Merge branch 'pci/resource'

- Use pci_resource_n() to simplify BAR/window resource lookup (Ilpo
  Järvinen)

- Fix typo that repeatedly distributed resources to a bridge instead of
  iterating over subordinate bridges, which resulted in too little space to
  assign some BARs (Kai-Heng Feng)

- Relax bridge window tail sizing for optional resources, e.g., IOV BARs,
  to avoid failures when removing and re-adding devices (Ilpo Järvinen)

- Fix a double counting error for I/O resources, as we previously did for
  memory resources (Ilpo Järvinen)

- Use resource_set_{range,size}() helpers in more places (Ilpo Järvinen)

- Add pci_resource_is_iov() to identify IOV resources (Ilpo Järvinen)

- Add pci_resource_num() to look up the BAR number from the resource
  pointer (Ilpo Järvinen)

- Add restore_dev_resource() to simplify code that resources saved device
  resources (Ilpo Järvinen)

- Allow drivers to enable devices even if we haven't assigned optional IOV
  resources to them (Ilpo Järvinen)

- Improve debug output during resource reallocation (Ilpo Järvinen)

- Rework handling of optional resources (IOV BARs, ROMs) to reduce failures
  if we can't allocate them (Ilpo Järvinen)

- Move declarations of pci_rescan_bus_bridge_resize(),
  pci_reassign_bridge_resources(), and CardBus-related sizes from
  include/linux/pci.h to drivers/pci/pci.h since they're not used outside
  the PCI core (Ilpo Järvinen)

- Make pci_setup_bridge() static (Ilpo Järvinen)

- Fix a NULL dereference in the SR-IOV VF creation error path (Shay Drory)

- Fix s390 mmio_read/write syscalls, which didn't cause page faults in some
  cases, which broke vfio-pci lazy mapping on first access (Niklas
  Schnelle)

- Add pdev->non_mappable_bars to replace CONFIG_VFIO_PCI_MMAP, which was
  disabled only for s390 (Niklas Schnelle)

- Support mmap of PCI resources on s390 except for ISM devices (Niklas
  Schnelle)

* pci/resource:
  s390/pci: Support mmap() of PCI resources except for ISM devices
  s390/pci: Introduce pdev->non_mappable_bars and replace VFIO_PCI_MMAP
  s390/pci: Fix s390_mmio_read/write syscall page fault handling
  PCI: Fix NULL dereference in SR-IOV VF creation error path
  PCI: Move cardbus IO size declarations into pci/pci.h
  PCI: Make pci_setup_bridge() static
  PCI: Move resource reassignment func declarations into pci/pci.h
  PCI: Move pci_rescan_bus_bridge_resize() declaration to pci/pci.h
  PCI: Fix BAR resizing when VF BARs are assigned
  PCI: Do not claim to release resource falsely
  PCI: Increase Resizable BAR support from 512 GB to 128 TB
  PCI: Rework optional resource handling
  PCI: Perform reset_resource() and build fail list in sync
  PCI: Use res->parent to check if resource is assigned
  PCI: Add debug print when releasing resources before retry
  PCI: Indicate optional resource assignment failures
  PCI: Always have realloc_head in __assign_resources_sorted()
  PCI: Extend enable to check for any optional resource
  PCI: Add restore_dev_resource()
  PCI: Remove incorrect comment from pci_reassign_resource()
  PCI: Consolidate assignment loop next round preparation
  PCI: Rename retval to ret
  PCI: Use while loop and break instead of gotos
  PCI: Refactor pdev_sort_resources() & __dev_sort_resources()
  PCI: Converge return paths in __assign_resources_sorted()
  PCI: Add dev & res local variables to resource assignment funcs
  PCI: Add pci_resource_num() helper
  PCI: Check resource_size() separately
  PCI: Add pci_resource_is_iov() to identify IOV resources
  PCI: Use resource_set_{range,size}() helpers
  PCI: Use SZ_* instead of literals in setup-bus.c
  PCI: Fix old_size lower bound in calculate_iosize() too
  PCI: Allow relaxed bridge window tail sizing for optional resources
  PCI: Simplify size1 assignment logic
  PCI: Use min_align, not unrelated add_align, for size0
  PCI: Remove add_align overwrite unrelated to size0
  PCI: Use downstream bridges for distributing resources
  PCI: Cleanup dev->resource + resno to use pci_resource_n()

Author: bjorn-helgaas

arch/s390/Kconfig

@@ -41,9 +41,6 @@ config AUDIT_ARCH
 config NO_IOPORT_MAP
 	def_bool y
 
-config PCI_QUIRKS
-	def_bool n
-
 config ARCH_SUPPORTS_UPROBES
 	def_bool y
 
@@ -258,6 +255,7 @@ config S390
 	select PCI_DOMAINS		if PCI
 	select PCI_MSI			if PCI
 	select PCI_MSI_ARCH_FALLBACKS	if PCI_MSI
+	select PCI_QUIRKS		if PCI
 	select SPARSE_IRQ
 	select SWIOTLB
 	select SYSCTL_EXCEPTION_TRACE

arch/s390/include/asm/pci.h

@@ -11,6 +11,9 @@
 #include <asm/pci_insn.h>
 #include <asm/sclp.h>
 
+#define ARCH_GENERIC_PCI_MMAP_RESOURCE	1
+#define arch_can_pci_mmap_wc()		1
+
 #define PCIBIOS_MIN_IO		0x1000
 #define PCIBIOS_MIN_MEM		0x10000000
 

arch/s390/pci/Makefile

@@ -5,6 +5,6 @@
 
 obj-$(CONFIG_PCI)	+= pci.o pci_irq.o pci_clp.o \
 			   pci_event.o pci_debug.o pci_insn.o pci_mmio.o \
-			   pci_bus.o pci_kvm_hook.o pci_report.o
+			   pci_bus.o pci_kvm_hook.o pci_report.o pci_fixup.o
 obj-$(CONFIG_PCI_IOV)	+= pci_iov.o
 obj-$(CONFIG_SYSFS)	+= pci_sysfs.o

arch/s390/pci/pci_fixup.c

@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Exceptions for specific devices,
+ *
+ * Copyright IBM Corp. 2025
+ *
+ * Author(s):
+ *   Niklas Schnelle <[email protected]>
+ */
+#include <linux/pci.h>
+
+static void zpci_ism_bar_no_mmap(struct pci_dev *pdev)
+{
+	/*
+	 * ISM's BAR is special. Drivers written for ISM know
+	 * how to handle this but others need to be aware of their
+	 * special nature e.g. to prevent attempts to mmap() it.
+	 */
+	pdev->non_mappable_bars = 1;
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_IBM,
+			PCI_DEVICE_ID_IBM_ISM,
+			zpci_ism_bar_no_mmap);

arch/s390/pci/pci_mmio.c

@@ -175,8 +175,12 @@ SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr,
 	args.address = mmio_addr;
 	args.vma = vma;
 	ret = follow_pfnmap_start(&args);
-	if (ret)
-		goto out_unlock_mmap;
+	if (ret) {
+		fixup_user_fault(current->mm, mmio_addr, FAULT_FLAG_WRITE, NULL);
+		ret = follow_pfnmap_start(&args);
+		if (ret)
+			goto out_unlock_mmap;
+	}
 
 	io_addr = (void __iomem *)((args.pfn << PAGE_SHIFT) |
 			(mmio_addr & ~PAGE_MASK));
@@ -315,14 +319,18 @@ SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr,
 	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
 		goto out_unlock_mmap;
 	ret = -EACCES;
-	if (!(vma->vm_flags & VM_WRITE))
+	if (!(vma->vm_flags & VM_READ))
 		goto out_unlock_mmap;
 
 	args.vma = vma;
 	args.address = mmio_addr;
 	ret = follow_pfnmap_start(&args);
-	if (ret)
-		goto out_unlock_mmap;
+	if (ret) {
+		fixup_user_fault(current->mm, mmio_addr, 0, NULL);
+		ret = follow_pfnmap_start(&args);
+		if (ret)
+			goto out_unlock_mmap;
+	}
 
 	io_addr = (void __iomem *)((args.pfn << PAGE_SHIFT) |
 			(mmio_addr & ~PAGE_MASK));

drivers/pci/iov.c

@@ -285,23 +285,16 @@ const struct attribute_group sriov_vf_dev_attr_group = {
 	.is_visible = sriov_vf_attrs_are_visible,
 };
 
-int pci_iov_add_virtfn(struct pci_dev *dev, int id)
+static struct pci_dev *pci_iov_scan_device(struct pci_dev *dev, int id,
+					   struct pci_bus *bus)
 {
-	int i;
-	int rc = -ENOMEM;
-	u64 size;
-	struct pci_dev *virtfn;
-	struct resource *res;
 	struct pci_sriov *iov = dev->sriov;
-	struct pci_bus *bus;
-
-	bus = virtfn_add_bus(dev->bus, pci_iov_virtfn_bus(dev, id));
-	if (!bus)
-		goto failed;
+	struct pci_dev *virtfn;
+	int rc;
 
 	virtfn = pci_alloc_dev(bus);
 	if (!virtfn)
-		goto failed0;
+		return ERR_PTR(-ENOMEM);
 
 	virtfn->devfn = pci_iov_virtfn_devfn(dev, id);
 	virtfn->vendor = dev->vendor;
@@ -314,8 +307,35 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id)
 		pci_read_vf_config_common(virtfn);
 
 	rc = pci_setup_device(virtfn);
-	if (rc)
-		goto failed1;
+	if (rc) {
+		pci_dev_put(dev);
+		pci_bus_put(virtfn->bus);
+		kfree(virtfn);
+		return ERR_PTR(rc);
+	}
+
+	return virtfn;
+}
+
+int pci_iov_add_virtfn(struct pci_dev *dev, int id)
+{
+	struct pci_bus *bus;
+	struct pci_dev *virtfn;
+	struct resource *res;
+	int rc, i;
+	u64 size;
+
+	bus = virtfn_add_bus(dev->bus, pci_iov_virtfn_bus(dev, id));
+	if (!bus) {
+		rc = -ENOMEM;
+		goto failed;
+	}
+
+	virtfn = pci_iov_scan_device(dev, id, bus);
+	if (IS_ERR(virtfn)) {
+		rc = PTR_ERR(virtfn);
+		goto failed0;
+	}
 
 	virtfn->dev.parent = dev->dev.parent;
 	virtfn->multifunction = 0;
@@ -952,7 +972,7 @@ void pci_iov_remove(struct pci_dev *dev)
 void pci_iov_update_resource(struct pci_dev *dev, int resno)
 {
 	struct pci_sriov *iov = dev->is_physfn ? dev->sriov : NULL;
-	struct resource *res = dev->resource + resno;
+	struct resource *res = pci_resource_n(dev, resno);
 	int vf_bar = resno - PCI_IOV_RESOURCES;
 	struct pci_bus_region region;
 	u16 cmd;

drivers/pci/pci-sysfs.c

@@ -1257,6 +1257,10 @@ static int pci_create_resource_files(struct pci_dev *pdev)
 	int i;
 	int retval;
 
+	/* Skip devices with non-mappable BARs */
+	if (pdev->non_mappable_bars)
+		return 0;
+
 	/* Expose the PCI resources from this device as files */
 	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
 
@@ -1556,7 +1560,7 @@ static ssize_t __resource_resize_store(struct device *dev, int n,
 		return -EINVAL;
 
 	device_lock(dev);
-	if (dev->driver) {
+	if (dev->driver || pci_num_vf(pdev)) {
 		ret = -EBUSY;
 		goto unlock;
 	}
@@ -1578,7 +1582,7 @@ static ssize_t __resource_resize_store(struct device *dev, int n,
 
 	pci_remove_resource_files(pdev);
 
-	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
+	for (i = 0; i < PCI_BRIDGE_RESOURCES; i++) {
 		if (pci_resource_len(pdev, i) &&
 		    pci_resource_flags(pdev, i) == flags)
 			pci_release_resource(pdev, i);

drivers/pci/pci.c

@@ -1892,7 +1892,7 @@ static void pci_restore_rebar_state(struct pci_dev *pdev)
 
 		pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl);
 		bar_idx = ctrl & PCI_REBAR_CTRL_BAR_IDX;
-		res = pdev->resource + bar_idx;
+		res = pci_resource_n(pdev, bar_idx);
 		size = pci_rebar_bytes_to_size(resource_size(res));
 		ctrl &= ~PCI_REBAR_CTRL_BAR_SIZE;
 		ctrl |= FIELD_PREP(PCI_REBAR_CTRL_BAR_SIZE, size);
@@ -3770,7 +3770,7 @@ static int pci_rebar_find_pos(struct pci_dev *pdev, int bar)
  * @bar: BAR to query
  *
  * Get the possible sizes of a resizable BAR as bitmask defined in the spec
- * (bit 0=1MB, bit 19=512GB). Returns 0 if BAR isn't resizable.
+ * (bit 0=1MB, bit 31=128TB). Returns 0 if BAR isn't resizable.
  */
 u32 pci_rebar_get_possible_sizes(struct pci_dev *pdev, int bar)
 {
@@ -3818,7 +3818,7 @@ int pci_rebar_get_current_size(struct pci_dev *pdev, int bar)
  * pci_rebar_set_size - set a new size for a BAR
  * @pdev: PCI device
  * @bar: BAR to set size to
- * @size: new size as defined in the spec (0=1MB, 19=512GB)
+ * @size: new size as defined in the spec (0=1MB, 31=128TB)
  *
  * Set the new size of a BAR as defined in the spec.
  * Returns zero if resizing was successful, error code otherwise.

drivers/pci/pci.h

@@ -283,6 +283,8 @@ extern unsigned long pci_hotplug_io_size;
 extern unsigned long pci_hotplug_mmio_size;
 extern unsigned long pci_hotplug_mmio_pref_size;
 extern unsigned long pci_hotplug_bus_size;
+extern unsigned long pci_cardbus_io_size;
+extern unsigned long pci_cardbus_mem_size;
 
 /**
  * pci_match_one_device - Tell if a PCI device structure has a matching
@@ -326,6 +328,10 @@ enum pci_bar_type {
 struct device *pci_get_host_bridge_device(struct pci_dev *dev);
 void pci_put_host_bridge_device(struct device *dev);
 
+unsigned int pci_rescan_bus_bridge_resize(struct pci_dev *bridge);
+int pci_reassign_bridge_resources(struct pci_dev *bridge, unsigned long type);
+int __must_check pci_reassign_resource(struct pci_dev *dev, int i, resource_size_t add_size, resource_size_t align);
+
 int pci_configure_extended_tags(struct pci_dev *dev, void *ign);
 bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *pl,
 				int rrs_timeout);
@@ -350,6 +356,29 @@ void pci_walk_bus_locked(struct pci_bus *top,
 			 void *userdata);
 
 const char *pci_resource_name(struct pci_dev *dev, unsigned int i);
+bool pci_resource_is_optional(const struct pci_dev *dev, int resno);
+
+/**
+ * pci_resource_num - Reverse lookup resource number from device resources
+ * @dev: PCI device
+ * @res: Resource to lookup index for (MUST be a @dev's resource)
+ *
+ * Perform reverse lookup to determine the resource number for @res within
+ * @dev resource array. NOTE: The caller is responsible for ensuring @res is
+ * among @dev's resources!
+ *
+ * Returns: resource number.
+ */
+static inline int pci_resource_num(const struct pci_dev *dev,
+				   const struct resource *res)
+{
+	int resno = res - &dev->resource[0];
+
+	/* Passing a resource that is not among dev's resources? */
+	WARN_ON_ONCE(resno >= PCI_NUM_RESOURCES);
+
+	return resno;
+}
 
 void pci_reassigndev_resource_alignment(struct pci_dev *dev);
 void pci_disable_bridge_window(struct pci_dev *dev);
@@ -659,6 +688,10 @@ void pci_iov_update_resource(struct pci_dev *dev, int resno);
 resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev, int resno);
 void pci_restore_iov_state(struct pci_dev *dev);
 int pci_iov_bus_range(struct pci_bus *bus);
+static inline bool pci_resource_is_iov(int resno)
+{
+	return resno >= PCI_IOV_RESOURCES && resno <= PCI_IOV_RESOURCE_END;
+}
 extern const struct attribute_group sriov_pf_dev_attr_group;
 extern const struct attribute_group sriov_vf_dev_attr_group;
 #else
@@ -668,12 +701,21 @@ static inline int pci_iov_init(struct pci_dev *dev)
 }
 static inline void pci_iov_release(struct pci_dev *dev) { }
 static inline void pci_iov_remove(struct pci_dev *dev) { }
+static inline void pci_iov_update_resource(struct pci_dev *dev, int resno) { }
+static inline resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev,
+							   int resno)
+{
+	return 0;
+}
 static inline void pci_restore_iov_state(struct pci_dev *dev) { }
 static inline int pci_iov_bus_range(struct pci_bus *bus)
 {
 	return 0;
 }
-
+static inline bool pci_resource_is_iov(int resno)
+{
+	return false;
+}
 #endif /* CONFIG_PCI_IOV */
 
 #ifdef CONFIG_PCIE_TPH
@@ -707,12 +749,10 @@ unsigned long pci_cardbus_resource_alignment(struct resource *);
 static inline resource_size_t pci_resource_alignment(struct pci_dev *dev,
 						     struct resource *res)
 {
-#ifdef CONFIG_PCI_IOV
-	int resno = res - dev->resource;
+	int resno = pci_resource_num(dev, res);
 
-	if (resno >= PCI_IOV_RESOURCES && resno <= PCI_IOV_RESOURCE_END)
+	if (pci_resource_is_iov(resno))
 		return pci_sriov_resource_alignment(dev, resno);
-#endif
 	if (dev->class >> 8 == PCI_CLASS_BRIDGE_CARDBUS)
 		return pci_cardbus_resource_alignment(res);
 	return resource_alignment(res);

drivers/pci/proc.c

@@ -251,6 +251,10 @@ static int proc_bus_pci_mmap(struct file *file, struct vm_area_struct *vma)
 	    security_locked_down(LOCKDOWN_PCI_ACCESS))
 		return -EPERM;
 
+	/* Skip devices with non-mappable BARs */
+	if (dev->non_mappable_bars)
+		return -EINVAL;
+
 	if (fpriv->mmap_state == pci_mmap_io) {
 		if (!arch_can_pci_mmap_io())
 			return -EINVAL;