August 2022 - Kernel - mailweb.openeuler.org

[PATCH openEuler-5.10 01/15] drivers/perf: hisi: Add driver for HiSilicon PCIe PMU
by Zheng Zengkai 09 Aug '22

09 Aug '22

From: Qi Liu <liuqi115(a)huawei.com> mainline inclusion from mainline-v5.17-rc1 commit 8404b0fbc7fb category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I5AZ87 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------------------------------------------------- PCIe PMU Root Complex Integrated End Point(RCiEP) device is supported to sample bandwidth, latency, buffer occupation etc. Each PMU RCiEP device monitors multiple Root Ports, and each RCiEP is registered as a PMU in /sys/bus/event_source/devices, so users can select target PMU, and use filter to do further sets. Filtering options contains: event - select the event. port - select target Root Ports. Information of Root Ports are shown under sysfs. bdf - select requester_id of target EP device. trig_len - set trigger condition for starting event statistics. trig_mode - set trigger mode. 0 means starting to statistic when bigger than trigger condition, and 1 means smaller. thr_len - set threshold for statistics. thr_mode - set threshold mode. 0 means count when bigger than threshold, and 1 means smaller. Acked-by: Krzysztof Wilczyński <kw(a)linux.com> Reviewed-by: John Garry <john.garry(a)huawei.com> Signed-off-by: Qi Liu <liuqi115(a)huawei.com> Reviewed-by: Shaokun Zhang <zhangshaokun(a)hisilicon.com> Link: https://lore.kernel.org/r/20211202080633.2919-3-liuqi115@huawei.com Signed-off-by: Will Deacon <will(a)kernel.org> Signed-off-by: Wangming Shao <shaowangming(a)h-partners.com> Reviewed-by: Junhao He <hejunhao3(a)huawei.com> Reviewed-by: Yang Jihong <yangjihong1(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- MAINTAINERS | 2 + drivers/perf/hisilicon/Kconfig | 9 + drivers/perf/hisilicon/Makefile | 2 + drivers/perf/hisilicon/hisi_pcie_pmu.c | 951 +++++++++++++++++++++++++ include/linux/cpuhotplug.h | 3 + 5 files changed, 967 insertions(+) create mode 100644 drivers/perf/hisilicon/hisi_pcie_pmu.c diff --git a/MAINTAINERS b/MAINTAINERS index 466b1c599848..9908e5442110 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7976,8 +7976,10 @@ F: Documentation/devicetree/bindings/misc/hisilicon-hikey-usb.yaml HISILICON PMU DRIVER M: Shaokun Zhang <zhangshaokun(a)hisilicon.com> +M: Qi Liu <liuqi115(a)huawei.com> S: Supported W: http://www.hisilicon.com +F: Documentation/admin-guide/perf/hisi-pcie-pmu.rst F: Documentation/admin-guide/perf/hisi-pmu.rst F: drivers/perf/hisilicon diff --git a/drivers/perf/hisilicon/Kconfig b/drivers/perf/hisilicon/Kconfig index c5d1b7019fff..5546218b5598 100644 --- a/drivers/perf/hisilicon/Kconfig +++ b/drivers/perf/hisilicon/Kconfig @@ -5,3 +5,12 @@ config HISI_PMU help Support for HiSilicon SoC L3 Cache performance monitor, Hydra Home Agent performance monitor and DDR Controller performance monitor. + +config HISI_PCIE_PMU + tristate "HiSilicon PCIE PERF PMU" + depends on PCI && ARM64 + help + Provide support for HiSilicon PCIe performance monitoring unit (PMU) + RCiEP devices. + Adds the PCIe PMU into perf events system for monitoring latency, + bandwidth etc. diff --git a/drivers/perf/hisilicon/Makefile b/drivers/perf/hisilicon/Makefile index 22e384cdfd53..ad0e8110f373 100644 --- a/drivers/perf/hisilicon/Makefile +++ b/drivers/perf/hisilicon/Makefile @@ -4,3 +4,5 @@ obj-$(CONFIG_HISI_PMU) += hisi_uncore_pmu.o hisi_uncore_l3c_pmu.o \ hisi_uncore_pa_pmu.o \ hisi_uncore_l3t_pmu.o \ hisi_uncore_lpddrc_pmu.o + +obj-$(CONFIG_HISI_PCIE_PMU) += hisi_pcie_pmu.o diff --git a/drivers/perf/hisilicon/hisi_pcie_pmu.c b/drivers/perf/hisilicon/hisi_pcie_pmu.c new file mode 100644 index 000000000000..2f18838754ec --- /dev/null +++ b/drivers/perf/hisilicon/hisi_pcie_pmu.c @@ -0,0 +1,951 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * This driver adds support for PCIe PMU RCiEP device. Related + * perf events are bandwidth, latency etc. + * + * Copyright (C) 2021 HiSilicon Limited + * Author: Qi Liu <liuqi115(a)huawei.com> + */ +#include <linux/bitfield.h> +#include <linux/bitmap.h> +#include <linux/bug.h> +#include <linux/device.h> +#include <linux/err.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/kernel.h> +#include <linux/list.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/perf_event.h> + +#define DRV_NAME "hisi_pcie_pmu" +/* Define registers */ +#define HISI_PCIE_GLOBAL_CTRL 0x00 +#define HISI_PCIE_EVENT_CTRL 0x010 +#define HISI_PCIE_CNT 0x090 +#define HISI_PCIE_EXT_CNT 0x110 +#define HISI_PCIE_INT_STAT 0x150 +#define HISI_PCIE_INT_MASK 0x154 +#define HISI_PCIE_REG_BDF 0xfe0 +#define HISI_PCIE_REG_VERSION 0xfe4 +#define HISI_PCIE_REG_INFO 0xfe8 + +/* Define command in HISI_PCIE_GLOBAL_CTRL */ +#define HISI_PCIE_GLOBAL_EN 0x01 +#define HISI_PCIE_GLOBAL_NONE 0 + +/* Define command in HISI_PCIE_EVENT_CTRL */ +#define HISI_PCIE_EVENT_EN BIT_ULL(20) +#define HISI_PCIE_RESET_CNT BIT_ULL(22) +#define HISI_PCIE_INIT_SET BIT_ULL(34) +#define HISI_PCIE_THR_EN BIT_ULL(26) +#define HISI_PCIE_TARGET_EN BIT_ULL(32) +#define HISI_PCIE_TRIG_EN BIT_ULL(52) + +/* Define offsets in HISI_PCIE_EVENT_CTRL */ +#define HISI_PCIE_EVENT_M GENMASK_ULL(15, 0) +#define HISI_PCIE_THR_MODE_M GENMASK_ULL(27, 27) +#define HISI_PCIE_THR_M GENMASK_ULL(31, 28) +#define HISI_PCIE_TARGET_M GENMASK_ULL(52, 36) +#define HISI_PCIE_TRIG_MODE_M GENMASK_ULL(53, 53) +#define HISI_PCIE_TRIG_M GENMASK_ULL(59, 56) + +#define HISI_PCIE_MAX_COUNTERS 8 +#define HISI_PCIE_REG_STEP 8 +#define HISI_PCIE_THR_MAX_VAL 10 +#define HISI_PCIE_TRIG_MAX_VAL 10 +#define HISI_PCIE_MAX_PERIOD (GENMASK_ULL(63, 0)) +#define HISI_PCIE_INIT_VAL BIT_ULL(63) + +struct hisi_pcie_pmu { + struct perf_event *hw_events[HISI_PCIE_MAX_COUNTERS]; + struct hlist_node node; + struct pci_dev *pdev; + struct pmu pmu; + void __iomem *base; + int irq; + u32 identifier; + /* Minimum and maximum BDF of root ports monitored by PMU */ + u16 bdf_min; + u16 bdf_max; + int on_cpu; +}; + +struct hisi_pcie_reg_pair { + u16 lo; + u16 hi; +}; + +#define to_pcie_pmu(p) (container_of((p), struct hisi_pcie_pmu, pmu)) +#define GET_PCI_DEVFN(bdf) ((bdf) & 0xff) + +#define HISI_PCIE_PMU_FILTER_ATTR(_name, _config, _hi, _lo) \ + static u64 hisi_pcie_get_##_name(struct perf_event *event) \ + { \ + return FIELD_GET(GENMASK(_hi, _lo), event->attr._config); \ + } \ + +HISI_PCIE_PMU_FILTER_ATTR(event, config, 16, 0); +HISI_PCIE_PMU_FILTER_ATTR(thr_len, config1, 3, 0); +HISI_PCIE_PMU_FILTER_ATTR(thr_mode, config1, 4, 4); +HISI_PCIE_PMU_FILTER_ATTR(trig_len, config1, 8, 5); +HISI_PCIE_PMU_FILTER_ATTR(trig_mode, config1, 9, 9); +HISI_PCIE_PMU_FILTER_ATTR(port, config2, 15, 0); +HISI_PCIE_PMU_FILTER_ATTR(bdf, config2, 31, 16); + +static ssize_t hisi_pcie_format_sysfs_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct dev_ext_attribute *eattr; + + eattr = container_of(attr, struct dev_ext_attribute, attr); + + return sysfs_emit(buf, "%s\n", (char *)eattr->var); +} + +static ssize_t hisi_pcie_event_sysfs_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct perf_pmu_events_attr *pmu_attr = + container_of(attr, struct perf_pmu_events_attr, attr); + + return sysfs_emit(buf, "config=0x%llx\n", pmu_attr->id); +} + +#define HISI_PCIE_PMU_FORMAT_ATTR(_name, _format) \ + (&((struct dev_ext_attribute[]){ \ + { .attr = __ATTR(_name, 0444, hisi_pcie_format_sysfs_show, \ + NULL), \ + .var = (void *)_format } \ + })[0].attr.attr) + +#define HISI_PCIE_PMU_EVENT_ATTR(_name, _id) \ + (&((struct perf_pmu_events_attr[]) { \ + { .attr = __ATTR(_name, 0444, hisi_pcie_event_sysfs_show, NULL), \ + .id = _id, } \ + })[0].attr.attr) + +static ssize_t cpumask_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(dev_get_drvdata(dev)); + + return cpumap_print_to_pagebuf(true, buf, cpumask_of(pcie_pmu->on_cpu)); +} +static DEVICE_ATTR_RO(cpumask); + +static ssize_t identifier_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(dev_get_drvdata(dev)); + + return sysfs_emit(buf, "%#x\n", pcie_pmu->identifier); +} +static DEVICE_ATTR_RO(identifier); + +static ssize_t bus_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(dev_get_drvdata(dev)); + + return sysfs_emit(buf, "%#04x\n", PCI_BUS_NUM(pcie_pmu->bdf_min)); +} +static DEVICE_ATTR_RO(bus); + +static struct hisi_pcie_reg_pair +hisi_pcie_parse_reg_value(struct hisi_pcie_pmu *pcie_pmu, u32 reg_off) +{ + u32 val = readl_relaxed(pcie_pmu->base + reg_off); + struct hisi_pcie_reg_pair regs = { + .lo = val, + .hi = val >> 16, + }; + + return regs; +} + +/* + * Hardware counter and ext_counter work together for bandwidth, latency, bus + * utilization and buffer occupancy events. For example, RX memory write latency + * events(index = 0x0010), counter counts total delay cycles and ext_counter + * counts RX memory write PCIe packets number. + * + * As we don't want PMU driver to process these two data, "delay cycles" can + * be treated as an independent event(index = 0x0010), "RX memory write packets + * number" as another(index = 0x10010). BIT 16 is used to distinguish and 0-15 + * bits are "real" event index, which can be used to set HISI_PCIE_EVENT_CTRL. + */ +#define EXT_COUNTER_IS_USED(idx) ((idx) & BIT(16)) + +static u32 hisi_pcie_get_real_event(struct perf_event *event) +{ + return hisi_pcie_get_event(event) & GENMASK(15, 0); +} + +static u32 hisi_pcie_pmu_get_offset(u32 offset, u32 idx) +{ + return offset + HISI_PCIE_REG_STEP * idx; +} + +static u32 hisi_pcie_pmu_readl(struct hisi_pcie_pmu *pcie_pmu, u32 reg_offset, + u32 idx) +{ + u32 offset = hisi_pcie_pmu_get_offset(reg_offset, idx); + + return readl_relaxed(pcie_pmu->base + offset); +} + +static void hisi_pcie_pmu_writel(struct hisi_pcie_pmu *pcie_pmu, u32 reg_offset, u32 idx, u32 val) +{ + u32 offset = hisi_pcie_pmu_get_offset(reg_offset, idx); + + writel_relaxed(val, pcie_pmu->base + offset); +} + +static u64 hisi_pcie_pmu_readq(struct hisi_pcie_pmu *pcie_pmu, u32 reg_offset, u32 idx) +{ + u32 offset = hisi_pcie_pmu_get_offset(reg_offset, idx); + + return readq_relaxed(pcie_pmu->base + offset); +} + +static void hisi_pcie_pmu_writeq(struct hisi_pcie_pmu *pcie_pmu, u32 reg_offset, u32 idx, u64 val) +{ + u32 offset = hisi_pcie_pmu_get_offset(reg_offset, idx); + + writeq_relaxed(val, pcie_pmu->base + offset); +} + +static void hisi_pcie_pmu_config_filter(struct perf_event *event) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + u64 reg = HISI_PCIE_INIT_SET; + u64 port, trig_len, thr_len; + + /* Config HISI_PCIE_EVENT_CTRL according to event. */ + reg |= FIELD_PREP(HISI_PCIE_EVENT_M, hisi_pcie_get_real_event(event)); + + /* Config HISI_PCIE_EVENT_CTRL according to root port or EP device. */ + port = hisi_pcie_get_port(event); + if (port) + reg |= FIELD_PREP(HISI_PCIE_TARGET_M, port); + else + reg |= HISI_PCIE_TARGET_EN | + FIELD_PREP(HISI_PCIE_TARGET_M, hisi_pcie_get_bdf(event)); + + /* Config HISI_PCIE_EVENT_CTRL according to trigger condition. */ + trig_len = hisi_pcie_get_trig_len(event); + if (trig_len) { + reg |= FIELD_PREP(HISI_PCIE_TRIG_M, trig_len); + reg |= FIELD_PREP(HISI_PCIE_TRIG_MODE_M, hisi_pcie_get_trig_mode(event)); + reg |= HISI_PCIE_TRIG_EN; + } + + /* Config HISI_PCIE_EVENT_CTRL according to threshold condition. */ + thr_len = hisi_pcie_get_thr_len(event); + if (thr_len) { + reg |= FIELD_PREP(HISI_PCIE_THR_M, thr_len); + reg |= FIELD_PREP(HISI_PCIE_THR_MODE_M, hisi_pcie_get_thr_mode(event)); + reg |= HISI_PCIE_THR_EN; + } + + hisi_pcie_pmu_writeq(pcie_pmu, HISI_PCIE_EVENT_CTRL, hwc->idx, reg); +} + +static void hisi_pcie_pmu_clear_filter(struct perf_event *event) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + + hisi_pcie_pmu_writeq(pcie_pmu, HISI_PCIE_EVENT_CTRL, hwc->idx, HISI_PCIE_INIT_SET); +} + +static bool hisi_pcie_pmu_valid_requester_id(struct hisi_pcie_pmu *pcie_pmu, u32 bdf) +{ + struct pci_dev *root_port, *pdev; + u16 rp_bdf; + + pdev = pci_get_domain_bus_and_slot(pci_domain_nr(pcie_pmu->pdev->bus), PCI_BUS_NUM(bdf), + GET_PCI_DEVFN(bdf)); + if (!pdev) + return false; + + root_port = pcie_find_root_port(pdev); + if (!root_port) { + pci_dev_put(pdev); + return false; + } + + pci_dev_put(pdev); + rp_bdf = pci_dev_id(root_port); + return rp_bdf >= pcie_pmu->bdf_min && rp_bdf <= pcie_pmu->bdf_max; +} + +static bool hisi_pcie_pmu_valid_filter(struct perf_event *event, + struct hisi_pcie_pmu *pcie_pmu) +{ + u32 requester_id = hisi_pcie_get_bdf(event); + + if (hisi_pcie_get_thr_len(event) > HISI_PCIE_THR_MAX_VAL) + return false; + + if (hisi_pcie_get_trig_len(event) > HISI_PCIE_TRIG_MAX_VAL) + return false; + + if (requester_id) { + if (!hisi_pcie_pmu_valid_requester_id(pcie_pmu, requester_id)) + return false; + } + + return true; +} + +static bool hisi_pcie_pmu_cmp_event(struct perf_event *target, + struct perf_event *event) +{ + return hisi_pcie_get_real_event(target) == hisi_pcie_get_real_event(event); +} + +static bool hisi_pcie_pmu_validate_event_group(struct perf_event *event) +{ + struct perf_event *sibling, *leader = event->group_leader; + struct perf_event *event_group[HISI_PCIE_MAX_COUNTERS]; + int counters = 1; + int num; + + event_group[0] = leader; + if (!is_software_event(leader)) { + if (leader->pmu != event->pmu) + return false; + + if (leader != event && !hisi_pcie_pmu_cmp_event(leader, event)) + event_group[counters++] = event; + } + + for_each_sibling_event(sibling, event->group_leader) { + if (is_software_event(sibling)) + continue; + + if (sibling->pmu != event->pmu) + return false; + + for (num = 0; num < counters; num++) { + if (hisi_pcie_pmu_cmp_event(event_group[num], sibling)) + break; + } + + if (num == counters) + event_group[counters++] = sibling; + } + + return counters <= HISI_PCIE_MAX_COUNTERS; +} + +static int hisi_pcie_pmu_event_init(struct perf_event *event) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + + event->cpu = pcie_pmu->on_cpu; + + if (EXT_COUNTER_IS_USED(hisi_pcie_get_event(event))) + hwc->event_base = HISI_PCIE_EXT_CNT; + else + hwc->event_base = HISI_PCIE_CNT; + + if (event->attr.type != event->pmu->type) + return -ENOENT; + + /* Sampling is not supported. */ + if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK) + return -EOPNOTSUPP; + + if (!hisi_pcie_pmu_valid_filter(event, pcie_pmu)) + return -EINVAL; + + if (!hisi_pcie_pmu_validate_event_group(event)) + return -EINVAL; + + return 0; +} + +static u64 hisi_pcie_pmu_read_counter(struct perf_event *event) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu); + u32 idx = event->hw.idx; + + return hisi_pcie_pmu_readq(pcie_pmu, event->hw.event_base, idx); +} + +static int hisi_pcie_pmu_find_related_event(struct hisi_pcie_pmu *pcie_pmu, + struct perf_event *event) +{ + struct perf_event *sibling; + int idx; + + for (idx = 0; idx < HISI_PCIE_MAX_COUNTERS; idx++) { + sibling = pcie_pmu->hw_events[idx]; + if (!sibling) + continue; + + if (!hisi_pcie_pmu_cmp_event(sibling, event)) + continue; + + /* Related events must be used in group */ + if (sibling->group_leader == event->group_leader) + return idx; + else + return -EINVAL; + } + + return idx; +} + +static int hisi_pcie_pmu_get_event_idx(struct hisi_pcie_pmu *pcie_pmu) +{ + int idx; + + for (idx = 0; idx < HISI_PCIE_MAX_COUNTERS; idx++) { + if (!pcie_pmu->hw_events[idx]) + return idx; + } + + return -EINVAL; +} + +static void hisi_pcie_pmu_event_update(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + u64 new_cnt, prev_cnt, delta; + + do { + prev_cnt = local64_read(&hwc->prev_count); + new_cnt = hisi_pcie_pmu_read_counter(event); + } while (local64_cmpxchg(&hwc->prev_count, prev_cnt, + new_cnt) != prev_cnt); + + delta = (new_cnt - prev_cnt) & HISI_PCIE_MAX_PERIOD; + local64_add(delta, &event->count); +} + +static void hisi_pcie_pmu_read(struct perf_event *event) +{ + hisi_pcie_pmu_event_update(event); +} + +static void hisi_pcie_pmu_set_period(struct perf_event *event) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; + + local64_set(&hwc->prev_count, HISI_PCIE_INIT_VAL); + hisi_pcie_pmu_writeq(pcie_pmu, HISI_PCIE_CNT, idx, HISI_PCIE_INIT_VAL); + hisi_pcie_pmu_writeq(pcie_pmu, HISI_PCIE_EXT_CNT, idx, HISI_PCIE_INIT_VAL); +} + +static void hisi_pcie_pmu_enable_counter(struct hisi_pcie_pmu *pcie_pmu, struct hw_perf_event *hwc) +{ + u32 idx = hwc->idx; + u64 val; + + val = hisi_pcie_pmu_readq(pcie_pmu, HISI_PCIE_EVENT_CTRL, idx); + val |= HISI_PCIE_EVENT_EN; + hisi_pcie_pmu_writeq(pcie_pmu, HISI_PCIE_EVENT_CTRL, idx, val); +} + +static void hisi_pcie_pmu_disable_counter(struct hisi_pcie_pmu *pcie_pmu, struct hw_perf_event *hwc) +{ + u32 idx = hwc->idx; + u64 val; + + val = hisi_pcie_pmu_readq(pcie_pmu, HISI_PCIE_EVENT_CTRL, idx); + val &= ~HISI_PCIE_EVENT_EN; + hisi_pcie_pmu_writeq(pcie_pmu, HISI_PCIE_EVENT_CTRL, idx, val); +} + +static void hisi_pcie_pmu_enable_int(struct hisi_pcie_pmu *pcie_pmu, struct hw_perf_event *hwc) +{ + u32 idx = hwc->idx; + + hisi_pcie_pmu_writel(pcie_pmu, HISI_PCIE_INT_MASK, idx, 0); +} + +static void hisi_pcie_pmu_disable_int(struct hisi_pcie_pmu *pcie_pmu, struct hw_perf_event *hwc) +{ + u32 idx = hwc->idx; + + hisi_pcie_pmu_writel(pcie_pmu, HISI_PCIE_INT_MASK, idx, 1); +} + +static void hisi_pcie_pmu_reset_counter(struct hisi_pcie_pmu *pcie_pmu, int idx) +{ + hisi_pcie_pmu_writeq(pcie_pmu, HISI_PCIE_EVENT_CTRL, idx, HISI_PCIE_RESET_CNT); + hisi_pcie_pmu_writeq(pcie_pmu, HISI_PCIE_EVENT_CTRL, idx, HISI_PCIE_INIT_SET); +} + +static void hisi_pcie_pmu_start(struct perf_event *event, int flags) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; + u64 prev_cnt; + + if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED))) + return; + + WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE)); + hwc->state = 0; + + hisi_pcie_pmu_config_filter(event); + hisi_pcie_pmu_enable_counter(pcie_pmu, hwc); + hisi_pcie_pmu_enable_int(pcie_pmu, hwc); + hisi_pcie_pmu_set_period(event); + + if (flags & PERF_EF_RELOAD) { + prev_cnt = local64_read(&hwc->prev_count); + hisi_pcie_pmu_writeq(pcie_pmu, hwc->event_base, idx, prev_cnt); + } + + perf_event_update_userpage(event); +} + +static void hisi_pcie_pmu_stop(struct perf_event *event, int flags) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + + hisi_pcie_pmu_event_update(event); + hisi_pcie_pmu_disable_int(pcie_pmu, hwc); + hisi_pcie_pmu_disable_counter(pcie_pmu, hwc); + hisi_pcie_pmu_clear_filter(event); + WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); + hwc->state |= PERF_HES_STOPPED; + + if (hwc->state & PERF_HES_UPTODATE) + return; + + hwc->state |= PERF_HES_UPTODATE; +} + +static int hisi_pcie_pmu_add(struct perf_event *event, int flags) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + int idx; + + hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE; + + /* Check all working events to find a related event. */ + idx = hisi_pcie_pmu_find_related_event(pcie_pmu, event); + if (idx < 0) + return idx; + + /* Current event shares an enabled counter with the related event */ + if (idx < HISI_PCIE_MAX_COUNTERS) { + hwc->idx = idx; + goto start_count; + } + + idx = hisi_pcie_pmu_get_event_idx(pcie_pmu); + if (idx < 0) + return idx; + + hwc->idx = idx; + pcie_pmu->hw_events[idx] = event; + /* Reset Counter to avoid previous statistic interference. */ + hisi_pcie_pmu_reset_counter(pcie_pmu, idx); + +start_count: + if (flags & PERF_EF_START) + hisi_pcie_pmu_start(event, PERF_EF_RELOAD); + + return 0; +} + +static void hisi_pcie_pmu_del(struct perf_event *event, int flags) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + + hisi_pcie_pmu_stop(event, PERF_EF_UPDATE); + pcie_pmu->hw_events[hwc->idx] = NULL; + perf_event_update_userpage(event); +} + +static void hisi_pcie_pmu_enable(struct pmu *pmu) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(pmu); + int num; + + for (num = 0; num < HISI_PCIE_MAX_COUNTERS; num++) { + if (pcie_pmu->hw_events[num]) + break; + } + + if (num == HISI_PCIE_MAX_COUNTERS) + return; + + writel(HISI_PCIE_GLOBAL_EN, pcie_pmu->base + HISI_PCIE_GLOBAL_CTRL); +} + +static void hisi_pcie_pmu_disable(struct pmu *pmu) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(pmu); + + writel(HISI_PCIE_GLOBAL_NONE, pcie_pmu->base + HISI_PCIE_GLOBAL_CTRL); +} + +static irqreturn_t hisi_pcie_pmu_irq(int irq, void *data) +{ + struct hisi_pcie_pmu *pcie_pmu = data; + irqreturn_t ret = IRQ_NONE; + struct perf_event *event; + u32 overflown; + int idx; + + for (idx = 0; idx < HISI_PCIE_MAX_COUNTERS; idx++) { + overflown = hisi_pcie_pmu_readl(pcie_pmu, HISI_PCIE_INT_STAT, idx); + if (!overflown) + continue; + + /* Clear status of interrupt. */ + hisi_pcie_pmu_writel(pcie_pmu, HISI_PCIE_INT_STAT, idx, 1); + event = pcie_pmu->hw_events[idx]; + if (!event) + continue; + + hisi_pcie_pmu_event_update(event); + hisi_pcie_pmu_set_period(event); + ret = IRQ_HANDLED; + } + + return ret; +} + +static int hisi_pcie_pmu_irq_register(struct pci_dev *pdev, struct hisi_pcie_pmu *pcie_pmu) +{ + int irq, ret; + + ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI); + if (ret < 0) { + pci_err(pdev, "Failed to enable MSI vectors: %d\n", ret); + return ret; + } + + irq = pci_irq_vector(pdev, 0); + ret = request_irq(irq, hisi_pcie_pmu_irq, IRQF_NOBALANCING | IRQF_NO_THREAD, DRV_NAME, + pcie_pmu); + if (ret) { + pci_err(pdev, "Failed to register IRQ: %d\n", ret); + pci_free_irq_vectors(pdev); + return ret; + } + + pcie_pmu->irq = irq; + + return 0; +} + +static void hisi_pcie_pmu_irq_unregister(struct pci_dev *pdev, struct hisi_pcie_pmu *pcie_pmu) +{ + free_irq(pcie_pmu->irq, pcie_pmu); + pci_free_irq_vectors(pdev); +} + +static int hisi_pcie_pmu_online_cpu(unsigned int cpu, struct hlist_node *node) +{ + struct hisi_pcie_pmu *pcie_pmu = hlist_entry_safe(node, struct hisi_pcie_pmu, node); + + if (pcie_pmu->on_cpu == -1) { + pcie_pmu->on_cpu = cpu; + WARN_ON(irq_set_affinity(pcie_pmu->irq, cpumask_of(cpu))); + } + + return 0; +} + +static int hisi_pcie_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node) +{ + struct hisi_pcie_pmu *pcie_pmu = hlist_entry_safe(node, struct hisi_pcie_pmu, node); + unsigned int target; + + /* Nothing to do if this CPU doesn't own the PMU */ + if (pcie_pmu->on_cpu != cpu) + return 0; + + pcie_pmu->on_cpu = -1; + /* Choose a new CPU from all online cpus. */ + target = cpumask_first(cpu_online_mask); + if (target >= nr_cpu_ids) { + pci_err(pcie_pmu->pdev, "There is no CPU to set\n"); + return 0; + } + + perf_pmu_migrate_context(&pcie_pmu->pmu, cpu, target); + /* Use this CPU for event counting */ + pcie_pmu->on_cpu = target; + WARN_ON(irq_set_affinity(pcie_pmu->irq, cpumask_of(target))); + + return 0; +} + +static struct attribute *hisi_pcie_pmu_events_attr[] = { + HISI_PCIE_PMU_EVENT_ATTR(rx_mwr_latency, 0x0010), + HISI_PCIE_PMU_EVENT_ATTR(rx_mwr_cnt, 0x10010), + HISI_PCIE_PMU_EVENT_ATTR(rx_mrd_latency, 0x0210), + HISI_PCIE_PMU_EVENT_ATTR(rx_mrd_cnt, 0x10210), + HISI_PCIE_PMU_EVENT_ATTR(tx_mrd_latency, 0x0011), + HISI_PCIE_PMU_EVENT_ATTR(tx_mrd_cnt, 0x10011), + HISI_PCIE_PMU_EVENT_ATTR(rx_mrd_flux, 0x1005), + HISI_PCIE_PMU_EVENT_ATTR(rx_mrd_time, 0x11005), + HISI_PCIE_PMU_EVENT_ATTR(tx_mrd_flux, 0x2004), + HISI_PCIE_PMU_EVENT_ATTR(tx_mrd_time, 0x12004), + NULL +}; + +static struct attribute_group hisi_pcie_pmu_events_group = { + .name = "events", + .attrs = hisi_pcie_pmu_events_attr, +}; + +static struct attribute *hisi_pcie_pmu_format_attr[] = { + HISI_PCIE_PMU_FORMAT_ATTR(event, "config:0-16"), + HISI_PCIE_PMU_FORMAT_ATTR(thr_len, "config1:0-3"), + HISI_PCIE_PMU_FORMAT_ATTR(thr_mode, "config1:4"), + HISI_PCIE_PMU_FORMAT_ATTR(trig_len, "config1:5-8"), + HISI_PCIE_PMU_FORMAT_ATTR(trig_mode, "config1:9"), + HISI_PCIE_PMU_FORMAT_ATTR(port, "config2:0-15"), + HISI_PCIE_PMU_FORMAT_ATTR(bdf, "config2:16-31"), + NULL +}; + +static const struct attribute_group hisi_pcie_pmu_format_group = { + .name = "format", + .attrs = hisi_pcie_pmu_format_attr, +}; + +static struct attribute *hisi_pcie_pmu_bus_attrs[] = { + &dev_attr_bus.attr, + NULL +}; + +static const struct attribute_group hisi_pcie_pmu_bus_attr_group = { + .attrs = hisi_pcie_pmu_bus_attrs, +}; + +static struct attribute *hisi_pcie_pmu_cpumask_attrs[] = { + &dev_attr_cpumask.attr, + NULL +}; + +static const struct attribute_group hisi_pcie_pmu_cpumask_attr_group = { + .attrs = hisi_pcie_pmu_cpumask_attrs, +}; + +static struct attribute *hisi_pcie_pmu_identifier_attrs[] = { + &dev_attr_identifier.attr, + NULL +}; + +static const struct attribute_group hisi_pcie_pmu_identifier_attr_group = { + .attrs = hisi_pcie_pmu_identifier_attrs, +}; + +static const struct attribute_group *hisi_pcie_pmu_attr_groups[] = { + &hisi_pcie_pmu_events_group, + &hisi_pcie_pmu_format_group, + &hisi_pcie_pmu_bus_attr_group, + &hisi_pcie_pmu_cpumask_attr_group, + &hisi_pcie_pmu_identifier_attr_group, + NULL +}; + +static int hisi_pcie_alloc_pmu(struct pci_dev *pdev, struct hisi_pcie_pmu *pcie_pmu) +{ + struct hisi_pcie_reg_pair regs; + u16 sicl_id, core_id; + char *name; + + regs = hisi_pcie_parse_reg_value(pcie_pmu, HISI_PCIE_REG_BDF); + pcie_pmu->bdf_min = regs.lo; + pcie_pmu->bdf_max = regs.hi; + + regs = hisi_pcie_parse_reg_value(pcie_pmu, HISI_PCIE_REG_INFO); + sicl_id = regs.hi; + core_id = regs.lo; + + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_pcie%u_core%u", sicl_id, core_id); + if (!name) + return -ENOMEM; + + pcie_pmu->pdev = pdev; + pcie_pmu->on_cpu = -1; + pcie_pmu->identifier = readl(pcie_pmu->base + HISI_PCIE_REG_VERSION); + pcie_pmu->pmu = (struct pmu) { + .name = name, + .module = THIS_MODULE, + .event_init = hisi_pcie_pmu_event_init, + .pmu_enable = hisi_pcie_pmu_enable, + .pmu_disable = hisi_pcie_pmu_disable, + .add = hisi_pcie_pmu_add, + .del = hisi_pcie_pmu_del, + .start = hisi_pcie_pmu_start, + .stop = hisi_pcie_pmu_stop, + .read = hisi_pcie_pmu_read, + .task_ctx_nr = perf_invalid_context, + .attr_groups = hisi_pcie_pmu_attr_groups, + .capabilities = PERF_PMU_CAP_NO_EXCLUDE, + }; + + return 0; +} + +static int hisi_pcie_init_pmu(struct pci_dev *pdev, struct hisi_pcie_pmu *pcie_pmu) +{ + int ret; + + pcie_pmu->base = pci_ioremap_bar(pdev, 2); + if (!pcie_pmu->base) { + pci_err(pdev, "Ioremap failed for pcie_pmu resource\n"); + return -ENOMEM; + } + + ret = hisi_pcie_alloc_pmu(pdev, pcie_pmu); + if (ret) + goto err_iounmap; + + ret = hisi_pcie_pmu_irq_register(pdev, pcie_pmu); + if (ret) + goto err_iounmap; + + ret = cpuhp_state_add_instance(CPUHP_AP_PERF_ARM_HISI_PCIE_PMU_ONLINE, &pcie_pmu->node); + if (ret) { + pci_err(pdev, "Failed to register hotplug: %d\n", ret); + goto err_irq_unregister; + } + + ret = perf_pmu_register(&pcie_pmu->pmu, pcie_pmu->pmu.name, -1); + if (ret) { + pci_err(pdev, "Failed to register PCIe PMU: %d\n", ret); + goto err_hotplug_unregister; + } + + return ret; + +err_hotplug_unregister: + cpuhp_state_remove_instance_nocalls( + CPUHP_AP_PERF_ARM_HISI_PCIE_PMU_ONLINE, &pcie_pmu->node); + +err_irq_unregister: + hisi_pcie_pmu_irq_unregister(pdev, pcie_pmu); + +err_iounmap: + iounmap(pcie_pmu->base); + + return ret; +} + +static void hisi_pcie_uninit_pmu(struct pci_dev *pdev) +{ + struct hisi_pcie_pmu *pcie_pmu = pci_get_drvdata(pdev); + + perf_pmu_unregister(&pcie_pmu->pmu); + cpuhp_state_remove_instance_nocalls( + CPUHP_AP_PERF_ARM_HISI_PCIE_PMU_ONLINE, &pcie_pmu->node); + hisi_pcie_pmu_irq_unregister(pdev, pcie_pmu); + iounmap(pcie_pmu->base); +} + +static int hisi_pcie_init_dev(struct pci_dev *pdev) +{ + int ret; + + ret = pcim_enable_device(pdev); + if (ret) { + pci_err(pdev, "Failed to enable PCI device: %d\n", ret); + return ret; + } + + ret = pcim_iomap_regions(pdev, BIT(2), DRV_NAME); + if (ret < 0) { + pci_err(pdev, "Failed to request PCI mem regions: %d\n", ret); + return ret; + } + + pci_set_master(pdev); + + return 0; +} + +static int hisi_pcie_pmu_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct hisi_pcie_pmu *pcie_pmu; + int ret; + + pcie_pmu = devm_kzalloc(&pdev->dev, sizeof(*pcie_pmu), GFP_KERNEL); + if (!pcie_pmu) + return -ENOMEM; + + ret = hisi_pcie_init_dev(pdev); + if (ret) + return ret; + + ret = hisi_pcie_init_pmu(pdev, pcie_pmu); + if (ret) + return ret; + + pci_set_drvdata(pdev, pcie_pmu); + + return ret; +} + +static void hisi_pcie_pmu_remove(struct pci_dev *pdev) +{ + hisi_pcie_uninit_pmu(pdev); + pci_set_drvdata(pdev, NULL); +} + +static const struct pci_device_id hisi_pcie_pmu_ids[] = { + { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, 0xa12d) }, + { 0, } +}; +MODULE_DEVICE_TABLE(pci, hisi_pcie_pmu_ids); + +static struct pci_driver hisi_pcie_pmu_driver = { + .name = DRV_NAME, + .id_table = hisi_pcie_pmu_ids, + .probe = hisi_pcie_pmu_probe, + .remove = hisi_pcie_pmu_remove, +}; + +static int __init hisi_pcie_module_init(void) +{ + int ret; + + ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_HISI_PCIE_PMU_ONLINE, + "AP_PERF_ARM_HISI_PCIE_PMU_ONLINE", + hisi_pcie_pmu_online_cpu, + hisi_pcie_pmu_offline_cpu); + if (ret) { + pr_err("Failed to setup PCIe PMU hotplug: %d\n", ret); + return ret; + } + + ret = pci_register_driver(&hisi_pcie_pmu_driver); + if (ret) + cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_PCIE_PMU_ONLINE); + + return ret; +} +module_init(hisi_pcie_module_init); + +static void __exit hisi_pcie_module_exit(void) +{ + pci_unregister_driver(&hisi_pcie_pmu_driver); + cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_PCIE_PMU_ONLINE); +} +module_exit(hisi_pcie_module_exit); + +MODULE_DESCRIPTION("HiSilicon PCIe PMU driver"); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Qi Liu <liuqi115(a)huawei.com>"); diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index b98b9eb7d5f8..24e7be132046 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -178,6 +178,9 @@ enum cpuhp_state { CPUHP_AP_PERF_ARM_HISI_L3_ONLINE, CPUHP_AP_PERF_ARM_HISI_PA_ONLINE, CPUHP_AP_PERF_ARM_HISI_SLLC_ONLINE, + #ifndef __GENKSYMS__ + CPUHP_AP_PERF_ARM_HISI_PCIE_PMU_ONLINE, + #endif CPUHP_AP_PERF_ARM_L2X0_ONLINE, CPUHP_AP_PERF_ARM_QCOM_L2_ONLINE, CPUHP_AP_PERF_ARM_QCOM_L3_ONLINE, -- 2.20.1

1 14

[PATCH openEuler-5.10-LTS 00/10] Backport 5.10.117 LTS
by Zheng Zengkai 09 Aug '22

09 Aug '22

d1ac096f8869 mm: userfaultfd: fix missing cache flush in mcopy_atomic_pte() and _mcopy_atomic() c6cbf5431a62 mm: hugetlb: fix missing cache flush in copy_huge_page_from_user() 308ff6a6e768 mm: fix missing cache flush for all tail pages of compound page 185fa5984d7a Bluetooth: Fix the creation of hdev->name 9ff4a6b80642 arm: remove CONFIG_ARCH_HAS_HOLES_MEMORYMODEL dfb55dcf9d39 nfp: bpf: silence bitwise vs. logical OR warning f89f76f4b0e7 drm/amd/display/dc/gpio/gpio_service: Pass around correct dce{version, environment} types efd1429fa99b block: drbd: drbd_nl: Make conversion to 'enum drbd_ret_code' explicit a71658c7db0b regulator: consumer: Add missing stubs to regulator/consumer.h 7648f42d1a62 MIPS: Use address-of operator on section symbols Total patches: 10 Dmitry Osipenko (1): regulator: consumer: Add missing stubs to regulator/consumer.h Itay Iellin (1): Bluetooth: Fix the creation of hdev->name Lee Jones (2): block: drbd: drbd_nl: Make conversion to 'enum drbd_ret_code' explicit drm/amd/display/dc/gpio/gpio_service: Pass around correct dce_{version, environment} types Mike Rapoport (1): arm: remove CONFIG_ARCH_HAS_HOLES_MEMORYMODEL Muchun Song (3): mm: fix missing cache flush for all tail pages of compound page mm: hugetlb: fix missing cache flush in copy_huge_page_from_user() mm: userfaultfd: fix missing cache flush in mcopy_atomic_pte() and __mcopy_atomic() Nathan Chancellor (2): MIPS: Use address-of operator on section symbols nfp: bpf: silence bitwise vs. logical OR warning Documentation/vm/memory-model.rst | 3 +- arch/arm/Kconfig | 8 ++--- arch/arm/mach-bcm/Kconfig | 1 - arch/arm/mach-davinci/Kconfig | 1 - arch/arm/mach-exynos/Kconfig | 1 - arch/arm/mach-highbank/Kconfig | 1 - arch/arm/mach-omap2/Kconfig | 1 - arch/arm/mach-s5pv210/Kconfig | 1 - arch/arm/mach-tango/Kconfig | 1 - arch/mips/bmips/setup.c | 2 +- arch/mips/lantiq/prom.c | 2 +- arch/mips/pic32/pic32mzda/init.c | 2 +- arch/mips/ralink/of.c | 2 +- drivers/block/drbd/drbd_nl.c | 13 +++++--- .../drm/amd/display/dc/gpio/gpio_service.c | 12 +++---- .../display/include/gpio_service_interface.h | 4 +-- drivers/net/ethernet/netronome/nfp/nfp_asm.c | 4 +-- fs/proc/kcore.c | 2 -- include/linux/mmzone.h | 31 ------------------- include/linux/regulator/consumer.h | 30 ++++++++++++++++++ include/net/bluetooth/hci_core.h | 3 ++ mm/memory.c | 2 ++ mm/migrate.c | 7 +++-- mm/mmzone.c | 14 --------- mm/userfaultfd.c | 3 ++ mm/vmstat.c | 4 --- net/bluetooth/hci_core.c | 6 ++-- 27 files changed, 71 insertions(+), 90 deletions(-) -- 2.20.1

1 10

[PATCH openEuler-5.10-LTS 1/6] coresight: etm4x: Workaround CPU hung bug on HiSilicon ETM
by Zheng Zengkai 09 Aug '22

09 Aug '22

From: Junhao He <hejunhao3(a)huawei.com> driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5EZY2 ------------------------------------------------------------------ In FIFO mode, when the state of sink buffer is full, the sink device will continuously backpressures the ETM, so that the ETM cannot switch to the idle state. In this case, the WFx instruction cannot be executed because the CPU detects that the ETM is not in the idle state which that will cause CPU hung. We workaround this issue on HiSilicon ETM by setting bit 13 of TRCAUXCTLR which is used to indicate that the ETM is in the idle state. The call trace is shown below: rcu: INFO: rcu_sched detected stalls on CPUs/tasks: rcu: 10-...0: (1 ticks this GP) idle=5b6/1/0x4000000000000000 softirq=12309/12318 fqs=114196 (detected by 67, t=330041 jiffies, g=309253, q=453663) Task dump for CPU 10: task:ksoftirqd/10 state:R running task stack: 0 pid: 64 ppid: 2 flags:0x0000000a Call trace: __switch_to+0xbc/0xfc irqtime_account_irq+0x58/0xc4 __do_softirq+0x6c/0x358 run_ksoftirqd+0x68/0x90 smpboot_thread_fn+0x15c/0x1a0 kthread+0x108/0x13c ret_from_fork+0x10/0x18 watchdog: BUG: soft lockup - CPU#35 stuck for 22s! [bash:133345] ... Call trace: smp_call_function_single+0x178/0x190 etm4_disable_sysfs+0x74/0xfc [coresight_etm4x] etm4_disable+0x6c/0x70 [coresight_etm4x] coresight_disable_source+0x7c/0xa0 [coresight] coresight_disable+0x6c/0x13c [coresight] enable_source_store+0x88/0xa0 [coresight] dev_attr_store+0x20/0x34 sysfs_kf_write+0x4c/0x5c kernfs_fop_write_iter+0x130/0x1c0 new_sync_write+0xec/0x18c vfs_write+0x214/0x2ac ksys_write+0x70/0xfc __arm64_sys_write+0x24/0x30 el0_svc_common.constprop.0+0x7c/0x1bc do_el0_svc+0x2c/0x94 el0_svc+0x20/0x30 el0_sync_handler+0xb0/0xb4 el0_sync+0x160/0x180 Signed-off-by: Qi Liu <liuqi115(a)huawei.com> Signed-off-by: Junhao He <hejunhao3(a)huawei.com> Reviewed-by: Jay Fang <f.fangjian(a)huawei.com> Acked-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- .../coresight/coresight-etm4x-core.c | 37 +++++++++++++++---- drivers/hwtracing/coresight/coresight-etm4x.h | 1 + 2 files changed, 30 insertions(+), 8 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c index d4d9c8bb88ca..881da29cbd5a 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c @@ -116,8 +116,10 @@ struct etm4_enable_arg { #define HISI_HIP08_CORE_COMMIT_LVL_1 0b01 #define HISI_HIP08_CORE_COMMIT_REG sys_reg(3, 1, 15, 2, 5) +#define HISI_HIP08_AUXCTRL_CHICKEN_BIT BIT(13) + struct etm4_arch_features { - void (*arch_callback)(bool enable); + void (*arch_callback)(void *info); }; static bool etm4_hisi_match_pid(unsigned int id) @@ -125,8 +127,9 @@ static bool etm4_hisi_match_pid(unsigned int id) return (id & ETM4_AMBA_MASK) == HISI_HIP08_AMBA_ID; } -static void etm4_hisi_config_core_commit(bool enable) +static void etm4_hisi_config_core_commit(void *info) { + bool enable = *(bool *)info; u8 commit = enable ? HISI_HIP08_CORE_COMMIT_LVL_1 : HISI_HIP08_CORE_COMMIT_FULL; u64 val; @@ -143,48 +146,67 @@ static void etm4_hisi_config_core_commit(bool enable) write_sysreg_s(val, HISI_HIP08_CORE_COMMIT_REG); } +static void etm4_hisi_config_auxctrlr(void *info) +{ + struct etmv4_drvdata *drvdata = info; + + /* Switch the ETM to idle state */ + writel_relaxed(HISI_HIP08_AUXCTRL_CHICKEN_BIT, drvdata->base + TRCAUXCTLR); +} + static struct etm4_arch_features etm4_features[] = { [ETM4_IMPDEF_HISI_CORE_COMMIT] = { .arch_callback = etm4_hisi_config_core_commit, }, + [ETM4_IMPDEF_HISI_SET_AUXCTRLR] = { + .arch_callback = etm4_hisi_config_auxctrlr, + }, {}, }; static void etm4_enable_arch_specific(struct etmv4_drvdata *drvdata) { struct etm4_arch_features *ftr; + bool enable = true; int bit; for_each_set_bit(bit, drvdata->arch_features, ETM4_IMPDEF_FEATURE_MAX) { ftr = &etm4_features[bit]; - if (ftr->arch_callback) - ftr->arch_callback(true); + if (bit == ETM4_IMPDEF_HISI_CORE_COMMIT && ftr->arch_callback) + ftr->arch_callback(&enable); + + if (bit == ETM4_IMPDEF_HISI_SET_AUXCTRLR && ftr->arch_callback) + ftr->arch_callback(drvdata); } } static void etm4_disable_arch_specific(struct etmv4_drvdata *drvdata) { struct etm4_arch_features *ftr; + bool enable = false; int bit; for_each_set_bit(bit, drvdata->arch_features, ETM4_IMPDEF_FEATURE_MAX) { ftr = &etm4_features[bit]; - if (ftr->arch_callback) - ftr->arch_callback(false); + if (bit == ETM4_IMPDEF_HISI_CORE_COMMIT && ftr->arch_callback) + ftr->arch_callback(&enable); } } static void etm4_check_arch_features(struct etmv4_drvdata *drvdata, unsigned int id) { - if (etm4_hisi_match_pid(id)) + if (etm4_hisi_match_pid(id)) { set_bit(ETM4_IMPDEF_HISI_CORE_COMMIT, drvdata->arch_features); + set_bit(ETM4_IMPDEF_HISI_SET_AUXCTRLR, drvdata->arch_features); + } } #else static void etm4_enable_arch_specific(struct etmv4_drvdata *drvdata) { + writel_relaxed(0x0, drvdata->base + TRCAUXCTLR); } static void etm4_disable_arch_specific(struct etmv4_drvdata *drvdata) @@ -223,7 +245,6 @@ static int etm4_enable_hw(struct etmv4_drvdata *drvdata) writel_relaxed(config->pe_sel, drvdata->base + TRCPROCSELR); writel_relaxed(config->cfg, drvdata->base + TRCCONFIGR); /* nothing specific implemented */ - writel_relaxed(0x0, drvdata->base + TRCAUXCTLR); writel_relaxed(config->eventctrl0, drvdata->base + TRCEVENTCTL0R); writel_relaxed(config->eventctrl1, drvdata->base + TRCEVENTCTL1R); if (drvdata->stallctl) diff --git a/drivers/hwtracing/coresight/coresight-etm4x.h b/drivers/hwtracing/coresight/coresight-etm4x.h index 3dd3e0633328..ef9d7365c2da 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x.h +++ b/drivers/hwtracing/coresight/coresight-etm4x.h @@ -206,6 +206,7 @@ enum etm_impdef_type { ETM4_IMPDEF_HISI_CORE_COMMIT, + ETM4_IMPDEF_HISI_SET_AUXCTRLR, ETM4_IMPDEF_FEATURE_MAX, }; -- 2.20.1

1 5

[PATCH openEuler-1.0-LTS 1/7] x86/unwind/orc: Change REG_SP_INDIRECT
by Yongqiang Liu 09 Aug '22

09 Aug '22

From: Peter Zijlstra <peterz(a)infradead.org> mainline inclusion from mainline-v5.12-rc1 commit 87ccc826bf1c9e5ab4c2f649b404e02c63e47622 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5LCHG CVE: NA -------------------------------- Currently REG_SP_INDIRECT is unused but means (%rsp + offset), change it to mean (%rsp) + offset. The reason is that we're going to swizzle stack in the middle of a C function with non-trivial stack footprint. This means that when the unwinder finds the ToS, it needs to dereference it (%rsp) and then add the offset to the next frame, resulting in: (%rsp) + offset This is somewhat unfortunate, since REG_BP_INDIRECT is used (by DRAP) and thus needs to retain the current (%rbp + offset). Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Reviewed-by: Miroslav Benes <mbenes(a)suse.cz> Acked-by: Josh Poimboeuf <jpoimboe(a)redhat.com> Signed-off-by: Yipeng Zou <zouyipeng(a)huawei.com> Reviewed-by: Zhang Jianhua <chris.zjh(a)huawei.com> Reviewed-by: Liao Chang <liaochang1(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- arch/x86/kernel/unwind_orc.c | 5 ++++- tools/objtool/orc_dump.c | 2 +- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index bafe953f5d7f..eea8ec5eca3b 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -450,7 +450,7 @@ bool unwind_next_frame(struct unwind_state *state) break; case ORC_REG_SP_INDIRECT: - sp = state->sp + orc->sp_offset; + sp = state->sp; indirect = true; break; @@ -500,6 +500,9 @@ bool unwind_next_frame(struct unwind_state *state) if (indirect) { if (!deref_stack_reg(state, sp, &sp)) goto err; + + if (orc->sp_reg == ORC_REG_SP_INDIRECT) + sp += orc->sp_offset; } /* Find IP, SP and possibly regs: */ diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c index faa444270ee3..ba28830aace2 100644 --- a/tools/objtool/orc_dump.c +++ b/tools/objtool/orc_dump.c @@ -64,7 +64,7 @@ static void print_reg(unsigned int reg, int offset) if (reg == ORC_REG_BP_INDIRECT) printf("(bp%+d)", offset); else if (reg == ORC_REG_SP_INDIRECT) - printf("(sp%+d)", offset); + printf("(sp)%+d", offset); else if (reg == ORC_REG_UNDEFINED) printf("(und)"); else -- 2.25.1

1 6

[PATCH openEuler-1.0-LTS] netfilter: nf_queue: do not allow packet truncation below transport header offset
by Yongqiang Liu 09 Aug '22

09 Aug '22

From: Florian Westphal <fw(a)strlen.de> mainline inclusion from mainline-v5.19-rc3 commit 99a63d36cb3ed5ca3aa6fcb64cffbeaf3b0fb164 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I5J9R4 CVE: CVE-2022-36946 -------------------------------- Domingo Dirutigliano and Nicola Guerrera report kernel panic when sending nf_queue verdict with 1-byte nfta_payload attribute. The IP/IPv6 stack pulls the IP(v6) header from the packet after the input hook. If user truncates the packet below the header size, this skb_pull() will result in a malformed skb (skb->len < 0). Fixes: 7af4cc3fa158 ("[NETFILTER]: Add "nfnetlink_queue" netfilter queue handler over nfnetlink") Reported-by: Domingo Dirutigliano <pwnzer0tt1(a)proton.me> Signed-off-by: Florian Westphal <fw(a)strlen.de> Reviewed-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Ziyang Xuan <william.xuanziyang(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Reviewed-by: Wei Yongjun <weiyongjun1(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- net/netfilter/nfnetlink_queue.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index a5aff2834bd6..cd496b074a71 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -850,11 +850,16 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) } static int -nfqnl_mangle(void *data, int data_len, struct nf_queue_entry *e, int diff) +nfqnl_mangle(void *data, unsigned int data_len, struct nf_queue_entry *e, int diff) { struct sk_buff *nskb; if (diff < 0) { + unsigned int min_len = skb_transport_offset(e->skb); + + if (data_len < min_len) + return -EINVAL; + if (pskb_trim(e->skb, data_len)) return -ENOMEM; } else if (diff > 0) { -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] openvswitch: fix OOB access in reserve_sfa_size()
by Yongqiang Liu 08 Aug '22

08 Aug '22

From: Paolo Valerio <pvalerio(a)redhat.com> stable inclusion from stable-v4.19.240 commit bbbf059337f9a74285c1cf088ff85ee92d149e64 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I5KKF2 CVE: CVE-2022-2639 ------------------------------------------------- commit cefa91b2332d7009bc0be5d951d6cbbf349f90f8 upstream. Given a sufficiently large number of actions, while copying and reserving memory for a new action of a new flow, if next_offset is greater than MAX_ACTIONS_BUFSIZE, the function reserve_sfa_size() does not return -EMSGSIZE as expected, but it allocates MAX_ACTIONS_BUFSIZE bytes increasing actions_len by req_size. This can then lead to an OOB write access, especially when further actions need to be copied. Fix it by rearranging the flow action size check. KASAN splat below: ================================================================== BUG: KASAN: slab-out-of-bounds in reserve_sfa_size+0x1ba/0x380 [openvswitch] Write of size 65360 at addr ffff888147e4001c by task handler15/836 CPU: 1 PID: 836 Comm: handler15 Not tainted 5.18.0-rc1+ #27 ... Call Trace: <TASK> dump_stack_lvl+0x45/0x5a print_report.cold+0x5e/0x5db ? __lock_text_start+0x8/0x8 ? reserve_sfa_size+0x1ba/0x380 [openvswitch] kasan_report+0xb5/0x130 ? reserve_sfa_size+0x1ba/0x380 [openvswitch] kasan_check_range+0xf5/0x1d0 memcpy+0x39/0x60 reserve_sfa_size+0x1ba/0x380 [openvswitch] __add_action+0x24/0x120 [openvswitch] ovs_nla_add_action+0xe/0x20 [openvswitch] ovs_ct_copy_action+0x29d/0x1130 [openvswitch] ? __kernel_text_address+0xe/0x30 ? unwind_get_return_address+0x56/0xa0 ? create_prof_cpu_mask+0x20/0x20 ? ovs_ct_verify+0xf0/0xf0 [openvswitch] ? prep_compound_page+0x198/0x2a0 ? __kasan_check_byte+0x10/0x40 ? kasan_unpoison+0x40/0x70 ? ksize+0x44/0x60 ? reserve_sfa_size+0x75/0x380 [openvswitch] __ovs_nla_copy_actions+0xc26/0x2070 [openvswitch] ? __zone_watermark_ok+0x420/0x420 ? validate_set.constprop.0+0xc90/0xc90 [openvswitch] ? __alloc_pages+0x1a9/0x3e0 ? __alloc_pages_slowpath.constprop.0+0x1da0/0x1da0 ? unwind_next_frame+0x991/0x1e40 ? __mod_node_page_state+0x99/0x120 ? __mod_lruvec_page_state+0x2e3/0x470 ? __kasan_kmalloc_large+0x90/0xe0 ovs_nla_copy_actions+0x1b4/0x2c0 [openvswitch] ovs_flow_cmd_new+0x3cd/0xb10 [openvswitch] ... Cc: stable(a)vger.kernel.org Fixes: f28cd2af22a0 ("openvswitch: fix flow actions reallocation") Signed-off-by: Paolo Valerio <pvalerio(a)redhat.com> Acked-by: Eelco Chaudron <echaudro(a)redhat.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Lu Wei <luwei32(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Reviewed-by: Wei Yongjun <weiyongjun1(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- net/openvswitch/flow_netlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index eab5e8eaddaa..217c64fbc659 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2316,7 +2316,7 @@ static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa, new_acts_size = max(next_offset + req_size, ksize(*sfa) * 2); if (new_acts_size > MAX_ACTIONS_BUFSIZE) { - if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size) { + if ((next_offset + req_size) > MAX_ACTIONS_BUFSIZE) { OVS_NLERR(log, "Flow action size exceeds max %u", MAX_ACTIONS_BUFSIZE); return ERR_PTR(-EMSGSIZE); -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] dm thin: use refcount_t for thin_c reference counting
by Yongqiang Liu 08 Aug '22

08 Aug '22

From: John Pittman <jpittman(a)redhat.com> mainline inclusion from mainline-v4.20-rc1 commit 22d4c291f58752d14efb8a185b772a3fc3e947d2 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5KSEX CVE: NA -------------------------------- The API surrounding refcount_t should be used in place of atomic_t when variables are being used as reference counters. It can potentially prevent reference counter overflows and use-after-free conditions. In the dm thin layer, one such example is tc->refcount. Change this from the atomic_t API to the refcount_t API to prevent mentioned conditions. Signed-off-by: John Pittman <jpittman(a)redhat.com> Signed-off-by: Mike Snitzer <snitzer(a)redhat.com> Signed-off-by: Luo Meng <luomeng12(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/md/dm-thin.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 2b6dd7a275eb..e352aa3fdfb0 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -355,7 +355,7 @@ struct thin_c { * Ensures the thin is not destroyed until the worker has finished * iterating the active_thins list. */ - atomic_t refcount; + refcount_t refcount; struct completion can_destroy; }; @@ -4100,12 +4100,12 @@ static struct target_type pool_target = { *--------------------------------------------------------------*/ static void thin_get(struct thin_c *tc) { - atomic_inc(&tc->refcount); + refcount_inc(&tc->refcount); } static void thin_put(struct thin_c *tc) { - if (atomic_dec_and_test(&tc->refcount)) + if (refcount_dec_and_test(&tc->refcount)) complete(&tc->can_destroy); } @@ -4255,7 +4255,7 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv) r = -EINVAL; goto bad; } - atomic_set(&tc->refcount, 1); + refcount_set(&tc->refcount, 1); init_completion(&tc->can_destroy); list_add_tail_rcu(&tc->list, &tc->pool->active_thins); spin_unlock_irqrestore(&tc->pool->lock, flags); -- 2.25.1

1 0

Kernel SIG 申报议题：英特尔Sapphire Rapids平台PMU新特性
by Jason Zeng 08 Aug '22

08 Aug '22

议题：英特尔Sapphire Rapids平台PMU新特性简介：主要介绍一下英特尔的新一代Sapphire Rapids平台上的PMU新特性，以及Linux的支持情况。

1 0

[PATCH openEuler-1.0-LTS 01/29] ata: libata-core: fix NULL pointer deref in ata_host_alloc_pinfo()
by Yongqiang Liu 08 Aug '22

08 Aug '22

From: Sergey Shtylyov <s.shtylyov(a)omp.ru> stable inclusion from stable-4.19.249 commit a810bd5af06977a847d1f202b22d7defd5c62497 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5I4FP CVE: NA -------------------------------- [ Upstream commit bf476fe22aa1851bab4728e0c49025a6a0bea307 ] In an unlikely (and probably wrong?) case that the 'ppi' parameter of ata_host_alloc_pinfo() points to an array starting with a NULL pointer, there's going to be a kernel oops as the 'pi' local variable won't get reassigned from the initial value of NULL. Initialize 'pi' instead to '&ata_dummy_port_info' to fix the possible kernel oops for good... Found by Linux Verification Center (linuxtesting.org) with the SVACE static analysis tool. Signed-off-by: Sergey Shtylyov <s.shtylyov(a)omp.ru> Signed-off-by: Damien Le Moal <damien.lemoal(a)opensource.wdc.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/ata/libata-core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 290ff99bf1d8..0bcdc5261480 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -6240,7 +6240,7 @@ struct ata_host *ata_host_alloc_pinfo(struct device *dev, const struct ata_port_info * const * ppi, int n_ports) { - const struct ata_port_info *pi; + const struct ata_port_info *pi = &ata_dummy_port_info; struct ata_host *host; int i, j; @@ -6248,7 +6248,7 @@ struct ata_host *ata_host_alloc_pinfo(struct device *dev, if (!host) return NULL; - for (i = 0, j = 0, pi = NULL; i < host->n_ports; i++) { + for (i = 0, j = 0; i < host->n_ports; i++) { struct ata_port *ap = host->ports[i]; if (ppi[j]) -- 2.25.1

1 28

[PATCH openEuler-1.0-LTS] ipv6/addrconf: fix a null-ptr-deref bug for ip6_ptr
by Yongqiang Liu 05 Aug '22

05 Aug '22

From: Ziyang Xuan <william.xuanziyang(a)huawei.com> mainline inclusion from mainline-v5.19 commit 85f0173df35e5462d89947135a6a5599c6c3ef6f category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5JW9C CVE: NA ------------------------------- Change net device's MTU to smaller than IPV6_MIN_MTU or unregister device while matching route. That may trigger null-ptr-deref bug for ip6_ptr probability as following. ========================================================= BUG: KASAN: null-ptr-deref in find_match.part.0+0x70/0x134 Read of size 4 at addr 0000000000000308 by task ping6/263 CPU: 2 PID: 263 Comm: ping6 Not tainted 5.19.0-rc7+ #14 Call trace: dump_backtrace+0x1a8/0x230 show_stack+0x20/0x70 dump_stack_lvl+0x68/0x84 print_report+0xc4/0x120 kasan_report+0x84/0x120 __asan_load4+0x94/0xd0 find_match.part.0+0x70/0x134 __find_rr_leaf+0x408/0x470 fib6_table_lookup+0x264/0x540 ip6_pol_route+0xf4/0x260 ip6_pol_route_output+0x58/0x70 fib6_rule_lookup+0x1a8/0x330 ip6_route_output_flags_noref+0xd8/0x1a0 ip6_route_output_flags+0x58/0x160 ip6_dst_lookup_tail+0x5b4/0x85c ip6_dst_lookup_flow+0x98/0x120 rawv6_sendmsg+0x49c/0xc70 inet_sendmsg+0x68/0x94 Reproducer as following: Firstly, prepare conditions: $ip netns add ns1 $ip netns add ns2 $ip link add veth1 type veth peer name veth2 $ip link set veth1 netns ns1 $ip link set veth2 netns ns2 $ip netns exec ns1 ip -6 addr add 2001:0db8:0:f101::1/64 dev veth1 $ip netns exec ns2 ip -6 addr add 2001:0db8:0:f101::2/64 dev veth2 $ip netns exec ns1 ifconfig veth1 up $ip netns exec ns2 ifconfig veth2 up $ip netns exec ns1 ip -6 route add 2000::/64 dev veth1 metric 1 $ip netns exec ns2 ip -6 route add 2001::/64 dev veth2 metric 1 Secondly, execute the following two commands in two ssh windows respectively: $ip netns exec ns1 sh $while true; do ip -6 addr add 2001:0db8:0:f101::1/64 dev veth1; ip -6 route add 2000::/64 dev veth1 metric 1; ping6 2000::2; done $ip netns exec ns1 sh $while true; do ip link set veth1 mtu 1000; ip link set veth1 mtu 1500; sleep 5; done It is because ip6_ptr has been assigned to NULL in addrconf_ifdown() firstly, then ip6_ignore_linkdown() accesses ip6_ptr directly without NULL check. cpu0 cpu1 fib6_table_lookup __find_rr_leaf addrconf_notify [ NETDEV_CHANGEMTU ] addrconf_ifdown RCU_INIT_POINTER(dev->ip6_ptr, NULL) find_match ip6_ignore_linkdown So we can add NULL check for ip6_ptr before using in ip6_ignore_linkdown() to fix the null-ptr-deref bug. Fixes: dcd1f572954f ("net/ipv6: Remove fib6_idev") Signed-off-by: Ziyang Xuan <william.xuanziyang(a)huawei.com> Reviewed-by: David Ahern <dsahern(a)kernel.org> Link: https://lore.kernel.org/r/20220728013307.656257-1-william.xuanziyang@huawei… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: include/net/addrconf.h net/ipv6/route.c Signed-off-by: Ziyang Xuan <william.xuanziyang(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Reviewed-by: Wei Yongjun <weiyongjun1(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- net/ipv6/route.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 8efb03cc6f24..31c285d0f8c3 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -655,6 +655,9 @@ static inline bool fib6_ignore_linkdown(const struct fib6_info *f6i) if (dev) { const struct inet6_dev *idev = __in6_dev_get(dev); + if (unlikely(!idev)) + return true; + rc = !!idev->cnf.ignore_routes_with_linkdown; } -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] io_uring: add missing item types for various requests
by Yongqiang Liu 05 Aug '22

05 Aug '22

From: Jens Axboe <axboe(a)kernel.dk> stable inclusion from stable-v5.10.125 commit df3f3bb5059d20ef094d6b2f0256c4bf4127a859 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I5IM3T CVE: CVE-2022-2327 -------------------------------- Any read/write should grab current->nsproxy, denoted by IO_WQ_WORK_FILES as it refers to current->files as well, and connect and recv/recvmsg, send/sendmsg should grab current->fs which is denoted by IO_WQ_WORK_FS. No upstream commit exists for this issue. Reported-by: Bing-Jhong Billy Jheng <billy(a)starlabs.sg> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: 1. read/write already grab current->nsproxy, thus don't modified read/write related ops. 2. 'work_flags' doesn't exist, io_op_def is using field 'needs_fs' to decide if 'current->fs' should be grabbed. Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- fs/io_uring.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/io_uring.c b/fs/io_uring.c index 8a96b7df4112..d4e430b51098 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -816,6 +816,7 @@ static const struct io_op_def io_op_defs[] = { .async_ctx = 1, .needs_mm = 1, .needs_file = 1, + .needs_fs = 1, .unbound_nonreg_file = 1, .pollout = 1, }, @@ -864,12 +865,14 @@ static const struct io_op_def io_op_defs[] = { [IORING_OP_SEND] = { .needs_mm = 1, .needs_file = 1, + .needs_fs = 1, .unbound_nonreg_file = 1, .pollout = 1, }, [IORING_OP_RECV] = { .needs_mm = 1, .needs_file = 1, + .needs_fs = 1, .unbound_nonreg_file = 1, .pollin = 1, .buffer_select = 1, -- 2.25.1

1 0

[PATCH openEuler-22.09 00/20] Add programmable schedule feature for
by Zheng Zengkai 05 Aug '22

05 Aug '22

Add programmable schedule feature for openEuler-22.09. Chen Hui (12): sched: programmable: Add a tag for the task group sched: programmable: Add user interface of task group tag sched: programmable: Add a tag for the task sched: programmable: Add user interface of task tag sched: programmable: add bpf_sched_task_tag_of helper function sched: programmable: Add convenient helper functions to convert sched entity bpf: BPF samples support SCHED program type samples: bpf: Add bpf sched preempt sample program bpf:programmable: Add four helper functions to get cpu stat bpf:programmable: Add cpumask ops collection sched: programmable: Add lib for sched programmable sched: programmable: Add hook for select_task_rq_fair Guan Jing (2): sched: programmable: Add hook for entity_before samples: bpf: Add bpf sched pick task sample Hui Tang (3): bpf:programmable: Add helper func to check cpu share cache bpf:programmable: Add helper func to set cpus_ptr in task samples:bpf: Add samples for cfs select core Ren Zhijie (3): sched: programmable: add bpf_sched_tg_tag_of helper function sched: programmable: Add helpers to set tag of task or task_group sched: programmable: Add helper function for cpu topology. fs/proc/base.c | 65 ++++ include/linux/bpf_topology.h | 46 +++ include/linux/sched.h | 85 ++++++ include/linux/sched_hook_defs.h | 7 +- include/uapi/linux/bpf.h | 112 +++++++ init/init_task.c | 3 + kernel/bpf/helpers.c | 12 + kernel/bpf/verifier.c | 4 +- kernel/sched/Makefile | 3 +- kernel/sched/bpf_sched.c | 409 +++++++++++++++++++++++++ kernel/sched/bpf_topology.c | 99 ++++++ kernel/sched/core.c | 103 +++++++ kernel/sched/fair.c | 58 ++++ kernel/sched/sched.h | 8 + samples/bpf/Makefile | 9 + samples/bpf/bpf_load.c | 8 +- samples/bpf/sched_pick_task_kern.c | 62 ++++ samples/bpf/sched_pick_task_user.c | 92 ++++++ samples/bpf/sched_preempt_kern.c | 151 ++++++++++ samples/bpf/sched_preempt_user.c | 139 +++++++++ samples/bpf/sched_select_core_kern.c | 239 +++++++++++++++ samples/bpf/sched_select_core_user.c | 114 +++++++ scripts/bpf_helpers_doc.py | 20 ++ tools/include/uapi/linux/bpf.h | 112 +++++++ tools/lib/bpf/libbpf_sched.h | 435 +++++++++++++++++++++++++++ 25 files changed, 2389 insertions(+), 6 deletions(-) create mode 100644 include/linux/bpf_topology.h create mode 100644 kernel/sched/bpf_topology.c create mode 100644 samples/bpf/sched_pick_task_kern.c create mode 100644 samples/bpf/sched_pick_task_user.c create mode 100644 samples/bpf/sched_preempt_kern.c create mode 100644 samples/bpf/sched_preempt_user.c create mode 100644 samples/bpf/sched_select_core_kern.c create mode 100644 samples/bpf/sched_select_core_user.c create mode 100644 tools/lib/bpf/libbpf_sched.h -- 2.20.1

1 20

[PATCH openEuler-1.0-LTS 1/3] net: sched: sch_teql: fix null-pointer dereference
by Yongqiang Liu 05 Aug '22

05 Aug '22

From: Pavel Tikhomirov <ptikhomirov(a)virtuozzo.com> stable inclusion from stable-v4.19.187 commit a9a7488979a7d0abfd30bc32f370b8e0c124db33 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5JPWC CVE: NA -------------------------------- commit 1ffbc7ea91606e4abd10eb60de5367f1c86daf5e upstream. Reproduce: modprobe sch_teql tc qdisc add dev teql0 root teql0 This leads to (for instance in Centos 7 VM) OOPS: [ 532.366633] BUG: unable to handle kernel NULL pointer dereference at 00000000000000a8 [ 532.366733] IP: [<ffffffffc06124a8>] teql_destroy+0x18/0x100 [sch_teql] [ 532.366825] PGD 80000001376d5067 PUD 137e37067 PMD 0 [ 532.366906] Oops: 0000 [#1] SMP [ 532.366987] Modules linked in: sch_teql ... [ 532.367945] CPU: 1 PID: 3026 Comm: tc Kdump: loaded Tainted: G ------------ T 3.10.0-1062.7.1.el7.x86_64 #1 [ 532.368041] Hardware name: Virtuozzo KVM, BIOS 1.11.0-2.vz7.2 04/01/2014 [ 532.368125] task: ffff8b7d37d31070 ti: ffff8b7c9fdbc000 task.ti: ffff8b7c9fdbc000 [ 532.368224] RIP: 0010:[<ffffffffc06124a8>] [<ffffffffc06124a8>] teql_destroy+0x18/0x100 [sch_teql] [ 532.368320] RSP: 0018:ffff8b7c9fdbf8e0 EFLAGS: 00010286 [ 532.368394] RAX: ffffffffc0612490 RBX: ffff8b7cb1565e00 RCX: ffff8b7d35ba2000 [ 532.368476] RDX: ffff8b7d35ba2000 RSI: 0000000000000000 RDI: ffff8b7cb1565e00 [ 532.368557] RBP: ffff8b7c9fdbf8f8 R08: ffff8b7d3fd1f140 R09: ffff8b7d3b001600 [ 532.368638] R10: ffff8b7d3b001600 R11: ffffffff84c7d65b R12: 00000000ffffffd8 [ 532.368719] R13: 0000000000008000 R14: ffff8b7d35ba2000 R15: ffff8b7c9fdbf9a8 [ 532.368800] FS: 00007f6a4e872740(0000) GS:ffff8b7d3fd00000(0000) knlGS:0000000000000000 [ 532.368885] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 532.368961] CR2: 00000000000000a8 CR3: 00000001396ee000 CR4: 00000000000206e0 [ 532.369046] Call Trace: [ 532.369159] [<ffffffff84c8192e>] qdisc_create+0x36e/0x450 [ 532.369268] [<ffffffff846a9b49>] ? ns_capable+0x29/0x50 [ 532.369366] [<ffffffff849afde2>] ? nla_parse+0x32/0x120 [ 532.369442] [<ffffffff84c81b4c>] tc_modify_qdisc+0x13c/0x610 [ 532.371508] [<ffffffff84c693e7>] rtnetlink_rcv_msg+0xa7/0x260 [ 532.372668] [<ffffffff84907b65>] ? sock_has_perm+0x75/0x90 [ 532.373790] [<ffffffff84c69340>] ? rtnl_newlink+0x890/0x890 [ 532.374914] [<ffffffff84c8da7b>] netlink_rcv_skb+0xab/0xc0 [ 532.376055] [<ffffffff84c63708>] rtnetlink_rcv+0x28/0x30 [ 532.377204] [<ffffffff84c8d400>] netlink_unicast+0x170/0x210 [ 532.378333] [<ffffffff84c8d7a8>] netlink_sendmsg+0x308/0x420 [ 532.379465] [<ffffffff84c2f3a6>] sock_sendmsg+0xb6/0xf0 [ 532.380710] [<ffffffffc034a56e>] ? __xfs_filemap_fault+0x8e/0x1d0 [xfs] [ 532.381868] [<ffffffffc034a75c>] ? xfs_filemap_fault+0x2c/0x30 [xfs] [ 532.383037] [<ffffffff847ec23a>] ? __do_fault.isra.61+0x8a/0x100 [ 532.384144] [<ffffffff84c30269>] ___sys_sendmsg+0x3e9/0x400 [ 532.385268] [<ffffffff847f3fad>] ? handle_mm_fault+0x39d/0x9b0 [ 532.386387] [<ffffffff84d88678>] ? __do_page_fault+0x238/0x500 [ 532.387472] [<ffffffff84c31921>] __sys_sendmsg+0x51/0x90 [ 532.388560] [<ffffffff84c31972>] SyS_sendmsg+0x12/0x20 [ 532.389636] [<ffffffff84d8dede>] system_call_fastpath+0x25/0x2a [ 532.390704] [<ffffffff84d8de21>] ? system_call_after_swapgs+0xae/0x146 [ 532.391753] Code: 00 00 00 00 00 00 5b 5d c3 66 2e 0f 1f 84 00 00 00 00 00 66 66 66 66 90 55 48 89 e5 41 55 41 54 53 48 8b b7 48 01 00 00 48 89 fb <48> 8b 8e a8 00 00 00 48 85 c9 74 43 48 89 ca eb 0f 0f 1f 80 00 [ 532.394036] RIP [<ffffffffc06124a8>] teql_destroy+0x18/0x100 [sch_teql] [ 532.395127] RSP <ffff8b7c9fdbf8e0> [ 532.396179] CR2: 00000000000000a8 Null pointer dereference happens on master->slaves dereference in teql_destroy() as master is null-pointer. When qdisc_create() calls teql_qdisc_init() it imediately fails after check "if (m->dev == dev)" because both devices are teql0, and it does not set qdisc_priv(sch)->m leaving it zero on error path, then qdisc_create() imediately calls teql_destroy() which does not expect zero master pointer and we get OOPS. Fixes: 87b60cfacf9f ("net_sched: fix error recovery at qdisc creation") Signed-off-by: Pavel Tikhomirov <ptikhomirov(a)virtuozzo.com> Reviewed-by: Eric Dumazet <edumazet(a)google.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Lu Wei <luwei32(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Reviewed-by: Wei Yongjun <weiyongjun1(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- net/sched/sch_teql.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 7ed53124069c..163364124691 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -138,6 +138,9 @@ teql_destroy(struct Qdisc *sch) struct teql_sched_data *dat = qdisc_priv(sch); struct teql_master *master = dat->m; + if (!master) + return; + prev = master->slaves; if (prev) { do { -- 2.25.1

1 2

[PATCH openEuler-22.09 0/4] add exec hugetlb support
by Zheng Zengkai 05 Aug '22

05 Aug '22

Some applications has large code and data segment, and this causes high TLB miss when page size is 4K. Mapping these apps into hugetlbfs will boost their performance. A userspace tool libhugetlbfs can do this but it seems to stopped development since 2020, and it does not support debugging. Tmpfs supports transparent hugepage, but it will be split into small pages during copy-on-write. Userspace hotpatch will do mprotect on code segment and trigger pmd split, and some users think performance degradation after hotpatch is unacceptable. This patch set implements hugetlb support in exec, and solved the debugging issue. --- v5: mark new Kconfigs default n and add sysctl knob v4: rebase to 5.10.0-107.0.0 v3: add MAP_FILE_HUGETLB v2: fix kabi Liu Zixian (4): hugetlb: support private file map elf: support hugetlb map enable elf huge map by default fs: add sysctl knob for exec_hugetlb arch/arm64/configs/openeuler_defconfig | 2 + arch/x86/configs/openeuler_defconfig | 2 + fs/Kconfig | 24 ++++++ fs/binfmt_elf.c | 115 +++++++++++++++++++++++++ fs/exec.c | 4 + fs/proc/task_mmu.c | 5 ++ include/linux/elf.h | 4 + include/linux/mm_types.h | 4 + include/uapi/asm-generic/mman-common.h | 1 + include/uapi/linux/elf.h | 1 + kernel/events/core.c | 7 ++ kernel/fork.c | 5 ++ kernel/sysctl.c | 11 +++ mm/hugetlb.c | 25 ++++++ mm/mmap.c | 20 +++++ mm/util.c | 40 +++++++++ 16 files changed, 270 insertions(+) -- 2.20.1

1 4

[PATCH openEuler-5.10 01/20] md: add io accounting for raid0 and raid5
by Zheng Zengkai 04 Aug '22

04 Aug '22

From: Guoqing Jiang <jgq516(a)gmail.com> mainline inclusion from mainline-v5.14-rc1 commit 10764815ff4728d2c57da677cd5d3dd6f446cf5f category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I587H6 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… ------------------------------- We introduce a new bioset (io_acct_set) for raid0 and raid5 since they don't own clone infrastructure to accounting io. And the bioset is added to mddev instead of to raid0 and raid5 layer, because with this way, we can put common functions to md.h and reuse them in raid0 and raid5. Also struct md_io_acct is added accordingly which includes io start_time, the origin bio and cloned bio. Then we can call bio_{start,end}_io_acct to get related io status. Signed-off-by: Guoqing Jiang <jiangguoqing(a)kylinos.cn> Signed-off-by: Song Liu <song(a)kernel.org> Conflict: drivers/md/md.c drivers/md/md.h Signed-off-by: Zhang Wensheng <zhangwensheng5(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- drivers/md/md.c | 52 ++++++++++++++++++++++++++++++++++++++++++---- drivers/md/md.h | 8 +++++++ drivers/md/raid0.c | 3 +++ drivers/md/raid5.c | 9 ++++++++ 4 files changed, 68 insertions(+), 4 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index a299fda5b0e9..10d9a8bed604 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2361,7 +2361,8 @@ int md_integrity_register(struct mddev *mddev) bdev_get_integrity(reference->bdev)); pr_debug("md: data integrity enabled on %s\n", mdname(mddev)); - if (bioset_integrity_create(&mddev->bio_set, BIO_POOL_SIZE)) { + if (bioset_integrity_create(&mddev->bio_set, BIO_POOL_SIZE) || + bioset_integrity_create(&mddev->io_acct_set, BIO_POOL_SIZE)) { pr_err("md: failed to create integrity pool for %s\n", mdname(mddev)); return -EINVAL; @@ -5597,6 +5598,7 @@ static void md_free(struct kobject *ko) bioset_exit(&mddev->bio_set); bioset_exit(&mddev->sync_set); + bioset_exit(&mddev->io_acct_set); kfree(mddev); } @@ -5885,7 +5887,13 @@ int md_run(struct mddev *mddev) if (!bioset_initialized(&mddev->sync_set)) { err = bioset_init(&mddev->sync_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); if (err) - return err; + goto exit_bio_set; + } + if (!bioset_initialized(&mddev->io_acct_set)) { + err = bioset_init(&mddev->io_acct_set, BIO_POOL_SIZE, + offsetof(struct md_io_acct, bio_clone), 0); + if (err) + goto exit_sync_set; } spin_lock(&pers_lock); @@ -6013,6 +6021,7 @@ int md_run(struct mddev *mddev) blk_queue_flag_set(QUEUE_FLAG_NONROT, mddev->queue); else blk_queue_flag_clear(QUEUE_FLAG_NONROT, mddev->queue); + blk_queue_flag_set(QUEUE_FLAG_IO_STAT, mddev->queue); } if (pers->sync_request) { if (mddev->kobj.sd && @@ -6062,8 +6071,11 @@ int md_run(struct mddev *mddev) module_put(pers->owner); md_bitmap_destroy(mddev); abort: - bioset_exit(&mddev->bio_set); + bioset_exit(&mddev->io_acct_set); +exit_sync_set: bioset_exit(&mddev->sync_set); +exit_bio_set: + bioset_exit(&mddev->bio_set); return err; } EXPORT_SYMBOL_GPL(md_run); @@ -6288,6 +6300,7 @@ void md_stop(struct mddev *mddev) __md_stop(mddev); bioset_exit(&mddev->bio_set); bioset_exit(&mddev->sync_set); + bioset_exit(&mddev->io_acct_set); } EXPORT_SYMBOL_GPL(md_stop); @@ -8571,9 +8584,40 @@ void md_write_end(struct mddev *mddev) roundup(jiffies, mddev->safemode_delay) + mddev->safemode_delay); } - EXPORT_SYMBOL(md_write_end); +static void md_end_io_acct(struct bio *bio) +{ + struct md_io_acct *md_io_acct = bio->bi_private; + struct bio *orig_bio = md_io_acct->orig_bio; + + orig_bio->bi_status = bio->bi_status; + + bio_end_io_acct(orig_bio, md_io_acct->start_time); + bio_put(bio); + bio_endio(orig_bio); +} + +/* used by personalities (raid0 and raid5) to account io stats */ +void md_account_bio(struct mddev *mddev, struct bio **bio) +{ + struct md_io_acct *md_io_acct; + struct bio *clone; + + if (!blk_queue_io_stat((*bio)->bi_disk->queue)) + return; + + clone = bio_clone_fast(*bio, GFP_NOIO, &mddev->io_acct_set); + md_io_acct = container_of(clone, struct md_io_acct, bio_clone); + md_io_acct->orig_bio = *bio; + md_io_acct->start_time = bio_start_io_acct(*bio); + + clone->bi_end_io = md_end_io_acct; + clone->bi_private = md_io_acct; + *bio = clone; +} +EXPORT_SYMBOL_GPL(md_account_bio); + /* md_allow_write(mddev) * Calling this ensures that the array is marked 'active' so that writes * may proceed without blocking. It is important to call this before diff --git a/drivers/md/md.h b/drivers/md/md.h index 85177d068322..20c16cfdd6bb 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -491,6 +491,7 @@ struct mddev { struct bio_set sync_set; /* for sync operations like * metadata and bitmap writes */ + struct bio_set io_acct_set; /* for raid0 and raid5 io accounting */ /* Generic flush handling. * The last to finish preflush schedules a worker to submit @@ -687,6 +688,12 @@ struct md_thread { void *private; }; +struct md_io_acct { + struct bio *orig_bio; + unsigned long start_time; + struct bio bio_clone; +}; + #define THREAD_WAKEUP 0 static inline void safe_put_page(struct page *p) @@ -716,6 +723,7 @@ extern void md_write_end(struct mddev *mddev); extern void md_done_sync(struct mddev *mddev, int blocks, int ok); extern void md_error(struct mddev *mddev, struct md_rdev *rdev); extern void md_finish_reshape(struct mddev *mddev); +void md_account_bio(struct mddev *mddev, struct bio **bio); extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio); extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev, diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 35843df15b5e..0312b192106a 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -556,6 +556,9 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio) bio = split; } + if (bio->bi_pool != &mddev->bio_set) + md_account_bio(mddev, &bio); + orig_sector = sector; zone = find_zone(mddev->private, &sector); switch (conf->layout) { diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index c82953a3299e..35dacc6e754f 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -5487,6 +5487,7 @@ static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio) sector_t sector = raid_bio->bi_iter.bi_sector; unsigned chunk_sects = mddev->chunk_sectors; unsigned sectors = chunk_sects - (sector & (chunk_sects-1)); + struct r5conf *conf = mddev->private; if (sectors < bio_sectors(raid_bio)) { struct r5conf *conf = mddev->private; @@ -5496,6 +5497,9 @@ static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio) raid_bio = split; } + if (raid_bio->bi_pool != &conf->bio_split) + md_account_bio(mddev, &raid_bio); + if (!raid5_read_one_chunk(mddev, raid_bio)) return raid_bio; @@ -5775,6 +5779,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) DEFINE_WAIT(w); bool do_prepare; bool do_flush = false; + bool do_clone = false; if (unlikely(bi->bi_opf & REQ_PREFLUSH)) { int ret = log_handle_flush_request(conf, bi); @@ -5803,6 +5808,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) if (rw == READ && mddev->degraded == 0 && mddev->reshape_position == MaxSector) { bi = chunk_aligned_read(mddev, bi); + do_clone = true; if (!bi) return true; } @@ -5817,6 +5823,9 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) last_sector = bio_end_sector(bi); bi->bi_next = NULL; + if (!do_clone) + md_account_bio(mddev, &bi); + prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE); for (; logical_sector < last_sector; logical_sector += RAID5_STRIPE_SECTORS(conf)) { int previous; -- 2.20.1

1 19

[PATCH openEuler-5.10 00/64] Backport 5.10.115 LTS
by Zheng Zengkai 04 Aug '22

04 Aug '22

Backport 5.10.115 LTS patches from upstream. git cherry-pick v5.10.114..v5.10.115~1 -s Complicts: Already merged(4): 8a9e7c64f4a0 nfc: replace improper check device_is_registered() in netlink related functions 1961c5a688ed nfc: nfcmrvl: main: reorder destructive operations in nfcmrvl_nci_unregister_dev to avoid bugs 879b075a9a36 NFC: netlink: fix sleep in atomic bug when firmware download timeout a439819f4797 block-map: add __GFP_ZERO flag for alloc_page in function bio_copy_kern Rejected(2): hinic driver drops related file in the patch: 475237e807a2 hinic: fix bug of wq out of bound access build failed due to reject of patch "845f44ce3d9f1 net/sched: flower: fix parsing of ethertype following VLAN header": d8338a7a0957 net/mlx5e: Don't match double-vlan packets if cvlan is not set Total patches: 70 - 4 - 2 = 64 Andreas Larsson (2): can: grcan: grcan_probe(): fix broken system id check for errata workaround needs can: grcan: only use the NAPI poll budget for RX Andrei Lalaev (1): gpiolib: of: fix bounds check for 'gpio-reserved-ranges' Armin Wolf (1): hwmon: (adt7470) Fix warning on module removal Aya Levin (1): net/mlx5: Fix slab-out-of-bounds while reading resource dump menu Brian Norris (1): mmc: core: Set HS clock speed before sending HS CMD13 Cheng Xu (1): RDMA/siw: Fix a condition race issue in MPA request processing Chengfeng Ye (1): firewire: fix potential uaf in outbound_phy_packet_callback() Codrin Ciubotariu (1): ASoC: dmaengine: Restore NULL prepare_slave_config() callback Daniel Hellstrom (1): can: grcan: use ofdev->dev when allocating DMA memory David Stevens (1): iommu/vt-d: Calculate mask for non-aligned flushes Duoming Zhou (1): can: grcan: grcan_close(): fix deadlock Eric Dumazet (1): net: igmp: respect RCU rules in ip_mc_source() and ip_mc_msfilter() Filipe Manana (1): btrfs: always log symlinks in full mode Frederic Weisbecker (2): rcu: Fix callbacks processing time limit retaining cond_resched() rcu: Apply callbacks processing time limit only on softirq Harry Wentland (1): drm/amd/display: Avoid reading audio pattern past AUDIO_CHANNELS_COUNT Helge Deller (1): parisc: Merge model and model name into one line in /proc/cpuinfo Ido Schimmel (1): selftests: mirror_gre_bridge_1q: Avoid changing PVID while interface is operational Jakob Koschel (1): firewire: remove check of list iterator against head past the loop body Jan Höppner (2): s390/dasd: Fix read for ESE with blksize < 4k s390/dasd: Fix read inconsistency for ESE DASD devices Jann Horn (1): selftests/seccomp: Don't call read() on TTY from background pgrp Kyle Huey (1): KVM: x86/svm: Account for family 17h event renumberings in amd_pmc_perf_hw_id Maciej W. Rozycki (1): MIPS: Fix CP0 counter erratum detection for R4k CPUs Mark Brown (5): ASoC: da7219: Fix change notifications for tone generator frequency ASoC: wm8958: Fix change notifications for DSP controls ASoC: meson: Fix event generation for AUI ACODEC mux ASoC: meson: Fix event generation for G12A tohdmi mux ASoC: meson: Fix event generation for AUI CODEC mux Mark Zhang (1): net/mlx5e: Fix the calling of update_buffer_lossy() API Michael Chan (1): bnxt_en: Fix unnecessary dropping of RX packets Mike Snitzer (1): dm: interlock pending dm_io and dm_wait_for_bios_completion Moshe Shemesh (1): net/mlx5: Avoid double clear or set of sync reset requested Moshe Tal (1): net/mlx5e: Fix trust state reset in reload Niels Dossche (1): firewire: core: extend card->lock in fw_core_handle_bus_reset Oliver Hartkopp (1): can: isotp: remove re-binding of bound socket Pali Rohár (2): PCI: aardvark: Clear all MSIs at setup PCI: aardvark: Fix reading MSI interrupt number Paolo Bonzini (2): KVM: x86: Do not change ICR on write to APIC_SELF_IPI KVM: x86/mmu: avoid NULL-pointer dereference on page freeing bugs Paul Blakey (1): net/mlx5e: CT: Fix queued up restore put() executing after relevant ft release Puyou Lu (1): gpio: pca953x: fix irq_stat not updated when irq is disabled (irq_mask not set) Ricky WU (1): mmc: rtsx: add 74 Clocks in power on flow Sandipan Das (1): kvm: x86/cpuid: Only provide CPUID leaf 0xA if host has architectural PMU Sergey Shtylyov (1): smsc911x: allow using IRQ0 Shaik Sajida Bhanu (1): mmc: sdhci-msm: Reset GCC_SDCC_BCR register for SDHC Shravya Kumbham (1): net: emaclite: Add error handling for of_address_to_resource() Somnath Kotur (1): bnxt_en: Fix possible bnxt_open() failure caused by wrong RFS flag Stefan Haberland (2): s390/dasd: fix data corruption for ESE devices s390/dasd: prevent double format of tracks for ESE devices Takashi Sakamoto (1): ALSA: fireworks: fix wrong return count shorter than expected by 4 bytes Tan Tee Min (1): net: stmmac: disable Split Header (SPH) for Intel platforms Thomas Pfaff (1): genirq: Synchronize interrupt thread startup Trond Myklebust (2): Revert "SUNRPC: attempt AF_LOCAL connect on setup" NFSv4: Don't invalidate inode attributes on delegation return Vladimir Oltean (1): selftests: ocelot: tc_flower_chains: specify conform-exceed action for policer Wanpeng Li (2): x86/kvm: Preserve BSP MSR_KVM_POLL_CONTROL across suspend/resume KVM: LAPIC: Enable timer posted-interrupt only when mwait/hlt is advertised Yang Yingliang (4): net: ethernet: mediatek: add missing of_node_put() in mtk_sgmii_init() net: dsa: mt7530: add missing of_node_put() in mt7530_setup() net: stmmac: dwmac-sun8i: add missing of_node_put() in sun8i_dwmac_register_mdio_mux() net: cpsw: add missing of_node_put() in cpsw_probe_dt() Zihao Wang (1): ALSA: hda/realtek: Add quirk for Yoga Duet 7 13ITL6 speakers arch/mips/include/asm/timex.h | 8 ++-- arch/mips/kernel/time.c | 11 ++--- arch/parisc/kernel/processor.c | 3 +- arch/x86/kernel/kvm.c | 13 ++++++ arch/x86/kvm/cpuid.c | 5 ++ arch/x86/kvm/lapic.c | 10 ++-- arch/x86/kvm/mmu/mmu.c | 2 + arch/x86/kvm/svm/pmu.c | 28 +++++++++-- drivers/firewire/core-card.c | 3 ++ drivers/firewire/core-cdev.c | 4 +- drivers/firewire/core-topology.c | 9 ++-- drivers/firewire/core-transaction.c | 30 ++++++------ drivers/firewire/sbp2.c | 13 +++--- drivers/gpio/gpio-pca953x.c | 4 +- drivers/gpio/gpiolib-of.c | 2 +- .../gpu/drm/amd/display/dc/core/dc_link_dp.c | 2 +- drivers/hwmon/adt7470.c | 4 +- drivers/infiniband/sw/siw/siw_cm.c | 7 +-- drivers/iommu/intel/iommu.c | 27 +++++++++-- drivers/md/dm.c | 8 +++- drivers/mmc/core/mmc.c | 23 ++++++++-- drivers/mmc/host/rtsx_pci_sdmmc.c | 31 +++++++++---- drivers/mmc/host/sdhci-msm.c | 42 +++++++++++++++++ drivers/net/can/grcan.c | 46 ++++++++++--------- drivers/net/dsa/mt7530.c | 1 + drivers/net/ethernet/broadcom/bnxt/bnxt.c | 13 ++++-- drivers/net/ethernet/mediatek/mtk_sgmii.c | 1 + .../mellanox/mlx5/core/diag/rsc_dump.c | 31 ++++++++++--- .../mellanox/mlx5/core/en/port_buffer.c | 4 +- .../ethernet/mellanox/mlx5/core/en/tc_ct.c | 4 ++ .../ethernet/mellanox/mlx5/core/en_dcbnl.c | 10 ++++ .../ethernet/mellanox/mlx5/core/fw_reset.c | 28 +++++++---- drivers/net/ethernet/smsc/smsc911x.c | 2 +- .../net/ethernet/stmicro/stmmac/dwmac-intel.c | 1 + .../net/ethernet/stmicro/stmmac/dwmac-sun8i.c | 1 + .../net/ethernet/stmicro/stmmac/stmmac_main.c | 2 +- drivers/net/ethernet/ti/cpsw_new.c | 5 +- drivers/net/ethernet/xilinx/xilinx_emaclite.c | 15 ++++-- drivers/pci/controller/pci-aardvark.c | 16 +++---- drivers/s390/block/dasd.c | 18 ++++++-- drivers/s390/block/dasd_eckd.c | 28 ++++++++--- drivers/s390/block/dasd_int.h | 14 ++++++ fs/btrfs/tree-log.c | 14 +++++- fs/nfs/nfs4proc.c | 12 ++++- include/linux/stmmac.h | 1 + kernel/irq/internals.h | 2 + kernel/irq/irqdesc.c | 2 + kernel/irq/manage.c | 39 ++++++++++++---- kernel/rcu/tree.c | 32 +++++++------ net/can/isotp.c | 22 ++------- net/ipv4/igmp.c | 9 ++-- net/sunrpc/xprtsock.c | 3 -- sound/firewire/fireworks/fireworks_hwdep.c | 1 + sound/pci/hda/patch_realtek.c | 1 + sound/soc/codecs/da7219.c | 14 ++++-- sound/soc/codecs/wm8958-dsp2.c | 8 ++-- sound/soc/meson/aiu-acodec-ctrl.c | 2 +- sound/soc/meson/aiu-codec-ctrl.c | 2 +- sound/soc/meson/g12a-tohdmitx.c | 2 +- sound/soc/soc-generic-dmaengine-pcm.c | 6 +-- .../drivers/net/ocelot/tc_flower_chains.sh | 2 +- .../net/forwarding/mirror_gre_bridge_1q.sh | 3 ++ tools/testing/selftests/seccomp/seccomp_bpf.c | 10 ++-- 63 files changed, 501 insertions(+), 215 deletions(-) -- 2.20.1

1 64

[PATCH openEuler-5.10 000/120] Backport 5.10.114 LTS
by Zheng Zengkai 04 Aug '22

04 Aug '22

Backport 5.10.114 LTS patches from upstream. git cherry-pick v5.10.113..v5.10.114~1 -s Complicts: Already merged(5): 54c028cfc496 floppy: disable FDRAWCMD by default e3ec78d82d48 net: hns3: modify the return code of hclge_get_ring_chain_from_mbx 929c30c02de4 net: hns3: add validity check for message data length 9eb25e00f59b net: hns3: add return value for mailbox handling in PF 1781beb87935 tls: Skip tls_append_frag on zero copy size Implementation changed(already merged, use mainline version b98535d09179, 1): 585ef03c9e79 ext4: fix bug_on in start_this_handle during umount filesystem Defered(3, kabi changed): 3c464db03c12 tcp: ensure to use the most recently sent skb when filling the rate sample 6f2bf9c5ddfe mtd: fix 'part' field data corruption in mtd_info 616d354fb9e8 hex2bin: make the function hex_to_bin constant-time Total patches: 129 - 5 - 1 - 3 = 120 Adam Ford (2): ARM: dts: am3517-evm: Fix misc pinmuxing ARM: dts: logicpd-som-lv: Fix wrong pinmuxing on OMAP35 Alexey Kardashevskiy (1): powerpc/perf: Fix 32bit compile Baruch Siach (1): net: phy: marvell10g: fix return value on error Borislav Petkov (1): x86/cpu: Load microcode during restore_processor_state() Bruno Thomsen (1): USB: serial: cp210x: add PIDs for Kamstrup USB Meter Reader Chao Song (1): ASoC: Intel: soc-acpi: correct device endpoints for max98373 Christian Hewitt (2): arm64: dts: meson: remove CPU opps below 1GHz for G12B boards arm64: dts: meson: remove CPU opps below 1GHz for SM1 boards Christophe JAILLET (1): bus: sunxi-rsb: Fix the return value of sunxi_rsb_device_create() Chuanhong Guo (1): mtd: rawnand: fix ecc parameters for mt7622 Claudiu Beznea (1): ARM: dts: at91: sama5d4_xplained: fix pinctrl phandle name Damien Le Moal (2): zonefs: Fix management of open zones zonefs: Clear inode information flags on inode creation Dan Vacura (1): usb: gadget: uvc: Fix crash when encoding data for usb request Daniel Starke (13): tty: n_gsm: fix restart handling via CLD command tty: n_gsm: fix decoupled mux resource tty: n_gsm: fix mux cleanup after unregister tty device tty: n_gsm: fix wrong signal octet encoding in convergence layer type 2 tty: n_gsm: fix malformed counter for out of frame data tty: n_gsm: fix insufficient txframe size tty: n_gsm: fix wrong DLCI release order tty: n_gsm: fix missing explicit ldisc flush tty: n_gsm: fix wrong command retry handling tty: n_gsm: fix wrong command frame length field encoding tty: n_gsm: fix reset fifo race condition tty: n_gsm: fix incorrect UA handling tty: n_gsm: fix software flow control handling Daniele Palmas (1): USB: serial: option: add Telit 0x1057, 0x1058, 0x1075 compositions Dany Madden (1): Revert "ibmvnic: Add ethtool private flag for driver-defined queue limits" David Yat Sin (1): drm/amdkfd: Fix GWS queue count Dinh Nguyen (1): net: ethernet: stmmac: fix write to sgmii_adapter_base Duoming Zhou (1): drivers: net: hippi: Fix deadlock in rr_close() Eric Dumazet (2): tcp: fix potential xmit stalls caused by TCP_NOTSENT_LOWAT tcp: make sure treq->af_specific is initialized Evan Green (1): xhci: Enable runtime PM on second Alderlake controller Eyal Birger (1): bpf, lwt: Fix crash when using bpf_skb_set_tunnel_key() from bpf_xmit lwt hook Fabio Estevam (2): ARM: dts: imx6qdl-apalis: Fix sgtl5000 detection issue arm64: dts: imx8mn-ddr4-evk: Describe the 32.768 kHz PMIC clock Fawzi Khaber (1): iio: imu: inv_icm42600: Fix I2C init possible nack Florian Westphal (1): netfilter: nft_socket: only do sk lookups when indev is available Francesco Ruggeri (1): tcp: md5: incorrect tcp_header_len for incoming connections Geert Uytterhoeven (1): memory: renesas-rpc-if: Fix HF/OSPI data transfer in Manual Mode Greg Kroah-Hartman (1): lightnvm: disable the subsystem Guo Ren (1): riscv: patch_text: Fixup last cpu should be master H. Nikolaus Schaller (1): ARM: dts: Fix mmc order for omap3-gta04 Hangyu Hua (1): usb: misc: fix improper handling of refcount in uss720_probe() Heikki Krogerus (2): usb: typec: ucsi: Fix reuse of completion structure usb: typec: ucsi: Fix role swapping Henry Lin (1): xhci: stop polling roothubs after shutdown Imre Deak (1): drm/i915: Fix SEL_FETCH_PLANE_*(PIPE_B+) register addresses Johan Hovold (1): serial: imx: fix overrun interrupts in DMA mode Jonathan Lemon (1): net: bcmgenet: hide status block before TX timestamping Kees Cook (2): USB: serial: whiteheat: fix heap overflow in WHITEHEAT_GET_DTR_RTS thermal: int340x: Fix attr.show callback prototype Krzysztof Kozlowski (2): pinctrl: samsung: fix missing GPIOLIB on ARM64 Exynos config phy: samsung: exynos5250-sata: fix missing device put in probe error paths Leon Romanovsky (1): ixgbe: ensure IPsec VF<->PF compatibility Lijun Pan (1): ibmvnic: fix miscellaneous checks Luca Ceresoli (1): pinctrl: rockchip: fix RK3308 pinmux bits Lv Ruyi (1): pinctrl: pistachio: fix use of irq_of_parse_and_map() Maciej W. Rozycki (2): serial: 8250: Also set sticky MCR bits in console restoration serial: 8250: Correct the clock for EndRun PTP/1588 PCIe device Macpaul Lin (1): usb: mtu3: fix USB 3.0 dual-role-switch from device to host Manish Chopra (1): bnx2x: fix napi API usage sequence Marek Vasut (2): pinctrl: stm32: Do not call stm32_gpio_get() for edge triggered IRQs in EOI pinctrl: stm32: Keep pinctrl block clock enabled when LEVEL IRQ requested Mark Brown (1): ARM: dts: at91: Map MCLK for wm8731 on at91sam9g20ek Martin Blumenstingl (1): net: dsa: lantiq_gswip: Don't set GSWIP_MII_CFG_RMII_CLK Mathias Nyman (1): xhci: increase usb U3 -> U0 link resume timeout from 100ms to 500ms Max Krummenacher (1): ARM: dts: imx6ull-colibri: fix vqmmc regulator Miaoqian Lin (8): phy: samsung: Fix missing of_node_put() in exynos_sata_phy_probe ARM: OMAP2+: Fix refcount leak in omap_gic_of_init phy: ti: omap-usb2: Fix error handling in omap_usb2_enable_clocks phy: mapphone-mdm6600: Fix PM error handling in phy_mdm6600_probe phy: ti: Add missing pm_runtime_disable() in serdes_am654_probe mtd: rawnand: Fix return value check of wait_for_completion_timeout net: dsa: Add missing of_node_put() in dsa_port_link_register_of drm/amd/display: Fix memory leak in dcn21_clock_source_create Michael Hennerich (1): iio: dac: ad5446: Fix read_raw not returning set value Mikulas Patocka (2): hex2bin: fix access beyond string end x86: __memcpy_flushcache: fix wrong alignment if size > 2^32 Namhyung Kim (3): perf symbol: Pass is_kallsyms to symbols__fixup_end() perf symbol: Update symbols__fixup_end() perf symbol: Remove arch__symbols__fixup_end() Nikolay Aleksandrov (1): wireguard: device: check for metadata_dst with skb_valid_dst() Oliver Neukum (2): USB: quirks: add a Realtek card reader USB: quirks: add STRING quirk for VCOM device Pablo Neira Ayuso (1): netfilter: nft_set_rbtree: overlap detection with element re-addition after deletion Pavel Skripkin (1): video: fbdev: udlfb: properly check endpoint type Pawel Laszczak (1): usb: cdns3: Fix issue for clear halt endpoint Peilin Ye (3): ip_gre: Make o_seqno start from 0 in native mode ip6_gre: Make o_seqno start from 0 in native mode ip_gre, ip6_gre: Fix race condition on o_seqno in collect_md mode Pengcheng Yang (2): ipvs: correctly print the memory size of ip_vs_conn_tab tcp: fix F-RTO may not work correctly when receiving DSACK Ronnie Sahlberg (1): cifs: destage any unwritten data to the server before calling copychunk_write Sean Anderson (1): usb: phy: generic: Get the vbus supply Slark Xiao (1): USB: serial: option: add support for Cinterion MV32-WA/MV32-WB Sven Peter (1): usb: dwc3: Try usb-role-switch first in dwc3_drd_init Tejun Heo (1): iocost: don't reset the inuse weight of under-weighted debtors Thinh Nguyen (3): usb: dwc3: core: Fix tx/rx threshold settings usb: dwc3: core: Only handle soft-reset in DCTL usb: dwc3: gadget: Return proper request status Thomas Gleixner (1): x86/pci/xen: Disable PCI/MSI[-X] masking for XEN_HVM guests Tong Zhang (1): iio:imu:bmi160: disable regulator in error path Tony Lindgren (1): bus: ti-sysc: Make omap3 gpt12 quirk handling SoC specific Vijayavardhan Vennapusa (1): usb: gadget: configfs: clear deactivation flag in configfs_composite_unbind() Wang Qing (1): arch_topology: Do not set llc_sibling if llc_id is invalid Weitao Wang (1): USB: Fix xhci event ring dequeue pointer ERDP update issue Xiaobing Luo (1): cpufreq: fix memory leak in sun50i_cpufreq_nvmem_probe Xin Long (1): sctp: check asoc strreset_chunk in sctp_generate_reconf_event Yang Yingliang (2): clk: sunxi: sun9i-mmc: check return value after calling platform_get_resource() net: fec: add missing of_node_put() in fec_enet_init_stop_mode() YueHaibing (1): pinctrl: mediatek: moore: Fix build error Zheyu Ma (2): iio: magnetometer: ak8975: Fix the error handling in ak8975_power_on() ASoC: wm8731: Disable the regulator when probing fails Zizhuang Deng (1): iio: dac: ad5592r: Fix the missing return value. Zqiang (1): kasan: prevent cpu_quarantine corruption when CPU offline and cache shrink occur at same time liuyacan (1): net/smc: sync err code when tcp connection was refused arch/arm/boot/dts/am3517-evm.dts | 45 +++- arch/arm/boot/dts/am3517-som.dtsi | 9 + arch/arm/boot/dts/at91-sama5d4_xplained.dts | 4 +- arch/arm/boot/dts/at91sam9g20ek_common.dtsi | 6 + arch/arm/boot/dts/imx6qdl-apalis.dtsi | 10 +- arch/arm/boot/dts/imx6ull-colibri.dtsi | 2 +- .../boot/dts/logicpd-som-lv-35xx-devkit.dts | 15 ++ .../boot/dts/logicpd-som-lv-37xx-devkit.dts | 15 ++ arch/arm/boot/dts/logicpd-som-lv.dtsi | 15 -- arch/arm/boot/dts/omap3-gta04.dtsi | 2 + arch/arm/mach-exynos/Kconfig | 1 - arch/arm/mach-omap2/omap4-common.c | 2 + .../boot/dts/amlogic/meson-g12b-a311d.dtsi | 40 ---- .../boot/dts/amlogic/meson-g12b-s922x.dtsi | 40 ---- arch/arm64/boot/dts/amlogic/meson-sm1.dtsi | 20 -- .../boot/dts/freescale/imx8mn-ddr4-evk.dts | 4 + arch/powerpc/perf/Makefile | 4 +- arch/riscv/kernel/patch.c | 2 +- arch/x86/include/asm/microcode.h | 2 + arch/x86/kernel/cpu/microcode/core.c | 6 +- arch/x86/lib/usercopy_64.c | 2 +- arch/x86/pci/xen.c | 6 +- arch/x86/power/cpu.c | 10 +- block/blk-iocost.c | 12 +- drivers/base/arch_topology.c | 2 +- drivers/bus/sunxi-rsb.c | 2 + drivers/bus/ti-sysc.c | 16 +- drivers/clk/sunxi/clk-sun9i-mmc.c | 2 + drivers/cpufreq/sun50i-cpufreq-nvmem.c | 4 +- .../drm/amd/amdkfd/kfd_device_queue_manager.c | 83 ++++---- .../drm/amd/display/dc/dcn21/dcn21_resource.c | 1 + drivers/gpu/drm/i915/i915_reg.h | 2 +- drivers/iio/dac/ad5446.c | 2 +- drivers/iio/dac/ad5592r-base.c | 2 +- drivers/iio/imu/bmi160/bmi160_core.c | 20 +- .../iio/imu/inv_icm42600/inv_icm42600_i2c.c | 15 +- drivers/iio/magnetometer/ak8975.c | 1 + drivers/lightnvm/Kconfig | 2 +- drivers/memory/renesas-rpc-if.c | 60 ++++-- drivers/mtd/nand/raw/mtk_ecc.c | 12 +- drivers/mtd/nand/raw/sh_flctl.c | 14 +- drivers/net/dsa/lantiq_gswip.c | 3 - .../net/ethernet/broadcom/bnx2x/bnx2x_main.c | 9 +- .../net/ethernet/broadcom/genet/bcmgenet.c | 7 + drivers/net/ethernet/freescale/fec_main.c | 2 +- drivers/net/ethernet/ibm/ibmvnic.c | 144 ++++--------- drivers/net/ethernet/ibm/ibmvnic.h | 6 - .../net/ethernet/intel/ixgbe/ixgbe_ipsec.c | 3 +- .../ethernet/stmicro/stmmac/dwmac-socfpga.c | 12 +- drivers/net/hippi/rrunner.c | 2 + drivers/net/phy/marvell10g.c | 2 +- drivers/net/wireguard/device.c | 3 +- drivers/phy/motorola/phy-mapphone-mdm6600.c | 3 +- drivers/phy/samsung/phy-exynos5250-sata.c | 21 +- drivers/phy/ti/phy-am654-serdes.c | 2 +- drivers/phy/ti/phy-omap-usb2.c | 2 +- drivers/pinctrl/mediatek/Kconfig | 1 + drivers/pinctrl/pinctrl-pistachio.c | 6 +- drivers/pinctrl/pinctrl-rockchip.c | 45 ++-- drivers/pinctrl/samsung/Kconfig | 11 +- drivers/pinctrl/stm32/pinctrl-stm32.c | 23 ++- .../intel/int340x_thermal/int3400_thermal.c | 4 +- drivers/tty/n_gsm.c | 194 ++++++++++-------- drivers/tty/serial/8250/8250_pci.c | 8 +- drivers/tty/serial/8250/8250_port.c | 2 +- drivers/tty/serial/imx.c | 2 +- drivers/usb/cdns3/gadget.c | 7 +- drivers/usb/core/quirks.c | 6 + drivers/usb/dwc3/core.c | 11 +- drivers/usb/dwc3/drd.c | 11 +- drivers/usb/dwc3/gadget.c | 31 ++- drivers/usb/gadget/configfs.c | 2 + drivers/usb/gadget/function/uvc_queue.c | 2 + drivers/usb/host/xhci-hub.c | 2 +- drivers/usb/host/xhci-pci.c | 4 +- drivers/usb/host/xhci-ring.c | 2 + drivers/usb/host/xhci.c | 11 + drivers/usb/misc/uss720.c | 3 +- drivers/usb/mtu3/mtu3_dr.c | 6 +- drivers/usb/phy/phy-generic.c | 7 + drivers/usb/serial/cp210x.c | 2 + drivers/usb/serial/option.c | 12 ++ drivers/usb/serial/whiteheat.c | 5 +- drivers/usb/typec/ucsi/ucsi.c | 24 ++- drivers/video/fbdev/udlfb.c | 14 +- fs/cifs/smb2ops.c | 8 + fs/zonefs/super.c | 46 ++++- include/memory/renesas-rpc-if.h | 1 + include/net/ip6_tunnel.h | 2 +- include/net/ip_tunnels.h | 2 +- include/net/tcp.h | 2 + lib/hexdump.c | 9 +- mm/kasan/quarantine.c | 7 + net/core/lwt_bpf.c | 7 +- net/dsa/port.c | 2 + net/ipv4/ip_gre.c | 12 +- net/ipv4/syncookies.c | 8 +- net/ipv4/tcp_input.c | 15 +- net/ipv4/tcp_minisocks.c | 2 +- net/ipv4/tcp_output.c | 1 + net/ipv6/ip6_gre.c | 16 +- net/ipv6/syncookies.c | 3 +- net/netfilter/ipvs/ip_vs_conn.c | 2 +- net/netfilter/nft_set_rbtree.c | 6 +- net/netfilter/nft_socket.c | 52 +++-- net/sctp/sm_sideeffect.c | 4 + net/smc/af_smc.c | 2 + sound/soc/codecs/wm8731.c | 19 +- .../intel/common/soc-acpi-intel-tgl-match.c | 4 +- tools/perf/arch/arm64/util/Build | 1 - tools/perf/arch/arm64/util/machine.c | 27 --- tools/perf/arch/s390/util/machine.c | 16 -- tools/perf/util/symbol-elf.c | 2 +- tools/perf/util/symbol.c | 37 +++- tools/perf/util/symbol.h | 3 +- 115 files changed, 879 insertions(+), 632 deletions(-) delete mode 100644 tools/perf/arch/arm64/util/machine.c -- 2.20.1

1 120

[PATCH openEuler-1.0-LTS] rcu: Set a maximum limit for back-to-back callback invocation
by Yongqiang Liu 04 Aug '22

04 Aug '22

From: "Paul E. McKenney" <paulmck(a)linux.ibm.com> mainline inclusion from mainline-v5.3-rc1 commit d5a9a8c3bc8068f2e5dfba30150ac09b596b461a category: bugfix bugzilla: 187356, https://gitee.com/openeuler/kernel/issues/I5KOZ5 CVE: NA --------------------------- Currently, if a CPU has more than 10,000 callbacks pending, it will increase rdp->blimit to LONG_MAX. If you are lucky, LONG_MAX is only about two billion, but this is still a bit too many callbacks to invoke back-to-back while otherwise ignoring the world. This commit therefore sets a maximum limit of DEFAULT_MAX_RCU_BLIMIT, which is set to 10,000, for rdp->blimit. Reported-by: Sebastian Andrzej Siewior <bigeasy(a)linutronix.de> Signed-off-by: Paul E. McKenney <paulmck(a)linux.ibm.com> Conflicts: kernel/rcu/tree.c Signed-off-by: Zhen Lei <thunder.leizhen(a)huawei.com> Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- kernel/rcu/tree.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index ea05c59096a2..a0dc5385bcbc 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -490,7 +490,8 @@ void rcu_all_qs(void) } EXPORT_SYMBOL_GPL(rcu_all_qs); -#define DEFAULT_RCU_BLIMIT 10 /* Maximum callbacks per rcu_do_batch. */ +#define DEFAULT_RCU_BLIMIT 10 /* Maximum callbacks per rcu_do_batch ... */ +#define DEFAULT_MAX_RCU_BLIMIT 10000 /* ... even during callback flood. */ static long blimit = DEFAULT_RCU_BLIMIT; #define DEFAULT_RCU_QHIMARK 10000 /* If this many pending, ignore blimit. */ static long qhimark = DEFAULT_RCU_QHIMARK; @@ -2604,7 +2605,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) /* Reinstate batch limit if we have worked down the excess. */ count = rcu_segcblist_n_cbs(&rdp->cblist); - if (rdp->blimit == LONG_MAX && count <= qlowmark) + if (rdp->blimit >= DEFAULT_MAX_RCU_BLIMIT && count <= qlowmark) rdp->blimit = blimit; /* Reset ->qlen_last_fqs_check trigger if enough CBs have drained. */ @@ -2940,7 +2941,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, rcu_accelerate_cbs_unlocked(rsp, rdp->mynode, rdp); } else { /* Give the grace period a kick. */ - rdp->blimit = LONG_MAX; + rdp->blimit = DEFAULT_MAX_RCU_BLIMIT; if (rsp->n_force_qs == rdp->n_force_qs_snap && rcu_segcblist_first_pend_cb(&rdp->cblist) != head) force_quiescent_state(rsp); -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] mm: Fix page counter mismatch in shmem_mfill_atomic_pte
by Yongqiang Liu 04 Aug '22

04 Aug '22

From: Ma Wupeng <mawupeng1(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5JT6V CVE: NA -------------------------------- shmem_mfill_atomic_pte() wrongly called mem_cgroup_cancel_charge() in "success" path, it should mem_cgroup_uncharge() to dec memory counter instead. mem_cgroup_cancel_charge() should only be used if this transaction is unsuccessful and mem_cgroup_uncharge() is used to do this if this transaction succeed. This will lead to page->memcg not null and will uncharge one more in put_page(). The page counter will underflow to maximum value and trigger oom to kill all process include sshd and leave system unaccessible. page->memcg is set in the following path: mem_cgroup_commit_charge commit_charge page->mem_cgroup = memcg; extra uncharge will be done in the following path: put_page __put_page __put_single_page mem_cgroup_uncharge if (!page->mem_cgroup) <-- should return return uncharge_page uncharge_batch To fix this, call mem_cgroup_commit_charge() at the end of this transaction to make sure this transaction is really finished. Fixes: 4c27fe4c4c84 ("userfaultfd: shmem: add shmem_mcopy_atomic_pte for userfaultfd support") Signed-off-by: Ma Wupeng <mawupeng1(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- mm/shmem.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mm/shmem.c b/mm/shmem.c index 34981c7aad14..e300395fe308 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2464,8 +2464,6 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, if (ret) goto out_release_uncharge; - mem_cgroup_commit_charge(page, memcg, false, false); - _dst_pte = mk_pte(page, dst_vma->vm_page_prot); if (dst_vma->vm_flags & VM_WRITE) _dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte)); @@ -2491,6 +2489,8 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, if (!pte_none(*dst_pte)) goto out_release_uncharge_unlock; + mem_cgroup_commit_charge(page, memcg, false, false); + lru_cache_add_anon(page); spin_lock_irq(&info->lock); -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] scsi: mpt3sas: Fix unlock imbalance
by Yongqiang Liu 04 Aug '22

04 Aug '22

From: Damien Le Moal <damien.lemoal(a)wdc.com> mainline inclusion from mainline-v5.8-rc5 commit cb551b8dc079d2ef189145782627c99cb68c0255 category: bugfix bugzilla: 187287, https://gitee.com/openeuler/kernel/issues/I5JQML CVE: NA -------------------------------- In BRM_status_show(), if the condition "!ioc->is_warpdrive" tested on entry to the function is true, a "goto out" is called. This results in unlocking ioc->pci_access_mutex without this mutex lock being taken. This generates the following splat: [ 1148.539883] mpt3sas_cm2: BRM_status_show: BRM attribute is only for warpdrive [ 1148.547184] [ 1148.548708] ===================================== [ 1148.553501] WARNING: bad unlock balance detected! [ 1148.558277] 5.8.0-rc3+ #827 Not tainted [ 1148.562183] ------------------------------------- [ 1148.566959] cat/5008 is trying to release lock (&ioc->pci_access_mutex) at: [ 1148.574035] [<ffffffffc070b7a3>] BRM_status_show+0xd3/0x100 [mpt3sas] [ 1148.580574] but there are no more locks to release! [ 1148.585524] [ 1148.585524] other info that might help us debug this: [ 1148.599624] 3 locks held by cat/5008: [ 1148.607085] #0: ffff92aea3e392c0 (&p->lock){+.+.}-{3:3}, at: seq_read+0x34/0x480 [ 1148.618509] #1: ffff922ef14c4888 (&of->mutex){+.+.}-{3:3}, at: kernfs_seq_start+0x2a/0xb0 [ 1148.630729] #2: ffff92aedb5d7310 (kn->active#224){.+.+}-{0:0}, at: kernfs_seq_start+0x32/0xb0 [ 1148.643347] [ 1148.643347] stack backtrace: [ 1148.655259] CPU: 73 PID: 5008 Comm: cat Not tainted 5.8.0-rc3+ #827 [ 1148.665309] Hardware name: HGST H4060-S/S2600STB, BIOS SE5C620.86B.02.01.0008.031920191559 03/19/2019 [ 1148.678394] Call Trace: [ 1148.684750] dump_stack+0x78/0xa0 [ 1148.691802] lock_release.cold+0x45/0x4a [ 1148.699451] __mutex_unlock_slowpath+0x35/0x270 [ 1148.707675] BRM_status_show+0xd3/0x100 [mpt3sas] [ 1148.716092] dev_attr_show+0x19/0x40 [ 1148.723664] sysfs_kf_seq_show+0x87/0x100 [ 1148.731193] seq_read+0xbc/0x480 [ 1148.737882] vfs_read+0xa0/0x160 [ 1148.744514] ksys_read+0x58/0xd0 [ 1148.751129] do_syscall_64+0x4c/0xa0 [ 1148.757941] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 1148.766240] RIP: 0033:0x7f1230566542 [ 1148.772957] Code: Bad RIP value. [ 1148.779206] RSP: 002b:00007ffeac1bcac8 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 [ 1148.790063] RAX: ffffffffffffffda RBX: 0000000000020000 RCX: 00007f1230566542 [ 1148.800284] RDX: 0000000000020000 RSI: 00007f1223460000 RDI: 0000000000000003 [ 1148.810474] RBP: 00007f1223460000 R08: 00007f122345f010 R09: 0000000000000000 [ 1148.820641] R10: 0000000000000022 R11: 0000000000000246 R12: 0000000000000000 [ 1148.830728] R13: 0000000000000003 R14: 0000000000020000 R15: 0000000000020000 Fix this by returning immediately instead of jumping to the out label. Link: https://lore.kernel.org/r/20200701085254.51740-1-damien.lemoal@wdc.com Reviewed-by: Johannes Thumshirn <johannes.thumshirn(a)wdc.com> Acked-by: Sreekanth Reddy <sreekanth.reddy(a)broadcom.com> Signed-off-by: Damien Le Moal <damien.lemoal(a)wdc.com> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Conflict: drivers/scsi/mpt3sas/mpt3sas_ctl.c Signed-off-by: Zhang Wensheng <zhangwensheng5(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/scsi/mpt3sas/mpt3sas_ctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c index 772d78d92d44..90060af097cc 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c +++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c @@ -2965,7 +2965,7 @@ _ctl_BRM_status_show(struct device *cdev, struct device_attribute *attr, if (!ioc->is_warpdrive) { pr_err(MPT3SAS_FMT "%s: BRM attribute is only for" " warpdrive\n", ioc->name, __func__); - goto out; + return 0; } /* pci_access_mutex lock acquired by sysfs show path */ mutex_lock(&ioc->pci_access_mutex); -- 2.25.1

1 0

openEuler kernel SIG例会
by openEuler conference 04 Aug '22

04 Aug '22

您好！ Kernel SIG 邀请您参加 2022-08-05 14:00 召开的Zoom会议(自动录制) 会议主题：openEuler kernel SIG例会会议内容： 1、arm64:support SME（Scalable Matrix Extension）特性回合评审 2、rust for openEuler特性回合评审会议链接：https://us06web.zoom.us/j/89651338599?pwd=RUMzN1B6WStiMXVwcEdZZVYxTWRmdz09 会议纪要：https://etherpad.openeuler.org/p/Kernel-meetings 温馨提醒：建议接入会议后修改参会人的姓名，也可以使用您在gitee.com的ID 更多资讯尽在：https://openeuler.org/zh/ Hello! openEuler Kernel SIG invites you to attend the Zoom conference(auto recording) will be held at 2022-08-05 14:00, The subject of the conference is openEuler kernel SIG例会, Summary: 1、arm64:support SME（Scalable Matrix Extension）特性回合评审 2、rust for openEuler特性回合评审 You can join the meeting at https://us06web.zoom.us/j/89651338599?pwd=RUMzN1B6WStiMXVwcEdZZVYxTWRmdz09. Add topics at https://etherpad.openeuler.org/p/Kernel-meetings. Note: You are advised to change the participant name after joining the conference or use your ID at gitee.com. More information: https://openeuler.org/en/

1 0

[PATCH openEuler-1.0-LTS] io-wq: Switch io_wqe_worker's fs before releasing request
by Yongqiang Liu 04 Aug '22

04 Aug '22

From: Zhihao Cheng <chengzhihao1(a)huawei.com> hulk inclusion category: bugfix bugzilla: 187369, https://gitee.com/openeuler/kernel/issues/I5K66O CVE: NA -------------------------------- Following process triggers an use-after-free problem while iterating every process's fs: main fd = setup_iouring fork => main' // task->fs->users = 1 submit(fd, STATX, async) id->fs = current->fs req->work.identity = id io_submit_sqes ... io_grab_identity id = req->work.identity id->fs->users++ // fs->users = 2 io_wqe_worker current->fs = work->identity->fs io_req_clean_work fs = req->work.identity->fs --fs->users // fs->user = 1 main' exit exit_fs --fs->users // fs->user = 0 free_fs_struct(fs) // FREE fs pivot_root chroot_fs_refs do_each_thread(g, p) { fs = p->fs // io_wqe_worker->fs if (fs) spin_lock(&fs->lock) // UAF! } io_wqe_worker io_worker_exit __io_worker_unuse if (current->fs != worker->restore_fs) current->fs = worker->restore_fs Task's fs_struct is used in do_work() and destroyed in free_work(), this problem can be fixed by switching io_wqe_worker's fs before releasing request. Signed-off-by: Zhihao Cheng <chengzhihao1(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- fs/io-wq.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/io-wq.c b/fs/io-wq.c index b6e311e57b47..67d157bcf2fb 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -534,6 +534,8 @@ static void io_worker_handle_work(struct io_worker *worker) linked = NULL; } io_assign_current_work(worker, work); + if (current->fs != worker->restore_fs) + current->fs = worker->restore_fs; wq->free_work(old_work); if (linked) -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] ath9k: fix use-after-free in ath9k_hif_usb_rx_cb
by Yongqiang Liu 03 Aug '22

03 Aug '22

From: Pavel Skripkin <paskripkin(a)gmail.com> mainline inclusion from linux-next commit 0ac4827f78c7ffe8eef074bc010e7e34bc22f533 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I58DFB CVE: CVE-2022-1679 -------------------------------- Syzbot reported use-after-free Read in ath9k_hif_usb_rx_cb() [0]. The problem was in incorrect htc_handle->drv_priv initialization. Probable call trace which can trigger use-after-free: ath9k_htc_probe_device() /* htc_handle->drv_priv = priv; */ ath9k_htc_wait_for_target() <--- Failed ieee80211_free_hw() <--- priv pointer is freed <IRQ> ... ath9k_hif_usb_rx_cb() ath9k_hif_usb_rx_stream() RX_STAT_INC() <--- htc_handle->drv_priv access In order to not add fancy protection for drv_priv we can move htc_handle->drv_priv initialization at the end of the ath9k_htc_probe_device() and add helper macro to make all *_STAT_* macros NULL safe, since syzbot has reported related NULL deref in that macros [1] Link: https://syzkaller.appspot.com/bug?id=6ead44e37afb6866ac0c7dd121b4ce07cb665f… [0] Link: https://syzkaller.appspot.com/bug?id=b8101ffcec107c0567a0cd8acbbacec91e9ee8… [1] Fixes: fb9987d0f748 ("ath9k_htc: Support for AR9271 chipset.") Reported-and-tested-by: syzbot+03110230a11411024147(a)syzkaller.appspotmail.com Reported-and-tested-by: syzbot+c6dde1f690b60e0b9fbe(a)syzkaller.appspotmail.com Signed-off-by: Pavel Skripkin <paskripkin(a)gmail.com> Acked-by: Toke Høiland-Jørgensen <toke(a)toke.dk> Signed-off-by: Kalle Valo <quic_kvalo(a)quicinc.com> Link: https://lore.kernel.org/r/d57bbedc857950659bfacac0ab48790c1eda00c8.16551457… Signed-off-by: Xu Jia <xujia39(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Reviewed-by: Wei Yongjun <weiyongjun1(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/net/wireless/ath/ath9k/htc.h | 10 +++++----- drivers/net/wireless/ath/ath9k/htc_drv_init.c | 3 ++- 2 files changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/net/wireless/ath/ath9k/htc.h b/drivers/net/wireless/ath/ath9k/htc.h index 9f64e32381f9..81107100e368 100644 --- a/drivers/net/wireless/ath/ath9k/htc.h +++ b/drivers/net/wireless/ath/ath9k/htc.h @@ -325,11 +325,11 @@ static inline struct ath9k_htc_tx_ctl *HTC_SKB_CB(struct sk_buff *skb) } #ifdef CONFIG_ATH9K_HTC_DEBUGFS - -#define TX_STAT_INC(c) (hif_dev->htc_handle->drv_priv->debug.tx_stats.c++) -#define TX_STAT_ADD(c, a) (hif_dev->htc_handle->drv_priv->debug.tx_stats.c += a) -#define RX_STAT_INC(c) (hif_dev->htc_handle->drv_priv->debug.skbrx_stats.c++) -#define RX_STAT_ADD(c, a) (hif_dev->htc_handle->drv_priv->debug.skbrx_stats.c += a) +#define __STAT_SAFE(expr) (hif_dev->htc_handle->drv_priv ? (expr) : 0) +#define TX_STAT_INC(c) __STAT_SAFE(hif_dev->htc_handle->drv_priv->debug.tx_stats.c++) +#define TX_STAT_ADD(c, a) __STAT_SAFE(hif_dev->htc_handle->drv_priv->debug.tx_stats.c += a) +#define RX_STAT_INC(c) __STAT_SAFE(hif_dev->htc_handle->drv_priv->debug.skbrx_stats.c++) +#define RX_STAT_ADD(c, a) __STAT_SAFE(hif_dev->htc_handle->drv_priv->debug.skbrx_stats.c += a) #define CAB_STAT_INC priv->debug.tx_stats.cab_queued++ #define TX_QSTAT_INC(q) (priv->debug.tx_stats.queue_stats[q]++) diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_init.c b/drivers/net/wireless/ath/ath9k/htc_drv_init.c index 214c68269a69..e3a6f48dbd8c 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_init.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_init.c @@ -945,7 +945,6 @@ int ath9k_htc_probe_device(struct htc_target *htc_handle, struct device *dev, priv->hw = hw; priv->htc = htc_handle; priv->dev = dev; - htc_handle->drv_priv = priv; SET_IEEE80211_DEV(hw, priv->dev); ret = ath9k_htc_wait_for_target(priv); @@ -966,6 +965,8 @@ int ath9k_htc_probe_device(struct htc_target *htc_handle, struct device *dev, if (ret) goto err_init; + htc_handle->drv_priv = priv; + return 0; err_init: -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] Revert "iommu/vt-d: Fix potential memory leak in intel_setup_irq_remapping()"
by Yongqiang Liu 03 Aug '22

03 Aug '22

From: Zhang Zekun <zhangzekun11(a)huawei.com> hulk inclusion category: bugfix bugzilla: 187358, https://gitee.com/openeuler/kernel/issues/I5KD2A CVE: NA --------------------------------- This reverts commit 75624b5bc0485778aef9f46ebbf5e5df3c0d054c. This patch could cause double-free problem, when 'irqdomain' is failed to add, in which case, irq_domain_free_fwnode(fn) will be called twice. Signed-off-by: Zhang Zekun <zhangzekun11(a)huawei.com> Reviewed-by: Weilong Chen <chenweilong(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/iommu/intel_irq_remapping.c | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c index 276005451914..967450bd421a 100644 --- a/drivers/iommu/intel_irq_remapping.c +++ b/drivers/iommu/intel_irq_remapping.c @@ -539,7 +539,7 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu) irq_domain_free_fwnode(fn); if (!iommu->ir_domain) { pr_err("IR%d: failed to allocate irqdomain\n", iommu->seq_id); - goto out_free_fwnode; + goto out_free_bitmap; } iommu->ir_msi_domain = arch_create_remap_msi_irq_domain(iommu->ir_domain, @@ -563,7 +563,7 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu) if (dmar_enable_qi(iommu)) { pr_err("Failed to enable queued invalidation\n"); - goto out_free_ir_domain; + goto out_free_bitmap; } } @@ -587,14 +587,6 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu) return 0; -out_free_ir_domain: - if (iommu->ir_msi_domain) - irq_domain_remove(iommu->ir_msi_domain); - iommu->ir_msi_domain = NULL; - irq_domain_remove(iommu->ir_domain); - iommu->ir_domain = NULL; -out_free_fwnode: - irq_domain_free_fwnode(fn); out_free_bitmap: kfree(bitmap); out_free_pages: -- 2.25.1

1 0

[PATCH openEuler-5.10-LTS 01/20] md: add io accounting for raid0 and raid5
by Zheng Zengkai 02 Aug '22

02 Aug '22

From: Guoqing Jiang <jgq516(a)gmail.com> mainline inclusion from mainline-v5.14-rc1 commit 10764815ff4728d2c57da677cd5d3dd6f446cf5f category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I587H6 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… ------------------------------- We introduce a new bioset (io_acct_set) for raid0 and raid5 since they don't own clone infrastructure to accounting io. And the bioset is added to mddev instead of to raid0 and raid5 layer, because with this way, we can put common functions to md.h and reuse them in raid0 and raid5. Also struct md_io_acct is added accordingly which includes io start_time, the origin bio and cloned bio. Then we can call bio_{start,end}_io_acct to get related io status. Signed-off-by: Guoqing Jiang <jiangguoqing(a)kylinos.cn> Signed-off-by: Song Liu <song(a)kernel.org> Conflict: drivers/md/md.c drivers/md/md.h Signed-off-by: Zhang Wensheng <zhangwensheng5(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- drivers/md/md.c | 52 ++++++++++++++++++++++++++++++++++++++++++---- drivers/md/md.h | 8 +++++++ drivers/md/raid0.c | 3 +++ drivers/md/raid5.c | 9 ++++++++ 4 files changed, 68 insertions(+), 4 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index a299fda5b0e9..10d9a8bed604 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2361,7 +2361,8 @@ int md_integrity_register(struct mddev *mddev) bdev_get_integrity(reference->bdev)); pr_debug("md: data integrity enabled on %s\n", mdname(mddev)); - if (bioset_integrity_create(&mddev->bio_set, BIO_POOL_SIZE)) { + if (bioset_integrity_create(&mddev->bio_set, BIO_POOL_SIZE) || + bioset_integrity_create(&mddev->io_acct_set, BIO_POOL_SIZE)) { pr_err("md: failed to create integrity pool for %s\n", mdname(mddev)); return -EINVAL; @@ -5597,6 +5598,7 @@ static void md_free(struct kobject *ko) bioset_exit(&mddev->bio_set); bioset_exit(&mddev->sync_set); + bioset_exit(&mddev->io_acct_set); kfree(mddev); } @@ -5885,7 +5887,13 @@ int md_run(struct mddev *mddev) if (!bioset_initialized(&mddev->sync_set)) { err = bioset_init(&mddev->sync_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); if (err) - return err; + goto exit_bio_set; + } + if (!bioset_initialized(&mddev->io_acct_set)) { + err = bioset_init(&mddev->io_acct_set, BIO_POOL_SIZE, + offsetof(struct md_io_acct, bio_clone), 0); + if (err) + goto exit_sync_set; } spin_lock(&pers_lock); @@ -6013,6 +6021,7 @@ int md_run(struct mddev *mddev) blk_queue_flag_set(QUEUE_FLAG_NONROT, mddev->queue); else blk_queue_flag_clear(QUEUE_FLAG_NONROT, mddev->queue); + blk_queue_flag_set(QUEUE_FLAG_IO_STAT, mddev->queue); } if (pers->sync_request) { if (mddev->kobj.sd && @@ -6062,8 +6071,11 @@ int md_run(struct mddev *mddev) module_put(pers->owner); md_bitmap_destroy(mddev); abort: - bioset_exit(&mddev->bio_set); + bioset_exit(&mddev->io_acct_set); +exit_sync_set: bioset_exit(&mddev->sync_set); +exit_bio_set: + bioset_exit(&mddev->bio_set); return err; } EXPORT_SYMBOL_GPL(md_run); @@ -6288,6 +6300,7 @@ void md_stop(struct mddev *mddev) __md_stop(mddev); bioset_exit(&mddev->bio_set); bioset_exit(&mddev->sync_set); + bioset_exit(&mddev->io_acct_set); } EXPORT_SYMBOL_GPL(md_stop); @@ -8571,9 +8584,40 @@ void md_write_end(struct mddev *mddev) roundup(jiffies, mddev->safemode_delay) + mddev->safemode_delay); } - EXPORT_SYMBOL(md_write_end); +static void md_end_io_acct(struct bio *bio) +{ + struct md_io_acct *md_io_acct = bio->bi_private; + struct bio *orig_bio = md_io_acct->orig_bio; + + orig_bio->bi_status = bio->bi_status; + + bio_end_io_acct(orig_bio, md_io_acct->start_time); + bio_put(bio); + bio_endio(orig_bio); +} + +/* used by personalities (raid0 and raid5) to account io stats */ +void md_account_bio(struct mddev *mddev, struct bio **bio) +{ + struct md_io_acct *md_io_acct; + struct bio *clone; + + if (!blk_queue_io_stat((*bio)->bi_disk->queue)) + return; + + clone = bio_clone_fast(*bio, GFP_NOIO, &mddev->io_acct_set); + md_io_acct = container_of(clone, struct md_io_acct, bio_clone); + md_io_acct->orig_bio = *bio; + md_io_acct->start_time = bio_start_io_acct(*bio); + + clone->bi_end_io = md_end_io_acct; + clone->bi_private = md_io_acct; + *bio = clone; +} +EXPORT_SYMBOL_GPL(md_account_bio); + /* md_allow_write(mddev) * Calling this ensures that the array is marked 'active' so that writes * may proceed without blocking. It is important to call this before diff --git a/drivers/md/md.h b/drivers/md/md.h index 85177d068322..20c16cfdd6bb 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -491,6 +491,7 @@ struct mddev { struct bio_set sync_set; /* for sync operations like * metadata and bitmap writes */ + struct bio_set io_acct_set; /* for raid0 and raid5 io accounting */ /* Generic flush handling. * The last to finish preflush schedules a worker to submit @@ -687,6 +688,12 @@ struct md_thread { void *private; }; +struct md_io_acct { + struct bio *orig_bio; + unsigned long start_time; + struct bio bio_clone; +}; + #define THREAD_WAKEUP 0 static inline void safe_put_page(struct page *p) @@ -716,6 +723,7 @@ extern void md_write_end(struct mddev *mddev); extern void md_done_sync(struct mddev *mddev, int blocks, int ok); extern void md_error(struct mddev *mddev, struct md_rdev *rdev); extern void md_finish_reshape(struct mddev *mddev); +void md_account_bio(struct mddev *mddev, struct bio **bio); extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio); extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev, diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 35843df15b5e..0312b192106a 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -556,6 +556,9 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio) bio = split; } + if (bio->bi_pool != &mddev->bio_set) + md_account_bio(mddev, &bio); + orig_sector = sector; zone = find_zone(mddev->private, &sector); switch (conf->layout) { diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index c82953a3299e..35dacc6e754f 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -5487,6 +5487,7 @@ static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio) sector_t sector = raid_bio->bi_iter.bi_sector; unsigned chunk_sects = mddev->chunk_sectors; unsigned sectors = chunk_sects - (sector & (chunk_sects-1)); + struct r5conf *conf = mddev->private; if (sectors < bio_sectors(raid_bio)) { struct r5conf *conf = mddev->private; @@ -5496,6 +5497,9 @@ static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio) raid_bio = split; } + if (raid_bio->bi_pool != &conf->bio_split) + md_account_bio(mddev, &raid_bio); + if (!raid5_read_one_chunk(mddev, raid_bio)) return raid_bio; @@ -5775,6 +5779,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) DEFINE_WAIT(w); bool do_prepare; bool do_flush = false; + bool do_clone = false; if (unlikely(bi->bi_opf & REQ_PREFLUSH)) { int ret = log_handle_flush_request(conf, bi); @@ -5803,6 +5808,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) if (rw == READ && mddev->degraded == 0 && mddev->reshape_position == MaxSector) { bi = chunk_aligned_read(mddev, bi); + do_clone = true; if (!bi) return true; } @@ -5817,6 +5823,9 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) last_sector = bio_end_sector(bi); bi->bi_next = NULL; + if (!do_clone) + md_account_bio(mddev, &bi); + prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE); for (; logical_sector < last_sector; logical_sector += RAID5_STRIPE_SECTORS(conf)) { int previous; -- 2.20.1

1 19