowing enough time for detection.

Cc: stable@vger.kernel.org Fixes: 746f316b753a ("usb: chipidea: introduce imx7d USB charger detection") Signed-off-by: Breno Lima breno.lima@nxp.com Signed-off-by: Jun Li jun.li@nxp.com Link: https://lore.kernel.org/r/20210614175013.495808-1-breno.lima@nxp.com Signed-off-by: Peter Chen peter.chen@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/chipidea/usbmisc_imx.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-)

--- a/drivers/usb/chipidea/usbmisc_imx.c +++ b/drivers/usb/chipidea/usbmisc_imx.c @@ -686,6 +686,16 @@ static int imx7d_charger_secondary_detec int val; unsigned long flags;

+ /* Clear VDATSRCENB0 to disable VDP_SRC and IDM_SNK required by BC 1.2 spec */ + spin_lock_irqsave(&usbmisc->lock, flags); + val = readl(usbmisc->base + MX7D_USB_OTG_PHY_CFG2); + val &= ~MX7D_USB_OTG_PHY_CFG2_CHRG_VDATSRCENB0; + writel(val, usbmisc->base + MX7D_USB_OTG_PHY_CFG2); + spin_unlock_irqrestore(&usbmisc->lock, flags); + + /* TVDMSRC_DIS */ + msleep(20); + /* VDM_SRC is connected to D- and IDP_SINK is connected to D+ */ spin_lock_irqsave(&usbmisc->lock, flags); val = readl(usbmisc->base + MX7D_USB_OTG_PHY_CFG2); @@ -695,7 +705,8 @@ static int imx7d_charger_secondary_detec usbmisc->base + MX7D_USB_OTG_PHY_CFG2); spin_unlock_irqrestore(&usbmisc->lock, flags);

- usleep_range(1000, 2000); + /* TVDMSRC_ON */ + msleep(40);

/* * Per BC 1.2, check voltage of D+: @@ -798,7 +809,8 @@ static int imx7d_charger_primary_detecti usbmisc->base + MX7D_USB_OTG_PHY_CFG2); spin_unlock_irqrestore(&usbmisc->lock, flags);

- usleep_range(1000, 2000); + /* TVDPSRC_ON */ + msleep(40);

/* Check if D- is less than VDAT_REF to determine an SDP per BC 1.2 */ val = readl(usbmisc->base + MX7D_USB_OTG_PHY_STATUS);

From: Steven Rostedt (VMware) rostedt@goodmis.org

commit 4fdd595e4f9a1ff6d93ec702eaecae451cfc6591 upstream.

A while ago, when the "trace" file was opened, tracing was stopped, and code was added to stop recording the comms to saved_cmdlines, for mapping of the pids to the task name.

Code has been added that only records the comm if a trace event occurred, and there's no reason to not trace it if the trace file is opened.

Cc: stable@vger.kernel.org Fixes: 7ffbd48d5cab2 ("tracing: Cache comms only after an event occurred") Signed-off-by: Steven Rostedt (VMware) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/trace/trace.c | 9 --------- 1 file changed, 9 deletions(-)

--- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2198,9 +2198,6 @@ struct saved_cmdlines_buffer { }; static struct saved_cmdlines_buffer *savedcmd;

-/* temporary disable recording */ -static atomic_t trace_record_taskinfo_disabled __read_mostly; - static inline char *get_saved_cmdlines(int idx) { return &savedcmd->saved_cmdlines[idx * TASK_COMM_LEN]; @@ -3740,9 +3737,6 @@ static void *s_start(struct seq_file *m, return ERR_PTR(-EBUSY); #endif

- if (!iter->snapshot) - atomic_inc(&trace_record_taskinfo_disabled); - if (*pos != iter->pos) { iter->ent = NULL; iter->cpu = 0; @@ -3785,9 +3779,6 @@ static void s_stop(struct seq_file *m, v return; #endif

- if (!iter->snapshot) - atomic_dec(&trace_record_taskinfo_disabled); - trace_access_unlock(iter->cpu_file); trace_event_read_unlock(); }

From: Antti Järvinen antti.jarvinen@gmail.com

commit b5cf198e74a91073d12839a3e2db99994a39995d upstream.

Some TI KeyStone C667X devices do not support bus/hot reset. The PCIESS automatically disables LTSSM when Secondary Bus Reset is received and device stops working. Prevent bus reset for these devices. With this change, the device can be assigned to VMs with VFIO, but it will leak state between VMs.

Reference: https://e2e.ti.com/support/processors/f/791/t/954382 Link: https://lore.kernel.org/r/20210315102606.17153-1-antti.jarvinen@gmail.com Signed-off-by: Antti Järvinen antti.jarvinen@gmail.com Signed-off-by: Bjorn Helgaas bhelgaas@google.com Reviewed-by: Kishon Vijay Abraham I kishon@ti.com Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/pci/quirks.c | 10 ++++++++++ 1 file changed, 10 insertions(+)

--- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -3578,6 +3578,16 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_A */ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_CAVIUM, 0xa100, quirk_no_bus_reset);

+/* + * Some TI KeyStone C667X devices do not support bus/hot reset. The PCIESS + * automatically disables LTSSM when Secondary Bus Reset is received and + * the device stops working. Prevent bus reset for these devices. With + * this change, the device can be assigned to VMs with VFIO, but it will + * leak state between VMs. Reference + * https://e2e.ti.com/support/processors/f/791/t/954382 + */ +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TI, 0xb005, quirk_no_bus_reset); + static void quirk_no_pm_reset(struct pci_dev *dev) { /*

From: Evan Quan evan.quan@amd.com

commit e8946a53e2a698c148b3b3ed732f43c7747fbeb6 upstream.

Observed unexpected GPU hang during runpm stress test on 0x7341 rev 0x00. Further debugging shows broken ATS is related.

Disable ATS on this part. Similar issues on other devices:

a2da5d8cc0b0 ("PCI: Mark AMD Raven iGPU ATS as broken in some platforms") 45beb31d3afb ("PCI: Mark AMD Navi10 GPU rev 0x00 ATS as broken") 5e89cd303e3a ("PCI: Mark AMD Navi14 GPU rev 0xc5 ATS as broken")

Suggested-by: Alex Deucher alexander.deucher@amd.com Link: https://lore.kernel.org/r/20210602021255.939090-1-evan.quan@amd.com Signed-off-by: Evan Quan evan.quan@amd.com Signed-off-by: Bjorn Helgaas bhelgaas@google.com Reviewed-by: Krzysztof Wilczyński kw@linux.com Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/pci/quirks.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -5187,7 +5187,8 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SE static void quirk_amd_harvest_no_ats(struct pci_dev *pdev) { if ((pdev->device == 0x7312 && pdev->revision != 0x00) || - (pdev->device == 0x7340 && pdev->revision != 0xc5)) + (pdev->device == 0x7340 && pdev->revision != 0xc5) || + (pdev->device == 0x7341 && pdev->revision != 0x00)) return;

if (pdev->device == 0x15d8) { @@ -5214,6 +5215,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AT DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7312, quirk_amd_harvest_no_ats); /* AMD Navi14 dGPU */ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7340, quirk_amd_harvest_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7341, quirk_amd_harvest_no_ats); /* AMD Raven platform iGPU */ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x15d8, quirk_amd_harvest_no_ats); #endif /* CONFIG_PCI_ATS */

From: Sriharsha Basavapatna sriharsha.basavapatna@broadcom.com

commit db2f77e2bd99dbd2fb23ddde58f0fae392fe3338 upstream.

The Broadcom BCM57414 NIC may be a multi-function device. While it does not advertise an ACS capability, peer-to-peer transactions are not possible between the individual functions, so it is safe to treat them as fully isolated.

Add an ACS quirk for this device so the functions can be in independent IOMMU groups and attached individually to userspace applications using VFIO.

[bhelgaas: commit log] Link: https://lore.kernel.org/r/1621645997-16251-1-git-send-email-michael.chan@bro... Signed-off-by: Sriharsha Basavapatna sriharsha.basavapatna@broadcom.com Signed-off-by: Michael Chan michael.chan@broadcom.com Signed-off-by: Bjorn Helgaas bhelgaas@google.com Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/pci/quirks.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -4786,6 +4786,8 @@ static const struct pci_dev_acs_enabled { PCI_VENDOR_ID_AMPERE, 0xE00A, pci_quirk_xgene_acs }, { PCI_VENDOR_ID_AMPERE, 0xE00B, pci_quirk_xgene_acs }, { PCI_VENDOR_ID_AMPERE, 0xE00C, pci_quirk_xgene_acs }, + /* Broadcom multi-function device */ + { PCI_VENDOR_ID_BROADCOM, 0x16D7, pci_quirk_mf_endpoint_acs }, { PCI_VENDOR_ID_BROADCOM, 0xD714, pci_quirk_brcm_acs }, /* Amazon Annapurna Labs */ { PCI_VENDOR_ID_AMAZON_ANNAPURNA_LABS, 0x0031, pci_quirk_al_acs },

From: Naohiro Aota naohiro.aota@wdc.com

commit f9f28e5bd0baee9708c9011897196f06ae3a2733 upstream.

Consider we have a using block group on zoned btrfs.

|<- ZU ->|<- used ->|<---free--->| `- Alloc offset ZU: Zone unusable

Marking the block group read-only will migrate the zone unusable bytes to the read-only bytes. So, we will have this.

|<- RO ->|<- used ->|<--- RO --->|

RO: Read only

When marking it back to read-write, btrfs_dec_block_group_ro() subtracts the above "RO" bytes from the space_info->bytes_readonly. And, it moves the zone unusable bytes back and again subtracts those bytes from the space_info->bytes_readonly, leading to negative bytes_readonly.

This can be observed in the output as eg.:

Data, single: total=512.00MiB, used=165.21MiB, zone_unusable=16.00EiB Data, single: total=536870912, used=173256704, zone_unusable=18446744073603186688

This commit fixes the issue by reordering the operations.

Link: https://github.com/naota/linux/issues/37 Reported-by: David Sterba dsterba@suse.com Fixes: 169e0da91a21 ("btrfs: zoned: track unusable bytes for zones") CC: stable@vger.kernel.org # 5.12+ Reviewed-by: Johannes Thumshirn johannes.thumshirn@wdc.com Signed-off-by: Naohiro Aota naohiro.aota@wdc.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/btrfs/block-group.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

--- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -2347,16 +2347,16 @@ void btrfs_dec_block_group_ro(struct btr spin_lock(&sinfo->lock); spin_lock(&cache->lock); if (!--cache->ro) { - num_bytes = cache->length - cache->reserved - - cache->pinned - cache->bytes_super - - cache->zone_unusable - cache->used; - sinfo->bytes_readonly -= num_bytes; if (btrfs_is_zoned(cache->fs_info)) { /* Migrate zone_unusable bytes back */ cache->zone_unusable = cache->alloc_offset - cache->used; sinfo->bytes_zone_unusable += cache->zone_unusable; sinfo->bytes_readonly -= cache->zone_unusable; } + num_bytes = cache->length - cache->reserved - + cache->pinned - cache->bytes_super - + cache->zone_unusable - cache->used; + sinfo->bytes_readonly -= num_bytes; list_del_init(&cache->ro_list); } spin_unlock(&cache->lock);

From: Sean Christopherson seanjc@google.com

commit 78fcb2c91adfec8ce3a2ba6b4d0dda89f2f4a7c6 upstream.

Immediately reset the MMU context when the vCPU's SMM flag is cleared so that the SMM flag in the MMU role is always synchronized with the vCPU's flag. If RSM fails (which isn't correctly emulated), KVM will bail without calling post_leave_smm() and leave the MMU in a bad state.

The bad MMU role can lead to a NULL pointer dereference when grabbing a shadow page's rmap for a page fault as the initial lookups for the gfn will happen with the vCPU's SMM flag (=0), whereas the rmap lookup will use the shadow page's SMM flag, which comes from the MMU (=1). SMM has an entirely different set of memslots, and so the initial lookup can find a memslot (SMM=0) and then explode on the rmap memslot lookup (SMM=1).

general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] CPU: 1 PID: 8410 Comm: syz-executor382 Not tainted 5.13.0-rc5-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:__gfn_to_rmap arch/x86/kvm/mmu/mmu.c:935 [inline] RIP: 0010:gfn_to_rmap+0x2b0/0x4d0 arch/x86/kvm/mmu/mmu.c:947 Code: <42> 80 3c 20 00 74 08 4c 89 ff e8 f1 79 a9 00 4c 89 fb 4d 8b 37 44 RSP: 0018:ffffc90000ffef98 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff888015b9f414 RCX: ffff888019669c40 RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000001 RBP: 0000000000000001 R08: ffffffff811d9cdb R09: ffffed10065a6002 R10: ffffed10065a6002 R11: 0000000000000000 R12: dffffc0000000000 R13: 0000000000000003 R14: 0000000000000001 R15: 0000000000000000 FS: 000000000124b300(0000) GS:ffff8880b9b00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000028e31000 CR4: 00000000001526e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: rmap_add arch/x86/kvm/mmu/mmu.c:965 [inline] mmu_set_spte+0x862/0xe60 arch/x86/kvm/mmu/mmu.c:2604 __direct_map arch/x86/kvm/mmu/mmu.c:2862 [inline] direct_page_fault+0x1f74/0x2b70 arch/x86/kvm/mmu/mmu.c:3769 kvm_mmu_do_page_fault arch/x86/kvm/mmu.h:124 [inline] kvm_mmu_page_fault+0x199/0x1440 arch/x86/kvm/mmu/mmu.c:5065 vmx_handle_exit+0x26/0x160 arch/x86/kvm/vmx/vmx.c:6122 vcpu_enter_guest+0x3bdd/0x9630 arch/x86/kvm/x86.c:9428 vcpu_run+0x416/0xc20 arch/x86/kvm/x86.c:9494 kvm_arch_vcpu_ioctl_run+0x4e8/0xa40 arch/x86/kvm/x86.c:9722 kvm_vcpu_ioctl+0x70f/0xbb0 arch/x86/kvm/../../../virt/kvm/kvm_main.c:3460 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:1069 [inline] __se_sys_ioctl+0xfb/0x170 fs/ioctl.c:1055 do_syscall_64+0x3f/0xb0 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x440ce9

Cc: stable@vger.kernel.org Reported-by: syzbot+fb0b6a7e8713aeb0319c@syzkaller.appspotmail.com Fixes: 9ec19493fb86 ("KVM: x86: clear SMM flags before loading state while leaving SMM") Signed-off-by: Sean Christopherson seanjc@google.com Message-Id: 20210609185619.992058-2-seanjc@google.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/x86.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

--- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6991,7 +6991,10 @@ static unsigned emulator_get_hflags(stru

static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_flags) { - emul_to_vcpu(ctxt)->arch.hflags = emul_flags; + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + + vcpu->arch.hflags = emul_flags; + kvm_mmu_reset_context(vcpu); }

static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt,

From: Wanpeng Li wanpengli@tencent.com

commit dfdc0a714d241bfbf951886c373cd1ae463fcc25 upstream.

Commit c9b8b07cded58 (KVM: x86: Dynamically allocate per-vCPU emulation context) tries to allocate per-vCPU emulation context dynamically, however, the x86_emulator slab cache is still exiting after the kvm module is unload as below after destroying the VM and unloading the kvm module.

grep x86_emulator /proc/slabinfo x86_emulator 36 36 2672 12 8 : tunables 0 0 0 : slabdata 3 3 0

This patch fixes this slab cache leak by destroying the x86_emulator slab cache when the kvm module is unloaded.

Fixes: c9b8b07cded58 (KVM: x86: Dynamically allocate per-vCPU emulation context) Cc: stable@vger.kernel.org Signed-off-by: Wanpeng Li wanpengli@tencent.com Message-Id: 1623387573-5969-1-git-send-email-wanpengli@tencent.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/x86.c | 1 + 1 file changed, 1 insertion(+)

--- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8150,6 +8150,7 @@ void kvm_arch_exit(void) kvm_x86_ops.hardware_enable = NULL; kvm_mmu_module_exit(); free_percpu(user_return_msrs); + kmem_cache_destroy(x86_emulator_cache); kmem_cache_destroy(x86_fpu_cache); #ifdef CONFIG_KVM_XEN static_key_deferred_flush(&kvm_xen_enabled);

From: Harald Freudenberger freude@linux.ibm.com

commit e73a99f3287a740a07d6618e9470f4d6cb217da8 upstream.

When a AP queue is switched to soft offline, all pending requests are purged out of the pending requests list and 'received' by the upper layer like zcrypt device drivers. This is also done for requests which are already enqueued into the firmware queue. A request in a firmware queue may eventually produce an response message, but there is no waiting process any more. However, the response was counted with the queue_counter and as this counter was reset to 0 with the offline switch, the pending response caused the queue_counter to get negative. The next request increased this counter to 0 (instead of 1) which caused the ap code to assume there is nothing to receive and so the response for this valid request was never tried to fetch from the firmware queue.

This all caused a queue to not work properly after a switch offline/online and in the end processes to hang forever when trying to send a crypto request after an queue offline/online switch cicle.

Fixed by a) making sure the counter does not drop below 0 and b) on a successful enqueue of a message has at least a value of 1.

Additionally a warning is emitted, when a reply can't get assigned to a waiting process. This may be normal operation (process had timeout or has been killed) but may give a hint that something unexpected happened (like this odd behavior described above).

Signed-off-by: Harald Freudenberger freude@linux.ibm.com Cc: stable@vger.kernel.org Signed-off-by: Vasily Gorbik gor@linux.ibm.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/s390/crypto/ap_queue.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-)

--- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -135,12 +135,13 @@ static struct ap_queue_status ap_sm_recv { struct ap_queue_status status; struct ap_message *ap_msg; + bool found = false;

status = ap_dqap(aq->qid, &aq->reply->psmid, aq->reply->msg, aq->reply->len); switch (status.response_code) { case AP_RESPONSE_NORMAL: - aq->queue_count--; + aq->queue_count = max_t(int, 0, aq->queue_count - 1); if (aq->queue_count > 0) mod_timer(&aq->timeout, jiffies + aq->request_timeout); @@ -150,8 +151,14 @@ static struct ap_queue_status ap_sm_recv list_del_init(&ap_msg->list); aq->pendingq_count--; ap_msg->receive(aq, ap_msg, aq->reply); + found = true; break; } + if (!found) { + AP_DBF_WARN("%s unassociated reply psmid=0x%016llx on 0x%02x.%04x\n", + __func__, aq->reply->psmid, + AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); + } fallthrough; case AP_RESPONSE_NO_PENDING_REPLY: if (!status.queue_empty || aq->queue_count <= 0) @@ -232,7 +239,7 @@ static enum ap_sm_wait ap_sm_write(struc ap_msg->flags & AP_MSG_FLAG_SPECIAL); switch (status.response_code) { case AP_RESPONSE_NORMAL: - aq->queue_count++; + aq->queue_count = max_t(int, 1, aq->queue_count + 1); if (aq->queue_count == 1) mod_timer(&aq->timeout, jiffies + aq->request_timeout); list_move_tail(&ap_msg->list, &aq->pendingq);

From: Fan Du fan.du@intel.com

commit 28e5e44aa3f4e0e0370864ed008fb5e2d85f4dc8 upstream.

tl;dr:

Several SGX users reported seeing the following message on NUMA systems:

sgx: [Firmware Bug]: Unable to map EPC section to online node. Fallback to the NUMA node 0.

This turned out to be the memblock code mistakenly throwing away SGX memory.

=== Full Changelog ===

The 'max_pfn' variable represents the highest known RAM address. It can be used, for instance, to quickly determine for which physical addresses there is mem_map[] space allocated. The numa_meminfo code makes an effort to throw out ("trim") all memory blocks which are above 'max_pfn'.

SGX memory is not considered RAM (it is marked as "Reserved" in the e820) and is not taken into account by max_pfn. Despite this, SGX memory areas have NUMA affinity and are enumerated in the ACPI SRAT table. The existing SGX code uses the numa_meminfo mechanism to look up the NUMA affinity for its memory areas.

In cases where SGX memory was above max_pfn (usually just the one EPC section in the last highest NUMA node), the numa_memblock is truncated at 'max_pfn', which is below the SGX memory. When the SGX code tries to look up the affinity of this memory, it fails and produces an error message:

sgx: [Firmware Bug]: Unable to map EPC section to online node. Fallback to the NUMA node 0.

and assigns the memory to NUMA node 0.

Instead of silently truncating the memory block at 'max_pfn' and dropping the SGX memory, add the truncated portion to 'numa_reserved_meminfo'. This allows the SGX code to later determine the NUMA affinity of its 'Reserved' area.

Before, numa_meminfo looked like this (from 'crash'):

blk = { start = 0x0, end = 0x2080000000, nid = 0x0 } { start = 0x2080000000, end = 0x4000000000, nid = 0x1 }

numa_reserved_meminfo is empty.

With this, numa_meminfo looks like this:

blk = { start = 0x0, end = 0x2080000000, nid = 0x0 } { start = 0x2080000000, end = 0x4000000000, nid = 0x1 }

and numa_reserved_meminfo has an entry for node 1's SGX memory:

blk = { start = 0x4000000000, end = 0x4080000000, nid = 0x1 }

[ daveh: completely rewrote/reworked changelog ]

Fixes: 5d30f92e7631 ("x86/NUMA: Provide a range-to-target_node lookup facility") Reported-by: Reinette Chatre reinette.chatre@intel.com Signed-off-by: Fan Du fan.du@intel.com Signed-off-by: Dave Hansen dave.hansen@intel.com Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Jarkko Sakkinen jarkko@kernel.org Reviewed-by: Dan Williams dan.j.williams@intel.com Reviewed-by: Dave Hansen dave.hansen@intel.com Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20210617194657.0A99CB22@viggo.jf.intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/mm/numa.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)

--- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -254,7 +254,13 @@ int __init numa_cleanup_meminfo(struct n

/* make sure all non-reserved blocks are inside the limits */ bi->start = max(bi->start, low); - bi->end = min(bi->end, high); + + /* preserve info for non-RAM areas above 'max_pfn': */ + if (bi->end > high) { + numa_add_memblk_to(bi->nid, high, bi->end, + &numa_reserved_meminfo); + bi->end = high; + }

/* and there's no empty block */ if (bi->start >= bi->end)

From: Tom Lendacky thomas.lendacky@amd.com

commit 8d651ee9c71bb12fc0c8eb2786b66cbe5aa3e43b upstream.

Some drivers require memory that is marked as EFI boot services data. In order for this memory to not be re-used by the kernel after ExitBootServices(), efi_mem_reserve() is used to preserve it by inserting a new EFI memory descriptor and marking it with the EFI_MEMORY_RUNTIME attribute.

Under SEV, memory marked with the EFI_MEMORY_RUNTIME attribute needs to be mapped encrypted by Linux, otherwise the kernel might crash at boot like below:

EFI Variables Facility v0.08 2004-May-17 general protection fault, probably for non-canonical address 0x3597688770a868b2: 0000 [#1] SMP NOPTI CPU: 13 PID: 1 Comm: swapper/0 Not tainted 5.12.4-2-default #1 openSUSE Tumbleweed Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 RIP: 0010:efi_mokvar_entry_next [...] Call Trace: efi_mokvar_sysfs_init ? efi_mokvar_table_init do_one_initcall ? __kmalloc kernel_init_freeable ? rest_init kernel_init ret_from_fork

Expand the __ioremap_check_other() function to additionally check for this other type of boot data reserved at runtime and indicate that it should be mapped encrypted for an SEV guest.

[ bp: Massage commit message. ]

Fixes: 58c909022a5a ("efi: Support for MOK variable config table") Reported-by: Joerg Roedel jroedel@suse.de Signed-off-by: Tom Lendacky thomas.lendacky@amd.com Signed-off-by: Joerg Roedel jroedel@suse.de Signed-off-by: Borislav Petkov bp@suse.de Tested-by: Joerg Roedel jroedel@suse.de Cc: stable@vger.kernel.org # 5.10+ Link: https://lkml.kernel.org/r/20210608095439.12668-2-joro@8bytes.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/mm/ioremap.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -118,7 +118,9 @@ static void __ioremap_check_other(resour if (!IS_ENABLED(CONFIG_EFI)) return;

- if (efi_mem_type(addr) == EFI_RUNTIME_SERVICES_DATA) + if (efi_mem_type(addr) == EFI_RUNTIME_SERVICES_DATA || + (efi_mem_type(addr) == EFI_BOOT_SERVICES_DATA && + efi_mem_attributes(addr) & EFI_MEMORY_RUNTIME)) desc->flags |= IORES_MAP_ENCRYPTED; }

From: Thomas Gleixner tglx@linutronix.de

commit 484cea4f362e1eeb5c869abbfb5f90eae6421b38 upstream.

The non-compacted slowpath uses __copy_from_user() and copies the entire user buffer into the kernel buffer, verbatim. This means that the kernel buffer may now contain entirely invalid state on which XRSTOR will #GP. validate_user_xstate_header() can detect some of that corruption, but that leaves the onus on callers to clear the buffer.

Prior to XSAVES support, it was possible just to reinitialize the buffer, completely, but with supervisor states that is not longer possible as the buffer clearing code split got it backwards. Fixing that is possible but not corrupting the state in the first place is more robust.

Avoid corruption of the kernel XSAVE buffer by using copy_user_to_xstate() which validates the XSAVE header contents before copying the actual states to the kernel. copy_user_to_xstate() was previously only called for compacted-format kernel buffers, but it works for both compacted and non-compacted forms.

Using it for the non-compacted form is slower because of multiple __copy_from_user() operations, but that cost is less important than robust code in an already slow path.

[ Changelog polished by Dave Hansen ]

Fixes: b860eb8dce59 ("x86/fpu/xstate: Define new functions for clearing fpregs and xstates") Reported-by: syzbot+2067e764dbcd10721e2e@syzkaller.appspotmail.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Borislav Petkov bp@suse.de Acked-by: Dave Hansen dave.hansen@linux.intel.com Acked-by: Rik van Riel riel@surriel.com Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20210608144345.611833074@linutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kernel/fpu/signal.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-)

--- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -405,14 +405,7 @@ static int __fpu__restore_sig(void __use if (use_xsave() && !fx_only) { u64 init_bv = xfeatures_mask_user() & ~user_xfeatures;

- if (using_compacted_format()) { - ret = copy_user_to_xstate(&fpu->state.xsave, buf_fx); - } else { - ret = __copy_from_user(&fpu->state.xsave, buf_fx, state_size); - - if (!ret && state_size > offsetof(struct xregs_state, header)) - ret = validate_user_xstate_header(&fpu->state.xsave.header); - } + ret = copy_user_to_xstate(&fpu->state.xsave, buf_fx); if (ret) goto err_out;

From: Thomas Gleixner tglx@linutronix.de

commit efa165504943f2128d50f63de0c02faf6dcceb0d upstream.

If access_ok() or fpregs_soft_set() fails in __fpu__restore_sig() then the function just returns but does not clear the FPU state as it does for all other fatal failures.

Clear the FPU state for these failures as well.

Fixes: 72a671ced66d ("x86, fpu: Unify signal handling code paths for x86 and x86_64 kernels") Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: Borislav Petkov bp@suse.de Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/87mtryyhhz.ffs@nanos.tec.linutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kernel/fpu/signal.c | 26 +++++++++++++++----------- 1 file changed, 15 insertions(+), 11 deletions(-)

--- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -307,13 +307,17 @@ static int __fpu__restore_sig(void __use return 0; }

- if (!access_ok(buf, size)) - return -EACCES; + if (!access_ok(buf, size)) { + ret = -EACCES; + goto out; + }

- if (!static_cpu_has(X86_FEATURE_FPU)) - return fpregs_soft_set(current, NULL, - 0, sizeof(struct user_i387_ia32_struct), - NULL, buf) != 0; + if (!static_cpu_has(X86_FEATURE_FPU)) { + ret = fpregs_soft_set(current, NULL, 0, + sizeof(struct user_i387_ia32_struct), + NULL, buf); + goto out; + }

if (use_xsave()) { struct _fpx_sw_bytes fx_sw_user; @@ -396,7 +400,7 @@ static int __fpu__restore_sig(void __use */ ret = __copy_from_user(&env, buf, sizeof(env)); if (ret) - goto err_out; + goto out; envp = &env; }

@@ -426,7 +430,7 @@ static int __fpu__restore_sig(void __use

ret = copy_user_to_xstate(&fpu->state.xsave, buf_fx); if (ret) - goto err_out; + goto out;

sanitize_restored_user_xstate(&fpu->state, envp, user_xfeatures, fx_only); @@ -446,7 +450,7 @@ static int __fpu__restore_sig(void __use ret = __copy_from_user(&fpu->state.fxsave, buf_fx, state_size); if (ret) { ret = -EFAULT; - goto err_out; + goto out; }

sanitize_restored_user_xstate(&fpu->state, envp, user_xfeatures, @@ -464,7 +468,7 @@ static int __fpu__restore_sig(void __use } else { ret = __copy_from_user(&fpu->state.fsave, buf_fx, state_size); if (ret) - goto err_out; + goto out;

fpregs_lock(); ret = copy_kernel_to_fregs_err(&fpu->state.fsave); @@ -475,7 +479,7 @@ static int __fpu__restore_sig(void __use fpregs_deactivate(fpu); fpregs_unlock();

-err_out: +out: if (ret) fpu__clear_user_states(fpu); return ret;

From: Tor Vic torvic9@mailbox.org

commit 0236526d76b87c1dc2cbe3eb31ae29be5b0ca151 upstream.

Since LLVM commit fc018eb, the '-warn-stack-size' flag has been dropped [1], leading to the following error message when building with Clang-13 and LLD-13:

ld.lld: error: -plugin-opt=-: ld.lld: Unknown command line argument '-warn-stack-size=2048'. Try: 'ld.lld --help' ld.lld: Did you mean '--asan-stack=2048'?

In the same way as with commit 2398ce80152a ("x86, lto: Pass -stack-alignment only on LLD < 13.0.0") , make '-warn-stack-size' conditional on LLD < 13.0.0.

[1] https://reviews.llvm.org/D103928

Fixes: 24845dcb170e ("Makefile: LTO: have linker check -Wframe-larger-than") Cc: stable@vger.kernel.org Link: https://github.com/ClangBuiltLinux/linux/issues/1377 Signed-off-by: Tor Vic torvic9@mailbox.org Reviewed-by: Nathan Chancellor nathan@kernel.org Reviewed-by: Nick Desaulniers ndesaulniers@google.com Signed-off-by: Kees Cook keescook@chromium.org Link: https://lore.kernel.org/r/7631bab7-a8ab-f884-ab54-f4198976125c@mailbox.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- Makefile | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

--- a/Makefile +++ b/Makefile @@ -913,11 +913,14 @@ CC_FLAGS_LTO += -fvisibility=hidden # Limit inlining across translation units to reduce binary size KBUILD_LDFLAGS += -mllvm -import-instr-limit=5

-# Check for frame size exceeding threshold during prolog/epilog insertion. +# Check for frame size exceeding threshold during prolog/epilog insertion +# when using lld < 13.0.0. ifneq ($(CONFIG_FRAME_WARN),0) +ifeq ($(shell test $(CONFIG_LLD_VERSION) -lt 130000; echo $$?),0) KBUILD_LDFLAGS += -plugin-opt=-warn-stack-size=$(CONFIG_FRAME_WARN) endif endif +endif

ifdef CONFIG_LTO KBUILD_CFLAGS += -fno-lto $(CC_FLAGS_LTO)

From: Bumyong Lee bumyong.lee@samsung.com

commit 4ad5dd2d7876d79507a20f026507d1a93b8fff10 upstream.

flags varible which is the input parameter of pl330_prep_dma_cyclic() should not be used by spinlock_irq[save/restore] function.

Signed-off-by: Jongho Park jongho7.park@samsung.com Signed-off-by: Bumyong Lee bumyong.lee@samsung.com Signed-off-by: Chanho Park chanho61.park@samsung.com Link: https://lore.kernel.org/r/20210507063647.111209-1-chanho61.park@samsung.com Fixes: f6f2421c0a1c ("dmaengine: pl330: Merge dma_pl330_dmac and pl330_dmac structs") Cc: stable@vger.kernel.org Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/dma/pl330.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

--- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -2694,13 +2694,15 @@ static struct dma_async_tx_descriptor *p for (i = 0; i < len / period_len; i++) { desc = pl330_get_desc(pch); if (!desc) { + unsigned long iflags; + dev_err(pch->dmac->ddma.dev, "%s:%d Unable to fetch desc\n", __func__, __LINE__);

if (!first) return NULL;

- spin_lock_irqsave(&pl330->pool_lock, flags); + spin_lock_irqsave(&pl330->pool_lock, iflags);

while (!list_empty(&first->node)) { desc = list_entry(first->node.next, @@ -2710,7 +2712,7 @@ static struct dma_async_tx_descriptor *p

list_move_tail(&first->node, &pl330->desc_pool);

- spin_unlock_irqrestore(&pl330->pool_lock, flags); + spin_unlock_irqrestore(&pl330->pool_lock, iflags);

return NULL; }

From: Mathy Vanhoef Mathy.Vanhoef@kuleuven.be

commit bddc0c411a45d3718ac535a070f349be8eca8d48 upstream.

The commit cb17ed29a7a5 ("mac80211: parse radiotap header when selecting Tx queue") moved the code to validate the radiotap header from ieee80211_monitor_start_xmit to ieee80211_parse_tx_radiotap. This made is possible to share more code with the new Tx queue selection code for injected frames. But at the same time, it now required the call of ieee80211_parse_tx_radiotap at the beginning of functions which wanted to handle the radiotap header. And this broke the rate parser for radiotap header parser.

The radiotap parser for rates is operating most of the time only on the data in the actual radiotap header. But for the 802.11a/b/g rates, it must also know the selected band from the chandef information. But this information is only written to the ieee80211_tx_info at the end of the ieee80211_monitor_start_xmit - long after ieee80211_parse_tx_radiotap was already called. The info->band information was therefore always 0 (NL80211_BAND_2GHZ) when the parser code tried to access it.

For a 5GHz only device, injecting a frame with 802.11a rates would cause a NULL pointer dereference because local->hw.wiphy->bands[NL80211_BAND_2GHZ] would most likely have been NULL when the radiotap parser searched for the correct rate index of the driver.

Cc: stable@vger.kernel.org Reported-by: Ben Greear greearb@candelatech.com Fixes: cb17ed29a7a5 ("mac80211: parse radiotap header when selecting Tx queue") Signed-off-by: Mathy Vanhoef Mathy.Vanhoef@kuleuven.be [sven@narfation.org: added commit message] Signed-off-by: Sven Eckelmann sven@narfation.org Link: https://lore.kernel.org/r/20210530133226.40587-1-sven@narfation.org Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/mac80211.h | 7 +++++- net/mac80211/tx.c | 52 +++++++++++++++++++++++++++++++++---------------- 2 files changed, 42 insertions(+), 17 deletions(-)

--- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -6388,7 +6388,12 @@ bool ieee80211_tx_prepare_skb(struct iee

/** * ieee80211_parse_tx_radiotap - Sanity-check and parse the radiotap header - * of injected frames + * of injected frames. + * + * To accurately parse and take into account rate and retransmission fields, + * you must initialize the chandef field in the ieee80211_tx_info structure + * of the skb before calling this function. + * * @skb: packet injected by userspace * @dev: the &struct device of this 802.11 device */ --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2002,6 +2002,26 @@ void ieee80211_xmit(struct ieee80211_sub ieee80211_tx(sdata, sta, skb, false); }

+static bool ieee80211_validate_radiotap_len(struct sk_buff *skb) +{ + struct ieee80211_radiotap_header *rthdr = + (struct ieee80211_radiotap_header *)skb->data; + + /* check for not even having the fixed radiotap header part */ + if (unlikely(skb->len < sizeof(struct ieee80211_radiotap_header))) + return false; /* too short to be possibly valid */ + + /* is it a header version we can trust to find length from? */ + if (unlikely(rthdr->it_version)) + return false; /* only version 0 is supported */ + + /* does the skb contain enough to deliver on the alleged length? */ + if (unlikely(skb->len < ieee80211_get_radiotap_len(skb->data))) + return false; /* skb too short for claimed rt header extent */ + + return true; +} + bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, struct net_device *dev) { @@ -2010,8 +2030,6 @@ bool ieee80211_parse_tx_radiotap(struct struct ieee80211_radiotap_header *rthdr = (struct ieee80211_radiotap_header *) skb->data; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - struct ieee80211_supported_band *sband = - local->hw.wiphy->bands[info->band]; int ret = ieee80211_radiotap_iterator_init(&iterator, rthdr, skb->len, NULL); u16 txflags; @@ -2024,17 +2042,8 @@ bool ieee80211_parse_tx_radiotap(struct u8 vht_mcs = 0, vht_nss = 0; int i;

- /* check for not even having the fixed radiotap header part */ - if (unlikely(skb->len < sizeof(struct ieee80211_radiotap_header))) - return false; /* too short to be possibly valid */ - - /* is it a header version we can trust to find length from? */ - if (unlikely(rthdr->it_version)) - return false; /* only version 0 is supported */ - - /* does the skb contain enough to deliver on the alleged length? */ - if (unlikely(skb->len < ieee80211_get_radiotap_len(skb->data))) - return false; /* skb too short for claimed rt header extent */ + if (!ieee80211_validate_radiotap_len(skb)) + return false;

info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT | IEEE80211_TX_CTL_DONTFRAG; @@ -2174,6 +2183,9 @@ bool ieee80211_parse_tx_radiotap(struct return false;

if (rate_found) { + struct ieee80211_supported_band *sband = + local->hw.wiphy->bands[info->band]; + info->control.flags |= IEEE80211_TX_CTRL_RATE_INJECT;

for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) { @@ -2187,7 +2199,7 @@ bool ieee80211_parse_tx_radiotap(struct } else if (rate_flags & IEEE80211_TX_RC_VHT_MCS) { ieee80211_rate_set_vht(info->control.rates, vht_mcs, vht_nss); - } else { + } else if (sband) { for (i = 0; i < sband->n_bitrates; i++) { if (rate * 5 != sband->bitrates[i].bitrate) continue; @@ -2224,8 +2236,8 @@ netdev_tx_t ieee80211_monitor_start_xmit info->flags = IEEE80211_TX_CTL_REQ_TX_STATUS | IEEE80211_TX_CTL_INJECTED;

- /* Sanity-check and process the injection radiotap header */ - if (!ieee80211_parse_tx_radiotap(skb, dev)) + /* Sanity-check the length of the radiotap header */ + if (!ieee80211_validate_radiotap_len(skb)) goto fail;

/* we now know there is a radiotap header with a length we can use */ @@ -2339,6 +2351,14 @@ netdev_tx_t ieee80211_monitor_start_xmit ieee80211_select_queue_80211(sdata, skb, hdr); skb_set_queue_mapping(skb, ieee80211_ac_from_tid(skb->priority));

+ /* + * Process the radiotap header. This will now take into account the + * selected chandef above to accurately set injection rates and + * retransmissions. + */ + if (!ieee80211_parse_tx_radiotap(skb, dev)) + goto fail_rcu; + /* remove the injection radiotap header */ skb_pull(skb, len_rthdr);

From: Johannes Berg johannes.berg@intel.com

commit 43076c1e074359f11c85d7d1b85ede1bbb8ee6b9 upstream.

When I moved around the code here, I neglected that we could still call register_netdev() or similar without the wiphy mutex held, which then calls cfg80211_register_wdev() - that's also done from cfg80211_register_netdevice(), but the phy80211 symlink creation was only there. Now, the symlink isn't needed for a *pure* wdev, but a netdev not registered via cfg80211_register_wdev() should still have the symlink, so move the creation to the right place.

Cc: stable@vger.kernel.org Fixes: 2fe8ef106238 ("cfg80211: change netdev registration/unregistration semantics") Link: https://lore.kernel.org/r/20210608113226.a5dc4c1e488c.Ia42fe663cefe47b0883af... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/wireless/core.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-)

--- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1339,6 +1339,11 @@ void cfg80211_register_wdev(struct cfg80 rdev->devlist_generation++; wdev->registered = true;

+ if (wdev->netdev && + sysfs_create_link(&wdev->netdev->dev.kobj, &rdev->wiphy.dev.kobj, + "phy80211")) + pr_err("failed to add phy80211 symlink to netdev!\n"); + nl80211_notify_iface(rdev, wdev, NL80211_CMD_NEW_INTERFACE); }

@@ -1364,14 +1369,6 @@ int cfg80211_register_netdevice(struct n if (ret) goto out;

- if (sysfs_create_link(&dev->dev.kobj, &rdev->wiphy.dev.kobj, - "phy80211")) { - pr_err("failed to add phy80211 symlink to netdev!\n"); - unregister_netdevice(dev); - ret = -EINVAL; - goto out; - } - cfg80211_register_wdev(rdev, wdev); ret = 0; out:

From: Johannes Berg johannes.berg@intel.com

commit f5baf287f5da5641099ad5c809b3b4ebfc08506d upstream.

When reconfiguration fails, we shut down everything, but we cannot call cfg80211_shutdown_all_interfaces() with the wiphy mutex held. Since cfg80211 now calls it on resume errors, we only need to do likewise for where we call reconfig (whether directly or indirectly), but not under the wiphy lock.

Cc: stable@vger.kernel.org Fixes: 2fe8ef106238 ("cfg80211: change netdev registration/unregistration semantics") Link: https://lore.kernel.org/r/20210608113226.78233c80f548.Iecc104aceb89f0568f50e... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/mac80211/debugfs.c | 7 ++++++- net/mac80211/main.c | 7 ++++++- net/mac80211/util.c | 2 -- 3 files changed, 12 insertions(+), 4 deletions(-)

--- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -387,12 +387,17 @@ static ssize_t reset_write(struct file * size_t count, loff_t *ppos) { struct ieee80211_local *local = file->private_data; + int ret;

rtnl_lock(); wiphy_lock(local->hw.wiphy); __ieee80211_suspend(&local->hw, NULL); - __ieee80211_resume(&local->hw); + ret = __ieee80211_resume(&local->hw); wiphy_unlock(local->hw.wiphy); + + if (ret) + cfg80211_shutdown_all_interfaces(local->hw.wiphy); + rtnl_unlock();

return count; --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -252,6 +252,7 @@ static void ieee80211_restart_work(struc struct ieee80211_local *local = container_of(work, struct ieee80211_local, restart_work); struct ieee80211_sub_if_data *sdata; + int ret;

/* wait for scan work complete */ flush_workqueue(local->workqueue); @@ -294,8 +295,12 @@ static void ieee80211_restart_work(struc /* wait for all packet processing to be done */ synchronize_net();

- ieee80211_reconfig(local); + ret = ieee80211_reconfig(local); wiphy_unlock(local->hw.wiphy); + + if (ret) + cfg80211_shutdown_all_interfaces(local->hw.wiphy); + rtnl_unlock(); }

--- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2186,8 +2186,6 @@ static void ieee80211_handle_reconfig_fa list_for_each_entry(ctx, &local->chanctx_list, list) ctx->driver_present = false; mutex_unlock(&local->chanctx_mtx); - - cfg80211_shutdown_all_interfaces(local->hw.wiphy); }

static void ieee80211_assign_chanctx(struct ieee80211_local *local,

From: Johannes Berg johannes.berg@intel.com

commit b5642479b0f7168fe16d156913533fe65ab4f8d5 upstream.

If all net/wireless/certs/*.hex files are deleted, the build will hang at this point since the 'cat' command will have no arguments. Do "echo | cat - ..." so that even if the "..." part is empty, the whole thing won't hang.

Cc: stable@vger.kernel.org Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Luca Coelho luciano.coelho@intel.com Link: https://lore.kernel.org/r/iwlwifi.20210618133832.c989056c3664.Ic3b77531d00b3... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/wireless/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -28,7 +28,7 @@ $(obj)/shipped-certs.c: $(wildcard $(src @$(kecho) " GEN $@" @(echo '#include "reg.h"'; \ echo 'const u8 shipped_regdb_certs[] = {'; \ - cat $^ ; \ + echo | cat - $^ ; \ echo '};'; \ echo 'unsigned int shipped_regdb_certs_len = sizeof(shipped_regdb_certs);'; \ ) > $@

From: Yifan Zhang yifan1.zhang@amd.com

commit 1c0b0efd148d5b24c4932ddb3fa03c8edd6097b3 upstream.

If GC has entered CGPG, ringing doorbell > first page doesn't wakeup GC. Enlarge CP_MEC_DOORBELL_RANGE_UPPER to workaround this issue.

Signed-off-by: Yifan Zhang yifan1.zhang@amd.com Reviewed-by: Felix Kuehling Felix.Kuehling@amd.com Reviewed-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -6769,8 +6769,12 @@ static int gfx_v10_0_kiq_init_register(s if (ring->use_doorbell) { WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_LOWER, (adev->doorbell_index.kiq * 2) << 2); + /* If GC has entered CGPG, ringing doorbell > first page doesn't + * wakeup GC. Enlarge CP_MEC_DOORBELL_RANGE_UPPER to workaround + * this issue. + */ WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_UPPER, - (adev->doorbell_index.userqueue_end * 2) << 2); + (adev->doorbell.size - 4)); }

WREG32_SOC15(GC, 0, mmCP_HQD_PQ_DOORBELL_CONTROL,

From: Esben Haabendal esben@geanix.com

commit 6aa32217a9a446275440ee8724b1ecaf1838df47 upstream.

With the skb pointer piggy-backed on the TX BD, we have a simple and efficient way to free the skb buffer when the frame has been transmitted. But in order to avoid freeing the skb while there are still fragments from the skb in use, we need to piggy-back on the TX BD of the skb, not the first.

Without this, we are doing use-after-free on the DMA side, when the first BD of a multi TX BD packet is seen as completed in xmit_done, and the remaining BDs are still being processed.

Cc: stable@vger.kernel.org # v5.4+ Signed-off-by: Esben Haabendal esben@geanix.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/xilinx/ll_temac_main.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

--- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -876,7 +876,6 @@ temac_start_xmit(struct sk_buff *skb, st return NETDEV_TX_OK; } cur_p->phys = cpu_to_be32(skb_dma_addr); - ptr_to_txbd((void *)skb, cur_p);

for (ii = 0; ii < num_frag; ii++) { if (++lp->tx_bd_tail >= lp->tx_bd_num) @@ -915,6 +914,11 @@ temac_start_xmit(struct sk_buff *skb, st } cur_p->app0 |= cpu_to_be32(STS_CTRL_APP0_EOP);

+ /* Mark last fragment with skb address, so it can be consumed + * in temac_start_xmit_done() + */ + ptr_to_txbd((void *)skb, cur_p); + tail_p = lp->tx_bd_p + sizeof(*lp->tx_bd_v) * lp->tx_bd_tail; lp->tx_bd_tail++; if (lp->tx_bd_tail >= lp->tx_bd_num)

From: Nikolay Aleksandrov nikolay@nvidia.com

commit 58e2071742e38f29f051b709a5cca014ba51166f upstream.

This patch fixes a tunnel_dst null pointer dereference due to lockless access in the tunnel egress path. When deleting a vlan tunnel the tunnel_dst pointer is set to NULL without waiting a grace period (i.e. while it's still usable) and packets egressing are dereferencing it without checking. Use READ/WRITE_ONCE to annotate the lockless use of tunnel_id, use RCU for accessing tunnel_dst and make sure it is read only once and checked in the egress path. The dst is already properly RCU protected so we don't need to do anything fancy than to make sure tunnel_id and tunnel_dst are read only once and checked in the egress path.

Cc: stable@vger.kernel.org Fixes: 11538d039ac6 ("bridge: vlan dst_metadata hooks in ingress and egress paths") Signed-off-by: Nikolay Aleksandrov nikolay@nvidia.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/bridge/br_private.h | 4 ++-- net/bridge/br_vlan_tunnel.c | 38 ++++++++++++++++++++++++-------------- 2 files changed, 26 insertions(+), 16 deletions(-)

--- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -90,8 +90,8 @@ struct bridge_mcast_stats { #endif

struct br_tunnel_info { - __be64 tunnel_id; - struct metadata_dst *tunnel_dst; + __be64 tunnel_id; + struct metadata_dst __rcu *tunnel_dst; };

/* private vlan flags */ --- a/net/bridge/br_vlan_tunnel.c +++ b/net/bridge/br_vlan_tunnel.c @@ -41,26 +41,33 @@ static struct net_bridge_vlan *br_vlan_t br_vlan_tunnel_rht_params); }

+static void vlan_tunnel_info_release(struct net_bridge_vlan *vlan) +{ + struct metadata_dst *tdst = rtnl_dereference(vlan->tinfo.tunnel_dst); + + WRITE_ONCE(vlan->tinfo.tunnel_id, 0); + RCU_INIT_POINTER(vlan->tinfo.tunnel_dst, NULL); + dst_release(&tdst->dst); +} + void vlan_tunnel_info_del(struct net_bridge_vlan_group *vg, struct net_bridge_vlan *vlan) { - if (!vlan->tinfo.tunnel_dst) + if (!rcu_access_pointer(vlan->tinfo.tunnel_dst)) return; rhashtable_remove_fast(&vg->tunnel_hash, &vlan->tnode, br_vlan_tunnel_rht_params); - vlan->tinfo.tunnel_id = 0; - dst_release(&vlan->tinfo.tunnel_dst->dst); - vlan->tinfo.tunnel_dst = NULL; + vlan_tunnel_info_release(vlan); }

static int __vlan_tunnel_info_add(struct net_bridge_vlan_group *vg, struct net_bridge_vlan *vlan, u32 tun_id) { - struct metadata_dst *metadata = NULL; + struct metadata_dst *metadata = rtnl_dereference(vlan->tinfo.tunnel_dst); __be64 key = key32_to_tunnel_id(cpu_to_be32(tun_id)); int err;

- if (vlan->tinfo.tunnel_dst) + if (metadata) return -EEXIST;

metadata = __ip_tun_set_dst(0, 0, 0, 0, 0, TUNNEL_KEY, @@ -69,8 +76,8 @@ static int __vlan_tunnel_info_add(struct return -EINVAL;

metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_BRIDGE; - vlan->tinfo.tunnel_dst = metadata; - vlan->tinfo.tunnel_id = key; + rcu_assign_pointer(vlan->tinfo.tunnel_dst, metadata); + WRITE_ONCE(vlan->tinfo.tunnel_id, key);

err = rhashtable_lookup_insert_fast(&vg->tunnel_hash, &vlan->tnode, br_vlan_tunnel_rht_params); @@ -79,9 +86,7 @@ static int __vlan_tunnel_info_add(struct

return 0; out: - dst_release(&vlan->tinfo.tunnel_dst->dst); - vlan->tinfo.tunnel_dst = NULL; - vlan->tinfo.tunnel_id = 0; + vlan_tunnel_info_release(vlan);

return err; } @@ -182,12 +187,15 @@ int br_handle_ingress_vlan_tunnel(struct int br_handle_egress_vlan_tunnel(struct sk_buff *skb, struct net_bridge_vlan *vlan) { + struct metadata_dst *tunnel_dst; + __be64 tunnel_id; int err;

- if (!vlan || !vlan->tinfo.tunnel_id) + if (!vlan) return 0;

- if (unlikely(!skb_vlan_tag_present(skb))) + tunnel_id = READ_ONCE(vlan->tinfo.tunnel_id); + if (!tunnel_id || unlikely(!skb_vlan_tag_present(skb))) return 0;

skb_dst_drop(skb); @@ -195,7 +203,9 @@ int br_handle_egress_vlan_tunnel(struct if (err) return err;

- skb_dst_set(skb, dst_clone(&vlan->tinfo.tunnel_dst->dst)); + tunnel_dst = rcu_dereference(vlan->tinfo.tunnel_dst); + if (tunnel_dst) + skb_dst_set(skb, dst_clone(&tunnel_dst->dst));

return 0; }