8 files changed, 173 insertions, 139 deletions
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 2fbd379923fd..5c3054aaec8c 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -203,6 +203,12 @@ config PCI_P2PDMA
 	  P2P DMA transactions must be between devices behind the same root
 	  port.
 
+	  Enabling this option will reduce the entropy of x86 KASLR memory
+	  regions. For example - on a 46 bit system, the entropy goes down
+	  from 16 bits to 15 bits. The actual reduction in entropy depends
+	  on the physical address bits, on processor features, kernel config
+	  (5 level page table) and physical memory present on the system.
+
 	  If unsure, say N.
 
 config PCI_LABEL
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index 6084b38bdda1..178da6b9fc33 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -1757,8 +1757,7 @@ static int hv_compose_multi_msi_req_get_cpu(void)
 
 	spin_lock_irqsave(&multi_msi_cpu_lock, flags);
 
-	cpu_next = cpumask_next_wrap(cpu_next, cpu_online_mask, nr_cpu_ids,
-				     false);
+	cpu_next = cpumask_next_wrap(cpu_next, cpu_online_mask);
 	cpu = cpu_next;
 
 	spin_unlock_irqrestore(&multi_msi_cpu_lock, flags);
@@ -3976,24 +3975,18 @@ static int hv_pci_restore_msi_msg(struct pci_dev *pdev, void *arg)
 {
 	struct irq_data *irq_data;
 	struct msi_desc *entry;
-	int ret = 0;
 
 	if (!pdev->msi_enabled && !pdev->msix_enabled)
 		return 0;
 
-	msi_lock_descs(&pdev->dev);
+	guard(msi_descs_lock)(&pdev->dev);
 	msi_for_each_desc(entry, &pdev->dev, MSI_DESC_ASSOCIATED) {
 		irq_data = irq_get_irq_data(entry->irq);
-		if (WARN_ON_ONCE(!irq_data)) {
-			ret = -EINVAL;
-			break;
-		}
-
+		if (WARN_ON_ONCE(!irq_data))
+			return -EINVAL;
 		hv_compose_msi_msg(irq_data, &entry->msg);
 	}
-	msi_unlock_descs(&pdev->dev);
-
-	return ret;
+	return 0;
 }
 
 /*
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index 9d9596947350..e619accca49d 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -17,6 +17,8 @@
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
 
+#include <xen/xen.h>
+
 #include <asm/irqdomain.h>
 
 #define VMD_CFGBAR	0
@@ -970,6 +972,24 @@ static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	struct vmd_dev *vmd;
 	int err;
 
+	if (xen_domain()) {
+		/*
+		 * Xen doesn't have knowledge about devices in the VMD bus
+		 * because the config space of devices behind the VMD bridge is
+		 * not known to Xen, and hence Xen cannot discover or configure
+		 * them in any way.
+		 *
+		 * Bypass of MSI remapping won't work in that case as direct
+		 * write by Linux to the MSI entries won't result in functional
+		 * interrupts, as Xen is the entity that manages the host
+		 * interrupt controller and must configure interrupts.  However
+		 * multiplexing of interrupts by the VMD bridge will work under
+		 * Xen, so force the usage of that mode which must always be
+		 * supported by VMD bridges.
+		 */
+		features &= ~VMD_FEAT_CAN_BYPASS_MSI_REMAP;
+	}
+
 	if (resource_size(&dev->resource[VMD_CFGBAR]) < (1 << 20))
 		return -ENOMEM;
 
diff --git a/drivers/pci/msi/api.c b/drivers/pci/msi/api.c
index b956ce591f96..d89f491afdf0 100644
--- a/drivers/pci/msi/api.c
+++ b/drivers/pci/msi/api.c
@@ -53,10 +53,9 @@ void pci_disable_msi(struct pci_dev *dev)
 	if (!pci_msi_enabled() || !dev || !dev->msi_enabled)
 		return;
 
-	msi_lock_descs(&dev->dev);
+	guard(msi_descs_lock)(&dev->dev);
 	pci_msi_shutdown(dev);
 	pci_free_msi_irqs(dev);
-	msi_unlock_descs(&dev->dev);
 }
 EXPORT_SYMBOL(pci_disable_msi);
 
@@ -196,10 +195,9 @@ void pci_disable_msix(struct pci_dev *dev)
 	if (!pci_msi_enabled() || !dev || !dev->msix_enabled)
 		return;
 
-	msi_lock_descs(&dev->dev);
+	guard(msi_descs_lock)(&dev->dev);
 	pci_msix_shutdown(dev);
 	pci_free_msi_irqs(dev);
-	msi_unlock_descs(&dev->dev);
 }
 EXPORT_SYMBOL(pci_disable_msix);
 
diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c
index 2f647cac4cae..d74162880d83 100644
--- a/drivers/pci/msi/msi.c
+++ b/drivers/pci/msi/msi.c
@@ -10,12 +10,12 @@
 #include <linux/err.h>
 #include <linux/export.h>
 #include <linux/irq.h>
+#include <linux/irqdomain.h>
 
 #include "../pci.h"
 #include "msi.h"
 
 int pci_msi_enable = 1;
-int pci_msi_ignore_mask;
 
 /**
  * pci_msi_supported - check whether MSI may be enabled on a device
@@ -285,6 +285,8 @@ static void pci_msi_set_enable(struct pci_dev *dev, int enable)
 static int msi_setup_msi_desc(struct pci_dev *dev, int nvec,
 			      struct irq_affinity_desc *masks)
 {
+	const struct irq_domain *d = dev_get_msi_domain(&dev->dev);
+	const struct msi_domain_info *info = d->host_data;
 	struct msi_desc desc;
 	u16 control;
 
@@ -295,8 +297,7 @@ static int msi_setup_msi_desc(struct pci_dev *dev, int nvec,
 	/* Lies, damned lies, and MSIs */
 	if (dev->dev_flags & PCI_DEV_FLAGS_HAS_MSI_MASKING)
 		control |= PCI_MSI_FLAGS_MASKBIT;
-	/* Respect XEN's mask disabling */
-	if (pci_msi_ignore_mask)
+	if (info->flags & MSI_FLAG_NO_MASK)
 		control &= ~PCI_MSI_FLAGS_MASKBIT;
 
 	desc.nvec_used			= nvec;
@@ -336,41 +337,11 @@ static int msi_verify_entries(struct pci_dev *dev)
 	return !entry ? 0 : -EIO;
 }
 
-/**
- * msi_capability_init - configure device's MSI capability structure
- * @dev: pointer to the pci_dev data structure of MSI device function
- * @nvec: number of interrupts to allocate
- * @affd: description of automatic IRQ affinity assignments (may be %NULL)
- *
- * Setup the MSI capability structure of the device with the requested
- * number of interrupts.  A return value of zero indicates the successful
- * setup of an entry with the new MSI IRQ.  A negative return value indicates
- * an error, and a positive return value indicates the number of interrupts
- * which could have been allocated.
- */
-static int msi_capability_init(struct pci_dev *dev, int nvec,
-			       struct irq_affinity *affd)
+static int __msi_capability_init(struct pci_dev *dev, int nvec, struct irq_affinity_desc *masks)
 {
-	struct irq_affinity_desc *masks = NULL;
+	int ret = msi_setup_msi_desc(dev, nvec, masks);
 	struct msi_desc *entry, desc;
-	int ret;
-
-	/* Reject multi-MSI early on irq domain enabled architectures */
-	if (nvec > 1 && !pci_msi_domain_supports(dev, MSI_FLAG_MULTI_PCI_MSI, ALLOW_LEGACY))
-		return 1;
 
-	/*
-	 * Disable MSI during setup in the hardware, but mark it enabled
-	 * so that setup code can evaluate it.
-	 */
-	pci_msi_set_enable(dev, 0);
-	dev->msi_enabled = 1;
-
-	if (affd)
-		masks = irq_create_affinity_masks(nvec, affd);
-
-	msi_lock_descs(&dev->dev);
-	ret = msi_setup_msi_desc(dev, nvec, masks);
 	if (ret)
 		goto fail;
 
@@ -399,19 +370,48 @@ static int msi_capability_init(struct pci_dev *dev, int nvec,
 
 	pcibios_free_irq(dev);
 	dev->irq = entry->irq;
-	goto unlock;
-
+	return 0;
 err:
 	pci_msi_unmask(&desc, msi_multi_mask(&desc));
 	pci_free_msi_irqs(dev);
 fail:
 	dev->msi_enabled = 0;
-unlock:
-	msi_unlock_descs(&dev->dev);
-	kfree(masks);
 	return ret;
 }
 
+/**
+ * msi_capability_init - configure device's MSI capability structure
+ * @dev: pointer to the pci_dev data structure of MSI device function
+ * @nvec: number of interrupts to allocate
+ * @affd: description of automatic IRQ affinity assignments (may be %NULL)
+ *
+ * Setup the MSI capability structure of the device with the requested
+ * number of interrupts.  A return value of zero indicates the successful
+ * setup of an entry with the new MSI IRQ.  A negative return value indicates
+ * an error, and a positive return value indicates the number of interrupts
+ * which could have been allocated.
+ */
+static int msi_capability_init(struct pci_dev *dev, int nvec,
+			       struct irq_affinity *affd)
+{
+	/* Reject multi-MSI early on irq domain enabled architectures */
+	if (nvec > 1 && !pci_msi_domain_supports(dev, MSI_FLAG_MULTI_PCI_MSI, ALLOW_LEGACY))
+		return 1;
+
+	/*
+	 * Disable MSI during setup in the hardware, but mark it enabled
+	 * so that setup code can evaluate it.
+	 */
+	pci_msi_set_enable(dev, 0);
+	dev->msi_enabled = 1;
+
+	struct irq_affinity_desc *masks __free(kfree) =
+		affd ? irq_create_affinity_masks(nvec, affd) : NULL;
+
+	guard(msi_descs_lock)(&dev->dev);
+	return __msi_capability_init(dev, nvec, masks);
+}
+
 int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec,
 			   struct irq_affinity *affd)
 {
@@ -604,12 +604,15 @@ static void __iomem *msix_map_region(struct pci_dev *dev,
  */
 void msix_prepare_msi_desc(struct pci_dev *dev, struct msi_desc *desc)
 {
+	const struct irq_domain *d = dev_get_msi_domain(&dev->dev);
+	const struct msi_domain_info *info = d->host_data;
+
 	desc->nvec_used				= 1;
 	desc->pci.msi_attrib.is_msix		= 1;
 	desc->pci.msi_attrib.is_64		= 1;
 	desc->pci.msi_attrib.default_irq	= dev->irq;
 	desc->pci.mask_base			= dev->msix_base;
-	desc->pci.msi_attrib.can_mask		= !pci_msi_ignore_mask &&
+	desc->pci.msi_attrib.can_mask		= !(info->flags & MSI_FLAG_NO_MASK) &&
 						  !desc->pci.msi_attrib.is_virtual;
 
 	if (desc->pci.msi_attrib.can_mask) {
@@ -659,47 +662,45 @@ static void msix_mask_all(void __iomem *base, int tsize)
 	u32 ctrl = PCI_MSIX_ENTRY_CTRL_MASKBIT;
 	int i;
 
-	if (pci_msi_ignore_mask)
-		return;
-
 	for (i = 0; i < tsize; i++, base += PCI_MSIX_ENTRY_SIZE)
 		writel(ctrl, base + PCI_MSIX_ENTRY_VECTOR_CTRL);
 }
 
-static int msix_setup_interrupts(struct pci_dev *dev, struct msix_entry *entries,
-				 int nvec, struct irq_affinity *affd)
+static int __msix_setup_interrupts(struct pci_dev *dev, struct msix_entry *entries,
+				   int nvec, struct irq_affinity_desc *masks)
 {
-	struct irq_affinity_desc *masks = NULL;
-	int ret;
-
-	if (affd)
-		masks = irq_create_affinity_masks(nvec, affd);
+	int ret = msix_setup_msi_descs(dev, entries, nvec, masks);
 
-	msi_lock_descs(&dev->dev);
-	ret = msix_setup_msi_descs(dev, entries, nvec, masks);
 	if (ret)
-		goto out_free;
+		goto fail;
 
 	ret = pci_msi_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSIX);
 	if (ret)
-		goto out_free;
+		goto fail;
 
 	/* Check if all MSI entries honor device restrictions */
 	ret = msi_verify_entries(dev);
 	if (ret)
-		goto out_free;
+		goto fail;
 
 	msix_update_entries(dev, entries);
-	goto out_unlock;
+	return 0;
 
-out_free:
+fail:
 	pci_free_msi_irqs(dev);
-out_unlock:
-	msi_unlock_descs(&dev->dev);
-	kfree(masks);
 	return ret;
 }
 
+static int msix_setup_interrupts(struct pci_dev *dev, struct msix_entry *entries,
+				 int nvec, struct irq_affinity *affd)
+{
+	struct irq_affinity_desc *masks __free(kfree) =
+		affd ? irq_create_affinity_masks(nvec, affd) : NULL;
+
+	guard(msi_descs_lock)(&dev->dev);
+	return __msix_setup_interrupts(dev, entries, nvec, masks);
+}
+
 /**
  * msix_capability_init - configure device's MSI-X capability
  * @dev: pointer to the pci_dev data structure of MSI-X device function
@@ -714,6 +715,8 @@ out_unlock:
 static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
 				int nvec, struct irq_affinity *affd)
 {
+	const struct irq_domain *d = dev_get_msi_domain(&dev->dev);
+	const struct msi_domain_info *info = d->host_data;
 	int ret, tsize;
 	u16 control;
 
@@ -744,15 +747,17 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
 	/* Disable INTX */
 	pci_intx_for_msi(dev, 0);
 
-	/*
-	 * Ensure that all table entries are masked to prevent
-	 * stale entries from firing in a crash kernel.
-	 *
-	 * Done late to deal with a broken Marvell NVME device
-	 * which takes the MSI-X mask bits into account even
-	 * when MSI-X is disabled, which prevents MSI delivery.
-	 */
-	msix_mask_all(dev->msix_base, tsize);
+	if (!(info->flags & MSI_FLAG_NO_MASK)) {
+		/*
+		 * Ensure that all table entries are masked to prevent
+		 * stale entries from firing in a crash kernel.
+		 *
+		 * Done late to deal with a broken Marvell NVME device
+		 * which takes the MSI-X mask bits into account even
+		 * when MSI-X is disabled, which prevents MSI delivery.
+		 */
+		msix_mask_all(dev->msix_base, tsize);
+	}
 	pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0);
 
 	pcibios_free_irq(dev);
@@ -871,13 +876,13 @@ void __pci_restore_msix_state(struct pci_dev *dev)
 
 	write_msg = arch_restore_msi_irqs(dev);
 
-	msi_lock_descs(&dev->dev);
-	msi_for_each_desc(entry, &dev->dev, MSI_DESC_ALL) {
-		if (write_msg)
-			__pci_write_msi_msg(entry, &entry->msg);
-		pci_msix_write_vector_ctrl(entry, entry->pci.msix_ctrl);
+	scoped_guard (msi_descs_lock, &dev->dev) {
+		msi_for_each_desc(entry, &dev->dev, MSI_DESC_ALL) {
+			if (write_msg)
+				__pci_write_msi_msg(entry, &entry->msg);
+			pci_msix_write_vector_ctrl(entry, entry->pci.msix_ctrl);
+		}
 	}
-	msi_unlock_descs(&dev->dev);
 
 	pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0);
 }
@@ -916,6 +921,53 @@ void pci_free_msi_irqs(struct pci_dev *dev)
 	}
 }
 
+#ifdef CONFIG_PCIE_TPH
+/**
+ * pci_msix_write_tph_tag - Update the TPH tag for a given MSI-X vector
+ * @pdev:	The PCIe device to update
+ * @index:	The MSI-X index to update
+ * @tag:	The tag to write
+ *
+ * Returns: 0 on success, error code on failure
+ */
+int pci_msix_write_tph_tag(struct pci_dev *pdev, unsigned int index, u16 tag)
+{
+	struct msi_desc *msi_desc;
+	struct irq_desc *irq_desc;
+	unsigned int virq;
+
+	if (!pdev->msix_enabled)
+		return -ENXIO;
+
+	guard(msi_descs_lock)(&pdev->dev);
+	virq = msi_get_virq(&pdev->dev, index);
+	if (!virq)
+		return -ENXIO;
+	/*
+	 * This is a horrible hack, but short of implementing a PCI
+	 * specific interrupt chip callback and a huge pile of
+	 * infrastructure, this is the minor nuissance. It provides the
+	 * protection against concurrent operations on this entry and keeps
+	 * the control word cache in sync.
+	 */
+	irq_desc = irq_to_desc(virq);
+	if (!irq_desc)
+		return -ENXIO;
+
+	guard(raw_spinlock_irq)(&irq_desc->lock);
+	msi_desc = irq_data_get_msi_desc(&irq_desc->irq_data);
+	if (!msi_desc || msi_desc->pci.msi_attrib.is_virtual)
+		return -ENXIO;
+
+	msi_desc->pci.msix_ctrl &= ~PCI_MSIX_ENTRY_CTRL_ST;
+	msi_desc->pci.msix_ctrl |= FIELD_PREP(PCI_MSIX_ENTRY_CTRL_ST, tag);
+	pci_msix_write_vector_ctrl(msi_desc, msi_desc->pci.msix_ctrl);
+	/* Flush the write */
+	readl(pci_msix_desc_addr(msi_desc));
+	return 0;
+}
+#endif
+
 /* Misc. infrastructure */
 
 struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc)
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index f57ea36d125d..02726f36beb5 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -812,8 +812,7 @@ static int pci_pm_suspend(struct device *dev)
 	 * suspend callbacks can cope with runtime-suspended devices, it is
 	 * better to resume the device from runtime suspend here.
 	 */
-	if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) ||
-	    pci_dev_need_resume(pci_dev)) {
+	if (!dev_pm_smart_suspend(dev) || pci_dev_need_resume(pci_dev)) {
 		pm_runtime_resume(dev);
 		pci_dev->state_saved = false;
 	} else {
@@ -1151,8 +1150,7 @@ static int pci_pm_poweroff(struct device *dev)
 	}
 
 	/* The reason to do that is the same as in pci_pm_suspend(). */
-	if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) ||
-	    pci_dev_need_resume(pci_dev)) {
+	if (!dev_pm_smart_suspend(dev) || pci_dev_need_resume(pci_dev)) {
 		pm_runtime_resume(dev);
 		pci_dev->state_saved = false;
 	} else {
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 01e51db8d285..2e9cf26a9ee9 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -989,6 +989,15 @@ int pcim_request_region_exclusive(struct pci_dev *pdev, int bar,
 				  const char *name);
 void pcim_release_region(struct pci_dev *pdev, int bar);
 
+#ifdef CONFIG_PCI_MSI
+int pci_msix_write_tph_tag(struct pci_dev *pdev, unsigned int index, u16 tag);
+#else
+static inline int pci_msix_write_tph_tag(struct pci_dev *pdev, unsigned int index, u16 tag)
+{
+	return -ENODEV;
+}
+#endif
+
 /*
  * Config Address for PCI Configuration Mechanism #1
  *
diff --git a/drivers/pci/tph.c b/drivers/pci/tph.c
index 07de59ca2ebf..77fce5e1b830 100644
--- a/drivers/pci/tph.c
+++ b/drivers/pci/tph.c
@@ -204,48 +204,6 @@ static u8 get_rp_completer_type(struct pci_dev *pdev)
 	return FIELD_GET(PCI_EXP_DEVCAP2_TPH_COMP_MASK, reg);
 }
 
-/* Write ST to MSI-X vector control reg - Return 0 if OK, otherwise -errno */
-static int write_tag_to_msix(struct pci_dev *pdev, int msix_idx, u16 tag)
-{
-#ifdef CONFIG_PCI_MSI
-	struct msi_desc *msi_desc = NULL;
-	void __iomem *vec_ctrl;
-	u32 val;
-	int err = 0;
-
-	msi_lock_descs(&pdev->dev);
-
-	/* Find the msi_desc entry with matching msix_idx */
-	msi_for_each_desc(msi_desc, &pdev->dev, MSI_DESC_ASSOCIATED) {
-		if (msi_desc->msi_index == msix_idx)
-			break;
-	}
-
-	if (!msi_desc) {
-		err = -ENXIO;
-		goto err_out;
-	}
-
-	/* Get the vector control register (offset 0xc) pointed by msix_idx */
-	vec_ctrl = pdev->msix_base + msix_idx * PCI_MSIX_ENTRY_SIZE;
-	vec_ctrl += PCI_MSIX_ENTRY_VECTOR_CTRL;
-
-	val = readl(vec_ctrl);
-	val &= ~PCI_MSIX_ENTRY_CTRL_ST;
-	val |= FIELD_PREP(PCI_MSIX_ENTRY_CTRL_ST, tag);
-	writel(val, vec_ctrl);
-
-	/* Read back to flush the update */
-	val = readl(vec_ctrl);
-
-err_out:
-	msi_unlock_descs(&pdev->dev);
-	return err;
-#else
-	return -ENODEV;
-#endif
-}
-
 /* Write tag to ST table - Return 0 if OK, otherwise -errno */
 static int write_tag_to_st_table(struct pci_dev *pdev, int index, u16 tag)
 {
@@ -346,7 +304,7 @@ int pcie_tph_set_st_entry(struct pci_dev *pdev, unsigned int index, u16 tag)
 
 	switch (loc) {
 	case PCI_TPH_LOC_MSIX:
-		err = write_tag_to_msix(pdev, index, tag);
+		err = pci_msix_write_tph_tag(pdev, index, tag);
 		break;
 	case PCI_TPH_LOC_CAP:
 		err = write_tag_to_st_table(pdev, index, tag);