PCI/sysfs: Convert PCI resource files to static attributes

Currently, the PCI resource files (resourceN, resourceN_wc) are dynamically
created by pci_create_sysfs_dev_files(), called from both
pci_bus_add_device() and the pci_sysfs_init() late_initcall, with only a
sysfs_initialized flag for synchronisation.  This has caused warnings and
boot panics when both paths race on the same device, e.g.:

  sysfs: cannot create duplicate filename '/devices/pci0000:3c/0000:3c:01.0/0000:3e:00.2/resource2'

This is especially likely on Devicetree-based platforms, where the PCI host
controllers are platform drivers that probe via the driver model, which can
happen during or after the late_initcall.  As such, pci_bus_add_device()
and pci_sysfs_init() are more likely to overlap.

Convert to static const attributes with three attribute groups (I/O, UC,
WC), each with an .is_bin_visible() callback that checks resource flags,
BAR length, and non_mappable_bars.  A .bin_size() callback provides
pci_resource_len() to the kernfs node for correct stat and lseek behaviour.

As part of this conversion:

  - Rename pci_read_resource_io() and pci_write_resource_io() to
    pci_read_resource() and pci_write_resource() since the callbacks are no
    longer I/O-specific in the static attribute context.

  - Update __resource_resize_store() to use sysfs_create_groups() and
    sysfs_remove_groups(), which re-evaluates visibility and runs the
    .bin_size() callback for the static resource attribute groups.

  - Remove pci_create_resource_files(), pci_remove_resource_files(), and
    pci_create_attr() which are no longer needed.

  - Move the __weak stubs outside the #if guard so they remain available
    for callers converted in subsequent commits.

Platforms that do not define the HAVE_PCI_MMAP macro or the
ARCH_GENERIC_PCI_MMAP_RESOURCE macro, such as Alpha architecture,
continue using their platform-specific resource file creation.

For reference, the dynamic creation dates back to the pre-Git era:

  https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git/commit/drivers/pci/pci-sysfs.c?id=42298be0eeb5ae98453b3374c36161b05a46c5dc

The write-combine support was added in commit 45aec1ae72fc ("x86: PAT
export resource_wc in pci sysfs").

Many other reports mentioned in the cover letter (first Link: below).

Link: https://lore.kernel.org/r/20260508043543.217179-1-kwilczynski@kernel.org/
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=215515
Closes: https://github.com/openwrt/openwrt/issues/17143
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Link: https://patch.msgid.link/20260508043543.217179-8-kwilczynski@kernel.org

2 files changed, 143 insertions, 126 deletions

diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index a74eca96918b..3bb808e0e80a 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -890,19 +890,6 @@ pci_llseek_resource_legacy(struct file *filep,
 	return fixed_size_llseek(filep, offset, whence, attr->size);
 }
 
-static __maybe_unused loff_t
-pci_llseek_resource(struct file *filep,
-		    struct kobject *kobj,
-		    const struct bin_attribute *attr,
-		    loff_t offset, int whence)
-{
-	struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj));
-	int bar = (unsigned long)attr->private;
-
-	return fixed_size_llseek(filep, offset, whence,
-				 pci_resource_len(pdev, bar));
-}
-
 #ifdef HAVE_PCI_LEGACY
 /**
  * pci_read_legacy_io - read byte(s) from legacy I/O port space
@@ -1177,14 +1164,14 @@ static ssize_t pci_resource_io(struct file *filp, struct kobject *kobj,
 #endif
 }
 
-static ssize_t pci_read_resource_io(struct file *filp, struct kobject *kobj,
+static ssize_t pci_read_resource(struct file *filp, struct kobject *kobj,
 				    const struct bin_attribute *attr, char *buf,
 				    loff_t off, size_t count)
 {
 	return pci_resource_io(filp, kobj, attr, buf, off, count, false);
 }
 
-static ssize_t pci_write_resource_io(struct file *filp, struct kobject *kobj,
+static ssize_t pci_write_resource(struct file *filp, struct kobject *kobj,
 				     const struct bin_attribute *attr, char *buf,
 				     loff_t off, size_t count)
 {
@@ -1197,6 +1184,18 @@ static ssize_t pci_write_resource_io(struct file *filp, struct kobject *kobj,
 	return pci_resource_io(filp, kobj, attr, buf, off, count, true);
 }
 
+static loff_t pci_llseek_resource(struct file *filep,
+				  struct kobject *kobj,
+				  const struct bin_attribute *attr,
+				  loff_t offset, int whence)
+{
+	struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj));
+	int bar = (unsigned long)attr->private;
+
+	return fixed_size_llseek(filep, offset, whence,
+				 pci_resource_len(pdev, bar));
+}
+
 /*
  * generic_file_llseek() consults f_mapping->host to determine
  * the file size. As iomem_inode knows nothing about the
@@ -1215,8 +1214,8 @@ static ssize_t pci_write_resource_io(struct file *filp, struct kobject *kobj,
 static const struct bin_attribute dev_resource##_bar##_io_attr = {	\
 	.attr = { .name = "resource" __stringify(_bar), .mode = 0600 },	\
 	.private = (void *)(unsigned long)(_bar),			\
-	.read = pci_read_resource_io,					\
-	.write = pci_write_resource_io,					\
+	.read = pci_read_resource,					\
+	.write = pci_write_resource,					\
 	__PCI_RESOURCE_IO_MMAP_ATTRS					\
 }
 
@@ -1238,129 +1237,144 @@ static const struct bin_attribute dev_resource##_bar##_wc_attr = {	      \
 	.mmap = pci_mmap_resource_wc,					      \
 }
 
-/**
- * pci_remove_resource_files - cleanup resource files
- * @pdev: dev to cleanup
- *
- * If we created resource files for @pdev, remove them from sysfs and
- * free their resources.
- */
-static void pci_remove_resource_files(struct pci_dev *pdev)
+static inline umode_t
+__pci_resource_attr_is_visible(struct kobject *kobj,
+			       const struct bin_attribute *a,
+			       int bar, bool write_combine,
+			       unsigned long flags)
 {
-	int i;
+	struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj));
 
-	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
-		struct bin_attribute *res_attr;
+	if (pdev->non_mappable_bars)
+		return 0;
 
-		res_attr = pdev->res_attr[i];
-		if (res_attr) {
-			sysfs_remove_bin_file(&pdev->dev.kobj, res_attr);
-			kfree(res_attr);
-		}
+	if (!pci_resource_len(pdev, bar))
+		return 0;
 
-		res_attr = pdev->res_attr_wc[i];
-		if (res_attr) {
-			sysfs_remove_bin_file(&pdev->dev.kobj, res_attr);
-			kfree(res_attr);
-		}
-	}
+	if ((pci_resource_flags(pdev, bar) & flags) != flags)
+		return 0;
+
+	if (write_combine && !arch_can_pci_mmap_wc())
+		return 0;
+
+	return a->attr.mode;
 }
 
-static int pci_create_attr(struct pci_dev *pdev, int num, int write_combine)
+static umode_t pci_dev_resource_io_is_visible(struct kobject *kobj,
+					      const struct bin_attribute *a,
+					      int n)
 {
-	/* allocate attribute structure, piggyback attribute name */
-	int name_len = write_combine ? 13 : 10;
-	struct bin_attribute *res_attr;
-	char *res_attr_name;
-	int retval;
+	return __pci_resource_attr_is_visible(kobj, a, n, false,
+					      IORESOURCE_IO);
+}
 
-	res_attr = kzalloc(sizeof(*res_attr) + name_len, GFP_ATOMIC);
-	if (!res_attr)
-		return -ENOMEM;
+static umode_t pci_dev_resource_uc_is_visible(struct kobject *kobj,
+					      const struct bin_attribute *a,
+					      int n)
+{
+	return __pci_resource_attr_is_visible(kobj, a, n, false,
+					      IORESOURCE_MEM);
+}
 
-	res_attr_name = (char *)(res_attr + 1);
+static umode_t pci_dev_resource_wc_is_visible(struct kobject *kobj,
+					      const struct bin_attribute *a,
+					      int n)
+{
+	return __pci_resource_attr_is_visible(kobj, a, n, true,
+					      IORESOURCE_MEM | IORESOURCE_PREFETCH);
+}
 
-	sysfs_bin_attr_init(res_attr);
-	if (write_combine) {
-		sprintf(res_attr_name, "resource%d_wc", num);
-		res_attr->mmap = pci_mmap_resource_wc;
-	} else {
-		sprintf(res_attr_name, "resource%d", num);
-		if (pci_resource_flags(pdev, num) & IORESOURCE_IO) {
-			res_attr->read = pci_read_resource_io;
-			res_attr->write = pci_write_resource_io;
-			if (arch_can_pci_mmap_io())
-				res_attr->mmap = pci_mmap_resource_uc;
-		} else {
-			res_attr->mmap = pci_mmap_resource_uc;
-		}
-	}
-	if (res_attr->mmap) {
-		res_attr->f_mapping = iomem_get_mapping;
-		/*
-		 * generic_file_llseek() consults f_mapping->host to determine
-		 * the file size. As iomem_inode knows nothing about the
-		 * attribute, it's not going to work, so override it as well.
-		 */
-		res_attr->llseek = pci_llseek_resource;
-	}
-	res_attr->attr.name = res_attr_name;
-	res_attr->attr.mode = 0600;
-	res_attr->size = pci_resource_len(pdev, num);
-	res_attr->private = (void *)(unsigned long)num;
-	retval = sysfs_create_bin_file(&pdev->dev.kobj, res_attr);
-	if (retval) {
-		kfree(res_attr);
-		return retval;
-	}
+static size_t pci_dev_resource_bin_size(struct kobject *kobj,
+					const struct bin_attribute *a,
+					int n)
+{
+	struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj));
 
-	if (write_combine)
-		pdev->res_attr_wc[num] = res_attr;
-	else
-		pdev->res_attr[num] = res_attr;
+	return pci_resource_len(pdev, n);
+}
+
+pci_dev_resource_io_attr(0);
+pci_dev_resource_io_attr(1);
+pci_dev_resource_io_attr(2);
+pci_dev_resource_io_attr(3);
+pci_dev_resource_io_attr(4);
+pci_dev_resource_io_attr(5);
+
+pci_dev_resource_uc_attr(0);
+pci_dev_resource_uc_attr(1);
+pci_dev_resource_uc_attr(2);
+pci_dev_resource_uc_attr(3);
+pci_dev_resource_uc_attr(4);
+pci_dev_resource_uc_attr(5);
+
+pci_dev_resource_wc_attr(0);
+pci_dev_resource_wc_attr(1);
+pci_dev_resource_wc_attr(2);
+pci_dev_resource_wc_attr(3);
+pci_dev_resource_wc_attr(4);
+pci_dev_resource_wc_attr(5);
+
+static const struct bin_attribute *const pci_dev_resource_io_attrs[] = {
+	&dev_resource0_io_attr,
+	&dev_resource1_io_attr,
+	&dev_resource2_io_attr,
+	&dev_resource3_io_attr,
+	&dev_resource4_io_attr,
+	&dev_resource5_io_attr,
+	NULL,
+};
 
-	return 0;
-}
+static const struct bin_attribute *const pci_dev_resource_uc_attrs[] = {
+	&dev_resource0_uc_attr,
+	&dev_resource1_uc_attr,
+	&dev_resource2_uc_attr,
+	&dev_resource3_uc_attr,
+	&dev_resource4_uc_attr,
+	&dev_resource5_uc_attr,
+	NULL,
+};
 
-/**
- * pci_create_resource_files - create resource files in sysfs for @dev
- * @pdev: dev in question
- *
- * Walk the resources in @pdev creating files for each resource available.
- */
-static int pci_create_resource_files(struct pci_dev *pdev)
-{
-	int i;
-	int retval;
+static const struct bin_attribute *const pci_dev_resource_wc_attrs[] = {
+	&dev_resource0_wc_attr,
+	&dev_resource1_wc_attr,
+	&dev_resource2_wc_attr,
+	&dev_resource3_wc_attr,
+	&dev_resource4_wc_attr,
+	&dev_resource5_wc_attr,
+	NULL,
+};
 
-	/* Skip devices with non-mappable BARs */
-	if (pdev->non_mappable_bars)
-		return 0;
+static const struct attribute_group pci_dev_resource_io_attr_group = {
+	.bin_attrs = pci_dev_resource_io_attrs,
+	.is_bin_visible = pci_dev_resource_io_is_visible,
+	.bin_size = pci_dev_resource_bin_size,
+};
 
-	/* Expose the PCI resources from this device as files */
-	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
+static const struct attribute_group pci_dev_resource_uc_attr_group = {
+	.bin_attrs = pci_dev_resource_uc_attrs,
+	.is_bin_visible = pci_dev_resource_uc_is_visible,
+	.bin_size = pci_dev_resource_bin_size,
+};
 
-		/* skip empty resources */
-		if (!pci_resource_len(pdev, i))
-			continue;
+static const struct attribute_group pci_dev_resource_wc_attr_group = {
+	.bin_attrs = pci_dev_resource_wc_attrs,
+	.is_bin_visible = pci_dev_resource_wc_is_visible,
+	.bin_size = pci_dev_resource_bin_size,
+};
 
-		retval = pci_create_attr(pdev, i, 0);
-		/* for prefetchable resources, create a WC mappable file */
-		if (!retval && arch_can_pci_mmap_wc() &&
-		    pci_resource_flags(pdev, i) & IORESOURCE_PREFETCH)
-			retval = pci_create_attr(pdev, i, 1);
-		if (retval) {
-			pci_remove_resource_files(pdev);
-			return retval;
-		}
-	}
-	return 0;
-}
-#else /* !(defined(HAVE_PCI_MMAP) || defined(ARCH_GENERIC_PCI_MMAP_RESOURCE)) */
-int __weak pci_create_resource_files(struct pci_dev *dev) { return 0; }
-void __weak pci_remove_resource_files(struct pci_dev *dev) { return; }
+static const struct attribute_group *pci_dev_resource_attr_groups[] = {
+	&pci_dev_resource_io_attr_group,
+	&pci_dev_resource_uc_attr_group,
+	&pci_dev_resource_wc_attr_group,
+	NULL,
+};
+#else
+#define pci_dev_resource_attr_groups NULL
 #endif
 
+int __weak pci_create_resource_files(struct pci_dev *dev) { return 0; }
+void __weak pci_remove_resource_files(struct pci_dev *dev) { }
+
 /**
  * pci_write_rom - used to enable access to the PCI ROM display
  * @filp: sysfs file
@@ -1662,14 +1676,14 @@ static ssize_t __resource_resize_store(struct device *dev, int n,
 	pci_write_config_word(pdev, PCI_COMMAND,
 			      cmd & ~PCI_COMMAND_MEMORY);
 
-	pci_remove_resource_files(pdev);
+	sysfs_remove_groups(&pdev->dev.kobj, pci_dev_resource_attr_groups);
 
 	ret = pci_resize_resource(pdev, n, size, 0);
 
 	pci_assign_unassigned_bus_resources(bus);
 
-	if (pci_create_resource_files(pdev))
-		pci_warn(pdev, "Failed to recreate resource files after BAR resizing\n");
+	if (sysfs_create_groups(&pdev->dev.kobj, pci_dev_resource_attr_groups))
+		pci_warn(pdev, "Failed to recreate resource groups after BAR resizing\n");
 
 	pci_write_config_word(pdev, PCI_COMMAND, cmd);
 pm_put:
@@ -1838,6 +1852,11 @@ static const struct attribute_group pci_dev_group = {
 
 const struct attribute_group *pci_dev_groups[] = {
 	&pci_dev_group,
+#if defined(HAVE_PCI_MMAP) || defined(ARCH_GENERIC_PCI_MMAP_RESOURCE)
+	&pci_dev_resource_io_attr_group,
+	&pci_dev_resource_uc_attr_group,
+	&pci_dev_resource_wc_attr_group,
+#endif
 	&pci_dev_config_attr_group,
 	&pci_dev_rom_attr_group,
 	&pci_dev_reset_attr_group,
diff --git a/include/linux/pci.h b/include/linux/pci.h
index e93fbe6b57fe..974605c9fce2 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -2531,10 +2531,8 @@ int pcibios_alloc_irq(struct pci_dev *dev);
 void pcibios_free_irq(struct pci_dev *dev);
 resource_size_t pcibios_default_alignment(void);
 
-#if !defined(HAVE_PCI_MMAP) && !defined(ARCH_GENERIC_PCI_MMAP_RESOURCE)
 extern int pci_create_resource_files(struct pci_dev *dev);
 extern void pci_remove_resource_files(struct pci_dev *dev);
-#endif
 
 #if defined(CONFIG_PCI_MMCONFIG) || defined(CONFIG_ACPI_MCFG)
 void __init pci_mmcfg_early_init(void);