PCI: Suspend iommu function prior to resetting a device

PCIe permits a device to ignore ATS invalidation TLPs while processing a
reset. This creates a problem visible to the OS where an ATS invalidation
command will time out: e.g. an SVA domain will have no coordination with a
reset event and can racily issue ATS invalidations to a resetting device.

The PCIe r6.0, sec 10.3.1 IMPLEMENTATION NOTE recommends SW to disable and
block ATS before initiating a Function Level Reset. It also mentions that
other reset methods could have the same vulnerability as well.

The IOMMU subsystem provides pci_dev_reset_iommu_prepare/done() callback
helpers for this matter. Use them in all the existing reset functions.

This will attach the device to its iommu_group->blocking_domain during the
device reset, so as to allow IOMMU driver to:
 - invoke pci_disable_ats() and pci_enable_ats(), if necessary
 - wait for all ATS invalidations to complete
 - stop issuing new ATS invalidations
 - fence any incoming ATS queries

Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Tested-by: Dheeraj Kumar Srivastava <dheerajkumar.srivastava@amd.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>

3 files changed, 87 insertions, 10 deletions

diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index 9369377725fa..651d9b5561ff 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -9,6 +9,7 @@
 
 #include <linux/delay.h>
 #include <linux/init.h>
+#include <linux/iommu.h>
 #include <linux/irqdomain.h>
 #include <linux/pci.h>
 #include <linux/msi.h>
@@ -971,6 +972,7 @@ void pci_set_acpi_fwnode(struct pci_dev *dev)
 int pci_dev_acpi_reset(struct pci_dev *dev, bool probe)
 {
 	acpi_handle handle = ACPI_HANDLE(&dev->dev);
+	int ret;
 
 	if (!handle || !acpi_has_method(handle, "_RST"))
 		return -ENOTTY;
@@ -978,12 +980,19 @@ int pci_dev_acpi_reset(struct pci_dev *dev, bool probe)
 	if (probe)
 		return 0;
 
+	ret = pci_dev_reset_iommu_prepare(dev);
+	if (ret) {
+		pci_err(dev, "failed to stop IOMMU for a PCI reset: %d\n", ret);
+		return ret;
+	}
+
 	if (ACPI_FAILURE(acpi_evaluate_object(handle, "_RST", NULL, NULL))) {
 		pci_warn(dev, "ACPI _RST failed\n");
-		return -ENOTTY;
+		ret = -ENOTTY;
 	}
 
-	return 0;
+	pci_dev_reset_iommu_done(dev);
+	return ret;
 }
 
 bool acpi_pci_power_manageable(struct pci_dev *dev)
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 13dbb405dc31..a0ba42ae7ee0 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -13,6 +13,7 @@
 #include <linux/delay.h>
 #include <linux/dmi.h>
 #include <linux/init.h>
+#include <linux/iommu.h>
 #include <linux/msi.h>
 #include <linux/of.h>
 #include <linux/pci.h>
@@ -25,6 +26,7 @@
 #include <linux/logic_pio.h>
 #include <linux/device.h>
 #include <linux/pm_runtime.h>
+#include <linux/pci-ats.h>
 #include <linux/pci_hotplug.h>
 #include <linux/vmalloc.h>
 #include <asm/dma.h>
@@ -4330,13 +4332,22 @@ EXPORT_SYMBOL(pci_wait_for_pending_transaction);
  */
 int pcie_flr(struct pci_dev *dev)
 {
+	int ret;
+
 	if (!pci_wait_for_pending_transaction(dev))
 		pci_err(dev, "timed out waiting for pending transaction; performing function level reset anyway\n");
 
+	/* Have to call it after waiting for pending DMA transaction */
+	ret = pci_dev_reset_iommu_prepare(dev);
+	if (ret) {
+		pci_err(dev, "failed to stop IOMMU for a PCI reset: %d\n", ret);
+		return ret;
+	}
+
 	pcie_capability_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_BCR_FLR);
 
 	if (dev->imm_ready)
-		return 0;
+		goto done;
 
 	/*
 	 * Per PCIe r4.0, sec 6.6.2, a device must complete an FLR within
@@ -4345,7 +4356,10 @@ int pcie_flr(struct pci_dev *dev)
 	 */
 	msleep(100);
 
-	return pci_dev_wait(dev, "FLR", PCIE_RESET_READY_POLL_MS);
+	ret = pci_dev_wait(dev, "FLR", PCIE_RESET_READY_POLL_MS);
+done:
+	pci_dev_reset_iommu_done(dev);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(pcie_flr);
 
@@ -4373,6 +4387,7 @@ EXPORT_SYMBOL_GPL(pcie_reset_flr);
 
 static int pci_af_flr(struct pci_dev *dev, bool probe)
 {
+	int ret;
 	int pos;
 	u8 cap;
 
@@ -4399,10 +4414,17 @@ static int pci_af_flr(struct pci_dev *dev, bool probe)
 				 PCI_AF_STATUS_TP << 8))
 		pci_err(dev, "timed out waiting for pending transaction; performing AF function level reset anyway\n");
 
+	/* Have to call it after waiting for pending DMA transaction */
+	ret = pci_dev_reset_iommu_prepare(dev);
+	if (ret) {
+		pci_err(dev, "failed to stop IOMMU for a PCI reset: %d\n", ret);
+		return ret;
+	}
+
 	pci_write_config_byte(dev, pos + PCI_AF_CTRL, PCI_AF_CTRL_FLR);
 
 	if (dev->imm_ready)
-		return 0;
+		goto done;
 
 	/*
 	 * Per Advanced Capabilities for Conventional PCI ECN, 13 April 2006,
@@ -4412,7 +4434,10 @@ static int pci_af_flr(struct pci_dev *dev, bool probe)
 	 */
 	msleep(100);
 
-	return pci_dev_wait(dev, "AF_FLR", PCIE_RESET_READY_POLL_MS);
+	ret = pci_dev_wait(dev, "AF_FLR", PCIE_RESET_READY_POLL_MS);
+done:
+	pci_dev_reset_iommu_done(dev);
+	return ret;
 }
 
 /**
@@ -4433,6 +4458,7 @@ static int pci_af_flr(struct pci_dev *dev, bool probe)
 static int pci_pm_reset(struct pci_dev *dev, bool probe)
 {
 	u16 csr;
+	int ret;
 
 	if (!dev->pm_cap || dev->dev_flags & PCI_DEV_FLAGS_NO_PM_RESET)
 		return -ENOTTY;
@@ -4447,6 +4473,12 @@ static int pci_pm_reset(struct pci_dev *dev, bool probe)
 	if (dev->current_state != PCI_D0)
 		return -EINVAL;
 
+	ret = pci_dev_reset_iommu_prepare(dev);
+	if (ret) {
+		pci_err(dev, "failed to stop IOMMU for a PCI reset: %d\n", ret);
+		return ret;
+	}
+
 	csr &= ~PCI_PM_CTRL_STATE_MASK;
 	csr |= PCI_D3hot;
 	pci_write_config_word(dev, dev->pm_cap + PCI_PM_CTRL, csr);
@@ -4457,7 +4489,9 @@ static int pci_pm_reset(struct pci_dev *dev, bool probe)
 	pci_write_config_word(dev, dev->pm_cap + PCI_PM_CTRL, csr);
 	pci_dev_d3_sleep(dev);
 
-	return pci_dev_wait(dev, "PM D3hot->D0", PCIE_RESET_READY_POLL_MS);
+	ret = pci_dev_wait(dev, "PM D3hot->D0", PCIE_RESET_READY_POLL_MS);
+	pci_dev_reset_iommu_done(dev);
+	return ret;
 }
 
 /**
@@ -4885,10 +4919,20 @@ static int pci_reset_bus_function(struct pci_dev *dev, bool probe)
 		return -ENOTTY;
 	}
 
+	rc = pci_dev_reset_iommu_prepare(dev);
+	if (rc) {
+		pci_err(dev, "failed to stop IOMMU for a PCI reset: %d\n", rc);
+		return rc;
+	}
+
 	rc = pci_dev_reset_slot_function(dev, probe);
 	if (rc != -ENOTTY)
-		return rc;
-	return pci_parent_bus_reset(dev, probe);
+		goto done;
+
+	rc = pci_parent_bus_reset(dev, probe);
+done:
+	pci_dev_reset_iommu_done(dev);
+	return rc;
 }
 
 static int cxl_reset_bus_function(struct pci_dev *dev, bool probe)
@@ -4912,6 +4956,12 @@ static int cxl_reset_bus_function(struct pci_dev *dev, bool probe)
 	if (rc)
 		return -ENOTTY;
 
+	rc = pci_dev_reset_iommu_prepare(dev);
+	if (rc) {
+		pci_err(dev, "failed to stop IOMMU for a PCI reset: %d\n", rc);
+		return rc;
+	}
+
 	if (reg & PCI_DVSEC_CXL_PORT_CTL_UNMASK_SBR) {
 		val = reg;
 	} else {
@@ -4926,6 +4976,7 @@ static int cxl_reset_bus_function(struct pci_dev *dev, bool probe)
 		pci_write_config_word(bridge, dvsec + PCI_DVSEC_CXL_PORT_CTL,
 				      reg);
 
+	pci_dev_reset_iommu_done(dev);
 	return rc;
 }
 
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index b9c252aa6fe0..c6b999045c70 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -21,6 +21,7 @@
 #include <linux/pci.h>
 #include <linux/isa-dma.h> /* isa_dma_bridge_buggy */
 #include <linux/init.h>
+#include <linux/iommu.h>
 #include <linux/delay.h>
 #include <linux/acpi.h>
 #include <linux/dmi.h>
@@ -4228,6 +4229,22 @@ static const struct pci_dev_reset_methods pci_dev_reset_methods[] = {
 	{ 0 }
 };
 
+static int __pci_dev_specific_reset(struct pci_dev *dev, bool probe,
+				    const struct pci_dev_reset_methods *i)
+{
+	int ret;
+
+	ret = pci_dev_reset_iommu_prepare(dev);
+	if (ret) {
+		pci_err(dev, "failed to stop IOMMU for a PCI reset: %d\n", ret);
+		return ret;
+	}
+
+	ret = i->reset(dev, probe);
+	pci_dev_reset_iommu_done(dev);
+	return ret;
+}
+
 /*
  * These device-specific reset methods are here rather than in a driver
  * because when a host assigns a device to a guest VM, the host may need
@@ -4242,7 +4259,7 @@ int pci_dev_specific_reset(struct pci_dev *dev, bool probe)
 		     i->vendor == (u16)PCI_ANY_ID) &&
 		    (i->device == dev->device ||
 		     i->device == (u16)PCI_ANY_ID))
-			return i->reset(dev, probe);
+			return __pci_dev_specific_reset(dev, probe, i);
 	}
 
 	return -ENOTTY;