June 2022 - Kernel - mailweb.openeuler.org

[PATCH] vfio: framework supporting vfio device hot migration
by RongWang 05 Jul '22

05 Jul '22

From: Rong Wang <w_angrong(a)163.com> kunpeng inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I5CO9A CVE: NA --------------------------------- As pass through devices, hypervisor can`t control the status of device, and can`t track dirty memory DMA from device, during migration. The goal of this framework is to combine hardware to accomplish the task above. qemu |status control and dirty memory report vfio |ops to hardware hardware Signed-off-by: Rong Wang <w_angrong(a)163.com> Signed-off-by: HuHua Li <18245010845(a)163.com> Signed-off-by: Ripeng Qiu <965412048(a)qq.com> --- drivers/vfio/pci/Makefile | 2 +- drivers/vfio/pci/vfio_pci.c | 54 +++ drivers/vfio/pci/vfio_pci_migration.c | 755 ++++++++++++++++++++++++++++++++++ drivers/vfio/pci/vfio_pci_private.h | 14 +- drivers/vfio/vfio.c | 411 +++++++++++++++++- include/linux/vfio_pci_migration.h | 136 ++++++ 6 files changed, 1367 insertions(+), 5 deletions(-) create mode 100644 drivers/vfio/pci/vfio_pci_migration.c create mode 100644 include/linux/vfio_pci_migration.h diff --git a/drivers/vfio/pci/Makefile b/drivers/vfio/pci/Makefile index 76d8ec0..80a777d 100644 --- a/drivers/vfio/pci/Makefile +++ b/drivers/vfio/pci/Makefile @@ -1,5 +1,5 @@ -vfio-pci-y := vfio_pci.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_config.o +vfio-pci-y := vfio_pci.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_config.o vfio_pci_migration.o vfio-pci-$(CONFIG_VFIO_PCI_IGD) += vfio_pci_igd.o obj-$(CONFIG_VFIO_PCI) += vfio-pci.o diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 51b791c..59d8280 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -30,6 +30,7 @@ #include <linux/vgaarb.h> #include <linux/nospec.h> #include <linux/sched/mm.h> +#include <linux/vfio_pci_migration.h> #include "vfio_pci_private.h" @@ -296,6 +297,14 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev) vfio_pci_probe_mmaps(vdev); + if (vfio_dev_migration_is_supported(pdev)) { + ret = vfio_pci_migration_init(vdev); + if (ret) { + dev_warn(&vdev->pdev->dev, "Failed to init vfio_pci_migration\n"); + vfio_pci_disable(vdev); + return ret; + } + } return 0; } @@ -392,6 +401,7 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev) out: pci_disable_device(pdev); + vfio_pci_migration_exit(vdev); vfio_pci_try_bus_reset(vdev); if (!disable_idle_d3) @@ -642,6 +652,41 @@ struct vfio_devices { int max_index; }; +static long vfio_pci_handle_log_buf_ctl(struct vfio_pci_device *vdev, + const unsigned long arg) +{ + struct vfio_log_buf_ctl *log_buf_ctl = NULL; + struct vfio_log_buf_info *log_buf_info = NULL; + struct vf_migration_log_info migration_log_info; + long ret = 0; + + log_buf_ctl = (struct vfio_log_buf_ctl *)arg; + log_buf_info = (struct vfio_log_buf_info *)log_buf_ctl->data; + + switch (log_buf_ctl->flags) { + case VFIO_DEVICE_LOG_BUF_FLAG_START: + migration_log_info.dom_uuid = log_buf_info->uuid; + migration_log_info.buffer_size = + log_buf_info->buffer_size; + migration_log_info.sge_num = log_buf_info->addrs_size; + migration_log_info.sge_len = log_buf_info->frag_size; + migration_log_info.sgevec = log_buf_info->sgevec; + ret = vfio_pci_device_log_start(vdev, + &migration_log_info); + break; + case VFIO_DEVICE_LOG_BUF_FLAG_STOP: + ret = vfio_pci_device_log_stop(vdev, + log_buf_info->uuid); + break; + case VFIO_DEVICE_LOG_BUF_FLAG_STATUS_QUERY: + ret = vfio_pci_device_log_status_query(vdev); + break; + default: + ret = -EINVAL; + break; + } + return ret; +} static long vfio_pci_ioctl(void *device_data, unsigned int cmd, unsigned long arg) { @@ -1142,6 +1187,8 @@ static long vfio_pci_ioctl(void *device_data, return vfio_pci_ioeventfd(vdev, ioeventfd.offset, ioeventfd.data, count, ioeventfd.fd); + } else if (cmd == VFIO_DEVICE_LOG_BUF_CTL) { + return vfio_pci_handle_log_buf_ctl(vdev, arg); } return -ENOTTY; @@ -1566,6 +1613,9 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) pci_set_power_state(pdev, PCI_D3hot); } + if (vfio_dev_migration_is_supported(pdev)) + ret = vfio_pci_device_init(pdev); + return ret; } @@ -1591,6 +1641,10 @@ static void vfio_pci_remove(struct pci_dev *pdev) if (!disable_idle_d3) pci_set_power_state(pdev, PCI_D0); + + if (vfio_dev_migration_is_supported(pdev)) { + vfio_pci_device_uninit(pdev); + } } static pci_ers_result_t vfio_pci_aer_err_detected(struct pci_dev *pdev, diff --git a/drivers/vfio/pci/vfio_pci_migration.c b/drivers/vfio/pci/vfio_pci_migration.c new file mode 100644 index 0000000..f69cd13 --- /dev/null +++ b/drivers/vfio/pci/vfio_pci_migration.c @@ -0,0 +1,755 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2022 Huawei Technologies Co., Ltd. All rights reserved. + */ + +#include <linux/module.h> +#include <linux/io.h> +#include <linux/pci.h> +#include <linux/uaccess.h> +#include <linux/vfio.h> +#include <linux/vfio_pci_migration.h> + +#include "vfio_pci_private.h" + +static LIST_HEAD(vfio_pci_mig_drivers_list); +static DEFINE_MUTEX(vfio_pci_mig_drivers_mutex); + +static void vfio_pci_add_mig_drv(struct vfio_pci_vendor_mig_driver *mig_drv) +{ + mutex_lock(&vfio_pci_mig_drivers_mutex); + atomic_set(&mig_drv->count, 1); + list_add_tail(&mig_drv->list, &vfio_pci_mig_drivers_list); + mutex_unlock(&vfio_pci_mig_drivers_mutex); +} + +static void vfio_pci_remove_mig_drv(struct vfio_pci_vendor_mig_driver *mig_drv) +{ + mutex_lock(&vfio_pci_mig_drivers_mutex); + list_del(&mig_drv->list); + mutex_unlock(&vfio_pci_mig_drivers_mutex); +} + +static struct vfio_pci_vendor_mig_driver * + vfio_pci_find_mig_drv(struct pci_dev *pdev, struct module *module) +{ + struct vfio_pci_vendor_mig_driver *mig_drv = NULL; + + mutex_lock(&vfio_pci_mig_drivers_mutex); + list_for_each_entry(mig_drv, &vfio_pci_mig_drivers_list, list) { + if (mig_drv->owner == module) { + if (mig_drv->bus_num == pdev->bus->number) + goto out; + } + } + mig_drv = NULL; +out: + mutex_unlock(&vfio_pci_mig_drivers_mutex); + return mig_drv; +} + +static struct vfio_pci_vendor_mig_driver * + vfio_pci_get_mig_driver(struct pci_dev *pdev) +{ + struct vfio_pci_vendor_mig_driver *mig_drv = NULL; + struct pci_dev *pf_dev = pci_physfn(pdev); + + mutex_lock(&vfio_pci_mig_drivers_mutex); + list_for_each_entry(mig_drv, &vfio_pci_mig_drivers_list, list) { + if (mig_drv->bus_num == pf_dev->bus->number) + goto out; + } + mig_drv = NULL; +out: + mutex_unlock(&vfio_pci_mig_drivers_mutex); + return mig_drv; +} + +bool vfio_dev_migration_is_supported(struct pci_dev *pdev) +{ + struct vfio_pci_vendor_mig_driver *mig_driver = NULL; + + mig_driver = vfio_pci_get_mig_driver(pdev); + if (!mig_driver || !mig_driver->dev_mig_ops) { + dev_warn(&pdev->dev, "unable to find a mig_drv module\n"); + return false; + } + + return true; +} + +int vfio_pci_device_log_start(struct vfio_pci_device *vdev, + struct vf_migration_log_info *log_info) +{ + struct vfio_pci_vendor_mig_driver *mig_driver; + + mig_driver = vfio_pci_get_mig_driver(vdev->pdev); + if (!mig_driver || !mig_driver->dev_mig_ops) { + dev_err(&vdev->pdev->dev, "unable to find a mig_drv module\n"); + return -EFAULT; + } + + if (!mig_driver->dev_mig_ops->log_start || + (mig_driver->dev_mig_ops->log_start(vdev->pdev, + log_info) != 0)) { + dev_err(&vdev->pdev->dev, "failed to set log start\n"); + return -EFAULT; + } + + return 0; +} + +int vfio_pci_device_log_stop(struct vfio_pci_device *vdev, uint32_t uuid) +{ + struct vfio_pci_vendor_mig_driver *mig_driver; + + mig_driver = vfio_pci_get_mig_driver(vdev->pdev); + if (!mig_driver || !mig_driver->dev_mig_ops) { + dev_err(&vdev->pdev->dev, "unable to find a mig_drv module\n"); + return -EFAULT; + } + + if (!mig_driver->dev_mig_ops->log_stop || + (mig_driver->dev_mig_ops->log_stop(vdev->pdev, uuid) != 0)) { + dev_err(&vdev->pdev->dev, "failed to set log stop\n"); + return -EFAULT; + } + + return 0; +} + +int vfio_pci_device_log_status_query(struct vfio_pci_device *vdev) +{ + struct vfio_pci_vendor_mig_driver *mig_driver; + + mig_driver = vfio_pci_get_mig_driver(vdev->pdev); + if (!mig_driver || !mig_driver->dev_mig_ops) { + dev_err(&vdev->pdev->dev, "unable to find a mig_drv module\n"); + return -EFAULT; + } + + if (!mig_driver->dev_mig_ops->get_log_status || + (mig_driver->dev_mig_ops->get_log_status(vdev->pdev) != 0)) { + dev_err(&vdev->pdev->dev, "failed to get log status\n"); + return -EFAULT; + } + + return 0; +} + +int vfio_pci_device_init(struct pci_dev *pdev) +{ + struct vfio_pci_vendor_mig_driver *mig_drv; + + mig_drv = vfio_pci_get_mig_driver(pdev); + if (!mig_drv || !mig_drv->dev_mig_ops) { + dev_err(&pdev->dev, "unable to find a mig_drv module\n"); + return -EFAULT; + } + + if (mig_drv->dev_mig_ops->init) + return mig_drv->dev_mig_ops->init(pdev); + + return -EFAULT; +} + +void vfio_pci_device_uninit(struct pci_dev *pdev) +{ + struct vfio_pci_vendor_mig_driver *mig_drv; + + mig_drv = vfio_pci_get_mig_driver(pdev); + if (!mig_drv || !mig_drv->dev_mig_ops) { + dev_err(&pdev->dev, "unable to find a mig_drv module\n"); + return; + } + + if (mig_drv->dev_mig_ops->uninit) + mig_drv->dev_mig_ops->uninit(pdev); +} + +static void vfio_pci_device_release(struct pci_dev *pdev, + struct vfio_pci_vendor_mig_driver *mig_drv) +{ + if (mig_drv->dev_mig_ops->release) + mig_drv->dev_mig_ops->release(pdev); +} + +static int vfio_pci_device_get_info(struct pci_dev *pdev, + struct vfio_device_migration_info *mig_info, + struct vfio_pci_vendor_mig_driver *mig_drv) +{ + if (mig_drv->dev_mig_ops->get_info) + return mig_drv->dev_mig_ops->get_info(pdev, mig_info); + return -EFAULT; +} + +static int vfio_pci_device_enable(struct pci_dev *pdev, + struct vfio_pci_vendor_mig_driver *mig_drv) +{ + if (!mig_drv->dev_mig_ops->enable || + (mig_drv->dev_mig_ops->enable(pdev) != 0)) { + return -EINVAL; + } + + return 0; +} + +static int vfio_pci_device_disable(struct pci_dev *pdev, + struct vfio_pci_vendor_mig_driver *mig_drv) +{ + if (!mig_drv->dev_mig_ops->disable || + (mig_drv->dev_mig_ops->disable(pdev) != 0)) + return -EINVAL; + + return 0; +} + +static int vfio_pci_device_pre_enable(struct pci_dev *pdev, + struct vfio_pci_vendor_mig_driver *mig_drv) +{ + if (!mig_drv->dev_mig_ops->pre_enable || + (mig_drv->dev_mig_ops->pre_enable(pdev) != 0)) + return -EINVAL; + + return 0; +} + +static int vfio_pci_device_state_save(struct pci_dev *pdev, + struct vfio_pci_migration_data *data) +{ + struct vfio_device_migration_info *mig_info = data->mig_ctl; + struct vfio_pci_vendor_mig_driver *mig_drv = data->mig_driver; + void *base = (void *)mig_info; + int ret = 0; + + if ((mig_info->device_state & VFIO_DEVICE_STATE_RUNNING) != 0) { + ret = vfio_pci_device_disable(pdev, mig_drv); + if (ret) { + dev_err(&pdev->dev, "failed to stop VF function!\n"); + return ret; + } + mig_info->device_state &= ~VFIO_DEVICE_STATE_RUNNING; + } + + if (mig_drv->dev_mig_ops && mig_drv->dev_mig_ops->save) { + ret = mig_drv->dev_mig_ops->save(pdev, base, + mig_info->data_offset, data->state_size); + if (ret) { + dev_err(&pdev->dev, "failed to save device state!\n"); + return -EINVAL; + } + } else { + return -EFAULT; + } + + mig_info->data_size = data->state_size; + mig_info->pending_bytes = mig_info->data_size; + return ret; +} + +static int vfio_pci_device_state_restore(struct vfio_pci_migration_data *data) +{ + struct vfio_device_migration_info *mig_info = data->mig_ctl; + struct vfio_pci_vendor_mig_driver *mig_drv = data->mig_driver; + struct pci_dev *pdev = data->vf_dev; + void *base = (void *)mig_info; + int ret; + + if (mig_drv->dev_mig_ops && mig_drv->dev_mig_ops->restore) { + ret = mig_drv->dev_mig_ops->restore(pdev, base, + mig_info->data_offset, mig_info->data_size); + if (ret) { + dev_err(&pdev->dev, "failed to restore device state!\n"); + return -EINVAL; + } + return 0; + } + + return -EFAULT; +} + +static int vfio_pci_set_device_state(struct vfio_pci_migration_data *data, + u32 state) +{ + struct vfio_device_migration_info *mig_ctl = data->mig_ctl; + struct vfio_pci_vendor_mig_driver *mig_drv = data->mig_driver; + struct pci_dev *pdev = data->vf_dev; + int ret = 0; + + if (state == mig_ctl->device_state) + return 0; + + if (!mig_drv->dev_mig_ops) + return -EINVAL; + + switch (state) { + case VFIO_DEVICE_STATE_RUNNING: + if (!(mig_ctl->device_state & + VFIO_DEVICE_STATE_RUNNING)) + ret = vfio_pci_device_enable(pdev, mig_drv); + break; + case VFIO_DEVICE_STATE_SAVING | VFIO_DEVICE_STATE_RUNNING: + /* + * (pre-copy) - device should start logging data. + */ + ret = 0; + break; + case VFIO_DEVICE_STATE_SAVING: + /* stop the vf function, save state */ + ret = vfio_pci_device_state_save(pdev, data); + break; + case VFIO_DEVICE_STATE_STOP: + if (mig_ctl->device_state & VFIO_DEVICE_STATE_RUNNING) + ret = vfio_pci_device_disable(pdev, mig_drv); + break; + case VFIO_DEVICE_STATE_RESUMING: + ret = vfio_pci_device_pre_enable(pdev, mig_drv); + break; + default: + ret = -EFAULT; + break; + } + + if (ret) + return ret; + + mig_ctl->device_state = state; + return 0; +} + +static ssize_t vfio_pci_handle_mig_dev_state( + struct vfio_pci_migration_data *data, + char __user *buf, size_t count, bool iswrite) +{ + struct vfio_device_migration_info *mig_ctl = data->mig_ctl; + u32 device_state; + int ret; + + if (count != sizeof(device_state)) + return -EINVAL; + + if (iswrite) { + if (copy_from_user(&device_state, buf, count)) + return -EFAULT; + + ret = vfio_pci_set_device_state(data, device_state); + if (ret) + return ret; + } else { + if (copy_to_user(buf, &mig_ctl->device_state, count)) + return -EFAULT; + } + + return count; +} + +static ssize_t vfio_pci_handle_mig_pending_bytes( + struct vfio_device_migration_info *mig_info, + char __user *buf, size_t count, bool iswrite) +{ + u64 pending_bytes; + + if (count != sizeof(pending_bytes) || iswrite) + return -EINVAL; + + if (mig_info->device_state == + (VFIO_DEVICE_STATE_SAVING | VFIO_DEVICE_STATE_RUNNING)) { + /* In pre-copy state we have no data to return for now, + * return 0 pending bytes + */ + pending_bytes = 0; + } else { + pending_bytes = mig_info->pending_bytes; + } + + if (copy_to_user(buf, &pending_bytes, count)) + return -EFAULT; + + return count; +} + +static ssize_t vfio_pci_handle_mig_data_offset( + struct vfio_device_migration_info *mig_info, + char __user *buf, size_t count, bool iswrite) +{ + u64 data_offset = mig_info->data_offset; + + if (count != sizeof(data_offset) || iswrite) + return -EINVAL; + + if (copy_to_user(buf, &data_offset, count)) + return -EFAULT; + + return count; +} + +static ssize_t vfio_pci_handle_mig_data_size( + struct vfio_device_migration_info *mig_info, + char __user *buf, size_t count, bool iswrite) +{ + u64 data_size; + + if (count != sizeof(data_size)) + return -EINVAL; + + if (iswrite) { + /* data_size is writable only during resuming state */ + if (mig_info->device_state != VFIO_DEVICE_STATE_RESUMING) + return -EINVAL; + + if (copy_from_user(&data_size, buf, sizeof(data_size))) + return -EFAULT; + + mig_info->data_size = data_size; + } else { + if (mig_info->device_state != VFIO_DEVICE_STATE_SAVING) + return -EINVAL; + + if (copy_to_user(buf, &mig_info->data_size, + sizeof(data_size))) + return -EFAULT; + } + + return count; +} + +static ssize_t vfio_pci_handle_mig_dev_cmd(struct vfio_pci_migration_data *data, + char __user *buf, size_t count, bool iswrite) +{ + struct vfio_pci_vendor_mig_driver *mig_drv = data->mig_driver; + struct pci_dev *pdev = data->vf_dev; + u32 device_cmd; + int ret = -EFAULT; + + if (count != sizeof(device_cmd) || !iswrite || !mig_drv->dev_mig_ops) + return -EINVAL; + + if (copy_from_user(&device_cmd, buf, count)) + return -EFAULT; + + switch (device_cmd) { + case VFIO_DEVICE_MIGRATION_CANCEL: + if (mig_drv->dev_mig_ops->cancel) + ret = mig_drv->dev_mig_ops->cancel(pdev); + break; + default: + dev_err(&pdev->dev, "cmd is invaild\n"); + return -EINVAL; + } + + if (ret != 0) + return ret; + + return count; +} + +static ssize_t vfio_pci_handle_mig_drv_version( + struct vfio_device_migration_info *mig_info, + char __user *buf, size_t count, bool iswrite) +{ + u32 version_id = mig_info->version_id; + + if (count != sizeof(version_id) || iswrite) + return -EINVAL; + + if (copy_to_user(buf, &version_id, count)) + return -EFAULT; + + return count; +} + +static ssize_t vfio_pci_handle_mig_data_rw( + struct vfio_pci_migration_data *data, + char __user *buf, size_t count, u64 pos, bool iswrite) +{ + struct vfio_device_migration_info *mig_ctl = data->mig_ctl; + void *data_addr = data->vf_data; + + if (count == 0) { + dev_err(&data->vf_dev->dev, "qemu operation data size error!\n"); + return -EINVAL; + } + + data_addr += pos - mig_ctl->data_offset; + if (iswrite) { + if (copy_from_user(data_addr, buf, count)) + return -EFAULT; + + mig_ctl->pending_bytes += count; + if (mig_ctl->pending_bytes > data->state_size) + return -EINVAL; + } else { + if (copy_to_user(buf, data_addr, count)) + return -EFAULT; + + if (mig_ctl->pending_bytes < count) + return -EINVAL; + + mig_ctl->pending_bytes -= count; + } + + return count; +} + +static ssize_t vfio_pci_dev_migrn_rw(struct vfio_pci_device *vdev, + char __user *buf, size_t count, loff_t *ppos, bool iswrite) +{ + unsigned int index = + VFIO_PCI_OFFSET_TO_INDEX(*ppos) - VFIO_PCI_NUM_REGIONS; + struct vfio_pci_migration_data *data = + (struct vfio_pci_migration_data *)vdev->region[index].data; + loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK; + struct vfio_device_migration_info *mig_ctl = data->mig_ctl; + int ret; + + if (pos >= vdev->region[index].size) + return -EINVAL; + + count = min(count, (size_t)(vdev->region[index].size - pos)); + if (pos >= VFIO_MIGRATION_REGION_DATA_OFFSET) + return vfio_pci_handle_mig_data_rw(data, + buf, count, pos, iswrite); + + switch (pos) { + case VFIO_DEVICE_MIGRATION_OFFSET(device_state): + ret = vfio_pci_handle_mig_dev_state(data, + buf, count, iswrite); + break; + case VFIO_DEVICE_MIGRATION_OFFSET(pending_bytes): + ret = vfio_pci_handle_mig_pending_bytes(mig_ctl, + buf, count, iswrite); + break; + case VFIO_DEVICE_MIGRATION_OFFSET(data_offset): + ret = vfio_pci_handle_mig_data_offset(mig_ctl, + buf, count, iswrite); + break; + case VFIO_DEVICE_MIGRATION_OFFSET(data_size): + ret = vfio_pci_handle_mig_data_size(mig_ctl, + buf, count, iswrite); + break; + case VFIO_DEVICE_MIGRATION_OFFSET(device_cmd): + ret = vfio_pci_handle_mig_dev_cmd(data, + buf, count, iswrite); + break; + case VFIO_DEVICE_MIGRATION_OFFSET(version_id): + ret = vfio_pci_handle_mig_drv_version(mig_ctl, + buf, count, iswrite); + break; + default: + dev_err(&vdev->pdev->dev, "invalid pos offset\n"); + ret = -EFAULT; + break; + } + + if (mig_ctl->device_state == VFIO_DEVICE_STATE_RESUMING && + mig_ctl->pending_bytes == data->state_size && + mig_ctl->data_size == data->state_size) { + if (vfio_pci_device_state_restore(data) != 0) { + dev_err(&vdev->pdev->dev, "Failed to restore device state!\n"); + return -EFAULT; + } + mig_ctl->pending_bytes = 0; + mig_ctl->data_size = 0; + } + + return ret; +} + +static void vfio_pci_dev_migrn_release(struct vfio_pci_device *vdev, + struct vfio_pci_region *region) +{ + struct vfio_pci_migration_data *data = region->data; + + if (data) { + kfree(data->mig_ctl); + kfree(data); + } +} + +static const struct vfio_pci_regops vfio_pci_migration_regops = { + .rw = vfio_pci_dev_migrn_rw, + .release = vfio_pci_dev_migrn_release, +}; + +static int vfio_pci_migration_info_init(struct pci_dev *pdev, + struct vfio_device_migration_info *mig_info, + struct vfio_pci_vendor_mig_driver *mig_drv) +{ + int ret; + + ret = vfio_pci_device_get_info(pdev, mig_info, mig_drv); + if (ret) { + dev_err(&pdev->dev, "failed to get device info\n"); + return ret; + } + + if (mig_info->data_size > VFIO_MIGRATION_BUFFER_MAX_SIZE) { + dev_err(&pdev->dev, "mig_info->data_size %llu is invalid\n", + mig_info->data_size); + return -EINVAL; + } + + mig_info->data_offset = VFIO_MIGRATION_REGION_DATA_OFFSET; + return ret; +} + +static int vfio_device_mig_data_init(struct vfio_pci_device *vdev, + struct vfio_pci_migration_data *data) +{ + struct vfio_device_migration_info *mig_ctl; + u64 mig_offset; + int ret; + + mig_ctl = kzalloc(sizeof(*mig_ctl), GFP_KERNEL); + if (!mig_ctl) + return -ENOMEM; + + ret = vfio_pci_migration_info_init(vdev->pdev, mig_ctl, + data->mig_driver); + if (ret) { + dev_err(&vdev->pdev->dev, "get device info error!\n"); + goto err; + } + + mig_offset = sizeof(struct vfio_device_migration_info); + data->state_size = mig_ctl->data_size; + data->mig_ctl = krealloc(mig_ctl, mig_offset + data->state_size, + GFP_KERNEL); + if (!data->mig_ctl) { + ret = -ENOMEM; + goto err; + } + + data->vf_data = (void *)((char *)data->mig_ctl + mig_offset); + memset(data->vf_data, 0, data->state_size); + data->mig_ctl->data_size = 0; + + ret = vfio_pci_register_dev_region(vdev, VFIO_REGION_TYPE_MIGRATION, + VFIO_REGION_SUBTYPE_MIGRATION, + &vfio_pci_migration_regops, mig_offset + data->state_size, + VFIO_REGION_INFO_FLAG_READ | VFIO_REGION_INFO_FLAG_WRITE, data); + if (ret) { + kfree(data->mig_ctl); + return ret; + } + + return 0; +err: + kfree(mig_ctl); + return ret; +} + +int vfio_pci_migration_init(struct vfio_pci_device *vdev) +{ + struct vfio_pci_vendor_mig_driver *mig_driver = NULL; + struct vfio_pci_migration_data *data = NULL; + struct pci_dev *pdev = vdev->pdev; + int ret; + + mig_driver = vfio_pci_get_mig_driver(pdev); + if (!mig_driver || !mig_driver->dev_mig_ops) { + dev_err(&pdev->dev, "unable to find a mig_driver module\n"); + return -EINVAL; + } + + if (!try_module_get(mig_driver->owner)) { + pr_err("module %s is not live\n", mig_driver->owner->name); + return -ENODEV; + } + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) { + module_put(mig_driver->owner); + return -ENOMEM; + } + + data->mig_driver = mig_driver; + data->vf_dev = pdev; + + ret = vfio_device_mig_data_init(vdev, data); + if (ret) { + dev_err(&pdev->dev, "failed to init vfio device migration data!\n"); + goto err; + } + + return ret; +err: + kfree(data); + module_put(mig_driver->owner); + return ret; +} + +void vfio_pci_migration_exit(struct vfio_pci_device *vdev) +{ + struct vfio_pci_vendor_mig_driver *mig_driver = NULL; + + mig_driver = vfio_pci_get_mig_driver(vdev->pdev); + if (!mig_driver || !mig_driver->dev_mig_ops) { + dev_warn(&vdev->pdev->dev, "mig_driver is not found\n"); + return; + } + + if (module_refcount(mig_driver->owner) > 0) { + vfio_pci_device_release(vdev->pdev, mig_driver); + module_put(mig_driver->owner); + } +} + +int vfio_pci_register_migration_ops(struct vfio_device_migration_ops *ops, + struct module *mod, struct pci_dev *pdev) +{ + struct vfio_pci_vendor_mig_driver *mig_driver = NULL; + + if (!ops || !mod || !pdev) + return -EINVAL; + + mig_driver = vfio_pci_find_mig_drv(pdev, mod); + if (mig_driver) { + pr_info("%s migration ops has already been registered\n", + mod->name); + atomic_add(1, &mig_driver->count); + return 0; + } + + if (!try_module_get(THIS_MODULE)) + return -ENODEV; + + mig_driver = kzalloc(sizeof(*mig_driver), GFP_KERNEL); + if (!mig_driver) { + module_put(THIS_MODULE); + return -ENOMEM; + } + + mig_driver->pdev = pdev; + mig_driver->bus_num = pdev->bus->number; + mig_driver->owner = mod; + mig_driver->dev_mig_ops = ops; + + vfio_pci_add_mig_drv(mig_driver); + + return 0; +} +EXPORT_SYMBOL_GPL(vfio_pci_register_migration_ops); + +void vfio_pci_unregister_migration_ops(struct module *mod, struct pci_dev *pdev) +{ + struct vfio_pci_vendor_mig_driver *mig_driver = NULL; + + if (!mod || !pdev) + return; + + mig_driver = vfio_pci_find_mig_drv(pdev, mod); + if (!mig_driver) { + pr_err("mig_driver is not found\n"); + return; + } + + if (atomic_sub_and_test(1, &mig_driver->count)) { + vfio_pci_remove_mig_drv(mig_driver); + kfree(mig_driver); + module_put(THIS_MODULE); + pr_info("%s succeed to unregister migration ops\n", + THIS_MODULE->name); + } +} +EXPORT_SYMBOL_GPL(vfio_pci_unregister_migration_ops); diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h index 17d2bae..03af269 100644 --- a/drivers/vfio/pci/vfio_pci_private.h +++ b/drivers/vfio/pci/vfio_pci_private.h @@ -15,6 +15,7 @@ #include <linux/pci.h> #include <linux/irqbypass.h> #include <linux/types.h> +#include <linux/vfio_pci_migration.h> #ifndef VFIO_PCI_PRIVATE_H #define VFIO_PCI_PRIVATE_H @@ -55,7 +56,7 @@ struct vfio_pci_irq_ctx { struct vfio_pci_region; struct vfio_pci_regops { - size_t (*rw)(struct vfio_pci_device *vdev, char __user *buf, + ssize_t (*rw)(struct vfio_pci_device *vdev, char __user *buf, size_t count, loff_t *ppos, bool iswrite); void (*release)(struct vfio_pci_device *vdev, struct vfio_pci_region *region); @@ -173,4 +174,15 @@ static inline int vfio_pci_igd_init(struct vfio_pci_device *vdev) return -ENODEV; } #endif + +extern bool vfio_dev_migration_is_supported(struct pci_dev *pdev); +extern int vfio_pci_migration_init(struct vfio_pci_device *vdev); +extern void vfio_pci_migration_exit(struct vfio_pci_device *vdev); +extern int vfio_pci_device_log_start(struct vfio_pci_device *vdev, + struct vf_migration_log_info *log_info); +extern int vfio_pci_device_log_stop(struct vfio_pci_device *vdev, + uint32_t uuid); +extern int vfio_pci_device_log_status_query(struct vfio_pci_device *vdev); +extern int vfio_pci_device_init(struct pci_dev *pdev); +extern void vfio_pci_device_uninit(struct pci_dev *pdev); #endif /* VFIO_PCI_PRIVATE_H */ diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 7a386fb..35f2a29 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -33,6 +33,7 @@ #include <linux/string.h> #include <linux/uaccess.h> #include <linux/vfio.h> +#include <linux/vfio_pci_migration.h> #include <linux/wait.h> #include <linux/sched/signal.h> @@ -40,6 +41,9 @@ #define DRIVER_AUTHOR "Alex Williamson <alex.williamson(a)redhat.com>" #define DRIVER_DESC "VFIO - User Level meta-driver" +#define LOG_BUF_FRAG_SIZE (2 * 1024 * 1024) // fix to 2M +#define LOG_BUF_MAX_ADDRS_SIZE 128 // max vm ram size is 1T + static struct vfio { struct class *class; struct list_head iommu_drivers_list; @@ -57,6 +61,14 @@ struct vfio_iommu_driver { struct list_head vfio_next; }; +struct vfio_log_buf { + struct vfio_log_buf_info info; + int fd; + int buffer_state; + int device_state; + unsigned long *cpu_addrs; +}; + struct vfio_container { struct kref kref; struct list_head group_list; @@ -64,6 +76,7 @@ struct vfio_container { struct vfio_iommu_driver *iommu_driver; void *iommu_data; bool noiommu; + struct vfio_log_buf log_buf; }; struct vfio_unbound_dev { @@ -1158,8 +1171,398 @@ static long vfio_ioctl_set_iommu(struct vfio_container *container, return ret; } +static long vfio_dispatch_cmd_to_devices(const struct vfio_container *container, + unsigned int cmd, unsigned long arg) +{ + struct vfio_group *group = NULL; + struct vfio_device *device = NULL; + long ret = -ENXIO; + + list_for_each_entry(group, &container->group_list, container_next) { + list_for_each_entry(device, &group->device_list, group_next) { + ret = device->ops->ioctl(device->device_data, cmd, arg); + if (ret) { + pr_err("dispatch cmd to devices failed\n"); + return ret; + } + } + } + return ret; +} + +static long vfio_log_buf_start(struct vfio_container *container) +{ + struct vfio_log_buf_ctl log_buf_ctl; + long ret; + + log_buf_ctl.argsz = sizeof(struct vfio_log_buf_info); + log_buf_ctl.flags = VFIO_DEVICE_LOG_BUF_FLAG_START; + log_buf_ctl.data = (void *)&container->log_buf.info; + ret = vfio_dispatch_cmd_to_devices(container, VFIO_DEVICE_LOG_BUF_CTL, + (unsigned long)&log_buf_ctl); + if (ret) + return ret; + + container->log_buf.device_state = 1; + return 0; +} + +static long vfio_log_buf_stop(struct vfio_container *container) +{ + struct vfio_log_buf_ctl log_buf_ctl; + long ret; + + if (container->log_buf.device_state == 0) { + pr_warn("device already stopped\n"); + return 0; + } + + log_buf_ctl.argsz = sizeof(struct vfio_log_buf_info); + log_buf_ctl.flags = VFIO_DEVICE_LOG_BUF_FLAG_STOP; + log_buf_ctl.data = (void *)&container->log_buf.info; + ret = vfio_dispatch_cmd_to_devices(container, VFIO_DEVICE_LOG_BUF_CTL, + (unsigned long)&log_buf_ctl); + if (ret) + return ret; + + container->log_buf.device_state = 0; + return 0; +} + +static long vfio_log_buf_query(struct vfio_container *container) +{ + struct vfio_log_buf_ctl log_buf_ctl; + + log_buf_ctl.argsz = sizeof(struct vfio_log_buf_info); + log_buf_ctl.flags = VFIO_DEVICE_LOG_BUF_FLAG_STATUS_QUERY; + log_buf_ctl.data = (void *)&container->log_buf.info; + + return vfio_dispatch_cmd_to_devices(container, + VFIO_DEVICE_LOG_BUF_CTL, (unsigned long)&log_buf_ctl); +} + +static int vfio_log_buf_fops_mmap(struct file *filep, + struct vm_area_struct *vma) +{ + struct vfio_container *container = filep->private_data; + struct vfio_log_buf *log_buf = &container->log_buf; + unsigned long frag_pg_size; + unsigned long frag_offset; + phys_addr_t pa; + int ret = -EINVAL; + + if (!log_buf->cpu_addrs) { + pr_err("mmap before setup, please setup log buf first\n"); + return ret; + } + + if (log_buf->info.frag_size < PAGE_SIZE) { + pr_err("mmap frag size should not less than page size!\n"); + return ret; + } + + frag_pg_size = log_buf->info.frag_size / PAGE_SIZE; + frag_offset = vma->vm_pgoff / frag_pg_size; + + if (frag_offset >= log_buf->info.addrs_size) { + pr_err("mmap offset out of range!\n"); + return ret; + } + + if (vma->vm_end - vma->vm_start != log_buf->info.frag_size) { + pr_err("mmap size error, should be aligned with frag size!\n"); + return ret; + } + + pa = virt_to_phys((void *)log_buf->cpu_addrs[frag_offset]); + ret = remap_pfn_range(vma, vma->vm_start, + pa >> PAGE_SHIFT, + vma->vm_end - vma->vm_start, + vma->vm_page_prot); + if (ret) + pr_err("remap_pfn_range error!\n"); + return ret; +} + +static struct device *vfio_get_dev(struct vfio_container *container) +{ + struct vfio_group *group = NULL; + struct vfio_device *device = NULL; + + list_for_each_entry(group, &container->group_list, container_next) { + list_for_each_entry(device, &group->device_list, group_next) { + return device->dev; + } + } + return NULL; +} + +static void vfio_log_buf_release_dma(struct device *dev, + struct vfio_log_buf *log_buf) +{ + int i; + + for (i = 0; i < log_buf->info.addrs_size; i++) { + if ((log_buf->cpu_addrs && log_buf->cpu_addrs[i] != 0) && + (log_buf->info.sgevec && + log_buf->info.sgevec[i].addr != 0)) { + dma_free_coherent(dev, log_buf->info.frag_size, + (void *)log_buf->cpu_addrs[i], + log_buf->info.sgevec[i].addr); + log_buf->cpu_addrs[i] = 0; + log_buf->info.sgevec[i].addr = 0; + } + } +} + +static long vfio_log_buf_alloc_dma(struct vfio_log_buf_info *info, + struct vfio_log_buf *log_buf, struct device *dev) +{ + int i; + + for (i = 0; i < info->addrs_size; i++) { + log_buf->cpu_addrs[i] = (unsigned long)dma_alloc_coherent(dev, + info->frag_size, &log_buf->info.sgevec[i].addr, + GFP_KERNEL); + log_buf->info.sgevec[i].len = info->frag_size; + if (log_buf->cpu_addrs[i] == 0 || + log_buf->info.sgevec[i].addr == 0) { + return -ENOMEM; + } + } + return 0; +} + +static long vfio_log_buf_alloc_addrs(struct vfio_log_buf_info *info, + struct vfio_log_buf *log_buf) +{ + log_buf->info.sgevec = kcalloc(info->addrs_size, + sizeof(struct vfio_log_buf_sge), GFP_KERNEL); + if (!log_buf->info.sgevec) + return -ENOMEM; + + log_buf->cpu_addrs = kcalloc(info->addrs_size, + sizeof(unsigned long), GFP_KERNEL); + if (!log_buf->cpu_addrs) { + kfree(log_buf->info.sgevec); + log_buf->info.sgevec = NULL; + return -ENOMEM; + } + + return 0; +} + +static long vfio_log_buf_info_valid(struct vfio_log_buf_info *info) +{ + if (info->addrs_size > LOG_BUF_MAX_ADDRS_SIZE || + info->addrs_size == 0) { + pr_err("can`t support vm ram size larger than 1T or equal to 0\n"); + return -EINVAL; + } + if (info->frag_size != LOG_BUF_FRAG_SIZE) { + pr_err("only support %d frag size\n", LOG_BUF_FRAG_SIZE); + return -EINVAL; + } + return 0; +} + +static long vfio_log_buf_setup(struct vfio_container *container, + unsigned long data) +{ + struct vfio_log_buf_info info; + struct vfio_log_buf *log_buf = &container->log_buf; + struct device *dev = NULL; + long ret; + + if (log_buf->info.sgevec) { + pr_warn("log buf already setup\n"); + return 0; + } + + if (copy_from_user(&info, (void __user *)data, + sizeof(struct vfio_log_buf_info))) + return -EFAULT; + + ret = vfio_log_buf_info_valid(&info); + if (ret) + return ret; + + ret = vfio_log_buf_alloc_addrs(&info, log_buf); + if (ret) + goto err_out; + + dev = vfio_get_dev(container); + if (!dev) { + pr_err("can`t get dev\n"); + goto err_free_addrs; + } + + ret = vfio_log_buf_alloc_dma(&info, log_buf, dev); + if (ret) + goto err_free_dma_array; + + log_buf->info.uuid = info.uuid; + log_buf->info.buffer_size = info.buffer_size; + log_buf->info.frag_size = info.frag_size; + log_buf->info.addrs_size = info.addrs_size; + log_buf->buffer_state = 1; + return 0; + +err_free_dma_array: + vfio_log_buf_release_dma(dev, log_buf); +err_free_addrs: + kfree(log_buf->cpu_addrs); + log_buf->cpu_addrs = NULL; + kfree(log_buf->info.sgevec); + log_buf->info.sgevec = NULL; +err_out: + return -ENOMEM; +} + +static long vfio_log_buf_release_buffer(struct vfio_container *container) +{ + struct vfio_log_buf *log_buf = &container->log_buf; + struct device *dev = NULL; + + if (log_buf->buffer_state == 0) { + pr_warn("buffer already released\n"); + return 0; + } + + dev = vfio_get_dev(container); + if (!dev) { + pr_err("can`t get dev\n"); + return -EFAULT; + } + + vfio_log_buf_release_dma(dev, log_buf); + + kfree(log_buf->cpu_addrs); + log_buf->cpu_addrs = NULL; + + kfree(log_buf->info.sgevec); + log_buf->info.sgevec = NULL; + + log_buf->buffer_state = 0; + return 0; +} + +static int vfio_log_buf_release(struct inode *inode, struct file *filep) +{ + struct vfio_container *container = filep->private_data; + + vfio_log_buf_stop(container); + vfio_log_buf_release_buffer(container); + memset(&container->log_buf, 0, sizeof(struct vfio_log_buf)); + return 0; +} + +static long vfio_ioctl_handle_log_buf_ctl(struct vfio_container *container, + unsigned long arg) +{ + struct vfio_log_buf_ctl log_buf_ctl; + long ret = 0; + + if (copy_from_user(&log_buf_ctl, (void __user *)arg, + sizeof(struct vfio_log_buf_ctl))) + return -EFAULT; + + switch (log_buf_ctl.flags) { + case VFIO_DEVICE_LOG_BUF_FLAG_SETUP: + ret = vfio_log_buf_setup(container, + (unsigned long)log_buf_ctl.data); + break; + case VFIO_DEVICE_LOG_BUF_FLAG_RELEASE: + ret = vfio_log_buf_release_buffer(container); + break; + case VFIO_DEVICE_LOG_BUF_FLAG_START: + ret = vfio_log_buf_start(container); + break; + case VFIO_DEVICE_LOG_BUF_FLAG_STOP: + ret = vfio_log_buf_stop(container); + break; + case VFIO_DEVICE_LOG_BUF_FLAG_STATUS_QUERY: + ret = vfio_log_buf_query(container); + break; + default: + pr_err("log buf control flag incorrect\n"); + ret = -EINVAL; + break; + } + return ret; +} + +static long vfio_log_buf_fops_unl_ioctl(struct file *filep, + unsigned int cmd, unsigned long arg) +{ + struct vfio_container *container = filep->private_data; + long ret = -EINVAL; + + switch (cmd) { + case VFIO_LOG_BUF_CTL: + ret = vfio_ioctl_handle_log_buf_ctl(container, arg); + break; + default: + pr_err("log buf control cmd incorrect\n"); + break; + } + + return ret; +} + +#ifdef CONFIG_COMPAT +static long vfio_log_buf_fops_compat_ioctl(struct file *filep, + unsigned int cmd, unsigned long arg) +{ + arg = (unsigned long)compat_ptr(arg); + return vfio_log_buf_fops_unl_ioctl(filep, cmd, arg); +} +#endif /* CONFIG_COMPAT */ + +static const struct file_operations vfio_log_buf_fops = { + .owner = THIS_MODULE, + .mmap = vfio_log_buf_fops_mmap, + .unlocked_ioctl = vfio_log_buf_fops_unl_ioctl, + .release = vfio_log_buf_release, +#ifdef CONFIG_COMPAT + .compat_ioctl = vfio_log_buf_fops_compat_ioctl, +#endif +}; + +static int vfio_get_log_buf_fd(struct vfio_container *container, + unsigned long arg) +{ + struct file *filep = NULL; + int ret; + + if (container->log_buf.fd > 0) + return container->log_buf.fd; + + ret = get_unused_fd_flags(O_CLOEXEC); + if (ret < 0) { + pr_err("get_unused_fd_flags get fd failed\n"); + return ret; + } + + filep = anon_inode_getfile("[vfio-log-buf]", &vfio_log_buf_fops, + container, O_RDWR); + if (IS_ERR(filep)) { + pr_err("anon_inode_getfile failed\n"); + put_unused_fd(ret); + ret = PTR_ERR(filep); + return ret; + } + + filep->f_mode |= (FMODE_READ | FMODE_WRITE | FMODE_LSEEK); + + fd_install(ret, filep); + + container->log_buf.fd = ret; + return ret; +} + static long vfio_fops_unl_ioctl(struct file *filep, - unsigned int cmd, unsigned long arg) + unsigned int cmd, unsigned long arg) { struct vfio_container *container = filep->private_data; struct vfio_iommu_driver *driver; @@ -1179,6 +1582,9 @@ static long vfio_fops_unl_ioctl(struct file *filep, case VFIO_SET_IOMMU: ret = vfio_ioctl_set_iommu(container, arg); break; + case VFIO_GET_LOG_BUF_FD: + ret = vfio_get_log_buf_fd(container, arg); + break; default: driver = container->iommu_driver; data = container->iommu_data; @@ -1210,6 +1616,7 @@ static int vfio_fops_open(struct inode *inode, struct file *filep) INIT_LIST_HEAD(&container->group_list); init_rwsem(&container->group_lock); kref_init(&container->kref); + memset(&container->log_buf, 0, sizeof(struct vfio_log_buf)); filep->private_data = container; @@ -1219,9 +1626,7 @@ static int vfio_fops_open(struct inode *inode, struct file *filep) static int vfio_fops_release(struct inode *inode, struct file *filep) { struct vfio_container *container = filep->private_data; - filep->private_data = NULL; - vfio_container_put(container); return 0; diff --git a/include/linux/vfio_pci_migration.h b/include/linux/vfio_pci_migration.h new file mode 100644 index 0000000..464ffb4 --- /dev/null +++ b/include/linux/vfio_pci_migration.h @@ -0,0 +1,136 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2022 Huawei Technologies Co., Ltd. All rights reserved. + */ + +#ifndef VFIO_PCI_MIGRATION_H +#define VFIO_PCI_MIGRATION_H + +#include <linux/types.h> +#include <linux/pci.h> + +#define VFIO_REGION_TYPE_MIGRATION (3) +/* sub-types for VFIO_REGION_TYPE_MIGRATION */ +#define VFIO_REGION_SUBTYPE_MIGRATION (1) + +#define VFIO_MIGRATION_BUFFER_MAX_SIZE SZ_256K +#define VFIO_MIGRATION_REGION_DATA_OFFSET \ + (sizeof(struct vfio_device_migration_info)) +#define VFIO_DEVICE_MIGRATION_OFFSET(x) \ + offsetof(struct vfio_device_migration_info, x) + +struct vfio_device_migration_info { + __u32 device_state; /* VFIO device state */ +#define VFIO_DEVICE_STATE_STOP (0) +#define VFIO_DEVICE_STATE_RUNNING (1 << 0) +#define VFIO_DEVICE_STATE_SAVING (1 << 1) +#define VFIO_DEVICE_STATE_RESUMING (1 << 2) +#define VFIO_DEVICE_STATE_MASK (VFIO_DEVICE_STATE_RUNNING | \ + VFIO_DEVICE_STATE_SAVING | VFIO_DEVICE_STATE_RESUMING) + __u32 reserved; + + __u32 device_cmd; + __u32 version_id; + + __u64 pending_bytes; + __u64 data_offset; + __u64 data_size; +}; + +enum { + VFIO_DEVICE_STOP = 0xffff0001, + VFIO_DEVICE_CONTINUE, + VFIO_DEVICE_MIGRATION_CANCEL, +}; + +struct vfio_log_buf_sge { + __u64 len; + __u64 addr; +}; + +struct vfio_log_buf_info { + __u32 uuid; + __u64 buffer_size; + __u64 addrs_size; + __u64 frag_size; + struct vfio_log_buf_sge *sgevec; +}; + +struct vfio_log_buf_ctl { + __u32 argsz; + __u32 flags; + #define VFIO_DEVICE_LOG_BUF_FLAG_SETUP (1 << 0) + #define VFIO_DEVICE_LOG_BUF_FLAG_RELEASE (1 << 1) + #define VFIO_DEVICE_LOG_BUF_FLAG_START (1 << 2) + #define VFIO_DEVICE_LOG_BUF_FLAG_STOP (1 << 3) + #define VFIO_DEVICE_LOG_BUF_FLAG_STATUS_QUERY (1 << 4) + void *data; +}; +#define VFIO_LOG_BUF_CTL _IO(VFIO_TYPE, VFIO_BASE + 21) +#define VFIO_GET_LOG_BUF_FD _IO(VFIO_TYPE, VFIO_BASE + 22) +#define VFIO_DEVICE_LOG_BUF_CTL _IO(VFIO_TYPE, VFIO_BASE + 23) + +struct vf_migration_log_info { + __u32 dom_uuid; + __u64 buffer_size; + __u64 sge_len; + __u64 sge_num; + struct vfio_log_buf_sge *sgevec; +}; + +struct vfio_device_migration_ops { + /* Get device information */ + int (*get_info)(struct pci_dev *pdev, + struct vfio_device_migration_info *info); + /* Enable a vf device */ + int (*enable)(struct pci_dev *pdev); + /* Disable a vf device */ + int (*disable)(struct pci_dev *pdev); + /* Save a vf device */ + int (*save)(struct pci_dev *pdev, void *base, + uint64_t off, uint64_t count); + /* Resuming a vf device */ + int (*restore)(struct pci_dev *pdev, void *base, + uint64_t off, uint64_t count); + /* Log start a vf device */ + int (*log_start)(struct pci_dev *pdev, + struct vf_migration_log_info *log_info); + /* Log stop a vf device */ + int (*log_stop)(struct pci_dev *pdev, uint32_t uuid); + /* Get vf device log status */ + int (*get_log_status)(struct pci_dev *pdev); + /* Pre enable a vf device(load_setup, before restore a vf) */ + int (*pre_enable)(struct pci_dev *pdev); + /* Cancel a vf device when live migration failed (rollback) */ + int (*cancel)(struct pci_dev *pdev); + /* Init a vf device */ + int (*init)(struct pci_dev *pdev); + /* Uninit a vf device */ + void (*uninit)(struct pci_dev *pdev); + /* Release a vf device */ + void (*release)(struct pci_dev *pdev); +}; + +struct vfio_pci_vendor_mig_driver { + struct pci_dev *pdev; + unsigned char bus_num; + struct vfio_device_migration_ops *dev_mig_ops; + struct module *owner; + atomic_t count; + struct list_head list; +}; + +struct vfio_pci_migration_data { + u64 state_size; + struct pci_dev *vf_dev; + struct vfio_pci_vendor_mig_driver *mig_driver; + struct vfio_device_migration_info *mig_ctl; + void *vf_data; +}; + +int vfio_pci_register_migration_ops(struct vfio_device_migration_ops *ops, + struct module *mod, struct pci_dev *pdev); +void vfio_pci_unregister_migration_ops(struct module *mod, + struct pci_dev *pdev); + +#endif /* VFIO_PCI_MIGRATION_H */ -- 1.8.3.1

3 2

[PATCH openEuler-1.0-LTS 1/4] alinux: sched: Defend cfs and rt bandwidth against overflow
by liuzhengyuan＠kylinos.cn 30 Jun '22

30 Jun '22

From: Huaixin Chang <changhuaixin(a)linux.alibaba.com> anolis inclusion from anolis_master commit 9d168f216486333f24aa1b33706eddf3b13d7228 category: performance bugzilla: NA CVE: NA --------------------------- Kernel limitation on cpu.cfs_quota_us is insufficient. Some large numbers might cause overflow in to_ratio() calculation and produce unexpected results. For example, if we make two cpu cgroups and then write a reasonable value and a large value into child's and parent's cpu.cfs_quota_us. This will cause a write error. cd /sys/fs/cgroup/cpu mkdir parent; mkdir parent/child echo 8000 > parent/child/cpu.cfs_quota_us # 17592186044416 is (1UL << 44) echo 17592186044416 > parent/cpu.cfs_quota_us In this case, quota will overflow and thus fail the __cfs_schedulable check. Similar overflow also affects rt bandwidth. Burstable CFS bandwidth controller will also benefit from limiting quota. Change-Id: I0f89d1f26b168c5cfa041e886395c7f3068114ae Reviewed-by: Shanpei Chen <shanpeic(a)linux.alibaba.com> Signed-off-by: Huaixin Chang <changhuaixin(a)linux.alibaba.com> Signed-off-by: Zhengyuan Liu <liuzhengyuan(a)kylinos.cn> --- kernel/sched/core.c | 8 ++++++++ kernel/sched/rt.c | 9 +++++++++ kernel/sched/sched.h | 2 ++ 3 files changed, 19 insertions(+) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 36d7422da0ac..51fdd30f188a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6679,6 +6679,8 @@ static DEFINE_MUTEX(cfs_constraints_mutex); const u64 max_cfs_quota_period = 1 * NSEC_PER_SEC; /* 1s */ const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */ +/* More than 203 days if BW_SHIFT equals 20. */ +const u64 max_cfs_runtime = MAX_BW_USEC * NSEC_PER_USEC; static int __cfs_schedulable(struct task_group *tg, u64 period, u64 runtime); @@ -6706,6 +6708,12 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota) if (period > max_cfs_quota_period) return -EINVAL; + /* + * Bound quota to defend quota against overflow during bandwidth shift. + */ + if (quota != RUNTIME_INF && quota > max_cfs_runtime) + return -EINVAL; + /* * Prevent race between setting of cfs_rq->runtime_enabled and * unthrottle_offline_cfs_rqs(). diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 301ba04d9130..f31e0aaf1f43 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -2518,6 +2518,9 @@ static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime) return ret; } +/* More than 203 days if BW_SHIFT equals 20. */ +static const u64 max_rt_runtime = MAX_BW_USEC * NSEC_PER_USEC; + static int tg_set_rt_bandwidth(struct task_group *tg, u64 rt_period, u64 rt_runtime) { @@ -2534,6 +2537,12 @@ static int tg_set_rt_bandwidth(struct task_group *tg, if (rt_period == 0) return -EINVAL; + /* + * Bound quota to defend quota against overflow during bandwidth shift. + */ + if (rt_runtime != RUNTIME_INF && rt_runtime > max_rt_runtime) + return -EINVAL; + mutex_lock(&rt_constraints_mutex); read_lock(&tasklist_lock); err = __rt_schedulable(tg, rt_period, rt_runtime); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index ae3068153093..f3808a49ce48 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1732,6 +1732,8 @@ extern void init_dl_rq_bw_ratio(struct dl_rq *dl_rq); #define BW_SHIFT 20 #define BW_UNIT (1 << BW_SHIFT) #define RATIO_SHIFT 8 +#define MAX_BW_BITS (64 - BW_SHIFT) +#define MAX_BW_USEC ((1UL << MAX_BW_BITS) - 1) unsigned long to_ratio(u64 period, u64 runtime); extern void init_entity_runnable_average(struct sched_entity *se); -- 2.25.1

3 6

[PATCH openEuler-1.0-LTS 01/14] mm/sharepool: Delete single-group mode
by Yongqiang Liu 29 Jun '22

29 Jun '22

From: Zhou Guanghui <zhouguanghui1(a)huawei.com> hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I5EORS CVE: NA -------------------------------- The single-group mode has no application scenario. Therefore, the related branch is deleted. The boot option "enable_sp_multi_group_mode" does not take effect. Signed-off-by: Zhou Guanghui <zhouguanghui1(a)huawei.com> Reviewed-by: Weilong Chen <chenweilong(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- mm/share_pool.c | 137 +++++++++--------------------------------------- 1 file changed, 25 insertions(+), 112 deletions(-) diff --git a/mm/share_pool.c b/mm/share_pool.c index 5ba353ddfabd..48e309e3ddd3 100644 --- a/mm/share_pool.c +++ b/mm/share_pool.c @@ -65,9 +65,6 @@ #define byte2mb(size) ((size) >> 20) #define page2kb(page_num) ((page_num) << (PAGE_SHIFT - 10)) -#define SINGLE_GROUP_MODE 1 -#define MULTI_GROUP_MODE 2 - #define MAX_GROUP_FOR_SYSTEM 50000 #define MAX_GROUP_FOR_TASK 3000 #define MAX_PROC_PER_GROUP 1024 @@ -98,8 +95,6 @@ int sysctl_sp_perf_alloc; int sysctl_sp_perf_k2u; -static int share_pool_group_mode = SINGLE_GROUP_MODE; - static int system_group_count; static unsigned int sp_device_number; @@ -1088,12 +1083,6 @@ static int mm_add_group_init(struct mm_struct *mm, struct sp_group *spg) struct sp_group_master *master = mm->sp_group_master; bool exist = false; - if (share_pool_group_mode == SINGLE_GROUP_MODE && master && - master->count == 1) { - pr_err_ratelimited("at most one sp group for a task is allowed in single mode\n"); - return -EEXIST; - } - master = sp_init_group_master_locked(mm, &exist); if (IS_ERR(master)) return PTR_ERR(master); @@ -2235,72 +2224,30 @@ static int sp_alloc_prepare(unsigned long size, unsigned long sp_flags, if (sp_flags & SP_HUGEPAGE_ONLY) sp_flags |= SP_HUGEPAGE; - if (share_pool_group_mode == SINGLE_GROUP_MODE) { - spg = __sp_find_spg(current->pid, SPG_ID_DEFAULT); - if (spg) { - if (spg_id != SPG_ID_DEFAULT && spg->id != spg_id) { - sp_group_drop(spg); - return -ENODEV; - } - - /* up_read will be at the end of sp_alloc */ - down_read(&spg->rw_lock); - if (!spg_valid(spg)) { - up_read(&spg->rw_lock); - sp_group_drop(spg); - pr_err_ratelimited("allocation failed, spg is dead\n"); - return -ENODEV; - } - } else { /* alocation pass through scene */ - if (enable_mdc_default_group) { - int ret = 0; - - ret = sp_group_add_task(current->tgid, spg_id); - if (ret < 0) { - pr_err_ratelimited("add group failed in pass through\n"); - return ret; - } - - spg = __sp_find_spg(current->pid, SPG_ID_DEFAULT); - - /* up_read will be at the end of sp_alloc */ - down_read(&spg->rw_lock); - if (!spg_valid(spg)) { - up_read(&spg->rw_lock); - sp_group_drop(spg); - pr_err_ratelimited("pass through allocation failed, spg is dead\n"); - return -ENODEV; - } - } else { - spg = spg_none; - } + if (spg_id != SPG_ID_DEFAULT) { + spg = __sp_find_spg(current->pid, spg_id); + if (!spg) { + pr_err_ratelimited("allocation failed, can't find group\n"); + return -ENODEV; } - } else { - if (spg_id != SPG_ID_DEFAULT) { - spg = __sp_find_spg(current->pid, spg_id); - if (!spg) { - pr_err_ratelimited("allocation failed, can't find group\n"); - return -ENODEV; - } - /* up_read will be at the end of sp_alloc */ - down_read(&spg->rw_lock); - if (!spg_valid(spg)) { - up_read(&spg->rw_lock); - sp_group_drop(spg); - pr_err_ratelimited("allocation failed, spg is dead\n"); - return -ENODEV; - } + /* up_read will be at the end of sp_alloc */ + down_read(&spg->rw_lock); + if (!spg_valid(spg)) { + up_read(&spg->rw_lock); + sp_group_drop(spg); + pr_err_ratelimited("allocation failed, spg is dead\n"); + return -ENODEV; + } - if (!is_process_in_group(spg, current->mm)) { - up_read(&spg->rw_lock); - sp_group_drop(spg); - pr_err_ratelimited("allocation failed, task not in group\n"); - return -ENODEV; - } - } else { /* alocation pass through scene */ - spg = spg_none; + if (!is_process_in_group(spg, current->mm)) { + up_read(&spg->rw_lock); + sp_group_drop(spg); + pr_err_ratelimited("allocation failed, task not in group\n"); + return -ENODEV; } + } else { /* alocation pass through scene */ + spg = spg_none; } if (sp_flags & SP_HUGEPAGE) { @@ -2914,33 +2861,12 @@ static int sp_k2u_prepare(unsigned long kva, unsigned long size, kc->size_aligned = size_aligned; kc->sp_flags = sp_flags; kc->spg_id = spg_id; - kc->to_task = false; - return 0; -} - -static int sp_check_k2task(struct sp_k2u_context *kc) -{ - int ret = 0; - int spg_id = kc->spg_id; - - if (share_pool_group_mode == SINGLE_GROUP_MODE) { - struct sp_group *spg = get_first_group(current->mm); + if (spg_id == SPG_ID_DEFAULT || spg_id == SPG_ID_NONE) + kc->to_task = true; + else + kc->to_task = false; - if (!spg) { - if (spg_id != SPG_ID_NONE && spg_id != SPG_ID_DEFAULT) - ret = -EINVAL; - else - kc->to_task = true; - } else { - if (spg_id != SPG_ID_DEFAULT && spg_id != spg->id) - ret = -EINVAL; - sp_group_drop(spg); - } - } else { - if (spg_id == SPG_ID_DEFAULT || spg_id == SPG_ID_NONE) - kc->to_task = true; - } - return ret; + return 0; } static void *sp_k2u_finish(void *uva, struct sp_k2u_context *kc) @@ -2985,12 +2911,6 @@ void *sp_make_share_k2u(unsigned long kva, unsigned long size, if (ret) return ERR_PTR(ret); - ret = sp_check_k2task(&kc); - if (ret) { - uva = ERR_PTR(ret); - goto out; - } - if (kc.to_task) uva = sp_make_share_kva_to_task(kc.kva_aligned, kc.size_aligned, kc.sp_flags); else { @@ -3738,13 +3658,6 @@ static int __init enable_share_k2u_to_group(char *s) } __setup("enable_sp_share_k2u_spg", enable_share_k2u_to_group); -static int __init enable_sp_multi_group_mode(char *s) -{ - share_pool_group_mode = MULTI_GROUP_MODE; - return 1; -} -__setup("enable_sp_multi_group_mode", enable_sp_multi_group_mode); - /*** Statistical and maintenance functions ***/ static void free_process_spg_proc_stat(struct sp_proc_stat *proc_stat) -- 2.25.1

1 13

[PATCH openEuler-22.03-LTS 1/2] ipmi/watchdog: replace atomic_add() and atomic_sub()
by Miaohe Lin 29 Jun '22

29 Jun '22

From: Yejune Deng <yejune.deng(a)gmail.com> mainline inclusion from v5.11-rc1 commit a01a89b1db1066a6af23ae08b9a0c345b7966f0b category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5DVR9 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- atomic_inc() and atomic_dec() looks better Signed-off-by: Yejune Deng <yejune.deng(a)gmail.com> Message-Id: <1605511807-7135-1-git-send-email-yejune.deng(a)gmail.com> Signed-off-by: Corey Minyard <cminyard(a)mvista.com> Signed-off-by: Miaohe Lin <linmiaohe(a)huawei.com> --- drivers/char/ipmi/ipmi_watchdog.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c index f78156d93c3f..32c334e34d55 100644 --- a/drivers/char/ipmi/ipmi_watchdog.c +++ b/drivers/char/ipmi/ipmi_watchdog.c @@ -495,7 +495,7 @@ static void panic_halt_ipmi_heartbeat(void) msg.cmd = IPMI_WDOG_RESET_TIMER; msg.data = NULL; msg.data_len = 0; - atomic_add(1, &panic_done_count); + atomic_inc(&panic_done_count); rv = ipmi_request_supply_msgs(watchdog_user, (struct ipmi_addr *) &addr, 0, @@ -505,7 +505,7 @@ static void panic_halt_ipmi_heartbeat(void) &panic_halt_heartbeat_recv_msg, 1); if (rv) - atomic_sub(1, &panic_done_count); + atomic_dec(&panic_done_count); } static struct ipmi_smi_msg panic_halt_smi_msg = { @@ -529,12 +529,12 @@ static void panic_halt_ipmi_set_timeout(void) /* Wait for the messages to be free. */ while (atomic_read(&panic_done_count) != 0) ipmi_poll_interface(watchdog_user); - atomic_add(1, &panic_done_count); + atomic_inc(&panic_done_count); rv = __ipmi_set_timeout(&panic_halt_smi_msg, &panic_halt_recv_msg, &send_heartbeat_now); if (rv) { - atomic_sub(1, &panic_done_count); + atomic_dec(&panic_done_count); pr_warn("Unable to extend the watchdog timeout\n"); } else { if (send_heartbeat_now) -- 2.23.0

1 1

[PATCH openEuler-5.10-LTS 1/8] net: hns3: set port base vlan tbl_sta to false before removing old vlan
by Zheng Zengkai 28 Jun '22

28 Jun '22

From: Guangbin Huang <huangguangbin2(a)huawei.com> mainline inclusion from mainline-v5.19-rc1 commit 9eda7d8bcbdb category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5DGNU CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ---------------------------------------------------------------------- When modify port base vlan, the port base vlan tbl_sta needs to set to false before removing old vlan, to indicate this operation is not finish. Fixes: c0f46de30c96 ("net: hns3: fix port base vlan add fail when concurrent with reset") Signed-off-by: Guangbin Huang <huangguangbin2(a)huawei.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Jiantao Xiao <xiaojiantao1(a)h-partners.com> Reviewed-by: Jian Shen <shenjian15(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 3e0d8388ad3f..57aaa2f1536f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -10117,6 +10117,7 @@ static int hclge_modify_port_base_vlan_tag(struct hclge_vport *vport, if (ret) return ret; + vport->port_base_vlan_cfg.tbl_sta = false; /* remove old VLAN tag */ if (old_info->vlan_tag == 0) ret = hclge_set_vf_vlan_common(hdev, vport->vport_id, -- 2.20.1

1 7

[PATCH OLK-5.10 v3 1/2] ipmi/watchdog: replace atomic_add() and atomic_sub()
by Miaohe Lin 28 Jun '22

28 Jun '22

From: Yejune Deng <yejune.deng(a)gmail.com> mainline inclusion from v5.11-rc1 commit a01a89b1db1066a6af23ae08b9a0c345b7966f0b category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5DVR9 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- atomic_inc() and atomic_dec() looks better Signed-off-by: Yejune Deng <yejune.deng(a)gmail.com> Message-Id: <1605511807-7135-1-git-send-email-yejune.deng(a)gmail.com> Signed-off-by: Corey Minyard <cminyard(a)mvista.com> Signed-off-by: Miaohe Lin <linmiaohe(a)huawei.com> --- drivers/char/ipmi/ipmi_watchdog.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c index f78156d93c3f..32c334e34d55 100644 --- a/drivers/char/ipmi/ipmi_watchdog.c +++ b/drivers/char/ipmi/ipmi_watchdog.c @@ -495,7 +495,7 @@ static void panic_halt_ipmi_heartbeat(void) msg.cmd = IPMI_WDOG_RESET_TIMER; msg.data = NULL; msg.data_len = 0; - atomic_add(1, &panic_done_count); + atomic_inc(&panic_done_count); rv = ipmi_request_supply_msgs(watchdog_user, (struct ipmi_addr *) &addr, 0, @@ -505,7 +505,7 @@ static void panic_halt_ipmi_heartbeat(void) &panic_halt_heartbeat_recv_msg, 1); if (rv) - atomic_sub(1, &panic_done_count); + atomic_dec(&panic_done_count); } static struct ipmi_smi_msg panic_halt_smi_msg = { @@ -529,12 +529,12 @@ static void panic_halt_ipmi_set_timeout(void) /* Wait for the messages to be free. */ while (atomic_read(&panic_done_count) != 0) ipmi_poll_interface(watchdog_user); - atomic_add(1, &panic_done_count); + atomic_inc(&panic_done_count); rv = __ipmi_set_timeout(&panic_halt_smi_msg, &panic_halt_recv_msg, &send_heartbeat_now); if (rv) { - atomic_sub(1, &panic_done_count); + atomic_dec(&panic_done_count); pr_warn("Unable to extend the watchdog timeout\n"); } else { if (send_heartbeat_now) -- 2.23.0

1 1

[PATCH openEuler-5.10 1/5] lockdown: also lock down previous kgdb use
by Zheng Zengkai 28 Jun '22

28 Jun '22

From: Daniel Thompson <daniel.thompson(a)linaro.org> from stable-v5.10.119 commit a8f4d63142f947cd22fa615b8b3b8921cdaf4991 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I5A5YP CVE: CVE-2022-21499 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… commit eadb2f47a3ced5c64b23b90fd2a3463f63726066 upstream. KGDB and KDB allow read and write access to kernel memory, and thus should be restricted during lockdown. An attacker with access to a serial port (for example, via a hypervisor console, which some cloud vendors provide over the network) could trigger the debugger so it is important that the debugger respect the lockdown mode when/if it is triggered. Fix this by integrating lockdown into kdb's existing permissions mechanism. Unfortunately kgdb does not have any permissions mechanism (although it certainly could be added later) so, for now, kgdb is simply and brutally disabled by immediately exiting the gdb stub without taking any action. For lockdowns established early in the boot (e.g. the normal case) then this should be fine but on systems where kgdb has set breakpoints before the lockdown is enacted than "bad things" will happen. CVE: CVE-2022-21499 Co-developed-by: Stephen Brennan <stephen.s.brennan(a)oracle.com> Signed-off-by: Stephen Brennan <stephen.s.brennan(a)oracle.com> Reviewed-by: Douglas Anderson <dianders(a)chromium.org> Signed-off-by: Daniel Thompson <daniel.thompson(a)linaro.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Zheng Yejian <zhengyejian1(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- include/linux/security.h | 2 ++ kernel/debug/debug_core.c | 24 ++++++++++++++ kernel/debug/kdb/kdb_main.c | 62 +++++++++++++++++++++++++++++++++++-- security/security.c | 2 ++ 4 files changed, 87 insertions(+), 3 deletions(-) diff --git a/include/linux/security.h b/include/linux/security.h index 35355429648e..330029ef7e89 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -121,10 +121,12 @@ enum lockdown_reason { LOCKDOWN_DEBUGFS, LOCKDOWN_XMON_WR, LOCKDOWN_BPF_WRITE_USER, + LOCKDOWN_DBG_WRITE_KERNEL, LOCKDOWN_INTEGRITY_MAX, LOCKDOWN_KCORE, LOCKDOWN_KPROBES, LOCKDOWN_BPF_READ, + LOCKDOWN_DBG_READ_KERNEL, LOCKDOWN_PERF, LOCKDOWN_TRACEFS, LOCKDOWN_XMON_RW, diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index be5b6b97adbf..363f781b56ca 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -56,6 +56,7 @@ #include <linux/vmacache.h> #include <linux/rcupdate.h> #include <linux/irq.h> +#include <linux/security.h> #include <asm/cacheflush.h> #include <asm/byteorder.h> @@ -762,6 +763,29 @@ static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs, continue; kgdb_connected = 0; } else { + /* + * This is a brutal way to interfere with the debugger + * and prevent gdb being used to poke at kernel memory. + * This could cause trouble if lockdown is applied when + * there is already an active gdb session. For now the + * answer is simply "don't do that". Typically lockdown + * *will* be applied before the debug core gets started + * so only developers using kgdb for fairly advanced + * early kernel debug can be biten by this. Hopefully + * they are sophisticated enough to take care of + * themselves, especially with help from the lockdown + * message printed on the console! + */ + if (security_locked_down(LOCKDOWN_DBG_WRITE_KERNEL)) { + if (IS_ENABLED(CONFIG_KGDB_KDB)) { + /* Switch back to kdb if possible... */ + dbg_kdb_mode = 1; + continue; + } else { + /* ... otherwise just bail */ + break; + } + } error = gdb_serial_stub(ks); } diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 930ac1b25ec7..4e09fab52faf 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -45,6 +45,7 @@ #include <linux/proc_fs.h> #include <linux/uaccess.h> #include <linux/slab.h> +#include <linux/security.h> #include "kdb_private.h" #undef MODULE_PARAM_PREFIX @@ -197,10 +198,62 @@ struct task_struct *kdb_curr_task(int cpu) } /* - * Check whether the flags of the current command and the permissions - * of the kdb console has allow a command to be run. + * Update the permissions flags (kdb_cmd_enabled) to match the + * current lockdown state. + * + * Within this function the calls to security_locked_down() are "lazy". We + * avoid calling them if the current value of kdb_cmd_enabled already excludes + * flags that might be subject to lockdown. Additionally we deliberately check + * the lockdown flags independently (even though read lockdown implies write + * lockdown) since that results in both simpler code and clearer messages to + * the user on first-time debugger entry. + * + * The permission masks during a read+write lockdown permits the following + * flags: INSPECT, SIGNAL, REBOOT (and ALWAYS_SAFE). + * + * The INSPECT commands are not blocked during lockdown because they are + * not arbitrary memory reads. INSPECT covers the backtrace family (sometimes + * forcing them to have no arguments) and lsmod. These commands do expose + * some kernel state but do not allow the developer seated at the console to + * choose what state is reported. SIGNAL and REBOOT should not be controversial, + * given these are allowed for root during lockdown already. + */ +static void kdb_check_for_lockdown(void) +{ + const int write_flags = KDB_ENABLE_MEM_WRITE | + KDB_ENABLE_REG_WRITE | + KDB_ENABLE_FLOW_CTRL; + const int read_flags = KDB_ENABLE_MEM_READ | + KDB_ENABLE_REG_READ; + + bool need_to_lockdown_write = false; + bool need_to_lockdown_read = false; + + if (kdb_cmd_enabled & (KDB_ENABLE_ALL | write_flags)) + need_to_lockdown_write = + security_locked_down(LOCKDOWN_DBG_WRITE_KERNEL); + + if (kdb_cmd_enabled & (KDB_ENABLE_ALL | read_flags)) + need_to_lockdown_read = + security_locked_down(LOCKDOWN_DBG_READ_KERNEL); + + /* De-compose KDB_ENABLE_ALL if required */ + if (need_to_lockdown_write || need_to_lockdown_read) + if (kdb_cmd_enabled & KDB_ENABLE_ALL) + kdb_cmd_enabled = KDB_ENABLE_MASK & ~KDB_ENABLE_ALL; + + if (need_to_lockdown_write) + kdb_cmd_enabled &= ~write_flags; + + if (need_to_lockdown_read) + kdb_cmd_enabled &= ~read_flags; +} + +/* + * Check whether the flags of the current command, the permissions of the kdb + * console and the lockdown state allow a command to be run. */ -static inline bool kdb_check_flags(kdb_cmdflags_t flags, int permissions, +static bool kdb_check_flags(kdb_cmdflags_t flags, int permissions, bool no_args) { /* permissions comes from userspace so needs massaging slightly */ @@ -1194,6 +1247,9 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs, kdb_curr_task(raw_smp_processor_id()); KDB_DEBUG_STATE("kdb_local 1", reason); + + kdb_check_for_lockdown(); + kdb_go_count = 0; if (reason == KDB_REASON_DEBUG) { /* special case below */ diff --git a/security/security.c b/security/security.c index 4fb58543eeb9..2fc40217d49d 100644 --- a/security/security.c +++ b/security/security.c @@ -59,10 +59,12 @@ const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX+1] = { [LOCKDOWN_DEBUGFS] = "debugfs access", [LOCKDOWN_XMON_WR] = "xmon write access", [LOCKDOWN_BPF_WRITE_USER] = "use of bpf to write user RAM", + [LOCKDOWN_DBG_WRITE_KERNEL] = "use of kgdb/kdb to write kernel RAM", [LOCKDOWN_INTEGRITY_MAX] = "integrity", [LOCKDOWN_KCORE] = "/proc/kcore access", [LOCKDOWN_KPROBES] = "use of kprobes", [LOCKDOWN_BPF_READ] = "use of bpf to read kernel RAM", + [LOCKDOWN_DBG_READ_KERNEL] = "use of kgdb/kdb to read kernel RAM", [LOCKDOWN_PERF] = "unsafe use of perf", [LOCKDOWN_TRACEFS] = "use of tracefs", [LOCKDOWN_XMON_RW] = "xmon read and write access", -- 2.20.1

1 4

[PATCH openEuler-5.10 00/31] Backport 5.10.109 LTS
by Zheng Zengkai 28 Jun '22

28 Jun '22

Backport 5.10.109 LTS patches from upstream nds32: fix access_ok() checks in get/put_user wcn36xx: Differentiate wcn3660 from wcn3620 tpm: use try_get_ops() in tpm-space.c mac80211: fix potential double free on mesh join rcu: Don't deboost before reporting expedited quiescent state Revert "ath: add support for special 0x0 regulatory domain" crypto: qat - disable registration of algorithms ACPI: video: Force backlight native for Clevo NL5xRU and NL5xNU ACPI: battery: Add device HID and quirk for Microsoft Surface Go 3 ACPI / x86: Work around broken XSDT on Advantech DAC-BJ01 board drivers: net: xgene: Fix regression in CRC stripping ALSA: pci: fix reading of swapped values from pcmreg in AC97 codec ALSA: cmipci: Restore aux vol on suspend/resume ALSA: usb-audio: Add mute TLV for playback volumes on RODE NT-USB ALSA: pcm: Add stream lock during PCM reset ioctl operations ALSA: pcm: Fix races among concurrent prealloc proc writes ALSA: pcm: Fix races among concurrent prepare and hw_params/hw_free calls ALSA: pcm: Fix races among concurrent read/write and buffer changes ALSA: pcm: Fix races among concurrent hw_params and hw_free calls ALSA: hda/realtek: Add quirk for ASUS GA402 ALSA: hda/realtek - Fix headset mic problem for a HP machine with alc671 ALSA: hda/realtek: Add quirk for Clevo NP50PNJ ALSA: hda/realtek: Add quirk for Clevo NP70PNJ ALSA: usb-audio: add mapping for new Corsair Virtuoso SE ALSA: oss: Fix PCM OSS buffer allocation overflow ASoC: sti: Fix deadlock via snd_pcm_stop_xrun() call staging: fbtft: fb_st7789v: reset display before initialization tpm: Fix error handling in async work cgroup-v1: Correct privileges check in release_agent writes exfat: avoid incorrectly releasing for root inode net: ipv6: fix skb_over_panic in __ip6_append_data Already merged: llc: only change llc->dev when bind() succeeds netfilter: nf_tables: initialize registers in nft_do_chain() llc: fix netdevice reference leaks in llc_ui_bind() cgroup: Use open-time cgroup namespace for process migration perm checks cgroup: Allocate cgroup_file_ctx for kernfs_open_file->priv nfc: st21nfca: Fix potential buffer overflows in EVT_TRANSACTION Total patches: 37 - 6 = 31 Arnd Bergmann (1): nds32: fix access_ok() checks in get/put_user Brian Norris (1): Revert "ath: add support for special 0x0 regulatory domain" Bryan O'Donoghue (1): wcn36xx: Differentiate wcn3660 from wcn3620 Chen Li (1): exfat: avoid incorrectly releasing for root inode Giacomo Guiduzzi (1): ALSA: pci: fix reading of swapped values from pcmreg in AC97 codec Giovanni Cabiddu (1): crypto: qat - disable registration of algorithms James Bottomley (1): tpm: use try_get_ops() in tpm-space.c Jason Zheng (1): ALSA: hda/realtek: Add quirk for ASUS GA402 Jonathan Teh (1): ALSA: cmipci: Restore aux vol on suspend/resume Lars-Peter Clausen (1): ALSA: usb-audio: Add mute TLV for playback volumes on RODE NT-USB Linus Lüssing (1): mac80211: fix potential double free on mesh join Mark Cilissen (1): ACPI / x86: Work around broken XSDT on Advantech DAC-BJ01 board Maximilian Luz (1): ACPI: battery: Add device HID and quirk for Microsoft Surface Go 3 Michal Koutný (1): cgroup-v1: Correct privileges check in release_agent writes Oliver Graute (1): staging: fbtft: fb_st7789v: reset display before initialization Paul E. McKenney (1): rcu: Don't deboost before reporting expedited quiescent state Reza Jahanbakhshi (1): ALSA: usb-audio: add mapping for new Corsair Virtuoso SE Stephane Graber (1): drivers: net: xgene: Fix regression in CRC stripping Tadeusz Struk (2): net: ipv6: fix skb_over_panic in __ip6_append_data tpm: Fix error handling in async work Takashi Iwai (7): ASoC: sti: Fix deadlock via snd_pcm_stop_xrun() call ALSA: oss: Fix PCM OSS buffer allocation overflow ALSA: pcm: Fix races among concurrent hw_params and hw_free calls ALSA: pcm: Fix races among concurrent read/write and buffer changes ALSA: pcm: Fix races among concurrent prepare and hw_params/hw_free calls ALSA: pcm: Fix races among concurrent prealloc proc writes ALSA: pcm: Add stream lock during PCM reset ioctl operations Tim Crawford (2): ALSA: hda/realtek: Add quirk for Clevo NP70PNJ ALSA: hda/realtek: Add quirk for Clevo NP50PNJ Werner Sembach (1): ACPI: video: Force backlight native for Clevo NL5xRU and NL5xNU huangwenhui (1): ALSA: hda/realtek - Fix headset mic problem for a HP machine with alc671 arch/nds32/include/asm/uaccess.h | 22 ++++- arch/x86/kernel/acpi/boot.c | 24 +++++ drivers/acpi/battery.c | 12 +++ drivers/acpi/video_detect.c | 75 ++++++++++++++ drivers/char/tpm/tpm-dev-common.c | 8 +- drivers/char/tpm/tpm2-space.c | 8 +- drivers/crypto/qat/qat_common/qat_crypto.c | 8 ++ .../net/ethernet/apm/xgene/xgene_enet_main.c | 12 ++- drivers/net/wireless/ath/regd.c | 10 +- drivers/net/wireless/ath/wcn36xx/main.c | 3 + drivers/net/wireless/ath/wcn36xx/wcn36xx.h | 1 + drivers/staging/fbtft/fb_st7789v.c | 2 + fs/exfat/super.c | 2 +- include/sound/pcm.h | 1 + kernel/cgroup/cgroup-v1.c | 6 +- kernel/rcu/tree_plugin.h | 9 +- net/ipv6/ip6_output.c | 4 +- net/mac80211/cfg.c | 3 - sound/core/oss/pcm_oss.c | 12 ++- sound/core/oss/pcm_plugin.c | 5 +- sound/core/pcm.c | 2 + sound/core/pcm_lib.c | 4 + sound/core/pcm_memory.c | 11 ++- sound/core/pcm_native.c | 97 ++++++++++++------- sound/pci/ac97/ac97_codec.c | 4 +- sound/pci/cmipci.c | 3 +- sound/pci/hda/patch_realtek.c | 4 + sound/soc/sti/uniperif_player.c | 6 +- sound/soc/sti/uniperif_reader.c | 2 +- sound/usb/mixer_maps.c | 10 ++ sound/usb/mixer_quirks.c | 7 +- 31 files changed, 289 insertions(+), 88 deletions(-) -- 2.20.1

1 31

[PATCH openEuler-1.0-LTS] io_uring: io_close: Set owner as current->files if req->work.files uninitialized
by Yongqiang Liu 28 Jun '22

28 Jun '22

From: Zhihao Cheng <chengzhihao1(a)huawei.com> hulk inclusion category: bugfix bugzilla: 186543, https://gitee.com/openeuler/kernel/issues/I5BGFA CVE: NA -------------------------------- Following process will trigger an use-after-free problem: 1. open /proc/sysvipc/msg and lock it by file lock fcntl_setlk do_lock_file_wait vfs_lock_file posix_lock_file locks_insert_lock_ctx locks_insert_global_locks // Added to lock list 2. Close /proc/sysvipc/msg by io_uring filp_close(close->put_file, req->work.files) // req->work.files equals NULL，io_grab_files() initialize it, non-async operations won't invokes the function. locks_remove_posix(filp, NULL) lock.fl_owner = NULL vfs_lock_file posix_lock_file posix_same_owner // Return false according to fl_owner. locks_delete_lock_ctx(fl, &dispose) and locks_dispose_list won't be executed, flock is not removed from lock list fput(filp) // release filp 3. Read /proc/locks seq_read locks_start // Get flock from lock list locks_show lock_get_status file_inode(f->file) // Access released file, UAF occurs! Fix it by passing current->files when req->work.files is uninitialized, because io-sq thread shares same files with uring_fd task, so it still works in SQPOLL mode. 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_uring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index c104425b2557..7ae8ba98e73b 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -3903,7 +3903,7 @@ static int io_close(struct io_kiocb *req, bool force_nonblock, } /* No ->flush() or already async, safely close from here */ - ret = filp_close(close->put_file, req->work.files); + ret = filp_close(close->put_file, req->work.files ? : current->files); if (ret < 0) req_set_fail_links(req); fput(close->put_file); -- 2.25.1

1 0

[PATCH openEuler-5.10-LTS 1/5] lockdown: also lock down previous kgdb use
by Zheng Zengkai 27 Jun '22

27 Jun '22

From: Daniel Thompson <daniel.thompson(a)linaro.org> from stable-v5.10.119 commit a8f4d63142f947cd22fa615b8b3b8921cdaf4991 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I5A5YP CVE: CVE-2022-21499 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… commit eadb2f47a3ced5c64b23b90fd2a3463f63726066 upstream. KGDB and KDB allow read and write access to kernel memory, and thus should be restricted during lockdown. An attacker with access to a serial port (for example, via a hypervisor console, which some cloud vendors provide over the network) could trigger the debugger so it is important that the debugger respect the lockdown mode when/if it is triggered. Fix this by integrating lockdown into kdb's existing permissions mechanism. Unfortunately kgdb does not have any permissions mechanism (although it certainly could be added later) so, for now, kgdb is simply and brutally disabled by immediately exiting the gdb stub without taking any action. For lockdowns established early in the boot (e.g. the normal case) then this should be fine but on systems where kgdb has set breakpoints before the lockdown is enacted than "bad things" will happen. CVE: CVE-2022-21499 Co-developed-by: Stephen Brennan <stephen.s.brennan(a)oracle.com> Signed-off-by: Stephen Brennan <stephen.s.brennan(a)oracle.com> Reviewed-by: Douglas Anderson <dianders(a)chromium.org> Signed-off-by: Daniel Thompson <daniel.thompson(a)linaro.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Zheng Yejian <zhengyejian1(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- include/linux/security.h | 2 ++ kernel/debug/debug_core.c | 24 ++++++++++++++ kernel/debug/kdb/kdb_main.c | 62 +++++++++++++++++++++++++++++++++++-- security/security.c | 2 ++ 4 files changed, 87 insertions(+), 3 deletions(-) diff --git a/include/linux/security.h b/include/linux/security.h index 35355429648e..330029ef7e89 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -121,10 +121,12 @@ enum lockdown_reason { LOCKDOWN_DEBUGFS, LOCKDOWN_XMON_WR, LOCKDOWN_BPF_WRITE_USER, + LOCKDOWN_DBG_WRITE_KERNEL, LOCKDOWN_INTEGRITY_MAX, LOCKDOWN_KCORE, LOCKDOWN_KPROBES, LOCKDOWN_BPF_READ, + LOCKDOWN_DBG_READ_KERNEL, LOCKDOWN_PERF, LOCKDOWN_TRACEFS, LOCKDOWN_XMON_RW, diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index be5b6b97adbf..363f781b56ca 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -56,6 +56,7 @@ #include <linux/vmacache.h> #include <linux/rcupdate.h> #include <linux/irq.h> +#include <linux/security.h> #include <asm/cacheflush.h> #include <asm/byteorder.h> @@ -762,6 +763,29 @@ static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs, continue; kgdb_connected = 0; } else { + /* + * This is a brutal way to interfere with the debugger + * and prevent gdb being used to poke at kernel memory. + * This could cause trouble if lockdown is applied when + * there is already an active gdb session. For now the + * answer is simply "don't do that". Typically lockdown + * *will* be applied before the debug core gets started + * so only developers using kgdb for fairly advanced + * early kernel debug can be biten by this. Hopefully + * they are sophisticated enough to take care of + * themselves, especially with help from the lockdown + * message printed on the console! + */ + if (security_locked_down(LOCKDOWN_DBG_WRITE_KERNEL)) { + if (IS_ENABLED(CONFIG_KGDB_KDB)) { + /* Switch back to kdb if possible... */ + dbg_kdb_mode = 1; + continue; + } else { + /* ... otherwise just bail */ + break; + } + } error = gdb_serial_stub(ks); } diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 930ac1b25ec7..4e09fab52faf 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -45,6 +45,7 @@ #include <linux/proc_fs.h> #include <linux/uaccess.h> #include <linux/slab.h> +#include <linux/security.h> #include "kdb_private.h" #undef MODULE_PARAM_PREFIX @@ -197,10 +198,62 @@ struct task_struct *kdb_curr_task(int cpu) } /* - * Check whether the flags of the current command and the permissions - * of the kdb console has allow a command to be run. + * Update the permissions flags (kdb_cmd_enabled) to match the + * current lockdown state. + * + * Within this function the calls to security_locked_down() are "lazy". We + * avoid calling them if the current value of kdb_cmd_enabled already excludes + * flags that might be subject to lockdown. Additionally we deliberately check + * the lockdown flags independently (even though read lockdown implies write + * lockdown) since that results in both simpler code and clearer messages to + * the user on first-time debugger entry. + * + * The permission masks during a read+write lockdown permits the following + * flags: INSPECT, SIGNAL, REBOOT (and ALWAYS_SAFE). + * + * The INSPECT commands are not blocked during lockdown because they are + * not arbitrary memory reads. INSPECT covers the backtrace family (sometimes + * forcing them to have no arguments) and lsmod. These commands do expose + * some kernel state but do not allow the developer seated at the console to + * choose what state is reported. SIGNAL and REBOOT should not be controversial, + * given these are allowed for root during lockdown already. + */ +static void kdb_check_for_lockdown(void) +{ + const int write_flags = KDB_ENABLE_MEM_WRITE | + KDB_ENABLE_REG_WRITE | + KDB_ENABLE_FLOW_CTRL; + const int read_flags = KDB_ENABLE_MEM_READ | + KDB_ENABLE_REG_READ; + + bool need_to_lockdown_write = false; + bool need_to_lockdown_read = false; + + if (kdb_cmd_enabled & (KDB_ENABLE_ALL | write_flags)) + need_to_lockdown_write = + security_locked_down(LOCKDOWN_DBG_WRITE_KERNEL); + + if (kdb_cmd_enabled & (KDB_ENABLE_ALL | read_flags)) + need_to_lockdown_read = + security_locked_down(LOCKDOWN_DBG_READ_KERNEL); + + /* De-compose KDB_ENABLE_ALL if required */ + if (need_to_lockdown_write || need_to_lockdown_read) + if (kdb_cmd_enabled & KDB_ENABLE_ALL) + kdb_cmd_enabled = KDB_ENABLE_MASK & ~KDB_ENABLE_ALL; + + if (need_to_lockdown_write) + kdb_cmd_enabled &= ~write_flags; + + if (need_to_lockdown_read) + kdb_cmd_enabled &= ~read_flags; +} + +/* + * Check whether the flags of the current command, the permissions of the kdb + * console and the lockdown state allow a command to be run. */ -static inline bool kdb_check_flags(kdb_cmdflags_t flags, int permissions, +static bool kdb_check_flags(kdb_cmdflags_t flags, int permissions, bool no_args) { /* permissions comes from userspace so needs massaging slightly */ @@ -1194,6 +1247,9 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs, kdb_curr_task(raw_smp_processor_id()); KDB_DEBUG_STATE("kdb_local 1", reason); + + kdb_check_for_lockdown(); + kdb_go_count = 0; if (reason == KDB_REASON_DEBUG) { /* special case below */ diff --git a/security/security.c b/security/security.c index 4fb58543eeb9..2fc40217d49d 100644 --- a/security/security.c +++ b/security/security.c @@ -59,10 +59,12 @@ const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX+1] = { [LOCKDOWN_DEBUGFS] = "debugfs access", [LOCKDOWN_XMON_WR] = "xmon write access", [LOCKDOWN_BPF_WRITE_USER] = "use of bpf to write user RAM", + [LOCKDOWN_DBG_WRITE_KERNEL] = "use of kgdb/kdb to write kernel RAM", [LOCKDOWN_INTEGRITY_MAX] = "integrity", [LOCKDOWN_KCORE] = "/proc/kcore access", [LOCKDOWN_KPROBES] = "use of kprobes", [LOCKDOWN_BPF_READ] = "use of bpf to read kernel RAM", + [LOCKDOWN_DBG_READ_KERNEL] = "use of kgdb/kdb to read kernel RAM", [LOCKDOWN_PERF] = "unsafe use of perf", [LOCKDOWN_TRACEFS] = "use of tracefs", [LOCKDOWN_XMON_RW] = "xmon read and write access", -- 2.20.1

1 4

[PATCH openEuler-5.10-LTS 00/31] Backport 5.10.109 LTS
by Zheng Zengkai 27 Jun '22

27 Jun '22

Backport 5.10.109 LTS patches from upstream nds32: fix access_ok() checks in get/put_user wcn36xx: Differentiate wcn3660 from wcn3620 tpm: use try_get_ops() in tpm-space.c mac80211: fix potential double free on mesh join rcu: Don't deboost before reporting expedited quiescent state Revert "ath: add support for special 0x0 regulatory domain" crypto: qat - disable registration of algorithms ACPI: video: Force backlight native for Clevo NL5xRU and NL5xNU ACPI: battery: Add device HID and quirk for Microsoft Surface Go 3 ACPI / x86: Work around broken XSDT on Advantech DAC-BJ01 board drivers: net: xgene: Fix regression in CRC stripping ALSA: pci: fix reading of swapped values from pcmreg in AC97 codec ALSA: cmipci: Restore aux vol on suspend/resume ALSA: usb-audio: Add mute TLV for playback volumes on RODE NT-USB ALSA: pcm: Add stream lock during PCM reset ioctl operations ALSA: pcm: Fix races among concurrent prealloc proc writes ALSA: pcm: Fix races among concurrent prepare and hw_params/hw_free calls ALSA: pcm: Fix races among concurrent read/write and buffer changes ALSA: pcm: Fix races among concurrent hw_params and hw_free calls ALSA: hda/realtek: Add quirk for ASUS GA402 ALSA: hda/realtek - Fix headset mic problem for a HP machine with alc671 ALSA: hda/realtek: Add quirk for Clevo NP50PNJ ALSA: hda/realtek: Add quirk for Clevo NP70PNJ ALSA: usb-audio: add mapping for new Corsair Virtuoso SE ALSA: oss: Fix PCM OSS buffer allocation overflow ASoC: sti: Fix deadlock via snd_pcm_stop_xrun() call staging: fbtft: fb_st7789v: reset display before initialization tpm: Fix error handling in async work cgroup-v1: Correct privileges check in release_agent writes exfat: avoid incorrectly releasing for root inode net: ipv6: fix skb_over_panic in __ip6_append_data Already merged: llc: only change llc->dev when bind() succeeds netfilter: nf_tables: initialize registers in nft_do_chain() llc: fix netdevice reference leaks in llc_ui_bind() cgroup: Use open-time cgroup namespace for process migration perm checks cgroup: Allocate cgroup_file_ctx for kernfs_open_file->priv nfc: st21nfca: Fix potential buffer overflows in EVT_TRANSACTION Total patches: 37 - 6 = 31 Arnd Bergmann (1): nds32: fix access_ok() checks in get/put_user Brian Norris (1): Revert "ath: add support for special 0x0 regulatory domain" Bryan O'Donoghue (1): wcn36xx: Differentiate wcn3660 from wcn3620 Chen Li (1): exfat: avoid incorrectly releasing for root inode Giacomo Guiduzzi (1): ALSA: pci: fix reading of swapped values from pcmreg in AC97 codec Giovanni Cabiddu (1): crypto: qat - disable registration of algorithms James Bottomley (1): tpm: use try_get_ops() in tpm-space.c Jason Zheng (1): ALSA: hda/realtek: Add quirk for ASUS GA402 Jonathan Teh (1): ALSA: cmipci: Restore aux vol on suspend/resume Lars-Peter Clausen (1): ALSA: usb-audio: Add mute TLV for playback volumes on RODE NT-USB Linus Lüssing (1): mac80211: fix potential double free on mesh join Mark Cilissen (1): ACPI / x86: Work around broken XSDT on Advantech DAC-BJ01 board Maximilian Luz (1): ACPI: battery: Add device HID and quirk for Microsoft Surface Go 3 Michal Koutný (1): cgroup-v1: Correct privileges check in release_agent writes Oliver Graute (1): staging: fbtft: fb_st7789v: reset display before initialization Paul E. McKenney (1): rcu: Don't deboost before reporting expedited quiescent state Reza Jahanbakhshi (1): ALSA: usb-audio: add mapping for new Corsair Virtuoso SE Stephane Graber (1): drivers: net: xgene: Fix regression in CRC stripping Tadeusz Struk (2): net: ipv6: fix skb_over_panic in __ip6_append_data tpm: Fix error handling in async work Takashi Iwai (7): ASoC: sti: Fix deadlock via snd_pcm_stop_xrun() call ALSA: oss: Fix PCM OSS buffer allocation overflow ALSA: pcm: Fix races among concurrent hw_params and hw_free calls ALSA: pcm: Fix races among concurrent read/write and buffer changes ALSA: pcm: Fix races among concurrent prepare and hw_params/hw_free calls ALSA: pcm: Fix races among concurrent prealloc proc writes ALSA: pcm: Add stream lock during PCM reset ioctl operations Tim Crawford (2): ALSA: hda/realtek: Add quirk for Clevo NP70PNJ ALSA: hda/realtek: Add quirk for Clevo NP50PNJ Werner Sembach (1): ACPI: video: Force backlight native for Clevo NL5xRU and NL5xNU huangwenhui (1): ALSA: hda/realtek - Fix headset mic problem for a HP machine with alc671 arch/nds32/include/asm/uaccess.h | 22 ++++- arch/x86/kernel/acpi/boot.c | 24 +++++ drivers/acpi/battery.c | 12 +++ drivers/acpi/video_detect.c | 75 ++++++++++++++ drivers/char/tpm/tpm-dev-common.c | 8 +- drivers/char/tpm/tpm2-space.c | 8 +- drivers/crypto/qat/qat_common/qat_crypto.c | 8 ++ .../net/ethernet/apm/xgene/xgene_enet_main.c | 12 ++- drivers/net/wireless/ath/regd.c | 10 +- drivers/net/wireless/ath/wcn36xx/main.c | 3 + drivers/net/wireless/ath/wcn36xx/wcn36xx.h | 1 + drivers/staging/fbtft/fb_st7789v.c | 2 + fs/exfat/super.c | 2 +- include/sound/pcm.h | 1 + kernel/cgroup/cgroup-v1.c | 6 +- kernel/rcu/tree_plugin.h | 9 +- net/ipv6/ip6_output.c | 4 +- net/mac80211/cfg.c | 3 - sound/core/oss/pcm_oss.c | 12 ++- sound/core/oss/pcm_plugin.c | 5 +- sound/core/pcm.c | 2 + sound/core/pcm_lib.c | 4 + sound/core/pcm_memory.c | 11 ++- sound/core/pcm_native.c | 97 ++++++++++++------- sound/pci/ac97/ac97_codec.c | 4 +- sound/pci/cmipci.c | 3 +- sound/pci/hda/patch_realtek.c | 4 + sound/soc/sti/uniperif_player.c | 6 +- sound/soc/sti/uniperif_reader.c | 2 +- sound/usb/mixer_maps.c | 10 ++ sound/usb/mixer_quirks.c | 7 +- 31 files changed, 289 insertions(+), 88 deletions(-) -- 2.20.1

1 31

[PATCH openEuler-1.0-LTS] mm/memcontrol: fix wrong vmstats for dying memcg
by Yongqiang Liu 27 Jun '22

27 Jun '22

From: Lu Jialin <lujialin4(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5E8LA CVE: NA -------------------------------- At present, only when the absolute value of stat_cpu->count exceeds MEMCG_CHARGE_BATCH will it be updated to stat, so there will always be a certain lag difference between stat and the correct value. In addition, since the partially deleted memcg is still referenced, it will not be freed immediately after it is offline. Although the remaining memcg has released the page, it and the parent's stat will still be not 0 or too large due to the update lag, which leads to the abnormality of the total_<count> parameter in the memory.stat file. This patch mainly solves the problem of synchronization between memcg's stat and the correct value during the destruction process from two aspects: 1) Perform a flush synchronization operation when memcg is offline 2) For memcg in the process of being destroyed, bypass the threshold judgment when updating vmstats Signed-off-by: Lu Jialin <lujialin4(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- mm/memcontrol.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2983baf910f4..345a9d159ad8 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -697,7 +697,8 @@ void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val) return; x = val + __this_cpu_read(memcg->stat_cpu->count[idx]); - if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) { + if (unlikely(abs(x) > MEMCG_CHARGE_BATCH || + memcg->css.flags & CSS_DYING)) { struct mem_cgroup *mi; struct mem_cgroup_extension *memcg_ext; @@ -3244,8 +3245,10 @@ static void memcg_flush_percpu_vmstats(struct mem_cgroup *memcg) stat[i] = 0; for_each_online_cpu(cpu) - for (i = 0; i < MEMCG_NR_STAT; i++) + for (i = 0; i < MEMCG_NR_STAT; i++) { stat[i] += per_cpu(memcg->stat_cpu->count[i], cpu); + per_cpu(memcg->stat_cpu->count[i], cpu) = 0; + } for (mi = memcg; mi; mi = parent_mem_cgroup(mi)) for (i = 0; i < MEMCG_NR_STAT; i++) @@ -3259,9 +3262,11 @@ static void memcg_flush_percpu_vmstats(struct mem_cgroup *memcg) stat[i] = 0; for_each_online_cpu(cpu) - for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) + for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) { stat[i] += per_cpu( pn->lruvec_stat_cpu->count[i], cpu); + per_cpu(pn->lruvec_stat_cpu->count[i], cpu) = 0; + } for (pi = pn; pi; pi = parent_nodeinfo(pi, node)) for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) @@ -3279,9 +3284,11 @@ static void memcg_flush_percpu_vmevents(struct mem_cgroup *memcg) events[i] = 0; for_each_online_cpu(cpu) - for (i = 0; i < NR_VM_EVENT_ITEMS; i++) + for (i = 0; i < NR_VM_EVENT_ITEMS; i++) { events[i] += per_cpu(memcg->stat_cpu->events[i], cpu); + per_cpu(memcg->stat_cpu->events[i], cpu) = 0; + } for (mi = memcg; mi; mi = parent_mem_cgroup(mi)) for (i = 0; i < NR_VM_EVENT_ITEMS; i++) @@ -5106,6 +5113,9 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) memcg_offline_kmem(memcg); wb_memcg_offline(memcg); + memcg_flush_percpu_vmstats(memcg); + memcg_flush_percpu_vmevents(memcg); + mem_cgroup_id_put(memcg); } -- 2.25.1

1 0

sig-Intel-Arch 例会
by Tian, Jun J 27 Jun '22

27 Jun '22

大家好，本次Intel Arch例会定于本周二6/28 10:00-11:00AM进行, 欢迎大家提出更多需求或议题和参与讨论。本次初步议题： Agenda: *Status update *SPR feature PRs merge into intel-kernel & OLK-5.10 kernel *Compiler support for new instructions *Support 22.09 release for SPR fundamental features -----Original Appointment----- From: openEuler conference <public(a)openeuler.org> Sent: Monday, June 20, 2022 3:10 PM To: openEuler conference; jun.j.tian@intel.com,kai.liu@suse.com Subject: sig-Intel-Arch When: Tuesday, June 28, 2022 10:00 AM-11:00 AM (UTC+08:00) Beijing, Chongqing, Hong Kong, Urumqi. Where: 您好！ sig-Intel-Arch SIG 邀请您参加 2022-06-28 10:00 召开的Zoom会议会议主题：sig-Intel-Arch 会议链接：https://us06web.zoom.us/j/81976528831?pwd=cVIxUkRhUXFGcldFV0ZtNkpvUFpxZz09 会议纪要：https://etherpad.openeuler.org/p/sig-Intel-Arch-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 sig-Intel-Arch SIG invites you to attend the Zoom conference will be held at 2022-06-28 10:00, The subject of the conference is sig-Intel-Arch, You can join the meeting at https://us06web.zoom.us/j/81976528831?pwd=cVIxUkRhUXFGcldFV0ZtNkpvUFpxZz09. Add topics at https://etherpad.openeuler.org/p/sig-Intel-Arch-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] ext4: recover csum seed of tmp_inode after migrating to extents
by Yongqiang Liu 25 Jun '22

25 Jun '22

From: Li Lingfeng <lilingfeng3(a)huawei.com> hulk inclusion category: bugfix bugzilla: 186944, https://gitee.com/openeuler/kernel/issues/I5DAJY CVE: NA -------------------------------- When migrating to extents, the checksum seed of temporary inode need to be replaced by inode's, otherwise the inode checksums will be incorrect when swapping the inodes data. However, the temporary inode can not match it's checksum to itself since it has lost it's own checksum seed. mkfs.ext4 -F /dev/sdc mount /dev/sdc /mnt/sdc xfs_io -fc "pwrite 4k 4k" -c "fsync" /mnt/sdc/testfile chattr -e /mnt/sdc/testfile chattr +e /mnt/sdc/testfile fsck -fn /dev/sdc ======== ... Pass 1: Checking inodes, blocks, and sizes Inode 13 passes checks, but checksum does not match inode. Fix? no ... ======== The fix is simple, save the checksum seed of temporary inode, and recover it after migrating to extents. Fixes: e81c9302a6c3 ("ext4: set csum seed in tmp inode while migrating to extents") Signed-off-by: Li Lingfeng <lilingfeng3(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- fs/ext4/migrate.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index 75a769634b2b..ed9e7816efbb 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -415,7 +415,7 @@ int ext4_ext_migrate(struct inode *inode) struct inode *tmp_inode = NULL; struct migrate_struct lb; unsigned long max_entries; - __u32 goal; + __u32 goal, tmp_csum_seed; uid_t owner[2]; /* @@ -463,6 +463,7 @@ int ext4_ext_migrate(struct inode *inode) * the migration. */ ei = EXT4_I(inode); + tmp_csum_seed = EXT4_I(tmp_inode)->i_csum_seed; EXT4_I(tmp_inode)->i_csum_seed = ei->i_csum_seed; i_size_write(tmp_inode, i_size_read(inode)); /* @@ -573,6 +574,7 @@ int ext4_ext_migrate(struct inode *inode) * the inode is not visible to user space. */ tmp_inode->i_blocks = 0; + EXT4_I(tmp_inode)->i_csum_seed = tmp_csum_seed; /* Reset the extent details */ ext4_ext_tree_init(handle, tmp_inode); -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] vfio: framework supporting vfio device hot migration
by RongWang 24 Jun '22

24 Jun '22

From: Rong Wang <w_angrong(a)163.com> kunpeng inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I5CO9A CVE: NA --------------------------------- As pass through devices, hypervisor can`t control the status of device, and can`t track dirty memory DMA from device, during migration. The goal of this framework is to combine hardware to accomplish the task above. qemu |status control and dirty memory report vfio |ops to hardware hardware Signed-off-by: Rong Wang <w_angrong(a)163.com> Signed-off-by: HuHua Li <18245010845(a)163.com> Signed-off-by: Ripeng Qiu <965412048(a)qq.com> --- drivers/vfio/pci/Makefile | 2 +- drivers/vfio/pci/vfio_pci.c | 54 +++ drivers/vfio/pci/vfio_pci_migration.c | 755 ++++++++++++++++++++++++++++++++++ drivers/vfio/pci/vfio_pci_private.h | 14 +- drivers/vfio/vfio.c | 411 +++++++++++++++++- include/linux/vfio_pci_migration.h | 136 ++++++ 6 files changed, 1367 insertions(+), 5 deletions(-) create mode 100644 drivers/vfio/pci/vfio_pci_migration.c create mode 100644 include/linux/vfio_pci_migration.h diff --git a/drivers/vfio/pci/Makefile b/drivers/vfio/pci/Makefile index 76d8ec0..80a777d 100644 --- a/drivers/vfio/pci/Makefile +++ b/drivers/vfio/pci/Makefile @@ -1,5 +1,5 @@ -vfio-pci-y := vfio_pci.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_config.o +vfio-pci-y := vfio_pci.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_config.o vfio_pci_migration.o vfio-pci-$(CONFIG_VFIO_PCI_IGD) += vfio_pci_igd.o obj-$(CONFIG_VFIO_PCI) += vfio-pci.o diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 51b791c..59d8280 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -30,6 +30,7 @@ #include <linux/vgaarb.h> #include <linux/nospec.h> #include <linux/sched/mm.h> +#include <linux/vfio_pci_migration.h> #include "vfio_pci_private.h" @@ -296,6 +297,14 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev) vfio_pci_probe_mmaps(vdev); + if (vfio_dev_migration_is_supported(pdev)) { + ret = vfio_pci_migration_init(vdev); + if (ret) { + dev_warn(&vdev->pdev->dev, "Failed to init vfio_pci_migration\n"); + vfio_pci_disable(vdev); + return ret; + } + } return 0; } @@ -392,6 +401,7 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev) out: pci_disable_device(pdev); + vfio_pci_migration_exit(vdev); vfio_pci_try_bus_reset(vdev); if (!disable_idle_d3) @@ -642,6 +652,41 @@ struct vfio_devices { int max_index; }; +static long vfio_pci_handle_log_buf_ctl(struct vfio_pci_device *vdev, + const unsigned long arg) +{ + struct vfio_log_buf_ctl *log_buf_ctl = NULL; + struct vfio_log_buf_info *log_buf_info = NULL; + struct vf_migration_log_info migration_log_info; + long ret = 0; + + log_buf_ctl = (struct vfio_log_buf_ctl *)arg; + log_buf_info = (struct vfio_log_buf_info *)log_buf_ctl->data; + + switch (log_buf_ctl->flags) { + case VFIO_DEVICE_LOG_BUF_FLAG_START: + migration_log_info.dom_uuid = log_buf_info->uuid; + migration_log_info.buffer_size = + log_buf_info->buffer_size; + migration_log_info.sge_num = log_buf_info->addrs_size; + migration_log_info.sge_len = log_buf_info->frag_size; + migration_log_info.sgevec = log_buf_info->sgevec; + ret = vfio_pci_device_log_start(vdev, + &migration_log_info); + break; + case VFIO_DEVICE_LOG_BUF_FLAG_STOP: + ret = vfio_pci_device_log_stop(vdev, + log_buf_info->uuid); + break; + case VFIO_DEVICE_LOG_BUF_FLAG_STATUS_QUERY: + ret = vfio_pci_device_log_status_query(vdev); + break; + default: + ret = -EINVAL; + break; + } + return ret; +} static long vfio_pci_ioctl(void *device_data, unsigned int cmd, unsigned long arg) { @@ -1142,6 +1187,8 @@ static long vfio_pci_ioctl(void *device_data, return vfio_pci_ioeventfd(vdev, ioeventfd.offset, ioeventfd.data, count, ioeventfd.fd); + } else if (cmd == VFIO_DEVICE_LOG_BUF_CTL) { + return vfio_pci_handle_log_buf_ctl(vdev, arg); } return -ENOTTY; @@ -1566,6 +1613,9 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) pci_set_power_state(pdev, PCI_D3hot); } + if (vfio_dev_migration_is_supported(pdev)) + ret = vfio_pci_device_init(pdev); + return ret; } @@ -1591,6 +1641,10 @@ static void vfio_pci_remove(struct pci_dev *pdev) if (!disable_idle_d3) pci_set_power_state(pdev, PCI_D0); + + if (vfio_dev_migration_is_supported(pdev)) { + vfio_pci_device_uninit(pdev); + } } static pci_ers_result_t vfio_pci_aer_err_detected(struct pci_dev *pdev, diff --git a/drivers/vfio/pci/vfio_pci_migration.c b/drivers/vfio/pci/vfio_pci_migration.c new file mode 100644 index 0000000..f69cd13 --- /dev/null +++ b/drivers/vfio/pci/vfio_pci_migration.c @@ -0,0 +1,755 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2022 Huawei Technologies Co., Ltd. All rights reserved. + */ + +#include <linux/module.h> +#include <linux/io.h> +#include <linux/pci.h> +#include <linux/uaccess.h> +#include <linux/vfio.h> +#include <linux/vfio_pci_migration.h> + +#include "vfio_pci_private.h" + +static LIST_HEAD(vfio_pci_mig_drivers_list); +static DEFINE_MUTEX(vfio_pci_mig_drivers_mutex); + +static void vfio_pci_add_mig_drv(struct vfio_pci_vendor_mig_driver *mig_drv) +{ + mutex_lock(&vfio_pci_mig_drivers_mutex); + atomic_set(&mig_drv->count, 1); + list_add_tail(&mig_drv->list, &vfio_pci_mig_drivers_list); + mutex_unlock(&vfio_pci_mig_drivers_mutex); +} + +static void vfio_pci_remove_mig_drv(struct vfio_pci_vendor_mig_driver *mig_drv) +{ + mutex_lock(&vfio_pci_mig_drivers_mutex); + list_del(&mig_drv->list); + mutex_unlock(&vfio_pci_mig_drivers_mutex); +} + +static struct vfio_pci_vendor_mig_driver * + vfio_pci_find_mig_drv(struct pci_dev *pdev, struct module *module) +{ + struct vfio_pci_vendor_mig_driver *mig_drv = NULL; + + mutex_lock(&vfio_pci_mig_drivers_mutex); + list_for_each_entry(mig_drv, &vfio_pci_mig_drivers_list, list) { + if (mig_drv->owner == module) { + if (mig_drv->bus_num == pdev->bus->number) + goto out; + } + } + mig_drv = NULL; +out: + mutex_unlock(&vfio_pci_mig_drivers_mutex); + return mig_drv; +} + +static struct vfio_pci_vendor_mig_driver * + vfio_pci_get_mig_driver(struct pci_dev *pdev) +{ + struct vfio_pci_vendor_mig_driver *mig_drv = NULL; + struct pci_dev *pf_dev = pci_physfn(pdev); + + mutex_lock(&vfio_pci_mig_drivers_mutex); + list_for_each_entry(mig_drv, &vfio_pci_mig_drivers_list, list) { + if (mig_drv->bus_num == pf_dev->bus->number) + goto out; + } + mig_drv = NULL; +out: + mutex_unlock(&vfio_pci_mig_drivers_mutex); + return mig_drv; +} + +bool vfio_dev_migration_is_supported(struct pci_dev *pdev) +{ + struct vfio_pci_vendor_mig_driver *mig_driver = NULL; + + mig_driver = vfio_pci_get_mig_driver(pdev); + if (!mig_driver || !mig_driver->dev_mig_ops) { + dev_warn(&pdev->dev, "unable to find a mig_drv module\n"); + return false; + } + + return true; +} + +int vfio_pci_device_log_start(struct vfio_pci_device *vdev, + struct vf_migration_log_info *log_info) +{ + struct vfio_pci_vendor_mig_driver *mig_driver; + + mig_driver = vfio_pci_get_mig_driver(vdev->pdev); + if (!mig_driver || !mig_driver->dev_mig_ops) { + dev_err(&vdev->pdev->dev, "unable to find a mig_drv module\n"); + return -EFAULT; + } + + if (!mig_driver->dev_mig_ops->log_start || + (mig_driver->dev_mig_ops->log_start(vdev->pdev, + log_info) != 0)) { + dev_err(&vdev->pdev->dev, "failed to set log start\n"); + return -EFAULT; + } + + return 0; +} + +int vfio_pci_device_log_stop(struct vfio_pci_device *vdev, uint32_t uuid) +{ + struct vfio_pci_vendor_mig_driver *mig_driver; + + mig_driver = vfio_pci_get_mig_driver(vdev->pdev); + if (!mig_driver || !mig_driver->dev_mig_ops) { + dev_err(&vdev->pdev->dev, "unable to find a mig_drv module\n"); + return -EFAULT; + } + + if (!mig_driver->dev_mig_ops->log_stop || + (mig_driver->dev_mig_ops->log_stop(vdev->pdev, uuid) != 0)) { + dev_err(&vdev->pdev->dev, "failed to set log stop\n"); + return -EFAULT; + } + + return 0; +} + +int vfio_pci_device_log_status_query(struct vfio_pci_device *vdev) +{ + struct vfio_pci_vendor_mig_driver *mig_driver; + + mig_driver = vfio_pci_get_mig_driver(vdev->pdev); + if (!mig_driver || !mig_driver->dev_mig_ops) { + dev_err(&vdev->pdev->dev, "unable to find a mig_drv module\n"); + return -EFAULT; + } + + if (!mig_driver->dev_mig_ops->get_log_status || + (mig_driver->dev_mig_ops->get_log_status(vdev->pdev) != 0)) { + dev_err(&vdev->pdev->dev, "failed to get log status\n"); + return -EFAULT; + } + + return 0; +} + +int vfio_pci_device_init(struct pci_dev *pdev) +{ + struct vfio_pci_vendor_mig_driver *mig_drv; + + mig_drv = vfio_pci_get_mig_driver(pdev); + if (!mig_drv || !mig_drv->dev_mig_ops) { + dev_err(&pdev->dev, "unable to find a mig_drv module\n"); + return -EFAULT; + } + + if (mig_drv->dev_mig_ops->init) + return mig_drv->dev_mig_ops->init(pdev); + + return -EFAULT; +} + +void vfio_pci_device_uninit(struct pci_dev *pdev) +{ + struct vfio_pci_vendor_mig_driver *mig_drv; + + mig_drv = vfio_pci_get_mig_driver(pdev); + if (!mig_drv || !mig_drv->dev_mig_ops) { + dev_err(&pdev->dev, "unable to find a mig_drv module\n"); + return; + } + + if (mig_drv->dev_mig_ops->uninit) + mig_drv->dev_mig_ops->uninit(pdev); +} + +static void vfio_pci_device_release(struct pci_dev *pdev, + struct vfio_pci_vendor_mig_driver *mig_drv) +{ + if (mig_drv->dev_mig_ops->release) + mig_drv->dev_mig_ops->release(pdev); +} + +static int vfio_pci_device_get_info(struct pci_dev *pdev, + struct vfio_device_migration_info *mig_info, + struct vfio_pci_vendor_mig_driver *mig_drv) +{ + if (mig_drv->dev_mig_ops->get_info) + return mig_drv->dev_mig_ops->get_info(pdev, mig_info); + return -EFAULT; +} + +static int vfio_pci_device_enable(struct pci_dev *pdev, + struct vfio_pci_vendor_mig_driver *mig_drv) +{ + if (!mig_drv->dev_mig_ops->enable || + (mig_drv->dev_mig_ops->enable(pdev) != 0)) { + return -EINVAL; + } + + return 0; +} + +static int vfio_pci_device_disable(struct pci_dev *pdev, + struct vfio_pci_vendor_mig_driver *mig_drv) +{ + if (!mig_drv->dev_mig_ops->disable || + (mig_drv->dev_mig_ops->disable(pdev) != 0)) + return -EINVAL; + + return 0; +} + +static int vfio_pci_device_pre_enable(struct pci_dev *pdev, + struct vfio_pci_vendor_mig_driver *mig_drv) +{ + if (!mig_drv->dev_mig_ops->pre_enable || + (mig_drv->dev_mig_ops->pre_enable(pdev) != 0)) + return -EINVAL; + + return 0; +} + +static int vfio_pci_device_state_save(struct pci_dev *pdev, + struct vfio_pci_migration_data *data) +{ + struct vfio_device_migration_info *mig_info = data->mig_ctl; + struct vfio_pci_vendor_mig_driver *mig_drv = data->mig_driver; + void *base = (void *)mig_info; + int ret = 0; + + if ((mig_info->device_state & VFIO_DEVICE_STATE_RUNNING) != 0) { + ret = vfio_pci_device_disable(pdev, mig_drv); + if (ret) { + dev_err(&pdev->dev, "failed to stop VF function!\n"); + return ret; + } + mig_info->device_state &= ~VFIO_DEVICE_STATE_RUNNING; + } + + if (mig_drv->dev_mig_ops && mig_drv->dev_mig_ops->save) { + ret = mig_drv->dev_mig_ops->save(pdev, base, + mig_info->data_offset, data->state_size); + if (ret) { + dev_err(&pdev->dev, "failed to save device state!\n"); + return -EINVAL; + } + } else { + return -EFAULT; + } + + mig_info->data_size = data->state_size; + mig_info->pending_bytes = mig_info->data_size; + return ret; +} + +static int vfio_pci_device_state_restore(struct vfio_pci_migration_data *data) +{ + struct vfio_device_migration_info *mig_info = data->mig_ctl; + struct vfio_pci_vendor_mig_driver *mig_drv = data->mig_driver; + struct pci_dev *pdev = data->vf_dev; + void *base = (void *)mig_info; + int ret; + + if (mig_drv->dev_mig_ops && mig_drv->dev_mig_ops->restore) { + ret = mig_drv->dev_mig_ops->restore(pdev, base, + mig_info->data_offset, mig_info->data_size); + if (ret) { + dev_err(&pdev->dev, "failed to restore device state!\n"); + return -EINVAL; + } + return 0; + } + + return -EFAULT; +} + +static int vfio_pci_set_device_state(struct vfio_pci_migration_data *data, + u32 state) +{ + struct vfio_device_migration_info *mig_ctl = data->mig_ctl; + struct vfio_pci_vendor_mig_driver *mig_drv = data->mig_driver; + struct pci_dev *pdev = data->vf_dev; + int ret = 0; + + if (state == mig_ctl->device_state) + return 0; + + if (!mig_drv->dev_mig_ops) + return -EINVAL; + + switch (state) { + case VFIO_DEVICE_STATE_RUNNING: + if (!(mig_ctl->device_state & + VFIO_DEVICE_STATE_RUNNING)) + ret = vfio_pci_device_enable(pdev, mig_drv); + break; + case VFIO_DEVICE_STATE_SAVING | VFIO_DEVICE_STATE_RUNNING: + /* + * (pre-copy) - device should start logging data. + */ + ret = 0; + break; + case VFIO_DEVICE_STATE_SAVING: + /* stop the vf function, save state */ + ret = vfio_pci_device_state_save(pdev, data); + break; + case VFIO_DEVICE_STATE_STOP: + if (mig_ctl->device_state & VFIO_DEVICE_STATE_RUNNING) + ret = vfio_pci_device_disable(pdev, mig_drv); + break; + case VFIO_DEVICE_STATE_RESUMING: + ret = vfio_pci_device_pre_enable(pdev, mig_drv); + break; + default: + ret = -EFAULT; + break; + } + + if (ret) + return ret; + + mig_ctl->device_state = state; + return 0; +} + +static ssize_t vfio_pci_handle_mig_dev_state( + struct vfio_pci_migration_data *data, + char __user *buf, size_t count, bool iswrite) +{ + struct vfio_device_migration_info *mig_ctl = data->mig_ctl; + u32 device_state; + int ret; + + if (count != sizeof(device_state)) + return -EINVAL; + + if (iswrite) { + if (copy_from_user(&device_state, buf, count)) + return -EFAULT; + + ret = vfio_pci_set_device_state(data, device_state); + if (ret) + return ret; + } else { + if (copy_to_user(buf, &mig_ctl->device_state, count)) + return -EFAULT; + } + + return count; +} + +static ssize_t vfio_pci_handle_mig_pending_bytes( + struct vfio_device_migration_info *mig_info, + char __user *buf, size_t count, bool iswrite) +{ + u64 pending_bytes; + + if (count != sizeof(pending_bytes) || iswrite) + return -EINVAL; + + if (mig_info->device_state == + (VFIO_DEVICE_STATE_SAVING | VFIO_DEVICE_STATE_RUNNING)) { + /* In pre-copy state we have no data to return for now, + * return 0 pending bytes + */ + pending_bytes = 0; + } else { + pending_bytes = mig_info->pending_bytes; + } + + if (copy_to_user(buf, &pending_bytes, count)) + return -EFAULT; + + return count; +} + +static ssize_t vfio_pci_handle_mig_data_offset( + struct vfio_device_migration_info *mig_info, + char __user *buf, size_t count, bool iswrite) +{ + u64 data_offset = mig_info->data_offset; + + if (count != sizeof(data_offset) || iswrite) + return -EINVAL; + + if (copy_to_user(buf, &data_offset, count)) + return -EFAULT; + + return count; +} + +static ssize_t vfio_pci_handle_mig_data_size( + struct vfio_device_migration_info *mig_info, + char __user *buf, size_t count, bool iswrite) +{ + u64 data_size; + + if (count != sizeof(data_size)) + return -EINVAL; + + if (iswrite) { + /* data_size is writable only during resuming state */ + if (mig_info->device_state != VFIO_DEVICE_STATE_RESUMING) + return -EINVAL; + + if (copy_from_user(&data_size, buf, sizeof(data_size))) + return -EFAULT; + + mig_info->data_size = data_size; + } else { + if (mig_info->device_state != VFIO_DEVICE_STATE_SAVING) + return -EINVAL; + + if (copy_to_user(buf, &mig_info->data_size, + sizeof(data_size))) + return -EFAULT; + } + + return count; +} + +static ssize_t vfio_pci_handle_mig_dev_cmd(struct vfio_pci_migration_data *data, + char __user *buf, size_t count, bool iswrite) +{ + struct vfio_pci_vendor_mig_driver *mig_drv = data->mig_driver; + struct pci_dev *pdev = data->vf_dev; + u32 device_cmd; + int ret = -EFAULT; + + if (count != sizeof(device_cmd) || !iswrite || !mig_drv->dev_mig_ops) + return -EINVAL; + + if (copy_from_user(&device_cmd, buf, count)) + return -EFAULT; + + switch (device_cmd) { + case VFIO_DEVICE_MIGRATION_CANCEL: + if (mig_drv->dev_mig_ops->cancel) + ret = mig_drv->dev_mig_ops->cancel(pdev); + break; + default: + dev_err(&pdev->dev, "cmd is invaild\n"); + return -EINVAL; + } + + if (ret != 0) + return ret; + + return count; +} + +static ssize_t vfio_pci_handle_mig_drv_version( + struct vfio_device_migration_info *mig_info, + char __user *buf, size_t count, bool iswrite) +{ + u32 version_id = mig_info->version_id; + + if (count != sizeof(version_id) || iswrite) + return -EINVAL; + + if (copy_to_user(buf, &version_id, count)) + return -EFAULT; + + return count; +} + +static ssize_t vfio_pci_handle_mig_data_rw( + struct vfio_pci_migration_data *data, + char __user *buf, size_t count, u64 pos, bool iswrite) +{ + struct vfio_device_migration_info *mig_ctl = data->mig_ctl; + void *data_addr = data->vf_data; + + if (count == 0) { + dev_err(&data->vf_dev->dev, "qemu operation data size error!\n"); + return -EINVAL; + } + + data_addr += pos - mig_ctl->data_offset; + if (iswrite) { + if (copy_from_user(data_addr, buf, count)) + return -EFAULT; + + mig_ctl->pending_bytes += count; + if (mig_ctl->pending_bytes > data->state_size) + return -EINVAL; + } else { + if (copy_to_user(buf, data_addr, count)) + return -EFAULT; + + if (mig_ctl->pending_bytes < count) + return -EINVAL; + + mig_ctl->pending_bytes -= count; + } + + return count; +} + +static ssize_t vfio_pci_dev_migrn_rw(struct vfio_pci_device *vdev, + char __user *buf, size_t count, loff_t *ppos, bool iswrite) +{ + unsigned int index = + VFIO_PCI_OFFSET_TO_INDEX(*ppos) - VFIO_PCI_NUM_REGIONS; + struct vfio_pci_migration_data *data = + (struct vfio_pci_migration_data *)vdev->region[index].data; + loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK; + struct vfio_device_migration_info *mig_ctl = data->mig_ctl; + int ret; + + if (pos >= vdev->region[index].size) + return -EINVAL; + + count = min(count, (size_t)(vdev->region[index].size - pos)); + if (pos >= VFIO_MIGRATION_REGION_DATA_OFFSET) + return vfio_pci_handle_mig_data_rw(data, + buf, count, pos, iswrite); + + switch (pos) { + case VFIO_DEVICE_MIGRATION_OFFSET(device_state): + ret = vfio_pci_handle_mig_dev_state(data, + buf, count, iswrite); + break; + case VFIO_DEVICE_MIGRATION_OFFSET(pending_bytes): + ret = vfio_pci_handle_mig_pending_bytes(mig_ctl, + buf, count, iswrite); + break; + case VFIO_DEVICE_MIGRATION_OFFSET(data_offset): + ret = vfio_pci_handle_mig_data_offset(mig_ctl, + buf, count, iswrite); + break; + case VFIO_DEVICE_MIGRATION_OFFSET(data_size): + ret = vfio_pci_handle_mig_data_size(mig_ctl, + buf, count, iswrite); + break; + case VFIO_DEVICE_MIGRATION_OFFSET(device_cmd): + ret = vfio_pci_handle_mig_dev_cmd(data, + buf, count, iswrite); + break; + case VFIO_DEVICE_MIGRATION_OFFSET(version_id): + ret = vfio_pci_handle_mig_drv_version(mig_ctl, + buf, count, iswrite); + break; + default: + dev_err(&vdev->pdev->dev, "invalid pos offset\n"); + ret = -EFAULT; + break; + } + + if (mig_ctl->device_state == VFIO_DEVICE_STATE_RESUMING && + mig_ctl->pending_bytes == data->state_size && + mig_ctl->data_size == data->state_size) { + if (vfio_pci_device_state_restore(data) != 0) { + dev_err(&vdev->pdev->dev, "Failed to restore device state!\n"); + return -EFAULT; + } + mig_ctl->pending_bytes = 0; + mig_ctl->data_size = 0; + } + + return ret; +} + +static void vfio_pci_dev_migrn_release(struct vfio_pci_device *vdev, + struct vfio_pci_region *region) +{ + struct vfio_pci_migration_data *data = region->data; + + if (data) { + kfree(data->mig_ctl); + kfree(data); + } +} + +static const struct vfio_pci_regops vfio_pci_migration_regops = { + .rw = vfio_pci_dev_migrn_rw, + .release = vfio_pci_dev_migrn_release, +}; + +static int vfio_pci_migration_info_init(struct pci_dev *pdev, + struct vfio_device_migration_info *mig_info, + struct vfio_pci_vendor_mig_driver *mig_drv) +{ + int ret; + + ret = vfio_pci_device_get_info(pdev, mig_info, mig_drv); + if (ret) { + dev_err(&pdev->dev, "failed to get device info\n"); + return ret; + } + + if (mig_info->data_size > VFIO_MIGRATION_BUFFER_MAX_SIZE) { + dev_err(&pdev->dev, "mig_info->data_size %llu is invalid\n", + mig_info->data_size); + return -EINVAL; + } + + mig_info->data_offset = VFIO_MIGRATION_REGION_DATA_OFFSET; + return ret; +} + +static int vfio_device_mig_data_init(struct vfio_pci_device *vdev, + struct vfio_pci_migration_data *data) +{ + struct vfio_device_migration_info *mig_ctl; + u64 mig_offset; + int ret; + + mig_ctl = kzalloc(sizeof(*mig_ctl), GFP_KERNEL); + if (!mig_ctl) + return -ENOMEM; + + ret = vfio_pci_migration_info_init(vdev->pdev, mig_ctl, + data->mig_driver); + if (ret) { + dev_err(&vdev->pdev->dev, "get device info error!\n"); + goto err; + } + + mig_offset = sizeof(struct vfio_device_migration_info); + data->state_size = mig_ctl->data_size; + data->mig_ctl = krealloc(mig_ctl, mig_offset + data->state_size, + GFP_KERNEL); + if (!data->mig_ctl) { + ret = -ENOMEM; + goto err; + } + + data->vf_data = (void *)((char *)data->mig_ctl + mig_offset); + memset(data->vf_data, 0, data->state_size); + data->mig_ctl->data_size = 0; + + ret = vfio_pci_register_dev_region(vdev, VFIO_REGION_TYPE_MIGRATION, + VFIO_REGION_SUBTYPE_MIGRATION, + &vfio_pci_migration_regops, mig_offset + data->state_size, + VFIO_REGION_INFO_FLAG_READ | VFIO_REGION_INFO_FLAG_WRITE, data); + if (ret) { + kfree(data->mig_ctl); + return ret; + } + + return 0; +err: + kfree(mig_ctl); + return ret; +} + +int vfio_pci_migration_init(struct vfio_pci_device *vdev) +{ + struct vfio_pci_vendor_mig_driver *mig_driver = NULL; + struct vfio_pci_migration_data *data = NULL; + struct pci_dev *pdev = vdev->pdev; + int ret; + + mig_driver = vfio_pci_get_mig_driver(pdev); + if (!mig_driver || !mig_driver->dev_mig_ops) { + dev_err(&pdev->dev, "unable to find a mig_driver module\n"); + return -EINVAL; + } + + if (!try_module_get(mig_driver->owner)) { + pr_err("module %s is not live\n", mig_driver->owner->name); + return -ENODEV; + } + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) { + module_put(mig_driver->owner); + return -ENOMEM; + } + + data->mig_driver = mig_driver; + data->vf_dev = pdev; + + ret = vfio_device_mig_data_init(vdev, data); + if (ret) { + dev_err(&pdev->dev, "failed to init vfio device migration data!\n"); + goto err; + } + + return ret; +err: + kfree(data); + module_put(mig_driver->owner); + return ret; +} + +void vfio_pci_migration_exit(struct vfio_pci_device *vdev) +{ + struct vfio_pci_vendor_mig_driver *mig_driver = NULL; + + mig_driver = vfio_pci_get_mig_driver(vdev->pdev); + if (!mig_driver || !mig_driver->dev_mig_ops) { + dev_warn(&vdev->pdev->dev, "mig_driver is not found\n"); + return; + } + + if (module_refcount(mig_driver->owner) > 0) { + vfio_pci_device_release(vdev->pdev, mig_driver); + module_put(mig_driver->owner); + } +} + +int vfio_pci_register_migration_ops(struct vfio_device_migration_ops *ops, + struct module *mod, struct pci_dev *pdev) +{ + struct vfio_pci_vendor_mig_driver *mig_driver = NULL; + + if (!ops || !mod || !pdev) + return -EINVAL; + + mig_driver = vfio_pci_find_mig_drv(pdev, mod); + if (mig_driver) { + pr_info("%s migration ops has already been registered\n", + mod->name); + atomic_add(1, &mig_driver->count); + return 0; + } + + if (!try_module_get(THIS_MODULE)) + return -ENODEV; + + mig_driver = kzalloc(sizeof(*mig_driver), GFP_KERNEL); + if (!mig_driver) { + module_put(THIS_MODULE); + return -ENOMEM; + } + + mig_driver->pdev = pdev; + mig_driver->bus_num = pdev->bus->number; + mig_driver->owner = mod; + mig_driver->dev_mig_ops = ops; + + vfio_pci_add_mig_drv(mig_driver); + + return 0; +} +EXPORT_SYMBOL_GPL(vfio_pci_register_migration_ops); + +void vfio_pci_unregister_migration_ops(struct module *mod, struct pci_dev *pdev) +{ + struct vfio_pci_vendor_mig_driver *mig_driver = NULL; + + if (!mod || !pdev) + return; + + mig_driver = vfio_pci_find_mig_drv(pdev, mod); + if (!mig_driver) { + pr_err("mig_driver is not found\n"); + return; + } + + if (atomic_sub_and_test(1, &mig_driver->count)) { + vfio_pci_remove_mig_drv(mig_driver); + kfree(mig_driver); + module_put(THIS_MODULE); + pr_info("%s succeed to unregister migration ops\n", + THIS_MODULE->name); + } +} +EXPORT_SYMBOL_GPL(vfio_pci_unregister_migration_ops); diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h index 17d2bae..03af269 100644 --- a/drivers/vfio/pci/vfio_pci_private.h +++ b/drivers/vfio/pci/vfio_pci_private.h @@ -15,6 +15,7 @@ #include <linux/pci.h> #include <linux/irqbypass.h> #include <linux/types.h> +#include <linux/vfio_pci_migration.h> #ifndef VFIO_PCI_PRIVATE_H #define VFIO_PCI_PRIVATE_H @@ -55,7 +56,7 @@ struct vfio_pci_irq_ctx { struct vfio_pci_region; struct vfio_pci_regops { - size_t (*rw)(struct vfio_pci_device *vdev, char __user *buf, + ssize_t (*rw)(struct vfio_pci_device *vdev, char __user *buf, size_t count, loff_t *ppos, bool iswrite); void (*release)(struct vfio_pci_device *vdev, struct vfio_pci_region *region); @@ -173,4 +174,15 @@ static inline int vfio_pci_igd_init(struct vfio_pci_device *vdev) return -ENODEV; } #endif + +extern bool vfio_dev_migration_is_supported(struct pci_dev *pdev); +extern int vfio_pci_migration_init(struct vfio_pci_device *vdev); +extern void vfio_pci_migration_exit(struct vfio_pci_device *vdev); +extern int vfio_pci_device_log_start(struct vfio_pci_device *vdev, + struct vf_migration_log_info *log_info); +extern int vfio_pci_device_log_stop(struct vfio_pci_device *vdev, + uint32_t uuid); +extern int vfio_pci_device_log_status_query(struct vfio_pci_device *vdev); +extern int vfio_pci_device_init(struct pci_dev *pdev); +extern void vfio_pci_device_uninit(struct pci_dev *pdev); #endif /* VFIO_PCI_PRIVATE_H */ diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 7a386fb..35f2a29 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -33,6 +33,7 @@ #include <linux/string.h> #include <linux/uaccess.h> #include <linux/vfio.h> +#include <linux/vfio_pci_migration.h> #include <linux/wait.h> #include <linux/sched/signal.h> @@ -40,6 +41,9 @@ #define DRIVER_AUTHOR "Alex Williamson <alex.williamson(a)redhat.com>" #define DRIVER_DESC "VFIO - User Level meta-driver" +#define LOG_BUF_FRAG_SIZE (2 * 1024 * 1024) // fix to 2M +#define LOG_BUF_MAX_ADDRS_SIZE 128 // max vm ram size is 1T + static struct vfio { struct class *class; struct list_head iommu_drivers_list; @@ -57,6 +61,14 @@ struct vfio_iommu_driver { struct list_head vfio_next; }; +struct vfio_log_buf { + struct vfio_log_buf_info info; + int fd; + int buffer_state; + int device_state; + unsigned long *cpu_addrs; +}; + struct vfio_container { struct kref kref; struct list_head group_list; @@ -64,6 +76,7 @@ struct vfio_container { struct vfio_iommu_driver *iommu_driver; void *iommu_data; bool noiommu; + struct vfio_log_buf log_buf; }; struct vfio_unbound_dev { @@ -1158,8 +1171,398 @@ static long vfio_ioctl_set_iommu(struct vfio_container *container, return ret; } +static long vfio_dispatch_cmd_to_devices(const struct vfio_container *container, + unsigned int cmd, unsigned long arg) +{ + struct vfio_group *group = NULL; + struct vfio_device *device = NULL; + long ret = -ENXIO; + + list_for_each_entry(group, &container->group_list, container_next) { + list_for_each_entry(device, &group->device_list, group_next) { + ret = device->ops->ioctl(device->device_data, cmd, arg); + if (ret) { + pr_err("dispatch cmd to devices failed\n"); + return ret; + } + } + } + return ret; +} + +static long vfio_log_buf_start(struct vfio_container *container) +{ + struct vfio_log_buf_ctl log_buf_ctl; + long ret; + + log_buf_ctl.argsz = sizeof(struct vfio_log_buf_info); + log_buf_ctl.flags = VFIO_DEVICE_LOG_BUF_FLAG_START; + log_buf_ctl.data = (void *)&container->log_buf.info; + ret = vfio_dispatch_cmd_to_devices(container, VFIO_DEVICE_LOG_BUF_CTL, + (unsigned long)&log_buf_ctl); + if (ret) + return ret; + + container->log_buf.device_state = 1; + return 0; +} + +static long vfio_log_buf_stop(struct vfio_container *container) +{ + struct vfio_log_buf_ctl log_buf_ctl; + long ret; + + if (container->log_buf.device_state == 0) { + pr_warn("device already stopped\n"); + return 0; + } + + log_buf_ctl.argsz = sizeof(struct vfio_log_buf_info); + log_buf_ctl.flags = VFIO_DEVICE_LOG_BUF_FLAG_STOP; + log_buf_ctl.data = (void *)&container->log_buf.info; + ret = vfio_dispatch_cmd_to_devices(container, VFIO_DEVICE_LOG_BUF_CTL, + (unsigned long)&log_buf_ctl); + if (ret) + return ret; + + container->log_buf.device_state = 0; + return 0; +} + +static long vfio_log_buf_query(struct vfio_container *container) +{ + struct vfio_log_buf_ctl log_buf_ctl; + + log_buf_ctl.argsz = sizeof(struct vfio_log_buf_info); + log_buf_ctl.flags = VFIO_DEVICE_LOG_BUF_FLAG_STATUS_QUERY; + log_buf_ctl.data = (void *)&container->log_buf.info; + + return vfio_dispatch_cmd_to_devices(container, + VFIO_DEVICE_LOG_BUF_CTL, (unsigned long)&log_buf_ctl); +} + +static int vfio_log_buf_fops_mmap(struct file *filep, + struct vm_area_struct *vma) +{ + struct vfio_container *container = filep->private_data; + struct vfio_log_buf *log_buf = &container->log_buf; + unsigned long frag_pg_size; + unsigned long frag_offset; + phys_addr_t pa; + int ret = -EINVAL; + + if (!log_buf->cpu_addrs) { + pr_err("mmap before setup, please setup log buf first\n"); + return ret; + } + + if (log_buf->info.frag_size < PAGE_SIZE) { + pr_err("mmap frag size should not less than page size!\n"); + return ret; + } + + frag_pg_size = log_buf->info.frag_size / PAGE_SIZE; + frag_offset = vma->vm_pgoff / frag_pg_size; + + if (frag_offset >= log_buf->info.addrs_size) { + pr_err("mmap offset out of range!\n"); + return ret; + } + + if (vma->vm_end - vma->vm_start != log_buf->info.frag_size) { + pr_err("mmap size error, should be aligned with frag size!\n"); + return ret; + } + + pa = virt_to_phys((void *)log_buf->cpu_addrs[frag_offset]); + ret = remap_pfn_range(vma, vma->vm_start, + pa >> PAGE_SHIFT, + vma->vm_end - vma->vm_start, + vma->vm_page_prot); + if (ret) + pr_err("remap_pfn_range error!\n"); + return ret; +} + +static struct device *vfio_get_dev(struct vfio_container *container) +{ + struct vfio_group *group = NULL; + struct vfio_device *device = NULL; + + list_for_each_entry(group, &container->group_list, container_next) { + list_for_each_entry(device, &group->device_list, group_next) { + return device->dev; + } + } + return NULL; +} + +static void vfio_log_buf_release_dma(struct device *dev, + struct vfio_log_buf *log_buf) +{ + int i; + + for (i = 0; i < log_buf->info.addrs_size; i++) { + if ((log_buf->cpu_addrs && log_buf->cpu_addrs[i] != 0) && + (log_buf->info.sgevec && + log_buf->info.sgevec[i].addr != 0)) { + dma_free_coherent(dev, log_buf->info.frag_size, + (void *)log_buf->cpu_addrs[i], + log_buf->info.sgevec[i].addr); + log_buf->cpu_addrs[i] = 0; + log_buf->info.sgevec[i].addr = 0; + } + } +} + +static long vfio_log_buf_alloc_dma(struct vfio_log_buf_info *info, + struct vfio_log_buf *log_buf, struct device *dev) +{ + int i; + + for (i = 0; i < info->addrs_size; i++) { + log_buf->cpu_addrs[i] = (unsigned long)dma_alloc_coherent(dev, + info->frag_size, &log_buf->info.sgevec[i].addr, + GFP_KERNEL); + log_buf->info.sgevec[i].len = info->frag_size; + if (log_buf->cpu_addrs[i] == 0 || + log_buf->info.sgevec[i].addr == 0) { + return -ENOMEM; + } + } + return 0; +} + +static long vfio_log_buf_alloc_addrs(struct vfio_log_buf_info *info, + struct vfio_log_buf *log_buf) +{ + log_buf->info.sgevec = kcalloc(info->addrs_size, + sizeof(struct vfio_log_buf_sge), GFP_KERNEL); + if (!log_buf->info.sgevec) + return -ENOMEM; + + log_buf->cpu_addrs = kcalloc(info->addrs_size, + sizeof(unsigned long), GFP_KERNEL); + if (!log_buf->cpu_addrs) { + kfree(log_buf->info.sgevec); + log_buf->info.sgevec = NULL; + return -ENOMEM; + } + + return 0; +} + +static long vfio_log_buf_info_valid(struct vfio_log_buf_info *info) +{ + if (info->addrs_size > LOG_BUF_MAX_ADDRS_SIZE || + info->addrs_size == 0) { + pr_err("can`t support vm ram size larger than 1T or equal to 0\n"); + return -EINVAL; + } + if (info->frag_size != LOG_BUF_FRAG_SIZE) { + pr_err("only support %d frag size\n", LOG_BUF_FRAG_SIZE); + return -EINVAL; + } + return 0; +} + +static long vfio_log_buf_setup(struct vfio_container *container, + unsigned long data) +{ + struct vfio_log_buf_info info; + struct vfio_log_buf *log_buf = &container->log_buf; + struct device *dev = NULL; + long ret; + + if (log_buf->info.sgevec) { + pr_warn("log buf already setup\n"); + return 0; + } + + if (copy_from_user(&info, (void __user *)data, + sizeof(struct vfio_log_buf_info))) + return -EFAULT; + + ret = vfio_log_buf_info_valid(&info); + if (ret) + return ret; + + ret = vfio_log_buf_alloc_addrs(&info, log_buf); + if (ret) + goto err_out; + + dev = vfio_get_dev(container); + if (!dev) { + pr_err("can`t get dev\n"); + goto err_free_addrs; + } + + ret = vfio_log_buf_alloc_dma(&info, log_buf, dev); + if (ret) + goto err_free_dma_array; + + log_buf->info.uuid = info.uuid; + log_buf->info.buffer_size = info.buffer_size; + log_buf->info.frag_size = info.frag_size; + log_buf->info.addrs_size = info.addrs_size; + log_buf->buffer_state = 1; + return 0; + +err_free_dma_array: + vfio_log_buf_release_dma(dev, log_buf); +err_free_addrs: + kfree(log_buf->cpu_addrs); + log_buf->cpu_addrs = NULL; + kfree(log_buf->info.sgevec); + log_buf->info.sgevec = NULL; +err_out: + return -ENOMEM; +} + +static long vfio_log_buf_release_buffer(struct vfio_container *container) +{ + struct vfio_log_buf *log_buf = &container->log_buf; + struct device *dev = NULL; + + if (log_buf->buffer_state == 0) { + pr_warn("buffer already released\n"); + return 0; + } + + dev = vfio_get_dev(container); + if (!dev) { + pr_err("can`t get dev\n"); + return -EFAULT; + } + + vfio_log_buf_release_dma(dev, log_buf); + + kfree(log_buf->cpu_addrs); + log_buf->cpu_addrs = NULL; + + kfree(log_buf->info.sgevec); + log_buf->info.sgevec = NULL; + + log_buf->buffer_state = 0; + return 0; +} + +static int vfio_log_buf_release(struct inode *inode, struct file *filep) +{ + struct vfio_container *container = filep->private_data; + + vfio_log_buf_stop(container); + vfio_log_buf_release_buffer(container); + memset(&container->log_buf, 0, sizeof(struct vfio_log_buf)); + return 0; +} + +static long vfio_ioctl_handle_log_buf_ctl(struct vfio_container *container, + unsigned long arg) +{ + struct vfio_log_buf_ctl log_buf_ctl; + long ret = 0; + + if (copy_from_user(&log_buf_ctl, (void __user *)arg, + sizeof(struct vfio_log_buf_ctl))) + return -EFAULT; + + switch (log_buf_ctl.flags) { + case VFIO_DEVICE_LOG_BUF_FLAG_SETUP: + ret = vfio_log_buf_setup(container, + (unsigned long)log_buf_ctl.data); + break; + case VFIO_DEVICE_LOG_BUF_FLAG_RELEASE: + ret = vfio_log_buf_release_buffer(container); + break; + case VFIO_DEVICE_LOG_BUF_FLAG_START: + ret = vfio_log_buf_start(container); + break; + case VFIO_DEVICE_LOG_BUF_FLAG_STOP: + ret = vfio_log_buf_stop(container); + break; + case VFIO_DEVICE_LOG_BUF_FLAG_STATUS_QUERY: + ret = vfio_log_buf_query(container); + break; + default: + pr_err("log buf control flag incorrect\n"); + ret = -EINVAL; + break; + } + return ret; +} + +static long vfio_log_buf_fops_unl_ioctl(struct file *filep, + unsigned int cmd, unsigned long arg) +{ + struct vfio_container *container = filep->private_data; + long ret = -EINVAL; + + switch (cmd) { + case VFIO_LOG_BUF_CTL: + ret = vfio_ioctl_handle_log_buf_ctl(container, arg); + break; + default: + pr_err("log buf control cmd incorrect\n"); + break; + } + + return ret; +} + +#ifdef CONFIG_COMPAT +static long vfio_log_buf_fops_compat_ioctl(struct file *filep, + unsigned int cmd, unsigned long arg) +{ + arg = (unsigned long)compat_ptr(arg); + return vfio_log_buf_fops_unl_ioctl(filep, cmd, arg); +} +#endif /* CONFIG_COMPAT */ + +static const struct file_operations vfio_log_buf_fops = { + .owner = THIS_MODULE, + .mmap = vfio_log_buf_fops_mmap, + .unlocked_ioctl = vfio_log_buf_fops_unl_ioctl, + .release = vfio_log_buf_release, +#ifdef CONFIG_COMPAT + .compat_ioctl = vfio_log_buf_fops_compat_ioctl, +#endif +}; + +static int vfio_get_log_buf_fd(struct vfio_container *container, + unsigned long arg) +{ + struct file *filep = NULL; + int ret; + + if (container->log_buf.fd > 0) + return container->log_buf.fd; + + ret = get_unused_fd_flags(O_CLOEXEC); + if (ret < 0) { + pr_err("get_unused_fd_flags get fd failed\n"); + return ret; + } + + filep = anon_inode_getfile("[vfio-log-buf]", &vfio_log_buf_fops, + container, O_RDWR); + if (IS_ERR(filep)) { + pr_err("anon_inode_getfile failed\n"); + put_unused_fd(ret); + ret = PTR_ERR(filep); + return ret; + } + + filep->f_mode |= (FMODE_READ | FMODE_WRITE | FMODE_LSEEK); + + fd_install(ret, filep); + + container->log_buf.fd = ret; + return ret; +} + static long vfio_fops_unl_ioctl(struct file *filep, - unsigned int cmd, unsigned long arg) + unsigned int cmd, unsigned long arg) { struct vfio_container *container = filep->private_data; struct vfio_iommu_driver *driver; @@ -1179,6 +1582,9 @@ static long vfio_fops_unl_ioctl(struct file *filep, case VFIO_SET_IOMMU: ret = vfio_ioctl_set_iommu(container, arg); break; + case VFIO_GET_LOG_BUF_FD: + ret = vfio_get_log_buf_fd(container, arg); + break; default: driver = container->iommu_driver; data = container->iommu_data; @@ -1210,6 +1616,7 @@ static int vfio_fops_open(struct inode *inode, struct file *filep) INIT_LIST_HEAD(&container->group_list); init_rwsem(&container->group_lock); kref_init(&container->kref); + memset(&container->log_buf, 0, sizeof(struct vfio_log_buf)); filep->private_data = container; @@ -1219,9 +1626,7 @@ static int vfio_fops_open(struct inode *inode, struct file *filep) static int vfio_fops_release(struct inode *inode, struct file *filep) { struct vfio_container *container = filep->private_data; - filep->private_data = NULL; - vfio_container_put(container); return 0; diff --git a/include/linux/vfio_pci_migration.h b/include/linux/vfio_pci_migration.h new file mode 100644 index 0000000..464ffb4 --- /dev/null +++ b/include/linux/vfio_pci_migration.h @@ -0,0 +1,136 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2022 Huawei Technologies Co., Ltd. All rights reserved. + */ + +#ifndef VFIO_PCI_MIGRATION_H +#define VFIO_PCI_MIGRATION_H + +#include <linux/types.h> +#include <linux/pci.h> + +#define VFIO_REGION_TYPE_MIGRATION (3) +/* sub-types for VFIO_REGION_TYPE_MIGRATION */ +#define VFIO_REGION_SUBTYPE_MIGRATION (1) + +#define VFIO_MIGRATION_BUFFER_MAX_SIZE SZ_256K +#define VFIO_MIGRATION_REGION_DATA_OFFSET \ + (sizeof(struct vfio_device_migration_info)) +#define VFIO_DEVICE_MIGRATION_OFFSET(x) \ + offsetof(struct vfio_device_migration_info, x) + +struct vfio_device_migration_info { + __u32 device_state; /* VFIO device state */ +#define VFIO_DEVICE_STATE_STOP (0) +#define VFIO_DEVICE_STATE_RUNNING (1 << 0) +#define VFIO_DEVICE_STATE_SAVING (1 << 1) +#define VFIO_DEVICE_STATE_RESUMING (1 << 2) +#define VFIO_DEVICE_STATE_MASK (VFIO_DEVICE_STATE_RUNNING | \ + VFIO_DEVICE_STATE_SAVING | VFIO_DEVICE_STATE_RESUMING) + __u32 reserved; + + __u32 device_cmd; + __u32 version_id; + + __u64 pending_bytes; + __u64 data_offset; + __u64 data_size; +}; + +enum { + VFIO_DEVICE_STOP = 0xffff0001, + VFIO_DEVICE_CONTINUE, + VFIO_DEVICE_MIGRATION_CANCEL, +}; + +struct vfio_log_buf_sge { + __u64 len; + __u64 addr; +}; + +struct vfio_log_buf_info { + __u32 uuid; + __u64 buffer_size; + __u64 addrs_size; + __u64 frag_size; + struct vfio_log_buf_sge *sgevec; +}; + +struct vfio_log_buf_ctl { + __u32 argsz; + __u32 flags; + #define VFIO_DEVICE_LOG_BUF_FLAG_SETUP (1 << 0) + #define VFIO_DEVICE_LOG_BUF_FLAG_RELEASE (1 << 1) + #define VFIO_DEVICE_LOG_BUF_FLAG_START (1 << 2) + #define VFIO_DEVICE_LOG_BUF_FLAG_STOP (1 << 3) + #define VFIO_DEVICE_LOG_BUF_FLAG_STATUS_QUERY (1 << 4) + void *data; +}; +#define VFIO_LOG_BUF_CTL _IO(VFIO_TYPE, VFIO_BASE + 21) +#define VFIO_GET_LOG_BUF_FD _IO(VFIO_TYPE, VFIO_BASE + 22) +#define VFIO_DEVICE_LOG_BUF_CTL _IO(VFIO_TYPE, VFIO_BASE + 23) + +struct vf_migration_log_info { + __u32 dom_uuid; + __u64 buffer_size; + __u64 sge_len; + __u64 sge_num; + struct vfio_log_buf_sge *sgevec; +}; + +struct vfio_device_migration_ops { + /* Get device information */ + int (*get_info)(struct pci_dev *pdev, + struct vfio_device_migration_info *info); + /* Enable a vf device */ + int (*enable)(struct pci_dev *pdev); + /* Disable a vf device */ + int (*disable)(struct pci_dev *pdev); + /* Save a vf device */ + int (*save)(struct pci_dev *pdev, void *base, + uint64_t off, uint64_t count); + /* Resuming a vf device */ + int (*restore)(struct pci_dev *pdev, void *base, + uint64_t off, uint64_t count); + /* Log start a vf device */ + int (*log_start)(struct pci_dev *pdev, + struct vf_migration_log_info *log_info); + /* Log stop a vf device */ + int (*log_stop)(struct pci_dev *pdev, uint32_t uuid); + /* Get vf device log status */ + int (*get_log_status)(struct pci_dev *pdev); + /* Pre enable a vf device(load_setup, before restore a vf) */ + int (*pre_enable)(struct pci_dev *pdev); + /* Cancel a vf device when live migration failed (rollback) */ + int (*cancel)(struct pci_dev *pdev); + /* Init a vf device */ + int (*init)(struct pci_dev *pdev); + /* Uninit a vf device */ + void (*uninit)(struct pci_dev *pdev); + /* Release a vf device */ + void (*release)(struct pci_dev *pdev); +}; + +struct vfio_pci_vendor_mig_driver { + struct pci_dev *pdev; + unsigned char bus_num; + struct vfio_device_migration_ops *dev_mig_ops; + struct module *owner; + atomic_t count; + struct list_head list; +}; + +struct vfio_pci_migration_data { + u64 state_size; + struct pci_dev *vf_dev; + struct vfio_pci_vendor_mig_driver *mig_driver; + struct vfio_device_migration_info *mig_ctl; + void *vf_data; +}; + +int vfio_pci_register_migration_ops(struct vfio_device_migration_ops *ops, + struct module *mod, struct pci_dev *pdev); +void vfio_pci_unregister_migration_ops(struct module *mod, + struct pci_dev *pdev); + +#endif /* VFIO_PCI_MIGRATION_H */ -- 1.8.3.1

2 1

[PATCH] vfio: framework supporting vfio device hot migration
by RongWang 24 Jun '22

24 Jun '22

From: Rong Wang <w_angrong(a)163.com> kunpeng inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I5CO9A CVE: NA --------------------------------- As pass through devices, hypervisor can`t control the status of device, and can`t track dirty memory DMA from device, during migration. The goal of this framework is to combine hardware to accomplish the task above. qemu |status control and dirty memory report vfio |ops to hardware hardware Signed-off-by: Rong Wang <w_angrong(a)163.com> Signed-off-by: HuHua Li <18245010845(a)163.com> Signed-off-by: Ripeng Qiu <965412048(a)qq.com> --- drivers/vfio/pci/Makefile | 2 +- drivers/vfio/pci/vfio_pci.c | 54 +++ drivers/vfio/pci/vfio_pci_migration.c | 755 ++++++++++++++++++++++++++++++++++ drivers/vfio/pci/vfio_pci_private.h | 14 +- drivers/vfio/vfio.c | 411 +++++++++++++++++- include/linux/vfio_pci_migration.h | 136 ++++++ 6 files changed, 1367 insertions(+), 5 deletions(-) create mode 100644 drivers/vfio/pci/vfio_pci_migration.c create mode 100644 include/linux/vfio_pci_migration.h diff --git a/drivers/vfio/pci/Makefile b/drivers/vfio/pci/Makefile index 76d8ec0..80a777d 100644 --- a/drivers/vfio/pci/Makefile +++ b/drivers/vfio/pci/Makefile @@ -1,5 +1,5 @@ -vfio-pci-y := vfio_pci.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_config.o +vfio-pci-y := vfio_pci.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_config.o vfio_pci_migration.o vfio-pci-$(CONFIG_VFIO_PCI_IGD) += vfio_pci_igd.o obj-$(CONFIG_VFIO_PCI) += vfio-pci.o diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 51b791c..59d8280 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -30,6 +30,7 @@ #include <linux/vgaarb.h> #include <linux/nospec.h> #include <linux/sched/mm.h> +#include <linux/vfio_pci_migration.h> #include "vfio_pci_private.h" @@ -296,6 +297,14 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev) vfio_pci_probe_mmaps(vdev); + if (vfio_dev_migration_is_supported(pdev)) { + ret = vfio_pci_migration_init(vdev); + if (ret) { + dev_warn(&vdev->pdev->dev, "Failed to init vfio_pci_migration\n"); + vfio_pci_disable(vdev); + return ret; + } + } return 0; } @@ -392,6 +401,7 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev) out: pci_disable_device(pdev); + vfio_pci_migration_exit(vdev); vfio_pci_try_bus_reset(vdev); if (!disable_idle_d3) @@ -642,6 +652,41 @@ struct vfio_devices { int max_index; }; +static long vfio_pci_handle_log_buf_ctl(struct vfio_pci_device *vdev, + const unsigned long arg) +{ + struct vfio_log_buf_ctl *log_buf_ctl = NULL; + struct vfio_log_buf_info *log_buf_info = NULL; + struct vf_migration_log_info migration_log_info; + long ret = 0; + + log_buf_ctl = (struct vfio_log_buf_ctl *)arg; + log_buf_info = (struct vfio_log_buf_info *)log_buf_ctl->data; + + switch (log_buf_ctl->flags) { + case VFIO_DEVICE_LOG_BUF_FLAG_START: + migration_log_info.dom_uuid = log_buf_info->uuid; + migration_log_info.buffer_size = + log_buf_info->buffer_size; + migration_log_info.sge_num = log_buf_info->addrs_size; + migration_log_info.sge_len = log_buf_info->frag_size; + migration_log_info.sgevec = log_buf_info->sgevec; + ret = vfio_pci_device_log_start(vdev, + &migration_log_info); + break; + case VFIO_DEVICE_LOG_BUF_FLAG_STOP: + ret = vfio_pci_device_log_stop(vdev, + log_buf_info->uuid); + break; + case VFIO_DEVICE_LOG_BUF_FLAG_STATUS_QUERY: + ret = vfio_pci_device_log_status_query(vdev); + break; + default: + ret = -EINVAL; + break; + } + return ret; +} static long vfio_pci_ioctl(void *device_data, unsigned int cmd, unsigned long arg) { @@ -1142,6 +1187,8 @@ static long vfio_pci_ioctl(void *device_data, return vfio_pci_ioeventfd(vdev, ioeventfd.offset, ioeventfd.data, count, ioeventfd.fd); + } else if (cmd == VFIO_DEVICE_LOG_BUF_CTL) { + return vfio_pci_handle_log_buf_ctl(vdev, arg); } return -ENOTTY; @@ -1566,6 +1613,9 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) pci_set_power_state(pdev, PCI_D3hot); } + if (vfio_dev_migration_is_supported(pdev)) + ret = vfio_pci_device_init(pdev); + return ret; } @@ -1591,6 +1641,10 @@ static void vfio_pci_remove(struct pci_dev *pdev) if (!disable_idle_d3) pci_set_power_state(pdev, PCI_D0); + + if (vfio_dev_migration_is_supported(pdev)) { + vfio_pci_device_uninit(pdev); + } } static pci_ers_result_t vfio_pci_aer_err_detected(struct pci_dev *pdev, diff --git a/drivers/vfio/pci/vfio_pci_migration.c b/drivers/vfio/pci/vfio_pci_migration.c new file mode 100644 index 0000000..f69cd13 --- /dev/null +++ b/drivers/vfio/pci/vfio_pci_migration.c @@ -0,0 +1,755 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2022 Huawei Technologies Co., Ltd. All rights reserved. + */ + +#include <linux/module.h> +#include <linux/io.h> +#include <linux/pci.h> +#include <linux/uaccess.h> +#include <linux/vfio.h> +#include <linux/vfio_pci_migration.h> + +#include "vfio_pci_private.h" + +static LIST_HEAD(vfio_pci_mig_drivers_list); +static DEFINE_MUTEX(vfio_pci_mig_drivers_mutex); + +static void vfio_pci_add_mig_drv(struct vfio_pci_vendor_mig_driver *mig_drv) +{ + mutex_lock(&vfio_pci_mig_drivers_mutex); + atomic_set(&mig_drv->count, 1); + list_add_tail(&mig_drv->list, &vfio_pci_mig_drivers_list); + mutex_unlock(&vfio_pci_mig_drivers_mutex); +} + +static void vfio_pci_remove_mig_drv(struct vfio_pci_vendor_mig_driver *mig_drv) +{ + mutex_lock(&vfio_pci_mig_drivers_mutex); + list_del(&mig_drv->list); + mutex_unlock(&vfio_pci_mig_drivers_mutex); +} + +static struct vfio_pci_vendor_mig_driver * + vfio_pci_find_mig_drv(struct pci_dev *pdev, struct module *module) +{ + struct vfio_pci_vendor_mig_driver *mig_drv = NULL; + + mutex_lock(&vfio_pci_mig_drivers_mutex); + list_for_each_entry(mig_drv, &vfio_pci_mig_drivers_list, list) { + if (mig_drv->owner == module) { + if (mig_drv->bus_num == pdev->bus->number) + goto out; + } + } + mig_drv = NULL; +out: + mutex_unlock(&vfio_pci_mig_drivers_mutex); + return mig_drv; +} + +static struct vfio_pci_vendor_mig_driver * + vfio_pci_get_mig_driver(struct pci_dev *pdev) +{ + struct vfio_pci_vendor_mig_driver *mig_drv = NULL; + struct pci_dev *pf_dev = pci_physfn(pdev); + + mutex_lock(&vfio_pci_mig_drivers_mutex); + list_for_each_entry(mig_drv, &vfio_pci_mig_drivers_list, list) { + if (mig_drv->bus_num == pf_dev->bus->number) + goto out; + } + mig_drv = NULL; +out: + mutex_unlock(&vfio_pci_mig_drivers_mutex); + return mig_drv; +} + +bool vfio_dev_migration_is_supported(struct pci_dev *pdev) +{ + struct vfio_pci_vendor_mig_driver *mig_driver = NULL; + + mig_driver = vfio_pci_get_mig_driver(pdev); + if (!mig_driver || !mig_driver->dev_mig_ops) { + dev_warn(&pdev->dev, "unable to find a mig_drv module\n"); + return false; + } + + return true; +} + +int vfio_pci_device_log_start(struct vfio_pci_device *vdev, + struct vf_migration_log_info *log_info) +{ + struct vfio_pci_vendor_mig_driver *mig_driver; + + mig_driver = vfio_pci_get_mig_driver(vdev->pdev); + if (!mig_driver || !mig_driver->dev_mig_ops) { + dev_err(&vdev->pdev->dev, "unable to find a mig_drv module\n"); + return -EFAULT; + } + + if (!mig_driver->dev_mig_ops->log_start || + (mig_driver->dev_mig_ops->log_start(vdev->pdev, + log_info) != 0)) { + dev_err(&vdev->pdev->dev, "failed to set log start\n"); + return -EFAULT; + } + + return 0; +} + +int vfio_pci_device_log_stop(struct vfio_pci_device *vdev, uint32_t uuid) +{ + struct vfio_pci_vendor_mig_driver *mig_driver; + + mig_driver = vfio_pci_get_mig_driver(vdev->pdev); + if (!mig_driver || !mig_driver->dev_mig_ops) { + dev_err(&vdev->pdev->dev, "unable to find a mig_drv module\n"); + return -EFAULT; + } + + if (!mig_driver->dev_mig_ops->log_stop || + (mig_driver->dev_mig_ops->log_stop(vdev->pdev, uuid) != 0)) { + dev_err(&vdev->pdev->dev, "failed to set log stop\n"); + return -EFAULT; + } + + return 0; +} + +int vfio_pci_device_log_status_query(struct vfio_pci_device *vdev) +{ + struct vfio_pci_vendor_mig_driver *mig_driver; + + mig_driver = vfio_pci_get_mig_driver(vdev->pdev); + if (!mig_driver || !mig_driver->dev_mig_ops) { + dev_err(&vdev->pdev->dev, "unable to find a mig_drv module\n"); + return -EFAULT; + } + + if (!mig_driver->dev_mig_ops->get_log_status || + (mig_driver->dev_mig_ops->get_log_status(vdev->pdev) != 0)) { + dev_err(&vdev->pdev->dev, "failed to get log status\n"); + return -EFAULT; + } + + return 0; +} + +int vfio_pci_device_init(struct pci_dev *pdev) +{ + struct vfio_pci_vendor_mig_driver *mig_drv; + + mig_drv = vfio_pci_get_mig_driver(pdev); + if (!mig_drv || !mig_drv->dev_mig_ops) { + dev_err(&pdev->dev, "unable to find a mig_drv module\n"); + return -EFAULT; + } + + if (mig_drv->dev_mig_ops->init) + return mig_drv->dev_mig_ops->init(pdev); + + return -EFAULT; +} + +void vfio_pci_device_uninit(struct pci_dev *pdev) +{ + struct vfio_pci_vendor_mig_driver *mig_drv; + + mig_drv = vfio_pci_get_mig_driver(pdev); + if (!mig_drv || !mig_drv->dev_mig_ops) { + dev_err(&pdev->dev, "unable to find a mig_drv module\n"); + return; + } + + if (mig_drv->dev_mig_ops->uninit) + mig_drv->dev_mig_ops->uninit(pdev); +} + +static void vfio_pci_device_release(struct pci_dev *pdev, + struct vfio_pci_vendor_mig_driver *mig_drv) +{ + if (mig_drv->dev_mig_ops->release) + mig_drv->dev_mig_ops->release(pdev); +} + +static int vfio_pci_device_get_info(struct pci_dev *pdev, + struct vfio_device_migration_info *mig_info, + struct vfio_pci_vendor_mig_driver *mig_drv) +{ + if (mig_drv->dev_mig_ops->get_info) + return mig_drv->dev_mig_ops->get_info(pdev, mig_info); + return -EFAULT; +} + +static int vfio_pci_device_enable(struct pci_dev *pdev, + struct vfio_pci_vendor_mig_driver *mig_drv) +{ + if (!mig_drv->dev_mig_ops->enable || + (mig_drv->dev_mig_ops->enable(pdev) != 0)) { + return -EINVAL; + } + + return 0; +} + +static int vfio_pci_device_disable(struct pci_dev *pdev, + struct vfio_pci_vendor_mig_driver *mig_drv) +{ + if (!mig_drv->dev_mig_ops->disable || + (mig_drv->dev_mig_ops->disable(pdev) != 0)) + return -EINVAL; + + return 0; +} + +static int vfio_pci_device_pre_enable(struct pci_dev *pdev, + struct vfio_pci_vendor_mig_driver *mig_drv) +{ + if (!mig_drv->dev_mig_ops->pre_enable || + (mig_drv->dev_mig_ops->pre_enable(pdev) != 0)) + return -EINVAL; + + return 0; +} + +static int vfio_pci_device_state_save(struct pci_dev *pdev, + struct vfio_pci_migration_data *data) +{ + struct vfio_device_migration_info *mig_info = data->mig_ctl; + struct vfio_pci_vendor_mig_driver *mig_drv = data->mig_driver; + void *base = (void *)mig_info; + int ret = 0; + + if ((mig_info->device_state & VFIO_DEVICE_STATE_RUNNING) != 0) { + ret = vfio_pci_device_disable(pdev, mig_drv); + if (ret) { + dev_err(&pdev->dev, "failed to stop VF function!\n"); + return ret; + } + mig_info->device_state &= ~VFIO_DEVICE_STATE_RUNNING; + } + + if (mig_drv->dev_mig_ops && mig_drv->dev_mig_ops->save) { + ret = mig_drv->dev_mig_ops->save(pdev, base, + mig_info->data_offset, data->state_size); + if (ret) { + dev_err(&pdev->dev, "failed to save device state!\n"); + return -EINVAL; + } + } else { + return -EFAULT; + } + + mig_info->data_size = data->state_size; + mig_info->pending_bytes = mig_info->data_size; + return ret; +} + +static int vfio_pci_device_state_restore(struct vfio_pci_migration_data *data) +{ + struct vfio_device_migration_info *mig_info = data->mig_ctl; + struct vfio_pci_vendor_mig_driver *mig_drv = data->mig_driver; + struct pci_dev *pdev = data->vf_dev; + void *base = (void *)mig_info; + int ret; + + if (mig_drv->dev_mig_ops && mig_drv->dev_mig_ops->restore) { + ret = mig_drv->dev_mig_ops->restore(pdev, base, + mig_info->data_offset, mig_info->data_size); + if (ret) { + dev_err(&pdev->dev, "failed to restore device state!\n"); + return -EINVAL; + } + return 0; + } + + return -EFAULT; +} + +static int vfio_pci_set_device_state(struct vfio_pci_migration_data *data, + u32 state) +{ + struct vfio_device_migration_info *mig_ctl = data->mig_ctl; + struct vfio_pci_vendor_mig_driver *mig_drv = data->mig_driver; + struct pci_dev *pdev = data->vf_dev; + int ret = 0; + + if (state == mig_ctl->device_state) + return 0; + + if (!mig_drv->dev_mig_ops) + return -EINVAL; + + switch (state) { + case VFIO_DEVICE_STATE_RUNNING: + if (!(mig_ctl->device_state & + VFIO_DEVICE_STATE_RUNNING)) + ret = vfio_pci_device_enable(pdev, mig_drv); + break; + case VFIO_DEVICE_STATE_SAVING | VFIO_DEVICE_STATE_RUNNING: + /* + * (pre-copy) - device should start logging data. + */ + ret = 0; + break; + case VFIO_DEVICE_STATE_SAVING: + /* stop the vf function, save state */ + ret = vfio_pci_device_state_save(pdev, data); + break; + case VFIO_DEVICE_STATE_STOP: + if (mig_ctl->device_state & VFIO_DEVICE_STATE_RUNNING) + ret = vfio_pci_device_disable(pdev, mig_drv); + break; + case VFIO_DEVICE_STATE_RESUMING: + ret = vfio_pci_device_pre_enable(pdev, mig_drv); + break; + default: + ret = -EFAULT; + break; + } + + if (ret) + return ret; + + mig_ctl->device_state = state; + return 0; +} + +static ssize_t vfio_pci_handle_mig_dev_state( + struct vfio_pci_migration_data *data, + char __user *buf, size_t count, bool iswrite) +{ + struct vfio_device_migration_info *mig_ctl = data->mig_ctl; + u32 device_state; + int ret; + + if (count != sizeof(device_state)) + return -EINVAL; + + if (iswrite) { + if (copy_from_user(&device_state, buf, count)) + return -EFAULT; + + ret = vfio_pci_set_device_state(data, device_state); + if (ret) + return ret; + } else { + if (copy_to_user(buf, &mig_ctl->device_state, count)) + return -EFAULT; + } + + return count; +} + +static ssize_t vfio_pci_handle_mig_pending_bytes( + struct vfio_device_migration_info *mig_info, + char __user *buf, size_t count, bool iswrite) +{ + u64 pending_bytes; + + if (count != sizeof(pending_bytes) || iswrite) + return -EINVAL; + + if (mig_info->device_state == + (VFIO_DEVICE_STATE_SAVING | VFIO_DEVICE_STATE_RUNNING)) { + /* In pre-copy state we have no data to return for now, + * return 0 pending bytes + */ + pending_bytes = 0; + } else { + pending_bytes = mig_info->pending_bytes; + } + + if (copy_to_user(buf, &pending_bytes, count)) + return -EFAULT; + + return count; +} + +static ssize_t vfio_pci_handle_mig_data_offset( + struct vfio_device_migration_info *mig_info, + char __user *buf, size_t count, bool iswrite) +{ + u64 data_offset = mig_info->data_offset; + + if (count != sizeof(data_offset) || iswrite) + return -EINVAL; + + if (copy_to_user(buf, &data_offset, count)) + return -EFAULT; + + return count; +} + +static ssize_t vfio_pci_handle_mig_data_size( + struct vfio_device_migration_info *mig_info, + char __user *buf, size_t count, bool iswrite) +{ + u64 data_size; + + if (count != sizeof(data_size)) + return -EINVAL; + + if (iswrite) { + /* data_size is writable only during resuming state */ + if (mig_info->device_state != VFIO_DEVICE_STATE_RESUMING) + return -EINVAL; + + if (copy_from_user(&data_size, buf, sizeof(data_size))) + return -EFAULT; + + mig_info->data_size = data_size; + } else { + if (mig_info->device_state != VFIO_DEVICE_STATE_SAVING) + return -EINVAL; + + if (copy_to_user(buf, &mig_info->data_size, + sizeof(data_size))) + return -EFAULT; + } + + return count; +} + +static ssize_t vfio_pci_handle_mig_dev_cmd(struct vfio_pci_migration_data *data, + char __user *buf, size_t count, bool iswrite) +{ + struct vfio_pci_vendor_mig_driver *mig_drv = data->mig_driver; + struct pci_dev *pdev = data->vf_dev; + u32 device_cmd; + int ret = -EFAULT; + + if (count != sizeof(device_cmd) || !iswrite || !mig_drv->dev_mig_ops) + return -EINVAL; + + if (copy_from_user(&device_cmd, buf, count)) + return -EFAULT; + + switch (device_cmd) { + case VFIO_DEVICE_MIGRATION_CANCEL: + if (mig_drv->dev_mig_ops->cancel) + ret = mig_drv->dev_mig_ops->cancel(pdev); + break; + default: + dev_err(&pdev->dev, "cmd is invaild\n"); + return -EINVAL; + } + + if (ret != 0) + return ret; + + return count; +} + +static ssize_t vfio_pci_handle_mig_drv_version( + struct vfio_device_migration_info *mig_info, + char __user *buf, size_t count, bool iswrite) +{ + u32 version_id = mig_info->version_id; + + if (count != sizeof(version_id) || iswrite) + return -EINVAL; + + if (copy_to_user(buf, &version_id, count)) + return -EFAULT; + + return count; +} + +static ssize_t vfio_pci_handle_mig_data_rw( + struct vfio_pci_migration_data *data, + char __user *buf, size_t count, u64 pos, bool iswrite) +{ + struct vfio_device_migration_info *mig_ctl = data->mig_ctl; + void *data_addr = data->vf_data; + + if (count == 0) { + dev_err(&data->vf_dev->dev, "qemu operation data size error!\n"); + return -EINVAL; + } + + data_addr += pos - mig_ctl->data_offset; + if (iswrite) { + if (copy_from_user(data_addr, buf, count)) + return -EFAULT; + + mig_ctl->pending_bytes += count; + if (mig_ctl->pending_bytes > data->state_size) + return -EINVAL; + } else { + if (copy_to_user(buf, data_addr, count)) + return -EFAULT; + + if (mig_ctl->pending_bytes < count) + return -EINVAL; + + mig_ctl->pending_bytes -= count; + } + + return count; +} + +static ssize_t vfio_pci_dev_migrn_rw(struct vfio_pci_device *vdev, + char __user *buf, size_t count, loff_t *ppos, bool iswrite) +{ + unsigned int index = + VFIO_PCI_OFFSET_TO_INDEX(*ppos) - VFIO_PCI_NUM_REGIONS; + struct vfio_pci_migration_data *data = + (struct vfio_pci_migration_data *)vdev->region[index].data; + loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK; + struct vfio_device_migration_info *mig_ctl = data->mig_ctl; + int ret; + + if (pos >= vdev->region[index].size) + return -EINVAL; + + count = min(count, (size_t)(vdev->region[index].size - pos)); + if (pos >= VFIO_MIGRATION_REGION_DATA_OFFSET) + return vfio_pci_handle_mig_data_rw(data, + buf, count, pos, iswrite); + + switch (pos) { + case VFIO_DEVICE_MIGRATION_OFFSET(device_state): + ret = vfio_pci_handle_mig_dev_state(data, + buf, count, iswrite); + break; + case VFIO_DEVICE_MIGRATION_OFFSET(pending_bytes): + ret = vfio_pci_handle_mig_pending_bytes(mig_ctl, + buf, count, iswrite); + break; + case VFIO_DEVICE_MIGRATION_OFFSET(data_offset): + ret = vfio_pci_handle_mig_data_offset(mig_ctl, + buf, count, iswrite); + break; + case VFIO_DEVICE_MIGRATION_OFFSET(data_size): + ret = vfio_pci_handle_mig_data_size(mig_ctl, + buf, count, iswrite); + break; + case VFIO_DEVICE_MIGRATION_OFFSET(device_cmd): + ret = vfio_pci_handle_mig_dev_cmd(data, + buf, count, iswrite); + break; + case VFIO_DEVICE_MIGRATION_OFFSET(version_id): + ret = vfio_pci_handle_mig_drv_version(mig_ctl, + buf, count, iswrite); + break; + default: + dev_err(&vdev->pdev->dev, "invalid pos offset\n"); + ret = -EFAULT; + break; + } + + if (mig_ctl->device_state == VFIO_DEVICE_STATE_RESUMING && + mig_ctl->pending_bytes == data->state_size && + mig_ctl->data_size == data->state_size) { + if (vfio_pci_device_state_restore(data) != 0) { + dev_err(&vdev->pdev->dev, "Failed to restore device state!\n"); + return -EFAULT; + } + mig_ctl->pending_bytes = 0; + mig_ctl->data_size = 0; + } + + return ret; +} + +static void vfio_pci_dev_migrn_release(struct vfio_pci_device *vdev, + struct vfio_pci_region *region) +{ + struct vfio_pci_migration_data *data = region->data; + + if (data) { + kfree(data->mig_ctl); + kfree(data); + } +} + +static const struct vfio_pci_regops vfio_pci_migration_regops = { + .rw = vfio_pci_dev_migrn_rw, + .release = vfio_pci_dev_migrn_release, +}; + +static int vfio_pci_migration_info_init(struct pci_dev *pdev, + struct vfio_device_migration_info *mig_info, + struct vfio_pci_vendor_mig_driver *mig_drv) +{ + int ret; + + ret = vfio_pci_device_get_info(pdev, mig_info, mig_drv); + if (ret) { + dev_err(&pdev->dev, "failed to get device info\n"); + return ret; + } + + if (mig_info->data_size > VFIO_MIGRATION_BUFFER_MAX_SIZE) { + dev_err(&pdev->dev, "mig_info->data_size %llu is invalid\n", + mig_info->data_size); + return -EINVAL; + } + + mig_info->data_offset = VFIO_MIGRATION_REGION_DATA_OFFSET; + return ret; +} + +static int vfio_device_mig_data_init(struct vfio_pci_device *vdev, + struct vfio_pci_migration_data *data) +{ + struct vfio_device_migration_info *mig_ctl; + u64 mig_offset; + int ret; + + mig_ctl = kzalloc(sizeof(*mig_ctl), GFP_KERNEL); + if (!mig_ctl) + return -ENOMEM; + + ret = vfio_pci_migration_info_init(vdev->pdev, mig_ctl, + data->mig_driver); + if (ret) { + dev_err(&vdev->pdev->dev, "get device info error!\n"); + goto err; + } + + mig_offset = sizeof(struct vfio_device_migration_info); + data->state_size = mig_ctl->data_size; + data->mig_ctl = krealloc(mig_ctl, mig_offset + data->state_size, + GFP_KERNEL); + if (!data->mig_ctl) { + ret = -ENOMEM; + goto err; + } + + data->vf_data = (void *)((char *)data->mig_ctl + mig_offset); + memset(data->vf_data, 0, data->state_size); + data->mig_ctl->data_size = 0; + + ret = vfio_pci_register_dev_region(vdev, VFIO_REGION_TYPE_MIGRATION, + VFIO_REGION_SUBTYPE_MIGRATION, + &vfio_pci_migration_regops, mig_offset + data->state_size, + VFIO_REGION_INFO_FLAG_READ | VFIO_REGION_INFO_FLAG_WRITE, data); + if (ret) { + kfree(data->mig_ctl); + return ret; + } + + return 0; +err: + kfree(mig_ctl); + return ret; +} + +int vfio_pci_migration_init(struct vfio_pci_device *vdev) +{ + struct vfio_pci_vendor_mig_driver *mig_driver = NULL; + struct vfio_pci_migration_data *data = NULL; + struct pci_dev *pdev = vdev->pdev; + int ret; + + mig_driver = vfio_pci_get_mig_driver(pdev); + if (!mig_driver || !mig_driver->dev_mig_ops) { + dev_err(&pdev->dev, "unable to find a mig_driver module\n"); + return -EINVAL; + } + + if (!try_module_get(mig_driver->owner)) { + pr_err("module %s is not live\n", mig_driver->owner->name); + return -ENODEV; + } + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) { + module_put(mig_driver->owner); + return -ENOMEM; + } + + data->mig_driver = mig_driver; + data->vf_dev = pdev; + + ret = vfio_device_mig_data_init(vdev, data); + if (ret) { + dev_err(&pdev->dev, "failed to init vfio device migration data!\n"); + goto err; + } + + return ret; +err: + kfree(data); + module_put(mig_driver->owner); + return ret; +} + +void vfio_pci_migration_exit(struct vfio_pci_device *vdev) +{ + struct vfio_pci_vendor_mig_driver *mig_driver = NULL; + + mig_driver = vfio_pci_get_mig_driver(vdev->pdev); + if (!mig_driver || !mig_driver->dev_mig_ops) { + dev_warn(&vdev->pdev->dev, "mig_driver is not found\n"); + return; + } + + if (module_refcount(mig_driver->owner) > 0) { + vfio_pci_device_release(vdev->pdev, mig_driver); + module_put(mig_driver->owner); + } +} + +int vfio_pci_register_migration_ops(struct vfio_device_migration_ops *ops, + struct module *mod, struct pci_dev *pdev) +{ + struct vfio_pci_vendor_mig_driver *mig_driver = NULL; + + if (!ops || !mod || !pdev) + return -EINVAL; + + mig_driver = vfio_pci_find_mig_drv(pdev, mod); + if (mig_driver) { + pr_info("%s migration ops has already been registered\n", + mod->name); + atomic_add(1, &mig_driver->count); + return 0; + } + + if (!try_module_get(THIS_MODULE)) + return -ENODEV; + + mig_driver = kzalloc(sizeof(*mig_driver), GFP_KERNEL); + if (!mig_driver) { + module_put(THIS_MODULE); + return -ENOMEM; + } + + mig_driver->pdev = pdev; + mig_driver->bus_num = pdev->bus->number; + mig_driver->owner = mod; + mig_driver->dev_mig_ops = ops; + + vfio_pci_add_mig_drv(mig_driver); + + return 0; +} +EXPORT_SYMBOL_GPL(vfio_pci_register_migration_ops); + +void vfio_pci_unregister_migration_ops(struct module *mod, struct pci_dev *pdev) +{ + struct vfio_pci_vendor_mig_driver *mig_driver = NULL; + + if (!mod || !pdev) + return; + + mig_driver = vfio_pci_find_mig_drv(pdev, mod); + if (!mig_driver) { + pr_err("mig_driver is not found\n"); + return; + } + + if (atomic_sub_and_test(1, &mig_driver->count)) { + vfio_pci_remove_mig_drv(mig_driver); + kfree(mig_driver); + module_put(THIS_MODULE); + pr_info("%s succeed to unregister migration ops\n", + THIS_MODULE->name); + } +} +EXPORT_SYMBOL_GPL(vfio_pci_unregister_migration_ops); diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h index 17d2bae..03af269 100644 --- a/drivers/vfio/pci/vfio_pci_private.h +++ b/drivers/vfio/pci/vfio_pci_private.h @@ -15,6 +15,7 @@ #include <linux/pci.h> #include <linux/irqbypass.h> #include <linux/types.h> +#include <linux/vfio_pci_migration.h> #ifndef VFIO_PCI_PRIVATE_H #define VFIO_PCI_PRIVATE_H @@ -55,7 +56,7 @@ struct vfio_pci_irq_ctx { struct vfio_pci_region; struct vfio_pci_regops { - size_t (*rw)(struct vfio_pci_device *vdev, char __user *buf, + ssize_t (*rw)(struct vfio_pci_device *vdev, char __user *buf, size_t count, loff_t *ppos, bool iswrite); void (*release)(struct vfio_pci_device *vdev, struct vfio_pci_region *region); @@ -173,4 +174,15 @@ static inline int vfio_pci_igd_init(struct vfio_pci_device *vdev) return -ENODEV; } #endif + +extern bool vfio_dev_migration_is_supported(struct pci_dev *pdev); +extern int vfio_pci_migration_init(struct vfio_pci_device *vdev); +extern void vfio_pci_migration_exit(struct vfio_pci_device *vdev); +extern int vfio_pci_device_log_start(struct vfio_pci_device *vdev, + struct vf_migration_log_info *log_info); +extern int vfio_pci_device_log_stop(struct vfio_pci_device *vdev, + uint32_t uuid); +extern int vfio_pci_device_log_status_query(struct vfio_pci_device *vdev); +extern int vfio_pci_device_init(struct pci_dev *pdev); +extern void vfio_pci_device_uninit(struct pci_dev *pdev); #endif /* VFIO_PCI_PRIVATE_H */ diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 7a386fb..35f2a29 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -33,6 +33,7 @@ #include <linux/string.h> #include <linux/uaccess.h> #include <linux/vfio.h> +#include <linux/vfio_pci_migration.h> #include <linux/wait.h> #include <linux/sched/signal.h> @@ -40,6 +41,9 @@ #define DRIVER_AUTHOR "Alex Williamson <alex.williamson(a)redhat.com>" #define DRIVER_DESC "VFIO - User Level meta-driver" +#define LOG_BUF_FRAG_SIZE (2 * 1024 * 1024) // fix to 2M +#define LOG_BUF_MAX_ADDRS_SIZE 128 // max vm ram size is 1T + static struct vfio { struct class *class; struct list_head iommu_drivers_list; @@ -57,6 +61,14 @@ struct vfio_iommu_driver { struct list_head vfio_next; }; +struct vfio_log_buf { + struct vfio_log_buf_info info; + int fd; + int buffer_state; + int device_state; + unsigned long *cpu_addrs; +}; + struct vfio_container { struct kref kref; struct list_head group_list; @@ -64,6 +76,7 @@ struct vfio_container { struct vfio_iommu_driver *iommu_driver; void *iommu_data; bool noiommu; + struct vfio_log_buf log_buf; }; struct vfio_unbound_dev { @@ -1158,8 +1171,398 @@ static long vfio_ioctl_set_iommu(struct vfio_container *container, return ret; } +static long vfio_dispatch_cmd_to_devices(const struct vfio_container *container, + unsigned int cmd, unsigned long arg) +{ + struct vfio_group *group = NULL; + struct vfio_device *device = NULL; + long ret = -ENXIO; + + list_for_each_entry(group, &container->group_list, container_next) { + list_for_each_entry(device, &group->device_list, group_next) { + ret = device->ops->ioctl(device->device_data, cmd, arg); + if (ret) { + pr_err("dispatch cmd to devices failed\n"); + return ret; + } + } + } + return ret; +} + +static long vfio_log_buf_start(struct vfio_container *container) +{ + struct vfio_log_buf_ctl log_buf_ctl; + long ret; + + log_buf_ctl.argsz = sizeof(struct vfio_log_buf_info); + log_buf_ctl.flags = VFIO_DEVICE_LOG_BUF_FLAG_START; + log_buf_ctl.data = (void *)&container->log_buf.info; + ret = vfio_dispatch_cmd_to_devices(container, VFIO_DEVICE_LOG_BUF_CTL, + (unsigned long)&log_buf_ctl); + if (ret) + return ret; + + container->log_buf.device_state = 1; + return 0; +} + +static long vfio_log_buf_stop(struct vfio_container *container) +{ + struct vfio_log_buf_ctl log_buf_ctl; + long ret; + + if (container->log_buf.device_state == 0) { + pr_warn("device already stopped\n"); + return 0; + } + + log_buf_ctl.argsz = sizeof(struct vfio_log_buf_info); + log_buf_ctl.flags = VFIO_DEVICE_LOG_BUF_FLAG_STOP; + log_buf_ctl.data = (void *)&container->log_buf.info; + ret = vfio_dispatch_cmd_to_devices(container, VFIO_DEVICE_LOG_BUF_CTL, + (unsigned long)&log_buf_ctl); + if (ret) + return ret; + + container->log_buf.device_state = 0; + return 0; +} + +static long vfio_log_buf_query(struct vfio_container *container) +{ + struct vfio_log_buf_ctl log_buf_ctl; + + log_buf_ctl.argsz = sizeof(struct vfio_log_buf_info); + log_buf_ctl.flags = VFIO_DEVICE_LOG_BUF_FLAG_STATUS_QUERY; + log_buf_ctl.data = (void *)&container->log_buf.info; + + return vfio_dispatch_cmd_to_devices(container, + VFIO_DEVICE_LOG_BUF_CTL, (unsigned long)&log_buf_ctl); +} + +static int vfio_log_buf_fops_mmap(struct file *filep, + struct vm_area_struct *vma) +{ + struct vfio_container *container = filep->private_data; + struct vfio_log_buf *log_buf = &container->log_buf; + unsigned long frag_pg_size; + unsigned long frag_offset; + phys_addr_t pa; + int ret = -EINVAL; + + if (!log_buf->cpu_addrs) { + pr_err("mmap before setup, please setup log buf first\n"); + return ret; + } + + if (log_buf->info.frag_size < PAGE_SIZE) { + pr_err("mmap frag size should not less than page size!\n"); + return ret; + } + + frag_pg_size = log_buf->info.frag_size / PAGE_SIZE; + frag_offset = vma->vm_pgoff / frag_pg_size; + + if (frag_offset >= log_buf->info.addrs_size) { + pr_err("mmap offset out of range!\n"); + return ret; + } + + if (vma->vm_end - vma->vm_start != log_buf->info.frag_size) { + pr_err("mmap size error, should be aligned with frag size!\n"); + return ret; + } + + pa = virt_to_phys((void *)log_buf->cpu_addrs[frag_offset]); + ret = remap_pfn_range(vma, vma->vm_start, + pa >> PAGE_SHIFT, + vma->vm_end - vma->vm_start, + vma->vm_page_prot); + if (ret) + pr_err("remap_pfn_range error!\n"); + return ret; +} + +static struct device *vfio_get_dev(struct vfio_container *container) +{ + struct vfio_group *group = NULL; + struct vfio_device *device = NULL; + + list_for_each_entry(group, &container->group_list, container_next) { + list_for_each_entry(device, &group->device_list, group_next) { + return device->dev; + } + } + return NULL; +} + +static void vfio_log_buf_release_dma(struct device *dev, + struct vfio_log_buf *log_buf) +{ + int i; + + for (i = 0; i < log_buf->info.addrs_size; i++) { + if ((log_buf->cpu_addrs && log_buf->cpu_addrs[i] != 0) && + (log_buf->info.sgevec && + log_buf->info.sgevec[i].addr != 0)) { + dma_free_coherent(dev, log_buf->info.frag_size, + (void *)log_buf->cpu_addrs[i], + log_buf->info.sgevec[i].addr); + log_buf->cpu_addrs[i] = 0; + log_buf->info.sgevec[i].addr = 0; + } + } +} + +static long vfio_log_buf_alloc_dma(struct vfio_log_buf_info *info, + struct vfio_log_buf *log_buf, struct device *dev) +{ + int i; + + for (i = 0; i < info->addrs_size; i++) { + log_buf->cpu_addrs[i] = (unsigned long)dma_alloc_coherent(dev, + info->frag_size, &log_buf->info.sgevec[i].addr, + GFP_KERNEL); + log_buf->info.sgevec[i].len = info->frag_size; + if (log_buf->cpu_addrs[i] == 0 || + log_buf->info.sgevec[i].addr == 0) { + return -ENOMEM; + } + } + return 0; +} + +static long vfio_log_buf_alloc_addrs(struct vfio_log_buf_info *info, + struct vfio_log_buf *log_buf) +{ + log_buf->info.sgevec = kcalloc(info->addrs_size, + sizeof(struct vfio_log_buf_sge), GFP_KERNEL); + if (!log_buf->info.sgevec) + return -ENOMEM; + + log_buf->cpu_addrs = kcalloc(info->addrs_size, + sizeof(unsigned long), GFP_KERNEL); + if (!log_buf->cpu_addrs) { + kfree(log_buf->info.sgevec); + log_buf->info.sgevec = NULL; + return -ENOMEM; + } + + return 0; +} + +static long vfio_log_buf_info_valid(struct vfio_log_buf_info *info) +{ + if (info->addrs_size > LOG_BUF_MAX_ADDRS_SIZE || + info->addrs_size == 0) { + pr_err("can`t support vm ram size larger than 1T or equal to 0\n"); + return -EINVAL; + } + if (info->frag_size != LOG_BUF_FRAG_SIZE) { + pr_err("only support %d frag size\n", LOG_BUF_FRAG_SIZE); + return -EINVAL; + } + return 0; +} + +static long vfio_log_buf_setup(struct vfio_container *container, + unsigned long data) +{ + struct vfio_log_buf_info info; + struct vfio_log_buf *log_buf = &container->log_buf; + struct device *dev = NULL; + long ret; + + if (log_buf->info.sgevec) { + pr_warn("log buf already setup\n"); + return 0; + } + + if (copy_from_user(&info, (void __user *)data, + sizeof(struct vfio_log_buf_info))) + return -EFAULT; + + ret = vfio_log_buf_info_valid(&info); + if (ret) + return ret; + + ret = vfio_log_buf_alloc_addrs(&info, log_buf); + if (ret) + goto err_out; + + dev = vfio_get_dev(container); + if (!dev) { + pr_err("can`t get dev\n"); + goto err_free_addrs; + } + + ret = vfio_log_buf_alloc_dma(&info, log_buf, dev); + if (ret) + goto err_free_dma_array; + + log_buf->info.uuid = info.uuid; + log_buf->info.buffer_size = info.buffer_size; + log_buf->info.frag_size = info.frag_size; + log_buf->info.addrs_size = info.addrs_size; + log_buf->buffer_state = 1; + return 0; + +err_free_dma_array: + vfio_log_buf_release_dma(dev, log_buf); +err_free_addrs: + kfree(log_buf->cpu_addrs); + log_buf->cpu_addrs = NULL; + kfree(log_buf->info.sgevec); + log_buf->info.sgevec = NULL; +err_out: + return -ENOMEM; +} + +static long vfio_log_buf_release_buffer(struct vfio_container *container) +{ + struct vfio_log_buf *log_buf = &container->log_buf; + struct device *dev = NULL; + + if (log_buf->buffer_state == 0) { + pr_warn("buffer already released\n"); + return 0; + } + + dev = vfio_get_dev(container); + if (!dev) { + pr_err("can`t get dev\n"); + return -EFAULT; + } + + vfio_log_buf_release_dma(dev, log_buf); + + kfree(log_buf->cpu_addrs); + log_buf->cpu_addrs = NULL; + + kfree(log_buf->info.sgevec); + log_buf->info.sgevec = NULL; + + log_buf->buffer_state = 0; + return 0; +} + +static int vfio_log_buf_release(struct inode *inode, struct file *filep) +{ + struct vfio_container *container = filep->private_data; + + vfio_log_buf_stop(container); + vfio_log_buf_release_buffer(container); + memset(&container->log_buf, 0, sizeof(struct vfio_log_buf)); + return 0; +} + +static long vfio_ioctl_handle_log_buf_ctl(struct vfio_container *container, + unsigned long arg) +{ + struct vfio_log_buf_ctl log_buf_ctl; + long ret = 0; + + if (copy_from_user(&log_buf_ctl, (void __user *)arg, + sizeof(struct vfio_log_buf_ctl))) + return -EFAULT; + + switch (log_buf_ctl.flags) { + case VFIO_DEVICE_LOG_BUF_FLAG_SETUP: + ret = vfio_log_buf_setup(container, + (unsigned long)log_buf_ctl.data); + break; + case VFIO_DEVICE_LOG_BUF_FLAG_RELEASE: + ret = vfio_log_buf_release_buffer(container); + break; + case VFIO_DEVICE_LOG_BUF_FLAG_START: + ret = vfio_log_buf_start(container); + break; + case VFIO_DEVICE_LOG_BUF_FLAG_STOP: + ret = vfio_log_buf_stop(container); + break; + case VFIO_DEVICE_LOG_BUF_FLAG_STATUS_QUERY: + ret = vfio_log_buf_query(container); + break; + default: + pr_err("log buf control flag incorrect\n"); + ret = -EINVAL; + break; + } + return ret; +} + +static long vfio_log_buf_fops_unl_ioctl(struct file *filep, + unsigned int cmd, unsigned long arg) +{ + struct vfio_container *container = filep->private_data; + long ret = -EINVAL; + + switch (cmd) { + case VFIO_LOG_BUF_CTL: + ret = vfio_ioctl_handle_log_buf_ctl(container, arg); + break; + default: + pr_err("log buf control cmd incorrect\n"); + break; + } + + return ret; +} + +#ifdef CONFIG_COMPAT +static long vfio_log_buf_fops_compat_ioctl(struct file *filep, + unsigned int cmd, unsigned long arg) +{ + arg = (unsigned long)compat_ptr(arg); + return vfio_log_buf_fops_unl_ioctl(filep, cmd, arg); +} +#endif /* CONFIG_COMPAT */ + +static const struct file_operations vfio_log_buf_fops = { + .owner = THIS_MODULE, + .mmap = vfio_log_buf_fops_mmap, + .unlocked_ioctl = vfio_log_buf_fops_unl_ioctl, + .release = vfio_log_buf_release, +#ifdef CONFIG_COMPAT + .compat_ioctl = vfio_log_buf_fops_compat_ioctl, +#endif +}; + +static int vfio_get_log_buf_fd(struct vfio_container *container, + unsigned long arg) +{ + struct file *filep = NULL; + int ret; + + if (container->log_buf.fd > 0) + return container->log_buf.fd; + + ret = get_unused_fd_flags(O_CLOEXEC); + if (ret < 0) { + pr_err("get_unused_fd_flags get fd failed\n"); + return ret; + } + + filep = anon_inode_getfile("[vfio-log-buf]", &vfio_log_buf_fops, + container, O_RDWR); + if (IS_ERR(filep)) { + pr_err("anon_inode_getfile failed\n"); + put_unused_fd(ret); + ret = PTR_ERR(filep); + return ret; + } + + filep->f_mode |= (FMODE_READ | FMODE_WRITE | FMODE_LSEEK); + + fd_install(ret, filep); + + container->log_buf.fd = ret; + return ret; +} + static long vfio_fops_unl_ioctl(struct file *filep, - unsigned int cmd, unsigned long arg) + unsigned int cmd, unsigned long arg) { struct vfio_container *container = filep->private_data; struct vfio_iommu_driver *driver; @@ -1179,6 +1582,9 @@ static long vfio_fops_unl_ioctl(struct file *filep, case VFIO_SET_IOMMU: ret = vfio_ioctl_set_iommu(container, arg); break; + case VFIO_GET_LOG_BUF_FD: + ret = vfio_get_log_buf_fd(container, arg); + break; default: driver = container->iommu_driver; data = container->iommu_data; @@ -1210,6 +1616,7 @@ static int vfio_fops_open(struct inode *inode, struct file *filep) INIT_LIST_HEAD(&container->group_list); init_rwsem(&container->group_lock); kref_init(&container->kref); + memset(&container->log_buf, 0, sizeof(struct vfio_log_buf)); filep->private_data = container; @@ -1219,9 +1626,7 @@ static int vfio_fops_open(struct inode *inode, struct file *filep) static int vfio_fops_release(struct inode *inode, struct file *filep) { struct vfio_container *container = filep->private_data; - filep->private_data = NULL; - vfio_container_put(container); return 0; diff --git a/include/linux/vfio_pci_migration.h b/include/linux/vfio_pci_migration.h new file mode 100644 index 0000000..464ffb4 --- /dev/null +++ b/include/linux/vfio_pci_migration.h @@ -0,0 +1,136 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2022 Huawei Technologies Co., Ltd. All rights reserved. + */ + +#ifndef VFIO_PCI_MIGRATION_H +#define VFIO_PCI_MIGRATION_H + +#include <linux/types.h> +#include <linux/pci.h> + +#define VFIO_REGION_TYPE_MIGRATION (3) +/* sub-types for VFIO_REGION_TYPE_MIGRATION */ +#define VFIO_REGION_SUBTYPE_MIGRATION (1) + +#define VFIO_MIGRATION_BUFFER_MAX_SIZE SZ_256K +#define VFIO_MIGRATION_REGION_DATA_OFFSET \ + (sizeof(struct vfio_device_migration_info)) +#define VFIO_DEVICE_MIGRATION_OFFSET(x) \ + offsetof(struct vfio_device_migration_info, x) + +struct vfio_device_migration_info { + __u32 device_state; /* VFIO device state */ +#define VFIO_DEVICE_STATE_STOP (0) +#define VFIO_DEVICE_STATE_RUNNING (1 << 0) +#define VFIO_DEVICE_STATE_SAVING (1 << 1) +#define VFIO_DEVICE_STATE_RESUMING (1 << 2) +#define VFIO_DEVICE_STATE_MASK (VFIO_DEVICE_STATE_RUNNING | \ + VFIO_DEVICE_STATE_SAVING | VFIO_DEVICE_STATE_RESUMING) + __u32 reserved; + + __u32 device_cmd; + __u32 version_id; + + __u64 pending_bytes; + __u64 data_offset; + __u64 data_size; +}; + +enum { + VFIO_DEVICE_STOP = 0xffff0001, + VFIO_DEVICE_CONTINUE, + VFIO_DEVICE_MIGRATION_CANCEL, +}; + +struct vfio_log_buf_sge { + __u64 len; + __u64 addr; +}; + +struct vfio_log_buf_info { + __u32 uuid; + __u64 buffer_size; + __u64 addrs_size; + __u64 frag_size; + struct vfio_log_buf_sge *sgevec; +}; + +struct vfio_log_buf_ctl { + __u32 argsz; + __u32 flags; + #define VFIO_DEVICE_LOG_BUF_FLAG_SETUP (1 << 0) + #define VFIO_DEVICE_LOG_BUF_FLAG_RELEASE (1 << 1) + #define VFIO_DEVICE_LOG_BUF_FLAG_START (1 << 2) + #define VFIO_DEVICE_LOG_BUF_FLAG_STOP (1 << 3) + #define VFIO_DEVICE_LOG_BUF_FLAG_STATUS_QUERY (1 << 4) + void *data; +}; +#define VFIO_LOG_BUF_CTL _IO(VFIO_TYPE, VFIO_BASE + 21) +#define VFIO_GET_LOG_BUF_FD _IO(VFIO_TYPE, VFIO_BASE + 22) +#define VFIO_DEVICE_LOG_BUF_CTL _IO(VFIO_TYPE, VFIO_BASE + 23) + +struct vf_migration_log_info { + __u32 dom_uuid; + __u64 buffer_size; + __u64 sge_len; + __u64 sge_num; + struct vfio_log_buf_sge *sgevec; +}; + +struct vfio_device_migration_ops { + /* Get device information */ + int (*get_info)(struct pci_dev *pdev, + struct vfio_device_migration_info *info); + /* Enable a vf device */ + int (*enable)(struct pci_dev *pdev); + /* Disable a vf device */ + int (*disable)(struct pci_dev *pdev); + /* Save a vf device */ + int (*save)(struct pci_dev *pdev, void *base, + uint64_t off, uint64_t count); + /* Resuming a vf device */ + int (*restore)(struct pci_dev *pdev, void *base, + uint64_t off, uint64_t count); + /* Log start a vf device */ + int (*log_start)(struct pci_dev *pdev, + struct vf_migration_log_info *log_info); + /* Log stop a vf device */ + int (*log_stop)(struct pci_dev *pdev, uint32_t uuid); + /* Get vf device log status */ + int (*get_log_status)(struct pci_dev *pdev); + /* Pre enable a vf device(load_setup, before restore a vf) */ + int (*pre_enable)(struct pci_dev *pdev); + /* Cancel a vf device when live migration failed (rollback) */ + int (*cancel)(struct pci_dev *pdev); + /* Init a vf device */ + int (*init)(struct pci_dev *pdev); + /* Uninit a vf device */ + void (*uninit)(struct pci_dev *pdev); + /* Release a vf device */ + void (*release)(struct pci_dev *pdev); +}; + +struct vfio_pci_vendor_mig_driver { + struct pci_dev *pdev; + unsigned char bus_num; + struct vfio_device_migration_ops *dev_mig_ops; + struct module *owner; + atomic_t count; + struct list_head list; +}; + +struct vfio_pci_migration_data { + u64 state_size; + struct pci_dev *vf_dev; + struct vfio_pci_vendor_mig_driver *mig_driver; + struct vfio_device_migration_info *mig_ctl; + void *vf_data; +}; + +int vfio_pci_register_migration_ops(struct vfio_device_migration_ops *ops, + struct module *mod, struct pci_dev *pdev); +void vfio_pci_unregister_migration_ops(struct module *mod, + struct pci_dev *pdev); + +#endif /* VFIO_PCI_MIGRATION_H */ -- 1.8.3.1

1 0

[PATCH OLK-5.10 v2 1/2] ipmi/watchdog: replace atomic_add() and atomic_sub()
by Miaohe Lin 24 Jun '22

24 Jun '22

From: Yejune Deng <yejune.deng(a)gmail.com> mainline inclusion from v5.11-rc1 commit a01a89b1db1066a6af23ae08b9a0c345b7966f0b category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5DVR9 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- atomic_inc() and atomic_dec() looks better Signed-off-by: Yejune Deng <yejune.deng(a)gmail.com> Message-Id: <1605511807-7135-1-git-send-email-yejune.deng(a)gmail.com> Signed-off-by: Corey Minyard <cminyard(a)mvista.com> --- drivers/char/ipmi/ipmi_watchdog.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c index f78156d93c3f..32c334e34d55 100644 --- a/drivers/char/ipmi/ipmi_watchdog.c +++ b/drivers/char/ipmi/ipmi_watchdog.c @@ -495,7 +495,7 @@ static void panic_halt_ipmi_heartbeat(void) msg.cmd = IPMI_WDOG_RESET_TIMER; msg.data = NULL; msg.data_len = 0; - atomic_add(1, &panic_done_count); + atomic_inc(&panic_done_count); rv = ipmi_request_supply_msgs(watchdog_user, (struct ipmi_addr *) &addr, 0, @@ -505,7 +505,7 @@ static void panic_halt_ipmi_heartbeat(void) &panic_halt_heartbeat_recv_msg, 1); if (rv) - atomic_sub(1, &panic_done_count); + atomic_dec(&panic_done_count); } static struct ipmi_smi_msg panic_halt_smi_msg = { @@ -529,12 +529,12 @@ static void panic_halt_ipmi_set_timeout(void) /* Wait for the messages to be free. */ while (atomic_read(&panic_done_count) != 0) ipmi_poll_interface(watchdog_user); - atomic_add(1, &panic_done_count); + atomic_inc(&panic_done_count); rv = __ipmi_set_timeout(&panic_halt_smi_msg, &panic_halt_recv_msg, &send_heartbeat_now); if (rv) { - atomic_sub(1, &panic_done_count); + atomic_dec(&panic_done_count); pr_warn("Unable to extend the watchdog timeout\n"); } else { if (send_heartbeat_now) -- 2.23.0

1 1

[PATCH OLK-5.10 1/2] ipmi/watchdog: replace atomic_add() and atomic_sub()
by Miaohe Lin 23 Jun '22

23 Jun '22

From: Yejune Deng <yejune.deng(a)gmail.com> mainline inclusion from v5.11-rc1 commit a01a89b1db1066a6af23ae08b9a0c345b7966f0b category: bugfix bugzilla: NA CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- atomic_inc() and atomic_dec() looks better Signed-off-by: Yejune Deng <yejune.deng(a)gmail.com> Message-Id: <1605511807-7135-1-git-send-email-yejune.deng(a)gmail.com> Signed-off-by: Corey Minyard <cminyard(a)mvista.com> --- drivers/char/ipmi/ipmi_watchdog.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c index f78156d93c3f..32c334e34d55 100644 --- a/drivers/char/ipmi/ipmi_watchdog.c +++ b/drivers/char/ipmi/ipmi_watchdog.c @@ -495,7 +495,7 @@ static void panic_halt_ipmi_heartbeat(void) msg.cmd = IPMI_WDOG_RESET_TIMER; msg.data = NULL; msg.data_len = 0; - atomic_add(1, &panic_done_count); + atomic_inc(&panic_done_count); rv = ipmi_request_supply_msgs(watchdog_user, (struct ipmi_addr *) &addr, 0, @@ -505,7 +505,7 @@ static void panic_halt_ipmi_heartbeat(void) &panic_halt_heartbeat_recv_msg, 1); if (rv) - atomic_sub(1, &panic_done_count); + atomic_dec(&panic_done_count); } static struct ipmi_smi_msg panic_halt_smi_msg = { @@ -529,12 +529,12 @@ static void panic_halt_ipmi_set_timeout(void) /* Wait for the messages to be free. */ while (atomic_read(&panic_done_count) != 0) ipmi_poll_interface(watchdog_user); - atomic_add(1, &panic_done_count); + atomic_inc(&panic_done_count); rv = __ipmi_set_timeout(&panic_halt_smi_msg, &panic_halt_recv_msg, &send_heartbeat_now); if (rv) { - atomic_sub(1, &panic_done_count); + atomic_dec(&panic_done_count); pr_warn("Unable to extend the watchdog timeout\n"); } else { if (send_heartbeat_now) -- 2.23.0

2 2

[PATCH openEuler-5.10 01/59] bcache: fix race between setting bdev state to none and new write request direct to backing
by Zheng Zengkai 22 Jun '22

22 Jun '22

From: Dongsheng Yang <dongsheng.yang(a)easystack.cn> mainline inclusion from v5.11-rc1 commit df4ad53242158f9f1f97daf4feddbb4f8b77f080 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I59A5L?from=project-issue CVE: N/A ----------------------------------------------- There is a race condition in detaching as below: A. detaching B. Write request (1) writing back (2) write back done, set bdev state to clean. (3) cached_dev_put() and schedule_work(&dc->detach); (4) write data [0 - 4K] directly into backing and ack to user. (5) power-failure... When we restart this bcache device, this bdev is clean but not detached, and read [0 - 4K], we will get unexpected old data from cache device. To fix this problem, set the bdev state to none when we writeback done in detaching, and then if power-failure happened as above, the data in cache will not be used in next bcache device starting, it's detached, we will read the correct data from backing derectly. Signed-off-by: Dongsheng Yang <dongsheng.yang(a)easystack.cn> Signed-off-by: Coly Li <colyli(a)suse.de> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- drivers/md/bcache/super.c | 9 --------- drivers/md/bcache/writeback.c | 9 +++++++++ 2 files changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 81f1cc5b3499..b7d9d1b79ac2 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1151,9 +1151,6 @@ static void cancel_writeback_rate_update_dwork(struct cached_dev *dc) static void cached_dev_detach_finish(struct work_struct *w) { struct cached_dev *dc = container_of(w, struct cached_dev, detach); - struct closure cl; - - closure_init_stack(&cl); BUG_ON(!test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags)); BUG_ON(refcount_read(&dc->count)); @@ -1167,12 +1164,6 @@ static void cached_dev_detach_finish(struct work_struct *w) dc->writeback_thread = NULL; } - memset(&dc->sb.set_uuid, 0, 16); - SET_BDEV_STATE(&dc->sb, BDEV_STATE_NONE); - - bch_write_bdev_super(dc, &cl); - closure_sync(&cl); - mutex_lock(&bch_register_lock); calc_cached_dev_sectors(dc->disk.c); diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index 3c74996978da..a129e4d2707c 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -705,6 +705,15 @@ static int bch_writeback_thread(void *arg) * bch_cached_dev_detach(). */ if (test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags)) { + struct closure cl; + + closure_init_stack(&cl); + memset(&dc->sb.set_uuid, 0, 16); + SET_BDEV_STATE(&dc->sb, BDEV_STATE_NONE); + + bch_write_bdev_super(dc, &cl); + closure_sync(&cl); + up_write(&dc->writeback_lock); break; } -- 2.20.1

1 58

[PATCH openEuler-5.10 00/28] Backport 5.10.108 LTS
by Zheng Zengkai 22 Jun '22

22 Jun '22

Backport 5.10.108 LTS patches from upstream Revert "selftests/bpf: Add test for bpf_timer overwriting crash" smsc95xx: Ignore -ENODEV errors when device is unplugged net: usb: Correct reset handling of smsc95xx net: usb: Correct PHY handling of smsc95xx perf symbols: Fix symbol size calculation condition Input: aiptek - properly check endpoint type scsi: mpt3sas: Page fault in reply q processing usb: usbtmc: Fix bug in pipe direction for control transfers usb: gadget: Fix use-after-free bug by not setting udc->dev.driver net: mscc: ocelot: fix backwards compatibility with single-chain tc-flower offload net: bcmgenet: skip invalid partial checksums bnx2x: fix built-in kernel driver load failure net: phy: mscc: Add MODULE_FIRMWARE macros net: dsa: Add missing of_node_put() in dsa_port_parse_of net: handle ARPHRD_PIMREG in dev_is_mac_header_xmit() drm/panel: simple: Fix Innolux G070Y2-L01 BPP settings drm/imx: parallel-display: Remove bus flags check in imx_pd_bridge_atomic_check() hv_netvsc: Add check for kvmalloc_array atm: eni: Add check for dma_map_single net/packet: fix slab-out-of-bounds access in packet_recvmsg() net: phy: marvell: Fix invalid comparison in the resume and suspend functions esp6: fix check on ipv6_skip_exthdr's return value vsock: each transport cycles only on its own sockets efi: fix return value of __setup handlers mm: swap: get rid of livelock in swapin readahead ocfs2: fix crash when initialize filecheck kobj fails crypto: qcom-rng - ensure buffer for generate is completely filled already merged (2) esp: Fix possible buffer overflow in ESP transformation arm64: fix clang warning about TRAMP_VALIAS Total patches = 30 - 2 = 28 Alan Stern (2): usb: gadget: Fix use-after-free bug by not setting udc->dev.driver usb: usbtmc: Fix bug in pipe direction for control transfers Brian Masney (1): crypto: qcom-rng - ensure buffer for generate is completely filled Christoph Niedermaier (1): drm/imx: parallel-display: Remove bus flags check in imx_pd_bridge_atomic_check() Dan Carpenter (1): usb: gadget: rndis: prevent integer overflow in rndis_set_response() Doug Berger (1): net: bcmgenet: skip invalid partial checksums Eric Dumazet (1): net/packet: fix slab-out-of-bounds access in packet_recvmsg() Fabio Estevam (1): smsc95xx: Ignore -ENODEV errors when device is unplugged Greg Kroah-Hartman (1): Revert "selftests/bpf: Add test for bpf_timer overwriting crash" Guo Ziliang (1): mm: swap: get rid of livelock in swapin readahead Jiasheng Jiang (2): atm: eni: Add check for dma_map_single hv_netvsc: Add check for kvmalloc_array Jiyong Park (1): vsock: each transport cycles only on its own sockets Joseph Qi (1): ocfs2: fix crash when initialize filecheck kobj fails Juerg Haefliger (1): net: phy: mscc: Add MODULE_FIRMWARE macros Kurt Cancemi (1): net: phy: marvell: Fix invalid comparison in the resume and suspend functions Manish Chopra (1): bnx2x: fix built-in kernel driver load failure Marek Vasut (1): drm/panel: simple: Fix Innolux G070Y2-L01 BPP settings Markus Reichl (1): net: usb: Correct reset handling of smsc95xx Martyn Welch (1): net: usb: Correct PHY handling of smsc95xx Matt Lupfer (1): scsi: mpt3sas: Page fault in reply q processing Miaoqian Lin (1): net: dsa: Add missing of_node_put() in dsa_port_parse_of Michael Petlan (1): perf symbols: Fix symbol size calculation condition Nicolas Dichtel (1): net: handle ARPHRD_PIMREG in dev_is_mac_header_xmit() Pavel Skripkin (1): Input: aiptek - properly check endpoint type Randy Dunlap (1): efi: fix return value of __setup handlers Sabrina Dubroca (1): esp6: fix check on ipv6_skip_exthdr's return value Vladimir Oltean (1): net: mscc: ocelot: fix backwards compatibility with single-chain tc-flower offload drivers/atm/eni.c | 2 + drivers/crypto/qcom-rng.c | 17 ++-- drivers/firmware/efi/apple-properties.c | 2 +- drivers/firmware/efi/efi.c | 2 +- drivers/gpu/drm/imx/parallel-display.c | 8 -- drivers/gpu/drm/panel/panel-simple.c | 2 +- drivers/input/tablet/aiptek.c | 10 +-- drivers/net/ethernet/broadcom/bnx2x/bnx2x.h | 2 - .../net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 28 +++--- .../net/ethernet/broadcom/bnx2x/bnx2x_main.c | 15 +--- .../net/ethernet/broadcom/genet/bcmgenet.c | 6 +- drivers/net/ethernet/mscc/ocelot_flower.c | 16 +++- drivers/net/hyperv/netvsc_drv.c | 3 + drivers/net/phy/marvell.c | 8 +- drivers/net/phy/mscc/mscc_main.c | 3 + drivers/net/usb/smsc95xx.c | 86 +++++++++++-------- drivers/scsi/mpt3sas/mpt3sas_base.c | 5 +- drivers/usb/class/usbtmc.c | 13 ++- drivers/usb/gadget/function/rndis.c | 1 + drivers/usb/gadget/udc/core.c | 3 - drivers/vhost/vsock.c | 3 +- fs/ocfs2/super.c | 22 ++--- include/linux/if_arp.h | 1 + include/net/af_vsock.h | 3 +- mm/swap_state.c | 2 +- net/dsa/dsa2.c | 1 + net/ipv6/esp6.c | 3 +- net/packet/af_packet.c | 11 ++- net/vmw_vsock/af_vsock.c | 9 +- net/vmw_vsock/virtio_transport.c | 7 +- net/vmw_vsock/vmci_transport.c | 5 +- tools/perf/util/symbol.c | 2 +- .../selftests/bpf/prog_tests/timer_crash.c | 32 ------- .../testing/selftests/bpf/progs/timer_crash.c | 54 ------------ 34 files changed, 175 insertions(+), 212 deletions(-) delete mode 100644 tools/testing/selftests/bpf/prog_tests/timer_crash.c delete mode 100644 tools/testing/selftests/bpf/progs/timer_crash.c -- 2.20.1

1 28

[PATCH openEuler-1.0-LTS] xfs: show the proper user quota options
by Laibin Qiu 22 Jun '22

22 Jun '22

From: Kaixu Xia <kaixuxia(a)tencent.com> mainline inclusion from mainline-v5.11-rc6 commit 237d7887ae723af7d978e8b9a385fdff416f357b category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5AG18 CVE: NA -------------------------------- The quota option 'usrquota' should be shown if both the XFS_UQUOTA_ACCT and XFS_UQUOTA_ENFD flags are set. The option 'uqnoenforce' should be shown when only the XFS_UQUOTA_ACCT flag is set. The current code logic seems wrong, Fix it and show proper options. Signed-off-by: Kaixu Xia <kaixuxia(a)tencent.com> Reviewed-by: Darrick J. Wong <darrick.wong(a)oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong(a)oracle.com> Signed-off-by: tangbin <tangbin(a)cmss.chinamobile.com> Reviewed-by: Xuenan Guo <guoxuenan(a)huawei.com> Signed-off-by: Laibin Qiu <qiulaibin(a)huawei.com> --- fs/xfs/xfs_super.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index e126bc6cdeb8..5d8e3a4d2671 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -505,10 +505,12 @@ xfs_showargs( seq_printf(m, ",swidth=%d", (int)XFS_FSB_TO_BB(mp, mp->m_swidth)); - if (mp->m_qflags & (XFS_UQUOTA_ACCT|XFS_UQUOTA_ENFD)) - seq_puts(m, ",usrquota"); - else if (mp->m_qflags & XFS_UQUOTA_ACCT) - seq_puts(m, ",uqnoenforce"); + if (mp->m_qflags & XFS_UQUOTA_ACCT) { + if (mp->m_qflags & XFS_UQUOTA_ENFD) + seq_puts(m, ",usrquota"); + else + seq_puts(m, ",uqnoenforce"); + } if (mp->m_qflags & XFS_PQUOTA_ACCT) { if (mp->m_qflags & XFS_PQUOTA_ENFD) -- 2.25.1

1 0

[PATCH openEuler-5.10-LTS 01/55] bcache: fix race between setting bdev state to none and new write request direct to backing
by Zheng Zengkai 21 Jun '22

21 Jun '22

From: Dongsheng Yang <dongsheng.yang(a)easystack.cn> mainline inclusion from v5.11-rc1 commit df4ad53242158f9f1f97daf4feddbb4f8b77f080 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I59A5L?from=project-issue CVE: N/A ----------------------------------------------- There is a race condition in detaching as below: A. detaching B. Write request (1) writing back (2) write back done, set bdev state to clean. (3) cached_dev_put() and schedule_work(&dc->detach); (4) write data [0 - 4K] directly into backing and ack to user. (5) power-failure... When we restart this bcache device, this bdev is clean but not detached, and read [0 - 4K], we will get unexpected old data from cache device. To fix this problem, set the bdev state to none when we writeback done in detaching, and then if power-failure happened as above, the data in cache will not be used in next bcache device starting, it's detached, we will read the correct data from backing derectly. Signed-off-by: Dongsheng Yang <dongsheng.yang(a)easystack.cn> Signed-off-by: Coly Li <colyli(a)suse.de> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- drivers/md/bcache/super.c | 9 --------- drivers/md/bcache/writeback.c | 9 +++++++++ 2 files changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 81f1cc5b3499..b7d9d1b79ac2 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1151,9 +1151,6 @@ static void cancel_writeback_rate_update_dwork(struct cached_dev *dc) static void cached_dev_detach_finish(struct work_struct *w) { struct cached_dev *dc = container_of(w, struct cached_dev, detach); - struct closure cl; - - closure_init_stack(&cl); BUG_ON(!test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags)); BUG_ON(refcount_read(&dc->count)); @@ -1167,12 +1164,6 @@ static void cached_dev_detach_finish(struct work_struct *w) dc->writeback_thread = NULL; } - memset(&dc->sb.set_uuid, 0, 16); - SET_BDEV_STATE(&dc->sb, BDEV_STATE_NONE); - - bch_write_bdev_super(dc, &cl); - closure_sync(&cl); - mutex_lock(&bch_register_lock); calc_cached_dev_sectors(dc->disk.c); diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index 3c74996978da..a129e4d2707c 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -705,6 +705,15 @@ static int bch_writeback_thread(void *arg) * bch_cached_dev_detach(). */ if (test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags)) { + struct closure cl; + + closure_init_stack(&cl); + memset(&dc->sb.set_uuid, 0, 16); + SET_BDEV_STATE(&dc->sb, BDEV_STATE_NONE); + + bch_write_bdev_super(dc, &cl); + closure_sync(&cl); + up_write(&dc->writeback_lock); break; } -- 2.20.1

1 54

[PATCH openEuler-5.10-LTS 00/28] Backport 5.10.108 LTS
by Zheng Zengkai 21 Jun '22

21 Jun '22

Backport 5.10.108 LTS patches from upstream Revert "selftests/bpf: Add test for bpf_timer overwriting crash" smsc95xx: Ignore -ENODEV errors when device is unplugged net: usb: Correct reset handling of smsc95xx net: usb: Correct PHY handling of smsc95xx perf symbols: Fix symbol size calculation condition Input: aiptek - properly check endpoint type scsi: mpt3sas: Page fault in reply q processing usb: usbtmc: Fix bug in pipe direction for control transfers usb: gadget: Fix use-after-free bug by not setting udc->dev.driver net: mscc: ocelot: fix backwards compatibility with single-chain tc-flower offload net: bcmgenet: skip invalid partial checksums bnx2x: fix built-in kernel driver load failure net: phy: mscc: Add MODULE_FIRMWARE macros net: dsa: Add missing of_node_put() in dsa_port_parse_of net: handle ARPHRD_PIMREG in dev_is_mac_header_xmit() drm/panel: simple: Fix Innolux G070Y2-L01 BPP settings drm/imx: parallel-display: Remove bus flags check in imx_pd_bridge_atomic_check() hv_netvsc: Add check for kvmalloc_array atm: eni: Add check for dma_map_single net/packet: fix slab-out-of-bounds access in packet_recvmsg() net: phy: marvell: Fix invalid comparison in the resume and suspend functions esp6: fix check on ipv6_skip_exthdr's return value vsock: each transport cycles only on its own sockets efi: fix return value of __setup handlers mm: swap: get rid of livelock in swapin readahead ocfs2: fix crash when initialize filecheck kobj fails crypto: qcom-rng - ensure buffer for generate is completely filled already merged (2) esp: Fix possible buffer overflow in ESP transformation arm64: fix clang warning about TRAMP_VALIAS Total patches = 30 - 2 = 28 Alan Stern (2): usb: gadget: Fix use-after-free bug by not setting udc->dev.driver usb: usbtmc: Fix bug in pipe direction for control transfers Brian Masney (1): crypto: qcom-rng - ensure buffer for generate is completely filled Christoph Niedermaier (1): drm/imx: parallel-display: Remove bus flags check in imx_pd_bridge_atomic_check() Dan Carpenter (1): usb: gadget: rndis: prevent integer overflow in rndis_set_response() Doug Berger (1): net: bcmgenet: skip invalid partial checksums Eric Dumazet (1): net/packet: fix slab-out-of-bounds access in packet_recvmsg() Fabio Estevam (1): smsc95xx: Ignore -ENODEV errors when device is unplugged Greg Kroah-Hartman (1): Revert "selftests/bpf: Add test for bpf_timer overwriting crash" Guo Ziliang (1): mm: swap: get rid of livelock in swapin readahead Jiasheng Jiang (2): atm: eni: Add check for dma_map_single hv_netvsc: Add check for kvmalloc_array Jiyong Park (1): vsock: each transport cycles only on its own sockets Joseph Qi (1): ocfs2: fix crash when initialize filecheck kobj fails Juerg Haefliger (1): net: phy: mscc: Add MODULE_FIRMWARE macros Kurt Cancemi (1): net: phy: marvell: Fix invalid comparison in the resume and suspend functions Manish Chopra (1): bnx2x: fix built-in kernel driver load failure Marek Vasut (1): drm/panel: simple: Fix Innolux G070Y2-L01 BPP settings Markus Reichl (1): net: usb: Correct reset handling of smsc95xx Martyn Welch (1): net: usb: Correct PHY handling of smsc95xx Matt Lupfer (1): scsi: mpt3sas: Page fault in reply q processing Miaoqian Lin (1): net: dsa: Add missing of_node_put() in dsa_port_parse_of Michael Petlan (1): perf symbols: Fix symbol size calculation condition Nicolas Dichtel (1): net: handle ARPHRD_PIMREG in dev_is_mac_header_xmit() Pavel Skripkin (1): Input: aiptek - properly check endpoint type Randy Dunlap (1): efi: fix return value of __setup handlers Sabrina Dubroca (1): esp6: fix check on ipv6_skip_exthdr's return value Vladimir Oltean (1): net: mscc: ocelot: fix backwards compatibility with single-chain tc-flower offload drivers/atm/eni.c | 2 + drivers/crypto/qcom-rng.c | 17 ++-- drivers/firmware/efi/apple-properties.c | 2 +- drivers/firmware/efi/efi.c | 2 +- drivers/gpu/drm/imx/parallel-display.c | 8 -- drivers/gpu/drm/panel/panel-simple.c | 2 +- drivers/input/tablet/aiptek.c | 10 +-- drivers/net/ethernet/broadcom/bnx2x/bnx2x.h | 2 - .../net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 28 +++--- .../net/ethernet/broadcom/bnx2x/bnx2x_main.c | 15 +--- .../net/ethernet/broadcom/genet/bcmgenet.c | 6 +- drivers/net/ethernet/mscc/ocelot_flower.c | 16 +++- drivers/net/hyperv/netvsc_drv.c | 3 + drivers/net/phy/marvell.c | 8 +- drivers/net/phy/mscc/mscc_main.c | 3 + drivers/net/usb/smsc95xx.c | 86 +++++++++++-------- drivers/scsi/mpt3sas/mpt3sas_base.c | 5 +- drivers/usb/class/usbtmc.c | 13 ++- drivers/usb/gadget/function/rndis.c | 1 + drivers/usb/gadget/udc/core.c | 3 - drivers/vhost/vsock.c | 3 +- fs/ocfs2/super.c | 22 ++--- include/linux/if_arp.h | 1 + include/net/af_vsock.h | 3 +- mm/swap_state.c | 2 +- net/dsa/dsa2.c | 1 + net/ipv6/esp6.c | 3 +- net/packet/af_packet.c | 11 ++- net/vmw_vsock/af_vsock.c | 9 +- net/vmw_vsock/virtio_transport.c | 7 +- net/vmw_vsock/vmci_transport.c | 5 +- tools/perf/util/symbol.c | 2 +- .../selftests/bpf/prog_tests/timer_crash.c | 32 ------- .../testing/selftests/bpf/progs/timer_crash.c | 54 ------------ 34 files changed, 175 insertions(+), 212 deletions(-) delete mode 100644 tools/testing/selftests/bpf/prog_tests/timer_crash.c delete mode 100644 tools/testing/selftests/bpf/progs/timer_crash.c -- 2.20.1

1 28

[PATCH openEuler-1.0-LTS 1/4] sched: Introduce qos smt expeller for co-location
by liuzhengyuan＠kylinos.cn 21 Jun '22

21 Jun '22

From: Guan Jing <guanjing6(a)huawei.com> hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I52611 CVE: NA -------------------------------- We introduce the qos smt expeller, which lets online tasks to expel offline tasks on the smt sibling cpus, and exclusively occupy CPU resources.In this way we are able to improve QOS of online tasks in co-location. Change-Id: I1860d20d5e78467773e67cc47b4fa2d1f0110783 Signed-off-by: Guan Jing <guanjing6(a)huawei.com> Reviewed-by: Chen Hui <judy.chenhui(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> Signed-off-by: Zhengyuan Liu <liuzhengyuan(a)kylinos.cn> --- init/Kconfig | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/init/Kconfig b/init/Kconfig index ac1c864524ac..dd81d19e2fcb 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -794,6 +794,15 @@ config QOS_SCHED default n +config QOS_SCHED_SMT_EXPELLER + bool "Qos smt expeller" + depends on SCHED_SMT + depends on QOS_SCHED + default n + help + This feature enable online tasks to expel offline tasks + on the smt sibling cpus, and exclusively occupy CPU resources. + config FAIR_GROUP_SCHED bool "Group scheduling for SCHED_OTHER" depends on CGROUP_SCHED -- 2.25.1

1 3

[PATCH openEuler-1.0-LTS 1/6] drivers core: Use sysfs_emit and sysfs_emit_at for show(device *...) functions
by Yongqiang Liu 21 Jun '22

21 Jun '22

From: Joe Perches <joe(a)perches.com> mainline inclusion from mainline-v5.10-rc1 commit aa838896d87af561a33ecefea1caa4c15a68bc47 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I5C32F CVE: CVE-2022-20166 ---------------------------------------------- Convert the various sprintf fmaily calls in sysfs device show functions to sysfs_emit and sysfs_emit_at for PAGE_SIZE buffer safety. Done with: $ spatch -sp-file sysfs_emit_dev.cocci --in-place --max-width=80 . And cocci script: $ cat sysfs_emit_dev.cocci @@ identifier d_show; identifier dev, attr, buf; @@ ssize_t d_show(struct device *dev, struct device_attribute *attr, char *buf) { <... return - sprintf(buf, + sysfs_emit(buf, ...); ...> } @@ identifier d_show; identifier dev, attr, buf; @@ ssize_t d_show(struct device *dev, struct device_attribute *attr, char *buf) { <... return - snprintf(buf, PAGE_SIZE, + sysfs_emit(buf, ...); ...> } @@ identifier d_show; identifier dev, attr, buf; @@ ssize_t d_show(struct device *dev, struct device_attribute *attr, char *buf) { <... return - scnprintf(buf, PAGE_SIZE, + sysfs_emit(buf, ...); ...> } @@ identifier d_show; identifier dev, attr, buf; expression chr; @@ ssize_t d_show(struct device *dev, struct device_attribute *attr, char *buf) { <... return - strcpy(buf, chr); + sysfs_emit(buf, chr); ...> } @@ identifier d_show; identifier dev, attr, buf; identifier len; @@ ssize_t d_show(struct device *dev, struct device_attribute *attr, char *buf) { <... len = - sprintf(buf, + sysfs_emit(buf, ...); ...> return len; } @@ identifier d_show; identifier dev, attr, buf; identifier len; @@ ssize_t d_show(struct device *dev, struct device_attribute *attr, char *buf) { <... len = - snprintf(buf, PAGE_SIZE, + sysfs_emit(buf, ...); ...> return len; } @@ identifier d_show; identifier dev, attr, buf; identifier len; @@ ssize_t d_show(struct device *dev, struct device_attribute *attr, char *buf) { <... len = - scnprintf(buf, PAGE_SIZE, + sysfs_emit(buf, ...); ...> return len; } @@ identifier d_show; identifier dev, attr, buf; identifier len; @@ ssize_t d_show(struct device *dev, struct device_attribute *attr, char *buf) { <... - len += scnprintf(buf + len, PAGE_SIZE - len, + len += sysfs_emit_at(buf, len, ...); ...> return len; } @@ identifier d_show; identifier dev, attr, buf; expression chr; @@ ssize_t d_show(struct device *dev, struct device_attribute *attr, char *buf) { ... - strcpy(buf, chr); - return strlen(buf); + return sysfs_emit(buf, chr); } Signed-off-by: Joe Perches <joe(a)perches.com> Link: https://lore.kernel.org/r/3d033c33056d88bbe34d4ddb62afd05ee166ab9a.16002859… Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: drivers/base/node.c Signed-off-by: Guo Mengqi <guomengqi3(a)huawei.com> Reviewed-by: Weilong Chen <chenweilong(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/base/arch_topology.c | 3 +- drivers/base/cacheinfo.c | 18 ++++----- drivers/base/core.c | 8 ++-- drivers/base/cpu.c | 26 ++++++------ drivers/base/firmware_loader/fallback.c | 2 +- drivers/base/memory.c | 24 +++++------ drivers/base/node.c | 26 ++++++------ drivers/base/platform.c | 2 +- drivers/base/power/sysfs.c | 53 +++++++++++++------------ drivers/base/soc.c | 8 ++-- 10 files changed, 86 insertions(+), 84 deletions(-) diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 7157e4039b4c..729dded51e7b 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -42,7 +42,8 @@ static ssize_t cpu_capacity_show(struct device *dev, { struct cpu *cpu = container_of(dev, struct cpu, dev); - return sprintf(buf, "%lu\n", topology_get_cpu_scale(NULL, cpu->dev.id)); + return sysfs_emit(buf, "%lu\n", + topology_get_cpu_scale(NULL, cpu->dev.id)); } static DEVICE_ATTR_RO(cpu_capacity); diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c index aee69d78c2e7..f7d107ca1a66 100644 --- a/drivers/base/cacheinfo.c +++ b/drivers/base/cacheinfo.c @@ -415,7 +415,7 @@ static ssize_t size_show(struct device *dev, { struct cacheinfo *this_leaf = dev_get_drvdata(dev); - return sprintf(buf, "%uK\n", this_leaf->size >> 10); + return sysfs_emit(buf, "%uK\n", this_leaf->size >> 10); } static ssize_t shared_cpumap_show_func(struct device *dev, bool list, char *buf) @@ -445,11 +445,11 @@ static ssize_t type_show(struct device *dev, switch (this_leaf->type) { case CACHE_TYPE_DATA: - return sprintf(buf, "Data\n"); + return sysfs_emit(buf, "Data\n"); case CACHE_TYPE_INST: - return sprintf(buf, "Instruction\n"); + return sysfs_emit(buf, "Instruction\n"); case CACHE_TYPE_UNIFIED: - return sprintf(buf, "Unified\n"); + return sysfs_emit(buf, "Unified\n"); default: return -EINVAL; } @@ -463,11 +463,11 @@ static ssize_t allocation_policy_show(struct device *dev, int n = 0; if ((ci_attr & CACHE_READ_ALLOCATE) && (ci_attr & CACHE_WRITE_ALLOCATE)) - n = sprintf(buf, "ReadWriteAllocate\n"); + n = sysfs_emit(buf, "ReadWriteAllocate\n"); else if (ci_attr & CACHE_READ_ALLOCATE) - n = sprintf(buf, "ReadAllocate\n"); + n = sysfs_emit(buf, "ReadAllocate\n"); else if (ci_attr & CACHE_WRITE_ALLOCATE) - n = sprintf(buf, "WriteAllocate\n"); + n = sysfs_emit(buf, "WriteAllocate\n"); return n; } @@ -479,9 +479,9 @@ static ssize_t write_policy_show(struct device *dev, int n = 0; if (ci_attr & CACHE_WRITE_THROUGH) - n = sprintf(buf, "WriteThrough\n"); + n = sysfs_emit(buf, "WriteThrough\n"); else if (ci_attr & CACHE_WRITE_BACK) - n = sprintf(buf, "WriteBack\n"); + n = sysfs_emit(buf, "WriteBack\n"); return n; } diff --git a/drivers/base/core.c b/drivers/base/core.c index f6d8a4246adf..b4f80e82a91f 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -994,7 +994,7 @@ ssize_t device_show_ulong(struct device *dev, char *buf) { struct dev_ext_attribute *ea = to_ext_attr(attr); - return snprintf(buf, PAGE_SIZE, "%lx\n", *(unsigned long *)(ea->var)); + return sysfs_emit(buf, "%lx\n", *(unsigned long *)(ea->var)); } EXPORT_SYMBOL_GPL(device_show_ulong); @@ -1019,7 +1019,7 @@ ssize_t device_show_int(struct device *dev, { struct dev_ext_attribute *ea = to_ext_attr(attr); - return snprintf(buf, PAGE_SIZE, "%d\n", *(int *)(ea->var)); + return sysfs_emit(buf, "%d\n", *(int *)(ea->var)); } EXPORT_SYMBOL_GPL(device_show_int); @@ -1040,7 +1040,7 @@ ssize_t device_show_bool(struct device *dev, struct device_attribute *attr, { struct dev_ext_attribute *ea = to_ext_attr(attr); - return snprintf(buf, PAGE_SIZE, "%d\n", *(bool *)(ea->var)); + return sysfs_emit(buf, "%d\n", *(bool *)(ea->var)); } EXPORT_SYMBOL_GPL(device_show_bool); @@ -1273,7 +1273,7 @@ static ssize_t online_show(struct device *dev, struct device_attribute *attr, device_lock(dev); val = !dev->offline; device_unlock(dev); - return sprintf(buf, "%u\n", val); + return sysfs_emit(buf, "%u\n", val); } static ssize_t online_store(struct device *dev, struct device_attribute *attr, diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 1df057486176..128e5867c35d 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -156,7 +156,7 @@ static ssize_t show_crash_notes(struct device *dev, struct device_attribute *att * operation should be safe. No locking required. */ addr = per_cpu_ptr_to_phys(per_cpu_ptr(crash_notes, cpunum)); - rc = sprintf(buf, "%Lx\n", addr); + rc = sysfs_emit(buf, "%Lx\n", addr); return rc; } static DEVICE_ATTR(crash_notes, 0400, show_crash_notes, NULL); @@ -167,7 +167,7 @@ static ssize_t show_crash_notes_size(struct device *dev, { ssize_t rc; - rc = sprintf(buf, "%zu\n", sizeof(note_buf_t)); + rc = sysfs_emit(buf, "%zu\n", sizeof(note_buf_t)); return rc; } static DEVICE_ATTR(crash_notes_size, 0400, show_crash_notes_size, NULL); @@ -328,8 +328,8 @@ static ssize_t print_cpu_modalias(struct device *dev, ssize_t n; u32 i; - n = sprintf(buf, "cpu:type:" CPU_FEATURE_TYPEFMT ":feature:", - CPU_FEATURE_TYPEVAL); + n = sysfs_emit(buf, "cpu:type:" CPU_FEATURE_TYPEFMT ":feature:", + CPU_FEATURE_TYPEVAL); for (i = 0; i < MAX_CPU_FEATURES; i++) if (cpu_have_feature(i)) { @@ -519,56 +519,56 @@ static void __init cpu_dev_register_generic(void) ssize_t __weak cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "Not affected\n"); + return sysfs_emit(buf, "Not affected\n"); } ssize_t __weak cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "Not affected\n"); + return sysfs_emit(buf, "Not affected\n"); } ssize_t __weak cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "Not affected\n"); + return sysfs_emit(buf, "Not affected\n"); } ssize_t __weak cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "Not affected\n"); + return sysfs_emit(buf, "Not affected\n"); } ssize_t __weak cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "Not affected\n"); + return sysfs_emit(buf, "Not affected\n"); } ssize_t __weak cpu_show_mds(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "Not affected\n"); + return sysfs_emit(buf, "Not affected\n"); } ssize_t __weak cpu_show_tsx_async_abort(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "Not affected\n"); + return sysfs_emit(buf, "Not affected\n"); } ssize_t __weak cpu_show_itlb_multihit(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "Not affected\n"); + return sysfs_emit(buf, "Not affected\n"); } ssize_t __weak cpu_show_srbds(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "Not affected\n"); + return sysfs_emit(buf, "Not affected\n"); } static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); diff --git a/drivers/base/firmware_loader/fallback.c b/drivers/base/firmware_loader/fallback.c index 818d8c37d70a..ab619da92734 100644 --- a/drivers/base/firmware_loader/fallback.c +++ b/drivers/base/firmware_loader/fallback.c @@ -216,7 +216,7 @@ static ssize_t firmware_loading_show(struct device *dev, loading = fw_sysfs_loading(fw_sysfs->fw_priv); mutex_unlock(&fw_lock); - return sprintf(buf, "%d\n", loading); + return sysfs_emit(buf, "%d\n", loading); } /* one pages buffer should be mapped/unmapped only once */ diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 1b97f305173f..54225b812cd7 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -140,7 +140,7 @@ static ssize_t phys_index_show(struct device *dev, unsigned long phys_index; phys_index = mem->start_section_nr / sections_per_block; - return sprintf(buf, "%08lx\n", phys_index); + return sysfs_emit(buf, "%08lx\n", phys_index); } /* @@ -164,7 +164,7 @@ static ssize_t removable_show(struct device *dev, struct device_attribute *attr, } out: - return sprintf(buf, "%d\n", ret); + return sysfs_emit(buf, "%d\n", ret); } /* @@ -182,17 +182,17 @@ static ssize_t state_show(struct device *dev, struct device_attribute *attr, */ switch (mem->state) { case MEM_ONLINE: - len = sprintf(buf, "online\n"); + len = sysfs_emit(buf, "online\n"); break; case MEM_OFFLINE: - len = sprintf(buf, "offline\n"); + len = sysfs_emit(buf, "offline\n"); break; case MEM_GOING_OFFLINE: - len = sprintf(buf, "going-offline\n"); + len = sysfs_emit(buf, "going-offline\n"); break; default: - len = sprintf(buf, "ERROR-UNKNOWN-%ld\n", - mem->state); + len = sysfs_emit(buf, "ERROR-UNKNOWN-%ld\n", + mem->state); WARN_ON(1); break; } @@ -389,7 +389,7 @@ static ssize_t phys_device_show(struct device *dev, struct device_attribute *attr, char *buf) { struct memory_block *mem = to_memory_block(dev); - return sprintf(buf, "%d\n", mem->phys_device); + return sysfs_emit(buf, "%d\n", mem->phys_device); } #ifdef CONFIG_MEMORY_HOTREMOVE @@ -427,7 +427,7 @@ static ssize_t valid_zones_show(struct device *dev, */ if (!test_pages_in_a_zone(start_pfn, start_pfn + nr_pages, &valid_start_pfn, &valid_end_pfn)) - return sprintf(buf, "none\n"); + return sysfs_emit(buf, "none\n"); start_pfn = valid_start_pfn; strcat(buf, page_zone(pfn_to_page(start_pfn))->name); goto out; @@ -461,7 +461,7 @@ static DEVICE_ATTR_RO(removable); static ssize_t block_size_bytes_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "%lx\n", get_memory_block_size()); + return sysfs_emit(buf, "%lx\n", get_memory_block_size()); } static DEVICE_ATTR_RO(block_size_bytes); @@ -473,8 +473,8 @@ static DEVICE_ATTR_RO(block_size_bytes); static ssize_t auto_online_blocks_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "%s\n", - online_type_to_str[memhp_default_online_type]); + return sysfs_emit(buf, "%s\n", + online_type_to_str[memhp_default_online_type]); } static ssize_t auto_online_blocks_store(struct device *dev, diff --git a/drivers/base/node.c b/drivers/base/node.c index ac44db3f63c7..7a807e471fbf 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -457,19 +457,19 @@ static DEVICE_ATTR(meminfo, S_IRUGO, node_read_meminfo, NULL); static ssize_t node_read_numastat(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, - "numa_hit %lu\n" - "numa_miss %lu\n" - "numa_foreign %lu\n" - "interleave_hit %lu\n" - "local_node %lu\n" - "other_node %lu\n", - sum_zone_numa_state(dev->id, NUMA_HIT), - sum_zone_numa_state(dev->id, NUMA_MISS), - sum_zone_numa_state(dev->id, NUMA_FOREIGN), - sum_zone_numa_state(dev->id, NUMA_INTERLEAVE_HIT), - sum_zone_numa_state(dev->id, NUMA_LOCAL), - sum_zone_numa_state(dev->id, NUMA_OTHER)); + return sysfs_emit(buf, + "numa_hit %lu\n" + "numa_miss %lu\n" + "numa_foreign %lu\n" + "interleave_hit %lu\n" + "local_node %lu\n" + "other_node %lu\n", + sum_zone_numa_state(dev->id, NUMA_HIT), + sum_zone_numa_state(dev->id, NUMA_MISS), + sum_zone_numa_state(dev->id, NUMA_FOREIGN), + sum_zone_numa_state(dev->id, NUMA_INTERLEAVE_HIT), + sum_zone_numa_state(dev->id, NUMA_LOCAL), + sum_zone_numa_state(dev->id, NUMA_OTHER)); } static DEVICE_ATTR(numastat, S_IRUGO, node_read_numastat, NULL); diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 349c2754eed7..fe3f4225d80a 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -907,7 +907,7 @@ static ssize_t driver_override_show(struct device *dev, ssize_t len; device_lock(dev); - len = sprintf(buf, "%s\n", pdev->driver_override); + len = sysfs_emit(buf, "%s\n", pdev->driver_override); device_unlock(dev); return len; } diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c index d713738ce796..d071d5d1a6d7 100644 --- a/drivers/base/power/sysfs.c +++ b/drivers/base/power/sysfs.c @@ -101,7 +101,7 @@ static const char ctrl_on[] = "on"; static ssize_t control_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "%s\n", + return sysfs_emit(buf, "%s\n", dev->power.runtime_auto ? ctrl_auto : ctrl_on); } @@ -127,7 +127,8 @@ static ssize_t runtime_active_time_show(struct device *dev, int ret; spin_lock_irq(&dev->power.lock); update_pm_runtime_accounting(dev); - ret = sprintf(buf, "%i\n", jiffies_to_msecs(dev->power.active_jiffies)); + ret = sysfs_emit(buf, "%i\n", + jiffies_to_msecs(dev->power.active_jiffies)); spin_unlock_irq(&dev->power.lock); return ret; } @@ -140,8 +141,8 @@ static ssize_t runtime_suspended_time_show(struct device *dev, int ret; spin_lock_irq(&dev->power.lock); update_pm_runtime_accounting(dev); - ret = sprintf(buf, "%i\n", - jiffies_to_msecs(dev->power.suspended_jiffies)); + ret = sysfs_emit(buf, "%i\n", + jiffies_to_msecs(dev->power.suspended_jiffies)); spin_unlock_irq(&dev->power.lock); return ret; } @@ -175,7 +176,7 @@ static ssize_t runtime_status_show(struct device *dev, return -EIO; } } - return sprintf(buf, p); + return sysfs_emit(buf, p); } static DEVICE_ATTR_RO(runtime_status); @@ -185,7 +186,7 @@ static ssize_t autosuspend_delay_ms_show(struct device *dev, { if (!dev->power.use_autosuspend) return -EIO; - return sprintf(buf, "%d\n", dev->power.autosuspend_delay); + return sysfs_emit(buf, "%d\n", dev->power.autosuspend_delay); } static ssize_t autosuspend_delay_ms_store(struct device *dev, @@ -214,11 +215,11 @@ static ssize_t pm_qos_resume_latency_us_show(struct device *dev, s32 value = dev_pm_qos_requested_resume_latency(dev); if (value == 0) - return sprintf(buf, "n/a\n"); + return sysfs_emit(buf, "n/a\n"); if (value == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT) value = 0; - return sprintf(buf, "%d\n", value); + return sysfs_emit(buf, "%d\n", value); } static ssize_t pm_qos_resume_latency_us_store(struct device *dev, @@ -258,11 +259,11 @@ static ssize_t pm_qos_latency_tolerance_us_show(struct device *dev, s32 value = dev_pm_qos_get_user_latency_tolerance(dev); if (value < 0) - return sprintf(buf, "auto\n"); + return sysfs_emit(buf, "auto\n"); if (value == PM_QOS_LATENCY_ANY) - return sprintf(buf, "any\n"); + return sysfs_emit(buf, "any\n"); - return sprintf(buf, "%d\n", value); + return sysfs_emit(buf, "%d\n", value); } static ssize_t pm_qos_latency_tolerance_us_store(struct device *dev, @@ -294,8 +295,8 @@ static ssize_t pm_qos_no_power_off_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "%d\n", !!(dev_pm_qos_requested_flags(dev) - & PM_QOS_FLAG_NO_POWER_OFF)); + return sysfs_emit(buf, "%d\n", !!(dev_pm_qos_requested_flags(dev) + & PM_QOS_FLAG_NO_POWER_OFF)); } static ssize_t pm_qos_no_power_off_store(struct device *dev, @@ -323,9 +324,9 @@ static const char _disabled[] = "disabled"; static ssize_t wakeup_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "%s\n", device_can_wakeup(dev) - ? (device_may_wakeup(dev) ? _enabled : _disabled) - : ""); + return sysfs_emit(buf, "%s\n", device_can_wakeup(dev) + ? (device_may_wakeup(dev) ? _enabled : _disabled) + : ""); } static ssize_t wakeup_store(struct device *dev, struct device_attribute *attr, @@ -511,7 +512,7 @@ static DEVICE_ATTR_RO(wakeup_prevent_sleep_time_ms); static ssize_t runtime_usage_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "%d\n", atomic_read(&dev->power.usage_count)); + return sysfs_emit(buf, "%d\n", atomic_read(&dev->power.usage_count)); } static DEVICE_ATTR_RO(runtime_usage); @@ -519,8 +520,8 @@ static ssize_t runtime_active_kids_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "%d\n", dev->power.ignore_children ? - 0 : atomic_read(&dev->power.child_count)); + return sysfs_emit(buf, "%d\n", dev->power.ignore_children ? + 0 : atomic_read(&dev->power.child_count)); } static DEVICE_ATTR_RO(runtime_active_kids); @@ -528,12 +529,12 @@ static ssize_t runtime_enabled_show(struct device *dev, struct device_attribute *attr, char *buf) { if (dev->power.disable_depth && (dev->power.runtime_auto == false)) - return sprintf(buf, "disabled & forbidden\n"); + return sysfs_emit(buf, "disabled & forbidden\n"); if (dev->power.disable_depth) - return sprintf(buf, "disabled\n"); + return sysfs_emit(buf, "disabled\n"); if (dev->power.runtime_auto == false) - return sprintf(buf, "forbidden\n"); - return sprintf(buf, "enabled\n"); + return sysfs_emit(buf, "forbidden\n"); + return sysfs_emit(buf, "enabled\n"); } static DEVICE_ATTR_RO(runtime_enabled); @@ -541,9 +542,9 @@ static DEVICE_ATTR_RO(runtime_enabled); static ssize_t async_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "%s\n", - device_async_suspend_enabled(dev) ? - _enabled : _disabled); + return sysfs_emit(buf, "%s\n", + device_async_suspend_enabled(dev) ? + _enabled : _disabled); } static ssize_t async_store(struct device *dev, struct device_attribute *attr, diff --git a/drivers/base/soc.c b/drivers/base/soc.c index 7e91894a380b..23bc9eb794a2 100644 --- a/drivers/base/soc.c +++ b/drivers/base/soc.c @@ -72,13 +72,13 @@ static ssize_t soc_info_get(struct device *dev, struct soc_device *soc_dev = container_of(dev, struct soc_device, dev); if (attr == &dev_attr_machine) - return sprintf(buf, "%s\n", soc_dev->attr->machine); + return sysfs_emit(buf, "%s\n", soc_dev->attr->machine); if (attr == &dev_attr_family) - return sprintf(buf, "%s\n", soc_dev->attr->family); + return sysfs_emit(buf, "%s\n", soc_dev->attr->family); if (attr == &dev_attr_revision) - return sprintf(buf, "%s\n", soc_dev->attr->revision); + return sysfs_emit(buf, "%s\n", soc_dev->attr->revision); if (attr == &dev_attr_soc_id) - return sprintf(buf, "%s\n", soc_dev->attr->soc_id); + return sysfs_emit(buf, "%s\n", soc_dev->attr->soc_id); return -EINVAL; -- 2.25.1

1 5

[PATCH] drm/atomic-helper: Bump vblank timeout to 100 ms
by jiazhenyuan＠uniontech.com 21 Jun '22

21 Jun '22

From: jiazhenyuan <jiazhenyuan(a)uniontech.com> mainline inclusion from mainline-v5.1.0-rc2 commit b3198c38f02d54a5e964258a2180d502abe6eaf0 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I5D0PL CVE: NA -------------------------------- The 50 ms default timeout waiting for vblanks is too small for the first vblank from the ST-Ericsson MCDE display controller over DSI. Presumably this is because the DSI display is command-mode only and the state machine will take some time setting up its state for the first display update, and we hit a timeout. 100 ms makes it pass without problems. Signed-off-by: Linus Walleij <linus.walleij(a)linaro.org> Reviewed-by: Ville Syrjälä <ville.syrjala(a)linux.intel.com> Reviewed-by: Daniel Vetter <daniel.vetter(a)ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20190430093746.26485-1-linus.… Signed-off-by: jiazhenyuan <jiazhenyuan(a)uniontech.com> --- drivers/gpu/drm/drm_atomic_helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index c22062cc9992..f9306c3e9bab 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -1380,7 +1380,7 @@ drm_atomic_helper_wait_for_vblanks(struct drm_device *dev, ret = wait_event_timeout(dev->vblank[i].queue, old_state->crtcs[i].last_vblank_count != drm_crtc_vblank_count(crtc), - msecs_to_jiffies(50)); + msecs_to_jiffies(100)); WARN(!ret, "[CRTC:%d:%s] vblank wait timed out\n", crtc->base.id, crtc->name); -- 2.27.0

1 0

[PATCH openEuler-1.0-LTS] RDMA/cma: Do not change route.addr.src_addr.ss_family
by tangbin 21 Jun '22

21 Jun '22

From: Jason Gunthorpe <jgg(a)nvidia.com> mainline inclusion from mainline-v5.15-rc4 commit bc0bdc5afaa740d782fbf936aaeebd65e5c2921d category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I59840 CVE: CVE-2021-4028 -------------------------------- Conflicts: The conditional statement to verify RDMA_CM_IDLE state is a little bit different from the upstream to 4.19. The commit 732d41c545bb (RDMA/cma: Make the locking for automatic state transition more clear) is missing from 4.19. So, the context has been modified. If the state is not idle then rdma_bind_addr() will immediately fail and no change to global state should happen. For instance if the state is already RDMA_CM_LISTEN then this will corrupt the src_addr and would cause the test in cma_cancel_operation(): if (cma_any_addr(cma_src_addr(id_priv)) && !id_priv->cma_dev) To view a mangled src_addr, eg with a IPv6 loopback address but an IPv4 family, failing the test. This would manifest as this trace from syzkaller: BUG: KASAN: use-after-free in __list_add_valid+0x93/0xa0 lib/list_debug.c:26 Read of size 8 at addr ffff8881546491e0 by task syz-executor.1/32204 CPU: 1 PID: 32204 Comm: syz-executor.1 Not tainted 5.12.0-rc8-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:79 [inline] dump_stack+0x141/0x1d7 lib/dump_stack.c:120 print_address_description.constprop.0.cold+0x5b/0x2f8 mm/kasan/report.c:232 __kasan_report mm/kasan/report.c:399 [inline] kasan_report.cold+0x7c/0xd8 mm/kasan/report.c:416 __list_add_valid+0x93/0xa0 lib/list_debug.c:26 __list_add include/linux/list.h:67 [inline] list_add_tail include/linux/list.h:100 [inline] cma_listen_on_all drivers/infiniband/core/cma.c:2557 [inline] rdma_listen+0x787/0xe00 drivers/infiniband/core/cma.c:3751 ucma_listen+0x16a/0x210 drivers/infiniband/core/ucma.c:1102 ucma_write+0x259/0x350 drivers/infiniband/core/ucma.c:1732 vfs_write+0x28e/0xa30 fs/read_write.c:603 ksys_write+0x1ee/0x250 fs/read_write.c:658 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xae Which is indicating that an rdma_id_private was destroyed without doing cma_cancel_listens(). Instead of trying to re-use the src_addr memory to indirectly create an any address build one explicitly on the stack and bind to that as any other normal flow would do. Link: https://lore.kernel.org/r/0-v1-9fbb33f5e201+2a-cma_listen_jgg@nvidia.com Cc: stable(a)vger.kernel.org Fixes: 732d41c545bb ("RDMA/cma: Make the locking for automatic state transition more clear") Reported-by: syzbot+6bb0528b13611047209c(a)syzkaller.appspotmail.com Tested-by: Hao Sun <sunhao.th(a)gmail.com> Reviewed-by: Leon Romanovsky <leonro(a)nvidia.com> Signed-off-by: Jason Gunthorpe <jgg(a)nvidia.com> Signed-off-by: tangbin <tangbin(a)cmss.chinamobile.com> --- drivers/infiniband/core/cma.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 319bfef00a4a..7444df92e7cf 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -3375,8 +3375,13 @@ int rdma_listen(struct rdma_cm_id *id, int backlog) id_priv = container_of(id, struct rdma_id_private, id); if (id_priv->state == RDMA_CM_IDLE) { - id->route.addr.src_addr.ss_family = AF_INET; - ret = rdma_bind_addr(id, cma_src_addr(id_priv)); + struct sockaddr_in any_in = { + .sin_family = AF_INET, + .sin_addr.s_addr = htonl(INADDR_ANY), + }; + + /* For a well behaved ULP state will be RDMA_CM_IDLE */ + ret = rdma_bind_addr(id, (struct sockaddr *)&any_in); if (ret) return ret; } -- 2.18.4

1 0

[PATCH openEuler-1.0-LTS] arm64: fix out-of-range error when adapting for ARM64_SPECTRE_BHB
by Yongqiang Liu 20 Jun '22

20 Jun '22

From: Chen Jiahao <chenjiahao16(a)huawei.com> hulk inclusion category: bugfix bugzilla: 186460, https://gitee.com/src-openeuler/kernel/issues/I53MHA CVE: CVE-2022-23960 -------------------------------- In cpufeature.c, when num is set to ARM64_SPECTRE_BHB, it should not be passed to cpu_hwcap_keys, otherwise the out-of-range error would happen as below: UBSAN: Undefined behaviour in arch/arm64/kernel/cpufeature.c:1742:3 index 40 is out of range for type 'static_key_false [39]' CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.19.90+ #1 Call trace: dump_backtrace+0x0/0x390 show_stack+0x24/0x30 dump_stack+0x130/0x188 ubsan_epilogue+0x14/0xa4 __ubsan_handle_out_of_bounds+0x144/0x184 __enable_cpu_capabilities+0x158/0x1d4 setup_cpu_features+0x34/0xc8 smp_cpus_done+0x44/0x13c smp_init+0x188/0x1a4 kernel_init_freeable+0x454/0x974 kernel_init+0x18/0x150 ret_from_fork+0x10/0x18 Because KABI cpu_hwcap_keys is consistent and defined with length ARM64_NCAPS, which is smaller than ARM64_SPECTRE_BHB. Fixes: 2df7cf898c5b ("arm64: fix extra cpucaps setup problem") Signed-off-by: Chen Jiahao <chenjiahao16(a)huawei.com> Reviewed-by: Liao Chang <liaochang1(a)huawei.com> Reviewed-by: Zhang Jianhua <chris.zjh(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- arch/arm64/kernel/cpufeature.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 996d3476f3c8..d7d8a4ab94b4 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1732,8 +1732,10 @@ __enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps, for (; caps->matches; caps++) { unsigned int num = caps->capability; - if (num == ARM64_SPECTRE_BHB) + if (num == ARM64_SPECTRE_BHB) { set_cap_spectre_bhb = true; + continue; + } if (!(caps->type & scope_mask) || !cpus_have_cap(num)) continue; -- 2.25.1

1 0

[Cancel] openEuler kernel SIG例会&技术分享
by openEuler conference 20 Jun '22

20 Jun '22

Sorry! The Zoom meeting will be held at 2022-06-24 14:00 scheduled by openEuler Kernel SIG has been cancelled.

1 0

openEuler kernel SIG例会&技术分享
by openEuler conference 20 Jun '22

20 Jun '22

您好！ Kernel SIG 邀请您参加 2022-06-24 14:00 召开的Zoom会议(自动录制) 会议主题：openEuler kernel SIG例会&技术分享会议内容： openEuler kernel 技术分享：执行实体创建与切换会议链接：https://us06web.zoom.us/j/83567640355?pwd=OHVRQ2VKcFNka0FhVjg2emQybG1Edz09 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 2022-06-24 14:00, The subject of the conference is openEuler kernel SIG例会&技术分享, Summary: openEuler kernel 技术分享：执行实体创建与切换 You can join the meeting at https://us06web.zoom.us/j/83567640355?pwd=OHVRQ2VKcFNka0FhVjg2emQybG1Edz09. 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

openEuler kernel SIG例会&技术分享
by openEuler conference 20 Jun '22

20 Jun '22

您好！ Kernel SIG 邀请您参加 2022-06-24 14:00 召开的Zoom会议(自动录制) 会议主题：openEuler kernel SIG例会&技术分享会议内容： openEuler kernel 技术分享：执行实体创建与切换会议链接：https://us06web.zoom.us/j/81671713618?pwd=eWIxeGowd1hvNTNZQUlRRmplNlZydz09 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 2022-06-24 14:00, The subject of the conference is openEuler kernel SIG例会&技术分享, Summary: openEuler kernel 技术分享：执行实体创建与切换 You can join the meeting at https://us06web.zoom.us/j/81671713618?pwd=eWIxeGowd1hvNTNZQUlRRmplNlZydz09. 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 1/8] xfs: abort xattr scrub if fatal signals are pending
by Laibin Qiu 18 Jun '22

18 Jun '22

From: "Darrick J. Wong" <darrick.wong(a)oracle.com> mainline inclusion from mainline-v5.1-rc1 commit 3258cb208caba74258ffdd8bd59972bbda9bfee1 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5BDCU CVE: NA -------------------------------- The extended attribute scrubber should abort the "read all attrs" loop if there's a fatal signal pending on the process. Signed-off-by: Darrick J. Wong <darrick.wong(a)oracle.com> Reviewed-by: Brian Foster <bfoster(a)redhat.com> Signed-off-by: tangbin <tangbin(a)cmss.chinamobile.com> Reviewed-by: Lihong Kou <koulihong(a)huawei.com> Reviewed-by: Xuenan Guo <guoxuenan(a)huawei.com> Signed-off-by: Laibin Qiu <qiulaibin(a)huawei.com> --- fs/xfs/scrub/attr.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c index 81d5e90547a1..9960bc5b5d76 100644 --- a/fs/xfs/scrub/attr.c +++ b/fs/xfs/scrub/attr.c @@ -82,6 +82,11 @@ xchk_xattr_listent( sx = container_of(context, struct xchk_xattr, context); + if (xchk_should_terminate(sx->sc, &error)) { + context->seen_enough = 1; + return; + } + if (flags & XFS_ATTR_INCOMPLETE) { /* Incomplete attr key, just mark the inode for preening. */ xchk_ino_set_preen(sx->sc, context->dp->i_ino); -- 2.25.1

1 7

[PATCH openEuler-1.0-LTS 0/8] xfs: fix the xfstests problem
by tangbin 18 Jun '22

18 Jun '22

Hi all: These patches are used to resolve the xfs problem when perform xfstests. For details about how to fix the problem, we can see the link below: https://lore.kernel.org/linux-xfs/154697976479.2839.3584921201780682011.stg… https://lore.kernel.org/linux-xfs/157232182246.593721.4902116478429075171.s… Thanks --- Darrick J. Wong (8): xfs: abort xattr scrub if fatal signals are pending xfs: scrub should flag dir/attr offsets that aren't mappable with xfs_dablk_t xfs: check directory name validity xfs: check attribute name validity xfs: check attribute leaf block structure xfs: namecheck attribute names before listing them xfs: namecheck directory entry names before listing them xfs: replace -EIO with -EFSCORRUPTED for corrupt metadata fs/xfs/libxfs/xfs_attr.c | 17 +++++++++ fs/xfs/libxfs/xfs_attr.h | 2 +- fs/xfs/libxfs/xfs_attr_leaf.c | 68 +++++++++++++++++++++++++++++++++-- fs/xfs/libxfs/xfs_attr_leaf.h | 4 +-- fs/xfs/libxfs/xfs_bmap.c | 6 ++-- fs/xfs/libxfs/xfs_dir2.c | 17 +++++++++ fs/xfs/libxfs/xfs_dir2.h | 1 + fs/xfs/libxfs/xfs_types.c | 11 ++++++ fs/xfs/libxfs/xfs_types.h | 1 + fs/xfs/scrub/attr.c | 11 ++++++ fs/xfs/scrub/bmap.c | 27 ++++++++++++++ fs/xfs/scrub/dir.c | 6 ++++ fs/xfs/xfs_attr_inactive.c | 6 ++-- fs/xfs/xfs_attr_list.c | 60 ++++++++++++++++++++----------- fs/xfs/xfs_dir2_readdir.c | 27 +++++++++++--- fs/xfs/xfs_dquot.c | 2 +- 16 files changed, 228 insertions(+), 38 deletions(-) -- 2.18.4

2 9

[PATCH OLK_5.10] update via-cputemp driver
by LeoLiuoc 17 Jun '22

17 Jun '22

zhaoxin inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I52DS7 CVE: NA -------------------------------- Optimize driver code and add support for Zhaoxin CPU. Signed-off-by: LeoLiuoc <LeoLiu-oc(a)zhaoxin.com> --- drivers/hwmon/Makefile | 3 +- drivers/hwmon/via-cputemp.c | 69 ++++++++++++++++++++----------------- 2 files changed, 39 insertions(+), 33 deletions(-) diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile index c22a5316bd91..115c0e002718 100644 --- a/drivers/hwmon/Makefile +++ b/drivers/hwmon/Makefile @@ -183,7 +183,8 @@ obj-$(CONFIG_SENSORS_TMP401) += tmp401.o obj-$(CONFIG_SENSORS_TMP421) += tmp421.o obj-$(CONFIG_SENSORS_TMP513) += tmp513.o obj-$(CONFIG_SENSORS_VEXPRESS) += vexpress-hwmon.o -obj-$(CONFIG_SENSORS_VIA_CPUTEMP)+= via-cputemp.o +obj-$(CONFIG_SENSORS_VIA_CPUTEMP) += cputemp-hwmon.o +cputemp-hwmon-objs := via-cputemp.o obj-$(CONFIG_SENSORS_VIA686A) += via686a.o obj-$(CONFIG_SENSORS_VT1211) += vt1211.o obj-$(CONFIG_SENSORS_VT8231) += vt8231.o diff --git a/drivers/hwmon/via-cputemp.c b/drivers/hwmon/via-cputemp.c index e5d18dac8ee7..1599440cc451 100644 --- a/drivers/hwmon/via-cputemp.c +++ b/drivers/hwmon/via-cputemp.c @@ -26,7 +26,8 @@ #include <asm/processor.h> #include <asm/cpu_device_id.h> -#define DRVNAME "via_cputemp" +#define VIA_DRVNAME "via_cputemp" +#define ZHAOXIN_DRVNAME "zhaoxin_cputemp" enum { SHOW_TEMP, SHOW_LABEL, SHOW_NAME }; @@ -114,17 +115,17 @@ static int via_cputemp_probe(struct platform_device *pdev) int err; u32 eax, edx; - data = devm_kzalloc(&pdev->dev, sizeof(struct via_cputemp_data), - GFP_KERNEL); + data = devm_kzalloc(&pdev->dev, sizeof(struct via_cputemp_data), GFP_KERNEL); if (!data) return -ENOMEM; data->id = pdev->id; - data->name = "via_cputemp"; if (c->x86 == 7) { + data->name = ZHAOXIN_DRVNAME; data->msr_temp = 0x1423; } else { + data->name = VIA_DRVNAME; switch (c->x86_model) { case 0xA: /* C7 A */ @@ -145,8 +146,7 @@ static int via_cputemp_probe(struct platform_device *pdev) /* test if we can access the TEMPERATURE MSR */ err = rdmsr_safe_on_cpu(data->id, data->msr_temp, &eax, &edx); if (err) { - dev_err(&pdev->dev, - "Unable to access TEMPERATURE MSR, giving up\n"); + dev_err(&pdev->dev, "Unable to access TEMPERATURE MSR, giving up\n"); return err; } @@ -165,11 +165,10 @@ static int via_cputemp_probe(struct platform_device *pdev) goto exit_remove; } - data->hwmon_dev = hwmon_device_register(&pdev->dev); + data->hwmon_dev = hwmon_device_register_with_info(&pdev->dev, data->name, NULL, NULL, NULL); if (IS_ERR(data->hwmon_dev)) { err = PTR_ERR(data->hwmon_dev); - dev_err(&pdev->dev, "Class registration failed (%d)\n", - err); + dev_err(&pdev->dev, "Class registration failed (%d)\n", err); goto exit_remove; } @@ -194,13 +193,12 @@ static int via_cputemp_remove(struct platform_device *pdev) } static struct platform_driver via_cputemp_driver = { - .driver = { - .name = DRVNAME, - }, .probe = via_cputemp_probe, .remove = via_cputemp_remove, }; +static struct platform_device_info cputemp_device_info; + struct pdev_entry { struct list_head list; struct platform_device *pdev; @@ -216,23 +214,20 @@ static int via_cputemp_online(unsigned int cpu) struct platform_device *pdev; struct pdev_entry *pdev_entry; - pdev = platform_device_alloc(DRVNAME, cpu); - if (!pdev) { - err = -ENOMEM; - pr_err("Device allocation failed\n"); + cputemp_device_info.id = cpu; + + pdev = platform_device_register_full(&cputemp_device_info); + if (IS_ERR(pdev)) { + err = PTR_ERR(pdev); + pr_err("Device registration failed (%d)\n", err); goto exit; } pdev_entry = kzalloc(sizeof(struct pdev_entry), GFP_KERNEL); if (!pdev_entry) { err = -ENOMEM; - goto exit_device_put; - } - - err = platform_device_add(pdev); - if (err) { - pr_err("Device addition failed (%d)\n", err); - goto exit_device_free; + pr_err("Pdev_entry alloc failed (%d)\n", err); + goto exit_device_unregister; } pdev_entry->pdev = pdev; @@ -243,10 +238,8 @@ static int via_cputemp_online(unsigned int cpu) return 0; -exit_device_free: - kfree(pdev_entry); -exit_device_put: - platform_device_put(pdev); +exit_device_unregister: + platform_device_unregister(pdev); exit: return err; } @@ -270,10 +263,11 @@ static int via_cputemp_down_prep(unsigned int cpu) } static const struct x86_cpu_id __initconst cputemp_ids[] = { - X86_MATCH_VENDOR_FAM_MODEL(CENTAUR, 6, X86_CENTAUR_FAM6_C7_A, NULL), - X86_MATCH_VENDOR_FAM_MODEL(CENTAUR, 6, X86_CENTAUR_FAM6_C7_D, NULL), - X86_MATCH_VENDOR_FAM_MODEL(CENTAUR, 6, X86_CENTAUR_FAM6_NANO, NULL), - X86_MATCH_VENDOR_FAM_MODEL(CENTAUR, 7, X86_MODEL_ANY, NULL), + X86_MATCH_VENDOR_FAM_MODEL(CENTAUR, 6, X86_CENTAUR_FAM6_C7_A, NULL), + X86_MATCH_VENDOR_FAM_MODEL(CENTAUR, 6, X86_CENTAUR_FAM6_C7_D, NULL), + X86_MATCH_VENDOR_FAM_MODEL(CENTAUR, 6, X86_CENTAUR_FAM6_NANO, NULL), + X86_MATCH_VENDOR_FAM_MODEL(CENTAUR, 7, X86_MODEL_ANY, NULL), + X86_MATCH_VENDOR_FAM_MODEL(ZHAOXIN, 7, X86_MODEL_ANY, NULL), {} }; MODULE_DEVICE_TABLE(x86cpu, cputemp_ids); @@ -283,15 +277,26 @@ static enum cpuhp_state via_temp_online; static int __init via_cputemp_init(void) { int err; + char *cpuhp_name; if (!x86_match_cpu(cputemp_ids)) return -ENODEV; + if (boot_cpu_data.x86 == 0x7) { + via_cputemp_driver.driver.name = ZHAOXIN_DRVNAME; + cputemp_device_info.name = ZHAOXIN_DRVNAME; + cpuhp_name = "hwmon/zhaoxin:online"; + } else { + via_cputemp_driver.driver.name = VIA_DRVNAME; + cputemp_device_info.name = VIA_DRVNAME; + cpuhp_name = "hwmon/via:online"; + } + err = platform_driver_register(&via_cputemp_driver); if (err) goto exit; - err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "hwmon/via:online", + err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, cpuhp_name, via_cputemp_online, via_cputemp_down_prep); if (err < 0) goto exit_driver_unreg; -- 2.20.1

1 0

[PATCH openEuler-1.0-LTS 1/2] tcp: change source port randomizarion at connect() time
by Yongqiang Liu 17 Jun '22

17 Jun '22

From: Eric Dumazet <edumazet(a)google.com> stable inclusion from stable-v4.19.246 commit ddec440133913a6b8880e53b896d521a4b7ff24f category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I5C3A9 CVE: CVE-2022-32296 -------------------------------- commit 190cc82489f46f9d88e73c81a47e14f80a791e1a upstream. RFC 6056 (Recommendations for Transport-Protocol Port Randomization) provides good summary of why source selection needs extra care. David Dworken reminded us that linux implements Algorithm 3 as described in RFC 6056 3.3.3 Quoting David : In the context of the web, this creates an interesting info leak where websites can count how many TCP connections a user's computer is establishing over time. For example, this allows a website to count exactly how many subresources a third party website loaded. This also allows: - Distinguishing between different users behind a VPN based on distinct source port ranges. - Tracking users over time across multiple networks. - Covert communication channels between different browsers/browser profiles running on the same computer - Tracking what applications are running on a computer based on the pattern of how fast source ports are getting incremented. Section 3.3.4 describes an enhancement, that reduces attackers ability to use the basic information currently stored into the shared 'u32 hint'. This change also decreases collision rate when multiple applications need to connect() to different destinations. Signed-off-by: Eric Dumazet <edumazet(a)google.com> Reported-by: David Dworken <ddworken(a)google.com> Cc: Willem de Bruijn <willemb(a)google.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> [SG: Adjusted context] Signed-off-by: Stefan Ghinea <stefan.ghinea(a)windriver.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: net/ipv4/inet_hashtables.c Signed-off-by: Baisong Zhong <zhongbaisong(a)huawei.com> Reviewed-by: Wei Yongjun <weiyongjun1(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- net/ipv4/inet_hashtables.c | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index bd0108aaa45b..72b8b6f44add 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -666,6 +666,17 @@ void inet_unhash(struct sock *sk) } EXPORT_SYMBOL_GPL(inet_unhash); +/* RFC 6056 3.3.4. Algorithm 4: Double-Hash Port Selection Algorithm + * Note that we use 32bit integers (vs RFC 'short integers') + * because 2^16 is not a multiple of num_ephemeral and this + * property might be used by clever attacker. + * RFC claims using TABLE_LENGTH=10 buckets gives an improvement, + * we use 256 instead to really give more isolation and + * privacy, this only consumes 1 KB of kernel memory. + */ +#define INET_TABLE_PERTURB_SHIFT 8 +static u32 table_perturb[1 << INET_TABLE_PERTURB_SHIFT]; + int __inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk, u64 port_offset, int (*check_established)(struct inet_timewait_death_row *, @@ -679,8 +690,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, struct inet_bind_bucket *tb; u32 remaining, offset; int ret, i, low, high; - static u32 hint; int l3mdev; + u32 index; if (port) { head = &hinfo->bhash[inet_bhashfn(net, port, @@ -707,7 +718,10 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, if (likely(remaining > 1)) remaining &= ~1U; - offset = hint + port_offset; + net_get_random_once(table_perturb, sizeof(table_perturb)); + index = hash_32(port_offset, INET_TABLE_PERTURB_SHIFT); + + offset = READ_ONCE(table_perturb[index]) + port_offset; offset %= remaining; /* In first pass we try ports of @low parity. * inet_csk_get_port() does the opposite choice. @@ -762,7 +776,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, return -EADDRNOTAVAIL; ok: - hint += i + 2; + WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + 2); /* Head lock still held and bh's disabled */ inet_bind_hash(sk, tb, port); -- 2.25.1

1 1

[PATCH openEuler-1.0-LTS] arm64: fix extra cpucaps setup problem
by Yongqiang Liu 16 Jun '22

16 Jun '22

From: Chen Jiahao <chenjiahao16(a)huawei.com> hulk inclusion category: bugfix bugzilla: 186460, https://gitee.com/src-openeuler/kernel/issues/I53MHA CVE: CVE-2022-23960 -------------------------------- When introducing a new cpucaps macro ARM64_SPECTRE_BHB, ARM64_NCAPS was not able to modified easily due to KABI consistency. Here introduce a workaround to properly setup ARM64_SPECTRE_BHB beyond ARM64_NCAPS range. Fixes: def2df575d30 ("KVM: arm64: Add templates for BHB mitigation sequences") Signed-off-by: Chen Jiahao <chenjiahao16(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/arm64/include/asm/cpufeature.h | 15 +++++++++++++++ arch/arm64/kernel/alternative.c | 5 +++++ arch/arm64/kernel/cpufeature.c | 3 +++ 3 files changed, 23 insertions(+) diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index bfb699957880..ffb0a1ec0088 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -368,6 +368,8 @@ extern struct static_key_false arm64_const_caps_ready; #define ARM64_NPATCHABLE (ARM64_NCAPS + 1) extern DECLARE_BITMAP(boot_capabilities, ARM64_NPATCHABLE); +extern bool set_cap_spectre_bhb; + bool this_cpu_has_cap(unsigned int cap); static inline bool cpu_have_feature(unsigned int num) @@ -378,15 +380,23 @@ static inline bool cpu_have_feature(unsigned int num) /* System capability check for constant caps */ static __always_inline bool __cpus_have_const_cap(int num) { + if (num == ARM64_SPECTRE_BHB) + return set_cap_spectre_bhb; + if (num >= ARM64_NCAPS) return false; + return static_branch_unlikely(&cpu_hwcap_keys[num]); } static inline bool cpus_have_cap(unsigned int num) { + if (num == ARM64_SPECTRE_BHB) + return set_cap_spectre_bhb; + if (num >= ARM64_NCAPS) return false; + return test_bit(num, cpu_hwcaps); } @@ -400,6 +410,11 @@ static __always_inline bool cpus_have_const_cap(int num) static inline void cpus_set_cap(unsigned int num) { + if (num == ARM64_SPECTRE_BHB) { + set_cap_spectre_bhb = true; + return; + } + if (num >= ARM64_NCAPS) { pr_warn("Attempt to set an illegal CPU capability (%d >= %d)\n", num, ARM64_NCAPS); diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c index 8511fc3b94bb..ce5a26080b46 100644 --- a/arch/arm64/kernel/alternative.c +++ b/arch/arm64/kernel/alternative.c @@ -41,8 +41,13 @@ struct alt_region { struct alt_instr *end; }; +bool set_cap_spectre_bhb; + bool alternative_is_applied(u16 cpufeature) { + if (cpufeature == ARM64_SPECTRE_BHB) + return set_cap_spectre_bhb; + if (WARN_ON(cpufeature >= ARM64_NCAPS)) return false; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index aa9178e9acc6..996d3476f3c8 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1732,6 +1732,9 @@ __enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps, for (; caps->matches; caps++) { unsigned int num = caps->capability; + if (num == ARM64_SPECTRE_BHB) + set_cap_spectre_bhb = true; + if (!(caps->type & scope_mask) || !cpus_have_cap(num)) continue; -- 2.25.1

1 0

[Cancel] openEuler kernel SIG例会&技术分享
by openEuler conference 16 Jun '22

16 Jun '22

Sorry! The Zoom meeting will be held at 2022-06-17 14:00 scheduled by openEuler Kernel SIG has been cancelled.

1 0

[PATCH openEuler-1.0-LTS 1/3] powerpc/32: Fix overread/overwrite of thread_struct via ptrace
by Yongqiang Liu 15 Jun '22

15 Jun '22

From: Michael Ellerman <mpe(a)ellerman.id.au> mainline inclusion from mainline-v5.19-rc2 commit 8e1278444446fc97778a5e5c99bca1ce0bbc5ec9 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I5C43D CVE: CVE-2022-32981 -------------------------------- The ptrace PEEKUSR/POKEUSR (aka PEEKUSER/POKEUSER) API allows a process to read/write registers of another process. To get/set a register, the API takes an index into an imaginary address space called the "USER area", where the registers of the process are laid out in some fashion. The kernel then maps that index to a particular register in its own data structures and gets/sets the value. The API only allows a single machine-word to be read/written at a time. So 4 bytes on 32-bit kernels and 8 bytes on 64-bit kernels. The way floating point registers (FPRs) are addressed is somewhat complicated, because double precision float values are 64-bit even on 32-bit CPUs. That means on 32-bit kernels each FPR occupies two word-sized locations in the USER area. On 64-bit kernels each FPR occupies one word-sized location in the USER area. Internally the kernel stores the FPRs in an array of u64s, or if VSX is enabled, an array of pairs of u64s where one half of each pair stores the FPR. Which half of the pair stores the FPR depends on the kernel's endianness. To handle the different layouts of the FPRs depending on VSX/no-VSX and big/little endian, the TS_FPR() macro was introduced. Unfortunately the TS_FPR() macro does not take into account the fact that the addressing of each FPR differs between 32-bit and 64-bit kernels. It just takes the index into the "USER area" passed from userspace and indexes into the fp_state.fpr array. On 32-bit there are 64 indexes that address FPRs, but only 32 entries in the fp_state.fpr array, meaning the user can read/write 256 bytes past the end of the array. Because the fp_state sits in the middle of the thread_struct there are various fields than can be overwritten, including some pointers. As such it may be exploitable. It has also been observed to cause systems to hang or otherwise misbehave when using gdbserver, and is probably the root cause of this report which could not be easily reproduced: https://lore.kernel.org/linuxppc-dev/dc38afe9-6b78-f3f5-666b-986939e40fc6@k… Rather than trying to make the TS_FPR() macro even more complicated to fix the bug, or add more macros, instead add a special-case for 32-bit kernels. This is more obvious and hopefully avoids a similar bug happening again in future. Note that because 32-bit kernels never have VSX enabled the code doesn't need to consider TS_FPRWIDTH/OFFSET at all. Add a BUILD_BUG_ON() to ensure that 32-bit && VSX is never enabled. Fixes: 87fec0514f61 ("powerpc: PTRACE_PEEKUSR/PTRACE_POKEUSER of FPR registers in little endian builds") Cc: stable(a)vger.kernel.org # v3.13+ Reported-by: Ariel Miculas <ariel.miculas(a)belden.com> Tested-by: Christophe Leroy <christophe.leroy(a)csgroup.eu> Signed-off-by: Michael Ellerman <mpe(a)ellerman.id.au> Link: https://lore.kernel.org/r/20220609133245.573565-1-mpe@ellerman.id.au Conflicts: arch/powerpc/kernel/ptrace/ptrace-fpu.c arch/powerpc/kernel/ptrace/ptrace.c 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/powerpc/kernel/ptrace.c | 25 +++++++++++++++++-------- 1 file changed, 17 insertions(+), 8 deletions(-) diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index e08b32ccf1d9..d245f0af412a 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -2980,6 +2980,9 @@ long arch_ptrace(struct task_struct *child, long request, void __user *datavp = (void __user *) data; unsigned long __user *datalp = datavp; + // ptrace_get/put_fpr() rely on PPC32 and VSX being incompatible + BUILD_BUG_ON(IS_ENABLED(CONFIG_PPC32) && IS_ENABLED(CONFIG_VSX)); + switch (request) { /* read the word at location addr in the USER area. */ case PTRACE_PEEKUSR: { @@ -3006,10 +3009,13 @@ long arch_ptrace(struct task_struct *child, long request, unsigned int fpidx = index - PT_FPR0; flush_fp_to_thread(child); - if (fpidx < (PT_FPSCR - PT_FPR0)) - memcpy(&tmp, &child->thread.TS_FPR(fpidx), - sizeof(long)); - else + if (fpidx < (PT_FPSCR - PT_FPR0)) { + if (IS_ENABLED(CONFIG_PPC32)) + // On 32-bit the index we are passed refers to 32-bit words + tmp = ((u32 *)child->thread.fp_state.fpr)[fpidx]; + else + memcpy(&tmp, &child->thread.TS_FPR(fpidx), sizeof(long)); + } else tmp = child->thread.fp_state.fpscr; } ret = put_user(tmp, datalp); @@ -3039,10 +3045,13 @@ long arch_ptrace(struct task_struct *child, long request, unsigned int fpidx = index - PT_FPR0; flush_fp_to_thread(child); - if (fpidx < (PT_FPSCR - PT_FPR0)) - memcpy(&child->thread.TS_FPR(fpidx), &data, - sizeof(long)); - else + if (fpidx < (PT_FPSCR - PT_FPR0)) { + if (IS_ENABLED(CONFIG_PPC32)) + // On 32-bit the index we are passed refers to 32-bit words + ((u32 *)child->thread.fp_state.fpr)[fpidx] = data; + else + memcpy(&child->thread.TS_FPR(fpidx), &data, sizeof(long)); + } else child->thread.fp_state.fpscr = data; ret = 0; } -- 2.25.1

1 2

[PATCH openEuler-1.0-LTS] sctp: use call_rcu to free endpoint
by Yongqiang Liu 14 Jun '22

14 Jun '22

From: Xin Long <lucien.xin(a)gmail.com> stable inclusion from stable-v4.19.224 commit af6e6e58f7ebf86b4e7201694b1e4f3a62cbc3ec category: bugfix bugzilla: 186701, https://gitee.com/src-openeuler/kernel/issues/I5CAM2 CVE: CVE-2022-20154 -------------------------------- [ Upstream commit 5ec7d18d1813a5bead0b495045606c93873aecbb ] This patch is to delay the endpoint free by calling call_rcu() to fix another use-after-free issue in sctp_sock_dump(): BUG: KASAN: use-after-free in __lock_acquire+0x36d9/0x4c20 Call Trace: __lock_acquire+0x36d9/0x4c20 kernel/locking/lockdep.c:3218 lock_acquire+0x1ed/0x520 kernel/locking/lockdep.c:3844 __raw_spin_lock_bh include/linux/spinlock_api_smp.h:135 [inline] _raw_spin_lock_bh+0x31/0x40 kernel/locking/spinlock.c:168 spin_lock_bh include/linux/spinlock.h:334 [inline] __lock_sock+0x203/0x350 net/core/sock.c:2253 lock_sock_nested+0xfe/0x120 net/core/sock.c:2774 lock_sock include/net/sock.h:1492 [inline] sctp_sock_dump+0x122/0xb20 net/sctp/diag.c:324 sctp_for_each_transport+0x2b5/0x370 net/sctp/socket.c:5091 sctp_diag_dump+0x3ac/0x660 net/sctp/diag.c:527 __inet_diag_dump+0xa8/0x140 net/ipv4/inet_diag.c:1049 inet_diag_dump+0x9b/0x110 net/ipv4/inet_diag.c:1065 netlink_dump+0x606/0x1080 net/netlink/af_netlink.c:2244 __netlink_dump_start+0x59a/0x7c0 net/netlink/af_netlink.c:2352 netlink_dump_start include/linux/netlink.h:216 [inline] inet_diag_handler_cmd+0x2ce/0x3f0 net/ipv4/inet_diag.c:1170 __sock_diag_cmd net/core/sock_diag.c:232 [inline] sock_diag_rcv_msg+0x31d/0x410 net/core/sock_diag.c:263 netlink_rcv_skb+0x172/0x440 net/netlink/af_netlink.c:2477 sock_diag_rcv+0x2a/0x40 net/core/sock_diag.c:274 This issue occurs when asoc is peeled off and the old sk is freed after getting it by asoc->base.sk and before calling lock_sock(sk). To prevent the sk free, as a holder of the sk, ep should be alive when calling lock_sock(). This patch uses call_rcu() and moves sock_put and ep free into sctp_endpoint_destroy_rcu(), so that it's safe to try to hold the ep under rcu_read_lock in sctp_transport_traverse_process(). If sctp_endpoint_hold() returns true, it means this ep is still alive and we have held it and can continue to dump it; If it returns false, it means this ep is dead and can be freed after rcu_read_unlock, and we should skip it. In sctp_sock_dump(), after locking the sk, if this ep is different from tsp->asoc->ep, it means during this dumping, this asoc was peeled off before calling lock_sock(), and the sk should be skipped; If this ep is the same with tsp->asoc->ep, it means no peeloff happens on this asoc, and due to lock_sock, no peeloff will happen either until release_sock. Note that delaying endpoint free won't delay the port release, as the port release happens in sctp_endpoint_destroy() before calling call_rcu(). Also, freeing endpoint by call_rcu() makes it safe to access the sk by asoc->base.sk in sctp_assocs_seq_show() and sctp_rcv(). Thanks Jones to bring this issue up. v1->v2: - improve the changelog. - add kfree(ep) into sctp_endpoint_destroy_rcu(), as Jakub noticed. Reported-by: syzbot+9276d76e83e3bcde6c99(a)syzkaller.appspotmail.com Reported-by: Lee Jones <lee.jones(a)linaro.org> Fixes: d25adbeb0cdb ("sctp: fix an use-after-free issue in sctp_sock_dump") Signed-off-by: Xin Long <lucien.xin(a)gmail.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Huang Guobin <huangguobin4(a)huawei.com> Reviewed-by: Wei Yongjun <weiyongjun1(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- include/net/sctp/sctp.h | 6 +++--- include/net/sctp/structs.h | 3 ++- net/sctp/diag.c | 12 ++++++------ net/sctp/endpointola.c | 23 +++++++++++++++-------- net/sctp/socket.c | 23 +++++++++++++++-------- 5 files changed, 41 insertions(+), 26 deletions(-) diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index fef8c3372aee..6d201c6700be 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -118,6 +118,7 @@ extern struct percpu_counter sctp_sockets_allocated; int sctp_asconf_mgmt(struct sctp_sock *, struct sctp_sockaddr_entry *); struct sk_buff *sctp_skb_recv_datagram(struct sock *, int, int, int *); +typedef int (*sctp_callback_t)(struct sctp_endpoint *, struct sctp_transport *, void *); void sctp_transport_walk_start(struct rhashtable_iter *iter); void sctp_transport_walk_stop(struct rhashtable_iter *iter); struct sctp_transport *sctp_transport_get_next(struct net *net, @@ -128,9 +129,8 @@ int sctp_transport_lookup_process(int (*cb)(struct sctp_transport *, void *), struct net *net, const union sctp_addr *laddr, const union sctp_addr *paddr, void *p); -int sctp_for_each_transport(int (*cb)(struct sctp_transport *, void *), - int (*cb_done)(struct sctp_transport *, void *), - struct net *net, int *pos, void *p); +int sctp_transport_traverse_process(sctp_callback_t cb, sctp_callback_t cb_done, + struct net *net, int *pos, void *p); int sctp_for_each_endpoint(int (*cb)(struct sctp_endpoint *, void *), void *p); int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc, struct sctp_info *info); diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 2882bc7a5b4b..18f9924aa250 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1348,6 +1348,7 @@ struct sctp_endpoint { u32 secid; u32 peer_secid; + struct rcu_head rcu; }; /* Recover the outter endpoint structure. */ @@ -1363,7 +1364,7 @@ static inline struct sctp_endpoint *sctp_ep(struct sctp_ep_common *base) struct sctp_endpoint *sctp_endpoint_new(struct sock *, gfp_t); void sctp_endpoint_free(struct sctp_endpoint *); void sctp_endpoint_put(struct sctp_endpoint *); -void sctp_endpoint_hold(struct sctp_endpoint *); +int sctp_endpoint_hold(struct sctp_endpoint *ep); void sctp_endpoint_add_asoc(struct sctp_endpoint *, struct sctp_association *); struct sctp_association *sctp_endpoint_lookup_assoc( const struct sctp_endpoint *ep, diff --git a/net/sctp/diag.c b/net/sctp/diag.c index 8767405de9fa..0a9db0a7f423 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -307,9 +307,8 @@ static int sctp_tsp_dump_one(struct sctp_transport *tsp, void *p) return err; } -static int sctp_sock_dump(struct sctp_transport *tsp, void *p) +static int sctp_sock_dump(struct sctp_endpoint *ep, struct sctp_transport *tsp, void *p) { - struct sctp_endpoint *ep = tsp->asoc->ep; struct sctp_comm_param *commp = p; struct sock *sk = ep->base.sk; struct sk_buff *skb = commp->skb; @@ -319,6 +318,8 @@ static int sctp_sock_dump(struct sctp_transport *tsp, void *p) int err = 0; lock_sock(sk); + if (ep != tsp->asoc->ep) + goto release; list_for_each_entry(assoc, &ep->asocs, asocs) { if (cb->args[4] < cb->args[1]) goto next; @@ -361,9 +362,8 @@ static int sctp_sock_dump(struct sctp_transport *tsp, void *p) return err; } -static int sctp_sock_filter(struct sctp_transport *tsp, void *p) +static int sctp_sock_filter(struct sctp_endpoint *ep, struct sctp_transport *tsp, void *p) { - struct sctp_endpoint *ep = tsp->asoc->ep; struct sctp_comm_param *commp = p; struct sock *sk = ep->base.sk; const struct inet_diag_req_v2 *r = commp->r; @@ -521,8 +521,8 @@ static void sctp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, if (!(idiag_states & ~(TCPF_LISTEN | TCPF_CLOSE))) goto done; - sctp_for_each_transport(sctp_sock_filter, sctp_sock_dump, - net, &pos, &commp); + sctp_transport_traverse_process(sctp_sock_filter, sctp_sock_dump, + net, &pos, &commp); cb->args[2] = pos; done: diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 8640dedcf64f..c4068451b9c7 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -242,6 +242,18 @@ void sctp_endpoint_free(struct sctp_endpoint *ep) } /* Final destructor for endpoint. */ +static void sctp_endpoint_destroy_rcu(struct rcu_head *head) +{ + struct sctp_endpoint *ep = container_of(head, struct sctp_endpoint, rcu); + struct sock *sk = ep->base.sk; + + sctp_sk(sk)->ep = NULL; + sock_put(sk); + + kfree(ep); + SCTP_DBG_OBJCNT_DEC(ep); +} + static void sctp_endpoint_destroy(struct sctp_endpoint *ep) { struct sock *sk; @@ -275,18 +287,13 @@ static void sctp_endpoint_destroy(struct sctp_endpoint *ep) if (sctp_sk(sk)->bind_hash) sctp_put_port(sk); - sctp_sk(sk)->ep = NULL; - /* Give up our hold on the sock */ - sock_put(sk); - - kfree(ep); - SCTP_DBG_OBJCNT_DEC(ep); + call_rcu(&ep->rcu, sctp_endpoint_destroy_rcu); } /* Hold a reference to an endpoint. */ -void sctp_endpoint_hold(struct sctp_endpoint *ep) +int sctp_endpoint_hold(struct sctp_endpoint *ep) { - refcount_inc(&ep->base.refcnt); + return refcount_inc_not_zero(&ep->base.refcnt); } /* Release a reference to an endpoint and clean up if there are diff --git a/net/sctp/socket.c b/net/sctp/socket.c index cfa54e56add9..0e979a273dcd 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -5059,11 +5059,12 @@ int sctp_transport_lookup_process(int (*cb)(struct sctp_transport *, void *), } EXPORT_SYMBOL_GPL(sctp_transport_lookup_process); -int sctp_for_each_transport(int (*cb)(struct sctp_transport *, void *), - int (*cb_done)(struct sctp_transport *, void *), - struct net *net, int *pos, void *p) { +int sctp_transport_traverse_process(sctp_callback_t cb, sctp_callback_t cb_done, + struct net *net, int *pos, void *p) +{ struct rhashtable_iter hti; struct sctp_transport *tsp; + struct sctp_endpoint *ep; int ret; again: @@ -5072,26 +5073,32 @@ int sctp_for_each_transport(int (*cb)(struct sctp_transport *, void *), tsp = sctp_transport_get_idx(net, &hti, *pos + 1); for (; !IS_ERR_OR_NULL(tsp); tsp = sctp_transport_get_next(net, &hti)) { - ret = cb(tsp, p); - if (ret) - break; + ep = tsp->asoc->ep; + if (sctp_endpoint_hold(ep)) { /* asoc can be peeled off */ + ret = cb(ep, tsp, p); + if (ret) + break; + sctp_endpoint_put(ep); + } (*pos)++; sctp_transport_put(tsp); } sctp_transport_walk_stop(&hti); if (ret) { - if (cb_done && !cb_done(tsp, p)) { + if (cb_done && !cb_done(ep, tsp, p)) { (*pos)++; + sctp_endpoint_put(ep); sctp_transport_put(tsp); goto again; } + sctp_endpoint_put(ep); sctp_transport_put(tsp); } return ret; } -EXPORT_SYMBOL_GPL(sctp_for_each_transport); +EXPORT_SYMBOL_GPL(sctp_transport_traverse_process); /* 7.2.1 Association Status (SCTP_STATUS) -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] ext4: convert from atomic_t to refcount_t on ext4_io_end->count
by Yongqiang Liu 14 Jun '22

14 Jun '22

From: Xiyu Yang <xiyuyang19(a)fudan.edu.cn> hulk inclusion category: bugfix bugzilla: 186971, https://gitee.com/openeuler/kernel/issues/I5C8IW CVE: NA -------------------------------- refcount_t type and corresponding API can protect refcounters from accidental underflow and overflow and further use-after-free situations. Signed-off-by: Xiyu Yang <xiyuyang19(a)fudan.edu.cn> Signed-off-by: Xin Tan <tanxin.ctf(a)gmail.com> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/1626674355-55795-1-git-send-email-xiyuyang19@fuda… Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Signed-off-by: Li Nan <linan122(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- fs/ext4/ext4.h | 3 ++- fs/ext4/page-io.c | 8 ++++---- 2 files changed, 6 insertions(+), 5 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 16e2b719d47c..6efc710b07bf 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -17,6 +17,7 @@ #ifndef _EXT4_H #define _EXT4_H +#include <linux/refcount.h> #include <linux/types.h> #include <linux/blkdev.h> #include <linux/magic.h> @@ -231,7 +232,7 @@ typedef struct ext4_io_end { struct bio *bio; /* Linked list of completed * bios covering the extent */ unsigned int flag; /* unwritten or not */ - atomic_t count; /* reference counter */ + refcount_t count; /* reference counter */ loff_t offset; /* offset in the file */ ssize_t size; /* size of the extent */ } ext4_io_end_t; diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 3de933354a08..decae80aeb98 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -256,14 +256,14 @@ ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags) if (io) { io->inode = inode; INIT_LIST_HEAD(&io->list); - atomic_set(&io->count, 1); + refcount_set(&io->count, 1); } return io; } void ext4_put_io_end_defer(ext4_io_end_t *io_end) { - if (atomic_dec_and_test(&io_end->count)) { + if (refcount_dec_and_test(&io_end->count)) { if (!(io_end->flag & EXT4_IO_END_UNWRITTEN) || !io_end->size) { ext4_release_io_end(io_end); return; @@ -276,7 +276,7 @@ int ext4_put_io_end(ext4_io_end_t *io_end) { int err = 0; - if (atomic_dec_and_test(&io_end->count)) { + if (refcount_dec_and_test(&io_end->count)) { if (io_end->flag & EXT4_IO_END_UNWRITTEN) { err = ext4_convert_unwritten_extents(io_end->handle, io_end->inode, io_end->offset, @@ -291,7 +291,7 @@ int ext4_put_io_end(ext4_io_end_t *io_end) ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end) { - atomic_inc(&io_end->count); + refcount_inc(&io_end->count); return io_end; } -- 2.25.1

1 0

[PATCH openEuler-5.10 01/49] io_uring: always use original task when preparing req identity
by Zheng Zengkai 14 Jun '22

14 Jun '22

From: Jens Axboe <axboe(a)kernel.dk> stable inclusion from stable-v5.10.116 commit 29f077d070519a88a793fbc70f1e6484dc6d9e35 category: bugfix bugzilla: 186865,https://gitee.com/src-openeuler/kernel/issues/I593SI CVE: CVE-2022-1786 -------------------------------- If the ring is setup with IORING_SETUP_IOPOLL and we have more than one task doing submissions on a ring, we can up in a situation where we assign the context from the current task rather than the request originator. Always use req->task rather than assume it's the same as current. No upstream patch exists for this issue, as only older kernels with the non-native workers have this problem. Reported-by: Kyle Zeng <zengyhkyle(a)gmail.com> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Guo Xuenan <guoxuenan(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- fs/io_uring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 2ed0da75000e..cadd491edc6f 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1156,7 +1156,7 @@ static inline void __io_req_init_async(struct io_kiocb *req) */ static inline void io_req_init_async(struct io_kiocb *req) { - struct io_uring_task *tctx = current->io_uring; + struct io_uring_task *tctx = req->task->io_uring; if (req->flags & REQ_F_WORK_INITIALIZED) return; -- 2.20.1

1 48

[openEuler-5.10 00/19] Backport 5.10.107 LTS
by Zheng Zengkai 14 Jun '22

14 Jun '22

Backport 5.10.107 LTS patches from upstream kselftest/vm: fix tests build with old libc sfc: extend the locking on mcdi->seqno tcp: make tcp_read_sock() more robust nl80211: Update bss channel on channel switch for P2P_CLIENT drm/vrr: Set VRR capable prop only if it is attached to connector iwlwifi: don't advertise TWT support atm: firestream: check the return value of ioremap() in fs_init() can: rcar_canfd: rcar_canfd_channel_probe(): register the CAN device when fully ready ARM: 9178/1: fix unmet dependency on BITREVERSE for HAVE_ARCH_BITREVERSE MIPS: smp: fill in sibling and core maps earlier mac80211: refuse aggregations sessions before authorized ARM: dts: rockchip: fix a typo on rk3288 crypto-controller ARM: dts: rockchip: reorder rk322x hmdi clocks arm64: dts: agilex: use the compatible "intel,socfpga-agilex-hsotg" arm64: dts: rockchip: reorder rk3399 hdmi clocks arm64: dts: rockchip: fix rk3399-puma eMMC HS400 signal integrity xfrm: Fix xfrm migrate issues when address family changes xfrm: Check if_id in xfrm_migrate Revert "xfrm: state and policy should fail if XFRMA_IF_ID 0" Already merged(3) arm64: kvm: Fix copy-and-paste error in bhb templates for v5.10 stable io_uring: return back safer resurrect sctp: fix the processing for INIT chunk Total patches: 22 - 3 = 19 Alexander Lobakin (1): MIPS: smp: fill in sibling and core maps earlier Chengming Zhou (1): kselftest/vm: fix tests build with old libc Corentin Labbe (1): ARM: dts: rockchip: fix a typo on rk3288 crypto-controller Dinh Nguyen (1): arm64: dts: agilex: use the compatible "intel,socfpga-agilex-hsotg" Eric Dumazet (1): tcp: make tcp_read_sock() more robust Golan Ben Ami (1): iwlwifi: don't advertise TWT support Jakob Unterwurzacher (1): arm64: dts: rockchip: fix rk3399-puma eMMC HS400 signal integrity Jia-Ju Bai (1): atm: firestream: check the return value of ioremap() in fs_init() Johannes Berg (1): mac80211: refuse aggregations sessions before authorized Julian Braha (1): ARM: 9178/1: fix unmet dependency on BITREVERSE for HAVE_ARCH_BITREVERSE Kai Lueke (1): Revert "xfrm: state and policy should fail if XFRMA_IF_ID 0" Lad Prabhakar (1): can: rcar_canfd: rcar_canfd_channel_probe(): register the CAN device when fully ready Manasi Navare (1): drm/vrr: Set VRR capable prop only if it is attached to connector Niels Dossche (1): sfc: extend the locking on mcdi->seqno Sascha Hauer (2): arm64: dts: rockchip: reorder rk3399 hdmi clocks ARM: dts: rockchip: reorder rk322x hmdi clocks Sreeramya Soratkal (1): nl80211: Update bss channel on channel switch for P2P_CLIENT Yan Yan (2): xfrm: Check if_id in xfrm_migrate xfrm: Fix xfrm migrate issues when address family changes arch/arm/boot/dts/rk322x.dtsi | 4 +-- arch/arm/boot/dts/rk3288.dtsi | 2 +- arch/arm64/boot/dts/intel/socfpga_agilex.dtsi | 4 +-- arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi | 6 +++++ arch/arm64/boot/dts/rockchip/rk3399.dtsi | 6 ++--- arch/mips/kernel/smp.c | 6 ++--- drivers/atm/firestream.c | 2 ++ drivers/gpu/drm/drm_connector.c | 3 +++ drivers/net/can/rcar/rcar_canfd.c | 6 ++--- drivers/net/ethernet/sfc/mcdi.c | 2 +- .../wireless/intel/iwlwifi/iwl-nvm-parse.c | 3 +-- .../net/wireless/intel/iwlwifi/mvm/mac80211.c | 1 - include/net/xfrm.h | 5 ++-- lib/Kconfig | 1 - net/ipv4/tcp.c | 10 ++++--- net/key/af_key.c | 2 +- net/mac80211/agg-tx.c | 10 ++++++- net/wireless/nl80211.c | 3 ++- net/xfrm/xfrm_policy.c | 14 +++++----- net/xfrm/xfrm_state.c | 15 ++++++++--- net/xfrm/xfrm_user.c | 27 ++++++------------- tools/testing/selftests/vm/userfaultfd.c | 1 + 22 files changed, 76 insertions(+), 57 deletions(-) -- 2.20.1

1 19

[PATCH openEuler-1.0-LTS 1/9] HID: add hid_is_usb() function to make it simpler for USB detection
by Yongqiang Liu 14 Jun '22

14 Jun '22

From: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> stable inclusion from linux-4.19.221 commit b1efa723b986a84f84a95b6907cffe3a357338c9 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I5BTIG CVE: CVE-2022-20132 -------------------------------- commit f83baa0cb6cfc92ebaf7f9d3a99d7e34f2e77a8a upstream. A number of HID drivers already call hid_is_using_ll_driver() but only for the detection of if this is a USB device or not. Make this more obvious by creating hid_is_usb() and calling the function that way. Also converts the existing hid_is_using_ll_driver() functions to use the new call. Cc: Jiri Kosina <jikos(a)kernel.org> Cc: Benjamin Tissoires <benjamin.tissoires(a)redhat.com> Cc: linux-input(a)vger.kernel.org Cc: stable(a)vger.kernel.org Tested-by: Benjamin Tissoires <benjamin.tissoires(a)redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Benjamin Tissoires <benjamin.tissoires(a)redhat.com> Link: https://lore.kernel.org/r/20211201183503.2373082-1-gregkh@linuxfoundation.o… Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Rui Xiang <rui.xiang(a)huawei.com> Reviewed-by: Zhang Xiaoxu <zhangxiaoxu5(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/hid/hid-asus.c | 2 +- drivers/hid/wacom_sys.c | 2 +- include/linux/hid.h | 5 +++++ 3 files changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index 88a5672f42cd..800b2364e29e 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -622,7 +622,7 @@ static int asus_probe(struct hid_device *hdev, const struct hid_device_id *id) if (drvdata->quirks & QUIRK_IS_MULTITOUCH) drvdata->tp = &asus_i2c_tp; - if (drvdata->quirks & QUIRK_T100_KEYBOARD) { + if ((drvdata->quirks & QUIRK_T100_KEYBOARD) && hid_is_usb(hdev)) { struct usb_interface *intf = to_usb_interface(hdev->dev.parent); if (intf->altsetting->desc.bInterfaceNumber == T100_TPAD_INTF) { diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index 3038c975e417..101b5ae2c3a7 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -2154,7 +2154,7 @@ static void wacom_update_name(struct wacom *wacom, const char *suffix) if ((features->type == HID_GENERIC) && !strcmp("Wacom HID", features->name)) { char *product_name = wacom->hdev->name; - if (hid_is_using_ll_driver(wacom->hdev, &usb_hid_driver)) { + if (hid_is_usb(wacom->hdev)) { struct usb_interface *intf = to_usb_interface(wacom->hdev->dev.parent); struct usb_device *dev = interface_to_usbdev(intf); product_name = dev->product; diff --git a/include/linux/hid.h b/include/linux/hid.h index bbbe6c0e0e26..7f321909ec58 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -832,6 +832,11 @@ static inline bool hid_is_using_ll_driver(struct hid_device *hdev, return hdev->ll_driver == driver; } +static inline bool hid_is_usb(struct hid_device *hdev) +{ + return hid_is_using_ll_driver(hdev, &usb_hid_driver); +} + #define PM_HINT_FULLON 1<<5 #define PM_HINT_NORMAL 1<<1 -- 2.25.1

1 8

[PATCH openEuler-5.10-LTS 01/42] netfilter: nf_tables: sanitize nft_set_desc_concat_parse()
by Zheng Zengkai 14 Jun '22

14 Jun '22

From: Pablo Neira Ayuso <pablo(a)netfilter.org> stable inclusion from stable-v5.10.120 commit c0aff1faf66b6b7a19103f83e6a5d0fdc64b9048 category: bugfix bugzilla: 186913 https://gitee.com/src-openeuler/kernel/issues/I5B69E CVE: CVE-2022-1972 -------------------------------- commit fecf31ee395b0295f2d7260aa29946b7605f7c85 upstream. Add several sanity checks for nft_set_desc_concat_parse(): - validate desc->field_count not larger than desc->field_len array. - field length cannot be larger than desc->field_len (ie. U8_MAX) - total length of the concatenation cannot be larger than register array. Joint work with Florian Westphal. Fixes: f3a2181e16f1 ("netfilter: nf_tables: Support for sets with multiple ranged fields") Reported-by: <zhangziming.zzm(a)antgroup.com> Reviewed-by: Stefano Brivio <sbrivio(a)redhat.com> Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> Reviewed-by: Wei Yongjun <weiyongjun1(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- net/netfilter/nf_tables_api.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index fdd1da9ecea9..164b686bb4c9 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4047,6 +4047,9 @@ static int nft_set_desc_concat_parse(const struct nlattr *attr, u32 len; int err; + if (desc->field_count >= ARRAY_SIZE(desc->field_len)) + return -E2BIG; + err = nla_parse_nested_deprecated(tb, NFTA_SET_FIELD_MAX, attr, nft_concat_policy, NULL); if (err < 0) @@ -4056,9 +4059,8 @@ static int nft_set_desc_concat_parse(const struct nlattr *attr, return -EINVAL; len = ntohl(nla_get_be32(tb[NFTA_SET_FIELD_LEN])); - - if (len * BITS_PER_BYTE / 32 > NFT_REG32_COUNT) - return -E2BIG; + if (!len || len > U8_MAX) + return -EINVAL; desc->field_len[desc->field_count++] = len; @@ -4069,7 +4071,8 @@ static int nft_set_desc_concat(struct nft_set_desc *desc, const struct nlattr *nla) { struct nlattr *attr; - int rem, err; + u32 num_regs = 0; + int rem, err, i; nla_for_each_nested(attr, nla, rem) { if (nla_type(attr) != NFTA_LIST_ELEM) @@ -4080,6 +4083,12 @@ static int nft_set_desc_concat(struct nft_set_desc *desc, return err; } + for (i = 0; i < desc->field_count; i++) + num_regs += DIV_ROUND_UP(desc->field_len[i], sizeof(u32)); + + if (num_regs > NFT_REG32_COUNT) + return -E2BIG; + return 0; } -- 2.20.1

1 41

[PATCH openEuler-5.10 00/19] Backport 5.10.107 LTS
by Zheng Zengkai 14 Jun '22

14 Jun '22

Backport 5.10.107 LTS patches from upstream kselftest/vm: fix tests build with old libc sfc: extend the locking on mcdi->seqno tcp: make tcp_read_sock() more robust nl80211: Update bss channel on channel switch for P2P_CLIENT drm/vrr: Set VRR capable prop only if it is attached to connector iwlwifi: don't advertise TWT support atm: firestream: check the return value of ioremap() in fs_init() can: rcar_canfd: rcar_canfd_channel_probe(): register the CAN device when fully ready ARM: 9178/1: fix unmet dependency on BITREVERSE for HAVE_ARCH_BITREVERSE MIPS: smp: fill in sibling and core maps earlier mac80211: refuse aggregations sessions before authorized ARM: dts: rockchip: fix a typo on rk3288 crypto-controller ARM: dts: rockchip: reorder rk322x hmdi clocks arm64: dts: agilex: use the compatible "intel,socfpga-agilex-hsotg" arm64: dts: rockchip: reorder rk3399 hdmi clocks arm64: dts: rockchip: fix rk3399-puma eMMC HS400 signal integrity xfrm: Fix xfrm migrate issues when address family changes xfrm: Check if_id in xfrm_migrate Revert "xfrm: state and policy should fail if XFRMA_IF_ID 0" Already merged(3) arm64: kvm: Fix copy-and-paste error in bhb templates for v5.10 stable io_uring: return back safer resurrect sctp: fix the processing for INIT chunk Total patches: 22 - 3 = 19 Alexander Lobakin (1): MIPS: smp: fill in sibling and core maps earlier Chengming Zhou (1): kselftest/vm: fix tests build with old libc Corentin Labbe (1): ARM: dts: rockchip: fix a typo on rk3288 crypto-controller Dinh Nguyen (1): arm64: dts: agilex: use the compatible "intel,socfpga-agilex-hsotg" Eric Dumazet (1): tcp: make tcp_read_sock() more robust Golan Ben Ami (1): iwlwifi: don't advertise TWT support Jakob Unterwurzacher (1): arm64: dts: rockchip: fix rk3399-puma eMMC HS400 signal integrity Jia-Ju Bai (1): atm: firestream: check the return value of ioremap() in fs_init() Johannes Berg (1): mac80211: refuse aggregations sessions before authorized Julian Braha (1): ARM: 9178/1: fix unmet dependency on BITREVERSE for HAVE_ARCH_BITREVERSE Kai Lueke (1): Revert "xfrm: state and policy should fail if XFRMA_IF_ID 0" Lad Prabhakar (1): can: rcar_canfd: rcar_canfd_channel_probe(): register the CAN device when fully ready Manasi Navare (1): drm/vrr: Set VRR capable prop only if it is attached to connector Niels Dossche (1): sfc: extend the locking on mcdi->seqno Sascha Hauer (2): arm64: dts: rockchip: reorder rk3399 hdmi clocks ARM: dts: rockchip: reorder rk322x hmdi clocks Sreeramya Soratkal (1): nl80211: Update bss channel on channel switch for P2P_CLIENT Yan Yan (2): xfrm: Check if_id in xfrm_migrate xfrm: Fix xfrm migrate issues when address family changes arch/arm/boot/dts/rk322x.dtsi | 4 +-- arch/arm/boot/dts/rk3288.dtsi | 2 +- arch/arm64/boot/dts/intel/socfpga_agilex.dtsi | 4 +-- arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi | 6 +++++ arch/arm64/boot/dts/rockchip/rk3399.dtsi | 6 ++--- arch/mips/kernel/smp.c | 6 ++--- drivers/atm/firestream.c | 2 ++ drivers/gpu/drm/drm_connector.c | 3 +++ drivers/net/can/rcar/rcar_canfd.c | 6 ++--- drivers/net/ethernet/sfc/mcdi.c | 2 +- .../wireless/intel/iwlwifi/iwl-nvm-parse.c | 3 +-- .../net/wireless/intel/iwlwifi/mvm/mac80211.c | 1 - include/net/xfrm.h | 5 ++-- lib/Kconfig | 1 - net/ipv4/tcp.c | 10 ++++--- net/key/af_key.c | 2 +- net/mac80211/agg-tx.c | 10 ++++++- net/wireless/nl80211.c | 3 ++- net/xfrm/xfrm_policy.c | 14 +++++----- net/xfrm/xfrm_state.c | 15 ++++++++--- net/xfrm/xfrm_user.c | 27 ++++++------------- tools/testing/selftests/vm/userfaultfd.c | 1 + 22 files changed, 76 insertions(+), 57 deletions(-) -- 2.20.1

1 19

[PATCH openEuler-1.0-LTS] netfilter: nf_tables: disallow non-stateful expression in sets earlier
by Yongqiang Liu 14 Jun '22

14 Jun '22

From: Pablo Neira Ayuso <pablo(a)netfilter.org> mainline inclusion from mainline-v5.19-rc1 commit 520778042ccca019f3ffa136dd0ca565c486cedd category: bugfix bugzilla: 186905, https://gitee.com/src-openeuler/kernel/issues/I5B3QZ CVE: CVE-2022-1966 -------------------------------- Since 3e135cd499bf ("netfilter: nft_dynset: dynamic stateful expression instantiation"), it is possible to attach stateful expressions to set elements. cd5125d8f518 ("netfilter: nf_tables: split set destruction in deactivate and destroy phase") introduces conditional destruction on the object to accomodate transaction semantics. nft_expr_init() calls expr->ops->init() first, then check for NFT_STATEFUL_EXPR, this stills allows to initialize a non-stateful lookup expressions which points to a set, which might lead to UAF since the set is not properly detached from the set->binding for this case. Anyway, this combination is non-sense from nf_tables perspective. This patch fixes this problem by checking for NFT_STATEFUL_EXPR before expr->ops->init() is called. The reporter provides a KASAN splat and a poc reproducer (similar to those autogenerated by syzbot to report use-after-free errors). It is unknown to me if they are using syzbot or if they use similar automated tool to locate the bug that they are reporting. For the record, this is the KASAN splat. [ 85.431824] ================================================================== [ 85.432901] BUG: KASAN: use-after-free in nf_tables_bind_set+0x81b/0xa20 [ 85.433825] Write of size 8 at addr ffff8880286f0e98 by task poc/776 [ 85.434756] [ 85.434999] CPU: 1 PID: 776 Comm: poc Tainted: G W 5.18.0+ #2 [ 85.436023] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014 Fixes: 0b2d8a7b638b ("netfilter: nf_tables: add helper functions for expression handling") Reported-and-tested-by: Aaron Adams <edg-e(a)nccgroup.com> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> conflict: net/netfilter/nf_tables_api.c net/netfilter/nft_dynset.c Signed-off-by: Lu Wei <luwei32(a)huawei.com> Reviewed-by: Wei Yongjun <weiyongjun1(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- net/netfilter/nf_tables_api.c | 16 ++++++++++------ net/netfilter/nft_dynset.c | 3 --- 2 files changed, 10 insertions(+), 9 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 9cc8e92f4b00..ab68076d2cba 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2167,27 +2167,31 @@ struct nft_expr *nft_expr_init(const struct nft_ctx *ctx, err = nf_tables_expr_parse(ctx, nla, &info); if (err < 0) - goto err1; + goto err_expr_parse; + + err = -EOPNOTSUPP; + if (!(info.ops->type->flags & NFT_EXPR_STATEFUL)) + goto err_expr_stateful; err = -ENOMEM; expr = kzalloc(info.ops->size, GFP_KERNEL); if (expr == NULL) - goto err2; + goto err_expr_stateful; err = nf_tables_newexpr(ctx, &info, expr); if (err < 0) - goto err3; + goto err_expr_new; return expr; -err3: +err_expr_new: kfree(expr); -err2: +err_expr_stateful: owner = info.ops->type->owner; if (info.ops->type->release_ops) info.ops->type->release_ops(info.ops); module_put(owner); -err1: +err_expr_parse: return ERR_PTR(err); } diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 4e544044fc2d..cc076d535e14 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -193,9 +193,6 @@ static int nft_dynset_init(const struct nft_ctx *ctx, return PTR_ERR(priv->expr); err = -EOPNOTSUPP; - if (!(priv->expr->ops->type->flags & NFT_EXPR_STATEFUL)) - goto err1; - if (priv->expr->ops->type->flags & NFT_EXPR_GC) { if (set->flags & NFT_SET_TIMEOUT) goto err1; -- 2.25.1

1 0

[PATCH OLK-5.10 v2] eulerfs: fix potential sbi->persisters free error
by gouhao＠uniontech.com 14 Jun '22

14 Jun '22

From: Gou Hao <gouhao(a)uniontech.com> uniontech inclusion category: bugfix bugzilla: NA CVE: NA ------------------- After alloc the sbi->persisters memory, dep_init will call dep_fini when error happened.Because sbi->persisters is not set to 0, -> dep_fini() can be called with sbi->persisters[] uninitialized, thus kthread_stop() can be called with random value. Signed-off-by: Gou Hao <gouhao(a)uniontech.com> --- fs/eulerfs/dep.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/eulerfs/dep.c b/fs/eulerfs/dep.c index ec014bbf3700..a41471c5f2ec 100644 --- a/fs/eulerfs/dep.c +++ b/fs/eulerfs/dep.c @@ -718,7 +718,7 @@ int dep_init(struct super_block *sb) for_each_possible_cpu(cpu) init_llist_head(per_cpu_ptr(sbi->persistee_list, cpu)); - sbi->persisters = kmalloc(sizeof(struct task_struct *) * + sbi->persisters = kzalloc(sizeof(struct task_struct *) * persisters_per_socket * num_sockets, GFP_KERNEL); if (!sbi->persisters) { -- 2.25.1

2 1

[PATCH openEuler-1.0-LTS 1/2] Revert "NFSv4: Handle the special Linux file open access mode"
by Yongqiang Liu 14 Jun '22

14 Jun '22

From: ChenXiaoSong <chenxiaosong2(a)huawei.com> mainline inclusion from mainline-v5.18-rc2 commit ab0fc21bc7105b54bafd85bd8b82742f9e68898a category: bugfix bugzilla: 186890, https://gitee.com/openeuler/kernel/issues/I5BZTX CVE: NA -------------------------------- This reverts commit 44942b4e457beda00981f616402a1a791e8c616e. After secondly opening a file with O_ACCMODE|O_DIRECT flags, nfs4_valid_open_stateid() will dereference NULL nfs4_state when lseek(). Reproducer: 1. mount -t nfs -o vers=4.2 $server_ip:/ /mnt/ 2. fd = open("/mnt/file", O_ACCMODE|O_DIRECT|O_CREAT) 3. close(fd) 4. fd = open("/mnt/file", O_ACCMODE|O_DIRECT) 5. lseek(fd) Reported-by: Lyu Tao <tao.lyu(a)epfl.ch> Signed-off-by: ChenXiaoSong <chenxiaosong2(a)huawei.com> Signed-off-by: Trond Myklebust <trond.myklebust(a)hammerspace.com> Signed-off-by: ChenXiaoSong <chenxiaosong2(a)huawei.com> Reviewed-by: Zhang Xiaoxu <zhangxiaoxu5(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- fs/nfs/inode.c | 1 - fs/nfs/nfs4file.c | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index db52430dfbd7..053e78d777f1 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1103,7 +1103,6 @@ int nfs_open(struct inode *inode, struct file *filp) nfs_fscache_open_file(inode, filp); return 0; } -EXPORT_SYMBOL_GPL(nfs_open); /* * This function is called whenever some part of NFS notices that diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index e053a883d08d..09d65a654c2b 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -49,7 +49,7 @@ nfs4_file_open(struct inode *inode, struct file *filp) return err; if ((openflags & O_ACCMODE) == 3) - return nfs_open(inode, filp); + openflags--; /* We can't create new files here */ openflags &= ~(O_CREAT|O_EXCL); -- 2.25.1

1 1

openEuler kernel SIG例会&技术分享
by openEuler conference 14 Jun '22

14 Jun '22

您好！ Kernel SIG 邀请您参加 2022-06-17 14:00 召开的Zoom会议(自动录制) 会议主题：openEuler kernel SIG例会&技术分享会议内容： openEuler kernel 技术分享：执行实体创建与切换会议链接：https://us06web.zoom.us/j/82875828076?pwd=cWVmcGtITlJlM0RxcXYzcDlXZjVJUT09 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 2022-06-17 14:00, The subject of the conference is openEuler kernel SIG例会&技术分享, Summary: openEuler kernel 技术分享：执行实体创建与切换 You can join the meeting at https://us06web.zoom.us/j/82875828076?pwd=cWVmcGtITlJlM0RxcXYzcDlXZjVJUT09. 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] nvme: Assign subsys instance from first ctrl
by Chen Taotao 09 Jun '22

09 Jun '22

mainline inclusion from mainline-5.3.0-rc3 commit 733e4b69d508d03c20adfdcf4bd27abc60fae9cc category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5986O CVE: NA -------------------------------- The namespace disk names must be unique for the lifetime of the subsystem. This was accomplished by using their parent subsystems' instances which were allocated independently from the controllers connected to that subsystem. This allowed name prefixes assigned to namespaces to match a controller from an unrelated subsystem, and has created confusion among users examining device nodes. Ensure a namespace's subsystem instance never clashes with a controller instance of another subsystem by transferring the instance ownership to the parent subsystem from the first controller discovered in that subsystem. Reviewed-by: Logan Gunthorpe <logang(a)deltatee.com> Signed-off-by: Keith Busch <kbusch(a)kernel.org> Reviewed-by: Christoph Hellwig <hch(a)lst.de> Reviewed-by: Minwoo Im <minwoo.im(a)samsung.com> Reviewed-by: Hannes Reinecke <hare(a)suse.com> Reviewed-off-by: Sagi Grimberg <sagi(a)grimberg.me> Signed-off-by: Sagi Grimberg <sagi(a)grimberg.me> Signed-off-by: Chen Taotao <chentt10(a)chinatelecom.cn> Signed-off-by: Ctyun Kernel <ctyuncommiter01(a)chinatelecom.cn> --- drivers/nvme/host/core.c | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 164ec45da..0b47c8fd8 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -89,7 +89,6 @@ EXPORT_SYMBOL_GPL(nvme_reset_wq); struct workqueue_struct *nvme_delete_wq; EXPORT_SYMBOL_GPL(nvme_delete_wq); -static DEFINE_IDA(nvme_subsystems_ida); static LIST_HEAD(nvme_subsystems); static DEFINE_MUTEX(nvme_subsystems_lock); @@ -2350,7 +2349,8 @@ static void nvme_release_subsystem(struct device *dev) struct nvme_subsystem *subsys = container_of(dev, struct nvme_subsystem, dev); - ida_simple_remove(&nvme_subsystems_ida, subsys->instance); + if (subsys->instance >= 0) + ida_simple_remove(&nvme_instance_ida, subsys->instance); kfree(subsys); } @@ -2461,12 +2461,8 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) subsys = kzalloc(sizeof(*subsys), GFP_KERNEL); if (!subsys) return -ENOMEM; - ret = ida_simple_get(&nvme_subsystems_ida, 0, 0, GFP_KERNEL); - if (ret < 0) { - kfree(subsys); - return ret; - } - subsys->instance = ret; + + subsys->instance = -1; mutex_init(&subsys->lock); kref_init(&subsys->ref); INIT_LIST_HEAD(&subsys->ctrls); @@ -2481,7 +2477,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) subsys->dev.class = nvme_subsys_class; subsys->dev.release = nvme_release_subsystem; subsys->dev.groups = nvme_subsys_attrs_groups; - dev_set_name(&subsys->dev, "nvme-subsys%d", subsys->instance); + dev_set_name(&subsys->dev, "nvme-subsys%d", ctrl->instance); device_initialize(&subsys->dev); mutex_lock(&nvme_subsystems_lock); @@ -2514,6 +2510,8 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) list_add_tail(&subsys->entry, &nvme_subsystems); } + if (!found) + subsys->instance = ctrl->instance; ctrl->subsys = subsys; mutex_unlock(&nvme_subsystems_lock); @@ -3840,7 +3838,9 @@ static void nvme_free_ctrl(struct device *dev) container_of(dev, struct nvme_ctrl, ctrl_device); struct nvme_subsystem *subsys = ctrl->subsys; - ida_simple_remove(&nvme_instance_ida, ctrl->instance); + if (subsys && ctrl->instance != subsys->instance) + ida_simple_remove(&nvme_instance_ida, ctrl->instance); + kfree(ctrl->effects); nvme_mpath_uninit(ctrl); __free_page(ctrl->discard_page); @@ -4102,7 +4102,6 @@ int __init nvme_core_init(void) void nvme_core_exit(void) { - ida_destroy(&nvme_subsystems_ida); class_destroy(nvme_subsys_class); class_destroy(nvme_class); unregister_chrdev_region(nvme_chr_devt, NVME_MINORS); -- 2.27.0

1 0