- Kernel - mailweb.openeuler.org

[PATCH] sdei_watchdog: fix compile error when CONFIG_HARDLOCKUP_DETECTOR is not set
by Yang Yingliang 07 Jul '20

07 Jul '20

From: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> hulk inclusion category: bugfix bugzilla: NA CVE: NA ----------------------------------------------- sdei_watchdog use function 'watchdog_hardlockup_check()' to check whether a hardlockup exists. This function is included by CONFIG_HARDLOCKUP_DETECTOR. So select CONFIG_HARDLOCKUP_DETECTOR when CONFIG_SDEI_WATCHDOG is set. Otherwise a compile error as below will be shown. arch/arm64/kernel/watchdog_sdei.c: In function ‘watchdog_nmi_enable’: arch/arm64/kernel/watchdog_sdei.c:38:35: error: ‘watchdog_thresh’ undeclared (first use in this function) sdei_api_set_secure_timer_period(watchdog_thresh); ^ arch/arm64/kernel/watchdog_sdei.c:38:35: note: each undeclared identifier is reported only once for each function it appears in arch/arm64/kernel/watchdog_sdei.c: In function ‘watchdog_nmi_probe’: arch/arm64/kernel/watchdog_sdei.c:119:39: error: ‘watchdog_thresh’ undeclared (first use in this function) if (sdei_api_set_secure_timer_period(watchdog_thresh)) { Signed-off-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> Reviewed-by: Hanjun Guo <guohanjun(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- lib/Kconfig.debug | 1 + 1 file changed, 1 insertion(+) diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index bc65f3b8a8b5..47dca144782b 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -845,6 +845,7 @@ config SDEI_WATCHDOG bool "SDEI NMI Watchdog support" depends on ARM_SDE_INTERFACE && !HARDLOCKUP_CHECK_TIMESTAMP select HAVE_HARDLOCKUP_DETECTOR_ARCH + select HARDLOCKUP_DETECTOR config PMU_WATCHDOG bool "PMU NMI Watchdog support" -- 2.25.1

1 0

[PATCH 1/2] net/hinic: Add support for X86 Arch
by Yang Yingliang 07 Jul '20

07 Jul '20

From: Chiqijun <chiqijun(a)huawei.com> driver inclusion category: feature bugzilla: 4472 ----------------------------------------------------------------------- Add support for X86 Arch. Add the best default interrupt aggregation parameter and LRO parameter on x86 platform. Signed-off-by: Chiqijun <chiqijun(a)huawei.com> Reviewed-by: Zengweiliang <zengweiliang.zengweiliang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/net/ethernet/huawei/Kconfig | 1 - drivers/net/ethernet/huawei/hinic/hinic_hwif.c | 10 ++++++++++ drivers/net/ethernet/huawei/hinic/hinic_hwif.h | 4 ++++ drivers/net/ethernet/huawei/hinic/hinic_lld.c | 17 ++++++++++++++++- drivers/net/ethernet/huawei/hinic/hinic_main.c | 6 ++++++ .../net/ethernet/huawei/hinic/hinic_nic_cfg.h | 14 ++++++++++++++ 6 files changed, 50 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/huawei/Kconfig b/drivers/net/ethernet/huawei/Kconfig index dc48e5163531..c1a95ae4058b 100644 --- a/drivers/net/ethernet/huawei/Kconfig +++ b/drivers/net/ethernet/huawei/Kconfig @@ -5,7 +5,6 @@ config NET_VENDOR_HUAWEI bool "Huawei devices" default y - depends on ARM64 ---help--- If you have a network (Ethernet) card belonging to this class, say Y. Note that the answer to this question doesn't directly affect the diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hwif.c b/drivers/net/ethernet/huawei/hinic/hinic_hwif.c index 1fc0fa57f313..b267084d3672 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hwif.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hwif.c @@ -368,7 +368,12 @@ void hinic_free_db_addr(void *hwdev, void __iomem *db_base, hwif = ((struct hinic_hwdev *)hwdev)->hwif; idx = DB_IDX(db_base, hwif->db_base); +#if defined(__aarch64__) /* No need to unmap */ +#else + if (dwqe_base && hwif->chip_mode == CHIP_MODE_NORMAL) + io_mapping_unmap(dwqe_base); +#endif free_db_idx(hwif, idx); } @@ -398,7 +403,12 @@ int hinic_alloc_db_addr(void *hwdev, void __iomem **db_base, offset = ((u64)idx) << PAGE_SHIFT; +#if defined(__aarch64__) *dwqe_base = hwif->dwqe_mapping + offset; +#else + *dwqe_base = io_mapping_map_wc(hwif->dwqe_mapping, offset, + HINIC_DB_PAGE_SIZE); +#endif if (!(*dwqe_base)) { hinic_free_db_addr(hwdev, *db_base, NULL); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hwif.h b/drivers/net/ethernet/huawei/hinic/hinic_hwif.h index 9cd2ad8c5962..3a58a44b6bfe 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hwif.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hwif.h @@ -58,7 +58,11 @@ struct hinic_hwif { u64 db_base_phy; u8 __iomem *db_base; +#if defined(__aarch64__) void __iomem *dwqe_mapping; +#else + struct io_mapping *dwqe_mapping; +#endif struct hinic_free_db_area free_db_area; struct hinic_func_attr attr; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_lld.c b/drivers/net/ethernet/huawei/hinic/hinic_lld.c index 2ad6d2d23207..20e3b0bde8ef 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_lld.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_lld.c @@ -114,7 +114,11 @@ struct hinic_pcidev { u64 db_base_phy; void __iomem *db_base; +#if defined(__aarch64__) void __iomem *dwqe_mapping; +#else + struct io_mapping *dwqe_mapping; +#endif /* lock for attach/detach uld */ struct mutex pdev_mutex; struct hinic_sriov_info sriov_info; @@ -1874,9 +1878,15 @@ static int mapping_bar(struct pci_dev *pdev, struct hinic_pcidev *pci_adapter) dwqe_addr = pci_adapter->db_base_phy + db_dwqe_size; +#if defined(__aarch64__) /* arm do not support call ioremap_wc() */ pci_adapter->dwqe_mapping = __ioremap(dwqe_addr, db_dwqe_size, __pgprot(PROT_DEVICE_nGnRnE)); +#else + pci_adapter->dwqe_mapping = io_mapping_create_wc(dwqe_addr, + db_dwqe_size); + +#endif if (!pci_adapter->dwqe_mapping) { sdk_err(&pci_adapter->pcidev->dev, "Failed to io_mapping_create_wc\n"); goto mapping_dwqe_err; @@ -1898,8 +1908,13 @@ static int mapping_bar(struct pci_dev *pdev, struct hinic_pcidev *pci_adapter) static void unmapping_bar(struct hinic_pcidev *pci_adapter) { - if (pci_adapter->chip_mode == CHIP_MODE_NORMAL) + if (pci_adapter->chip_mode == CHIP_MODE_NORMAL) { +#if defined(__aarch64__) iounmap(pci_adapter->dwqe_mapping); +#else + io_mapping_free(pci_adapter->dwqe_mapping); +#endif + } iounmap(pci_adapter->db_base); iounmap(pci_adapter->intr_reg_base); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index dd67d903f739..d78a5e3678b1 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -2908,7 +2908,13 @@ static void adaptive_configuration_init(struct hinic_nic_dev *nic_dev) nic_dev->env_info.os = HINIC_OS_HUAWEI; +#if defined(__aarch64__) nic_dev->env_info.cpu = HINIC_CPU_ARM_GENERIC; +#elif defined(__x86_64__) + nic_dev->env_info.cpu = HINIC_CPU_X86_GENERIC; +#else + nic_dev->env_info.cpu = HINIC_CPU_UNKNOWN; +#endif nic_info(&nic_dev->pdev->dev, "Board type %u, OS type %u, CPU type %u\n", diff --git a/drivers/net/ethernet/huawei/hinic/hinic_nic_cfg.h b/drivers/net/ethernet/huawei/hinic/hinic_nic_cfg.h index e0979df6e209..243265072710 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_nic_cfg.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_nic_cfg.h @@ -56,6 +56,7 @@ #define HINIC_LRO_RX_TIMER_DEFAULT_PG_10GE 10 #define HINIC_LRO_RX_TIMER_DEFAULT_PG_100GE 8 +#if defined(__aarch64__) #define HINIC_LOWEST_LATENCY 1 #define HINIC_RX_RATE_LOW 400000 #define HINIC_RX_COAL_TIME_LOW 20 @@ -67,6 +68,19 @@ #define HINIC_TX_RATE_THRESH 35000 #define HINIC_RX_RATE_LOW_VM 400000 #define HINIC_RX_PENDING_LIMIT_HIGH_VM 50 +#else +#define HINIC_LOWEST_LATENCY 1 +#define HINIC_RX_RATE_LOW 400000 +#define HINIC_RX_COAL_TIME_LOW 16 +#define HINIC_RX_PENDING_LIMIT_LOW 2 +#define HINIC_RX_RATE_HIGH 1000000 +#define HINIC_RX_COAL_TIME_HIGH 225 +#define HINIC_RX_PENDING_LIMIT_HIGH 8 +#define HINIC_RX_RATE_THRESH 50000 +#define HINIC_TX_RATE_THRESH 50000 +#define HINIC_RX_RATE_LOW_VM 100000 +#define HINIC_RX_PENDING_LIMIT_HIGH_VM 87 +#endif enum hinic_board_type { HINIC_BOARD_UNKNOWN = 0, -- 2.25.1

1 1

[PATCH 00/13] steal tasks to improve CPU utilization
by Yang Yingliang 07 Jul '20

07 Jul '20

Cheng Jian (3): disable stealing by default sched/fair: introduce SCHED_STEAL config: enable CONFIG_SCHED_STEAL by default Steve Sistare (10): sched: Provide sparsemask, a reduced contention bitmap sched/topology: Provide hooks to allocate data shared per LLC sched/topology: Provide cfs_overload_cpus bitmap sched/fair: Dynamically update cfs_overload_cpus sched/fair: Hoist idle_stamp up from idle_balance sched/fair: Generalize the detach_task interface sched/fair: Provide can_migrate_task_llc sched/fair: Steal work from an overloaded CPU when CPU goes idle sched/fair: disable stealing if too many NUMA nodes sched/fair: Provide idle search schedstats arch/arm64/configs/euleros_defconfig | 1 + arch/arm64/configs/hulk_defconfig | 1 + arch/arm64/configs/openeuler_defconfig | 1 + arch/arm64/configs/storage_ci_defconfig | 1 + arch/arm64/configs/syzkaller_defconfig | 1 + arch/x86/configs/hulk_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + arch/x86/configs/storage_ci_defconfig | 1 + include/linux/sched/topology.h | 3 + init/Kconfig | 15 + kernel/sched/core.c | 35 ++- kernel/sched/fair.c | 367 ++++++++++++++++++++++-- kernel/sched/features.h | 8 + kernel/sched/sched.h | 20 ++ kernel/sched/sparsemask.h | 210 ++++++++++++++ kernel/sched/stats.c | 15 + kernel/sched/stats.h | 20 ++ kernel/sched/topology.c | 141 ++++++++- 18 files changed, 810 insertions(+), 32 deletions(-) create mode 100644 kernel/sched/sparsemask.h -- 2.25.1

1 13

[PATCH 001/125] net: be more gentle about silly gso requests coming from user
by Yang Yingliang 07 Jul '20

07 Jul '20

From: Eric Dumazet <edumazet(a)google.com> commit 7c6d2ecbda83150b2036a2b36b21381ad4667762 upstream. Recent change in virtio_net_hdr_to_skb() broke some packetdrill tests. When --mss=XXX option is set, packetdrill always provide gso_type & gso_size for its inbound packets, regardless of packet size. if (packet->tcp && packet->mss) { if (packet->ipv4) gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV6; gso.gso_size = packet->mss; } Since many other programs could do the same, relax virtio_net_hdr_to_skb() to no longer return an error, but instead ignore gso settings. This keeps Willem intent to make sure no malicious packet could reach gso stack. Note that TCP stack has a special logic in tcp_set_skb_tso_segs() to clear gso_size for small packets. Fixes: 6dd912f82680 ("net: check untrusted gso_size at kernel entry") Signed-off-by: Eric Dumazet <edumazet(a)google.com> Cc: Willem de Bruijn <willemb(a)google.com> Acked-by: Willem de Bruijn <willemb(a)google.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Cc: Guenter Roeck <linux(a)roeck-us.net> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- include/linux/virtio_net.h | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 1c296f370e46..f32fe7080d2e 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -109,16 +109,17 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size); + struct skb_shared_info *shinfo = skb_shinfo(skb); - if (skb->len - p_off <= gso_size) - return -EINVAL; - - skb_shinfo(skb)->gso_size = gso_size; - skb_shinfo(skb)->gso_type = gso_type; + /* Too small packets are not really GSO ones. */ + if (skb->len - p_off > gso_size) { + shinfo->gso_size = gso_size; + shinfo->gso_type = gso_type; - /* Header must be checked, and gso_segs computed. */ - skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; - skb_shinfo(skb)->gso_segs = 0; + /* Header must be checked, and gso_segs computed. */ + shinfo->gso_type |= SKB_GSO_DODGY; + shinfo->gso_segs = 0; + } } return 0; -- 2.25.1

1 124

[PATCH 01/35] selinux: allow labeling before policy is loaded
by Roberto Sassu 06 Jul '20

06 Jul '20

From: Jonathan Lebon <jlebon(a)redhat.com> mainline inclusion from mainline-v5.5-rc1 commit 3e3e24b42043eceb97ed834102c2d094dfd7aaa6 category: bugfix --------------------------- Currently, the SELinux LSM prevents one from setting the `security.selinux` xattr on an inode without a policy first being loaded. However, this restriction is problematic: it makes it impossible to have newly created files with the correct label before actually loading the policy. This is relevant in distributions like Fedora, where the policy is loaded by systemd shortly after pivoting out of the initrd. In such instances, all files created prior to pivoting will be unlabeled. One then has to relabel them after pivoting, an operation which inherently races with other processes trying to access those same files. Going further, there are use cases for creating the entire root filesystem on first boot from the initrd (e.g. Container Linux supports this today[1], and we'd like to support it in Fedora CoreOS as well[2]). One can imagine doing this in two ways: at the block device level (e.g. laying down a disk image), or at the filesystem level. In the former, labeling can simply be part of the image. But even in the latter scenario, one still really wants to be able to set the right labels when populating the new filesystem. This patch enables this by changing behaviour in the following two ways: 1. allow `setxattr` on mounts without `SBLABEL_MNT` (which is all of them if no policy is loaded yet) 2. don't try to set the in-core inode SID if we're not initialized; instead leave it as `LABEL_INVALID` so that revalidation may be attempted at a later time Note the first hunk of this patch is functionally the same as a previously discussed one[3], though it was part of a larger series which wasn't accepted. Co-developed-by: Victor Kamensky <kamensky(a)cisco.com> Signed-off-by: Victor Kamensky <kamensky(a)cisco.com> Signed-off-by: Jonathan Lebon <jlebon(a)redhat.com> [1] https://coreos.com/os/docs/latest/root-filesystem-placement.html [2] https://github.com/coreos/fedora-coreos-tracker/issues/94 [3] https://www.spinics.net/lists/linux-initramfs/msg04593.html --- security/selinux/hooks.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 452254fd89f8..931546d80211 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3305,7 +3305,7 @@ static int selinux_inode_setxattr(struct dentry *dentry, const char *name, } sbsec = inode->i_sb->s_security; - if (!(sbsec->flags & SBLABEL_MNT)) + if (!(sbsec->flags & SBLABEL_MNT) && selinux_state.initialized) return -EOPNOTSUPP; if (!inode_owner_or_capable(inode)) @@ -3387,6 +3387,15 @@ static void selinux_inode_post_setxattr(struct dentry *dentry, const char *name, return; } + if (!selinux_state.initialized) { + /* If we haven't even been initialized, then we can't validate + * against a policy, so leave the label as invalid. It may + * resolve to a valid label on the next revalidation try if + * we've since initialized. + */ + return; + } + rc = security_context_to_sid_force(&selinux_state, value, size, &newsid); if (rc) { -- 2.27.GIT

1 4

[PATCH] fs/filescontrol: add a switch to enable / disable accounting of open fds
by Yang Yingliang 02 Jul '20

02 Jul '20

From: Yu Kuai <yukuai3(a)huawei.com> hulk inclusion category: bugfix bugzilla: 38268 CVE: NA --------------------------- Such switch can only set the accounting of open fds in filescontrol from enable to disable. If it is disabled arealdy, the switch can't enable it. The counter is enabled by default, and it can be disabled by: a. echo 1 > /sys/fs/cgroup/files/files.no_acct b. add "filescontrol.no_acct=1" to boot cmd Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Reviewed-by: zhangyi (F) <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/filescontrol.c | 30 +++++++++++++++++++++++++++--- 1 file changed, 27 insertions(+), 3 deletions(-) diff --git a/fs/filescontrol.c b/fs/filescontrol.c index 5ec5096383c3..32f3a127579c 100644 --- a/fs/filescontrol.c +++ b/fs/filescontrol.c @@ -25,14 +25,17 @@ #include <linux/seq_file.h> #include <linux/fdtable.h> #include <linux/sched/signal.h> +#include <linux/module.h> #define FILES_MAX D_COUNT_MAX #define FILES_MAX_STR "max" - +static bool no_acct; struct cgroup_subsys files_cgrp_subsys __read_mostly; EXPORT_SYMBOL(files_cgrp_subsys); +module_param(no_acct, bool, 0444); + struct files_cgroup { struct cgroup_subsys_state css; struct page_counter open_handles; @@ -204,7 +207,7 @@ int files_cgroup_alloc_fd(struct files_struct *files, u64 n) * we don't charge their fds, only issue is that files.usage * won't be accurate in root files cgroup. */ - if (files != &init_files) { + if (!no_acct && files != &init_files) { struct page_counter *fail_res; struct files_cgroup *files_cgroup = files_cgroup_from_files(files); @@ -222,7 +225,7 @@ void files_cgroup_unalloc_fd(struct files_struct *files, u64 n) * It's not charged so no need to uncharge, see comments in * files_cgroup_alloc_fd. */ - if (files != &init_files) { + if (!no_acct && files != &init_files) { struct files_cgroup *files_cgroup = files_cgroup_from_files(files); page_counter_uncharge(&files_cgroup->open_handles, n); @@ -230,6 +233,21 @@ void files_cgroup_unalloc_fd(struct files_struct *files, u64 n) } EXPORT_SYMBOL(files_cgroup_unalloc_fd); +static u64 files_disabled_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return no_acct; +} + +static int files_disabled_write(struct cgroup_subsys_state *css, + struct cftype *cft, u64 val) +{ + if (!val) + return -EINVAL; + no_acct = true; + + return 0; +} static int files_limit_read(struct seq_file *sf, void *v) { @@ -291,6 +309,12 @@ static struct cftype files[] = { .name = "usage", .read_u64 = files_usage_read, }, + { + .name = "no_acct", + .flags = CFTYPE_ONLY_ON_ROOT, + .read_u64 = files_disabled_read, + .write_u64 = files_disabled_write, + }, { } }; -- 2.25.1

1 0

[PATCH] usb: usbtest: fix missing kfree(dev->buf) in usbtest_disconnect
by Yang Yingliang 01 Jul '20

01 Jul '20

From: Zqiang <qiang.zhang(a)windriver.com> mainline inclusion from mainline-v5.8-rc3 commit 28ebeb8db77035e058a510ce9bd17c2b9a009dba category: bugfix bugzilla: NA CVE: CVE-2020-15393 --------------------------- BUG: memory leak unreferenced object 0xffff888055046e00 (size 256): comm "kworker/2:9", pid 2570, jiffies 4294942129 (age 1095.500s) hex dump (first 32 bytes): 00 70 04 55 80 88 ff ff 18 bb 5a 81 ff ff ff ff .p.U......Z..... f5 96 78 81 ff ff ff ff 37 de 8e 81 ff ff ff ff ..x.....7....... backtrace: [<00000000d121dccf>] kmemleak_alloc_recursive include/linux/kmemleak.h:43 [inline] [<00000000d121dccf>] slab_post_alloc_hook mm/slab.h:586 [inline] [<00000000d121dccf>] slab_alloc_node mm/slub.c:2786 [inline] [<00000000d121dccf>] slab_alloc mm/slub.c:2794 [inline] [<00000000d121dccf>] kmem_cache_alloc_trace+0x15e/0x2d0 mm/slub.c:2811 [<000000005c3c3381>] kmalloc include/linux/slab.h:555 [inline] [<000000005c3c3381>] usbtest_probe+0x286/0x19d0 drivers/usb/misc/usbtest.c:2790 [<000000001cec6910>] usb_probe_interface+0x2bd/0x870 drivers/usb/core/driver.c:361 [<000000007806c118>] really_probe+0x48d/0x8f0 drivers/base/dd.c:551 [<00000000a3308c3e>] driver_probe_device+0xfc/0x2a0 drivers/base/dd.c:724 [<000000003ef66004>] __device_attach_driver+0x1b6/0x240 drivers/base/dd.c:831 [<00000000eee53e97>] bus_for_each_drv+0x14e/0x1e0 drivers/base/bus.c:431 [<00000000bb0648d0>] __device_attach+0x1f9/0x350 drivers/base/dd.c:897 [<00000000838b324a>] device_initial_probe+0x1a/0x20 drivers/base/dd.c:944 [<0000000030d501c1>] bus_probe_device+0x1e1/0x280 drivers/base/bus.c:491 [<000000005bd7adef>] device_add+0x131d/0x1c40 drivers/base/core.c:2504 [<00000000a0937814>] usb_set_configuration+0xe84/0x1ab0 drivers/usb/core/message.c:2030 [<00000000e3934741>] generic_probe+0x6a/0xe0 drivers/usb/core/generic.c:210 [<0000000098ade0f1>] usb_probe_device+0x90/0xd0 drivers/usb/core/driver.c:266 [<000000007806c118>] really_probe+0x48d/0x8f0 drivers/base/dd.c:551 [<00000000a3308c3e>] driver_probe_device+0xfc/0x2a0 drivers/base/dd.c:724 Acked-by: Alan Stern <stern(a)rowland.harvard.edu> Reported-by: Kyungtae Kim <kt0755(a)gmail.com> Signed-off-by: Zqiang <qiang.zhang(a)windriver.com> Link: https://lore.kernel.org/r/20200612035210.20494-1-qiang.zhang@windriver.com Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/usb/misc/usbtest.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/misc/usbtest.c b/drivers/usb/misc/usbtest.c index c7f82310e73e..fc3fc9d48a55 100644 --- a/drivers/usb/misc/usbtest.c +++ b/drivers/usb/misc/usbtest.c @@ -2853,6 +2853,7 @@ static void usbtest_disconnect(struct usb_interface *intf) usb_set_intfdata(intf, NULL); dev_dbg(&intf->dev, "disconnect\n"); + kfree(dev->buf); kfree(dev); } -- 2.25.1

1 0

[PATCH] genirq/debugfs: Add missing sanity checks to interrupt injection
by Yang Yingliang 01 Jul '20

01 Jul '20

From: Thomas Gleixner <tglx(a)linutronix.de> mainline inclusion from mainline-v5.6 commit a740a423c36932695b01a3e920f697bc55b05fec category: bugfix bugzilla: 32425 CVE: NA ------------------- Interrupts cannot be injected when the interrupt is not activated and when a replay is already in progress. Fixes: 536e2e34bd00 ("genirq/debugfs: Triggering of interrupts from userspace") Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Acked-by: Marc Zyngier <maz(a)kernel.org> Link: https://lkml.kernel.org/r/20200306130623.500019114@linutronix.de Signed-off-by: Yuan Can <yuancan(a)huawei.com> Reviewed-by: Hanjun Guo <guohanjun(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- kernel/irq/debugfs.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c index 0a7365456e72..4eb5c62991fe 100644 --- a/kernel/irq/debugfs.c +++ b/kernel/irq/debugfs.c @@ -206,8 +206,15 @@ static ssize_t irq_debug_write(struct file *file, const char __user *user_buf, chip_bus_lock(desc); raw_spin_lock_irqsave(&desc->lock, flags); - if (irq_settings_is_level(desc) || desc->istate & IRQS_NMI) { - /* Can't do level nor NMIs, sorry */ + /* + * Don't allow injection when the interrupt is: + * - Level or NMI type + * - not activated + * - replaying already + */ + if (irq_settings_is_level(desc) || + !irqd_is_activated(&desc->irq_data) || + (desc->istate & (IRQS_NMI | IRQS_REPLAY))) { err = -EINVAL; } else { desc->istate |= IRQS_PENDING; -- 2.25.1

1 0

[PATCH] perf top: Fix stdio interface input handling with glibc 2.28+
by Yang Yingliang 01 Jul '20

01 Jul '20

From: Tommi Rantala <tommi.t.rantala(a)nokia.com> mainline inclusion from mainline-5.6-rc6 commit 29b4f5f18857 category: bugfix bugzilla: 31774 CVE: NA ------------------------------------------------- Since glibc 2.28 when running 'perf top --stdio', input handling no longer works, but hitting any key always just prints the "Mapped keys" help text. To fix it, call clearerr() in the display_thread() loop to clear any EOF sticky errors, as instructed in the glibc NEWS file (https://sourceware.org/git/?p=glibc.git;a=blob;f=NEWS): * All stdio functions now treat end-of-file as a sticky condition. If you read from a file until EOF, and then the file is enlarged by another process, you must call clearerr or another function with the same effect (e.g. fseek, rewind) before you can read the additional data. This corrects a longstanding C99 conformance bug. It is most likely to affect programs that use stdio to read interactive input from a terminal. (Bug #1190.) Signed-off-by: Tommi Rantala <tommi.t.rantala(a)nokia.com> Tested-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> Cc: Alexander Shishkin <alexander.shishkin(a)linux.intel.com> Cc: Jiri Olsa <jolsa(a)redhat.com> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Namhyung Kim <namhyung(a)kernel.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Link: http://lore.kernel.org/lkml/20200305083714.9381-2-tommi.t.rantala@nokia.com Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> Signed-off-by: Wei Li <liwei391(a)huawei.com> Reviewed-by: Jian Cheng <cj.chengjian(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- tools/perf/builtin-top.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 781f6cf1cda6..265c074cbe3b 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -661,7 +661,9 @@ static void *display_thread(void *arg) delay_msecs = top->delay_secs * MSEC_PER_SEC; set_term_quiet_input(&save); /* trash return*/ - getc(stdin); + clearerr(stdin); + if (poll(&stdin_poll, 1, 0) > 0) + getc(stdin); while (!done) { perf_top__print_sym_table(top); -- 2.25.1

1 0

[PATCH] vfio/pci: Fix SR-IOV VF handling with MMIO blocking
by Yang Yingliang 30 Jun '20

30 Jun '20

From: Alex Williamson <alex.williamson(a)redhat.com> mainline inclusion from mainline-v5.8-rc3 commit ebfa440ce38b7e2e04c3124aa89c8a9f4094cf21 category: bugfix bugzilla: NA CVE: CVE-2020-12888 --------------------------- SR-IOV VFs do not implement the memory enable bit of the command register, therefore this bit is not set in config space after pci_enable_device(). This leads to an unintended difference between PF and VF in hand-off state to the user. We can correct this by setting the initial value of the memory enable bit in our virtualized config space. There's really no need however to ever fault a user on a VF though as this would only indicate an error in the user's management of the enable bit, versus a PF where the same access could trigger hardware faults. Fixes: abafbc551fdd ("vfio-pci: Invalidate mmaps and block MMIO access on disabled memory") Signed-off-by: Alex Williamson <alex.williamson(a)redhat.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/vfio/pci/vfio_pci_config.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c index 4fe71fbce194..a1a26465d224 100644 --- a/drivers/vfio/pci/vfio_pci_config.c +++ b/drivers/vfio/pci/vfio_pci_config.c @@ -401,9 +401,15 @@ static inline void p_setd(struct perm_bits *p, int off, u32 virt, u32 write) /* Caller should hold memory_lock semaphore */ bool __vfio_pci_memory_enabled(struct vfio_pci_device *vdev) { + struct pci_dev *pdev = vdev->pdev; u16 cmd = le16_to_cpu(*(__le16 *)&vdev->vconfig[PCI_COMMAND]); - return cmd & PCI_COMMAND_MEMORY; + /* + * SR-IOV VF memory enable is handled by the MSE bit in the + * PF SR-IOV capability, there's therefore no need to trigger + * faults based on the virtual value. + */ + return pdev->is_virtfn || (cmd & PCI_COMMAND_MEMORY); } /* @@ -1732,6 +1738,15 @@ int vfio_config_init(struct vfio_pci_device *vdev) vconfig[PCI_INTERRUPT_PIN]); vconfig[PCI_INTERRUPT_PIN] = 0; /* Gratuitous for good VFs */ + + /* + * VFs do no implement the memory enable bit of the COMMAND + * register therefore we'll not have it set in our initial + * copy of config space after pci_enable_device(). For + * consistency with PFs, set the virtual enable bit here. + */ + *(__le16 *)&vconfig[PCI_COMMAND] |= + cpu_to_le16(PCI_COMMAND_MEMORY); } if (!IS_ENABLED(CONFIG_VFIO_PCI_INTX) || vdev->nointx) -- 2.25.1

1 0

[PATCH 1/5] sched/core: Create task_has_idle_policy() helper
by Yang Yingliang 30 Jun '20

30 Jun '20

From: Viresh Kumar <viresh.kumar(a)linaro.org> mainline inclusion from mainline-v5.0-rc1 commit 1da1843f9f0334e2428308945d396ffecc2acfe1 category: feature bugzilla: 38260 CVE: NA --------------------------- We already have task_has_rt_policy() and task_has_dl_policy() helpers, create task_has_idle_policy() as well and update sched core to start using it. While at it, use task_has_dl_policy() at one more place. Signed-off-by: Viresh Kumar <viresh.kumar(a)linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Acked-by: Daniel Lezcano <daniel.lezcano(a)linaro.org> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Vincent Guittot <vincent.guittot(a)linaro.org> Link: http://lkml.kernel.org/r/ce3915d5b490fc81af926a3b6bfb775e7188e005.154141689… Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Cheng Jian <cj.chengjian(a)huawei.com> Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- kernel/sched/core.c | 4 ++-- kernel/sched/debug.c | 2 +- kernel/sched/fair.c | 10 +++++----- kernel/sched/sched.h | 5 +++++ 4 files changed, 13 insertions(+), 8 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 0fbdc620697b..c1513905c0de 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -724,7 +724,7 @@ static void set_load_weight(struct task_struct *p, bool update_load) /* * SCHED_IDLE tasks get minimal weight: */ - if (idle_policy(p->policy)) { + if (task_has_idle_policy(p)) { load->weight = scale_load(WEIGHT_IDLEPRIO); load->inv_weight = WMULT_IDLEPRIO; return; @@ -4270,7 +4270,7 @@ static int __sched_setscheduler(struct task_struct *p, * Treat SCHED_IDLE as nice 20. Only allow a switch to * SCHED_NORMAL if the RLIMIT_NICE would normally permit it. */ - if (idle_policy(p->policy) && !idle_policy(policy)) { + if (task_has_idle_policy(p) && !idle_policy(policy)) { if (!can_nice(p, task_nice(p))) return -EPERM; } diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index c542d84dafce..f12382877390 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -1012,7 +1012,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, #endif P(policy); P(prio); - if (p->policy == SCHED_DEADLINE) { + if (task_has_dl_policy(p)) { P(dl.runtime); P(dl.deadline); } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 09b0d83d5bbc..807c7fb78b6f 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6609,7 +6609,7 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se) static void set_last_buddy(struct sched_entity *se) { - if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE)) + if (entity_is_task(se) && unlikely(task_has_idle_policy(task_of(se)))) return; for_each_sched_entity(se) { @@ -6621,7 +6621,7 @@ static void set_last_buddy(struct sched_entity *se) static void set_next_buddy(struct sched_entity *se) { - if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE)) + if (entity_is_task(se) && unlikely(task_has_idle_policy(task_of(se)))) return; for_each_sched_entity(se) { @@ -6679,8 +6679,8 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ return; /* Idle tasks are by definition preempted by non-idle tasks. */ - if (unlikely(curr->policy == SCHED_IDLE) && - likely(p->policy != SCHED_IDLE)) + if (unlikely(task_has_idle_policy(curr)) && + likely(!task_has_idle_policy(p))) goto preempt; /* @@ -7090,7 +7090,7 @@ static int task_hot(struct task_struct *p, struct lb_env *env) if (p->sched_class != &fair_sched_class) return 0; - if (unlikely(p->policy == SCHED_IDLE)) + if (unlikely(task_has_idle_policy(p))) return 0; /* diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 955abd645ff9..fbe3b3b8a19f 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -184,6 +184,11 @@ static inline bool valid_policy(int policy) rt_policy(policy) || dl_policy(policy); } +static inline int task_has_idle_policy(struct task_struct *p) +{ + return idle_policy(p->policy); +} + static inline int task_has_rt_policy(struct task_struct *p) { return rt_policy(p->policy); -- 2.25.1

1 4

[PATCH 001/204] power: supply: bq24257_charger: Replace depends on REGMAP_I2C with select
by Yang Yingliang 29 Jun '20

29 Jun '20

From: Enric Balletbo i Serra <enric.balletbo(a)collabora.com> [ Upstream commit 87c3d579c8ed0eaea6b1567d529a8daa85a2bc6c ] regmap is a library function that gets selected by drivers that need it. No driver modules should depend on it. Depending on REGMAP_I2C makes this driver only build if another driver already selected REGMAP_I2C, as the symbol can't be selected through the menu kernel configuration. Fixes: 2219a935963e ("power_supply: Add TI BQ24257 charger driver") Signed-off-by: Enric Balletbo i Serra <enric.balletbo(a)collabora.com> Signed-off-by: Sebastian Reichel <sebastian.reichel(a)collabora.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/power/supply/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/power/supply/Kconfig b/drivers/power/supply/Kconfig index ff6dab0bf0dd..76c699b5abda 100644 --- a/drivers/power/supply/Kconfig +++ b/drivers/power/supply/Kconfig @@ -555,7 +555,7 @@ config CHARGER_BQ24257 tristate "TI BQ24250/24251/24257 battery charger driver" depends on I2C depends on GPIOLIB || COMPILE_TEST - depends on REGMAP_I2C + select REGMAP_I2C help Say Y to enable support for the TI BQ24250, BQ24251, and BQ24257 battery chargers. -- 2.25.1

1 203

[PATCH 1/2] Revert "ipmi: fix sleep-in-atomic in free_user at cleanup SRCU user->release_barrier"
by Yang Yingliang 29 Jun '20

29 Jun '20

hulk inclusion category: bugfix bugzilla: 5499 CVE: NA --------------------------- cleanup_srcu_struct_quiesced won't free memory if work_pending() is true, and it will cause a memory leak, so revert it and using mainline patch instead. Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Hanjun Guo <guohanjun(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/char/ipmi/ipmi_msghandler.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index 0085d32cef46..7510013f28f8 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -1190,12 +1190,7 @@ EXPORT_SYMBOL(ipmi_get_smi_info); static void free_user(struct kref *ref) { struct ipmi_user *user = container_of(ref, struct ipmi_user, refcount); - - /* - * Cleanup without waiting. This could be called in atomic context. - * Refcount is zero: all read-sections should have been ended. - */ - cleanup_srcu_struct_quiesced(&user->release_barrier); + cleanup_srcu_struct(&user->release_barrier); kfree(user); } -- 2.25.1

1 1

[PATCH 001/257] ipv6: fix IPV6_ADDRFORM operation logic
by Yang Yingliang 29 Jun '20

29 Jun '20

From: Hangbin Liu <liuhangbin(a)gmail.com> [ Upstream commit 79a1f0ccdbb4ad700590f61b00525b390cb53905 ] Socket option IPV6_ADDRFORM supports UDP/UDPLITE and TCP at present. Previously the checking logic looks like: if (sk->sk_protocol == IPPROTO_UDP || sk->sk_protocol == IPPROTO_UDPLITE) do_some_check; else if (sk->sk_protocol != IPPROTO_TCP) break; After commit b6f6118901d1 ("ipv6: restrict IPV6_ADDRFORM operation"), TCP was blocked as the logic changed to: if (sk->sk_protocol == IPPROTO_UDP || sk->sk_protocol == IPPROTO_UDPLITE) do_some_check; else if (sk->sk_protocol == IPPROTO_TCP) do_some_check; break; else break; Then after commit 82c9ae440857 ("ipv6: fix restrict IPV6_ADDRFORM operation") UDP/UDPLITE were blocked as the logic changed to: if (sk->sk_protocol == IPPROTO_UDP || sk->sk_protocol == IPPROTO_UDPLITE) do_some_check; if (sk->sk_protocol == IPPROTO_TCP) do_some_check; if (sk->sk_protocol != IPPROTO_TCP) break; Fix it by using Eric's code and simply remove the break in TCP check, which looks like: if (sk->sk_protocol == IPPROTO_UDP || sk->sk_protocol == IPPROTO_UDPLITE) do_some_check; else if (sk->sk_protocol == IPPROTO_TCP) do_some_check; else break; Fixes: 82c9ae440857 ("ipv6: fix restrict IPV6_ADDRFORM operation") Signed-off-by: Hangbin Liu <liuhangbin(a)gmail.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- net/ipv6/ipv6_sockglue.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index f255eaaf0136..9ca4e8657534 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -187,14 +187,15 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, retv = -EBUSY; break; } - } - if (sk->sk_protocol == IPPROTO_TCP && - sk->sk_prot != &tcpv6_prot) { - retv = -EBUSY; + } else if (sk->sk_protocol == IPPROTO_TCP) { + if (sk->sk_prot != &tcpv6_prot) { + retv = -EBUSY; + break; + } + } else { break; } - if (sk->sk_protocol != IPPROTO_TCP) - break; + if (sk->sk_state != TCP_ESTABLISHED) { retv = -ENOTCONN; break; -- 2.25.1

1 256

[PATCH 1/3] vfio/type1: Support faulting PFNMAP vmas
by Yang Yingliang 28 Jun '20

28 Jun '20

From: Alex Williamson <alex.williamson(a)redhat.com> mainline inclusion from mainline-v5.8-rc1 commit 41311242221e3482b20bfed10fa4d9db98d87016 category: bugfix bugzilla: NA CVE: CVE-2020-12888 --------------------------- With conversion to follow_pfn(), DMA mapping a PFNMAP range depends on the range being faulted into the vma. Add support to manually provide that, in the same way as done on KVM with hva_to_pfn_remapped(). Reviewed-by: Peter Xu <peterx(a)redhat.com> Signed-off-by: Alex Williamson <alex.williamson(a)redhat.com> Conflicts: drivers/vfio/vfio_iommu_type1.c [yyl: adjust context] Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/vfio/vfio_iommu_type1.c | 36 ++++++++++++++++++++++++++++++--- 1 file changed, 33 insertions(+), 3 deletions(-) diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 4bfc79635c6a..01be1496307b 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -346,6 +346,32 @@ static int put_pfn(unsigned long pfn, int prot) return 0; } +static int follow_fault_pfn(struct vm_area_struct *vma, struct mm_struct *mm, + unsigned long vaddr, unsigned long *pfn, + bool write_fault) +{ + int ret; + + ret = follow_pfn(vma, vaddr, pfn); + if (ret) { + bool unlocked = false; + + ret = fixup_user_fault(NULL, mm, vaddr, + FAULT_FLAG_REMOTE | + (write_fault ? FAULT_FLAG_WRITE : 0), + &unlocked); + if (unlocked) + return -EAGAIN; + + if (ret) + return ret; + + ret = follow_pfn(vma, vaddr, pfn); + } + + return ret; +} + static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr, int prot, unsigned long *pfn) { @@ -385,12 +411,16 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr, down_read(&mm->mmap_sem); +retry: vma = find_vma_intersection(mm, vaddr, vaddr + 1); if (vma && vma->vm_flags & VM_PFNMAP) { - if (!follow_pfn(vma, vaddr, pfn) && - is_invalid_reserved_pfn(*pfn)) - ret = 0; + ret = follow_fault_pfn(vma, mm, vaddr, pfn, prot & IOMMU_WRITE); + if (ret == -EAGAIN) + goto retry; + + if (!ret && !is_invalid_reserved_pfn(*pfn)) + ret = -EFAULT; } up_read(&mm->mmap_sem); -- 2.25.1

1 2

[PATCH] Disable cache readunique on 1620 which can cause performance decrease
by shenkai (D) 28 Jun '20

28 Jun '20

From 85f6f7c3bd13b3d6fd064899e2818ee70bdf29e2 Mon Sep 17 00:00:00 2001 euleros inclusion commit 85f6f7c3bd13b3d6fd064899e2818ee70bdf29e2 category: bugfix Random performance decreases appear on cases of Hackbench which test pipe or socket communication among multi-threads on Hisi 1620 SoC. Cache sharing which caused by the change of the data layout and the cache readunique mechanism both lead to this problem. Readunique mechanism which may caused by store operation will invalid cachelines on other cores during data fetching stage which can cause cacheline invalidation happens frequently in a sharing data access situation. Disable cache readunique can trackle this problem. Test cases are like: ./hackbench -pipe 20 thread 1000 On 128 cores 1620 machine, the time cost of above test cases is basicly 0.3s when RU is off while when RU is on the time cost can be over 1s. What's more, we disble readunique only in el2 for in el1 disabling readunique may cause panic due to lack of related priority which often be set in BIOS. Signed-off-by: Kai Shen <shenkai8(a)huawei.com> Reviewed-by: Wenliang He <hewenliang4(a)huawei.com> Reviewed-by: Jinxian He <hejingxian(a)huawei.com> Reviewed-by: Hanjun Guo <guohanjun(a)huawei.com> Reviewed-by: Wei Li <liwei391(a)huawei.com> --- arch/arm64/Kconfig | 9 +++++++ arch/arm64/configs/euleros_defconfig | 1 + arch/arm64/include/asm/cpucaps.h | 3 ++- arch/arm64/kernel/cpu_errata.c | 37 ++++++++++++++++++++++++++++ 4 files changed, 49 insertions(+), 1 deletion(-) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index b818273ef..33e185af5 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -642,6 +642,15 @@ config QCOM_FALKOR_ERRATUM_E1041 If unsure, say Y. +config HISILICON_ERRATUM_1620_RU + bool "Hisi 1620 cache readunique might compromise performance" + default y + help + The HiSilicon 1620 cache readunique might compromise performance, + use cmdline to enable or disable RU. + + If unsure, say Y. + endmenu diff --git a/arch/arm64/configs/euleros_defconfig b/arch/arm64/configs/euleros_defconfig index 360e69291..29403bfe4 100644 --- a/arch/arm64/configs/euleros_defconfig +++ b/arch/arm64/configs/euleros_defconfig @@ -5650,3 +5650,4 @@ CONFIG_IO_STRICT_DEVMEM=y # CONFIG_DEBUG_EFI is not set # CONFIG_ARM64_RELOC_TEST is not set # CONFIG_CORESIGHT is not set +CONFIG_HISILICON_ERRATUM_1620=y diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index d56d815b9..112c866c1 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -58,7 +58,8 @@ #define ARM64_SSBS 37 #define ARM64_CLEARPAGE_STNP 38 #define ARM64_WORKAROUND_1542419 39 +#define ARM64_HISI_1620_RU 40 -#define ARM64_NCAPS 40 +#define ARM64_NCAPS 41 #endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 7522163c1..fa751abed 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -25,6 +25,11 @@ #include <asm/cpufeature.h> #include <asm/smp_plat.h> +#ifdef CONFIG_HISILICON_ERRATUM_1620_RU +#include <asm/ptrace.h> +#include <asm/sysreg.h> +#endif + static bool __maybe_unused is_affected_midr_range(const struct arm64_cpu_capabilities *entry, int scope) { @@ -491,6 +496,30 @@ cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused) sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCI, 0); } +#ifdef CONFIG_HISILICON_ERRATUM_1620_RU +static bool readunique_enabled = false; + +static int __init enable_readunique(char *data) +{ + readunique_enabled = true; + return 0; +} +__setup("readunique_enable", enable_readunique); + +#define CTLR_HISI_1620_RU (1L << 40) +static void __maybe_unused +hisi_1620_ru_disable(const struct arm64_cpu_capabilities *__unused) +{ + u64 el; + if (readunique_enabled) + return; + + el = read_sysreg(CurrentEL); + if (el == CurrentEL_EL2) + sysreg_clear_set(S3_1_c15_c6_4, 0, CTLR_HISI_1620_RU); +} +#endif + /* known invulnerable cores */ static const struct midr_range arm64_ssb_cpus[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A35), @@ -884,6 +913,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .matches = has_neoverse_n1_erratum_1542419, .cpu_enable = cpu_enable_trap_ctr_access, }, +#endif +#ifdef CONFIG_HISILICON_ERRATUM_1620_RU + { + .desc = "Hisi 1620 Cache Readunique Disable", + .capability = ARM64_HISI_1620_RU, + ERRATA_MIDR_ALL_VERSIONS(MIDR_HISI_TSV110), + .cpu_enable = hisi_1620_ru_disable, + }, #endif { } -- 2.19.1

1 0

[hulk-4.19 v3 0/6] Adding Huawei BMA drivers
by yunaixin03610＠163.com 28 Jun '20

28 Jun '20

From: yunaixin <yunaixin03610(a)163.com> This patch set contains 5 communication drivers for Huawei BMA software. The BMA software is a system management software. It supports the status monitoring, performance monitoring, and event monitoring of various components, including server CPUs, memory, hard disks, NICs, IB cards, PCIe cards, RAID controller cards, and optical modules. These 5 drivers are used to send/receive message through PCIe channel in different ways by BMA software. yunaixin (6): Huawei BMA: Adding Huawei BMA driver: host_edma_drv Huawei BMA: Adding Huawei BMA driver: host_cdev_drv Huawei BMA: Adding Huawei BMA driver: host_veth_drv Huawei BMA: Adding Huawei BMA driver: cdev_veth_drv Huawei BMA: Adding Huawei BMA driver: host_kbox_drv Huawei BMA: Add BMA driver config options arch/arm64/configs/euleros_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + drivers/net/ethernet/huawei/Kconfig | 1 + drivers/net/ethernet/huawei/Makefile | 3 +- drivers/net/ethernet/huawei/bma/Kconfig | 5 + drivers/net/ethernet/huawei/bma/Makefile | 9 + .../net/ethernet/huawei/bma/cdev_drv/Kconfig | 11 + .../net/ethernet/huawei/bma/cdev_drv/Makefile | 2 + .../ethernet/huawei/bma/cdev_drv/bma_cdev.c | 369 +++ .../ethernet/huawei/bma/cdev_veth_drv/Kconfig | 11 + .../huawei/bma/cdev_veth_drv/Makefile | 2 + .../bma/cdev_veth_drv/virtual_cdev_eth_net.c | 1839 ++++++++++++ .../bma/cdev_veth_drv/virtual_cdev_eth_net.h | 300 ++ .../net/ethernet/huawei/bma/edma_drv/Kconfig | 11 + .../net/ethernet/huawei/bma/edma_drv/Makefile | 2 + .../huawei/bma/edma_drv/bma_devintf.c | 597 ++++ .../huawei/bma/edma_drv/bma_devintf.h | 40 + .../huawei/bma/edma_drv/bma_include.h | 116 + .../ethernet/huawei/bma/edma_drv/bma_pci.c | 533 ++++ .../ethernet/huawei/bma/edma_drv/bma_pci.h | 94 + .../ethernet/huawei/bma/edma_drv/edma_host.c | 1462 ++++++++++ .../ethernet/huawei/bma/edma_drv/edma_host.h | 351 +++ .../huawei/bma/include/bma_ker_intf.h | 94 + .../net/ethernet/huawei/bma/kbox_drv/Kconfig | 11 + .../net/ethernet/huawei/bma/kbox_drv/Makefile | 2 + .../ethernet/huawei/bma/kbox_drv/kbox_dump.c | 121 + .../ethernet/huawei/bma/kbox_drv/kbox_dump.h | 33 + .../ethernet/huawei/bma/kbox_drv/kbox_hook.c | 101 + .../ethernet/huawei/bma/kbox_drv/kbox_hook.h | 33 + .../huawei/bma/kbox_drv/kbox_include.h | 40 + .../ethernet/huawei/bma/kbox_drv/kbox_main.c | 168 ++ .../ethernet/huawei/bma/kbox_drv/kbox_main.h | 23 + .../ethernet/huawei/bma/kbox_drv/kbox_mce.c | 264 ++ .../ethernet/huawei/bma/kbox_drv/kbox_mce.h | 23 + .../ethernet/huawei/bma/kbox_drv/kbox_panic.c | 187 ++ .../ethernet/huawei/bma/kbox_drv/kbox_panic.h | 25 + .../huawei/bma/kbox_drv/kbox_printk.c | 363 +++ .../huawei/bma/kbox_drv/kbox_printk.h | 33 + .../huawei/bma/kbox_drv/kbox_ram_drive.c | 188 ++ .../huawei/bma/kbox_drv/kbox_ram_drive.h | 31 + .../huawei/bma/kbox_drv/kbox_ram_image.c | 135 + .../huawei/bma/kbox_drv/kbox_ram_image.h | 84 + .../huawei/bma/kbox_drv/kbox_ram_op.c | 986 +++++++ .../huawei/bma/kbox_drv/kbox_ram_op.h | 77 + .../net/ethernet/huawei/bma/veth_drv/Kconfig | 11 + .../net/ethernet/huawei/bma/veth_drv/Makefile | 2 + .../ethernet/huawei/bma/veth_drv/veth_hb.c | 2502 +++++++++++++++++ .../ethernet/huawei/bma/veth_drv/veth_hb.h | 440 +++ 48 files changed, 11736 insertions(+), 1 deletion(-) create mode 100644 drivers/net/ethernet/huawei/bma/Kconfig create mode 100644 drivers/net/ethernet/huawei/bma/Makefile create mode 100644 drivers/net/ethernet/huawei/bma/cdev_drv/Kconfig create mode 100644 drivers/net/ethernet/huawei/bma/cdev_drv/Makefile create mode 100644 drivers/net/ethernet/huawei/bma/cdev_drv/bma_cdev.c create mode 100644 drivers/net/ethernet/huawei/bma/cdev_veth_drv/Kconfig create mode 100644 drivers/net/ethernet/huawei/bma/cdev_veth_drv/Makefile create mode 100644 drivers/net/ethernet/huawei/bma/cdev_veth_drv/virtual_cdev_eth_net.c create mode 100644 drivers/net/ethernet/huawei/bma/cdev_veth_drv/virtual_cdev_eth_net.h create mode 100644 drivers/net/ethernet/huawei/bma/edma_drv/Kconfig create mode 100644 drivers/net/ethernet/huawei/bma/edma_drv/Makefile create mode 100644 drivers/net/ethernet/huawei/bma/edma_drv/bma_devintf.c create mode 100644 drivers/net/ethernet/huawei/bma/edma_drv/bma_devintf.h create mode 100644 drivers/net/ethernet/huawei/bma/edma_drv/bma_include.h create mode 100644 drivers/net/ethernet/huawei/bma/edma_drv/bma_pci.c create mode 100644 drivers/net/ethernet/huawei/bma/edma_drv/bma_pci.h create mode 100644 drivers/net/ethernet/huawei/bma/edma_drv/edma_host.c create mode 100644 drivers/net/ethernet/huawei/bma/edma_drv/edma_host.h create mode 100644 drivers/net/ethernet/huawei/bma/include/bma_ker_intf.h create mode 100644 drivers/net/ethernet/huawei/bma/kbox_drv/Kconfig create mode 100644 drivers/net/ethernet/huawei/bma/kbox_drv/Makefile create mode 100644 drivers/net/ethernet/huawei/bma/kbox_drv/kbox_dump.c create mode 100644 drivers/net/ethernet/huawei/bma/kbox_drv/kbox_dump.h create mode 100644 drivers/net/ethernet/huawei/bma/kbox_drv/kbox_hook.c create mode 100644 drivers/net/ethernet/huawei/bma/kbox_drv/kbox_hook.h create mode 100644 drivers/net/ethernet/huawei/bma/kbox_drv/kbox_include.h create mode 100644 drivers/net/ethernet/huawei/bma/kbox_drv/kbox_main.c create mode 100644 drivers/net/ethernet/huawei/bma/kbox_drv/kbox_main.h create mode 100644 drivers/net/ethernet/huawei/bma/kbox_drv/kbox_mce.c create mode 100644 drivers/net/ethernet/huawei/bma/kbox_drv/kbox_mce.h create mode 100644 drivers/net/ethernet/huawei/bma/kbox_drv/kbox_panic.c create mode 100644 drivers/net/ethernet/huawei/bma/kbox_drv/kbox_panic.h create mode 100644 drivers/net/ethernet/huawei/bma/kbox_drv/kbox_printk.c create mode 100644 drivers/net/ethernet/huawei/bma/kbox_drv/kbox_printk.h create mode 100644 drivers/net/ethernet/huawei/bma/kbox_drv/kbox_ram_drive.c create mode 100644 drivers/net/ethernet/huawei/bma/kbox_drv/kbox_ram_drive.h create mode 100644 drivers/net/ethernet/huawei/bma/kbox_drv/kbox_ram_image.c create mode 100644 drivers/net/ethernet/huawei/bma/kbox_drv/kbox_ram_image.h create mode 100644 drivers/net/ethernet/huawei/bma/kbox_drv/kbox_ram_op.c create mode 100644 drivers/net/ethernet/huawei/bma/kbox_drv/kbox_ram_op.h create mode 100644 drivers/net/ethernet/huawei/bma/veth_drv/Kconfig create mode 100644 drivers/net/ethernet/huawei/bma/veth_drv/Makefile create mode 100644 drivers/net/ethernet/huawei/bma/veth_drv/veth_hb.c create mode 100644 drivers/net/ethernet/huawei/bma/veth_drv/veth_hb.h -- 2.26.2.windows.1

2 7

[PATCH 1/8] ovl: fix lookup failure on multi lower squashfs
by Yang Yingliang 24 Jun '20

24 Jun '20

From: Amir Goldstein <amir73il(a)gmail.com> mainline inclusion from mainline-5.5-rc2 commit 7e63c87fc2dcf3be9d3aab82d4a0ea085880bdca category: bugfix bugzilla: 37632 CVE: NA --------------------------- In the past, overlayfs required that lower fs have non null uuid in order to support nfs export and decode copy up origin file handles. Commit 9df085f3c9a2 ("ovl: relax requirement for non null uuid of lower fs") relaxed this requirement for nfs export support, as long as uuid (even if null) is unique among all lower fs. However, said commit unintentionally also relaxed the non null uuid requirement for decoding copy up origin file handles, regardless of the unique uuid requirement. Amend this mistake by disabling decoding of copy up origin file handle from lower fs with a conflicting uuid. We still encode copy up origin file handles from those fs, because file handles like those already exist in the wild and because they might provide useful information in the future. There is an unhandled corner case described by Miklos this way: - two filesystems, A and B, both have null uuid - upper layer is on A - lower layer 1 is also on A - lower layer 2 is on B In this case bad_uuid won't be set for B, because the check only involves the list of lower fs. Hence we'll try to decode a layer 2 origin on layer 1 and fail. We will deal with this corner case later. Reported-by: Colin Ian King <colin.king(a)canonical.com> Tested-by: Colin Ian King <colin.king(a)canonical.com> Link: https://lore.kernel.org/lkml/20191106234301.283006-1-colin.king@canonical.c… Fixes: 9df085f3c9a2 ("ovl: relax requirement for non null uuid ...") Cc: stable(a)vger.kernel.org # v4.20+ Signed-off-by: Amir Goldstein <amir73il(a)gmail.com> Signed-off-by: Miklos Szeredi <mszeredi(a)redhat.com> Signed-off-by: Zhihao Cheng <chengzhihao1(a)huawei.com> Reviewed-by: zhangyi (F) <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/overlayfs/namei.c | 8 ++++++++ fs/overlayfs/ovl_entry.h | 2 ++ fs/overlayfs/super.c | 24 +++++++++++++++++------- 3 files changed, 27 insertions(+), 7 deletions(-) diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index badf039267a2..62515ec25481 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -328,6 +328,14 @@ int ovl_check_origin_fh(struct ovl_fs *ofs, struct ovl_fh *fh, bool connected, int i; for (i = 0; i < ofs->numlower; i++) { + /* + * If lower fs uuid is not unique among lower fs we cannot match + * fh->uuid to layer. + */ + if (ofs->lower_layers[i].fsid && + ofs->lower_layers[i].fs->bad_uuid) + continue; + origin = ovl_decode_real_fh(fh, ofs->lower_layers[i].mnt, connected); if (origin) diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h index 1a1adc697c55..787fe4be835e 100644 --- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -25,6 +25,8 @@ struct ovl_config { struct ovl_sb { struct super_block *sb; dev_t pseudo_dev; + /* Unusable (conflicting) uuid */ + bool bad_uuid; }; struct ovl_layer { diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index ddcf8d3a83bf..3881f07a2434 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1259,7 +1259,7 @@ static bool ovl_lower_uuid_ok(struct ovl_fs *ofs, const uuid_t *uuid) { unsigned int i; - if (!ofs->config.nfs_export && !(ofs->config.index && ofs->upper_mnt)) + if (!ofs->config.nfs_export && !ofs->upper_mnt) return true; for (i = 0; i < ofs->numlowerfs; i++) { @@ -1267,9 +1267,13 @@ static bool ovl_lower_uuid_ok(struct ovl_fs *ofs, const uuid_t *uuid) * We use uuid to associate an overlay lower file handle with a * lower layer, so we can accept lower fs with null uuid as long * as all lower layers with null uuid are on the same fs. + * if we detect multiple lower fs with the same uuid, we + * disable lower file handle decoding on all of them. */ - if (uuid_equal(&ofs->lower_fs[i].sb->s_uuid, uuid)) + if (uuid_equal(&ofs->lower_fs[i].sb->s_uuid, uuid)) { + ofs->lower_fs[i].bad_uuid = true; return false; + } } return true; } @@ -1281,6 +1285,7 @@ static int ovl_get_fsid(struct ovl_fs *ofs, const struct path *path) unsigned int i; dev_t dev; int err; + bool bad_uuid = false; /* fsid 0 is reserved for upper fs even with non upper overlay */ if (ofs->upper_mnt && ofs->upper_mnt->mnt_sb == sb) @@ -1292,11 +1297,15 @@ static int ovl_get_fsid(struct ovl_fs *ofs, const struct path *path) } if (!ovl_lower_uuid_ok(ofs, &sb->s_uuid)) { - ofs->config.index = false; - ofs->config.nfs_export = false; - pr_warn("overlayfs: %s uuid detected in lower fs '%pd2', falling back to index=off,nfs_export=off.\n", - uuid_is_null(&sb->s_uuid) ? "null" : "conflicting", - path->dentry); + bad_uuid = true; + if (ofs->config.index || ofs->config.nfs_export) { + ofs->config.index = false; + ofs->config.nfs_export = false; + pr_warn("overlayfs: %s uuid detected in lower fs '%pd2', falling back to index=off,nfs_export=off.\n", + uuid_is_null(&sb->s_uuid) ? "null" : + "conflicting", + path->dentry); + } } err = get_anon_bdev(&dev); @@ -1307,6 +1316,7 @@ static int ovl_get_fsid(struct ovl_fs *ofs, const struct path *path) ofs->lower_fs[ofs->numlowerfs].sb = sb; ofs->lower_fs[ofs->numlowerfs].pseudo_dev = dev; + ofs->lower_fs[ofs->numlowerfs].bad_uuid = bad_uuid; ofs->numlowerfs++; return ofs->numlowerfs; -- 2.25.1

1 7

[PATCH 1/6] perf top: Fix wrong hottest instruction highlighted
by Yang Yingliang 21 Jun '20

21 Jun '20

From: He Kuang <hekuang(a)huawei.com> mainline inclusion from mainline-5.0-rc5 commit da06d5683868 category: bugfix bugzilla: 38073 CVE: NA ------------------------------------------------- The annotation line percentage is compared and inserted into the rbtree, but the percent field of 'struct annotation_data' is an array, the comparison result between them is the address difference. This patch compares the right slot of percent array according to opts->percent_type and makes things right. The problem can be reproduced by pressing 'H' in perf top annotation view. It should highlight the instruction line which has the highest sampling percentage. Signed-off-by: He Kuang <hekuang(a)huawei.com> Reviewed-by: Jiri Olsa <jolsa(a)kernel.org> Cc: Alexander Shishkin <alexander.shishkin(a)linux.intel.com> Cc: Namhyung Kim <namhyung(a)kernel.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Link: http://lkml.kernel.org/r/20190120160523.4391-1-hekuang@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> Signed-off-by: Wei Li <liwei391(a)huawei.com> Reviewed-by: Jian Cheng <cj.chengjian(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- tools/perf/ui/browsers/annotate.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index a3c255228d62..131f51131b52 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -225,20 +225,24 @@ static unsigned int annotate_browser__refresh(struct ui_browser *browser) return ret; } -static int disasm__cmp(struct annotation_line *a, struct annotation_line *b) +static double disasm__cmp(struct annotation_line *a, struct annotation_line *b, + int percent_type) { int i; for (i = 0; i < a->data_nr; i++) { - if (a->data[i].percent == b->data[i].percent) + if (a->data[i].percent[percent_type] == b->data[i].percent[percent_type]) continue; - return a->data[i].percent < b->data[i].percent; + return a->data[i].percent[percent_type] - + b->data[i].percent[percent_type]; } return 0; } -static void disasm_rb_tree__insert(struct rb_root *root, struct annotation_line *al) +static void disasm_rb_tree__insert(struct annotate_browser *browser, + struct annotation_line *al) { + struct rb_root *root = &browser->entries; struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; struct annotation_line *l; @@ -247,7 +251,7 @@ static void disasm_rb_tree__insert(struct rb_root *root, struct annotation_line parent = *p; l = rb_entry(parent, struct annotation_line, rb_node); - if (disasm__cmp(al, l)) + if (disasm__cmp(al, l, browser->opts->percent_type) < 0) p = &(*p)->rb_left; else p = &(*p)->rb_right; @@ -330,7 +334,7 @@ static void annotate_browser__calc_percent(struct annotate_browser *browser, RB_CLEAR_NODE(&pos->al.rb_node); continue; } - disasm_rb_tree__insert(&browser->entries, &pos->al); + disasm_rb_tree__insert(browser, &pos->al); } pthread_mutex_unlock(&notes->lock); -- 2.25.1

1 5

[PATCH 1/2] xfs: Use scnprintf() for avoiding potential buffer overflow
by Yang Yingliang 17 Jun '20

17 Jun '20

From: Takashi Iwai <tiwai(a)suse.de> mainline inclusion from mainline-v5.7-rc1 commit 17bb60b74124e9491d593e2601e3afe14daa2f57 category: bugfix bugzilla: 33322 CVE: NA --------------------------- Since snprintf() returns the would-be-output size instead of the actual output size, the succeeding calls may go beyond the given buffer limit. Fix it by replacing with scnprintf(). Signed-off-by: Takashi Iwai <tiwai(a)suse.de> Reviewed-by: Darrick J. Wong <darrick.wong(a)oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong(a)oracle.com> Signed-off-by: yu kuai <yukuai3(a)huawei.com> Reviewed-by: zhangyi (F) <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/xfs/xfs_stats.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/xfs/xfs_stats.c b/fs/xfs/xfs_stats.c index 740ac9674848..0373d9ea7334 100644 --- a/fs/xfs/xfs_stats.c +++ b/fs/xfs/xfs_stats.c @@ -58,13 +58,13 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf) /* Loop over all stats groups */ for (i = j = 0; i < ARRAY_SIZE(xstats); i++) { - len += snprintf(buf + len, PATH_MAX - len, "%s", + len += scnprintf(buf + len, PATH_MAX - len, "%s", xstats[i].desc); /* inner loop does each group */ for (; j < xstats[i].endpoint; j++) - len += snprintf(buf + len, PATH_MAX - len, " %u", + len += scnprintf(buf + len, PATH_MAX - len, " %u", counter_val(stats, j)); - len += snprintf(buf + len, PATH_MAX - len, "\n"); + len += scnprintf(buf + len, PATH_MAX - len, "\n"); } /* extra precision counters */ for_each_possible_cpu(i) { @@ -73,9 +73,9 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf) xs_read_bytes += per_cpu_ptr(stats, i)->s.xs_read_bytes; } - len += snprintf(buf + len, PATH_MAX-len, "xpc %Lu %Lu %Lu\n", + len += scnprintf(buf + len, PATH_MAX-len, "xpc %Lu %Lu %Lu\n", xs_xstrat_bytes, xs_write_bytes, xs_read_bytes); - len += snprintf(buf + len, PATH_MAX-len, "debug %u\n", + len += scnprintf(buf + len, PATH_MAX-len, "debug %u\n", #if defined(DEBUG) 1); #else -- 2.25.1

1 1

[PATCH] nfs: set invalid blocks after NFSv4 writes
by Yang Yingliang 16 Jun '20

16 Jun '20

From: Zheng Bin <zhengbin13(a)huawei.com> mainline inclusion from mainline-bc5603c314bd commit bc5603c314bd1d2a931ad3088fcea52f20cfbac5 category: bugfix bugzilla: 34591 CVE: NA --------------------------- Use the following command to test nfsv4(size of file1M is 1MB): mount -t nfs -o vers=4.0,actimeo=60 127.0.0.1/dir1 /mnt cp file1M /mnt du -h /mnt/file1M -->0 within 60s, then 1M When write is done(cp file1M /mnt), will call this: nfs_writeback_done nfs4_write_done nfs4_write_done_cb nfs_writeback_update_inode nfs_post_op_update_inode_force_wcc_locked(change, ctime, mtime nfs_post_op_update_inode_force_wcc_locked nfs_set_cache_invalid nfs_refresh_inode_locked nfs_update_inode nfsd write response contains change, ctime, mtime, the flag will be clear after nfs_update_inode. Howerver, write response does not contain space_used, previous open response contains space_used whose value is 0, so inode->i_blocks is still 0. nfs_getattr -->called by "du -h" do_update |= force_sync || nfs_attribute_cache_expired -->false in 60s cache_validity = READ_ONCE(NFS_I(inode)->cache_validity) do_update |= cache_validity & (NFS_INO_INVALID_ATTR -->false if (do_update) { __nfs_revalidate_inode } Within 60s, does not send getattr request to nfsd, thus "du -h /mnt/file1M" is 0. Add a NFS_INO_INVALID_BLOCKS flag, set it when nfsv4 write is done. [zb: although commit 1c341b777501 ("NFS: Add deferred cache invalidation for close-to-open consistency violations") not merged, still define NFS_INO_INVALID_BLOCKS BIT(14)] Fixes: 16e143751727 ("NFS: More fine grained attribute tracking") Signed-off-by: Zheng Bin <zhengbin13(a)huawei.com> Signed-off-by: Anna Schumaker <Anna.Schumaker(a)Netapp.com> Signed-off-by: Zheng Bin <zhengbin13(a)huawei.com> Reviewed-by: zhangyi (F) <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/nfs/inode.c | 14 +++++++++++--- include/linux/nfs_fs.h | 1 + 2 files changed, 12 insertions(+), 3 deletions(-) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index e4cd3a2fe698..5d8e0eb0d663 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -822,6 +822,8 @@ int nfs_getattr(const struct path *path, struct kstat *stat, do_update |= cache_validity & NFS_INO_INVALID_ATIME; if (request_mask & (STATX_CTIME|STATX_MTIME)) do_update |= cache_validity & NFS_INO_REVAL_PAGECACHE; + if (request_mask & STATX_BLOCKS) + do_update |= cache_validity & NFS_INO_INVALID_BLOCKS; if (do_update) { /* Update the attribute cache */ if (!(server->flags & NFS_MOUNT_NOAC)) @@ -1741,7 +1743,8 @@ int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fa status = nfs_post_op_update_inode_locked(inode, fattr, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME - | NFS_INO_INVALID_MTIME); + | NFS_INO_INVALID_MTIME + | NFS_INO_INVALID_BLOCKS); return status; } @@ -1851,7 +1854,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ATIME | NFS_INO_REVAL_FORCED - | NFS_INO_REVAL_PAGECACHE); + | NFS_INO_REVAL_PAGECACHE + | NFS_INO_INVALID_BLOCKS); /* Do atomic weak cache consistency updates */ nfs_wcc_update_inode(inode, fattr); @@ -2012,8 +2016,12 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used); } else if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) inode->i_blocks = fattr->du.nfs2.blocks; - else + else { + nfsi->cache_validity |= save_cache_validity & + (NFS_INO_INVALID_BLOCKS + | NFS_INO_REVAL_FORCED); cache_revalidated = false; + } /* Update attrtimeo value if we're out of the unstable period */ if (attr_changed) { diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index a0831e9d19c9..620306b1604d 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -221,6 +221,7 @@ struct nfs4_copy_state { #define NFS_INO_INVALID_MTIME BIT(10) /* cached mtime is invalid */ #define NFS_INO_INVALID_SIZE BIT(11) /* cached size is invalid */ #define NFS_INO_INVALID_OTHER BIT(12) /* other attrs are invalid */ +#define NFS_INO_INVALID_BLOCKS BIT(14) /* cached blocks are invalid */ #define NFS_INO_INVALID_ATTR (NFS_INO_INVALID_CHANGE \ | NFS_INO_INVALID_CTIME \ -- 2.25.1

1 0

[PATCH 1/4] xfs: fix inode fork extent count overflow
by Yang Yingliang 16 Jun '20

16 Jun '20

From: Dave Chinner <dchinner(a)redhat.com> mainline inclusion from mainline-5.5-rc1 commit 3f8a4f1d876d3e3e49e50b0396eaffcc4ba71b08 category: bugfix bugzilla: 26723 CVE: NA --------------------------- [commit message is verbose for discussion purposes - will trim it down later. Some questions about implementation details at the end.] Zorro Lang recently ran a new test to stress single inode extent counts now that they are no longer limited by memory allocation. The test was simply: This test uncovered a problem where the hole punching operation appeared to finish with no error, but apparently only created 268M extents instead of the 10 billion it was supposed to. Further, trying to punch out extents that should have been present resulted in success, but no change in the extent count. It looked like a silent failure. While running the test and observing the behaviour in real time, I observed the extent coutn growing at ~2M extents/minute, and saw this after about an hour: > sleep 60 ; \ > xfs_io -f -c "stat" /mnt/scratch/big-file |grep next fsxattr.nextents = 127657993 fsxattr.nextents = 129683339 And a few minutes later this: fsxattr.nextents = 4177861124 Ah, what? Where did that 4 billion extra extents suddenly come from? Stop the workload, unmount, mount: fsxattr.nextents = 166044375 And it's back at the expected number. i.e. the extent count is correct on disk, but it's screwed up in memory. I loaded up the extent list, and immediately: fsxattr.nextents = 4192576215 It's bad again. So, where does that number come from? xfs_fill_fsxattr(): if (ip->i_df.if_flags & XFS_IFEXTENTS) fa->fsx_nextents = xfs_iext_count(&ip->i_df); else fa->fsx_nextents = ip->i_d.di_nextents; And that's the behaviour I just saw in a nutshell. The on disk count is correct, but once the tree is loaded into memory, it goes whacky. Clearly there's something wrong with xfs_iext_count(): inline xfs_extnum_t xfs_iext_count(struct xfs_ifork *ifp) { return ifp->if_bytes / sizeof(struct xfs_iext_rec); } Simple enough, but 134M extents is 2**27, and that's right about where things went wrong. A struct xfs_iext_rec is 16 bytes in size, which means 2**27 * 2**4 = 2**31 and we're right on target for an integer overflow. And, sure enough: struct xfs_ifork { int if_bytes; /* bytes in if_u1 */ .... Once we get 2**27 extents in a file, we overflow if_bytes and the in-core extent count goes wrong. And when we reach 2**28 extents, if_bytes wraps back to zero and things really start to go wrong there. This is where the silent failure comes from - only the first 2**28 extents can be looked up directly due to the overflow, all the extents above this index wrap back to somewhere in the first 2**28 extents. Hence with a regular pattern, trying to punch a hole in the range that didn't have holes mapped to a hole in the first 2**28 extents and so "succeeded" without changing anything. Hence "silent failure"... Fix this by converting if_bytes to a int64_t and converting all the index variables and size calculations to use int64_t types to avoid overflows in future. Signed integers are still used to enable easy detection of extent count underflows. This enables scalability of extent counts to the limits of the on-disk format - MAXEXTNUM (2**31) extents. Current testing is at over 500M extents and still going: fsxattr.nextents = 517310478 Reported-by: Zorro Lang <zlang(a)redhat.com> Signed-off-by: Dave Chinner <dchinner(a)redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong(a)oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong(a)oracle.com> Conflict: fs/xfs/libxfs/xfs_inode_fork.h Signed-off-by: yu kuai <yukuai3(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/xfs/libxfs/xfs_attr_leaf.c | 18 ++++++++++-------- fs/xfs/libxfs/xfs_dir2_sf.c | 2 +- fs/xfs/libxfs/xfs_iext_tree.c | 2 +- fs/xfs/libxfs/xfs_inode_fork.c | 8 ++++---- fs/xfs/libxfs/xfs_inode_fork.h | 14 ++++++++------ 5 files changed, 24 insertions(+), 20 deletions(-) diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 2652d00842d6..ceb9b0045725 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -421,13 +421,15 @@ xfs_attr_namesp_match(int arg_flags, int ondisk_flags) * special case for dev/uuid inodes, they have fixed size data forks. */ int -xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes) +xfs_attr_shortform_bytesfit( + struct xfs_inode *dp, + int bytes) { - int offset; - int minforkoff; /* lower limit on valid forkoff locations */ - int maxforkoff; /* upper limit on valid forkoff locations */ - int dsize; - xfs_mount_t *mp = dp->i_mount; + struct xfs_mount *mp = dp->i_mount; + int64_t dsize; + int minforkoff; + int maxforkoff; + int offset; /* rounded down */ offset = (XFS_LITINO(mp, dp->i_d.di_version) - bytes) >> 3; @@ -493,7 +495,7 @@ xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes) * A data fork btree root must have space for at least * MINDBTPTRS key/ptr pairs if the data fork is small or empty. */ - minforkoff = max(dsize, XFS_BMDR_SPACE_CALC(MINDBTPTRS)); + minforkoff = max_t(int64_t, dsize, XFS_BMDR_SPACE_CALC(MINDBTPTRS)); minforkoff = roundup(minforkoff, 8) >> 3; /* attr fork btree root can have at least this many key/ptr pairs */ @@ -913,7 +915,7 @@ xfs_attr_shortform_verify( char *endp; struct xfs_ifork *ifp; int i; - int size; + int64_t size; ASSERT(ip->i_d.di_aformat == XFS_DINODE_FMT_LOCAL); ifp = XFS_IFORK_PTR(ip, XFS_ATTR_FORK); diff --git a/fs/xfs/libxfs/xfs_dir2_sf.c b/fs/xfs/libxfs/xfs_dir2_sf.c index 716c8c50f8bc..e126446a9484 100644 --- a/fs/xfs/libxfs/xfs_dir2_sf.c +++ b/fs/xfs/libxfs/xfs_dir2_sf.c @@ -653,7 +653,7 @@ xfs_dir2_sf_verify( int i; int i8count; int offset; - int size; + int64_t size; int error; uint8_t filetype; diff --git a/fs/xfs/libxfs/xfs_iext_tree.c b/fs/xfs/libxfs/xfs_iext_tree.c index 771dd072015d..22beaab8f9b4 100644 --- a/fs/xfs/libxfs/xfs_iext_tree.c +++ b/fs/xfs/libxfs/xfs_iext_tree.c @@ -600,7 +600,7 @@ xfs_iext_realloc_root( struct xfs_ifork *ifp, struct xfs_iext_cursor *cur) { - size_t new_size = ifp->if_bytes + sizeof(struct xfs_iext_rec); + int64_t new_size = ifp->if_bytes + sizeof(struct xfs_iext_rec); void *new; /* account for the prev/next pointers */ diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index f9acf1d436f6..80aa0f1a04dd 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -131,7 +131,7 @@ xfs_init_local_fork( struct xfs_inode *ip, int whichfork, const void *data, - int size) + int64_t size) { struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); int mem_size = size, real_size = 0; @@ -469,11 +469,11 @@ xfs_iroot_realloc( void xfs_idata_realloc( struct xfs_inode *ip, - int byte_diff, + int64_t byte_diff, int whichfork) { struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); - int new_size = (int)ifp->if_bytes + byte_diff; + int64_t new_size = ifp->if_bytes + byte_diff; ASSERT(new_size >= 0); ASSERT(new_size <= XFS_IFORK_SIZE(ip, whichfork)); @@ -554,7 +554,7 @@ xfs_iextents_copy( struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); struct xfs_iext_cursor icur; struct xfs_bmbt_irec rec; - int copied = 0; + int64_t copied = 0; ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED)); ASSERT(ifp->if_bytes > 0); diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h index 60361d2d74a1..09e3548afdde 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.h +++ b/fs/xfs/libxfs/xfs_inode_fork.h @@ -13,16 +13,16 @@ struct xfs_dinode; * File incore extent information, present for each of data & attr forks. */ struct xfs_ifork { - int if_bytes; /* bytes in if_u1 */ - unsigned int if_seq; /* cow fork mod counter */ + int64_t if_bytes; /* bytes in if_u1 */ struct xfs_btree_block *if_broot; /* file's incore btree root */ - short if_broot_bytes; /* bytes allocated for root */ - unsigned char if_flags; /* per-fork flags */ + unsigned int if_seq; /* cow fork mod counter */ int if_height; /* height of the extent tree */ union { void *if_root; /* extent tree root */ char *if_data; /* inline file data */ } if_u1; + short if_broot_bytes; /* bytes allocated for root */ + unsigned char if_flags; /* per-fork flags */ }; /* @@ -93,12 +93,14 @@ int xfs_iformat_fork(struct xfs_inode *, struct xfs_dinode *); void xfs_iflush_fork(struct xfs_inode *, struct xfs_dinode *, struct xfs_inode_log_item *, int); void xfs_idestroy_fork(struct xfs_inode *, int); -void xfs_idata_realloc(struct xfs_inode *, int, int); +void xfs_idata_realloc(struct xfs_inode *ip, int64_t byte_diff, + int whichfork); void xfs_iroot_realloc(struct xfs_inode *, int, int); int xfs_iread_extents(struct xfs_trans *, struct xfs_inode *, int); int xfs_iextents_copy(struct xfs_inode *, struct xfs_bmbt_rec *, int); -void xfs_init_local_fork(struct xfs_inode *, int, const void *, int); +void xfs_init_local_fork(struct xfs_inode *ip, int whichfork, + const void *data, int64_t size); xfs_extnum_t xfs_iext_count(struct xfs_ifork *ifp); void xfs_iext_insert(struct xfs_inode *, struct xfs_iext_cursor *cur, -- 2.25.1

1 3

[PATCH] signal: Export tracepoint symbol signal_generate
by Yang Yingliang 15 Jun '20

15 Jun '20

From: Tang Yizhou <tangyizhou(a)huawei.com> hulk inclusion category: feature bugzilla: 37631 CVE: NA ------------------------------------------------- To support signal monitoring, we need to export the defined tracepoint signal_generate so that it can be used in kernel modules. Signed-off-by: Tang Yizhou <tangyizhou(a)huawei.com> Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- kernel/signal.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/signal.c b/kernel/signal.c index 718f22da0305..091a3a313410 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -52,6 +52,8 @@ #include <asm/cacheflush.h> #include "audit.h" /* audit_signal_info() */ +EXPORT_TRACEPOINT_SYMBOL(signal_generate); + /* * SLAB caches for signal bits. */ -- 2.25.1

1 0

[PATCH 1/2] perf/x86: Make perf callchains work without CONFIG_FRAME_POINTER
by Yang Yingliang 15 Jun '20

15 Jun '20

From: Kairui Song <kasong(a)redhat.com> mainline inclusion from mainline-5.2-rc1 commit d15d356887e7 category: bugfix bugzilla: 35738 CVE: NA ------------------------------------------------- Currently perf callchain doesn't work well with ORC unwinder when sampling from trace point. We'll get useless in kernel callchain like this: perf 6429 [000] 22.498450: kmem:mm_page_alloc: page=0x176a17 pfn=1534487 order=0 migratetype=0 gfp_flags=GFP_KERNEL ffffffffbe23e32e __alloc_pages_nodemask+0x22e (/lib/modules/5.1.0-rc3+/build/vmlinux) 7efdf7f7d3e8 __poll+0x18 (/usr/lib64/libc-2.28.so) 5651468729c1 [unknown] (/usr/bin/perf) 5651467ee82a main+0x69a (/usr/bin/perf) 7efdf7eaf413 __libc_start_main+0xf3 (/usr/lib64/libc-2.28.so) 5541f689495641d7 [unknown] ([unknown]) The root cause is that, for trace point events, it doesn't provide a real snapshot of the hardware registers. Instead perf tries to get required caller's registers and compose a fake register snapshot which suppose to contain enough information for start a unwinding. However without CONFIG_FRAME_POINTER, if failed to get caller's BP as the frame pointer, so current frame pointer is returned instead. We get a invalid register combination which confuse the unwinder, and end the stacktrace early. So in such case just don't try dump BP, and let the unwinder start directly when the register is not a real snapshot. Use SP as the skip mark, unwinder will skip all the frames until it meet the frame of the trace point caller. Tested with frame pointer unwinder and ORC unwinder, this makes perf callchain get the full kernel space stacktrace again like this: perf 6503 [000] 1567.570191: kmem:mm_page_alloc: page=0x16c904 pfn=1493252 order=0 migratetype=0 gfp_flags=GFP_KERNEL ffffffffb523e2ae __alloc_pages_nodemask+0x22e (/lib/modules/5.1.0-rc3+/build/vmlinux) ffffffffb52383bd __get_free_pages+0xd (/lib/modules/5.1.0-rc3+/build/vmlinux) ffffffffb52fd28a __pollwait+0x8a (/lib/modules/5.1.0-rc3+/build/vmlinux) ffffffffb521426f perf_poll+0x2f (/lib/modules/5.1.0-rc3+/build/vmlinux) ffffffffb52fe3e2 do_sys_poll+0x252 (/lib/modules/5.1.0-rc3+/build/vmlinux) ffffffffb52ff027 __x64_sys_poll+0x37 (/lib/modules/5.1.0-rc3+/build/vmlinux) ffffffffb500418b do_syscall_64+0x5b (/lib/modules/5.1.0-rc3+/build/vmlinux) ffffffffb5a0008c entry_SYSCALL_64_after_hwframe+0x44 (/lib/modules/5.1.0-rc3+/build/vmlinux) 7f71e92d03e8 __poll+0x18 (/usr/lib64/libc-2.28.so) 55a22960d9c1 [unknown] (/usr/bin/perf) 55a22958982a main+0x69a (/usr/bin/perf) 7f71e9202413 __libc_start_main+0xf3 (/usr/lib64/libc-2.28.so) 5541f689495641d7 [unknown] ([unknown]) Co-developed-by: Josh Poimboeuf <jpoimboe(a)redhat.com> Signed-off-by: Kairui Song <kasong(a)redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Cc: Alexander Shishkin <alexander.shishkin(a)linux.intel.com> Cc: Alexei Starovoitov <alexei.starovoitov(a)gmail.com> Cc: Arnaldo Carvalho de Melo <acme(a)kernel.org> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Dave Young <dyoung(a)redhat.com> Cc: Jiri Olsa <jolsa(a)redhat.com> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Namhyung Kim <namhyung(a)kernel.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Link: https://lkml.kernel.org/r/20190422162652.15483-1-kasong@redhat.com Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Wei Li <liwei391(a)huawei.com> Reviewed-by: Jian Cheng <cj.chengjian(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/x86/events/core.c | 21 +++++++++++++++++---- arch/x86/include/asm/perf_event.h | 7 +------ arch/x86/include/asm/stacktrace.h | 13 ------------- include/linux/perf_event.h | 14 ++++++++++---- 4 files changed, 28 insertions(+), 27 deletions(-) diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index c89e6c6e26f6..0a6b48afeb05 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2332,6 +2332,15 @@ void arch_perf_update_userpage(struct perf_event *event, cyc2ns_read_end(); } +/* + * Determine whether the regs were taken from an irq/exception handler rather + * than from perf_arch_fetch_caller_regs(). + */ +static bool perf_hw_regs(struct pt_regs *regs) +{ + return regs->flags & X86_EFLAGS_FIXED; +} + void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { @@ -2343,11 +2352,15 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re return; } - if (perf_callchain_store(entry, regs->ip)) - return; + if (perf_hw_regs(regs)) { + if (perf_callchain_store(entry, regs->ip)) + return; + unwind_start(&state, current, regs, NULL); + } else { + unwind_start(&state, current, NULL, (void *)regs->sp); + } - for (unwind_start(&state, current, regs, NULL); !unwind_done(&state); - unwind_next_frame(&state)) { + for (; !unwind_done(&state); unwind_next_frame(&state)) { addr = unwind_get_return_address(&state); if (!addr || perf_callchain_store(entry, addr)) return; diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index f6c4915a863e..620c3e3564be 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -264,14 +264,9 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs); */ #define perf_arch_fetch_caller_regs(regs, __ip) { \ (regs)->ip = (__ip); \ - (regs)->bp = caller_frame_pointer(); \ + (regs)->sp = (unsigned long)__builtin_frame_address(0); \ (regs)->cs = __KERNEL_CS; \ regs->flags = 0; \ - asm volatile( \ - _ASM_MOV "%%"_ASM_SP ", %0\n" \ - : "=m" ((regs)->sp) \ - :: "memory" \ - ); \ } struct perf_guest_switch_msr { diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index f335aad404a4..beef7ad9e43a 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -98,19 +98,6 @@ struct stack_frame_ia32 { u32 return_address; }; -static inline unsigned long caller_frame_pointer(void) -{ - struct stack_frame *frame; - - frame = __builtin_frame_address(0); - -#ifdef CONFIG_FRAME_POINTER - frame = frame->next_frame; -#endif - - return (unsigned long)frame; -} - void show_opcodes(struct pt_regs *regs, const char *loglvl); void show_ip(struct pt_regs *regs, const char *loglvl); #endif /* _ASM_X86_STACKTRACE_H */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index d8b4d31acd18..cf3da70056f7 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1050,12 +1050,18 @@ static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned lo #endif /* - * Take a snapshot of the regs. Skip ip and frame pointer to - * the nth caller. We only need a few of the regs: + * When generating a perf sample in-line, instead of from an interrupt / + * exception, we lack a pt_regs. This is typically used from software events + * like: SW_CONTEXT_SWITCHES, SW_MIGRATIONS and the tie-in with tracepoints. + * + * We typically don't need a full set, but (for x86) do require: * - ip for PERF_SAMPLE_IP * - cs for user_mode() tests - * - bp for callchains - * - eflags, for future purposes, just in case + * - sp for PERF_SAMPLE_CALLCHAIN + * - eflags for MISC bits and CALLCHAIN (see: perf_hw_regs()) + * + * NOTE: assumes @regs is otherwise already 0 filled; this is important for + * things like PERF_SAMPLE_REGS_INTR. */ static inline void perf_fetch_caller_regs(struct pt_regs *regs) { -- 2.25.1

1 1

[PATCH] ext4: stop overwrite the errcode in ext4_setup_super
by Yang Yingliang 15 Jun '20

15 Jun '20

From: yangerkun <yangerkun(a)huawei.com> hulk inclusion category: bugfix bugzilla: 35487 CVE: NA ----------------------------------------------- Now the errcode from ext4_commit_super will overwrite EROFS exists in ext4_setup_super. Actually, no need to call ext4_commit_super since we will return EROFS. Fix it by goto done directly. Fixes: c89128a00838 ("ext4: handle errors on ext4_commit_super") Signed-off-by: yangerkun <yangerkun(a)huawei.com> Reviewed-by: zhangyi (F) <yi.zhang(a)huawei.com> Signed-off-by: Ye Bin <yebin10(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/ext4/super.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index cc057001961e..b10f96860dd8 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2305,6 +2305,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, ext4_msg(sb, KERN_ERR, "revision level too high, " "forcing read-only mode"); err = -EROFS; + goto done; } if (read_only) goto done; -- 2.25.1

1 0

[PATCH] panic/printk: fix zap_lock
by Yang Yingliang 15 Jun '20

15 Jun '20

From: Cheng Jian <cj.chengjian(a)huawei.com> hulk inclusion category: bugfix bugzilla: 34546 CVE: NA ---------------------------------------- There are two problems with the implementation and use of zap_lock(). Firstly, This console_sem does not require reinit in zap_lock(), this is because: 1). printk() itself does try_lock() and skips console handling when the semaphore is not available. 2). panic() tries to push the messages later in console_flush_on_panic(). It ignores the semaphore. Also most console drivers ignore their internal locks because oops_in_progress is set by bust_spinlocks(). Secondly, The situation is more complicated when NMI is not used. 1). Non-stopped CPUs are in unknown state, most likely in a busy loop. Nobody knows whether printk() is repeatedly called in the loop. When it was called, re-initializing any lock would cause double unlock and deadlock. 2). It would be possible to add some more hacks. One problem is that there are two groups of users. One prefer to risk a deadlock and have a chance to see the messages. Others prefer to always reach emergency_restart() and reboot the machine. Fixes: b15f5676d00e ("printk/panic: Avoid deadlock in printk()") Signed-off-by: Cheng Jian <cj.chengjian(a)huawei.com> Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- kernel/panic.c | 25 +++++++++++++++++++++++++ kernel/printk/printk.c | 3 --- 2 files changed, 25 insertions(+), 3 deletions(-) diff --git a/kernel/panic.c b/kernel/panic.c index 9434f6c2da9e..ebdb58e761c0 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -238,7 +238,32 @@ void panic(const char *fmt, ...) crash_smp_send_stop(); } + /* + * ZAP console related locks when nmi broadcast. If a crash is occurring, + * make sure we can't deadlock. And make sure that we print immediately. + * + * A deadlock caused by logbuf_lock can be occured when panic: + * a) Panic CPU is running in non-NMI context; + * b) Panic CPU sends out shutdown IPI via NMI vector; + * c) One of the CPUs that we bring down via NMI vector holded logbuf_lock; + * d) Panic CPU try to hold logbuf_lock, then deadlock occurs. + * + * At present, only try to solve this problem for the ARCH with NMI, + * by reinit lock, this situation is more complicated when NMI is not + * used. + * 1). Non-stopped CPUs are in unknown state, most likely in a busy loop. + * Nobody knows whether printk() is repeatedly called in the loop. + * When it was called, re-initializing any lock would cause double + * unlock and deadlock. + * + * 2). It would be possible to add some more hacks. One problem is that + * there are two groups of users. One prefer to risk a deadlock and + * have a chance to see the messages. Others prefer to always + * reach emergency_restart() and reboot the machine. + */ +#ifdef CONFIG_X86 zap_locks(); +#endif /* * Run any panic handlers, including those that might need to diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 7225f5ef0f54..f67b6a1c8f74 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1592,9 +1592,6 @@ void zap_locks(void) if (raw_spin_is_locked(&logbuf_lock)) { debug_locks_off(); raw_spin_lock_init(&logbuf_lock); - - console_suspended = 1; - sema_init(&console_sem, 1); } if (raw_spin_is_locked(&console_owner_lock)) { -- 2.25.1

1 0

[PATCH 1/3] net: hns3: add device name valid check
by Yang Yingliang 15 Jun '20

15 Jun '20

From: Junxin Chen <chenjunxin1(a)huawei.com> driver inclusion category: bugfix bugzilla: NA CVE: NA ---------------------------------- Nowadays, we have checked device name at user tool, and have limited length of device name at kernel driver. But when get_netdev_by_ifname return NULL, it would cause print device name without check terminator. This patch fixes this bug, when device name's last character isn't a '\0', kernel driver would return -EINVAL to user. Signed-off-by: Junxin Chen <chenjunxin1(a)huawei.com> Reviewed-by: Weiwei Deng <dengweiwei(a)huawei.com> Reviewed-by: Shengzui You <youshengzui(a)huawei.com> Reviewed-by: Zhaohui Zhong <zhongzhaohui(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/net/ethernet/hisilicon/hns3/hns3_cae/hns3_cae_init.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_cae/hns3_cae_init.c b/drivers/net/ethernet/hisilicon/hns3/hns3_cae/hns3_cae_init.c index 7c084a6fbe18..1e012917e010 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_cae/hns3_cae_init.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_cae/hns3_cae_init.c @@ -335,6 +335,11 @@ static long hns3_cae_k_unlocked_ioctl(struct file *pfile, unsigned int cmd, * code yet, so we don't need lock. */ rtnl_lock(); + if (nt_msg.device_name[IFNAMSIZ - 1] != '\0') { + pr_err("the device name is invalid.\n"); + ret = -EINVAL; + goto out_invalid; + } ret = hns3_cae_k_get_netdev_by_ifname(nt_msg.device_name, &nic_dev); if (ret) { pr_err("can not get the netdevice correctly\n"); -- 2.25.1

1 2

[PATCH] netdevsim: Fix error handling in nsim_fib_init and nsim_fib_exit
by liaichun 15 Jun '20

15 Jun '20

From: YueHaibing <yuehaibing(a)huawei.com> mainline inclusion from mainline-5.4 commit 33902b4a4227877896dd9368ac10f4ca0d100de5 category: bugfix issue: I1JZHT bugzilla: NA ------------------------------ In nsim_fib_init(), if register_fib_notifier failed, nsim_fib_net_ops should be unregistered before return. In nsim_fib_exit(), unregister_fib_notifier should be called before nsim_fib_net_ops be unregistered, otherwise may cause use-after-free: BUG: KASAN: use-after-free in nsim_fib_event_nb+0x342/0x570 [netdevsim] Read of size 8 at addr ffff8881daaf4388 by task kworker/0:3/3499 CPU: 0 PID: 3499 Comm: kworker/0:3 Not tainted 5.3.0-rc7+ #30 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 Workqueue: ipv6_addrconf addrconf_dad_work [ipv6] Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0xa9/0x10e lib/dump_stack.c:113 print_address_description+0x65/0x380 mm/kasan/report.c:351 __kasan_report+0x149/0x18d mm/kasan/report.c:482 kasan_report+0xe/0x20 mm/kasan/common.c:618 nsim_fib_event_nb+0x342/0x570 [netdevsim] notifier_call_chain+0x52/0xf0 kernel/notifier.c:95 __atomic_notifier_call_chain+0x78/0x140 kernel/notifier.c:185 call_fib_notifiers+0x30/0x60 net/core/fib_notifier.c:30 call_fib6_entry_notifiers+0xc1/0x100 [ipv6] fib6_add+0x92e/0x1b10 [ipv6] __ip6_ins_rt+0x40/0x60 [ipv6] ip6_ins_rt+0x84/0xb0 [ipv6] __ipv6_ifa_notify+0x4b6/0x550 [ipv6] ipv6_ifa_notify+0xa5/0x180 [ipv6] addrconf_dad_completed+0xca/0x640 [ipv6] addrconf_dad_work+0x296/0x960 [ipv6] process_one_work+0x5c0/0xc00 kernel/workqueue.c:2269 worker_thread+0x5c/0x670 kernel/workqueue.c:2415 kthread+0x1d7/0x200 kernel/kthread.c:255 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:352 Allocated by task 3388: save_stack+0x19/0x80 mm/kasan/common.c:69 set_track mm/kasan/common.c:77 [inline] __kasan_kmalloc.constprop.3+0xa0/0xd0 mm/kasan/common.c:493 kmalloc include/linux/slab.h:557 [inline] kzalloc include/linux/slab.h:748 [inline] ops_init+0xa9/0x220 net/core/net_namespace.c:127 __register_pernet_operations net/core/net_namespace.c:1135 [inline] register_pernet_operations+0x1d4/0x420 net/core/net_namespace.c:1212 register_pernet_subsys+0x24/0x40 net/core/net_namespace.c:1253 nsim_fib_init+0x12/0x70 [netdevsim] veth_get_link_ksettings+0x2b/0x50 [veth] do_one_initcall+0xd4/0x454 init/main.c:939 do_init_module+0xe0/0x330 kernel/module.c:3490 load_module+0x3c2f/0x4620 kernel/module.c:3841 __do_sys_finit_module+0x163/0x190 kernel/module.c:3931 do_syscall_64+0x72/0x2e0 arch/x86/entry/common.c:296 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 3534: save_stack+0x19/0x80 mm/kasan/common.c:69 set_track mm/kasan/common.c:77 [inline] __kasan_slab_free+0x130/0x180 mm/kasan/common.c:455 slab_free_hook mm/slub.c:1423 [inline] slab_free_freelist_hook mm/slub.c:1474 [inline] slab_free mm/slub.c:3016 [inline] kfree+0xe9/0x2d0 mm/slub.c:3957 ops_free net/core/net_namespace.c:151 [inline] ops_free_list.part.7+0x156/0x220 net/core/net_namespace.c:184 ops_free_list net/core/net_namespace.c:182 [inline] __unregister_pernet_operations net/core/net_namespace.c:1165 [inline] unregister_pernet_operations+0x221/0x2a0 net/core/net_namespace.c:1224 unregister_pernet_subsys+0x1d/0x30 net/core/net_namespace.c:1271 nsim_fib_exit+0x11/0x20 [netdevsim] nsim_module_exit+0x16/0x21 [netdevsim] __do_sys_delete_module kernel/module.c:1015 [inline] __se_sys_delete_module kernel/module.c:958 [inline] __x64_sys_delete_module+0x244/0x330 kernel/module.c:958 do_syscall_64+0x72/0x2e0 arch/x86/entry/common.c:296 entry_SYSCALL_64_after_hwframe+0x49/0xbe Reported-by: Hulk Robot <hulkci(a)huawei.com> Fixes: 59c84b9fcf42 ("netdevsim: Restore per-network namespace accounting for fib entries") Signed-off-by: YueHaibing <yuehaibing(a)huawei.com> Acked-by: Jakub Kicinski <jakub.kicinski(a)netronome.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: LiAichun <liaichun(a)huawei.com> --- drivers/net/netdevsim/fib.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c index f61d094746c0..1a251f76d09b 100644 --- a/drivers/net/netdevsim/fib.c +++ b/drivers/net/netdevsim/fib.c @@ -241,8 +241,8 @@ static struct pernet_operations nsim_fib_net_ops = { void nsim_fib_exit(void) { - unregister_pernet_subsys(&nsim_fib_net_ops); unregister_fib_notifier(&nsim_fib_nb); + unregister_pernet_subsys(&nsim_fib_net_ops); } int nsim_fib_init(void) @@ -258,6 +258,7 @@ int nsim_fib_init(void) err = register_fib_notifier(&nsim_fib_nb, nsim_fib_dump_inconsistent); if (err < 0) { pr_err("Failed to register fib notifier\n"); + unregister_pernet_subsys(&nsim_fib_net_ops); goto err_out; } -- 2.20.1

4 3

[PATCH] scsi: Fix kabi change due to add offline_already member in struct scsi_device
by Yang Yingliang 12 Jun '20

12 Jun '20

From: Ye Bin <yebin10(a)huawei.com> hulk inclusion category: bugfix bugzilla: 34604 CVE: NA ----------------------------------------------- Signed-off-by: Ye Bin <yebin10(a)huawei.com> Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/scsi/scsi_lib.c | 4 ++-- include/scsi/scsi_device.h | 7 ++++--- 2 files changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index a8043039f53e..bdb90f5c9eeb 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1438,7 +1438,7 @@ scsi_prep_state_check(struct scsi_device *sdev, struct request *req) * before trying any recovery commands. */ if (!sdev->offline_already) { - sdev->offline_already = true; + sdev->offline_already = 1; sdev_printk(KERN_ERR, sdev, "rejecting I/O to offline device\n"); } @@ -2859,7 +2859,7 @@ scsi_device_set_state(struct scsi_device *sdev, enum scsi_device_state state) break; } - sdev->offline_already = false; + sdev->offline_already = 0; sdev->sdev_state = state; return 0; diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 52b255e868a9..550739a5ea96 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -201,8 +201,6 @@ struct scsi_device { unsigned lun_in_cdb:1; /* Store LUN bits in CDB[1] */ unsigned unmap_limit_for_ws:1; /* Use the UNMAP limit for WRITE SAME */ - bool offline_already; /* Device offline message logged */ - atomic_t disk_events_disable_depth; /* disable depth for disk events */ DECLARE_BITMAP(supported_events, SDEV_EVT_MAXBITS); /* supported events */ @@ -230,8 +228,11 @@ struct scsi_device { struct mutex state_mutex; enum scsi_device_state sdev_state; struct task_struct *quiesced_by; - +#ifndef __GENKSYMS__ + unsigned long offline_already; /* Device offline message logged */ +#else KABI_RESERVE(1) +#endif KABI_RESERVE(2) KABI_RESERVE(3) KABI_RESERVE(4) -- 2.25.1

1 0

[PATCH] ALSA: proc: Avoid possible leaks of snd_info_entry objects
by Yang Yingliang 12 Jun '20

12 Jun '20

From: Takashi Iwai <tiwai(a)suse.de> mainline inclusion from mainline-v5.1-rc1 commit 3a55437141a1d287dead685b37fe240185144f15 category: bugfix bugzilla: 34614 CVE: NA ----------------------------------------------- This patch changes the parent pointer assignment of snd_info_entry object to be always non-NULL. More specifically,check the parent argument in snd_info_create_module_entry() & co, and assign snd_proc_root if NULL is passed there. This assures that the proc object is always freed when the root is freed, so avoid possible memory leaks. For example, some error paths (e.g. snd_info_register() error at snd_minor_info_init()) may leave snd_info_entry object although the proc file itself is freed. Signed-off-by: Takashi Iwai <tiwai(a)suse.de> Signed-off-by: Ye Bin <yebin10(a)huawei.com> Reviewed-by: Yang Yingliang <yangyingliang(a)huawei.com> Signed-off-by: Ye Bin <yebin10(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- sound/core/info.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/sound/core/info.c b/sound/core/info.c index 679136fba730..3411bea54d66 100644 --- a/sound/core/info.c +++ b/sound/core/info.c @@ -744,7 +744,11 @@ struct snd_info_entry *snd_info_create_module_entry(struct module * module, const char *name, struct snd_info_entry *parent) { - struct snd_info_entry *entry = snd_info_create_entry(name, parent); + struct snd_info_entry *entry; + + if (!parent) + parent = snd_proc_root; + entry = snd_info_create_entry(name, parent); if (entry) entry->module = module; return entry; @@ -765,7 +769,11 @@ struct snd_info_entry *snd_info_create_card_entry(struct snd_card *card, const char *name, struct snd_info_entry * parent) { - struct snd_info_entry *entry = snd_info_create_entry(name, parent); + struct snd_info_entry *entry; + + if (!parent) + parent = card->proc_root; + entry = snd_info_create_entry(name, parent); if (entry) { entry->module = card->module; entry->card = card; -- 2.25.1

1 0

[PATCH 01/12] jbd2: clean __jbd2_journal_abort_hard() and __journal_abort_soft()
by Yang Yingliang 12 Jun '20

12 Jun '20

From: "zhangyi (F)" <yi.zhang(a)huawei.com> mainline inclusion from mainline-5.6-rc1 commit 7f6225e446cc8dfa4c3c7959a4de3dd03ec277bf category: bugfix bugzilla: 34619 CVE: NA --------------------------- __jbd2_journal_abort_hard() is no longer used, so now we can merge __jbd2_journal_abort_hard() and __journal_abort_soft() these two functions into jbd2_journal_abort() and remove them. Signed-off-by: zhangyi (F) <yi.zhang(a)huawei.com> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/20191204124614.45424-5-yi.zhang@huawei.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Reviewed-by: Zhang Xiaoxu <zhangxiaoxu5(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/jbd2/journal.c | 103 ++++++++++++++++++------------------------- include/linux/jbd2.h | 1 - 2 files changed, 42 insertions(+), 62 deletions(-) diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 1f085f0bf908..7301bb766172 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -101,7 +101,6 @@ EXPORT_SYMBOL(jbd2_journal_release_jbd_inode); EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate); EXPORT_SYMBOL(jbd2_inode_cache); -static void __journal_abort_soft (journal_t *journal, int errno); static int jbd2_journal_create_slab(size_t slab_size); #ifdef CONFIG_JBD2_DEBUG @@ -810,7 +809,7 @@ int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr, "at offset %lu on %s\n", __func__, blocknr, journal->j_devname); err = -EIO; - __journal_abort_soft(journal, err); + jbd2_journal_abort(journal, err); } } else { *retp = blocknr; /* +journal->j_blk_offset */ @@ -2108,64 +2107,6 @@ int jbd2_journal_wipe(journal_t *journal, int write) return err; } -/* - * Journal abort has very specific semantics, which we describe - * for journal abort. - * - * Two internal functions, which provide abort to the jbd layer - * itself are here. - */ - -/* - * Quick version for internal journal use (doesn't lock the journal). - * Aborts hard --- we mark the abort as occurred, but do _nothing_ else, - * and don't attempt to make any other journal updates. - */ -void __jbd2_journal_abort_hard(journal_t *journal) -{ - transaction_t *transaction; - - if (journal->j_flags & JBD2_ABORT) - return; - - printk(KERN_ERR "Aborting journal on device %s.\n", - journal->j_devname); - - write_lock(&journal->j_state_lock); - journal->j_flags |= JBD2_ABORT; - transaction = journal->j_running_transaction; - if (transaction) - __jbd2_log_start_commit(journal, transaction->t_tid); - write_unlock(&journal->j_state_lock); -} - -/* Soft abort: record the abort error status in the journal superblock, - * but don't do any other IO. */ -static void __journal_abort_soft (journal_t *journal, int errno) -{ - int old_errno; - - write_lock(&journal->j_state_lock); - old_errno = journal->j_errno; - if (!journal->j_errno || errno == -ESHUTDOWN) - journal->j_errno = errno; - - if (journal->j_flags & JBD2_ABORT) { - write_unlock(&journal->j_state_lock); - if (old_errno != -ESHUTDOWN && errno == -ESHUTDOWN) - jbd2_journal_update_sb_errno(journal); - return; - } - write_unlock(&journal->j_state_lock); - - __jbd2_journal_abort_hard(journal); - - jbd2_journal_update_sb_errno(journal); - write_lock(&journal->j_state_lock); - journal->j_flags |= JBD2_REC_ERR; - write_unlock(&journal->j_state_lock); -} - /** * void jbd2_journal_abort () - Shutdown the journal immediately. * @journal: the journal to shutdown. @@ -2209,7 +2150,47 @@ static void __journal_abort_soft (journal_t *journal, int errno) void jbd2_journal_abort(journal_t *journal, int errno) { - __journal_abort_soft(journal, errno); + transaction_t *transaction; + + /* + * ESHUTDOWN always takes precedence because a file system check + * caused by any other journal abort error is not required after + * a shutdown triggered. + */ + write_lock(&journal->j_state_lock); + if (journal->j_flags & JBD2_ABORT) { + int old_errno = journal->j_errno; + + write_unlock(&journal->j_state_lock); + if (old_errno != -ESHUTDOWN && errno == -ESHUTDOWN) { + journal->j_errno = errno; + jbd2_journal_update_sb_errno(journal); + } + return; + } + + /* + * Mark the abort as occurred and start current running transaction + * to release all journaled buffer. + */ + pr_err("Aborting journal on device %s.\n", journal->j_devname); + + journal->j_flags |= JBD2_ABORT; + journal->j_errno = errno; + transaction = journal->j_running_transaction; + if (transaction) + __jbd2_log_start_commit(journal, transaction->t_tid); + write_unlock(&journal->j_state_lock); + + /* + * Record errno to the journal super block, so that fsck and jbd2 + * layer could realise that a filesystem check is needed. + */ + jbd2_journal_update_sb_errno(journal); + + write_lock(&journal->j_state_lock); + journal->j_flags |= JBD2_REC_ERR; + write_unlock(&journal->j_state_lock); } /** diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 7dd9d25a9cbb..12b935c9ec1e 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1427,7 +1427,6 @@ extern int jbd2_journal_skip_recovery (journal_t *); extern void jbd2_journal_update_sb_errno(journal_t *); extern int jbd2_journal_update_sb_log_tail (journal_t *, tid_t, unsigned long, int); -extern void __jbd2_journal_abort_hard (journal_t *); extern void jbd2_journal_abort (journal_t *, int); extern int jbd2_journal_errno (journal_t *); extern void jbd2_journal_ack_err (journal_t *); -- 2.25.1

1 11

Minutes of the meeting //: 【Meeting Notice】Kernel & testing sync between Linaro and openEuler Time: 2020-06-10 16:00-17:30
by Guohanjun (Hanjun Guo) 11 Jun '20

11 Jun '20

Attendees (I can see more people join later but can’t remember now): [cid:image001.png@01D63F6C.270B2CF0] Following action items: * Vincent to share the JIRA link for thermal pressure * Vincent to share the JIRA link for scheduler improvements * Anmar to work on the opening of Power and Performance Project * Hanjun/Jonathan to share some plan for openEuler kernel in the coming 6 or 12 months * Anmar to create the open mailing list for LKQ project, so that Fengguang and the team can participate And see attached for Linaro slide, thanks! 发件人: Meeting Book via Kernel [mailto:kernel@openeuler.org] 发送时间: 2020年6月3日 16:01 收件人: kernel(a)openeuler.org 主题: 【Meeting Notice】Kernel & testing sync between Linaro and openEuler Time: 2020-06-10 16:00-17:30 Topic Kernel & testing sync between Linaro and openEuler Time 2020-06-10 16:00-17:30((UTC+08:00)Beijing) Join Conference Join (External) >><https://welink-meeting.zoom.us/j/834726983> Meeting ID 834 726 983 Convener 郭寒军 Agenda * Linux Kernel Update by Linaro - 15 mins * Linux Kernel Functional Testing (LKFT) introduction - 15mins * Brief introduction for openEuler and the kernel - 15mins * Brief introduction for Crystal testing system - 15 mins * Open discussions - about 30 mins Tips: Dial the access number to join conference<http://app.huawei.com/eshare/voiceMeetings> 注：仅支持部分国家和地区。( Only some countries and regions are supported.) 请点击会议链接按照提示下载Zoom客户端入会，并升级Zoom最新版本。 Please click the conference link and download the Zoom to join the conference, and upgrade to the latest version of Zoom.

2 1

[PATCH] irqchip/gic-v3-its: its supoport s3/s4
by Hongbo Yao 09 Jun '20

09 Jun '20

commit dba0bc7b76dcf(irqchip/gic-v3-its: add ability to save/restore ITS state) add support to save/restore its suspend state. However, it needs to set ITS_FLAGS_SAVE_SUSPEND_STATE to 1 when we want to resend MAPC. In GIC500, GITS_typer.HCC is not zero, and it can be used to judge if we can resend MAPC if the firmware restores the state, but when GITS_typer.HCC is zero, and it will never have chance to set the flag, which will lead to a failuer to power off GIC logic in suspend. Signed-off-by: Hongbo Yao <yaohongbo(a)huawei.com> --- drivers/irqchip/irq-gic-v3-its.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 881466163c99..6ea2809b8680 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -3733,8 +3733,7 @@ static int __init its_probe_one(struct resource *res, ctlr |= GITS_CTLR_ImDe; writel_relaxed(ctlr, its->base + GITS_CTLR); - if (GITS_TYPER_HCC(typer)) - its->flags |= ITS_FLAGS_SAVE_SUSPEND_STATE; + its->flags |= ITS_FLAGS_SAVE_SUSPEND_STATE; err = its_init_domain(handle, its); if (err) -- 2.20.1

1 0

(no subject)
by liaichun 09 Jun '20

09 Jun '20

From: LiAichun <liaichun(a)huawei.com> euleros inclusion commit NA category:bugfix bugzilla:NA CVE:NA issue:I1JZHT ------------------------------------------------- From:YueHaibing<> Subject: [PATCH] netdevsim: Fix error handling in nsim_fib_init and neim_fib_exit Date: Mon, 8 Jun 2020 15:13:40 +0800 In nsim_fib_init(),if register_fib_notifier failed,nsim_fib_net_ops should be unregistered before return; In nsim_fib_exit(),unregister_fib_notifier should be called before nsim_fib_net_ops be unregistered, otherwise may cause use-after-free More detailed information can refer to: https://lkml.org/lkml/2019/10/11/216 Reported-by:Hulk Robot <hulkci(a)huawei.com> Fixes: 59c84b9fcf42("netdevsim: Restore per-network namespace accounting for fib entries") Signed-off-by: YueHaibing <yuehaibing(a)huawei.com> Signed-off-by: LiAichun <liaichun(a)huawei.com> --- drivers/net/netdevsim/fib.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c index f61d094..d5c01b8 100644 --- a/drivers/net/netdevsim/fib.c +++ b/drivers/net/netdevsim/fib.c @@ -241,8 +241,8 @@ static int __net_init nsim_fib_netns_init(struct net *net) void nsim_fib_exit(void) { - unregister_pernet_subsys(&nsim_fib_net_ops); unregister_fib_notifier(&nsim_fib_nb); + unregister_pernet_subsys(&nsim_fib_net_ops); } int nsim_fib_init(void) @@ -257,6 +257,7 @@ int nsim_fib_init(void) err = register_fib_notifier(&nsim_fib_nb, nsim_fib_dump_inconsistent); if (err < 0) { + unregister_pernet_subsys(&nsim_fib_net_ops); pr_err("Failed to register fib notifier\n"); goto err_out; } -- 1.8.3.1

1 0

(no subject)
by liaichun 09 Jun '20

09 Jun '20

From: LiAichun <liaichun(a)huawei.com> euleros inclusion commit NA category:bugfix bugzilla:NA CVE:NA Fix issue:gitee.com/openeuler/kernel/issues/I1JZHT ------------------------------------------------- From:YueHaibing<> Subject: [PATCH] netdevsim: Fix error handling in nsim_fib_init and neim_fib_exit Date: Mon, 8 Jun 2020 15:13:40 +0800 In nsim_fib_init(),if register_fib_notifier failed,nsim_fib_net_ops should be unregistered before return; In nsim_fib_exit(),unregister_fib_notifier should be called before nsim_fib_net_ops be unregistered, otherwise may cause use-after-free More detailed information can refer to: https://lkml.org/lkml/2019/10/11/216 Reported-by:Hulk Robot <hulkci(a)huawei.com> Fixes: 59c84b9fcf42("netdevsim: Restore per-network namespace accounting for fib entries") Signed-off-by: YueHaibing <yuehaibing(a)huawei.com> Signed-off-by: LiAichun <liaichun(a)huawei.com> --- drivers/net/netdevsim/fib.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c index f61d094..d5c01b8 100644 --- a/drivers/net/netdevsim/fib.c +++ b/drivers/net/netdevsim/fib.c @@ -241,8 +241,8 @@ static int __net_init nsim_fib_netns_init(struct net *net) void nsim_fib_exit(void) { - unregister_pernet_subsys(&nsim_fib_net_ops); unregister_fib_notifier(&nsim_fib_nb); + unregister_pernet_subsys(&nsim_fib_net_ops); } int nsim_fib_init(void) @@ -257,6 +257,7 @@ int nsim_fib_init(void) err = register_fib_notifier(&nsim_fib_nb, nsim_fib_dump_inconsistent); if (err < 0) { + unregister_pernet_subsys(&nsim_fib_net_ops); pr_err("Failed to register fib notifier\n"); goto err_out; } -- 1.8.3.1

1 0

(no subject)
by liaichun 09 Jun '20

09 Jun '20

From: LiAichun <liaichun(a)huawei.com> mainline inclusion from mainline-4.19.90-2003.4.0 commit a91b7a28e76a702bd81357bf41a45dab6486716b category:bugfix bugzilla:NA CVE:NA ------------------------------------------------- From:YueHaibing<> Subject: [PATCH] netdevsim: Fix error handling in nsim_fib_init and neim_fib_exit Date: Mon, 8 Jun 2020 15:13:40 +0800 In nsim_fib_init(),if register_fib_notifier failed,nsim_fib_net_ops should be unregistered before return; In nsim_fib_exit(),unregister_fib_notifier should be called before nsim_fib_net_ops be unregistered, otherwise may cause use-after-free More detailed information can refer to: https://lkml.org/lkml/2019/10/11/216 Reported-by:Hulk Robot <hulkci(a)huawei.com> Fixes: 59c84b9fcf42("netdevsim: Restore per-network namespace accounting for fib entries") Signed-off-by: YueHaibing <yuehaibing(a)huawei.com> Signed-off-by: LiAichun <liaichun(a)huawei.com> --- drivers/net/netdevsim/fib.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c index f61d094..d5c01b8 100644 --- a/drivers/net/netdevsim/fib.c +++ b/drivers/net/netdevsim/fib.c @@ -241,8 +241,8 @@ static int __net_init nsim_fib_netns_init(struct net *net) void nsim_fib_exit(void) { - unregister_pernet_subsys(&nsim_fib_net_ops); unregister_fib_notifier(&nsim_fib_nb); + unregister_pernet_subsys(&nsim_fib_net_ops); } int nsim_fib_init(void) @@ -257,6 +257,7 @@ int nsim_fib_init(void) err = register_fib_notifier(&nsim_fib_nb, nsim_fib_dump_inconsistent); if (err < 0) { + unregister_pernet_subsys(&nsim_fib_net_ops); pr_err("Failed to register fib notifier\n"); goto err_out; } -- 1.8.3.1

2 1

[PATCH] net-netdevsim-fix-resource-leak
by liaichun 09 Jun '20

09 Jun '20

In nsim_fib_init(),if register_fib_notifier failed,nsim_fib_net_ops should be unregistered before return; In nsim_fib_exit(),unregister_fib_notifier should be called before nsim_fib_net_ops be unregistered, otherwise may cause use-after-free More detailed information can refer to: https://lkml.org/lkml/2019/10/11/216 kernel inclusion from:kernel-4.19 commit:2dca76fa95bf03c15bdcacd7cfa8f974c1a799f6 category:bugfix bugzilla:NA CVE:NA Signed-off-by: liaichun <513565428(a)qq.com> DESC:fix netdevsim resource leak --- drivers/net/netdevsim/fib.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c index f61d094..d5c01b8 100644 --- a/drivers/net/netdevsim/fib.c +++ b/drivers/net/netdevsim/fib.c @@ -241,8 +241,8 @@ static int __net_init nsim_fib_netns_init(struct net *net) void nsim_fib_exit(void) { - unregister_pernet_subsys(&nsim_fib_net_ops); unregister_fib_notifier(&nsim_fib_nb); + unregister_pernet_subsys(&nsim_fib_net_ops); } int nsim_fib_init(void) @@ -257,6 +257,7 @@ int nsim_fib_init(void) err = register_fib_notifier(&nsim_fib_nb, nsim_fib_dump_inconsistent); if (err < 0) { + unregister_pernet_subsys(&nsim_fib_net_ops); pr_err("Failed to register fib notifier\n"); goto err_out; } -- 1.8.3.1

2 1

[PATCH] net-netdevsim-fix-resource-leak
by liaichun 08 Jun '20

08 Jun '20

In nsim_fib_init(),if register_fib_notifier failed,nsim_fib_net_ops should be unregistered before return; In nsim_fib_exit(),unregister_fib_notifier should be called before nsim_fib_net_ops be unregistered, otherwise may cause use-after-free More detailed information can refer to: https://lkml.org/lkml/2019/10/11/216 Signed-off-by: liaichun <513565428(a)qq.com> Tested-by: liaichun <513565428(a)qq.com> Type:bugfix ID:NA SUG:restart DESC:fix netdevsim resource leak --- drivers/net/netdevsim/fib.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c index f61d094..d5c01b8 100644 --- a/drivers/net/netdevsim/fib.c +++ b/drivers/net/netdevsim/fib.c @@ -241,8 +241,8 @@ static int __net_init nsim_fib_netns_init(struct net *net) void nsim_fib_exit(void) { - unregister_pernet_subsys(&nsim_fib_net_ops); unregister_fib_notifier(&nsim_fib_nb); + unregister_pernet_subsys(&nsim_fib_net_ops); } int nsim_fib_init(void) @@ -257,6 +257,7 @@ int nsim_fib_init(void) err = register_fib_notifier(&nsim_fib_nb, nsim_fib_dump_inconsistent); if (err < 0) { + unregister_pernet_subsys(&nsim_fib_net_ops); pr_err("Failed to register fib notifier\n"); goto err_out; } -- 1.8.3.1

1 0

[PATCH] net-netdevsim-fix-resource-leak
by liaichun 08 Jun '20

08 Jun '20

diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c index f61d094..d5c01b8 100644 --- a/drivers/net/netdevsim/fib.c +++ b/drivers/net/netdevsim/fib.c @@ -241,8 +241,8 @@ static int __net_init nsim_fib_netns_init(struct net *net) void nsim_fib_exit(void) { - unregister_pernet_subsys(&nsim_fib_net_ops); unregister_fib_notifier(&nsim_fib_nb); + unregister_pernet_subsys(&nsim_fib_net_ops); } int nsim_fib_init(void) @@ -257,6 +257,7 @@ int nsim_fib_init(void) err = register_fib_notifier(&nsim_fib_nb, nsim_fib_dump_inconsistent); if (err < 0) { + unregister_pernet_subsys(&nsim_fib_net_ops); pr_err("Failed to register fib notifier\n"); goto err_out; } -- 1.8.3.1

2 1

[PATCH] net-netdevsim-fix-resource-leak
by liaichun 08 Jun '20

08 Jun '20

From: liaichun <liaichun(a)huawei.com> diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c index f61d094..d5c01b8 100644 --- a/drivers/net/netdevsim/fib.c +++ b/drivers/net/netdevsim/fib.c @@ -241,8 +241,8 @@ static int __net_init nsim_fib_netns_init(struct net *net) void nsim_fib_exit(void) { - unregister_pernet_subsys(&nsim_fib_net_ops); unregister_fib_notifier(&nsim_fib_nb); + unregister_pernet_subsys(&nsim_fib_net_ops); } int nsim_fib_init(void) @@ -257,6 +257,7 @@ int nsim_fib_init(void) err = register_fib_notifier(&nsim_fib_nb, nsim_fib_dump_inconsistent); if (err < 0) { + unregister_pernet_subsys(&nsim_fib_net_ops); pr_err("Failed to register fib notifier\n"); goto err_out; } -- 1.8.3.1

1 0

[PATCH] net-netdevsim-fix-resource-leak
by liaichun 08 Jun '20

08 Jun '20

diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c index f61d094..d5c01b8 100644 --- a/drivers/net/netdevsim/fib.c +++ b/drivers/net/netdevsim/fib.c @@ -241,8 +241,8 @@ static int __net_init nsim_fib_netns_init(struct net *net) void nsim_fib_exit(void) { - unregister_pernet_subsys(&nsim_fib_net_ops); unregister_fib_notifier(&nsim_fib_nb); + unregister_pernet_subsys(&nsim_fib_net_ops); } int nsim_fib_init(void) @@ -257,6 +257,7 @@ int nsim_fib_init(void) err = register_fib_notifier(&nsim_fib_nb, nsim_fib_dump_inconsistent); if (err < 0) { + unregister_pernet_subsys(&nsim_fib_net_ops); pr_err("Failed to register fib notifier\n"); goto err_out; } -- 1.8.3.1

1 0

[PATCH] net-netdevsim-fix-resource-leak
by liaichun 08 Jun '20

08 Jun '20

From: liaichun <liaichun(a)huawei.com> diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c index f61d094..d5c01b8 100644 --- a/drivers/net/netdevsim/fib.c +++ b/drivers/net/netdevsim/fib.c @@ -241,8 +241,8 @@ static int __net_init nsim_fib_netns_init(struct net *net) void nsim_fib_exit(void) { - unregister_pernet_subsys(&nsim_fib_net_ops); unregister_fib_notifier(&nsim_fib_nb); + unregister_pernet_subsys(&nsim_fib_net_ops); } int nsim_fib_init(void) @@ -257,6 +257,7 @@ int nsim_fib_init(void) err = register_fib_notifier(&nsim_fib_nb, nsim_fib_dump_inconsistent); if (err < 0) { + unregister_pernet_subsys(&nsim_fib_net_ops); pr_err("Failed to register fib notifier\n"); goto err_out; } -- 1.8.3.1

1 0

[PATCH] net-netdevsim-fix-resource-leak
by liaichun 08 Jun '20

08 Jun '20

diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c index f61d094..d5c01b8 100644 --- a/drivers/net/netdevsim/fib.c +++ b/drivers/net/netdevsim/fib.c @@ -241,8 +241,8 @@ static int __net_init nsim_fib_netns_init(struct net *net) void nsim_fib_exit(void) { - unregister_pernet_subsys(&nsim_fib_net_ops); unregister_fib_notifier(&nsim_fib_nb); + unregister_pernet_subsys(&nsim_fib_net_ops); } int nsim_fib_init(void) @@ -257,6 +257,7 @@ int nsim_fib_init(void) err = register_fib_notifier(&nsim_fib_nb, nsim_fib_dump_inconsistent); if (err < 0) { + unregister_pernet_subsys(&nsim_fib_net_ops); pr_err("Failed to register fib notifier\n"); goto err_out; } -- 1.8.3.1

1 0

[PATCH v2] scsi: hisi_sas: directly trigger error handle of scsi instead of waiting for timeout
by Luo Jiaxing 05 Jun '20

05 Jun '20

We used timeout mechanism of scsi layer to trigger some IO's error handle, this type of abnormal IO require driver to enter error handle to clear the residue in the hardware. But timeout mechanism caught error handle time to be longer, some threads need to wait for tens of seconds when IO failed and enter error handle, so we try to trigger error handling directly. Signed-off-by: Luo Jiaxing <luojiaxing(a)huawei.com> --- drivers/scsi/hisi_sas/hisi_sas_v1_hw.c | 4 +++- drivers/scsi/hisi_sas/hisi_sas_v2_hw.c | 4 +++- drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 4 +++- 3 files changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c index 031091e..49ea3b7 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c @@ -1263,8 +1263,10 @@ static int slot_complete_v1_hw(struct hisi_hba *hisi_hba, !(cmplt_hdr_data & CMPLT_HDR_RSPNS_XFRD_MSK)) { slot_err_v1_hw(hisi_hba, task, slot); - if (unlikely(slot->abort)) + if (unlikely(slot->abort)) { + sas_task_abort(task); return ts->stat; + } goto out; } diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c index 6568e20..8ebddf5 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c @@ -2406,8 +2406,10 @@ slot_complete_v2_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot) error_info[0], error_info[1], error_info[2], error_info[3]); - if (unlikely(slot->abort)) + if (unlikely(slot->abort)) { + sas_task_abort(task); return ts->stat; + } goto out; } diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index 5b80856..7fd067c 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -2408,8 +2408,10 @@ slot_complete_v3_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot) dev_info(dev, "data underflow without sense, rsp_code:0x%x, rc:%d.\n", iu->resp_data[0], rc); } - if (unlikely(slot->abort)) + if (unlikely(slot->abort)) { + sas_task_abort(task); return ts->stat; + } goto out; } -- 2.7.4

1 0

[PATCH v1 hulk-4.19-next] scsi: hisi_sas: directly trigger error handle of scsi instead of waiting for timeout
by Luo Jiaxing 05 Jun '20

05 Jun '20

driver inclusion category: bugfix bugzilla: NA DTS: NA ----------------------------------------------------------------------- We used timeout mechanism of scsi layer to trigger some IO's error handle, this type of abnormal IO require driver to enter error handle to clear the residue in the hardware. But timeout mechanism caught error handle time to be longer, some threads need to wait for tens of seconds when IO failed and enter error handle, so we try to trigger error handling directly. Signed-off-by: Luo Jiaxing <luojiaxing(a)huawei.com> --- drivers/scsi/hisi_sas/hisi_sas_v1_hw.c | 4 +++- drivers/scsi/hisi_sas/hisi_sas_v2_hw.c | 4 +++- drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 4 +++- 3 files changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c index 031091e..49ea3b7 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c @@ -1263,8 +1263,10 @@ static int slot_complete_v1_hw(struct hisi_hba *hisi_hba, !(cmplt_hdr_data & CMPLT_HDR_RSPNS_XFRD_MSK)) { slot_err_v1_hw(hisi_hba, task, slot); - if (unlikely(slot->abort)) + if (unlikely(slot->abort)) { + sas_task_abort(task); return ts->stat; + } goto out; } diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c index 6568e20..8ebddf5 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c @@ -2406,8 +2406,10 @@ slot_complete_v2_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot) error_info[0], error_info[1], error_info[2], error_info[3]); - if (unlikely(slot->abort)) + if (unlikely(slot->abort)) { + sas_task_abort(task); return ts->stat; + } goto out; } diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index 5b80856..7fd067c 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -2408,8 +2408,10 @@ slot_complete_v3_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot) dev_info(dev, "data underflow without sense, rsp_code:0x%x, rc:%d.\n", iu->resp_data[0], rc); } - if (unlikely(slot->abort)) + if (unlikely(slot->abort)) { + sas_task_abort(task); return ts->stat; + } goto out; } -- 2.7.4

1 0

【Meeting Notice】Kernel & testing sync between Linaro and openEuler Time: 2020-06-10 16:00-17:30
by Meeting Book 03 Jun '20

03 Jun '20

1 0

【Meeting Notice】Kernel & testing sync between Linaro and openEuler Time: 2020-06-10 16:00-17:30
by Meeting Book 03 Jun '20

03 Jun '20

1 0

[PATCH 01/76] net: dsa: Do not make user port errors fatal
by Yang Yingliang 01 Jun '20

01 Jun '20

From: Florian Fainelli <f.fainelli(a)gmail.com> commit 86f8b1c01a0a537a73d2996615133be63cdf75db upstream. Prior to 1d27732f411d ("net: dsa: setup and teardown ports"), we would not treat failures to set-up an user port as fatal, but after this commit we would, which is a regression for some systems where interfaces may be declared in the Device Tree, but the underlying hardware may not be present (pluggable daughter cards for instance). Fixes: 1d27732f411d ("net: dsa: setup and teardown ports") Signed-off-by: Florian Fainelli <f.fainelli(a)gmail.com> Reviewed-by: Andrew Lunn <andrew(a)lunn.ch> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- net/dsa/dsa2.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 46ae4de..b036c55 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -412,7 +412,7 @@ static int dsa_tree_setup_switches(struct dsa_switch_tree *dst) err = dsa_switch_setup(ds); if (err) - return err; + continue; for (port = 0; port < ds->num_ports; port++) { dp = &ds->ports[port]; -- 1.8.3

1 75

[PATCH 1/9] net/hinic: Fix the firmware compatibility bug in the MAC reuse scenario
by Yang Yingliang 01 Jun '20

01 Jun '20

From: Chiqijun <chiqijun(a)huawei.com> driver inclusion category: bugfix bugzilla: 4472 ----------------------------------------------------------------------- 2.3.0.1 and later drivers and firmware add MAC reuse feature, when the driver is compatible with firmware version 2.3.0.0 and before, if the ip link command is used to configure the MAC and VLAN for the VF, it will cause the VF network anomaly. To solve this problem, the driver obtains the function capability from the firmware when loading, and determines whether to support MAC reuse for different processing. Signed-off-by: Chiqijun <chiqijun(a)huawei.com> Reviewed-by: Zengweiliang <zengweiliang.zengweiliang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/net/ethernet/huawei/hinic/hinic_hwdev.h | 1 + .../ethernet/huawei/hinic/hinic_mgmt_interface.h | 11 ++++ drivers/net/ethernet/huawei/hinic/hinic_nic_cfg.c | 45 +++++++++++++++-- drivers/net/ethernet/huawei/hinic/hinic_nic_cfg.h | 4 ++ drivers/net/ethernet/huawei/hinic/hinic_nic_io.c | 10 +++- drivers/net/ethernet/huawei/hinic/hinic_port_cmd.h | 2 + drivers/net/ethernet/huawei/hinic/hinic_sriov.c | 59 ++++++++++++++-------- 7 files changed, 106 insertions(+), 26 deletions(-) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hwdev.h b/drivers/net/ethernet/huawei/hinic/hinic_hwdev.h index a096f91..2a81867 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hwdev.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hwdev.h @@ -319,6 +319,7 @@ struct hinic_hwdev { struct hinic_board_info board_info; #define MGMT_VERSION_MAX_LEN 32 u8 mgmt_ver[MGMT_VERSION_MAX_LEN]; + u64 fw_support_func_flag; }; int hinic_init_comm_ch(struct hinic_hwdev *hwdev); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_mgmt_interface.h b/drivers/net/ethernet/huawei/hinic/hinic_mgmt_interface.h index 3c3be6e..8673cf5 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_mgmt_interface.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_mgmt_interface.h @@ -690,6 +690,15 @@ struct hinic_port_rt_cmd { u8 rsvd1[6]; }; +struct fw_support_func { + u8 status; + u8 version; + u8 rsvd0[6]; + + u64 flag; + u64 rsvd; +}; + struct hinic_vf_dcb_state { u8 status; u8 version; @@ -741,6 +750,8 @@ struct hinic_set_link_follow { int hinic_get_base_qpn(void *hwdev, u16 *global_qpn); +int hinic_get_fw_support_func(void *hwdev); + int hinic_vf_func_init(struct hinic_hwdev *hwdev); void hinic_vf_func_free(struct hinic_hwdev *hwdev); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_nic_cfg.c b/drivers/net/ethernet/huawei/hinic/hinic_nic_cfg.c index f9e16ec..7dfedbd 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_nic_cfg.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_nic_cfg.c @@ -201,6 +201,34 @@ int hinic_get_base_qpn(void *hwdev, u16 *global_qpn) return 0; } +int hinic_get_fw_support_func(void *hwdev) +{ + struct fw_support_func support_flag = {0}; + struct hinic_hwdev *dev = hwdev; + u16 out_size = sizeof(support_flag); + int err; + + if (!hwdev) + return -EINVAL; + + err = hinic_msg_to_mgmt_sync(hwdev, HINIC_MOD_L2NIC, + HINIC_PORT_CMD_GET_FW_SUPPORT_FLAG, + &support_flag, sizeof(support_flag), + &support_flag, &out_size, 0); + if (support_flag.status == HINIC_MGMT_CMD_UNSUPPORTED) { + nic_info(dev->dev_hdl, "Current firmware doesn't support to get function capability\n"); + support_flag.flag = 0; + } else if (support_flag.status || err || !out_size) { + nic_err(dev->dev_hdl, "Failed to get function capability, err: %d, status: 0x%x, out size: 0x%x\n", + err, support_flag.status, out_size); + return -EFAULT; + } + + dev->fw_support_func_flag = support_flag.flag; + + return 0; +} + #define HINIC_ADD_VLAN_IN_MAC 0x8000 #define HINIC_VLAN_ID_MASK 0x7FFF @@ -352,6 +380,11 @@ int hinic_update_mac_vlan(void *hwdev, u16 old_vlan, u16 new_vlan, int vf_id) if (!vf_info->pf_set_mac) return 0; + if (!FW_SUPPORT_MAC_REUSE_FUNC(dev)) { + nic_info(dev->dev_hdl, "Current firmware doesn't support mac reuse\n"); + return 0; + } + func_id = hinic_glb_pf_vf_offset(dev) + (u16)vf_id; vlan_id = old_vlan; if (vlan_id) @@ -2562,9 +2595,14 @@ static int hinic_init_vf_config(struct hinic_hwdev *hwdev, u16 vf_id) vf_info = hwdev->nic_io->vf_infos + HW_VF_ID_TO_OS(vf_id); if (vf_info->pf_set_mac) { func_id = hinic_glb_pf_vf_offset(hwdev) + vf_id; - vlan_id = vf_info->pf_vlan; - if (vlan_id) - vlan_id |= HINIC_ADD_VLAN_IN_MAC; + if (FW_SUPPORT_MAC_REUSE_FUNC(hwdev)) { + vlan_id = vf_info->pf_vlan; + if (vlan_id) + vlan_id |= HINIC_ADD_VLAN_IN_MAC; + } else { + vlan_id = 0; + } + err = hinic_set_mac(hwdev, vf_info->vf_mac_addr, vlan_id, func_id); if (err) { @@ -4065,3 +4103,4 @@ int hinic_get_sfp_type(void *hwdev, u8 *data0, u8 *data1) return 0; } + diff --git a/drivers/net/ethernet/huawei/hinic/hinic_nic_cfg.h b/drivers/net/ethernet/huawei/hinic/hinic_nic_cfg.h index 427d469..e0979df 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_nic_cfg.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_nic_cfg.h @@ -19,6 +19,10 @@ #define OS_VF_ID_TO_HW(os_vf_id) ((os_vf_id) + 1) #define HW_VF_ID_TO_OS(hw_vf_id) ((hw_vf_id) - 1) +#define FW_SUPPORT_MAC_REUSE 0x1 +#define FW_SUPPORT_MAC_REUSE_FUNC(hwdev) \ + ((hwdev)->fw_support_func_flag & FW_SUPPORT_MAC_REUSE) + #define HINIC_VLAN_PRIORITY_SHIFT 13 #define HINIC_RSS_INDIR_SIZE 256 diff --git a/drivers/net/ethernet/huawei/hinic/hinic_nic_io.c b/drivers/net/ethernet/huawei/hinic/hinic_nic_io.c index 1cb4e26..f2fb0bc 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_nic_io.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_nic_io.c @@ -831,9 +831,17 @@ int hinic_init_nic_hwdev(void *hwdev, u16 rx_buff_len) } /* VFs don't set port routine command report */ - if (hinic_func_type(dev) != TYPE_VF) + if (hinic_func_type(dev) != TYPE_VF) { + /* Get the fw support mac reuse flag */ + err = hinic_get_fw_support_func(hwdev); + if (err) { + nic_err(dev->dev_hdl, "Failed to get function capability\n"); + return err; + } + /* Inform mgmt to send sfp's information to driver */ err = hinic_set_port_routine_cmd_report(hwdev, true); + } return err; } diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port_cmd.h b/drivers/net/ethernet/huawei/hinic/hinic_port_cmd.h index 46464b1f..d428f48 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_port_cmd.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_port_cmd.h @@ -146,6 +146,8 @@ enum hinic_port_cmd { HINIC_PORT_CMD_SET_PORT_LINK_STATUS = 0x76, HINIC_PORT_CMD_SET_CGE_PAUSE_TIME_CFG = 0x77, + HINIC_PORT_CMD_GET_FW_SUPPORT_FLAG = 0x79, + HINIC_PORT_CMD_SET_PORT_REPORT = 0x7B, HINIC_PORT_CMD_LINK_STATUS_REPORT = 0xa0, diff --git a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c index 37d0116..73ab2d7 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c @@ -266,6 +266,42 @@ int hinic_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) /*lint -save -e574 -e734*/ #ifdef IFLA_VF_MAX +static int set_hw_vf_vlan(struct hinic_sriov_info *sriov_info, + u16 cur_vlanprio, int vf, u16 vlan, u8 qos) +{ + int err = 0; + u16 old_vlan = cur_vlanprio & VLAN_VID_MASK; + + if (vlan || qos) { + if (cur_vlanprio) { + err = hinic_kill_vf_vlan(sriov_info->hwdev, + OS_VF_ID_TO_HW(vf)); + if (err) { + nic_err(&sriov_info->pdev->dev, "Failed to delete vf %d old vlan %d\n", + vf, old_vlan); + return err; + } + } + err = hinic_add_vf_vlan(sriov_info->hwdev, + OS_VF_ID_TO_HW(vf), vlan, qos); + if (err) { + nic_err(&sriov_info->pdev->dev, "Failed to add vf %d new vlan %d\n", + vf, vlan); + return err; + } + } else { + err = hinic_kill_vf_vlan(sriov_info->hwdev, OS_VF_ID_TO_HW(vf)); + if (err) { + nic_err(&sriov_info->pdev->dev, "Failed to delete vf %d vlan %d\n", + vf, old_vlan); + return err; + } + } + + return hinic_update_mac_vlan(sriov_info->hwdev, old_vlan, vlan, + OS_VF_ID_TO_HW(vf)); +} + #ifdef IFLA_VF_VLAN_INFO_MAX int hinic_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos, __be16 vlan_proto) @@ -276,7 +312,6 @@ int hinic_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos) struct hinic_nic_dev *adapter = netdev_priv(netdev); struct hinic_sriov_info *sriov_info; u16 vlanprio, cur_vlanprio; - int err = 0; if (!FUNC_SUPPORT_SET_VF_MAC_VLAN(adapter->hwdev)) { nicif_err(adapter, drv, netdev, @@ -298,27 +333,7 @@ int hinic_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos) if (vlanprio == cur_vlanprio) return 0; - if (vlan || qos) { - if (cur_vlanprio) - err = hinic_kill_vf_vlan(sriov_info->hwdev, - OS_VF_ID_TO_HW(vf)); - if (err) - goto out; - err = hinic_add_vf_vlan(sriov_info->hwdev, OS_VF_ID_TO_HW(vf), - vlan, qos); - } else { - err = hinic_kill_vf_vlan(sriov_info->hwdev, OS_VF_ID_TO_HW(vf)); - } - - if (err) - return err; - - err = hinic_update_mac_vlan(sriov_info->hwdev, - cur_vlanprio & VLAN_VID_MASK, vlan, - OS_VF_ID_TO_HW(vf)); - -out: - return err; + return set_hw_vf_vlan(sriov_info, cur_vlanprio, vf, vlan, qos); } #endif -- 1.8.3

1 8

[PATCH] irqchip/gic-v3-its: Probe ITS page size for all GITS_BASERn registers
by Yang Yingliang 01 Jun '20

01 Jun '20

From: Marc Zyngier <maz(a)kernel.org> mainline inclusion from mainline-v5.6-rc4 commit d5df9dc96eb7423d3f742b13d5e1e479ff795eaa category: bugfix bugzilla: NA CVE: NA --------------------------- The GICv3 ITS driver assumes that once it has latched on a page size for a given BASER register, it can use the same page size as the maximum page size for all subsequent BASER registers. Although it worked so far, nothing in the architecture guarantees this, and Nianyao Tang hit this problem on some undisclosed implementation. Let's bite the bullet and probe the the supported page size on all BASER registers before starting to populate the tables. This simplifies the setup a bit, at the expense of a few additional MMIO accesses. Signed-off-by: Marc Zyngier <maz(a)kernel.org> Reported-by: Nianyao Tang <tangnianyao(a)huawei.com> Tested-by: Nianyao Tang <tangnianyao(a)huawei.com> Link: https://lore.kernel.org/r/1584089195-63897-1-git-send-email-zhangshaokun@hi… Signed-off-by: Hongbo Yao <yaohongbo(a)huawei.com> conflicts: drivers/irqchip/irq-gic-v3-its.c Reviewed-by: Hanjun Guo <guohanjun(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/irqchip/irq-gic-v3-its.c | 101 ++++++++++++++++++++++++++------------- 1 file changed, 67 insertions(+), 34 deletions(-) diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 59c6c0d..bfedab2 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -17,6 +17,7 @@ #include <linux/acpi.h> #include <linux/acpi_iort.h> +#include <linux/bitfield.h> #include <linux/bitmap.h> #include <linux/cpu.h> #include <linux/crash_dump.h> @@ -1768,17 +1769,16 @@ static void its_write_baser(struct its_node *its, struct its_baser *baser, } static int its_setup_baser(struct its_node *its, struct its_baser *baser, - u64 cache, u64 shr, u32 psz, u32 order, - bool indirect) + u64 cache, u64 shr, u32 order, bool indirect) { u64 val = its_read_baser(its, baser); u64 esz = GITS_BASER_ENTRY_SIZE(val); u64 type = GITS_BASER_TYPE(val); u64 baser_phys, tmp; - u32 alloc_pages; + u32 alloc_pages, psz; void *base; -retry_alloc_baser: + psz = baser->psz; alloc_pages = (PAGE_ORDER_TO_SIZE(order) / psz); if (alloc_pages > GITS_BASER_PAGES_MAX) { pr_warn("ITS@%pa: %s too large, reduce ITS pages %u->%u\n", @@ -1851,25 +1851,6 @@ static int its_setup_baser(struct its_node *its, struct its_baser *baser, goto retry_baser; } - if ((val ^ tmp) & GITS_BASER_PAGE_SIZE_MASK) { - /* - * Page size didn't stick. Let's try a smaller - * size and retry. If we reach 4K, then - * something is horribly wrong... - */ - free_pages((unsigned long)base, order); - baser->base = NULL; - - switch (psz) { - case SZ_16K: - psz = SZ_4K; - goto retry_alloc_baser; - case SZ_64K: - psz = SZ_16K; - goto retry_alloc_baser; - } - } - if (val != tmp) { pr_err("ITS@%pa: %s doesn't stick: %llx %llx\n", &its->phys_base, its_base_type_string[type], @@ -1895,13 +1876,14 @@ static int its_setup_baser(struct its_node *its, struct its_baser *baser, static bool its_parse_indirect_baser(struct its_node *its, struct its_baser *baser, - u32 psz, u32 *order, u32 ids) + u32 *order, u32 ids) { u64 tmp = its_read_baser(its, baser); u64 type = GITS_BASER_TYPE(tmp); u64 esz = GITS_BASER_ENTRY_SIZE(tmp); u64 val = GITS_BASER_InnerShareable | GITS_BASER_RaWaWb; u32 new_order = *order; + u32 psz = baser->psz; bool indirect = false; /* No need to enable Indirection if memory requirement < (psz*2)bytes */ @@ -1960,11 +1942,58 @@ static void its_free_tables(struct its_node *its) } } +static int its_probe_baser_psz(struct its_node *its, struct its_baser *baser) +{ + u64 psz = SZ_64K; + + while (psz) { + u64 val, gpsz; + + val = its_read_baser(its, baser); + val &= ~GITS_BASER_PAGE_SIZE_MASK; + + switch (psz) { + case SZ_64K: + gpsz = GITS_BASER_PAGE_SIZE_64K; + break; + case SZ_16K: + gpsz = GITS_BASER_PAGE_SIZE_16K; + break; + case SZ_4K: + default: + gpsz = GITS_BASER_PAGE_SIZE_4K; + break; + } + + gpsz >>= GITS_BASER_PAGE_SIZE_SHIFT; + + val |= FIELD_PREP(GITS_BASER_PAGE_SIZE_MASK, gpsz); + its_write_baser(its, baser, val); + + if (FIELD_GET(GITS_BASER_PAGE_SIZE_MASK, baser->val) == gpsz) + break; + + switch (psz) { + case SZ_64K: + psz = SZ_16K; + break; + case SZ_16K: + psz = SZ_4K; + break; + case SZ_4K: + default: + return -1; + } + } + + baser->psz = psz; + return 0; +} + static int its_alloc_tables(struct its_node *its) { u64 shr = GITS_BASER_InnerShareable; u64 cache = GITS_BASER_RaWaWb; - u32 psz = SZ_64K; int err, i; if (its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_22375) @@ -1975,34 +2004,38 @@ static int its_alloc_tables(struct its_node *its) struct its_baser *baser = its->tables + i; u64 val = its_read_baser(its, baser); u64 type = GITS_BASER_TYPE(val); - u32 order = get_order(psz); bool indirect = false; + u32 order; - switch (type) { - case GITS_BASER_TYPE_NONE: + if (type == GITS_BASER_TYPE_NONE) continue; + if (its_probe_baser_psz(its, baser)) { + its_free_tables(its); + return -ENXIO; + } + + order = get_order(baser->psz); + + switch (type) { case GITS_BASER_TYPE_DEVICE: - indirect = its_parse_indirect_baser(its, baser, - psz, &order, + indirect = its_parse_indirect_baser(its, baser, &order, its->device_ids); break; case GITS_BASER_TYPE_VCPU: - indirect = its_parse_indirect_baser(its, baser, - psz, &order, + indirect = its_parse_indirect_baser(its, baser, &order, ITS_MAX_VPEID_BITS); break; } - err = its_setup_baser(its, baser, cache, shr, psz, order, indirect); + err = its_setup_baser(its, baser, cache, shr, order, indirect); if (err < 0) { its_free_tables(its); return err; } /* Update settings which will be used for next BASERn */ - psz = baser->psz; cache = baser->val & GITS_BASER_CACHEABILITY_MASK; shr = baser->val & GITS_BASER_SHAREABILITY_MASK; } -- 1.8.3

1 0

2024

2023

2022

2021

2020

2019

Kernel