Merge branch 'next' of https://github.com/awilliam/linux-vfio.git

author: Mark Brown <broonie@kernel.org> 2026-05-29 23:13:31 +0100
committer: Mark Brown <broonie@kernel.org> 2026-05-29 23:13:31 +0100
commit: 291a7683c4fe13d7242adb3022cce917af62e5da (patch)
tree: 6b8797e2b8c264dfc83450eb4e59792a37433df9 /drivers
parent: 9806d07c2f5635f9ae268f1200ee4a1a159b0e17 (diff)
parent: 40ef3edf151e184d021917a5c4c771cc0870844a (diff)
download: linux-next-history-291a7683c4fe13d7242adb3022cce917af62e5da.tar.gz
7 files changed, 50 insertions, 84 deletions
diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
index bb121f635b9f7..86362ec424a50 100644
--- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
+++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
@@ -81,13 +81,10 @@ static int qm_get_vft(struct hisi_qm *qm, u32 *base)
 	u32 qp_num;
 	int ret;
 
-	ret = hisi_qm_mb(qm, QM_MB_CMD_SQC_VFT_V2, 0, 0, 1);
+	ret = hisi_qm_mb_read(qm, &sqc_vft, QM_MB_CMD_SQC_VFT_V2, 0);
 	if (ret)
 		return ret;
 
-	sqc_vft = readl(qm->io_base + QM_MB_CMD_DATA_ADDR_L) |
-		  ((u64)readl(qm->io_base + QM_MB_CMD_DATA_ADDR_H) <<
-		  QM_XQC_ADDR_OFFSET);
 	*base = QM_SQC_VFT_BASE_MASK_V2 & (sqc_vft >> QM_SQC_VFT_BASE_SHIFT_V2);
 	qp_num = (QM_SQC_VFT_NUM_MASK_V2 &
 		  (sqc_vft >> QM_SQC_VFT_NUM_SHIFT_V2)) + 1;
@@ -95,36 +92,6 @@ static int qm_get_vft(struct hisi_qm *qm, u32 *base)
 	return qp_num;
 }
 
-static int qm_get_sqc(struct hisi_qm *qm, u64 *addr)
-{
-	int ret;
-
-	ret = hisi_qm_mb(qm, QM_MB_CMD_SQC_BT, 0, 0, 1);
-	if (ret)
-		return ret;
-
-	*addr = readl(qm->io_base + QM_MB_CMD_DATA_ADDR_L) |
-		  ((u64)readl(qm->io_base + QM_MB_CMD_DATA_ADDR_H) <<
-		  QM_XQC_ADDR_OFFSET);
-
-	return 0;
-}
-
-static int qm_get_cqc(struct hisi_qm *qm, u64 *addr)
-{
-	int ret;
-
-	ret = hisi_qm_mb(qm, QM_MB_CMD_CQC_BT, 0, 0, 1);
-	if (ret)
-		return ret;
-
-	*addr = readl(qm->io_base + QM_MB_CMD_DATA_ADDR_L) |
-		  ((u64)readl(qm->io_base + QM_MB_CMD_DATA_ADDR_H) <<
-		  QM_XQC_ADDR_OFFSET);
-
-	return 0;
-}
-
 static void qm_xqc_reg_offsets(struct hisi_qm *qm,
 			       u32 *eqc_addr, u32 *aeqc_addr)
 {
@@ -575,13 +542,13 @@ static int vf_qm_read_data(struct hisi_qm *vf_qm, struct acc_vf_data *vf_data)
 	vf_data->aeqe_dma |= vf_data->qm_aeqc_dw[QM_XQC_ADDR_LOW];
 
 	/* Through SQC_BT/CQC_BT to get sqc and cqc address */
-	ret = qm_get_sqc(vf_qm, &vf_data->sqc_dma);
+	ret = hisi_qm_mb_read(vf_qm, &vf_data->sqc_dma, QM_MB_CMD_SQC_BT, 0);
 	if (ret) {
 		dev_err(dev, "failed to read SQC addr!\n");
 		return ret;
 	}
 
-	ret = qm_get_cqc(vf_qm, &vf_data->cqc_dma);
+	ret = hisi_qm_mb_read(vf_qm, &vf_data->cqc_dma, QM_MB_CMD_CQC_BT, 0);
 	if (ret) {
 		dev_err(dev, "failed to read CQC addr!\n");
 		return ret;
diff --git a/drivers/vfio/pci/nvgrace-gpu/main.c b/drivers/vfio/pci/nvgrace-gpu/main.c
index fa056b69f899a..15e2f03c6cd44 100644
--- a/drivers/vfio/pci/nvgrace-gpu/main.c
+++ b/drivers/vfio/pci/nvgrace-gpu/main.c
@@ -61,6 +61,7 @@ struct nvgrace_gpu_pci_core_device {
 	struct mem_region resmem;
 	/* Lock to control device memory kernel mapping */
 	struct mutex remap_lock;
+	void __iomem *bar0_base;
 	bool has_mig_hw_bug;
 	/* GPU has just been reset */
 	bool reset_done;
@@ -171,6 +172,7 @@ static int nvgrace_gpu_open_device(struct vfio_device *core_vdev)
 	struct nvgrace_gpu_pci_core_device *nvdev =
 		container_of(core_vdev, struct nvgrace_gpu_pci_core_device,
 			     core_device.vdev);
+	void __iomem *io;
 	int ret;
 
 	ret = vfio_pci_core_enable(vdev);
@@ -184,14 +186,14 @@ static int nvgrace_gpu_open_device(struct vfio_device *core_vdev)
 
 	/*
 	 * GPU readiness is checked by reading the BAR0 registers.
-	 *
-	 * ioremap BAR0 to ensure that the BAR0 mapping is present before
-	 * register reads on first fault before establishing any GPU
-	 * memory mapping.
+	 * The BAR map was just set up by vfio_pci_core_enable(), so
+	 * bail early if that wasn't successful:
 	 */
-	ret = vfio_pci_core_setup_barmap(vdev, 0);
-	if (ret)
+	io = vfio_pci_core_get_iomap(vdev, 0);
+	if (IS_ERR(io)) {
+		ret = PTR_ERR(io);
 		goto error_exit;
+	}
 
 	if (nvdev->resmem.memlength) {
 		ret = nvgrace_gpu_vfio_pci_register_pfn_range(core_vdev, &nvdev->resmem);
@@ -204,6 +206,8 @@ static int nvgrace_gpu_open_device(struct vfio_device *core_vdev)
 		goto register_mem_failed;
 
 	vfio_pci_core_finish_enable(vdev);
+	nvdev->bar0_base = io;
+
 	return 0;
 
 register_mem_failed:
@@ -220,6 +224,8 @@ static void nvgrace_gpu_close_device(struct vfio_device *core_vdev)
 		container_of(core_vdev, struct nvgrace_gpu_pci_core_device,
 			     core_device.vdev);
 
+	nvdev->bar0_base = NULL;
+
 	if (nvdev->resmem.memlength)
 		unregister_pfn_address_space(&nvdev->resmem.pfn_address_space);
 
@@ -275,7 +281,7 @@ nvgrace_gpu_check_device_ready(struct nvgrace_gpu_pci_core_device *nvdev)
 	if (!__vfio_pci_memory_enabled(vdev))
 		return -EIO;
 
-	ret = nvgrace_gpu_wait_device_ready(vdev->barmap[0]);
+	ret = nvgrace_gpu_wait_device_ready(nvdev->bar0_base);
 	if (ret)
 		return ret;
 
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 050e7542952ed..a28f1e99362c1 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -271,8 +271,11 @@ int vfio_pci_set_power_state(struct vfio_pci_core_device *vdev, pci_power_t stat
 	int ret;
 
 	/* Prevent changing power state for PFs with VFs enabled */
-	if (pci_num_vf(pdev) && state > PCI_D0)
-		return -EBUSY;
+	if (state > PCI_D0) {
+		lockdep_assert_held_write(&vdev->memory_lock);
+		if (vdev->sriov_active)
+			return -EBUSY;
+	}
 
 	if (vdev->needs_pm_restore) {
 		if (pdev->current_state < PCI_D3hot && state >= PCI_D3hot) {
@@ -1762,7 +1765,7 @@ int vfio_pci_core_mmap(struct vfio_device *core_vdev, struct vm_area_struct *vma
 	struct pci_dev *pdev = vdev->pdev;
 	unsigned int index;
 	u64 phys_len, req_len, pgoff, req_start;
-	int ret;
+	void __iomem *bar_io;
 
 	index = vma->vm_pgoff >> (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT);
 
@@ -1796,12 +1799,11 @@ int vfio_pci_core_mmap(struct vfio_device *core_vdev, struct vm_area_struct *vma
 		return -EINVAL;
 
 	/*
-	 * Even though we don't make use of the barmap for the mmap,
-	 * we need to request the region and the barmap tracks that.
+	 * Ensure the BAR resource region is reserved for use.
 	 */
-	ret = vfio_pci_core_setup_barmap(vdev, index);
-	if (ret)
-		return ret;
+	bar_io = vfio_pci_core_get_iomap(vdev, index);
+	if (IS_ERR(bar_io))
+		return PTR_ERR(bar_io);
 
 	vma->vm_private_data = vdev;
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
@@ -2327,8 +2329,9 @@ int vfio_pci_core_sriov_configure(struct vfio_pci_core_device *vdev,
 
 		down_write(&vdev->memory_lock);
 		vfio_pci_set_power_state(vdev, PCI_D0);
-		ret = pci_enable_sriov(pdev, nr_virtfn);
+		vdev->sriov_active = true;
 		up_write(&vdev->memory_lock);
+		ret = pci_enable_sriov(pdev, nr_virtfn);
 		if (ret) {
 			pm_runtime_put(&pdev->dev);
 			goto out_del;
@@ -2342,6 +2345,13 @@ int vfio_pci_core_sriov_configure(struct vfio_pci_core_device *vdev,
 	}
 
 out_del:
+	/*
+	 * Avoid taking the memory_lock intentionally. A race with a power
+	 * state transition would at most result in an -EBUSY, leaving the
+	 * device in PCI_D0.
+	 */
+	vdev->sriov_active = false;
+
 	mutex_lock(&vfio_pci_sriov_pfs_mutex);
 	list_del_init(&vdev->sriov_pfs_item);
 out_unlock:
diff --git a/drivers/vfio/pci/vfio_pci_dmabuf.c b/drivers/vfio/pci/vfio_pci_dmabuf.c
index 1a177ce7de546..c16f460c01d68 100644
--- a/drivers/vfio/pci/vfio_pci_dmabuf.c
+++ b/drivers/vfio/pci/vfio_pci_dmabuf.c
@@ -248,7 +248,7 @@ int vfio_pci_core_feature_dma_buf(struct vfio_pci_core_device *vdev, u32 flags,
 	 * else.  Check that PCI resources have been claimed for it.
 	 */
 	if (get_dma_buf.region_index >= VFIO_PCI_ROM_REGION_INDEX ||
-	    vfio_pci_core_setup_barmap(vdev, get_dma_buf.region_index))
+	    IS_ERR(vfio_pci_core_get_iomap(vdev, get_dma_buf.region_index)))
 		return -ENODEV;
 
 	dma_ranges = memdup_array_user(&arg->dma_ranges, get_dma_buf.nr_ranges,
diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c
index 3bfbb879a0051..7f14dd46de17a 100644
--- a/drivers/vfio/pci/vfio_pci_rdwr.c
+++ b/drivers/vfio/pci/vfio_pci_rdwr.c
@@ -198,19 +198,6 @@ ssize_t vfio_pci_core_do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem,
 }
 EXPORT_SYMBOL_GPL(vfio_pci_core_do_io_rw);
 
-/*
- * The barmap is set up in vfio_pci_core_enable().  Callers use this
- * function to check that the BAR resources are requested or that the
- * pci_iomap() was done.
- */
-int vfio_pci_core_setup_barmap(struct vfio_pci_core_device *vdev, int bar)
-{
-	if (IS_ERR(vdev->barmap[bar]))
-		return PTR_ERR(vdev->barmap[bar]);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(vfio_pci_core_setup_barmap);
-
 ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf,
 			size_t count, loff_t *ppos, bool iswrite)
 {
@@ -262,13 +249,11 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf,
 		 */
 		max_width = VFIO_PCI_IO_WIDTH_4;
 	} else {
-		int ret = vfio_pci_core_setup_barmap(vdev, bar);
-		if (ret) {
-			done = ret;
+		io = vfio_pci_core_get_iomap(vdev, bar);
+		if (IS_ERR(io)) {
+			done = PTR_ERR(io);
 			goto out;
 		}
-
-		io = vdev->barmap[bar];
 	}
 
 	if (bar == vdev->msix_bar) {
@@ -423,6 +408,7 @@ int vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset,
 	loff_t pos = offset & VFIO_PCI_OFFSET_MASK;
 	int ret, bar = VFIO_PCI_OFFSET_TO_INDEX(offset);
 	struct vfio_pci_ioeventfd *ioeventfd;
+	void __iomem *io;
 
 	/* Only support ioeventfds into BARs */
 	if (bar > VFIO_PCI_BAR5_REGION_INDEX)
@@ -440,9 +426,9 @@ int vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset,
 	if (count == 8)
 		return -EINVAL;
 
-	ret = vfio_pci_core_setup_barmap(vdev, bar);
-	if (ret)
-		return ret;
+	io = vfio_pci_core_get_iomap(vdev, bar);
+	if (IS_ERR(io))
+		return PTR_ERR(io);
 
 	mutex_lock(&vdev->ioeventfds_lock);
 
@@ -479,7 +465,7 @@ int vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset,
 	}
 
 	ioeventfd->vdev = vdev;
-	ioeventfd->addr = vdev->barmap[bar] + pos;
+	ioeventfd->addr = io + pos;
 	ioeventfd->data = data;
 	ioeventfd->pos = pos;
 	ioeventfd->bar = bar;
diff --git a/drivers/vfio/pci/virtio/legacy_io.c b/drivers/vfio/pci/virtio/legacy_io.c
index f022301e60d6e..74ff302edc9f0 100644
--- a/drivers/vfio/pci/virtio/legacy_io.c
+++ b/drivers/vfio/pci/virtio/legacy_io.c
@@ -298,19 +298,18 @@ int virtiovf_pci_ioctl_get_region_info(struct vfio_device *core_vdev,
 static int virtiovf_set_notify_addr(struct virtiovf_pci_core_device *virtvdev)
 {
 	struct vfio_pci_core_device *core_device = &virtvdev->core_device;
-	int ret;
+	void __iomem *io;
 
 	/*
 	 * Setup the BAR where the 'notify' exists to be used by vfio as well
 	 * This will let us mmap it only once and use it when needed.
 	 */
-	ret = vfio_pci_core_setup_barmap(core_device,
-					 virtvdev->notify_bar);
-	if (ret)
-		return ret;
+	io = vfio_pci_core_get_iomap(core_device,
+				     virtvdev->notify_bar);
+	if (IS_ERR(io))
+		return PTR_ERR(io);
 
-	virtvdev->notify_addr = core_device->barmap[virtvdev->notify_bar] +
-			virtvdev->notify_offset;
+	virtvdev->notify_addr = io + virtvdev->notify_offset;
 	return 0;
 }
 
diff --git a/drivers/vfio/pci/xe/main.c b/drivers/vfio/pci/xe/main.c
index 4ecadbbfd86ec..cbff5af385ef5 100644
--- a/drivers/vfio/pci/xe/main.c
+++ b/drivers/vfio/pci/xe/main.c
@@ -135,8 +135,6 @@ static void xe_vfio_pci_reset_done(struct pci_dev *pdev)
 	}
 	spin_unlock(&xe_vdev->reset_lock);
 	xe_vfio_pci_state_mutex_unlock(xe_vdev);
-
-	xe_vfio_pci_reset(xe_vdev);
 }
 
 static const struct pci_error_handlers xe_vfio_pci_err_handlers = {
author	Mark Brown <broonie@kernel.org>	2026-05-29 23:13:31 +0100
committer	Mark Brown <broonie@kernel.org>	2026-05-29 23:13:31 +0100
commit	291a7683c4fe13d7242adb3022cce917af62e5da (patch)
tree	6b8797e2b8c264dfc83450eb4e59792a37433df9 /drivers
parent	9806d07c2f5635f9ae268f1200ee4a1a159b0e17 (diff)
parent	40ef3edf151e184d021917a5c4c771cc0870844a (diff)
download	linux-next-history-291a7683c4fe13d7242adb3022cce917af62e5da.tar.gz