x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

When using eBPF to probe CS CALL instructions within a function,
a crash can be triggered.

The eBPF tool probes offset 257 of the __hrtimer_run_queues()
function:

<__hrtimer_run_queues+249>:  nopl   0x0(%rax,%rax,1)
<__hrtimer_run_queues+254>:  mov    %r14,%rdi
<__hrtimer_run_queues+257>:  cs call <__x86_indirect_thunk_r12>
<__hrtimer_run_queues+263>:  mov    %eax,%r12d
<__hrtimer_run_queues+266>:  xchg   %ax,%ax
<__hrtimer_run_queues+268>:  mov    %r13,%rdi

Which triggers this crash:

  BUG: unable to handle page fault for address: 00000000000f41c9
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0002) - not-present page
  PGD 0 P4D 0
  Oops: 0002 [#1] SMP NOPTI
  CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P
  RIP: 0010:__hrtimer_run_queues+0x106/0x230

Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is
at the 6th byte of the above CS CALL instruction. Since the CS CALL
instruction occupies 6 bytes, the exception occurred in the middle of that
call instruction.

The root cause is that when using eBPF tools to probe in the middle of a
function, a kprobe with INT3 is used as the underlying implementation.

During single-step emulation of the original CALL instruction,
int3_emulate_call() assumes that the probed CALL instruction is 5 bytes
long. However, the actual CS-prefixed CALL instruction occupies 6 bytes,
so it constructs an incorrect exception return address. When the CPU
returns from the kprobe handler, the next instruction to be executed is at
the address of the last byte of that CS CALL instruction. Coincidentally,
starting from that address, the CPU fetches and decodes a completely
different instruction, which ultimately triggers a kernel crash.

Fix the issue by using the actual instruction length obtained from
the instruction decoder when constructing the exception return
address, rather than relying on the hardcoded CALL_INSN_SIZE macro.

[ mingo: Refined the changelog ]

Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step")
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

7 files changed, 2098 insertions, 0 deletions

diff --git a/drivers/pci/msi/Makefile b/drivers/pci/msi/Makefile
new file mode 100644
index 000000000..839ff72d7
--- /dev/null
+++ b/drivers/pci/msi/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the PCI/MSI
+obj-$(CONFIG_PCI)			+= pcidev_msi.o
+obj-$(CONFIG_PCI_MSI)			+= api.o msi.o irqdomain.o
+obj-$(CONFIG_PCI_MSI_ARCH_FALLBACKS)	+= legacy.o
diff --git a/drivers/pci/msi/api.c b/drivers/pci/msi/api.c
new file mode 100644
index 000000000..c18559b62
--- /dev/null
+++ b/drivers/pci/msi/api.c
@@ -0,0 +1,411 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * PCI MSI/MSI-X — Exported APIs for device drivers
+ *
+ * Copyright (C) 2003-2004 Intel
+ * Copyright (C) Tom Long Nguyen (tom.l.nguyen@intel.com)
+ * Copyright (C) 2016 Christoph Hellwig.
+ * Copyright (C) 2022 Linutronix GmbH
+ */
+
+#include <linux/export.h>
+#include <linux/irq.h>
+
+#include "msi.h"
+
+/**
+ * pci_enable_msi() - Enable MSI interrupt mode on device
+ * @dev: the PCI device to operate on
+ *
+ * Legacy device driver API to enable MSI interrupts mode on device and
+ * allocate a single interrupt vector. On success, the allocated vector
+ * Linux IRQ will be saved at @dev->irq. The driver must invoke
+ * pci_disable_msi() on cleanup.
+ *
+ * NOTE: The newer pci_alloc_irq_vectors() / pci_free_irq_vectors() API
+ * pair should, in general, be used instead.
+ *
+ * Return: 0 on success, errno otherwise
+ */
+int pci_enable_msi(struct pci_dev *dev)
+{
+	int rc = __pci_enable_msi_range(dev, 1, 1, NULL);
+	if (rc < 0)
+		return rc;
+	return 0;
+}
+EXPORT_SYMBOL(pci_enable_msi);
+
+/**
+ * pci_disable_msi() - Disable MSI interrupt mode on device
+ * @dev: the PCI device to operate on
+ *
+ * Legacy device driver API to disable MSI interrupt mode on device,
+ * free earlier allocated interrupt vectors, and restore INTx emulation.
+ * The PCI device Linux IRQ (@dev->irq) is restored to its default
+ * pin-assertion IRQ. This is the cleanup pair of pci_enable_msi().
+ *
+ * NOTE: The newer pci_alloc_irq_vectors() / pci_free_irq_vectors() API
+ * pair should, in general, be used instead.
+ */
+void pci_disable_msi(struct pci_dev *dev)
+{
+	if (!pci_msi_enabled() || !dev || !dev->msi_enabled)
+		return;
+
+	guard(msi_descs_lock)(&dev->dev);
+	pci_msi_shutdown(dev);
+	pci_free_msi_irqs(dev);
+}
+EXPORT_SYMBOL(pci_disable_msi);
+
+/**
+ * pci_msix_vec_count() - Get number of MSI-X interrupt vectors on device
+ * @dev: the PCI device to operate on
+ *
+ * Return: number of MSI-X interrupt vectors available on this device
+ * (i.e., the device's MSI-X capability structure "table size"), -EINVAL
+ * if the device is not MSI-X capable, other errnos otherwise.
+ */
+int pci_msix_vec_count(struct pci_dev *dev)
+{
+	u16 control;
+
+	if (!dev->msix_cap)
+		return -EINVAL;
+
+	pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &control);
+	return msix_table_size(control);
+}
+EXPORT_SYMBOL(pci_msix_vec_count);
+
+/**
+ * pci_enable_msix_range() - Enable MSI-X interrupt mode on device
+ * @dev:     the PCI device to operate on
+ * @entries: input/output parameter, array of MSI-X configuration entries
+ * @minvec:  minimum required number of MSI-X vectors
+ * @maxvec:  maximum desired number of MSI-X vectors
+ *
+ * Legacy device driver API to enable MSI-X interrupt mode on device and
+ * configure its MSI-X capability structure as appropriate.  The passed
+ * @entries array must have each of its members "entry" field set to a
+ * desired (valid) MSI-X vector number, where the range of valid MSI-X
+ * vector numbers can be queried through pci_msix_vec_count().  If
+ * successful, the driver must invoke pci_disable_msix() on cleanup.
+ *
+ * NOTE: The newer pci_alloc_irq_vectors() / pci_free_irq_vectors() API
+ * pair should, in general, be used instead.
+ *
+ * Return: number of MSI-X vectors allocated (which might be smaller
+ * than @maxvecs), where Linux IRQ numbers for such allocated vectors
+ * are saved back in the @entries array elements' "vector" field. Return
+ * -ENOSPC if less than @minvecs interrupt vectors are available.
+ * Return -EINVAL if one of the passed @entries members "entry" field
+ * was invalid or a duplicate, or if plain MSI interrupts mode was
+ * earlier enabled on device. Return other errnos otherwise.
+ */
+int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries,
+			  int minvec, int maxvec)
+{
+	return __pci_enable_msix_range(dev, entries, minvec, maxvec, NULL, 0);
+}
+EXPORT_SYMBOL(pci_enable_msix_range);
+
+/**
+ * pci_msix_can_alloc_dyn - Query whether dynamic allocation after enabling
+ *			    MSI-X is supported
+ *
+ * @dev:	PCI device to operate on
+ *
+ * Return: True if supported, false otherwise
+ */
+bool pci_msix_can_alloc_dyn(struct pci_dev *dev)
+{
+	if (!dev->msix_cap)
+		return false;
+
+	return pci_msi_domain_supports(dev, MSI_FLAG_PCI_MSIX_ALLOC_DYN, DENY_LEGACY);
+}
+EXPORT_SYMBOL_GPL(pci_msix_can_alloc_dyn);
+
+/**
+ * pci_msix_alloc_irq_at - Allocate an MSI-X interrupt after enabling MSI-X
+ *			   at a given MSI-X vector index or any free vector index
+ *
+ * @dev:	PCI device to operate on
+ * @index:	Index to allocate. If @index == MSI_ANY_INDEX this allocates
+ *		the next free index in the MSI-X table
+ * @affdesc:	Optional pointer to an affinity descriptor structure. NULL otherwise
+ *
+ * Return: A struct msi_map
+ *
+ *	On success msi_map::index contains the allocated index (>= 0) and
+ *	msi_map::virq contains the allocated Linux interrupt number (> 0).
+ *
+ *	On fail msi_map::index contains the error code and msi_map::virq
+ *	is set to 0.
+ */
+struct msi_map pci_msix_alloc_irq_at(struct pci_dev *dev, unsigned int index,
+				     const struct irq_affinity_desc *affdesc)
+{
+	struct msi_map map = { .index = -ENOTSUPP };
+
+	if (!dev->msix_enabled)
+		return map;
+
+	if (!pci_msix_can_alloc_dyn(dev))
+		return map;
+
+	return msi_domain_alloc_irq_at(&dev->dev, MSI_DEFAULT_DOMAIN, index, affdesc, NULL);
+}
+EXPORT_SYMBOL_GPL(pci_msix_alloc_irq_at);
+
+/**
+ * pci_msix_free_irq - Free an interrupt on a PCI/MSI-X interrupt domain
+ *
+ * @dev:	The PCI device to operate on
+ * @map:	A struct msi_map describing the interrupt to free
+ *
+ * Undo an interrupt vector allocation. Does not disable MSI-X.
+ */
+void pci_msix_free_irq(struct pci_dev *dev, struct msi_map map)
+{
+	if (WARN_ON_ONCE(map.index < 0 || map.virq <= 0))
+		return;
+	if (WARN_ON_ONCE(!pci_msix_can_alloc_dyn(dev)))
+		return;
+	msi_domain_free_irqs_range(&dev->dev, MSI_DEFAULT_DOMAIN, map.index, map.index);
+}
+EXPORT_SYMBOL_GPL(pci_msix_free_irq);
+
+/**
+ * pci_disable_msix() - Disable MSI-X interrupt mode on device
+ * @dev: the PCI device to operate on
+ *
+ * Legacy device driver API to disable MSI-X interrupt mode on device,
+ * free earlier-allocated interrupt vectors, and restore INTx.
+ * The PCI device Linux IRQ (@dev->irq) is restored to its default pin
+ * assertion IRQ. This is the cleanup pair of pci_enable_msix_range().
+ *
+ * NOTE: The newer pci_alloc_irq_vectors() / pci_free_irq_vectors() API
+ * pair should, in general, be used instead.
+ */
+void pci_disable_msix(struct pci_dev *dev)
+{
+	if (!pci_msi_enabled() || !dev || !dev->msix_enabled)
+		return;
+
+	guard(msi_descs_lock)(&dev->dev);
+	pci_msix_shutdown(dev);
+	pci_free_msi_irqs(dev);
+}
+EXPORT_SYMBOL(pci_disable_msix);
+
+/**
+ * pci_alloc_irq_vectors() - Allocate multiple device interrupt vectors
+ * @dev:      the PCI device to operate on
+ * @min_vecs: minimum required number of vectors (must be >= 1)
+ * @max_vecs: maximum desired number of vectors
+ * @flags:    One or more of:
+ *
+ *            * %PCI_IRQ_MSIX      Allow trying MSI-X vector allocations
+ *            * %PCI_IRQ_MSI       Allow trying MSI vector allocations
+ *
+ *            * %PCI_IRQ_INTX      Allow trying INTx interrupts, if and
+ *              only if @min_vecs == 1
+ *
+ *            * %PCI_IRQ_AFFINITY  Auto-manage IRQs affinity by spreading
+ *              the vectors around available CPUs
+ *
+ * Allocate up to @max_vecs interrupt vectors on device. MSI-X irq
+ * vector allocation has a higher precedence over plain MSI, which has a
+ * higher precedence over legacy INTx emulation.
+ *
+ * Upon a successful allocation, the caller should use pci_irq_vector()
+ * to get the Linux IRQ number to be passed to request_threaded_irq().
+ * The driver must call pci_free_irq_vectors() on cleanup.
+ *
+ * Return: number of allocated vectors (which might be smaller than
+ * @max_vecs), -ENOSPC if less than @min_vecs interrupt vectors are
+ * available, other errnos otherwise.
+ */
+int pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs,
+			  unsigned int max_vecs, unsigned int flags)
+{
+	return pci_alloc_irq_vectors_affinity(dev, min_vecs, max_vecs,
+					      flags, NULL);
+}
+EXPORT_SYMBOL(pci_alloc_irq_vectors);
+
+/**
+ * pci_alloc_irq_vectors_affinity() - Allocate multiple device interrupt
+ *                                    vectors with affinity requirements
+ * @dev:      the PCI device to operate on
+ * @min_vecs: minimum required number of vectors (must be >= 1)
+ * @max_vecs: maximum desired number of vectors
+ * @flags:    allocation flags, as in pci_alloc_irq_vectors()
+ * @affd:     affinity requirements (can be %NULL).
+ *
+ * Same as pci_alloc_irq_vectors(), but with the extra @affd parameter.
+ * Check that function docs, and &struct irq_affinity, for more details.
+ */
+int pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs,
+				   unsigned int max_vecs, unsigned int flags,
+				   struct irq_affinity *affd)
+{
+	struct irq_affinity msi_default_affd = {0};
+	int nvecs = -ENOSPC;
+
+	if (flags & PCI_IRQ_AFFINITY) {
+		if (!affd)
+			affd = &msi_default_affd;
+	} else {
+		if (WARN_ON(affd))
+			affd = NULL;
+	}
+
+	if (flags & PCI_IRQ_MSIX) {
+		nvecs = __pci_enable_msix_range(dev, NULL, min_vecs, max_vecs,
+						affd, flags);
+		if (nvecs > 0)
+			return nvecs;
+	}
+
+	if (flags & PCI_IRQ_MSI) {
+		nvecs = __pci_enable_msi_range(dev, min_vecs, max_vecs, affd);
+		if (nvecs > 0)
+			return nvecs;
+	}
+
+	/* use INTx IRQ if allowed */
+	if (flags & PCI_IRQ_INTX) {
+		if (min_vecs == 1 && dev->irq) {
+			/*
+			 * Invoke the affinity spreading logic to ensure that
+			 * the device driver can adjust queue configuration
+			 * for the single interrupt case.
+			 */
+			if (affd)
+				irq_create_affinity_masks(1, affd);
+			pci_intx(dev, 1);
+			return 1;
+		}
+	}
+
+	return nvecs;
+}
+EXPORT_SYMBOL(pci_alloc_irq_vectors_affinity);
+
+/**
+ * pci_irq_vector() - Get Linux IRQ number of a device interrupt vector
+ * @dev: the PCI device to operate on
+ * @nr:  device-relative interrupt vector index (0-based); has different
+ *       meanings, depending on interrupt mode:
+ *
+ *         * MSI-X     the index in the MSI-X vector table
+ *         * MSI       the index of the enabled MSI vectors
+ *         * INTx      must be 0
+ *
+ * Return: the Linux IRQ number, or -EINVAL if @nr is out of range
+ */
+int pci_irq_vector(struct pci_dev *dev, unsigned int nr)
+{
+	unsigned int irq;
+
+	if (!dev->msi_enabled && !dev->msix_enabled)
+		return !nr ? dev->irq : -EINVAL;
+
+	irq = msi_get_virq(&dev->dev, nr);
+	return irq ? irq : -EINVAL;
+}
+EXPORT_SYMBOL(pci_irq_vector);
+
+/**
+ * pci_irq_get_affinity() - Get a device interrupt vector affinity
+ * @dev: the PCI device to operate on
+ * @nr:  device-relative interrupt vector index (0-based); has different
+ *       meanings, depending on interrupt mode:
+ *
+ *         * MSI-X     the index in the MSI-X vector table
+ *         * MSI       the index of the enabled MSI vectors
+ *         * INTx      must be 0
+ *
+ * Return: MSI/MSI-X vector affinity, NULL if @nr is out of range or if
+ * the MSI(-X) vector was allocated without explicit affinity
+ * requirements (e.g., by pci_enable_msi(), pci_enable_msix_range(), or
+ * pci_alloc_irq_vectors() without the %PCI_IRQ_AFFINITY flag). Return a
+ * generic set of CPU IDs representing all possible CPUs available
+ * during system boot if the device is in legacy INTx mode.
+ */
+const struct cpumask *pci_irq_get_affinity(struct pci_dev *dev, int nr)
+{
+	int idx, irq = pci_irq_vector(dev, nr);
+	struct msi_desc *desc;
+
+	if (WARN_ON_ONCE(irq <= 0))
+		return NULL;
+
+	desc = irq_get_msi_desc(irq);
+	/* Non-MSI does not have the information handy */
+	if (!desc)
+		return cpu_possible_mask;
+
+	/* MSI[X] interrupts can be allocated without affinity descriptor */
+	if (!desc->affinity)
+		return NULL;
+
+	/*
+	 * MSI has a mask array in the descriptor.
+	 * MSI-X has a single mask.
+	 */
+	idx = dev->msi_enabled ? nr : 0;
+	return &desc->affinity[idx].mask;
+}
+EXPORT_SYMBOL(pci_irq_get_affinity);
+
+/**
+ * pci_free_irq_vectors() - Free previously allocated IRQs for a device
+ * @dev: the PCI device to operate on
+ *
+ * Undo the interrupt vector allocations and possible device MSI/MSI-X
+ * enablement earlier done through pci_alloc_irq_vectors_affinity() or
+ * pci_alloc_irq_vectors().
+ *
+ * WARNING: Do not call this function if the device has been enabled
+ * with pcim_enable_device(). In that case, IRQ vectors are automatically
+ * managed via pcim_msi_release() and calling pci_free_irq_vectors() can
+ * lead to double-free issues.
+ */
+void pci_free_irq_vectors(struct pci_dev *dev)
+{
+	pci_disable_msix(dev);
+	pci_disable_msi(dev);
+}
+EXPORT_SYMBOL(pci_free_irq_vectors);
+
+/**
+ * pci_restore_msi_state() - Restore cached MSI(-X) state on device
+ * @dev: the PCI device to operate on
+ *
+ * Write the Linux-cached MSI(-X) state back on device. This is
+ * typically useful upon system resume, or after an error-recovery PCI
+ * adapter reset.
+ */
+void pci_restore_msi_state(struct pci_dev *dev)
+{
+	__pci_restore_msi_state(dev);
+	__pci_restore_msix_state(dev);
+}
+EXPORT_SYMBOL_GPL(pci_restore_msi_state);
+
+/**
+ * pci_msi_enabled() - Are MSI(-X) interrupts enabled system-wide?
+ *
+ * Return: true if MSI has not been globally disabled through ACPI FADT,
+ * PCI bridge quirks, or the "pci=nomsi" kernel command-line option.
+ */
+bool pci_msi_enabled(void)
+{
+	return pci_msi_enable;
+}
+EXPORT_SYMBOL(pci_msi_enabled);
diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c
new file mode 100644
index 000000000..6e65f0f44
--- /dev/null
+++ b/drivers/pci/msi/irqdomain.c
@@ -0,0 +1,431 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * PCI Message Signaled Interrupt (MSI) - irqdomain support
+ */
+#include <linux/acpi_iort.h>
+#include <linux/irqdomain.h>
+#include <linux/of_irq.h>
+
+#include "msi.h"
+
+int pci_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+	struct irq_domain *domain;
+
+	domain = dev_get_msi_domain(&dev->dev);
+	if (domain && irq_domain_is_hierarchy(domain))
+		return msi_domain_alloc_irqs_all_locked(&dev->dev, MSI_DEFAULT_DOMAIN, nvec);
+
+	return pci_msi_legacy_setup_msi_irqs(dev, nvec, type);
+}
+
+void pci_msi_teardown_msi_irqs(struct pci_dev *dev)
+{
+	struct irq_domain *domain;
+
+	domain = dev_get_msi_domain(&dev->dev);
+	if (domain && irq_domain_is_hierarchy(domain)) {
+		msi_domain_free_irqs_all_locked(&dev->dev, MSI_DEFAULT_DOMAIN);
+	} else {
+		pci_msi_legacy_teardown_msi_irqs(dev);
+		msi_free_msi_descs(&dev->dev);
+	}
+}
+
+/**
+ * pci_msi_domain_write_msg - Helper to write MSI message to PCI config space
+ * @irq_data:	Pointer to interrupt data of the MSI interrupt
+ * @msg:	Pointer to the message
+ */
+static void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg)
+{
+	struct msi_desc *desc = irq_data_get_msi_desc(irq_data);
+
+	/*
+	 * For MSI-X desc->irq is always equal to irq_data->irq. For
+	 * MSI only the first interrupt of MULTI MSI passes the test.
+	 */
+	if (desc->irq == irq_data->irq)
+		__pci_write_msi_msg(desc, msg);
+}
+
+/*
+ * Per device MSI[-X] domain functionality
+ */
+static void pci_device_domain_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc)
+{
+	arg->desc = desc;
+	arg->hwirq = desc->msi_index;
+}
+
+static void cond_shutdown_parent(struct irq_data *data)
+{
+	struct msi_domain_info *info = data->domain->host_data;
+
+	if (unlikely(info->flags & MSI_FLAG_PCI_MSI_STARTUP_PARENT))
+		irq_chip_shutdown_parent(data);
+	else if (unlikely(info->flags & MSI_FLAG_PCI_MSI_MASK_PARENT))
+		irq_chip_mask_parent(data);
+}
+
+static unsigned int cond_startup_parent(struct irq_data *data)
+{
+	struct msi_domain_info *info = data->domain->host_data;
+
+	if (unlikely(info->flags & MSI_FLAG_PCI_MSI_STARTUP_PARENT))
+		return irq_chip_startup_parent(data);
+	else if (unlikely(info->flags & MSI_FLAG_PCI_MSI_MASK_PARENT))
+		irq_chip_unmask_parent(data);
+
+	return 0;
+}
+
+static void pci_irq_shutdown_msi(struct irq_data *data)
+{
+	struct msi_desc *desc = irq_data_get_msi_desc(data);
+
+	pci_msi_mask(desc, BIT(data->irq - desc->irq));
+	cond_shutdown_parent(data);
+}
+
+static unsigned int pci_irq_startup_msi(struct irq_data *data)
+{
+	struct msi_desc *desc = irq_data_get_msi_desc(data);
+	unsigned int ret = cond_startup_parent(data);
+
+	pci_msi_unmask(desc, BIT(data->irq - desc->irq));
+	return ret;
+}
+
+static void pci_irq_mask_msi(struct irq_data *data)
+{
+	struct msi_desc *desc = irq_data_get_msi_desc(data);
+
+	pci_msi_mask(desc, BIT(data->irq - desc->irq));
+}
+
+static void pci_irq_unmask_msi(struct irq_data *data)
+{
+	struct msi_desc *desc = irq_data_get_msi_desc(data);
+
+	pci_msi_unmask(desc, BIT(data->irq - desc->irq));
+}
+
+#ifdef CONFIG_GENERIC_IRQ_RESERVATION_MODE
+# define MSI_REACTIVATE		MSI_FLAG_MUST_REACTIVATE
+#else
+# define MSI_REACTIVATE		0
+#endif
+
+#define MSI_COMMON_FLAGS	(MSI_FLAG_FREE_MSI_DESCS |	\
+				 MSI_FLAG_ACTIVATE_EARLY |	\
+				 MSI_FLAG_DEV_SYSFS |		\
+				 MSI_REACTIVATE)
+
+static const struct msi_domain_template pci_msi_template = {
+	.chip = {
+		.name			= "PCI-MSI",
+		.irq_startup		= pci_irq_startup_msi,
+		.irq_shutdown		= pci_irq_shutdown_msi,
+		.irq_mask		= pci_irq_mask_msi,
+		.irq_unmask		= pci_irq_unmask_msi,
+		.irq_write_msi_msg	= pci_msi_domain_write_msg,
+		.flags			= IRQCHIP_ONESHOT_SAFE,
+	},
+
+	.ops = {
+		.set_desc		= pci_device_domain_set_desc,
+	},
+
+	.info = {
+		.flags			= MSI_COMMON_FLAGS | MSI_FLAG_MULTI_PCI_MSI,
+		.bus_token		= DOMAIN_BUS_PCI_DEVICE_MSI,
+	},
+};
+
+static void pci_irq_shutdown_msix(struct irq_data *data)
+{
+	pci_msix_mask(irq_data_get_msi_desc(data));
+	cond_shutdown_parent(data);
+}
+
+static unsigned int pci_irq_startup_msix(struct irq_data *data)
+{
+	unsigned int ret = cond_startup_parent(data);
+
+	pci_msix_unmask(irq_data_get_msi_desc(data));
+	return ret;
+}
+
+static void pci_irq_mask_msix(struct irq_data *data)
+{
+	pci_msix_mask(irq_data_get_msi_desc(data));
+}
+
+static void pci_irq_unmask_msix(struct irq_data *data)
+{
+	pci_msix_unmask(irq_data_get_msi_desc(data));
+}
+
+void pci_msix_prepare_desc(struct irq_domain *domain, msi_alloc_info_t *arg,
+			   struct msi_desc *desc)
+{
+	/* Don't fiddle with preallocated MSI descriptors */
+	if (!desc->pci.mask_base)
+		msix_prepare_msi_desc(to_pci_dev(desc->dev), desc);
+}
+EXPORT_SYMBOL_GPL(pci_msix_prepare_desc);
+
+static const struct msi_domain_template pci_msix_template = {
+	.chip = {
+		.name			= "PCI-MSIX",
+		.irq_startup		= pci_irq_startup_msix,
+		.irq_shutdown		= pci_irq_shutdown_msix,
+		.irq_mask		= pci_irq_mask_msix,
+		.irq_unmask		= pci_irq_unmask_msix,
+		.irq_write_msi_msg	= pci_msi_domain_write_msg,
+		.flags			= IRQCHIP_ONESHOT_SAFE,
+	},
+
+	.ops = {
+		.prepare_desc		= pci_msix_prepare_desc,
+		.set_desc		= pci_device_domain_set_desc,
+	},
+
+	.info = {
+		.flags			= MSI_COMMON_FLAGS | MSI_FLAG_PCI_MSIX |
+					  MSI_FLAG_PCI_MSIX_ALLOC_DYN,
+		.bus_token		= DOMAIN_BUS_PCI_DEVICE_MSIX,
+	},
+};
+
+static bool pci_match_device_domain(struct pci_dev *pdev, enum irq_domain_bus_token bus_token)
+{
+	return msi_match_device_irq_domain(&pdev->dev, MSI_DEFAULT_DOMAIN, bus_token);
+}
+
+static bool pci_create_device_domain(struct pci_dev *pdev, const struct msi_domain_template *tmpl,
+				     unsigned int hwsize)
+{
+	struct irq_domain *domain = dev_get_msi_domain(&pdev->dev);
+
+	if (!domain || !irq_domain_is_msi_parent(domain))
+		return true;
+
+	return msi_create_device_irq_domain(&pdev->dev, MSI_DEFAULT_DOMAIN, tmpl,
+					    hwsize, NULL, NULL);
+}
+
+/**
+ * pci_setup_msi_device_domain - Setup a device MSI interrupt domain
+ * @pdev:	The PCI device to create the domain on
+ * @hwsize:	The maximum number of MSI vectors
+ *
+ * Return:
+ *  True when:
+ *	- The device does not have a MSI parent irq domain associated,
+ *	  which keeps the legacy architecture specific and the global
+ *	  PCI/MSI domain models working
+ *	- The MSI domain exists already
+ *	- The MSI domain was successfully allocated
+ *  False when:
+ *	- MSI-X is enabled
+ *	- The domain creation fails.
+ *
+ * The created MSI domain is preserved until:
+ *	- The device is removed
+ *	- MSI is disabled and a MSI-X domain is created
+ */
+bool pci_setup_msi_device_domain(struct pci_dev *pdev, unsigned int hwsize)
+{
+	if (WARN_ON_ONCE(pdev->msix_enabled))
+		return false;
+
+	if (pci_match_device_domain(pdev, DOMAIN_BUS_PCI_DEVICE_MSI))
+		return true;
+	if (pci_match_device_domain(pdev, DOMAIN_BUS_PCI_DEVICE_MSIX))
+		msi_remove_device_irq_domain(&pdev->dev, MSI_DEFAULT_DOMAIN);
+
+	return pci_create_device_domain(pdev, &pci_msi_template, hwsize);
+}
+
+/**
+ * pci_setup_msix_device_domain - Setup a device MSI-X interrupt domain
+ * @pdev:	The PCI device to create the domain on
+ * @hwsize:	The size of the MSI-X vector table
+ *
+ * Return:
+ *  True when:
+ *	- The device does not have a MSI parent irq domain associated,
+ *	  which keeps the legacy architecture specific and the global
+ *	  PCI/MSI domain models working
+ *	- The MSI-X domain exists already
+ *	- The MSI-X domain was successfully allocated
+ *  False when:
+ *	- MSI is enabled
+ *	- The domain creation fails.
+ *
+ * The created MSI-X domain is preserved until:
+ *	- The device is removed
+ *	- MSI-X is disabled and a MSI domain is created
+ */
+bool pci_setup_msix_device_domain(struct pci_dev *pdev, unsigned int hwsize)
+{
+	if (WARN_ON_ONCE(pdev->msi_enabled))
+		return false;
+
+	if (pci_match_device_domain(pdev, DOMAIN_BUS_PCI_DEVICE_MSIX))
+		return true;
+	if (pci_match_device_domain(pdev, DOMAIN_BUS_PCI_DEVICE_MSI))
+		msi_remove_device_irq_domain(&pdev->dev, MSI_DEFAULT_DOMAIN);
+
+	return pci_create_device_domain(pdev, &pci_msix_template, hwsize);
+}
+
+/**
+ * pci_msi_domain_supports - Check for support of a particular feature flag
+ * @pdev:		The PCI device to operate on
+ * @feature_mask:	The feature mask to check for (full match)
+ * @mode:		If ALLOW_LEGACY this grants the feature when there is no irq domain
+ *			associated to the device. If DENY_LEGACY the lack of an irq domain
+ *			makes the feature unsupported
+ */
+bool pci_msi_domain_supports(struct pci_dev *pdev, unsigned int feature_mask,
+			     enum support_mode mode)
+{
+	struct msi_domain_info *info;
+	struct irq_domain *domain;
+	unsigned int supported;
+
+	domain = dev_get_msi_domain(&pdev->dev);
+
+	if (!domain || !irq_domain_is_hierarchy(domain)) {
+		if (IS_ENABLED(CONFIG_PCI_MSI_ARCH_FALLBACKS))
+			return mode == ALLOW_LEGACY;
+		return false;
+	}
+
+	if (!irq_domain_is_msi_parent(domain)) {
+		/*
+		 * For "global" PCI/MSI interrupt domains the associated
+		 * msi_domain_info::flags is the authoritative source of
+		 * information.
+		 */
+		info = domain->host_data;
+		supported = info->flags;
+	} else {
+		/*
+		 * For MSI parent domains the supported feature set
+		 * is available in the parent ops. This makes checks
+		 * possible before actually instantiating the
+		 * per device domain because the parent is never
+		 * expanding the PCI/MSI functionality.
+		 */
+		supported = domain->msi_parent_ops->supported_flags;
+	}
+
+	return (supported & feature_mask) == feature_mask;
+}
+
+/*
+ * Users of the generic MSI infrastructure expect a device to have a single ID,
+ * so with DMA aliases we have to pick the least-worst compromise. Devices with
+ * DMA phantom functions tend to still emit MSIs from the real function number,
+ * so we ignore those and only consider topological aliases where either the
+ * alias device or RID appears on a different bus number. We also make the
+ * reasonable assumption that bridges are walked in an upstream direction (so
+ * the last one seen wins), and the much braver assumption that the most likely
+ * case is that of PCI->PCIe so we should always use the alias RID. This echoes
+ * the logic from intel_irq_remapping's set_msi_sid(), which presumably works
+ * well enough in practice; in the face of the horrible PCIe<->PCI-X conditions
+ * for taking ownership all we can really do is close our eyes and hope...
+ */
+static int get_msi_id_cb(struct pci_dev *pdev, u16 alias, void *data)
+{
+	u32 *pa = data;
+	u8 bus = PCI_BUS_NUM(*pa);
+
+	if (pdev->bus->number != bus || PCI_BUS_NUM(alias) != bus)
+		*pa = alias;
+
+	return 0;
+}
+
+/**
+ * pci_msi_domain_get_msi_rid - Get the MSI requester id (RID)
+ * @domain:	The interrupt domain
+ * @pdev:	The PCI device.
+ *
+ * The RID for a device is formed from the alias, with a firmware
+ * supplied mapping applied
+ *
+ * Returns: The RID.
+ */
+u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev)
+{
+	struct device_node *of_node;
+	u32 rid = pci_dev_id(pdev);
+
+	pci_for_each_dma_alias(pdev, get_msi_id_cb, &rid);
+
+	of_node = irq_domain_get_of_node(domain);
+	rid = of_node ? of_msi_xlate(&pdev->dev, &of_node, rid) :
+			iort_msi_map_id(&pdev->dev, rid);
+
+	return rid;
+}
+
+/**
+ * pci_msi_map_rid_ctlr_node - Get the MSI controller fwnode_handle and MSI requester id (RID)
+ * @domain:	The interrupt domain
+ * @pdev:	The PCI device
+ * @node:	Pointer to store the MSI controller fwnode_handle
+ *
+ * Use the firmware data to find the MSI controller fwnode_handle for @pdev.
+ * If found map the RID and initialize @node with it. @node value must
+ * be set to NULL on entry.
+ *
+ * Returns: The RID.
+ */
+u32 pci_msi_map_rid_ctlr_node(struct irq_domain *domain, struct pci_dev *pdev,
+			      struct fwnode_handle **node)
+{
+	u32 rid = pci_dev_id(pdev);
+
+	pci_for_each_dma_alias(pdev, get_msi_id_cb, &rid);
+
+	/* Check whether the domain fwnode is an OF node */
+	if (irq_domain_get_of_node(domain)) {
+		struct device_node *msi_ctlr_node = NULL;
+
+		rid = of_msi_xlate(&pdev->dev, &msi_ctlr_node, rid);
+		if (msi_ctlr_node)
+			*node = of_fwnode_handle(msi_ctlr_node);
+	} else {
+		rid = iort_msi_xlate(&pdev->dev, rid, node);
+	}
+
+	return rid;
+}
+
+/**
+ * pci_msi_get_device_domain - Get the MSI domain for a given PCI device
+ * @pdev:	The PCI device
+ *
+ * Use the firmware data to find a device-specific MSI domain
+ * (i.e. not one that is set as a default).
+ *
+ * Returns: The corresponding MSI domain or NULL if none has been found.
+ */
+struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev)
+{
+	struct irq_domain *dom;
+	u32 rid = pci_dev_id(pdev);
+
+	pci_for_each_dma_alias(pdev, get_msi_id_cb, &rid);
+	dom = of_msi_map_get_device_domain(&pdev->dev, rid, DOMAIN_BUS_PCI_MSI);
+	if (!dom)
+		dom = iort_get_device_domain(&pdev->dev, rid,
+					     DOMAIN_BUS_PCI_MSI);
+	return dom;
+}
diff --git a/drivers/pci/msi/legacy.c b/drivers/pci/msi/legacy.c
new file mode 100644
index 000000000..db761adef
--- /dev/null
+++ b/drivers/pci/msi/legacy.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * PCI Message Signaled Interrupt (MSI).
+ *
+ * Legacy architecture specific setup and teardown mechanism.
+ */
+#include "msi.h"
+
+/* Arch hooks */
+int __weak arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
+{
+	return -EINVAL;
+}
+
+void __weak arch_teardown_msi_irq(unsigned int irq)
+{
+}
+
+int __weak arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+	struct msi_desc *desc;
+	int ret;
+
+	/*
+	 * If an architecture wants to support multiple MSI, it needs to
+	 * override arch_setup_msi_irqs()
+	 */
+	if (type == PCI_CAP_ID_MSI && nvec > 1)
+		return 1;
+
+	msi_for_each_desc(desc, &dev->dev, MSI_DESC_NOTASSOCIATED) {
+		ret = arch_setup_msi_irq(dev, desc);
+		if (ret)
+			return ret < 0 ? ret : -ENOSPC;
+	}
+
+	return 0;
+}
+
+void __weak arch_teardown_msi_irqs(struct pci_dev *dev)
+{
+	struct msi_desc *desc;
+	int i;
+
+	msi_for_each_desc(desc, &dev->dev, MSI_DESC_ASSOCIATED) {
+		for (i = 0; i < desc->nvec_used; i++)
+			arch_teardown_msi_irq(desc->irq + i);
+	}
+}
+
+static int pci_msi_setup_check_result(struct pci_dev *dev, int type, int ret)
+{
+	struct msi_desc *desc;
+	int avail = 0;
+
+	if (type != PCI_CAP_ID_MSIX || ret >= 0)
+		return ret;
+
+	/* Scan the MSI descriptors for successfully allocated ones. */
+	msi_for_each_desc(desc, &dev->dev, MSI_DESC_ASSOCIATED)
+		avail++;
+
+	return avail ? avail : ret;
+}
+
+int pci_msi_legacy_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+	int ret = arch_setup_msi_irqs(dev, nvec, type);
+
+	ret = pci_msi_setup_check_result(dev, type, ret);
+	if (!ret)
+		ret = msi_device_populate_sysfs(&dev->dev);
+	return ret;
+}
+
+void pci_msi_legacy_teardown_msi_irqs(struct pci_dev *dev)
+{
+	msi_device_destroy_sysfs(&dev->dev);
+	arch_teardown_msi_irqs(dev);
+}
diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c
new file mode 100644
index 000000000..80a9db417
--- /dev/null
+++ b/drivers/pci/msi/msi.c
@@ -0,0 +1,998 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * PCI Message Signaled Interrupt (MSI)
+ *
+ * Copyright (C) 2003-2004 Intel
+ * Copyright (C) Tom Long Nguyen (tom.l.nguyen@intel.com)
+ * Copyright (C) 2016 Christoph Hellwig.
+ */
+#include <linux/bitfield.h>
+#include <linux/err.h>
+#include <linux/export.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
+
+#include "../pci.h"
+#include "msi.h"
+
+bool pci_msi_enable = true;
+
+/**
+ * pci_msi_supported - check whether MSI may be enabled on a device
+ * @dev: pointer to the pci_dev data structure of MSI device function
+ * @nvec: how many MSIs have been requested?
+ *
+ * Look at global flags, the device itself, and its parent buses
+ * to determine if MSI/-X are supported for the device. If MSI/-X is
+ * supported return 1, else return 0.
+ **/
+static int pci_msi_supported(struct pci_dev *dev, int nvec)
+{
+	struct pci_bus *bus;
+
+	/* MSI must be globally enabled and supported by the device */
+	if (!pci_msi_enable)
+		return 0;
+
+	if (!dev || dev->no_msi)
+		return 0;
+
+	/*
+	 * You can't ask to have 0 or less MSIs configured.
+	 *  a) it's stupid ..
+	 *  b) the list manipulation code assumes nvec >= 1.
+	 */
+	if (nvec < 1)
+		return 0;
+
+	/*
+	 * Any bridge which does NOT route MSI transactions from its
+	 * secondary bus to its primary bus must set NO_MSI flag on
+	 * the secondary pci_bus.
+	 *
+	 * The NO_MSI flag can either be set directly by:
+	 * - arch-specific PCI host bus controller drivers (deprecated)
+	 * - quirks for specific PCI bridges
+	 *
+	 * or indirectly by platform-specific PCI host bridge drivers by
+	 * advertising the 'msi_domain' property, which results in
+	 * the NO_MSI flag when no MSI domain is found for this bridge
+	 * at probe time.
+	 */
+	for (bus = dev->bus; bus; bus = bus->parent)
+		if (bus->bus_flags & PCI_BUS_FLAGS_NO_MSI)
+			return 0;
+
+	return 1;
+}
+
+static void pcim_msi_release(void *pcidev)
+{
+	struct pci_dev *dev = pcidev;
+
+	dev->is_msi_managed = false;
+	pci_free_irq_vectors(dev);
+}
+
+/*
+ * Needs to be separate from pcim_release to prevent an ordering problem
+ * vs. msi_device_data_release() in the MSI core code.
+ *
+ * TODO: Remove the legacy side-effect of pcim_enable_device() that
+ * activates automatic IRQ vector management. This design is dangerous
+ * and confusing because it switches normally un-managed functions
+ * into managed mode. Drivers should explicitly manage their IRQ vectors
+ * without this implicit behavior.
+ *
+ * The current implementation uses both pdev->is_managed and
+ * pdev->is_msi_managed flags, which adds unnecessary complexity.
+ * This should be simplified in a future kernel version.
+ */
+static int pcim_setup_msi_release(struct pci_dev *dev)
+{
+	int ret;
+
+	if (!pci_is_managed(dev) || dev->is_msi_managed)
+		return 0;
+
+	ret = devm_add_action(&dev->dev, pcim_msi_release, dev);
+	if (ret)
+		return ret;
+
+	dev->is_msi_managed = true;
+	return 0;
+}
+
+/*
+ * Ordering vs. devres: msi device data has to be installed first so that
+ * pcim_msi_release() is invoked before it on device release.
+ */
+static int pci_setup_msi_context(struct pci_dev *dev)
+{
+	int ret = msi_setup_device_data(&dev->dev);
+
+	if (ret)
+		return ret;
+
+	return pcim_setup_msi_release(dev);
+}
+
+/*
+ * Helper functions for mask/unmask and MSI message handling
+ */
+
+void pci_msi_update_mask(struct msi_desc *desc, u32 clear, u32 set)
+{
+	struct pci_dev *dev = msi_desc_to_pci_dev(desc);
+	raw_spinlock_t *lock = &dev->msi_lock;
+	unsigned long flags;
+
+	if (!desc->pci.msi_attrib.can_mask)
+		return;
+
+	raw_spin_lock_irqsave(lock, flags);
+	desc->pci.msi_mask &= ~clear;
+	desc->pci.msi_mask |= set;
+	pci_write_config_dword(dev, desc->pci.mask_pos, desc->pci.msi_mask);
+	raw_spin_unlock_irqrestore(lock, flags);
+}
+
+/**
+ * pci_msi_mask_irq - Generic IRQ chip callback to mask PCI/MSI interrupts
+ * @data:	pointer to irqdata associated to that interrupt
+ */
+void pci_msi_mask_irq(struct irq_data *data)
+{
+	struct msi_desc *desc = irq_data_get_msi_desc(data);
+
+	__pci_msi_mask_desc(desc, BIT(data->irq - desc->irq));
+}
+EXPORT_SYMBOL_GPL(pci_msi_mask_irq);
+
+/**
+ * pci_msi_unmask_irq - Generic IRQ chip callback to unmask PCI/MSI interrupts
+ * @data:	pointer to irqdata associated to that interrupt
+ */
+void pci_msi_unmask_irq(struct irq_data *data)
+{
+	struct msi_desc *desc = irq_data_get_msi_desc(data);
+
+	__pci_msi_unmask_desc(desc, BIT(data->irq - desc->irq));
+}
+EXPORT_SYMBOL_GPL(pci_msi_unmask_irq);
+
+void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
+{
+	struct pci_dev *dev = msi_desc_to_pci_dev(entry);
+
+	BUG_ON(dev->current_state != PCI_D0);
+
+	if (entry->pci.msi_attrib.is_msix) {
+		void __iomem *base = pci_msix_desc_addr(entry);
+
+		if (WARN_ON_ONCE(entry->pci.msi_attrib.is_virtual))
+			return;
+
+		msg->address_lo = readl(base + PCI_MSIX_ENTRY_LOWER_ADDR);
+		msg->address_hi = readl(base + PCI_MSIX_ENTRY_UPPER_ADDR);
+		msg->data = readl(base + PCI_MSIX_ENTRY_DATA);
+	} else {
+		int pos = dev->msi_cap;
+		u16 data;
+
+		pci_read_config_dword(dev, pos + PCI_MSI_ADDRESS_LO,
+				      &msg->address_lo);
+		if (entry->pci.msi_attrib.is_64) {
+			pci_read_config_dword(dev, pos + PCI_MSI_ADDRESS_HI,
+					      &msg->address_hi);
+			pci_read_config_word(dev, pos + PCI_MSI_DATA_64, &data);
+		} else {
+			msg->address_hi = 0;
+			pci_read_config_word(dev, pos + PCI_MSI_DATA_32, &data);
+		}
+		msg->data = data;
+	}
+}
+
+static inline void pci_write_msg_msi(struct pci_dev *dev, struct msi_desc *desc,
+				     struct msi_msg *msg)
+{
+	int pos = dev->msi_cap;
+	u16 msgctl;
+
+	pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &msgctl);
+	FIELD_MODIFY(PCI_MSI_FLAGS_QSIZE, &msgctl, desc->pci.msi_attrib.multiple);
+	pci_write_config_word(dev, pos + PCI_MSI_FLAGS, msgctl);
+
+	pci_write_config_dword(dev, pos + PCI_MSI_ADDRESS_LO, msg->address_lo);
+	if (desc->pci.msi_attrib.is_64) {
+		pci_write_config_dword(dev, pos + PCI_MSI_ADDRESS_HI,  msg->address_hi);
+		pci_write_config_word(dev, pos + PCI_MSI_DATA_64, msg->data);
+	} else {
+		pci_write_config_word(dev, pos + PCI_MSI_DATA_32, msg->data);
+	}
+	/* Ensure that the writes are visible in the device */
+	pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &msgctl);
+}
+
+static inline void pci_write_msg_msix(struct msi_desc *desc, struct msi_msg *msg)
+{
+	void __iomem *base = pci_msix_desc_addr(desc);
+	u32 ctrl = desc->pci.msix_ctrl;
+	bool unmasked = !(ctrl & PCI_MSIX_ENTRY_CTRL_MASKBIT);
+
+	if (desc->pci.msi_attrib.is_virtual)
+		return;
+	/*
+	 * The specification mandates that the entry is masked
+	 * when the message is modified:
+	 *
+	 * "If software changes the Address or Data value of an
+	 * entry while the entry is unmasked, the result is
+	 * undefined."
+	 */
+	if (unmasked)
+		pci_msix_write_vector_ctrl(desc, ctrl | PCI_MSIX_ENTRY_CTRL_MASKBIT);
+
+	writel(msg->address_lo, base + PCI_MSIX_ENTRY_LOWER_ADDR);
+	writel(msg->address_hi, base + PCI_MSIX_ENTRY_UPPER_ADDR);
+	writel(msg->data, base + PCI_MSIX_ENTRY_DATA);
+
+	if (unmasked)
+		pci_msix_write_vector_ctrl(desc, ctrl);
+
+	/* Ensure that the writes are visible in the device */
+	readl(base + PCI_MSIX_ENTRY_DATA);
+}
+
+void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
+{
+	struct pci_dev *dev = msi_desc_to_pci_dev(entry);
+
+	if (dev->current_state != PCI_D0 || pci_dev_is_disconnected(dev)) {
+		/* Don't touch the hardware now */
+	} else if (entry->pci.msi_attrib.is_msix) {
+		pci_write_msg_msix(entry, msg);
+	} else {
+		pci_write_msg_msi(dev, entry, msg);
+	}
+
+	entry->msg = *msg;
+
+	if (entry->write_msi_msg)
+		entry->write_msi_msg(entry, entry->write_msi_msg_data);
+}
+
+void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg)
+{
+	struct msi_desc *entry = irq_get_msi_desc(irq);
+
+	__pci_write_msi_msg(entry, msg);
+}
+EXPORT_SYMBOL_GPL(pci_write_msi_msg);
+
+
+/* PCI/MSI specific functionality */
+
+static void pci_intx_for_msi(struct pci_dev *dev, int enable)
+{
+	if (!(dev->dev_flags & PCI_DEV_FLAGS_MSI_INTX_DISABLE_BUG))
+		pci_intx(dev, enable);
+}
+
+static void pci_msi_set_enable(struct pci_dev *dev, int enable)
+{
+	u16 control;
+
+	pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control);
+	control &= ~PCI_MSI_FLAGS_ENABLE;
+	if (enable)
+		control |= PCI_MSI_FLAGS_ENABLE;
+	pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, control);
+}
+
+static int msi_setup_msi_desc(struct pci_dev *dev, int nvec,
+			      struct irq_affinity_desc *masks)
+{
+	struct msi_desc desc;
+	u16 control;
+
+	/* MSI Entry Initialization */
+	memset(&desc, 0, sizeof(desc));
+
+	pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control);
+	/* Lies, damned lies, and MSIs */
+	if (dev->dev_flags & PCI_DEV_FLAGS_HAS_MSI_MASKING)
+		control |= PCI_MSI_FLAGS_MASKBIT;
+	if (pci_msi_domain_supports(dev, MSI_FLAG_NO_MASK, DENY_LEGACY))
+		control &= ~PCI_MSI_FLAGS_MASKBIT;
+
+	desc.nvec_used			= nvec;
+	desc.pci.msi_attrib.is_64	= !!(control & PCI_MSI_FLAGS_64BIT);
+	desc.pci.msi_attrib.can_mask	= !!(control & PCI_MSI_FLAGS_MASKBIT);
+	desc.pci.msi_attrib.default_irq	= dev->irq;
+	desc.pci.msi_attrib.multi_cap	= FIELD_GET(PCI_MSI_FLAGS_QMASK, control);
+	desc.pci.msi_attrib.multiple	= ilog2(__roundup_pow_of_two(nvec));
+	desc.affinity			= masks;
+
+	if (control & PCI_MSI_FLAGS_64BIT)
+		desc.pci.mask_pos = dev->msi_cap + PCI_MSI_MASK_64;
+	else
+		desc.pci.mask_pos = dev->msi_cap + PCI_MSI_MASK_32;
+
+	/* Save the initial mask status */
+	if (desc.pci.msi_attrib.can_mask)
+		pci_read_config_dword(dev, desc.pci.mask_pos, &desc.pci.msi_mask);
+
+	return msi_insert_msi_desc(&dev->dev, &desc);
+}
+
+static int msi_verify_entries(struct pci_dev *dev)
+{
+	struct msi_desc *entry;
+	u64 address;
+
+	if (dev->msi_addr_mask == DMA_BIT_MASK(64))
+		return 0;
+
+	msi_for_each_desc(entry, &dev->dev, MSI_DESC_ALL) {
+		address = (u64)entry->msg.address_hi << 32 | entry->msg.address_lo;
+		if (address & ~dev->msi_addr_mask) {
+			pci_err(dev, "arch assigned 64-bit MSI address %#llx above device MSI address mask %#llx\n",
+				address, dev->msi_addr_mask);
+			break;
+		}
+	}
+	return !entry ? 0 : -EIO;
+}
+
+static int __msi_capability_init(struct pci_dev *dev, int nvec, struct irq_affinity_desc *masks)
+{
+	int ret = msi_setup_msi_desc(dev, nvec, masks);
+	struct msi_desc *entry, desc;
+
+	if (ret)
+		return ret;
+
+	/* All MSIs are unmasked by default; mask them all */
+	entry = msi_first_desc(&dev->dev, MSI_DESC_ALL);
+	pci_msi_mask(entry, msi_multi_mask(entry));
+	/*
+	 * Copy the MSI descriptor for the error path because
+	 * pci_msi_setup_msi_irqs() will free it for the hierarchical
+	 * interrupt domain case.
+	 */
+	memcpy(&desc, entry, sizeof(desc));
+
+	/* Configure MSI capability structure */
+	ret = pci_msi_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSI);
+	if (ret)
+		goto err;
+
+	ret = msi_verify_entries(dev);
+	if (ret)
+		goto err;
+
+	/* Set MSI enabled bits	*/
+	dev->msi_enabled = 1;
+	pci_intx_for_msi(dev, 0);
+	pci_msi_set_enable(dev, 1);
+
+	pcibios_free_irq(dev);
+	dev->irq = entry->irq;
+	return 0;
+err:
+	pci_msi_unmask(&desc, msi_multi_mask(&desc));
+	pci_free_msi_irqs(dev);
+	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);
+
+	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)
+{
+	int nvec;
+	int rc;
+
+	if (!pci_msi_supported(dev, minvec) || dev->current_state != PCI_D0)
+		return -EINVAL;
+
+	/* Check whether driver already requested MSI-X IRQs */
+	if (dev->msix_enabled) {
+		pci_info(dev, "can't enable MSI (MSI-X already enabled)\n");
+		return -EINVAL;
+	}
+
+	if (maxvec < minvec)
+		return -ERANGE;
+
+	if (WARN_ON_ONCE(dev->msi_enabled))
+		return -EINVAL;
+
+	/* Test for the availability of MSI support */
+	if (!pci_msi_domain_supports(dev, 0, ALLOW_LEGACY))
+		return -ENOTSUPP;
+
+	nvec = pci_msi_vec_count(dev);
+	if (nvec < 0)
+		return nvec;
+	if (nvec < minvec)
+		return -ENOSPC;
+
+	rc = pci_setup_msi_context(dev);
+	if (rc)
+		return rc;
+
+	if (!pci_setup_msi_device_domain(dev, nvec))
+		return -ENODEV;
+
+	if (nvec > maxvec)
+		nvec = maxvec;
+
+	for (;;) {
+		if (affd) {
+			nvec = irq_calc_affinity_vectors(minvec, nvec, affd);
+			if (nvec < minvec)
+				return -ENOSPC;
+		}
+
+		rc = msi_capability_init(dev, nvec, affd);
+		if (rc == 0)
+			return nvec;
+
+		if (rc < 0)
+			return rc;
+		if (rc < minvec)
+			return -ENOSPC;
+
+		nvec = rc;
+	}
+}
+
+/**
+ * pci_msi_vec_count - Return the number of MSI vectors a device can send
+ * @dev: device to report about
+ *
+ * This function returns the number of MSI vectors a device requested via
+ * Multiple Message Capable register. It returns a negative errno if the
+ * device is not capable sending MSI interrupts. Otherwise, the call succeeds
+ * and returns a power of two, up to a maximum of 2^5 (32), according to the
+ * MSI specification.
+ **/
+int pci_msi_vec_count(struct pci_dev *dev)
+{
+	int ret;
+	u16 msgctl;
+
+	if (!dev->msi_cap)
+		return -EINVAL;
+
+	pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &msgctl);
+	ret = 1 << FIELD_GET(PCI_MSI_FLAGS_QMASK, msgctl);
+
+	return ret;
+}
+EXPORT_SYMBOL(pci_msi_vec_count);
+
+/*
+ * Architecture override returns true when the PCI MSI message should be
+ * written by the generic restore function.
+ */
+bool __weak arch_restore_msi_irqs(struct pci_dev *dev)
+{
+	return true;
+}
+
+void __pci_restore_msi_state(struct pci_dev *dev)
+{
+	struct msi_desc *entry;
+	u16 control;
+
+	if (!dev->msi_enabled)
+		return;
+
+	entry = irq_get_msi_desc(dev->irq);
+
+	pci_intx_for_msi(dev, 0);
+	pci_msi_set_enable(dev, 0);
+	if (arch_restore_msi_irqs(dev))
+		__pci_write_msi_msg(entry, &entry->msg);
+
+	pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control);
+	pci_msi_update_mask(entry, 0, 0);
+	FIELD_MODIFY(PCI_MSI_FLAGS_QSIZE, &control, entry->pci.msi_attrib.multiple);
+	control |= PCI_MSI_FLAGS_ENABLE;
+	pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, control);
+}
+
+void pci_msi_shutdown(struct pci_dev *dev)
+{
+	struct msi_desc *desc;
+
+	if (!pci_msi_enable || !dev || !dev->msi_enabled)
+		return;
+
+	pci_msi_set_enable(dev, 0);
+	pci_intx_for_msi(dev, 1);
+	dev->msi_enabled = 0;
+
+	/* Return the device with MSI unmasked as initial states */
+	desc = msi_first_desc(&dev->dev, MSI_DESC_ALL);
+	if (!WARN_ON_ONCE(!desc))
+		pci_msi_unmask(desc, msi_multi_mask(desc));
+
+	/* Restore dev->irq to its default pin-assertion IRQ */
+	dev->irq = desc->pci.msi_attrib.default_irq;
+	pcibios_alloc_irq(dev);
+}
+
+/* PCI/MSI-X specific functionality */
+
+static void pci_msix_clear_and_set_ctrl(struct pci_dev *dev, u16 clear, u16 set)
+{
+	u16 ctrl;
+
+	pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &ctrl);
+	ctrl &= ~clear;
+	ctrl |= set;
+	pci_write_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, ctrl);
+}
+
+static void __iomem *msix_map_region(struct pci_dev *dev,
+				     unsigned int nr_entries)
+{
+	resource_size_t phys_addr;
+	u32 table_offset;
+	unsigned long flags;
+	u8 bir;
+
+	pci_read_config_dword(dev, dev->msix_cap + PCI_MSIX_TABLE,
+			      &table_offset);
+	bir = (u8)(table_offset & PCI_MSIX_TABLE_BIR);
+	flags = pci_resource_flags(dev, bir);
+	if (!flags || (flags & IORESOURCE_UNSET))
+		return NULL;
+
+	table_offset &= PCI_MSIX_TABLE_OFFSET;
+	phys_addr = pci_resource_start(dev, bir) + table_offset;
+
+	return ioremap(phys_addr, nr_entries * PCI_MSIX_ENTRY_SIZE);
+}
+
+/**
+ * msix_prepare_msi_desc - Prepare a half initialized MSI descriptor for operation
+ * @dev:	The PCI device for which the descriptor is prepared
+ * @desc:	The MSI descriptor for preparation
+ *
+ * This is separate from msix_setup_msi_descs() below to handle dynamic
+ * allocations for MSI-X after initial enablement.
+ *
+ * Ideally the whole MSI-X setup would work that way, but there is no way to
+ * support this for the legacy arch_setup_msi_irqs() mechanism and for the
+ * fake irq domains like the x86 XEN one. Sigh...
+ *
+ * The descriptor is zeroed and only @desc::msi_index and @desc::affinity
+ * are set. When called from msix_setup_msi_descs() then the is_virtual
+ * attribute is initialized as well.
+ *
+ * Fill in the rest.
+ */
+void msix_prepare_msi_desc(struct pci_dev *dev, struct msi_desc *desc)
+{
+	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;
+
+
+	if (!pci_msi_domain_supports(dev, MSI_FLAG_NO_MASK, DENY_LEGACY) &&
+	    !desc->pci.msi_attrib.is_virtual) {
+		void __iomem *addr = pci_msix_desc_addr(desc);
+
+		desc->pci.msi_attrib.can_mask = 1;
+		/* Workaround for SUN NIU insanity, which requires write before read */
+		if (dev->dev_flags & PCI_DEV_FLAGS_MSIX_TOUCH_ENTRY_DATA_FIRST)
+			writel(0, addr + PCI_MSIX_ENTRY_DATA);
+		desc->pci.msix_ctrl = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL);
+	}
+}
+
+static int msix_setup_msi_descs(struct pci_dev *dev, struct msix_entry *entries,
+				int nvec, struct irq_affinity_desc *masks)
+{
+	int ret = 0, i, vec_count = pci_msix_vec_count(dev);
+	struct irq_affinity_desc *curmsk;
+	struct msi_desc desc;
+
+	memset(&desc, 0, sizeof(desc));
+
+	for (i = 0, curmsk = masks; i < nvec; i++, curmsk++) {
+		desc.msi_index = entries ? entries[i].entry : i;
+		desc.affinity = masks ? curmsk : NULL;
+		desc.pci.msi_attrib.is_virtual = desc.msi_index >= vec_count;
+
+		msix_prepare_msi_desc(dev, &desc);
+
+		ret = msi_insert_msi_desc(&dev->dev, &desc);
+		if (ret)
+			break;
+	}
+	return ret;
+}
+
+static void msix_update_entries(struct pci_dev *dev, struct msix_entry *entries)
+{
+	struct msi_desc *desc;
+
+	if (entries) {
+		msi_for_each_desc(desc, &dev->dev, MSI_DESC_ALL) {
+			entries->vector = desc->irq;
+			entries++;
+		}
+	}
+}
+
+static void msix_mask_all(void __iomem *base, int tsize)
+{
+	u32 ctrl = PCI_MSIX_ENTRY_CTRL_MASKBIT;
+	int i;
+
+	for (i = 0; i < tsize; i++, base += PCI_MSIX_ENTRY_SIZE)
+		writel(ctrl, base + PCI_MSIX_ENTRY_VECTOR_CTRL);
+}
+
+DEFINE_FREE(free_msi_irqs, struct pci_dev *, if (_T) pci_free_msi_irqs(_T));
+
+static int __msix_setup_interrupts(struct pci_dev *__dev, struct msix_entry *entries,
+				   int nvec, struct irq_affinity_desc *masks)
+{
+	struct pci_dev *dev __free(free_msi_irqs) = __dev;
+
+	int ret = msix_setup_msi_descs(dev, entries, nvec, masks);
+	if (ret)
+		return ret;
+
+	ret = pci_msi_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSIX);
+	if (ret)
+		return ret;
+
+	/* Check if all MSI entries honor device restrictions */
+	ret = msi_verify_entries(dev);
+	if (ret)
+		return ret;
+
+	msix_update_entries(dev, entries);
+	retain_and_null_ptr(dev);
+	return 0;
+}
+
+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
+ * @entries: pointer to an array of struct msix_entry entries
+ * @nvec: number of @entries
+ * @affd: Optional pointer to enable automatic affinity assignment
+ *
+ * Setup the MSI-X capability structure of device function with a
+ * single MSI-X IRQ. A return of zero indicates the successful setup of
+ * requested MSI-X entries with allocated IRQs or non-zero for otherwise.
+ **/
+static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
+				int nvec, struct irq_affinity *affd)
+{
+	int ret, tsize;
+	u16 control;
+
+	/*
+	 * Some devices require MSI-X to be enabled before the MSI-X
+	 * registers can be accessed.  Mask all the vectors to prevent
+	 * interrupts coming in before they're fully set up.
+	 */
+	pci_msix_clear_and_set_ctrl(dev, 0, PCI_MSIX_FLAGS_MASKALL |
+				    PCI_MSIX_FLAGS_ENABLE);
+
+	/* Mark it enabled so setup functions can query it */
+	dev->msix_enabled = 1;
+
+	pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &control);
+	/* Request & Map MSI-X table region */
+	tsize = msix_table_size(control);
+	dev->msix_base = msix_map_region(dev, tsize);
+	if (!dev->msix_base) {
+		ret = -ENOMEM;
+		goto out_disable;
+	}
+
+	ret = msix_setup_interrupts(dev, entries, nvec, affd);
+	if (ret)
+		goto out_disable;
+
+	/* Disable INTX */
+	pci_intx_for_msi(dev, 0);
+
+	if (!pci_msi_domain_supports(dev, MSI_FLAG_NO_MASK, DENY_LEGACY)) {
+		/*
+		 * 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);
+	return 0;
+
+out_disable:
+	dev->msix_enabled = 0;
+	pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL | PCI_MSIX_FLAGS_ENABLE, 0);
+
+	return ret;
+}
+
+static bool pci_msix_validate_entries(struct pci_dev *dev, struct msix_entry *entries, int nvec)
+{
+	bool nogap;
+	int i, j;
+
+	if (!entries)
+		return true;
+
+	nogap = pci_msi_domain_supports(dev, MSI_FLAG_MSIX_CONTIGUOUS, DENY_LEGACY);
+
+	for (i = 0; i < nvec; i++) {
+		/* Check for duplicate entries */
+		for (j = i + 1; j < nvec; j++) {
+			if (entries[i].entry == entries[j].entry)
+				return false;
+		}
+		/* Check for unsupported gaps */
+		if (nogap && entries[i].entry != i)
+			return false;
+	}
+	return true;
+}
+
+int __pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int minvec,
+			    int maxvec, struct irq_affinity *affd, int flags)
+{
+	int hwsize, rc, nvec = maxvec;
+
+	if (maxvec < minvec)
+		return -ERANGE;
+
+	if (dev->msi_enabled) {
+		pci_info(dev, "can't enable MSI-X (MSI already enabled)\n");
+		return -EINVAL;
+	}
+
+	if (WARN_ON_ONCE(dev->msix_enabled))
+		return -EINVAL;
+
+	/* Check MSI-X early on irq domain enabled architectures */
+	if (!pci_msi_domain_supports(dev, MSI_FLAG_PCI_MSIX, ALLOW_LEGACY))
+		return -ENOTSUPP;
+
+	if (!pci_msi_supported(dev, nvec) || dev->current_state != PCI_D0)
+		return -EINVAL;
+
+	hwsize = pci_msix_vec_count(dev);
+	if (hwsize < 0)
+		return hwsize;
+
+	if (!pci_msix_validate_entries(dev, entries, nvec))
+		return -EINVAL;
+
+	if (hwsize < nvec) {
+		/* Keep the IRQ virtual hackery working */
+		if (flags & PCI_IRQ_VIRTUAL)
+			hwsize = nvec;
+		else
+			nvec = hwsize;
+	}
+
+	if (nvec < minvec)
+		return -ENOSPC;
+
+	rc = pci_setup_msi_context(dev);
+	if (rc)
+		return rc;
+
+	if (!pci_setup_msix_device_domain(dev, hwsize))
+		return -ENODEV;
+
+	for (;;) {
+		if (affd) {
+			nvec = irq_calc_affinity_vectors(minvec, nvec, affd);
+			if (nvec < minvec)
+				return -ENOSPC;
+		}
+
+		rc = msix_capability_init(dev, entries, nvec, affd);
+		if (rc == 0)
+			return nvec;
+
+		if (rc < 0)
+			return rc;
+		if (rc < minvec)
+			return -ENOSPC;
+
+		nvec = rc;
+	}
+}
+
+void __pci_restore_msix_state(struct pci_dev *dev)
+{
+	struct msi_desc *entry;
+	bool write_msg;
+	u16 cmd;
+
+	if (!dev->msix_enabled)
+		return;
+
+	/* route the table */
+	pci_intx_for_msi(dev, 0);
+	pci_msix_clear_and_set_ctrl(dev, 0,
+				PCI_MSIX_FLAGS_ENABLE | PCI_MSIX_FLAGS_MASKALL);
+
+	/*
+	 * The restored device state may not have Memory Space enabled.
+	 * Since the MSI-X Table and PBA are in Memory Space, enable it
+	 * while restoring them.
+	 */
+	pci_read_config_word(dev, PCI_COMMAND, &cmd);
+	pci_write_config_word(dev, PCI_COMMAND, cmd | PCI_COMMAND_MEMORY);
+
+	write_msg = arch_restore_msi_irqs(dev);
+
+	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);
+		}
+	}
+
+	pci_write_config_word(dev, PCI_COMMAND, cmd);
+	pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0);
+}
+
+void pci_msix_shutdown(struct pci_dev *dev)
+{
+	struct msi_desc *desc;
+
+	if (!pci_msi_enable || !dev || !dev->msix_enabled)
+		return;
+
+	if (pci_dev_is_disconnected(dev)) {
+		dev->msix_enabled = 0;
+		return;
+	}
+
+	/* Return the device with MSI-X masked as initial states */
+	msi_for_each_desc(desc, &dev->dev, MSI_DESC_ALL)
+		pci_msix_mask(desc);
+
+	pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0);
+	pci_intx_for_msi(dev, 1);
+	dev->msix_enabled = 0;
+	pcibios_alloc_irq(dev);
+}
+
+/* Common interfaces */
+
+void pci_free_msi_irqs(struct pci_dev *dev)
+{
+	pci_msi_teardown_msi_irqs(dev);
+
+	if (dev->msix_base) {
+		iounmap(dev->msix_base);
+		dev->msix_base = NULL;
+	}
+}
+
+#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;
+
+	virq = msi_get_virq(&pdev->dev, index);
+	if (!virq)
+		return -ENXIO;
+
+	guard(msi_descs_lock)(&pdev->dev);
+
+	/*
+	 * 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 nuisance. 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;
+
+	FIELD_MODIFY(PCI_MSIX_ENTRY_CTRL_ST, &msi_desc->pci.msix_ctrl, 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)
+{
+	return to_pci_dev(desc->dev);
+}
+EXPORT_SYMBOL(msi_desc_to_pci_dev);
+
+void pci_no_msi(void)
+{
+	pci_msi_enable = false;
+}
diff --git a/drivers/pci/msi/msi.h b/drivers/pci/msi/msi.h
new file mode 100644
index 000000000..0b420b319
--- /dev/null
+++ b/drivers/pci/msi/msi.h
@@ -0,0 +1,129 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/pci.h>
+#include <linux/msi.h>
+
+#define msix_table_size(flags)	((flags & PCI_MSIX_FLAGS_QSIZE) + 1)
+
+int pci_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type);
+void pci_msi_teardown_msi_irqs(struct pci_dev *dev);
+
+/* Mask/unmask helpers */
+void pci_msi_update_mask(struct msi_desc *desc, u32 clear, u32 set);
+
+static inline void pci_msi_mask(struct msi_desc *desc, u32 mask)
+{
+	pci_msi_update_mask(desc, 0, mask);
+}
+
+static inline void pci_msi_unmask(struct msi_desc *desc, u32 mask)
+{
+	pci_msi_update_mask(desc, mask, 0);
+}
+
+static inline void __iomem *pci_msix_desc_addr(struct msi_desc *desc)
+{
+	return desc->pci.mask_base + desc->msi_index * PCI_MSIX_ENTRY_SIZE;
+}
+
+/*
+ * This internal function does not flush PCI writes to the device.  All
+ * users must ensure that they read from the device before either assuming
+ * that the device state is up to date, or returning out of this file.
+ * It does not affect the msi_desc::msix_ctrl cache either. Use with care!
+ */
+static inline void pci_msix_write_vector_ctrl(struct msi_desc *desc, u32 ctrl)
+{
+	void __iomem *desc_addr = pci_msix_desc_addr(desc);
+
+	if (desc->pci.msi_attrib.can_mask)
+		writel(ctrl, desc_addr + PCI_MSIX_ENTRY_VECTOR_CTRL);
+}
+
+static inline void pci_msix_mask(struct msi_desc *desc)
+{
+	desc->pci.msix_ctrl |= PCI_MSIX_ENTRY_CTRL_MASKBIT;
+	pci_msix_write_vector_ctrl(desc, desc->pci.msix_ctrl);
+	/* Flush write to device */
+	readl(desc->pci.mask_base);
+}
+
+static inline void pci_msix_unmask(struct msi_desc *desc)
+{
+	desc->pci.msix_ctrl &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT;
+	pci_msix_write_vector_ctrl(desc, desc->pci.msix_ctrl);
+}
+
+static inline void __pci_msi_mask_desc(struct msi_desc *desc, u32 mask)
+{
+	if (desc->pci.msi_attrib.is_msix)
+		pci_msix_mask(desc);
+	else
+		pci_msi_mask(desc, mask);
+}
+
+static inline void __pci_msi_unmask_desc(struct msi_desc *desc, u32 mask)
+{
+	if (desc->pci.msi_attrib.is_msix)
+		pci_msix_unmask(desc);
+	else
+		pci_msi_unmask(desc, mask);
+}
+
+/*
+ * PCI 2.3 does not specify mask bits for each MSI interrupt.  Attempting to
+ * mask all MSI interrupts by clearing the MSI enable bit does not work
+ * reliably as devices without an INTx disable bit will then generate a
+ * level IRQ which will never be cleared.
+ */
+static inline __attribute_const__ u32 msi_multi_mask(struct msi_desc *desc)
+{
+	/* Don't shift by >= width of type */
+	if (desc->pci.msi_attrib.multi_cap >= 5)
+		return 0xffffffff;
+	return (1 << (1 << desc->pci.msi_attrib.multi_cap)) - 1;
+}
+
+void msix_prepare_msi_desc(struct pci_dev *dev, struct msi_desc *desc);
+
+/* Subsystem variables */
+extern bool pci_msi_enable;
+
+/* MSI internal functions invoked from the public APIs */
+void pci_msi_shutdown(struct pci_dev *dev);
+void pci_msix_shutdown(struct pci_dev *dev);
+void pci_free_msi_irqs(struct pci_dev *dev);
+int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, struct irq_affinity *affd);
+int __pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int minvec,
+			    int maxvec,  struct irq_affinity *affd, int flags);
+void __pci_restore_msi_state(struct pci_dev *dev);
+void __pci_restore_msix_state(struct pci_dev *dev);
+
+/* irq_domain related functionality */
+
+enum support_mode {
+	ALLOW_LEGACY,
+	DENY_LEGACY,
+};
+
+bool pci_msi_domain_supports(struct pci_dev *dev, unsigned int feature_mask, enum support_mode mode);
+bool pci_setup_msi_device_domain(struct pci_dev *pdev, unsigned int hwsize);
+bool pci_setup_msix_device_domain(struct pci_dev *pdev, unsigned int hwsize);
+
+/* Legacy (!IRQDOMAIN) fallbacks */
+
+#ifdef CONFIG_PCI_MSI_ARCH_FALLBACKS
+int pci_msi_legacy_setup_msi_irqs(struct pci_dev *dev, int nvec, int type);
+void pci_msi_legacy_teardown_msi_irqs(struct pci_dev *dev);
+#else
+static inline int pci_msi_legacy_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+	WARN_ON_ONCE(1);
+	return -ENODEV;
+}
+
+static inline void pci_msi_legacy_teardown_msi_irqs(struct pci_dev *dev)
+{
+	WARN_ON_ONCE(1);
+}
+#endif
diff --git a/drivers/pci/msi/pcidev_msi.c b/drivers/pci/msi/pcidev_msi.c
new file mode 100644
index 000000000..0b0346813
--- /dev/null
+++ b/drivers/pci/msi/pcidev_msi.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * MSI[X} related functions which are available unconditionally.
+ */
+#include "../pci.h"
+
+/*
+ * Disable the MSI[X] hardware to avoid screaming interrupts during boot.
+ * This is the power on reset default so usually this should be a noop.
+ */
+
+void pci_msi_init(struct pci_dev *dev)
+{
+	u16 ctrl;
+
+	dev->msi_cap = pci_find_capability(dev, PCI_CAP_ID_MSI);
+	if (!dev->msi_cap)
+		return;
+
+	pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &ctrl);
+	if (ctrl & PCI_MSI_FLAGS_ENABLE) {
+		pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS,
+				      ctrl & ~PCI_MSI_FLAGS_ENABLE);
+	}
+
+	if (!(ctrl & PCI_MSI_FLAGS_64BIT))
+		dev->msi_addr_mask = DMA_BIT_MASK(32);
+}
+
+void pci_msix_init(struct pci_dev *dev)
+{
+	u16 ctrl;
+
+	dev->msix_cap = pci_find_capability(dev, PCI_CAP_ID_MSIX);
+	if (!dev->msix_cap)
+		return;
+
+	pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &ctrl);
+	if (ctrl & PCI_MSIX_FLAGS_ENABLE) {
+		pci_write_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS,
+				      ctrl & ~PCI_MSIX_FLAGS_ENABLE);
+	}
+}