From: Manish Honap <mhonap@nvidia.com>
Check media readiness at probe time and create a CXL memdev for region
management.
Media/range-active check is performed at probe time to keep the
vfio-is-advertised-as-cxl behavior consistent. A pre-committed HDM
decoder already implies media is active, so set media_ready directly
instead of calling the potentially blocking cxl_await_range_active().
For memdev creation we need to determine capacity before calling
devm_cxl_add_memdev(). Read the committed decoder size directly from
HDM decoder hardware registers; the CXL core will see the same values
when it enumerates decoders inside add_memdev.
For firmware uncommitted decoders, handling will be added in a later
commit.
Signed-off-by: Manish Honap <mhonap@nvidia.com>
---
drivers/vfio/pci/cxl/vfio_cxl_core.c | 67 +++++++++++++++++++++++++++-
drivers/vfio/pci/cxl/vfio_cxl_emu.c | 48 ++++++++++++++++++++
drivers/vfio/pci/cxl/vfio_cxl_priv.h | 2 +
3 files changed, 115 insertions(+), 2 deletions(-)
diff --git a/drivers/vfio/pci/cxl/vfio_cxl_core.c b/drivers/vfio/pci/cxl/vfio_cxl_core.c
index d2401871489d..15b6c0d75d9e 100644
--- a/drivers/vfio/pci/cxl/vfio_cxl_core.c
+++ b/drivers/vfio/pci/cxl/vfio_cxl_core.c
@@ -132,6 +132,37 @@ static int vfio_cxl_setup_regs(struct vfio_pci_core_device *vdev)
return 0;
}
+static int vfio_cxl_create_memdev(struct vfio_pci_core_device *vdev,
+ resource_size_t capacity)
+{
+ struct vfio_pci_cxl_state *cxl = vdev->cxl;
+ struct pci_dev *pdev = vdev->pdev;
+ int ret;
+
+ ret = cxl_set_capacity(&cxl->cxlds, capacity);
+ if (ret) {
+ pci_err(pdev, "Failed to set capacity: %d\n", ret);
+ return ret;
+ }
+
+ pci_dbg(pdev, "Device capacity: %llu MB (from %s)\n",
+ capacity >> 20,
+ cxl->precommitted ? "committed decoder" : "sysfs");
+ pci_dbg(pdev,
+ "vfio_cxl: creating memdev: capacity=0x%llx bytes (%llu MiB)\n",
+ (unsigned long long)capacity,
+ (unsigned long long)(capacity >> 20));
+
+ cxl->cxlmd = devm_cxl_add_memdev(&cxl->cxlds, NULL);
+ if (IS_ERR(cxl->cxlmd)) {
+ pci_err(pdev, "Failed to add CXL memdev: %ld\n",
+ PTR_ERR(cxl->cxlmd));
+ return PTR_ERR(cxl->cxlmd);
+ }
+
+ return 0;
+}
+
int vfio_cxl_create_cxl_region(struct vfio_pci_core_device *vdev, resource_size_t size)
{
struct vfio_pci_cxl_state *cxl = vdev->cxl;
@@ -250,6 +281,7 @@ void vfio_pci_cxl_detect_and_init(struct vfio_pci_core_device *vdev)
{
struct pci_dev *pdev = vdev->pdev;
struct vfio_pci_cxl_state *cxl;
+ resource_size_t capacity = 0;
u16 dvsec;
int ret;
@@ -282,13 +314,44 @@ void vfio_pci_cxl_detect_and_init(struct vfio_pci_core_device *vdev)
goto failed;
}
+ cxl->cxlds.media_ready = !cxl_await_range_active(&cxl->cxlds);
+ if (!cxl->cxlds.media_ready) {
+ pci_disable_device(pdev);
+ pci_err(pdev, "CXL media not ready\n");
+ goto regs_failed;
+ }
+
+ /*
+ * Take the single authoritative HDM decoder snapshot now that
+ * MEM_ACTIVE is confirmed and BAR memory is still enabled. Using
+ * readl() per-dword ensures correct MMIO serialisation and captures
+ * the final firmware-written values for all fields including SIZE_HIGH,
+ * which firmware commits to the BAR at MEM_ACTIVE time.
+ */
+ vfio_cxl_reinit_comp_regs(vdev);
+
pci_disable_device(pdev);
- ret = vfio_cxl_create_region_helper(vdev, SZ_256M);
- if (ret)
+ capacity = vfio_cxl_read_committed_decoder_size(vdev);
+ if (capacity == 0) {
+ /*
+ * TODO: Add handling for devices which do not have
+ * firmware pre-committed decoders
+ */
+ pci_info(pdev, "Uncommitted region size must be configured via sysfs before bind\n");
goto regs_failed;
+ }
cxl->precommitted = true;
+ cxl->dpa_size = capacity;
+
+ ret = vfio_cxl_create_memdev(vdev, capacity);
+ if (ret)
+ goto regs_failed;
+
+ ret = vfio_cxl_create_region_helper(vdev, capacity);
+ if (ret)
+ goto regs_failed;
return;
diff --git a/drivers/vfio/pci/cxl/vfio_cxl_emu.c b/drivers/vfio/pci/cxl/vfio_cxl_emu.c
index d5603c80fe51..178a42267642 100644
--- a/drivers/vfio/pci/cxl/vfio_cxl_emu.c
+++ b/drivers/vfio/pci/cxl/vfio_cxl_emu.c
@@ -300,6 +300,54 @@ int vfio_cxl_setup_virt_regs(struct vfio_pci_core_device *vdev)
return 0;
}
+/*
+ * vfio_cxl_read_committed_decoder_size - Extract committed DPA capacity from
+ * comp_reg_virt[].
+ *
+ * Called from probe context after vfio_cxl_reinit_comp_regs() has taken the
+ * post-MEM_ACTIVE readl() snapshot and patched SIZE_HIGH/SIZE_LOW from DVSEC.
+ * comp_reg_virt[] is already correct at this point; no hardware access needed.
+ *
+ * Returns the committed DPA capacity in bytes, or 0 if the decoder is not
+ * committed.
+ */
+resource_size_t
+vfio_cxl_read_committed_decoder_size(struct vfio_pci_core_device *vdev)
+{
+ struct vfio_pci_cxl_state *cxl = vdev->cxl;
+ struct pci_dev *pdev = vdev->pdev;
+ resource_size_t capacity;
+ u32 ctrl, sz_hi, sz_lo;
+
+ if (WARN_ON(!cxl || !cxl->comp_reg_virt))
+ return 0;
+
+ ctrl = le32_to_cpu(cxl->comp_reg_virt[CXL_HDM_DECODER0_CTRL_OFFSET(0) /
+ CXL_REG_SIZE_DWORD]);
+ sz_hi = le32_to_cpu(cxl->comp_reg_virt[CXL_HDM_DECODER0_SIZE_HIGH_OFFSET(0) /
+ CXL_REG_SIZE_DWORD]);
+ sz_lo = le32_to_cpu(cxl->comp_reg_virt[CXL_HDM_DECODER0_SIZE_LOW_OFFSET(0) /
+ CXL_REG_SIZE_DWORD]);
+
+ if (!(ctrl & CXL_HDM_DECODER0_CTRL_COMMITTED)) {
+ pci_dbg(pdev,
+ "vfio_cxl: decoder0 not committed: ctrl=0x%08x\n",
+ ctrl);
+ return 0;
+ }
+
+ capacity = ((resource_size_t)sz_hi << 32) | (sz_lo & GENMASK(31, 28));
+
+ pci_dbg(pdev,
+ "vfio_cxl: decoder0 committed: sz_hi=0x%08x sz_lo=0x%08x "
+ "capacity=0x%llx (%llu MiB)\n",
+ sz_hi, sz_lo,
+ (unsigned long long)capacity,
+ (unsigned long long)(capacity >> 20));
+
+ return capacity;
+}
+
/*
* Called with memory_lock write side held (from vfio_cxl_reactivate_region).
* Uses the pre-established hdm_iobase, no ioremap() under the lock,
diff --git a/drivers/vfio/pci/cxl/vfio_cxl_priv.h b/drivers/vfio/pci/cxl/vfio_cxl_priv.h
index 4f2637874e9d..3ef8d923a7e8 100644
--- a/drivers/vfio/pci/cxl/vfio_cxl_priv.h
+++ b/drivers/vfio/pci/cxl/vfio_cxl_priv.h
@@ -26,6 +26,7 @@ struct vfio_pci_cxl_state {
resource_size_t comp_reg_offset;
size_t comp_reg_size;
__le32 *comp_reg_virt;
+ size_t dpa_size;
void __iomem *hdm_iobase;
u32 hdm_count;
int dpa_region_idx;
@@ -81,5 +82,6 @@ struct vfio_pci_cxl_state {
int vfio_cxl_setup_virt_regs(struct vfio_pci_core_device *vdev);
void vfio_cxl_clean_virt_regs(struct vfio_pci_core_device *vdev);
void vfio_cxl_reinit_comp_regs(struct vfio_pci_core_device *vdev);
+resource_size_t vfio_cxl_read_committed_decoder_size(struct vfio_pci_core_device *vdev);
#endif /* __LINUX_VFIO_CXL_PRIV_H */
--
2.25.1