diff --git a/Makefile b/Makefile
index 3712b4deafbe..d503d041b526 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
VERSION = 4
PATCHLEVEL = 14
-SUBLEVEL = 197
+SUBLEVEL = 198
EXTRAVERSION =
NAME = Petit Gorille
diff --git a/block/blk-core.c b/block/blk-core.c
index 4e04c79aa2c2..2407c898ba7d 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -852,6 +852,8 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
q->backing_dev_info->ra_pages =
(VM_MAX_READAHEAD * 1024) / PAGE_SIZE;
+ q->backing_dev_info->io_pages =
+ (VM_MAX_READAHEAD * 1024) / PAGE_SIZE;
q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK;
q->backing_dev_info->name = "block";
q->node = node_id;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 7de38ae5c18f..a03239ba1a32 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6378,14 +6378,14 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
}
}
- bnxt_enable_napi(bp);
-
rc = bnxt_init_nic(bp, irq_re_init);
if (rc) {
netdev_err(bp->dev, "bnxt_init_nic err: %x\n", rc);
- goto open_err;
+ goto open_err_irq;
}
+ bnxt_enable_napi(bp);
+
if (link_re_init) {
mutex_lock(&bp->link_lock);
rc = bnxt_update_phy_setting(bp);
@@ -6410,9 +6410,6 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
bnxt_vf_reps_open(bp);
return 0;
-open_err:
- bnxt_disable_napi(bp);
-
open_err_irq:
bnxt_del_napi(bp);
diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c
index b91f92e4e5f2..915ac75b55fc 100644
--- a/drivers/net/usb/dm9601.c
+++ b/drivers/net/usb/dm9601.c
@@ -625,6 +625,10 @@ static const struct usb_device_id products[] = {
USB_DEVICE(0x0a46, 0x1269), /* DM9621A USB to Fast Ethernet Adapter */
.driver_info = (unsigned long)&dm9601_info,
},
+ {
+ USB_DEVICE(0x0586, 0x3427), /* ZyXEL Keenetic Plus DSL xDSL modem */
+ .driver_info = (unsigned long)&dm9601_info,
+ },
{}, // END
};
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 550ab7707b57..794dc90aa5c9 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -29,6 +29,7 @@
#include <linux/vfio.h>
#include <linux/vgaarb.h>
#include <linux/nospec.h>
+#include <linux/sched/mm.h>
#include "vfio_pci_private.h"
@@ -181,6 +182,7 @@ static void vfio_pci_probe_mmaps(struct vfio_pci_device *vdev)
static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev);
static void vfio_pci_disable(struct vfio_pci_device *vdev);
+static int vfio_pci_try_zap_and_vma_lock_cb(struct pci_dev *pdev, void *data);
/*
* INTx masking requires the ability to disable INTx signaling via PCI_COMMAND
@@ -644,6 +646,12 @@ int vfio_pci_register_dev_region(struct vfio_pci_device *vdev,
return 0;
}
+struct vfio_devices {
+ struct vfio_device **devices;
+ int cur_index;
+ int max_index;
+};
+
static long vfio_pci_ioctl(void *device_data,
unsigned int cmd, unsigned long arg)
{
@@ -717,7 +725,7 @@ static long vfio_pci_ioctl(void *device_data,
{
void __iomem *io;
size_t size;
- u16 orig_cmd;
+ u16 cmd;
info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
info.flags = 0;
@@ -737,10 +745,7 @@ static long vfio_pci_ioctl(void *device_data,
* Is it really there? Enable memory decode for
* implicit access in pci_map_rom().
*/
- pci_read_config_word(pdev, PCI_COMMAND, &orig_cmd);
- pci_write_config_word(pdev, PCI_COMMAND,
- orig_cmd | PCI_COMMAND_MEMORY);
-
+ cmd = vfio_pci_memory_lock_and_enable(vdev);
io = pci_map_rom(pdev, &size);
if (io) {
info.flags = VFIO_REGION_INFO_FLAG_READ;
@@ -748,8 +753,8 @@ static long vfio_pci_ioctl(void *device_data,
} else {
info.size = 0;
}
+ vfio_pci_memory_unlock_and_restore(vdev, cmd);
- pci_write_config_word(pdev, PCI_COMMAND, orig_cmd);
break;
}
case VFIO_PCI_VGA_REGION_INDEX:
@@ -885,8 +890,16 @@ static long vfio_pci_ioctl(void *device_data,
return ret;
} else if (cmd == VFIO_DEVICE_RESET) {
- return vdev->reset_works ?
- pci_try_reset_function(vdev->pdev) : -EINVAL;
+ int ret;
+
+ if (!vdev->reset_works)
+ return -EINVAL;
+
+ vfio_pci_zap_and_down_write_memory_lock(vdev);
+ ret = pci_try_reset_function(vdev->pdev);
+ up_write(&vdev->memory_lock);
+
+ return ret;
} else if (cmd == VFIO_DEVICE_GET_PCI_HOT_RESET_INFO) {
struct vfio_pci_hot_reset_info hdr;
@@ -966,8 +979,9 @@ static long vfio_pci_ioctl(void *device_data,
int32_t *group_fds;
struct vfio_pci_group_entry *groups;
struct vfio_pci_group_info info;
+ struct vfio_devices devs = { .cur_index = 0 };
bool slot = false;
- int i, count = 0, ret = 0;
+ int i, group_idx, mem_idx = 0, count = 0, ret = 0;
minsz = offsetofend(struct vfio_pci_hot_reset, count);
@@ -1019,9 +1033,9 @@ static long vfio_pci_ioctl(void *device_data,
* user interface and store the group and iommu ID. This
* ensures the group is held across the reset.
*/
- for (i = 0; i < hdr.count; i++) {
+ for (group_idx = 0; group_idx < hdr.count; group_idx++) {
struct vfio_group *group;
- struct fd f = fdget(group_fds[i]);
+ struct fd f = fdget(group_fds[group_idx]);
if (!f.file) {
ret = -EBADF;
break;
@@ -1034,8 +1048,9 @@ static long vfio_pci_ioctl(void *device_data,
break;
}
- groups[i].group = group;
- groups[i].id = vfio_external_user_iommu_id(group);
+ groups[group_idx].group = group;
+ groups[group_idx].id =
+ vfio_external_user_iommu_id(group);
}
kfree(group_fds);
@@ -1054,14 +1069,65 @@ static long vfio_pci_ioctl(void *device_data,
ret = vfio_pci_for_each_slot_or_bus(vdev->pdev,
vfio_pci_validate_devs,
&info, slot);
- if (!ret)
- /* User has access, do the reset */
- ret = slot ? pci_try_reset_slot(vdev->pdev->slot) :
- pci_try_reset_bus(vdev->pdev->bus);
+
+ if (ret)
+ goto hot_reset_release;
+
+ devs.max_index = count;
+ devs.devices = kcalloc(count, sizeof(struct vfio_device *),
+ GFP_KERNEL);
+ if (!devs.devices) {
+ ret = -ENOMEM;
+ goto hot_reset_release;
+ }
+
+ /*
+ * We need to get memory_lock for each device, but devices
+ * can share mmap_sem, therefore we need to zap and hold
+ * the vma_lock for each device, and only then get each
+ * memory_lock.
+ */
+ ret = vfio_pci_for_each_slot_or_bus(vdev->pdev,
+ vfio_pci_try_zap_and_vma_lock_cb,
+ &devs, slot);
+ if (ret)
+ goto hot_reset_release;
+
+ for (; mem_idx < devs.cur_index; mem_idx++) {
+ struct vfio_pci_device *tmp;
+
+ tmp = vfio_device_data(devs.devices[mem_idx]);
+
+ ret = down_write_trylock(&tmp->memory_lock);
+ if (!ret) {
+ ret = -EBUSY;
+ goto hot_reset_release;
+ }
+ mutex_unlock(&tmp->vma_lock);
+ }
+
+ /* User has access, do the reset */
+ ret = slot ? pci_try_reset_slot(vdev->pdev->slot) :
+ pci_try_reset_bus(vdev->pdev->bus);
hot_reset_release:
- for (i--; i >= 0; i--)
- vfio_group_put_external_user(groups[i].group);
+ for (i = 0; i < devs.cur_index; i++) {
+ struct vfio_device *device;
+ struct vfio_pci_device *tmp;
+
+ device = devs.devices[i];
+ tmp = vfio_device_data(device);
+
+ if (i < mem_idx)
+ up_write(&tmp->memory_lock);
+ else
+ mutex_unlock(&tmp->vma_lock);
+ vfio_device_put(device);
+ }
+ kfree(devs.devices);
+
+ for (group_idx--; group_idx >= 0; group_idx--)
+ vfio_group_put_external_user(groups[group_idx].group);
kfree(groups);
return ret;
@@ -1120,6 +1186,202 @@ static ssize_t vfio_pci_write(void *device_data, const char __user *buf,
return vfio_pci_rw(device_data, (char __user *)buf, count, ppos, true);
}
+/* Return 1 on zap and vma_lock acquired, 0 on contention (only with @try) */
+static int vfio_pci_zap_and_vma_lock(struct vfio_pci_device *vdev, bool try)
+{
+ struct vfio_pci_mmap_vma *mmap_vma, *tmp;
+
+ /*
+ * Lock ordering:
+ * vma_lock is nested under mmap_sem for vm_ops callback paths.
+ * The memory_lock semaphore is used by both code paths calling
+ * into this function to zap vmas and the vm_ops.fault callback
+ * to protect the memory enable state of the device.
+ *
+ * When zapping vmas we need to maintain the mmap_sem => vma_lock
+ * ordering, which requires using vma_lock to walk vma_list to
+ * acquire an mm, then dropping vma_lock to get the mmap_sem and
+ * reacquiring vma_lock. This logic is derived from similar
+ * requirements in uverbs_user_mmap_disassociate().
+ *
+ * mmap_sem must always be the top-level lock when it is taken.
+ * Therefore we can only hold the memory_lock write lock when
+ * vma_list is empty, as we'd need to take mmap_sem to clear
+ * entries. vma_list can only be guaranteed empty when holding
+ * vma_lock, thus memory_lock is nested under vma_lock.
+ *
+ * This enables the vm_ops.fault callback to acquire vma_lock,
+ * followed by memory_lock read lock, while already holding
+ * mmap_sem without risk of deadlock.
+ */
+ while (1) {
+ struct mm_struct *mm = NULL;
+
+ if (try) {
+ if (!mutex_trylock(&vdev->vma_lock))
+ return 0;
+ } else {
+ mutex_lock(&vdev->vma_lock);
+ }
+ while (!list_empty(&vdev->vma_list)) {
+ mmap_vma = list_first_entry(&vdev->vma_list,
+ struct vfio_pci_mmap_vma,
+ vma_next);
+ mm = mmap_vma->vma->vm_mm;
+ if (mmget_not_zero(mm))
+ break;
+
+ list_del(&mmap_vma->vma_next);
+ kfree(mmap_vma);
+ mm = NULL;
+ }
+ if (!mm)
+ return 1;
+ mutex_unlock(&vdev->vma_lock);
+
+ if (try) {
+ if (!down_read_trylock(&mm->mmap_sem)) {
+ mmput(mm);
+ return 0;
+ }
+ } else {
+ down_read(&mm->mmap_sem);
+ }
+ if (mmget_still_valid(mm)) {
+ if (try) {
+ if (!mutex_trylock(&vdev->vma_lock)) {
+ up_read(&mm->mmap_sem);
+ mmput(mm);
+ return 0;
+ }
+ } else {
+ mutex_lock(&vdev->vma_lock);
+ }
+ list_for_each_entry_safe(mmap_vma, tmp,
+ &vdev->vma_list, vma_next) {
+ struct vm_area_struct *vma = mmap_vma->vma;
+
+ if (vma->vm_mm != mm)
+ continue;
+
+ list_del(&mmap_vma->vma_next);
+ kfree(mmap_vma);
+
+ zap_vma_ptes(vma, vma->vm_start,
+ vma->vm_end - vma->vm_start);
+ }
+ mutex_unlock(&vdev->vma_lock);
+ }
+ up_read(&mm->mmap_sem);
+ mmput(mm);
+ }
+}
+
+void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_device *vdev)
+{
+ vfio_pci_zap_and_vma_lock(vdev, false);
+ down_write(&vdev->memory_lock);
+ mutex_unlock(&vdev->vma_lock);
+}
+
+u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_device *vdev)
+{
+ u16 cmd;
+
+ down_write(&vdev->memory_lock);
+ pci_read_config_word(vdev->pdev, PCI_COMMAND, &cmd);
+ if (!(cmd & PCI_COMMAND_MEMORY))
+ pci_write_config_word(vdev->pdev, PCI_COMMAND,
+ cmd | PCI_COMMAND_MEMORY);
+
+ return cmd;
+}
+
+void vfio_pci_memory_unlock_and_restore(struct vfio_pci_device *vdev, u16 cmd)
+{
+ pci_write_config_word(vdev->pdev, PCI_COMMAND, cmd);
+ up_write(&vdev->memory_lock);
+}
+
+/* Caller holds vma_lock */
+static int __vfio_pci_add_vma(struct vfio_pci_device *vdev,
+ struct vm_area_struct *vma)
+{
+ struct vfio_pci_mmap_vma *mmap_vma;
+
+ mmap_vma = kmalloc(sizeof(*mmap_vma), GFP_KERNEL);
+ if (!mmap_vma)
+ return -ENOMEM;
+
+ mmap_vma->vma = vma;
+ list_add(&mmap_vma->vma_next, &vdev->vma_list);
+
+ return 0;
+}
+
+/*
+ * Zap mmaps on open so that we can fault them in on access and therefore
+ * our vma_list only tracks mappings accessed since last zap.
+ */
+static void vfio_pci_mmap_open(struct vm_area_struct *vma)
+{
+ zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start);
+}
+
+static void vfio_pci_mmap_close(struct vm_area_struct *vma)
+{
+ struct vfio_pci_device *vdev = vma->vm_private_data;
+ struct vfio_pci_mmap_vma *mmap_vma;
+
+ mutex_lock(&vdev->vma_lock);
+ list_for_each_entry(mmap_vma, &vdev->vma_list, vma_next) {
+ if (mmap_vma->vma == vma) {
+ list_del(&mmap_vma->vma_next);
+ kfree(mmap_vma);
+ break;
+ }
+ }
+ mutex_unlock(&vdev->vma_lock);
+}
+
+static int vfio_pci_mmap_fault(struct vm_fault *vmf)
+{
+ struct vm_area_struct *vma = vmf->vma;
+ struct vfio_pci_device *vdev = vma->vm_private_data;
+ int ret = VM_FAULT_NOPAGE;
+
+ mutex_lock(&vdev->vma_lock);
+ down_read(&vdev->memory_lock);
+
+ if (!__vfio_pci_memory_enabled(vdev)) {
+ ret = VM_FAULT_SIGBUS;
+ mutex_unlock(&vdev->vma_lock);
+ goto up_out;
+ }
+
+ if (__vfio_pci_add_vma(vdev, vma)) {
+ ret = VM_FAULT_OOM;
+ mutex_unlock(&vdev->vma_lock);
+ goto up_out;
+ }
+
+ mutex_unlock(&vdev->vma_lock);
+
+ if (remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+ vma->vm_end - vma->vm_start, vma->vm_page_prot))
+ ret = VM_FAULT_SIGBUS;
+
+up_out:
+ up_read(&vdev->memory_lock);
+ return ret;
+}
+
+static const struct vm_operations_struct vfio_pci_mmap_ops = {
+ .open = vfio_pci_mmap_open,
+ .close = vfio_pci_mmap_close,
+ .fault = vfio_pci_mmap_fault,
+};
+
static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
{
struct vfio_pci_device *vdev = device_data;
@@ -1185,8 +1447,14 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
vma->vm_pgoff = (pci_resource_start(pdev, index) >> PAGE_SHIFT) + pgoff;
- return remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
- req_len, vma->vm_page_prot);
+ /*
+ * See remap_pfn_range(), called from vfio_pci_fault() but we can't
+ * change vm_flags within the fault handler. Set them now.
+ */
+ vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP;
+ vma->vm_ops = &vfio_pci_mmap_ops;
+
+ return 0;
}
static void vfio_pci_request(void *device_data, unsigned int count)
@@ -1243,6 +1511,9 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
vdev->irq_type = VFIO_PCI_NUM_IRQS;
mutex_init(&vdev->igate);
spin_lock_init(&vdev->irqlock);
+ mutex_init(&vdev->vma_lock);
+ INIT_LIST_HEAD(&vdev->vma_list);
+ init_rwsem(&vdev->memory_lock);
ret = vfio_add_group_dev(&pdev->dev, &vfio_pci_ops, vdev);
if (ret) {
@@ -1337,12 +1608,6 @@ static struct pci_driver vfio_pci_driver = {
.err_handler = &vfio_err_handlers,
};
-struct vfio_devices {
- struct vfio_device **devices;
- int cur_index;
- int max_index;
-};
-
static int vfio_pci_get_devs(struct pci_dev *pdev, void *data)
{
struct vfio_devices *devs = data;
@@ -1364,6 +1629,39 @@ static int vfio_pci_get_devs(struct pci_dev *pdev, void *data)
return 0;
}
+static int vfio_pci_try_zap_and_vma_lock_cb(struct pci_dev *pdev, void *data)
+{
+ struct vfio_devices *devs = data;
+ struct vfio_device *device;
+ struct vfio_pci_device *vdev;
+
+ if (devs->cur_index == devs->max_index)
+ return -ENOSPC;
+
+ device = vfio_device_get_from_dev(&pdev->dev);
+ if (!device)
+ return -EINVAL;
+
+ if (pci_dev_driver(pdev) != &vfio_pci_driver) {
+ vfio_device_put(device);
+ return -EBUSY;
+ }
+
+ vdev = vfio_device_data(device);
+
+ /*
+ * Locking multiple devices is prone to deadlock, runaway and
+ * unwind if we hit contention.
+ */
+ if (!vfio_pci_zap_and_vma_lock(vdev, true)) {
+ vfio_device_put(device);
+ return -EBUSY;
+ }
+
+ devs->devices[devs->cur_index++] = device;
+ return 0;
+}
+
/*
* Attempt to do a bus/slot reset if there are devices affected by a reset for
* this device that are needs_reset and all of the affected devices are unused
diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index 36bc8f104e42..a1a26465d224 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -398,6 +398,20 @@ static inline void p_setd(struct perm_bits *p, int off, u32 virt, u32 write)
*(__le32 *)(&p->write[off]) = cpu_to_le32(write);
}
+/* Caller should hold memory_lock semaphore */
+bool __vfio_pci_memory_enabled(struct vfio_pci_device *vdev)
+{
+ struct pci_dev *pdev = vdev->pdev;
+ u16 cmd = le16_to_cpu(*(__le16 *)&vdev->vconfig[PCI_COMMAND]);
+
+ /*
+ * SR-IOV VF memory enable is handled by the MSE bit in the
+ * PF SR-IOV capability, there's therefore no need to trigger
+ * faults based on the virtual value.
+ */
+ return pdev->is_virtfn || (cmd & PCI_COMMAND_MEMORY);
+}
+
/*
* Restore the *real* BARs after we detect a FLR or backdoor reset.
* (backdoor = some device specific technique that we didn't catch)
@@ -558,13 +572,18 @@ static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos,
new_cmd = le32_to_cpu(val);
+ phys_io = !!(phys_cmd & PCI_COMMAND_IO);
+ virt_io = !!(le16_to_cpu(*virt_cmd) & PCI_COMMAND_IO);
+ new_io = !!(new_cmd & PCI_COMMAND_IO);
+
phys_mem = !!(phys_cmd & PCI_COMMAND_MEMORY);
virt_mem = !!(le16_to_cpu(*virt_cmd) & PCI_COMMAND_MEMORY);
new_mem = !!(new_cmd & PCI_COMMAND_MEMORY);
- phys_io = !!(phys_cmd & PCI_COMMAND_IO);
- virt_io = !!(le16_to_cpu(*virt_cmd) & PCI_COMMAND_IO);
- new_io = !!(new_cmd & PCI_COMMAND_IO);
+ if (!new_mem)
+ vfio_pci_zap_and_down_write_memory_lock(vdev);
+ else
+ down_write(&vdev->memory_lock);
/*
* If the user is writing mem/io enable (new_mem/io) and we
@@ -581,8 +600,11 @@ static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos,
}
count = vfio_default_config_write(vdev, pos, count, perm, offset, val);
- if (count < 0)
+ if (count < 0) {
+ if (offset == PCI_COMMAND)
+ up_write(&vdev->memory_lock);
return count;
+ }
/*
* Save current memory/io enable bits in vconfig to allow for
@@ -593,6 +615,8 @@ static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos,
*virt_cmd &= cpu_to_le16(~mask);
*virt_cmd |= cpu_to_le16(new_cmd & mask);
+
+ up_write(&vdev->memory_lock);
}
/* Emulate INTx disable */
@@ -830,8 +854,11 @@ static int vfio_exp_config_write(struct vfio_pci_device *vdev, int pos,
pos - offset + PCI_EXP_DEVCAP,
&cap);
- if (!ret && (cap & PCI_EXP_DEVCAP_FLR))
+ if (!ret && (cap & PCI_EXP_DEVCAP_FLR)) {
+ vfio_pci_zap_and_down_write_memory_lock(vdev);
pci_try_reset_function(vdev->pdev);
+ up_write(&vdev->memory_lock);
+ }
}
/*
@@ -909,8 +936,11 @@ static int vfio_af_config_write(struct vfio_pci_device *vdev, int pos,
pos - offset + PCI_AF_CAP,
&cap);
- if (!ret && (cap & PCI_AF_CAP_FLR) && (cap & PCI_AF_CAP_TP))
+ if (!ret && (cap & PCI_AF_CAP_FLR) && (cap & PCI_AF_CAP_TP)) {
+ vfio_pci_zap_and_down_write_memory_lock(vdev);
pci_try_reset_function(vdev->pdev);
+ up_write(&vdev->memory_lock);
+ }
}
return count;
@@ -1708,6 +1738,15 @@ int vfio_config_init(struct vfio_pci_device *vdev)
vconfig[PCI_INTERRUPT_PIN]);
vconfig[PCI_INTERRUPT_PIN] = 0; /* Gratuitous for good VFs */
+
+ /*
+ * VFs do no implement the memory enable bit of the COMMAND
+ * register therefore we'll not have it set in our initial
+ * copy of config space after pci_enable_device(). For
+ * consistency with PFs, set the virtual enable bit here.
+ */
+ *(__le16 *)&vconfig[PCI_COMMAND] |=
+ cpu_to_le16(PCI_COMMAND_MEMORY);
}
if (!IS_ENABLED(CONFIG_VFIO_PCI_INTX) || vdev->nointx)
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index 94594dc63c41..bdfdd506bc58 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -252,6 +252,7 @@ static int vfio_msi_enable(struct vfio_pci_device *vdev, int nvec, bool msix)
struct pci_dev *pdev = vdev->pdev;
unsigned int flag = msix ? PCI_IRQ_MSIX : PCI_IRQ_MSI;
int ret;
+ u16 cmd;
if (!is_irq_none(vdev))
return -EINVAL;
@@ -261,13 +262,16 @@ static int vfio_msi_enable(struct vfio_pci_device *vdev, int nvec, bool msix)
return -ENOMEM;
/* return the number of supported vectors if we can't get all: */
+ cmd = vfio_pci_memory_lock_and_enable(vdev);
ret = pci_alloc_irq_vectors(pdev, 1, nvec, flag);
if (ret < nvec) {
if (ret > 0)
pci_free_irq_vectors(pdev);
+ vfio_pci_memory_unlock_and_restore(vdev, cmd);
kfree(vdev->ctx);
return ret;
}
+ vfio_pci_memory_unlock_and_restore(vdev, cmd);
vdev->num_ctx = nvec;
vdev->irq_type = msix ? VFIO_PCI_MSIX_IRQ_INDEX :
@@ -290,6 +294,7 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,
struct pci_dev *pdev = vdev->pdev;
struct eventfd_ctx *trigger;
int irq, ret;
+ u16 cmd;
if (vector < 0 || vector >= vdev->num_ctx)
return -EINVAL;
@@ -298,7 +303,11 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,
if (vdev->ctx[vector].trigger) {
irq_bypass_unregister_producer(&vdev->ctx[vector].producer);
+
+ cmd = vfio_pci_memory_lock_and_enable(vdev);
free_irq(irq, vdev->ctx[vector].trigger);
+ vfio_pci_memory_unlock_and_restore(vdev, cmd);
+
kfree(vdev->ctx[vector].name);
eventfd_ctx_put(vdev->ctx[vector].trigger);
vdev->ctx[vector].trigger = NULL;
@@ -326,6 +335,7 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,
* such a reset it would be unsuccessful. To avoid this, restore the
* cached value of the message prior to enabling.
*/
+ cmd = vfio_pci_memory_lock_and_enable(vdev);
if (msix) {
struct msi_msg msg;
@@ -335,6 +345,7 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,
ret = request_irq(irq, vfio_msihandler, 0,
vdev->ctx[vector].name, trigger);
+ vfio_pci_memory_unlock_and_restore(vdev, cmd);
if (ret) {
kfree(vdev->ctx[vector].name);
eventfd_ctx_put(trigger);
@@ -379,6 +390,7 @@ static void vfio_msi_disable(struct vfio_pci_device *vdev, bool msix)
{
struct pci_dev *pdev = vdev->pdev;
int i;
+ u16 cmd;
for (i = 0; i < vdev->num_ctx; i++) {
vfio_virqfd_disable(&vdev->ctx[i].unmask);
@@ -387,7 +399,9 @@ static void vfio_msi_disable(struct vfio_pci_device *vdev, bool msix)
vfio_msi_set_block(vdev, 0, vdev->num_ctx, NULL, msix);
+ cmd = vfio_pci_memory_lock_and_enable(vdev);
pci_free_irq_vectors(pdev);
+ vfio_pci_memory_unlock_and_restore(vdev, cmd);
/*
* Both disable paths above use pci_intx_for_msi() to clear DisINTx
diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h
index f561ac1c78a0..f896cebb5c2c 100644
--- a/drivers/vfio/pci/vfio_pci_private.h
+++ b/drivers/vfio/pci/vfio_pci_private.h
@@ -63,6 +63,11 @@ struct vfio_pci_dummy_resource {
struct list_head res_next;
};
+struct vfio_pci_mmap_vma {
+ struct vm_area_struct *vma;
+ struct list_head vma_next;
+};
+
struct vfio_pci_device {
struct pci_dev *pdev;
void __iomem *barmap[PCI_STD_RESOURCE_END + 1];
@@ -95,6 +100,9 @@ struct vfio_pci_device {
struct eventfd_ctx *err_trigger;
struct eventfd_ctx *req_trigger;
struct list_head dummy_resources_list;
+ struct mutex vma_lock;
+ struct list_head vma_list;
+ struct rw_semaphore memory_lock;
};
#define is_intx(vdev) (vdev->irq_type == VFIO_PCI_INTX_IRQ_INDEX)
@@ -130,6 +138,14 @@ extern int vfio_pci_register_dev_region(struct vfio_pci_device *vdev,
unsigned int type, unsigned int subtype,
const struct vfio_pci_regops *ops,
size_t size, u32 flags, void *data);
+
+extern bool __vfio_pci_memory_enabled(struct vfio_pci_device *vdev);
+extern void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_device
+ *vdev);
+extern u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_device *vdev);
+extern void vfio_pci_memory_unlock_and_restore(struct vfio_pci_device *vdev,
+ u16 cmd);
+
#ifdef CONFIG_VFIO_PCI_IGD
extern int vfio_pci_igd_init(struct vfio_pci_device *vdev);
#else
diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c
index 357243d76f10..6445461a5601 100644
--- a/drivers/vfio/pci/vfio_pci_rdwr.c
+++ b/drivers/vfio/pci/vfio_pci_rdwr.c
@@ -122,6 +122,7 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf,
size_t x_start = 0, x_end = 0;
resource_size_t end;
void __iomem *io;
+ struct resource *res = &vdev->pdev->resource[bar];
ssize_t done;
if (pci_resource_start(pdev, bar))
@@ -137,6 +138,14 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf,
count = min(count, (size_t)(end - pos));
+ if (res->flags & IORESOURCE_MEM) {
+ down_read(&vdev->memory_lock);
+ if (!__vfio_pci_memory_enabled(vdev)) {
+ up_read(&vdev->memory_lock);
+ return -EIO;
+ }
+ }
+
if (bar == PCI_ROM_RESOURCE) {
/*
* The ROM can fill less space than the BAR, so we start the
@@ -144,20 +153,21 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf,
* filling large ROM BARs much faster.
*/
io = pci_map_rom(pdev, &x_start);
- if (!io)
- return -ENOMEM;
+ if (!io) {
+ done = -ENOMEM;
+ goto out;
+ }
x_end = end;
} else if (!vdev->barmap[bar]) {
- int ret;
-
- ret = pci_request_selected_regions(pdev, 1 << bar, "vfio");
- if (ret)
- return ret;
+ done = pci_request_selected_regions(pdev, 1 << bar, "vfio");
+ if (done)
+ goto out;
io = pci_iomap(pdev, bar, 0);
if (!io) {
pci_release_selected_regions(pdev, 1 << bar);
- return -ENOMEM;
+ done = -ENOMEM;
+ goto out;
}
vdev->barmap[bar] = io;
@@ -176,6 +186,9 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf,
if (bar == PCI_ROM_RESOURCE)
pci_unmap_rom(pdev, io);
+out:
+ if (res->flags & IORESOURCE_MEM)
+ up_read(&vdev->memory_lock);
return done;
}
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index f22425501bc1..9c8ed9d7f9aa 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -336,6 +336,32 @@ static int put_pfn(unsigned long pfn, int prot)
return 0;
}
+static int follow_fault_pfn(struct vm_area_struct *vma, struct mm_struct *mm,
+ unsigned long vaddr, unsigned long *pfn,
+ bool write_fault)
+{
+ int ret;
+
+ ret = follow_pfn(vma, vaddr, pfn);
+ if (ret) {
+ bool unlocked = false;
+
+ ret = fixup_user_fault(NULL, mm, vaddr,
+ FAULT_FLAG_REMOTE |
+ (write_fault ? FAULT_FLAG_WRITE : 0),
+ &unlocked);
+ if (unlocked)
+ return -EAGAIN;
+
+ if (ret)
+ return ret;
+
+ ret = follow_pfn(vma, vaddr, pfn);
+ }
+
+ return ret;
+}
+
static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
int prot, unsigned long *pfn)
{
@@ -375,12 +401,16 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
down_read(&mm->mmap_sem);
+retry:
vma = find_vma_intersection(mm, vaddr, vaddr + 1);
if (vma && vma->vm_flags & VM_PFNMAP) {
- if (!follow_pfn(vma, vaddr, pfn) &&
- is_invalid_reserved_pfn(*pfn))
- ret = 0;
+ ret = follow_fault_pfn(vma, mm, vaddr, pfn, prot & IOMMU_WRITE);
+ if (ret == -EAGAIN)
+ goto retry;
+
+ if (!ret && !is_invalid_reserved_pfn(*pfn))
+ ret = -EFAULT;
}
up_read(&mm->mmap_sem);
diff --git a/net/core/dev.c b/net/core/dev.c
index 7ec549e481e3..d101f95a47fb 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5532,12 +5532,13 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
pr_err_once("netif_napi_add() called with weight %d on device %s\n",
weight, dev->name);
napi->weight = weight;
- list_add(&napi->dev_list, &dev->napi_list);
napi->dev = dev;
#ifdef CONFIG_NETPOLL
napi->poll_owner = -1;
#endif
set_bit(NAPI_STATE_SCHED, &napi->state);
+ set_bit(NAPI_STATE_NPSVC, &napi->state);
+ list_add_rcu(&napi->dev_list, &dev->napi_list);
napi_hash_add(napi);
}
EXPORT_SYMBOL(netif_napi_add);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index abab3753a9e0..0b247f7cd583 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -179,7 +179,7 @@ static void poll_napi(struct net_device *dev)
struct napi_struct *napi;
int cpu = smp_processor_id();
- list_for_each_entry(napi, &dev->napi_list, dev_list) {
+ list_for_each_entry_rcu(napi, &dev->napi_list, dev_list) {
if (cmpxchg(&napi->poll_owner, -1, cpu) == -1) {
poll_one_napi(napi);
smp_store_release(&napi->poll_owner, -1);
diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c
index 41d0e95d171e..b1a1718495f3 100644
--- a/net/netlabel/netlabel_domainhash.c
+++ b/net/netlabel/netlabel_domainhash.c
@@ -99,6 +99,7 @@ static void netlbl_domhsh_free_entry(struct rcu_head *entry)
kfree(netlbl_domhsh_addr6_entry(iter6));
}
#endif /* IPv6 */
+ kfree(ptr->def.addrsel);
}
kfree(ptr->domain);
kfree(ptr);
@@ -550,6 +551,8 @@ int netlbl_domhsh_add(struct netlbl_dom_map *entry,
goto add_return;
}
#endif /* IPv6 */
+ /* cleanup the new entry since we've moved everything over */
+ netlbl_domhsh_free_entry(&entry->rcu);
} else
ret_val = -EINVAL;
@@ -593,6 +596,12 @@ int netlbl_domhsh_remove_entry(struct netlbl_dom_map *entry,
{
int ret_val = 0;
struct audit_buffer *audit_buf;
+ struct netlbl_af4list *iter4;
+ struct netlbl_domaddr4_map *map4;
+#if IS_ENABLED(CONFIG_IPV6)
+ struct netlbl_af6list *iter6;
+ struct netlbl_domaddr6_map *map6;
+#endif /* IPv6 */
if (entry == NULL)
return -ENOENT;
@@ -610,6 +619,9 @@ int netlbl_domhsh_remove_entry(struct netlbl_dom_map *entry,
ret_val = -ENOENT;
spin_unlock(&netlbl_domhsh_lock);
+ if (ret_val)
+ return ret_val;
+
audit_buf = netlbl_audit_start_common(AUDIT_MAC_MAP_DEL, audit_info);
if (audit_buf != NULL) {
audit_log_format(audit_buf,
@@ -619,40 +631,29 @@ int netlbl_domhsh_remove_entry(struct netlbl_dom_map *entry,
audit_log_end(audit_buf);
}
- if (ret_val == 0) {
- struct netlbl_af4list *iter4;
- struct netlbl_domaddr4_map *map4;
-#if IS_ENABLED(CONFIG_IPV6)
- struct netlbl_af6list *iter6;
- struct netlbl_domaddr6_map *map6;
-#endif /* IPv6 */
-
- switch (entry->def.type) {
- case NETLBL_NLTYPE_ADDRSELECT:
- netlbl_af4list_foreach_rcu(iter4,
- &entry->def.addrsel->list4) {
- map4 = netlbl_domhsh_addr4_entry(iter4);
- cipso_v4_doi_putdef(map4->def.cipso);
- }
+ switch (entry->def.type) {
+ case NETLBL_NLTYPE_ADDRSELECT:
+ netlbl_af4list_foreach_rcu(iter4, &entry->def.addrsel->list4) {
+ map4 = netlbl_domhsh_addr4_entry(iter4);
+ cipso_v4_doi_putdef(map4->def.cipso);
+ }
#if IS_ENABLED(CONFIG_IPV6)
- netlbl_af6list_foreach_rcu(iter6,
- &entry->def.addrsel->list6) {
- map6 = netlbl_domhsh_addr6_entry(iter6);
- calipso_doi_putdef(map6->def.calipso);
- }
+ netlbl_af6list_foreach_rcu(iter6, &entry->def.addrsel->list6) {
+ map6 = netlbl_domhsh_addr6_entry(iter6);
+ calipso_doi_putdef(map6->def.calipso);
+ }
#endif /* IPv6 */
- break;
- case NETLBL_NLTYPE_CIPSOV4:
- cipso_v4_doi_putdef(entry->def.cipso);
- break;
+ break;
+ case NETLBL_NLTYPE_CIPSOV4:
+ cipso_v4_doi_putdef(entry->def.cipso);
+ break;
#if IS_ENABLED(CONFIG_IPV6)
- case NETLBL_NLTYPE_CALIPSO:
- calipso_doi_putdef(entry->def.calipso);
- break;
+ case NETLBL_NLTYPE_CALIPSO:
+ calipso_doi_putdef(entry->def.calipso);
+ break;
#endif /* IPv6 */
- }
- call_rcu(&entry->rcu, netlbl_domhsh_free_entry);
}
+ call_rcu(&entry->rcu, netlbl_domhsh_free_entry);
return ret_val;
}
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 442780515760..1f154276a681 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -7086,8 +7086,6 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
pr_debug("%s: begins, snum:%d\n", __func__, snum);
- local_bh_disable();
-
if (snum == 0) {
/* Search for an available port. */
int low, high, remaining, index;
@@ -7106,20 +7104,21 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
continue;
index = sctp_phashfn(sock_net(sk), rover);
head = &sctp_port_hashtable[index];
- spin_lock(&head->lock);
+ spin_lock_bh(&head->lock);
sctp_for_each_hentry(pp, &head->chain)
if ((pp->port == rover) &&
net_eq(sock_net(sk), pp->net))
goto next;
break;
next:
- spin_unlock(&head->lock);
+ spin_unlock_bh(&head->lock);
+ cond_resched();
} while (--remaining > 0);
/* Exhausted local port range during search? */
ret = 1;
if (remaining <= 0)
- goto fail;
+ return ret;
/* OK, here is the one we will use. HEAD (the port
* hash table list entry) is non-NULL and we hold it's
@@ -7134,7 +7133,7 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
* port iterator, pp being NULL.
*/
head = &sctp_port_hashtable[sctp_phashfn(sock_net(sk), snum)];
- spin_lock(&head->lock);
+ spin_lock_bh(&head->lock);
sctp_for_each_hentry(pp, &head->chain) {
if ((pp->port == snum) && net_eq(pp->net, sock_net(sk)))
goto pp_found;
@@ -7218,10 +7217,7 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
ret = 0;
fail_unlock:
- spin_unlock(&head->lock);
-
-fail:
- local_bh_enable();
+ spin_unlock_bh(&head->lock);
return ret;
}
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index d9ec6335c7dc..cbec2242f79a 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2126,18 +2126,21 @@ static int tipc_shutdown(struct socket *sock, int how)
lock_sock(sk);
__tipc_shutdown(sock, TIPC_CONN_SHUTDOWN);
- sk->sk_shutdown = SEND_SHUTDOWN;
+ if (tipc_sk_type_connectionless(sk))
+ sk->sk_shutdown = SHUTDOWN_MASK;
+ else
+ sk->sk_shutdown = SEND_SHUTDOWN;
if (sk->sk_state == TIPC_DISCONNECTING) {
/* Discard any unreceived messages */
__skb_queue_purge(&sk->sk_receive_queue);
- /* Wake up anyone sleeping in poll */
- sk->sk_state_change(sk);
res = 0;
} else {
res = -ENOTCONN;
}
+ /* Wake up anyone sleeping in poll. */
+ sk->sk_state_change(sk);
release_sock(sk);
return res;
diff --git a/sound/firewire/tascam/tascam.c b/sound/firewire/tascam/tascam.c
index d3fdc463a884..1e61cdce2895 100644
--- a/sound/firewire/tascam/tascam.c
+++ b/sound/firewire/tascam/tascam.c
@@ -225,11 +225,39 @@ static void snd_tscm_remove(struct fw_unit *unit)
}
static const struct ieee1394_device_id snd_tscm_id_table[] = {
+ // Tascam, FW-1884.
{
.match_flags = IEEE1394_MATCH_VENDOR_ID |
- IEEE1394_MATCH_SPECIFIER_ID,
+ IEEE1394_MATCH_SPECIFIER_ID |
+ IEEE1394_MATCH_VERSION,
.vendor_id = 0x00022e,
.specifier_id = 0x00022e,
+ .version = 0x800000,
+ },
+ // Tascam, FE-8 (.version = 0x800001)
+ // This kernel module doesn't support FE-8 because the most of features
+ // can be implemented in userspace without any specific support of this
+ // module.
+ //
+ // .version = 0x800002 is unknown.
+ //
+ // Tascam, FW-1082.
+ {
+ .match_flags = IEEE1394_MATCH_VENDOR_ID |
+ IEEE1394_MATCH_SPECIFIER_ID |
+ IEEE1394_MATCH_VERSION,
+ .vendor_id = 0x00022e,
+ .specifier_id = 0x00022e,
+ .version = 0x800003,
+ },
+ // Tascam, FW-1804.
+ {
+ .match_flags = IEEE1394_MATCH_VENDOR_ID |
+ IEEE1394_MATCH_SPECIFIER_ID |
+ IEEE1394_MATCH_VERSION,
+ .vendor_id = 0x00022e,
+ .specifier_id = 0x00022e,
+ .version = 0x800004,
},
/* FE-08 requires reverse-engineering because it just has faders. */
{}
